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.1697545916.rhmmedcatt-proliant-ml350-gen10 b/.summary/0/events.out.tfevents.1697545916.rhmmedcatt-proliant-ml350-gen10 new file mode 100644 index 0000000000000000000000000000000000000000..906c1083aa6f4bfcbb52a36b03f260c306f1e45e --- /dev/null +++ b/.summary/0/events.out.tfevents.1697545916.rhmmedcatt-proliant-ml350-gen10 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:739332f8a54de12ecb2e276ef86376e1952fa149ab37d8b9e0b5de4780f0840f +size 1180 diff --git a/.summary/0/events.out.tfevents.1697643349.rhmmedcatt-proliant-ml350-gen10 b/.summary/0/events.out.tfevents.1697643349.rhmmedcatt-proliant-ml350-gen10 new file mode 100644 index 0000000000000000000000000000000000000000..05bb029a706ebe65f8ec1ca23ef3a68a95faf304 --- /dev/null +++ b/.summary/0/events.out.tfevents.1697643349.rhmmedcatt-proliant-ml350-gen10 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:636017b4237c16c0d1a347ad47d74ade18c16b5b3c2a2cf68ce00e7ec4ca0357 +size 40 diff --git a/.summary/0/events.out.tfevents.1697718879.rhmmedcatt-proliant-ml350-gen10 b/.summary/0/events.out.tfevents.1697718879.rhmmedcatt-proliant-ml350-gen10 new file mode 100644 index 0000000000000000000000000000000000000000..c9526561e4b438674929fda0254f1818710c0a6c --- /dev/null +++ b/.summary/0/events.out.tfevents.1697718879.rhmmedcatt-proliant-ml350-gen10 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36d664e354cc66e8b10eb1172ff5e5531c36bc4bf108be3085507b8ab41ee888 +size 2354845 diff --git a/.summary/0/events.out.tfevents.1697722839.rhmmedcatt-proliant-ml350-gen10 b/.summary/0/events.out.tfevents.1697722839.rhmmedcatt-proliant-ml350-gen10 new file mode 100644 index 0000000000000000000000000000000000000000..79a7c066fd96ed3972361fe0244fac2c9520d82d --- /dev/null +++ b/.summary/0/events.out.tfevents.1697722839.rhmmedcatt-proliant-ml350-gen10 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ad65f968afb1f5c29929ceeeea4896e1bc156f28587b3110dc0736a43d0199b +size 821 diff --git a/.summary/0/events.out.tfevents.1697722878.rhmmedcatt-proliant-ml350-gen10 b/.summary/0/events.out.tfevents.1697722878.rhmmedcatt-proliant-ml350-gen10 new file mode 100644 index 0000000000000000000000000000000000000000..61798e1ece132be13ab2da2ec03f995305766e28 --- /dev/null +++ b/.summary/0/events.out.tfevents.1697722878.rhmmedcatt-proliant-ml350-gen10 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e257b37ac11c574f1f4c3788e68433cce06bfef113236255e9f24c2639b89005 +size 57595 diff --git a/.summary/0/events.out.tfevents.1697723034.rhmmedcatt-proliant-ml350-gen10 b/.summary/0/events.out.tfevents.1697723034.rhmmedcatt-proliant-ml350-gen10 new file mode 100644 index 0000000000000000000000000000000000000000..8353a22ba701a3576851919339a2e703f1764827 --- /dev/null +++ b/.summary/0/events.out.tfevents.1697723034.rhmmedcatt-proliant-ml350-gen10 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06d64b42be4da7b75c6842204a3e4ea84815b61fd2e50045465431f422b38432 +size 59732 diff --git a/.summary/0/events.out.tfevents.1697723216.rhmmedcatt-proliant-ml350-gen10 b/.summary/0/events.out.tfevents.1697723216.rhmmedcatt-proliant-ml350-gen10 new file mode 100644 index 0000000000000000000000000000000000000000..c561fc5afe8d60fc202835e7ba5f0ae1cc526482 --- /dev/null +++ b/.summary/0/events.out.tfevents.1697723216.rhmmedcatt-proliant-ml350-gen10 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b6992e0b102159c3c4c7a3acfedc613aa51353f1c8753eb7722c6a4d9395bc2 +size 23983628 diff --git a/.summary/0/events.out.tfevents.1697818119.rhmmedcatt-proliant-ml350-gen10 b/.summary/0/events.out.tfevents.1697818119.rhmmedcatt-proliant-ml350-gen10 new file mode 100644 index 0000000000000000000000000000000000000000..ef6c7eabcebca81c0f9ada465debd359386f9558 --- /dev/null +++ b/.summary/0/events.out.tfevents.1697818119.rhmmedcatt-proliant-ml350-gen10 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c42911dac6f3ce48409841fb3d5c20bb47afca0c85ce804b816975f77269eb5c +size 64005360 diff --git a/.summary/1/events.out.tfevents.1697545916.rhmmedcatt-proliant-ml350-gen10 b/.summary/1/events.out.tfevents.1697545916.rhmmedcatt-proliant-ml350-gen10 new file mode 100644 index 0000000000000000000000000000000000000000..28598f72ad9b232f17b4c3b386fdef4cfecb6dda --- /dev/null +++ b/.summary/1/events.out.tfevents.1697545916.rhmmedcatt-proliant-ml350-gen10 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b2ad207cb360eaf7826168045af6dc425777916b664b51d5b545c038965142c +size 217 diff --git a/.summary/1/events.out.tfevents.1697643349.rhmmedcatt-proliant-ml350-gen10 b/.summary/1/events.out.tfevents.1697643349.rhmmedcatt-proliant-ml350-gen10 new file mode 100644 index 0000000000000000000000000000000000000000..376136e84737953becf260e82144d98277a4c245 --- /dev/null +++ b/.summary/1/events.out.tfevents.1697643349.rhmmedcatt-proliant-ml350-gen10 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4976d78a9aa31688c74db67d11d5ad265bc606dcd8159430cadcdfc9068ad9e0 +size 40 diff --git a/.summary/1/events.out.tfevents.1697718879.rhmmedcatt-proliant-ml350-gen10 b/.summary/1/events.out.tfevents.1697718879.rhmmedcatt-proliant-ml350-gen10 new file mode 100644 index 0000000000000000000000000000000000000000..58fafde839872e95b667ecc7327dc1939d5c22c9 --- /dev/null +++ b/.summary/1/events.out.tfevents.1697718879.rhmmedcatt-proliant-ml350-gen10 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24750301f35e252440f1cadc9c872bac4226423c16e6fceaf8e549923b47729a +size 1465144 diff --git a/.summary/1/events.out.tfevents.1697722839.rhmmedcatt-proliant-ml350-gen10 b/.summary/1/events.out.tfevents.1697722839.rhmmedcatt-proliant-ml350-gen10 new file mode 100644 index 0000000000000000000000000000000000000000..7ce4e689545dc74b590d1e47250090f701953d4e --- /dev/null +++ b/.summary/1/events.out.tfevents.1697722839.rhmmedcatt-proliant-ml350-gen10 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d3222213af83de428f659cc17b506d7034d33b3ffc7a57f6e436390c890845e +size 168 diff --git a/.summary/1/events.out.tfevents.1697722878.rhmmedcatt-proliant-ml350-gen10 b/.summary/1/events.out.tfevents.1697722878.rhmmedcatt-proliant-ml350-gen10 new file mode 100644 index 0000000000000000000000000000000000000000..01c1da75e26aac7a81af2b78712d44e36b45d83c --- /dev/null +++ b/.summary/1/events.out.tfevents.1697722878.rhmmedcatt-proliant-ml350-gen10 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59ad5f0621689fef8e7526874e2122491c011127875081791846737760166328 +size 29356 diff --git a/.summary/1/events.out.tfevents.1697723034.rhmmedcatt-proliant-ml350-gen10 b/.summary/1/events.out.tfevents.1697723034.rhmmedcatt-proliant-ml350-gen10 new file mode 100644 index 0000000000000000000000000000000000000000..2856ae0346cf4ea0b8e2e6e8ceb50ae2c967ae88 --- /dev/null +++ b/.summary/1/events.out.tfevents.1697723034.rhmmedcatt-proliant-ml350-gen10 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5021592fde71c867f360c19a50a630fd67697a8dd245ef599d9e0ca2471de90 +size 31060 diff --git a/.summary/1/events.out.tfevents.1697723216.rhmmedcatt-proliant-ml350-gen10 b/.summary/1/events.out.tfevents.1697723216.rhmmedcatt-proliant-ml350-gen10 new file mode 100644 index 0000000000000000000000000000000000000000..60be09c44dfc0f4d6d305cbc5e3422b246b4d733 --- /dev/null +++ b/.summary/1/events.out.tfevents.1697723216.rhmmedcatt-proliant-ml350-gen10 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9213ad22a2bc89ae760d4ba4892aad067e38bb6a338a65a0b01956709ad9e64b +size 12713449 diff --git a/.summary/1/events.out.tfevents.1697818119.rhmmedcatt-proliant-ml350-gen10 b/.summary/1/events.out.tfevents.1697818119.rhmmedcatt-proliant-ml350-gen10 new file mode 100644 index 0000000000000000000000000000000000000000..a0ce776692e769238d896006ae6774290794f13d --- /dev/null +++ b/.summary/1/events.out.tfevents.1697818119.rhmmedcatt-proliant-ml350-gen10 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6deb015ecf4a11dd917ed62d4ec789bf07aab9e41f120118c24ac6363de50a90 +size 33280131 diff --git a/README.md b/README.md index 61a503576101ac722fec064d0f4776f71cf035c8..3350c31e9da065eb9d029b97b8969c5db389cf58 100644 --- a/README.md +++ b/README.md @@ -15,35 +15,39 @@ model-index: type: atari_battlezone metrics: - type: mean_reward - value: 78900.00 +/- 30044.80 + value: 234600.00 +/- 114609.95 name: mean_reward verified: false --- -A(n) **APPO** model trained on the **atari_battlezone** 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_battlezone -``` +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_battlezone** 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_battlezone +``` + + ## Using the model To run the model after download, use the `enjoy` script corresponding to this environment: diff --git a/checkpoint_p0/best_000562880_144097280_reward_21.206.pth b/checkpoint_p0/best_000562880_144097280_reward_21.206.pth new file mode 100644 index 0000000000000000000000000000000000000000..5d1d093e8dbb0ce78ad6a5be585f754b513a71d6 --- /dev/null +++ b/checkpoint_p0/best_000562880_144097280_reward_21.206.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3413858d52aafdeb098940a4603cb7ef85970dcc10dc7b1833714fe37d131b5d +size 20795955 diff --git a/checkpoint_p0/checkpoint_001967872_503775232.pth b/checkpoint_p0/checkpoint_001967872_503775232.pth new file mode 100644 index 0000000000000000000000000000000000000000..e3af36d273c7749373dd33bd7b8db8776122e7ac --- /dev/null +++ b/checkpoint_p0/checkpoint_001967872_503775232.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1bb5605711bdc509eb7099e383293e541311745cdc3c4707cd60633c5d3e078 +size 20796291 diff --git a/checkpoint_p0/checkpoint_001968768_504004608.pth b/checkpoint_p0/checkpoint_001968768_504004608.pth new file mode 100644 index 0000000000000000000000000000000000000000..5d4519e58197b6a7bc7f5f1224a73815152a14e1 --- /dev/null +++ b/checkpoint_p0/checkpoint_001968768_504004608.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3425c5951f2dab69b07de50dcd6ae56ac21d2f1b736d2af555e8583a45decb8e +size 20796291 diff --git a/checkpoint_p0/milestones/checkpoint_000012640_3235840.pth b/checkpoint_p0/milestones/checkpoint_000012640_3235840.pth new file mode 100644 index 0000000000000000000000000000000000000000..56d543ed697b00ce3a1312a3c1fef33be873df72 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000012640_3235840.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30c50fdb5eea3c638f0f923f2ca48b2ecfb1688a343da52b7639ec2b54464508 +size 20797083 diff --git a/checkpoint_p0/milestones/checkpoint_000025344_6488064.pth b/checkpoint_p0/milestones/checkpoint_000025344_6488064.pth new file mode 100644 index 0000000000000000000000000000000000000000..81f7ccb4ba6ac4bb4078489328c08696aa2df972 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000025344_6488064.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d99cbf30c03fcab539e21b8085680be6724768a49fea02a56cab50f55a3c398c +size 20797083 diff --git a/checkpoint_p0/milestones/checkpoint_000038016_9732096.pth b/checkpoint_p0/milestones/checkpoint_000038016_9732096.pth new file mode 100644 index 0000000000000000000000000000000000000000..e2ebb5fc1745a84447bbee69158fb2b6eaa66b89 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000038016_9732096.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bc35a8390caae151a2d8a48fc342343465c3173a89b6f0c8bec5298997382a8 +size 20797083 diff --git a/checkpoint_p0/milestones/checkpoint_000057280_14663680.pth b/checkpoint_p0/milestones/checkpoint_000057280_14663680.pth new file mode 100644 index 0000000000000000000000000000000000000000..2f0384010cc98093a7df4b05ad2815354f211e8c --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000057280_14663680.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5925c73cadca62e21067418b7d0e3dff93d518e1b77b0edb87015a93965cdddd +size 20797139 diff --git a/checkpoint_p0/milestones/checkpoint_000069984_17915904.pth b/checkpoint_p0/milestones/checkpoint_000069984_17915904.pth new file mode 100644 index 0000000000000000000000000000000000000000..064fcf6bfc59b04de8809ff192ec4aaf5a3c8784 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000069984_17915904.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c4f3322b2ecd925e6da9a8d367611d8125dd3deb445772e0fa272af517ebe97 +size 20797139 diff --git a/checkpoint_p0/milestones/checkpoint_000082688_21168128.pth b/checkpoint_p0/milestones/checkpoint_000082688_21168128.pth new file mode 100644 index 0000000000000000000000000000000000000000..786a9277dce293af6f871830d7267017e0692233 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000082688_21168128.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:056ca4b261652dd0e0cf4844db187240ee9e151fbcedba26d220ae546ae2091d +size 20797139 diff --git a/checkpoint_p0/milestones/checkpoint_000095392_24420352.pth b/checkpoint_p0/milestones/checkpoint_000095392_24420352.pth new file mode 100644 index 0000000000000000000000000000000000000000..b3eb111f9345b800ea6d3d12bc5d307ec75a8695 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000095392_24420352.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd93383e052b097bb31f6fd45bcdfe570c88352ee98cb050979a86ff44c9f7c0 +size 20797139 diff --git a/checkpoint_p0/milestones/checkpoint_000108128_27680768.pth b/checkpoint_p0/milestones/checkpoint_000108128_27680768.pth new file mode 100644 index 0000000000000000000000000000000000000000..cfa66004447b8a23d4088ff9f754432ea83139ea --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000108128_27680768.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71f387a5a80ed135b7e6b49d02ac8b1584d41985b5348731d68b093ef2d02d15 +size 20797139 diff --git a/checkpoint_p0/milestones/checkpoint_000120800_30924800.pth b/checkpoint_p0/milestones/checkpoint_000120800_30924800.pth new file mode 100644 index 0000000000000000000000000000000000000000..96ea0a658bb736e97e699a015df9c8b6ba32c945 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000120800_30924800.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b865ca4d020feb0ef0ae8584bda4ab662440a771a2c5e0d016d4ffbc9ce3671 +size 20797139 diff --git a/checkpoint_p0/milestones/checkpoint_000133568_34193408.pth b/checkpoint_p0/milestones/checkpoint_000133568_34193408.pth new file mode 100644 index 0000000000000000000000000000000000000000..a32db5e29782d5722a1caedc25a5b00e99f96067 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000133568_34193408.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa9200bf83bbb10d570f1ffbd6a2de1141062d90a0766d3bd2e0e191fa3273d6 +size 20797139 diff --git a/checkpoint_p0/milestones/checkpoint_000146272_37445632.pth b/checkpoint_p0/milestones/checkpoint_000146272_37445632.pth new file mode 100644 index 0000000000000000000000000000000000000000..7cd6d3bfda6ab6d50e6dcd5f5000beee8360ac02 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000146272_37445632.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9f426069fe1acca44783aba3744e3d237aa2214d35a22c4f71aaca009012fd8 +size 20797139 diff --git a/checkpoint_p0/milestones/checkpoint_000159104_40730624.pth b/checkpoint_p0/milestones/checkpoint_000159104_40730624.pth new file mode 100644 index 0000000000000000000000000000000000000000..daf2d38cf69d5d9a6c1f9aae53390439eb9b5f8c --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000159104_40730624.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b803f24a314c23674a470403c45b8f31dffbb60cd24569e1a8d4e64dc5d357bd +size 20797139 diff --git a/checkpoint_p0/milestones/checkpoint_000171904_44007424.pth b/checkpoint_p0/milestones/checkpoint_000171904_44007424.pth new file mode 100644 index 0000000000000000000000000000000000000000..23633ec1ad757ff5c2afc8bfff8062983ccecbdf --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000171904_44007424.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0962b3dc19ac64c940f81b89a498faeac53adfe0c94a823ffdcb8625fb735aa +size 20797139 diff --git a/checkpoint_p0/milestones/checkpoint_000184768_47300608.pth b/checkpoint_p0/milestones/checkpoint_000184768_47300608.pth new file mode 100644 index 0000000000000000000000000000000000000000..44302c7be8413484e4cbfe6fcf42296acda75ce5 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000184768_47300608.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:016afc0ed8e47bb7ddc04fd2f644ad85ad466652eebe64ec413d7f0c052dc1f4 +size 20797139 diff --git a/checkpoint_p0/milestones/checkpoint_000197472_50552832.pth b/checkpoint_p0/milestones/checkpoint_000197472_50552832.pth new file mode 100644 index 0000000000000000000000000000000000000000..1045552c16f4e32bff10143134bd101264694516 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000197472_50552832.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa365cd11171880aa4b126927a82eda698fe43e6e87be051cca65d32cc7caea8 +size 20797139 diff --git a/checkpoint_p0/milestones/checkpoint_000210208_53813248.pth b/checkpoint_p0/milestones/checkpoint_000210208_53813248.pth new file mode 100644 index 0000000000000000000000000000000000000000..b7d5c6c621a20ad427bdb3486dd8b66e4a326c41 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000210208_53813248.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ae10edf8335d0081422dbc074a0785a7073d4bd1d10d2772dd8c5814a0551f5 +size 20797139 diff --git a/checkpoint_p0/milestones/checkpoint_000223040_57098240.pth b/checkpoint_p0/milestones/checkpoint_000223040_57098240.pth new file mode 100644 index 0000000000000000000000000000000000000000..96fde672db2bd15fa7b8d7c83abc8ad315467bf8 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000223040_57098240.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74e274cf9f8951e43d24e2da2278826b379b8d9f3d06a22aa70bb43f3f03bd01 +size 20797139 diff --git a/checkpoint_p0/milestones/checkpoint_000235712_60342272.pth b/checkpoint_p0/milestones/checkpoint_000235712_60342272.pth new file mode 100644 index 0000000000000000000000000000000000000000..362ed7e3bfaf31342ccdd49cbfe01669ef8a7483 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000235712_60342272.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79107707a49be81b5d0e12fdaa5731d2b7f9660b40cb44e92a851cac965748d4 +size 20797139 diff --git a/checkpoint_p0/milestones/checkpoint_000248480_63610880.pth b/checkpoint_p0/milestones/checkpoint_000248480_63610880.pth new file mode 100644 index 0000000000000000000000000000000000000000..d715bb14fadbe8cbb2782b14b2da927a30a7e872 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000248480_63610880.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5bd38eff0825c5fb40e048c708bd83ed82884aa44cd0d7da27b7d4e7cf32d81 +size 20797139 diff --git a/checkpoint_p0/milestones/checkpoint_000261312_66895872.pth b/checkpoint_p0/milestones/checkpoint_000261312_66895872.pth new file mode 100644 index 0000000000000000000000000000000000000000..be3507f824576fcf19105a17cd1e478c9a8f28b0 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000261312_66895872.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7470cae8c5c83e73df3a528d44290d29cecdffa14815c7e82780df50b268745c +size 20797139 diff --git a/checkpoint_p0/milestones/checkpoint_000273984_70139904.pth b/checkpoint_p0/milestones/checkpoint_000273984_70139904.pth new file mode 100644 index 0000000000000000000000000000000000000000..c81911c0b4e2796f27e1d9a65f3bf3ba5d2dfe8d --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000273984_70139904.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37e6842618fe3dcfaaa2eeacdbd8376e4fabf0f6580d926af2bd7068b9b43a9b +size 20797139 diff --git a/checkpoint_p0/milestones/checkpoint_000286752_73408512.pth b/checkpoint_p0/milestones/checkpoint_000286752_73408512.pth new file mode 100644 index 0000000000000000000000000000000000000000..8a7179d836d4a8716e8e5c83d6557b4e70c54d1d --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000286752_73408512.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6cd6371e2d0835ed53bb9aaed0e2058d56d35ce31a2e7fce515d9535041cd2e +size 20797139 diff --git a/checkpoint_p0/milestones/checkpoint_000299488_76668928.pth b/checkpoint_p0/milestones/checkpoint_000299488_76668928.pth new file mode 100644 index 0000000000000000000000000000000000000000..07ce840b0bb8d4b6b239fd3946ec77b29f0ff8d2 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000299488_76668928.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:508bc304e3ad3bef29850d9ae67e3f4358a4784d2eb79b6b9f1aa435f6a58e76 +size 20797139 diff --git a/checkpoint_p0/milestones/checkpoint_000312288_79945728.pth b/checkpoint_p0/milestones/checkpoint_000312288_79945728.pth new file mode 100644 index 0000000000000000000000000000000000000000..7b101769cf124af7c30a6f64e7a9e066d5c2a110 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000312288_79945728.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04b295a58825bfd1659af7d677bc1e4d550705117642d49a35ed9cc640bce3d6 +size 20797139 diff --git a/checkpoint_p0/milestones/checkpoint_000325024_83206144.pth b/checkpoint_p0/milestones/checkpoint_000325024_83206144.pth new file mode 100644 index 0000000000000000000000000000000000000000..2a3e22704fc83c14957500d9ebb36f6dc2095183 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000325024_83206144.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8213ff6a93ee5bb116974464bf3de68ce0691d1c80f62b59efeb1e14e793d30 +size 20797139 diff --git a/checkpoint_p0/milestones/checkpoint_000337792_86474752.pth b/checkpoint_p0/milestones/checkpoint_000337792_86474752.pth new file mode 100644 index 0000000000000000000000000000000000000000..f6cacb187202e35aafc538ff3f0edc3dcf7a9c35 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000337792_86474752.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b4325d4a89fed069dfdd7ae11cd5ea0c0fc35ec2dc708418938a82efe090599 +size 20797139 diff --git a/checkpoint_p0/milestones/checkpoint_000350432_89710592.pth b/checkpoint_p0/milestones/checkpoint_000350432_89710592.pth new file mode 100644 index 0000000000000000000000000000000000000000..eadb84281b5ae67c54fda86cd709b6bf63aa56c3 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000350432_89710592.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:777cb4a6018e86065534096b3b718ae4089be50bf5ddfa2a3019931fa648531d +size 20797139 diff --git a/checkpoint_p0/milestones/checkpoint_000363200_92979200.pth b/checkpoint_p0/milestones/checkpoint_000363200_92979200.pth new file mode 100644 index 0000000000000000000000000000000000000000..bbbf7bd4e42b085b38af98aab2f8eb493a752b60 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000363200_92979200.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db86969ea4ad6a842835eeddfd58c83122185294190c68b35a82afd1eb096b40 +size 20797139 diff --git a/checkpoint_p0/milestones/checkpoint_000375872_96223232.pth b/checkpoint_p0/milestones/checkpoint_000375872_96223232.pth new file mode 100644 index 0000000000000000000000000000000000000000..4adb5e1bf4846af27dd3b0fe9a2000e63a9a83fa --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000375872_96223232.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8a98d6ecdf035693361e7265ac6281727cd409d58491c8811fae6a746e03976 +size 20797139 diff --git a/checkpoint_p0/milestones/checkpoint_000388640_99491840.pth b/checkpoint_p0/milestones/checkpoint_000388640_99491840.pth new file mode 100644 index 0000000000000000000000000000000000000000..2aa8eb2d77f6f2070b2259acc1c676b4bc9eca0d --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000388640_99491840.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2dcd2b495d6c9d2ce7be56da5d8b22f532d9f2704d83e3bc86eda4aac501f3e7 +size 20797139 diff --git a/checkpoint_p0/milestones/checkpoint_000401248_102719488.pth b/checkpoint_p0/milestones/checkpoint_000401248_102719488.pth new file mode 100644 index 0000000000000000000000000000000000000000..c74bbafdfdac2837c414e3270a74b161b6334262 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000401248_102719488.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c873b819073096ff17f345482a2949e668064b285643b3377032e28d899597e2 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_000413920_105963520.pth b/checkpoint_p0/milestones/checkpoint_000413920_105963520.pth new file mode 100644 index 0000000000000000000000000000000000000000..332bf1070713a3398db98ddc46efb8efb4ba378e --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000413920_105963520.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59239c520712c0f453a31cee739231adc929e2d5fcad4dcfe964b611ed4a076e +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_000426656_109223936.pth b/checkpoint_p0/milestones/checkpoint_000426656_109223936.pth new file mode 100644 index 0000000000000000000000000000000000000000..7fe6152a20a492e32a47589212639208d0a88a33 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000426656_109223936.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd9058f26ef616e1f4abf7c7976ce68971452e6439caddfc1c76223d4ac42714 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_000439488_112508928.pth b/checkpoint_p0/milestones/checkpoint_000439488_112508928.pth new file mode 100644 index 0000000000000000000000000000000000000000..3e5ff910756124d8329d1b6aab944166caa1cadd --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000439488_112508928.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a12a69f23228b37f0255a3237d11623716aef753f8522090a8d0dbac76f9e103 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_000452192_115761152.pth b/checkpoint_p0/milestones/checkpoint_000452192_115761152.pth new file mode 100644 index 0000000000000000000000000000000000000000..aa172a5eff00ef0030109f05ebf74eaa033653b3 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000452192_115761152.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d38c12024993a712a84195e9d01a72473987793652b8e1b3a2b7542d838e4a7 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_000464896_119013376.pth b/checkpoint_p0/milestones/checkpoint_000464896_119013376.pth new file mode 100644 index 0000000000000000000000000000000000000000..532a3d02e89628641e7287bc412209f16df2e184 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000464896_119013376.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b61607d3b425a709709a30841d57a8716d56cf3b6a9c10aabbbde33413908fa4 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_000477600_122265600.pth b/checkpoint_p0/milestones/checkpoint_000477600_122265600.pth new file mode 100644 index 0000000000000000000000000000000000000000..8327a6381e50bfafe17b1179dfa38e01739625ee --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000477600_122265600.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fe6e58a28be77b225b77c31cb920c3bea66887ed51bbc2d52e22961cede109e +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_000490240_125501440.pth b/checkpoint_p0/milestones/checkpoint_000490240_125501440.pth new file mode 100644 index 0000000000000000000000000000000000000000..2974a4a2180c38bf2d5dd6f620fe7e9281ec45f8 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000490240_125501440.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22326f0e0e0aea57583865a75a5d8c2df7859310836fa34bdc2be1088ac2fd96 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_000502912_128745472.pth b/checkpoint_p0/milestones/checkpoint_000502912_128745472.pth new file mode 100644 index 0000000000000000000000000000000000000000..d4f8d50a8917c6bc4cd584f842d8b1ffb022b3bd --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000502912_128745472.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5a73d2199e238a3b48a81b76a8e4243e32083f5012d3a675e733d3a71bf0a8c +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_000515680_132014080.pth b/checkpoint_p0/milestones/checkpoint_000515680_132014080.pth new file mode 100644 index 0000000000000000000000000000000000000000..94e3f47652f333a47e4d4ec0f4f79543b1eb1b51 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000515680_132014080.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbf6c1e9a1ecba55bc3f47e7893e257b3bc4636f66d26b5c79cd832e71db2e79 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_000528384_135266304.pth b/checkpoint_p0/milestones/checkpoint_000528384_135266304.pth new file mode 100644 index 0000000000000000000000000000000000000000..5246fe0e7d455bd3b484cfdf3e1a043d38ebdcb2 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000528384_135266304.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f73b331aaa1a9e2b5b522ac075782720d76b94d19da9d7e6174d74b2fa96e11 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_000541088_138518528.pth b/checkpoint_p0/milestones/checkpoint_000541088_138518528.pth new file mode 100644 index 0000000000000000000000000000000000000000..02521c0255587307152f8a87137e66020ecf6db4 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000541088_138518528.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15a05291449f9b1372ba9334ac94c10135fe293260eb1a401be0b3c6ed097a20 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_000553824_141778944.pth b/checkpoint_p0/milestones/checkpoint_000553824_141778944.pth new file mode 100644 index 0000000000000000000000000000000000000000..ba2103db4d1b1a90909bfeeeb53bcbfd5122a162 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000553824_141778944.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:588fc72d6ba381aaa5ae9b6c2a0508925ea55866433e5c990c489eadd0cebd37 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_000575232_147259392.pth b/checkpoint_p0/milestones/checkpoint_000575232_147259392.pth new file mode 100644 index 0000000000000000000000000000000000000000..a1ecba7163da8d47578945c88dfa7da3497942b7 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000575232_147259392.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcea6d7233aa16fff1396f1cf18c9eff19947b543ee44662a024c11c6ae49c86 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_000588000_150528000.pth b/checkpoint_p0/milestones/checkpoint_000588000_150528000.pth new file mode 100644 index 0000000000000000000000000000000000000000..5ba86ace6a806d318dbec4340761c1e560a73527 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000588000_150528000.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:536ec94e0654f9a33c4206a12604e6ad4ec18bcfd8e4894cf5b4c8ba55522329 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_000600896_153829376.pth b/checkpoint_p0/milestones/checkpoint_000600896_153829376.pth new file mode 100644 index 0000000000000000000000000000000000000000..699674bedec47177f6e3c1dd6e6dfd67302c2ed8 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000600896_153829376.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72243c64c68adcbf155b32ef657761f8de9d1bf65640a12763c90a83e385c8ce +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_000613728_157114368.pth b/checkpoint_p0/milestones/checkpoint_000613728_157114368.pth new file mode 100644 index 0000000000000000000000000000000000000000..db71fe9b51f686e60e34fdec5397bcc4eb6b83b4 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000613728_157114368.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72ffbc16dd7a1a75887f99db5b2991d89c973e42196a769603294d0b0bf78a14 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_000626560_160399360.pth b/checkpoint_p0/milestones/checkpoint_000626560_160399360.pth new file mode 100644 index 0000000000000000000000000000000000000000..bce286b45014266e7c7b533442042f09a1094370 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000626560_160399360.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74e6a8da994cce8041007873cbb45b6b1368db96e99ffd37f94710c3397a2439 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_000639264_163651584.pth b/checkpoint_p0/milestones/checkpoint_000639264_163651584.pth new file mode 100644 index 0000000000000000000000000000000000000000..f2ef4b9a17555a4e52f4dfc40d4ea2ebf62d7708 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000639264_163651584.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1970f70c857a1fd2074ba2e6a4ab45c7da3b1b3ac4d1b456cf4d5a86f37e55e8 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_000652192_166961152.pth b/checkpoint_p0/milestones/checkpoint_000652192_166961152.pth new file mode 100644 index 0000000000000000000000000000000000000000..5fb69d155ca6239a1a60effe0e2591df5817b7dc --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000652192_166961152.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7297b0e395d5e602d48274f20231b0a029dbbf6dbe280621c172f16475ec7e5 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_000665056_170254336.pth b/checkpoint_p0/milestones/checkpoint_000665056_170254336.pth new file mode 100644 index 0000000000000000000000000000000000000000..5b8902cb178448e0035cbc9d039c6b94bf0b3159 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000665056_170254336.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e85603e87a1ba4c537f05fd68b2c8d2829dca48bb6536643a266f5fd3259e70 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_000677824_173522944.pth b/checkpoint_p0/milestones/checkpoint_000677824_173522944.pth new file mode 100644 index 0000000000000000000000000000000000000000..f380117738c988e9897495f945b6008d2f211198 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000677824_173522944.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:925ea5302bcb095c56eb4047b6ea3c5da8c940dc123c5a59ad680529037f2638 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_000690752_176832512.pth b/checkpoint_p0/milestones/checkpoint_000690752_176832512.pth new file mode 100644 index 0000000000000000000000000000000000000000..22e62f8290b215d7006b15b56279bdd1d498a452 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000690752_176832512.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5030c58f1a828dcd9916f84ea500778354c1eb54ca1bce5d509ad6debf4ee35 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_000703584_180117504.pth b/checkpoint_p0/milestones/checkpoint_000703584_180117504.pth new file mode 100644 index 0000000000000000000000000000000000000000..47a9dec377ac41958f8fc67d9f484549421fa99f --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000703584_180117504.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34e3884b83ba5a227e6ef5a407d4128075cbc5cd314e223df8f498611ce2258d +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_000716448_183410688.pth b/checkpoint_p0/milestones/checkpoint_000716448_183410688.pth new file mode 100644 index 0000000000000000000000000000000000000000..14dde0e88992846919f8a460e1ef9efd76a031d8 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000716448_183410688.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e418a1c7fa761f98a3c6e2552f6965046a9063ad9a953a8fd6b3cd85a02c51f4 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_000729408_186728448.pth b/checkpoint_p0/milestones/checkpoint_000729408_186728448.pth new file mode 100644 index 0000000000000000000000000000000000000000..0088792402a61edb1b3d8cb422091688d6b77f51 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000729408_186728448.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35680d329f56f0ddd73180697b6c8b2afde1fa89b6512ab7e923eb216ab1acec +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_000742240_190013440.pth b/checkpoint_p0/milestones/checkpoint_000742240_190013440.pth new file mode 100644 index 0000000000000000000000000000000000000000..634faf9b61ae1c727c002f44e9b4d2fae5d68951 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000742240_190013440.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:740221cbaf6d0faf040a99652ef9e118bf63dcd8bc79765a8c874cd1ae44aafe +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_000755072_193298432.pth b/checkpoint_p0/milestones/checkpoint_000755072_193298432.pth new file mode 100644 index 0000000000000000000000000000000000000000..b78584943aef1bc220846d4b7ed5bf281079a591 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000755072_193298432.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:094336b40c5d3096e119c1f70af298f350528cecc295ffe9baa42494f3f56473 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_000767904_196583424.pth b/checkpoint_p0/milestones/checkpoint_000767904_196583424.pth new file mode 100644 index 0000000000000000000000000000000000000000..1bcc78a647865fbfb207b291f0a854581118f35a --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000767904_196583424.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:adef4381261ee32ccdcac4371e1211826df1e7bf34e46015b1b4c2449d2e0442 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_000780800_199884800.pth b/checkpoint_p0/milestones/checkpoint_000780800_199884800.pth new file mode 100644 index 0000000000000000000000000000000000000000..5b26536657c02756693004e9554f167f6c7eaf1d --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000780800_199884800.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02908e7ec8e52b70e76e9d4fc76867750cebdedfd86b62919fc2b53502d67302 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_000793664_203177984.pth b/checkpoint_p0/milestones/checkpoint_000793664_203177984.pth new file mode 100644 index 0000000000000000000000000000000000000000..ed041b7b8f2f9191f5f82eb1cc231372296471d3 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000793664_203177984.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15d57ad1fb525f692ac6ab2eab074bb3a865311e38728d12339f916d55175d60 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_000806624_206495744.pth b/checkpoint_p0/milestones/checkpoint_000806624_206495744.pth new file mode 100644 index 0000000000000000000000000000000000000000..0c59a0bf62475e15481f3e453e7ff49283b59265 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000806624_206495744.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bf2e13cf68f84e15ef2760f4db3b6752463f09ca3b4ac20421bb84dcbeb92dd +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_000819520_209797120.pth b/checkpoint_p0/milestones/checkpoint_000819520_209797120.pth new file mode 100644 index 0000000000000000000000000000000000000000..edaaaf2d745297cdcb28160deba233fa41faa56e --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000819520_209797120.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99ce247fdf279a125034f5026366202785ac2eaff1824418fd3acc02b141bb30 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_000832288_213065728.pth b/checkpoint_p0/milestones/checkpoint_000832288_213065728.pth new file mode 100644 index 0000000000000000000000000000000000000000..e58aa1a5f482593d9c064a3ee57134c48d81e6b7 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000832288_213065728.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2ad7ed41584454044667dcd3ddf98baa5a59fe467150e31cf02f0a99b6334b6 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_000845152_216358912.pth b/checkpoint_p0/milestones/checkpoint_000845152_216358912.pth new file mode 100644 index 0000000000000000000000000000000000000000..6b88df7238c4673ceab8eeeae9485369809bc2ec --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000845152_216358912.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9624e23194c80cb3d4b2d5da57e1e3872fd7a307f8da6f58dc1e35421de9aa1e +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_000857920_219627520.pth b/checkpoint_p0/milestones/checkpoint_000857920_219627520.pth new file mode 100644 index 0000000000000000000000000000000000000000..558efc915ec2bfe79dd5e57634fe9977005ccd1c --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000857920_219627520.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:115b4252fa9bb8c5729078d35d543efe3cb5ad5815aeb92748d86647813f09e9 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_000870848_222937088.pth b/checkpoint_p0/milestones/checkpoint_000870848_222937088.pth new file mode 100644 index 0000000000000000000000000000000000000000..7746626584389938122a6a696bca2feab2906ec4 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000870848_222937088.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5e7bc0dc973435e5128acbb6ad6cc385db7e5af1abddd3753ee8c9f83860d27 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_000883680_226222080.pth b/checkpoint_p0/milestones/checkpoint_000883680_226222080.pth new file mode 100644 index 0000000000000000000000000000000000000000..8ae14060c06d4bbaa0d0506667c34078512e2bfe --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000883680_226222080.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f007f80a6d73bbab6eef37a4536ab35a69fad83f5a5dfe2a28204489dbe7f48 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_000896448_229490688.pth b/checkpoint_p0/milestones/checkpoint_000896448_229490688.pth new file mode 100644 index 0000000000000000000000000000000000000000..2f9d0b0567edbe04006208a8913b577ebe1c39f0 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000896448_229490688.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40c903cc1a24f5301b9de24bab99fd1bb062f702d705b8661dbbb076e0195bec +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_000909248_232767488.pth b/checkpoint_p0/milestones/checkpoint_000909248_232767488.pth new file mode 100644 index 0000000000000000000000000000000000000000..075da5caa0988d3ec1b2f2ef43b63add723f562d --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000909248_232767488.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3eff7ee878af4210bf2366703f080c1009b7b398cad219b276c4773c368a0e16 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_000921952_236019712.pth b/checkpoint_p0/milestones/checkpoint_000921952_236019712.pth new file mode 100644 index 0000000000000000000000000000000000000000..613bf1d6ea9adeacb83d983152b3cbe1eab579b3 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000921952_236019712.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da7317b1538ccb2bf69db59ba43d7021f6b837216efef74629bf3cf033c227c4 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_000934880_239329280.pth b/checkpoint_p0/milestones/checkpoint_000934880_239329280.pth new file mode 100644 index 0000000000000000000000000000000000000000..9dfdb31a9cccd146f2f1116707a1eae80968d2a4 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000934880_239329280.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c8d6e24cc5500f5dda50e023f72446b2f316f3e623cb875117a9cfd2327415b +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_000947680_242606080.pth b/checkpoint_p0/milestones/checkpoint_000947680_242606080.pth new file mode 100644 index 0000000000000000000000000000000000000000..fbf6c20b8c0edaab636170bef051540c00a77e3b --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000947680_242606080.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8295b608faaa90a42ec368e96bdb3160ad99c898650bbddfb48d3bda4f2c716c +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_000960352_245850112.pth b/checkpoint_p0/milestones/checkpoint_000960352_245850112.pth new file mode 100644 index 0000000000000000000000000000000000000000..8a56397f1eb8f1d5240b8da745d3e501635baf44 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000960352_245850112.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51f25af678a27bd16c9ee05706bd4b0e6722e009c138b4e6107307ad99ecf235 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_000973248_249151488.pth b/checkpoint_p0/milestones/checkpoint_000973248_249151488.pth new file mode 100644 index 0000000000000000000000000000000000000000..ff04b9ac6eaef99ce6aff853834112e81694d926 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000973248_249151488.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d58a7577dc8a274c23990ac64f514e7735120a924d0f95a1829c6232f03f1887 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_000985984_252411904.pth b/checkpoint_p0/milestones/checkpoint_000985984_252411904.pth new file mode 100644 index 0000000000000000000000000000000000000000..d6828c98bc9e8758fb42203e44aa3757e9c5a7c4 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000985984_252411904.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce44365efff6754577ca42edc4132262685ff957e2b5dc665c9bf33a64231a4b +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_000998848_255705088.pth b/checkpoint_p0/milestones/checkpoint_000998848_255705088.pth new file mode 100644 index 0000000000000000000000000000000000000000..be8066ec516fe9889bc10856788bbbdbdb660534 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000998848_255705088.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70f6c2ac815402316df8a2bb95d0b3eef7d751ffbd81a90d819ff50971c8c997 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001011648_258981888.pth b/checkpoint_p0/milestones/checkpoint_001011648_258981888.pth new file mode 100644 index 0000000000000000000000000000000000000000..0762148ebcc41b80b398187599bad6a3146aad57 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001011648_258981888.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:beae30aa73e301b95b044308b718f98fbf27afd437ad664affbd2aea41d56159 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001024448_262258688.pth b/checkpoint_p0/milestones/checkpoint_001024448_262258688.pth new file mode 100644 index 0000000000000000000000000000000000000000..8f9b32d6194aa5e3fb0e40edc63c7b045a8b703d --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001024448_262258688.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3618a9e73dfce41f352018ffd4dbb6fb53b991c57a7e03b18cfe547a1356a1e8 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001037184_265519104.pth b/checkpoint_p0/milestones/checkpoint_001037184_265519104.pth new file mode 100644 index 0000000000000000000000000000000000000000..d54f29baa2cef28d57cd8273ea8e473a8ac597e4 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001037184_265519104.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1aeee101582b6ebe9facf0d1a9837d0b2355e16c815691c775716a80190b3ee6 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001049920_268779520.pth b/checkpoint_p0/milestones/checkpoint_001049920_268779520.pth new file mode 100644 index 0000000000000000000000000000000000000000..916a2694e4e1a235ae2264964ead02bfe9c0d677 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001049920_268779520.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c61e2e6afb31aeb249e3e241879fe11a4fd633fa463b08edadeb8e8e015310a +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001062784_272072704.pth b/checkpoint_p0/milestones/checkpoint_001062784_272072704.pth new file mode 100644 index 0000000000000000000000000000000000000000..e2a3a12b33d2506adad69fa6f237749aa19ea9bb --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001062784_272072704.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5169212cc0b497c12f6b5d5e51ad98238ffb2321ffcd374d79e573183ba913d +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001075552_275341312.pth b/checkpoint_p0/milestones/checkpoint_001075552_275341312.pth new file mode 100644 index 0000000000000000000000000000000000000000..45058d78f589e05e98a3473bc772d9a4765404f1 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001075552_275341312.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6e6a4ae1581a0778efac14f465e6395ade3cee2e23b87d2111a8b0d8189b13d +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001088064_278544384.pth b/checkpoint_p0/milestones/checkpoint_001088064_278544384.pth new file mode 100644 index 0000000000000000000000000000000000000000..005f95f626ec50b4ae94c4391202443c07150805 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001088064_278544384.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff9094a5a4c0e97a48829d6b2b6a5f0dd5a42fe00c92665883e6f973a2a47c91 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001100864_281821184.pth b/checkpoint_p0/milestones/checkpoint_001100864_281821184.pth new file mode 100644 index 0000000000000000000000000000000000000000..a07b2a430acd669ff0384fed773929f8d5e9d015 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001100864_281821184.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5bc5ae4a79357c76d05d535482a58eb4bedfe8dd68218a0309916d81a817493 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001113696_285106176.pth b/checkpoint_p0/milestones/checkpoint_001113696_285106176.pth new file mode 100644 index 0000000000000000000000000000000000000000..c119821ab3fc0808d8c403ee03795d956ff92348 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001113696_285106176.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95c435ec1ee1ce9c9b0270624442e66e9dafe977646a2b097efe359e7676a165 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001126432_288366592.pth b/checkpoint_p0/milestones/checkpoint_001126432_288366592.pth new file mode 100644 index 0000000000000000000000000000000000000000..0404d9a136fd19a9754eedc13f5206f901dd5e44 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001126432_288366592.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0686a835c825c1686f11a8fc7152d658873455e341b9497c23ef45a38dfdc51 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001139168_291627008.pth b/checkpoint_p0/milestones/checkpoint_001139168_291627008.pth new file mode 100644 index 0000000000000000000000000000000000000000..2e5e0c64d320232fbb9a808ead019b1bdf3fc0b0 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001139168_291627008.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:766e2bfaa733ddae0d254250a864d4484612bc52c833406c8b5ac9236cee9dab +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001151840_294871040.pth b/checkpoint_p0/milestones/checkpoint_001151840_294871040.pth new file mode 100644 index 0000000000000000000000000000000000000000..07ab3c323fc9e13111b86eb8d0d440f1efee9643 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001151840_294871040.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a317c10da648baaa7037a5e14cf117ba1c2e1904264778f95cf8d8030bbfe3e6 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001164608_298139648.pth b/checkpoint_p0/milestones/checkpoint_001164608_298139648.pth new file mode 100644 index 0000000000000000000000000000000000000000..c19011d6c6cf0ef854d7927ff2f6aa5f1f2accfd --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001164608_298139648.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31e762f3206a9601b3caebbbf12644988f91d6a2c7670b1e65e62af97a46cbbd +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001177440_301424640.pth b/checkpoint_p0/milestones/checkpoint_001177440_301424640.pth new file mode 100644 index 0000000000000000000000000000000000000000..a65686ad533d8a9245618d572d92e24fd534ed75 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001177440_301424640.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af17155a11030f42a93ad4560bf510bad8e48b1fc52eb87e292fee344ab45c11 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001190240_304701440.pth b/checkpoint_p0/milestones/checkpoint_001190240_304701440.pth new file mode 100644 index 0000000000000000000000000000000000000000..ef9a21252035b1da49974d2fdf5748a2256b5d2a --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001190240_304701440.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d569b7677cabe68621c5bec9c2da5c9efe1ce8d0d668959acda5ce87ee90f1e +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001203104_307994624.pth b/checkpoint_p0/milestones/checkpoint_001203104_307994624.pth new file mode 100644 index 0000000000000000000000000000000000000000..e6e4981eb83bb5fd8b2478c4b9b3549170058d1f --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001203104_307994624.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:802dc5956bea932a6d03b1d48590450de5233f39024facf032efdee4a14aa99d +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001215904_311271424.pth b/checkpoint_p0/milestones/checkpoint_001215904_311271424.pth new file mode 100644 index 0000000000000000000000000000000000000000..0ccb2bc2e12bedf67e1d026ea7bcb19ac260f493 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001215904_311271424.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d2c2f85b3226ff71668426516e8b24b638910590fe894b6a9ff847717e2303c +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001228736_314556416.pth b/checkpoint_p0/milestones/checkpoint_001228736_314556416.pth new file mode 100644 index 0000000000000000000000000000000000000000..9c5427653425fe27820bbc91a8e6ceed32c52f88 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001228736_314556416.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d95696969840723c1a94d417b64cb706276f27a82bd1616c4be2168e1976a680 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001241536_317833216.pth b/checkpoint_p0/milestones/checkpoint_001241536_317833216.pth new file mode 100644 index 0000000000000000000000000000000000000000..c183e37ecb9992e1a1bbf7ee7161c1375ad38d7d --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001241536_317833216.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5144e96a1d045a9229bfca099590fdac2dc44934ae5659329d1252521f3b8e56 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001254336_321110016.pth b/checkpoint_p0/milestones/checkpoint_001254336_321110016.pth new file mode 100644 index 0000000000000000000000000000000000000000..7bc7a9f20f8ec68e096083f77b2529805cc95bd3 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001254336_321110016.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26d2d3d11ff321bd884c35c038b4f61f8699ad79a3bcf346505ea74939c35229 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001267232_324411392.pth b/checkpoint_p0/milestones/checkpoint_001267232_324411392.pth new file mode 100644 index 0000000000000000000000000000000000000000..c5857ed64d932fab1cf19bee36edbff0308f3919 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001267232_324411392.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ad070808cfc400d3e664d50296ddad9f556aebefbc5ac771d8261dc004f5dad +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001279968_327671808.pth b/checkpoint_p0/milestones/checkpoint_001279968_327671808.pth new file mode 100644 index 0000000000000000000000000000000000000000..34eb9f61f413394f6cc10b37a081ee1c08331ec3 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001279968_327671808.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:298c5eb11219745f82e9f65257dc91abf26986d47cdb249217807bac5b4465ed +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001292768_330948608.pth b/checkpoint_p0/milestones/checkpoint_001292768_330948608.pth new file mode 100644 index 0000000000000000000000000000000000000000..86a72d34837a06a0294682e0982c556e7c6f8339 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001292768_330948608.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7cebf7d470a7719ae0a7bc8f34b79498cd9f7a242c84fed8fd0e25089db30ca +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001305632_334241792.pth b/checkpoint_p0/milestones/checkpoint_001305632_334241792.pth new file mode 100644 index 0000000000000000000000000000000000000000..13d1ec37cf06a1a2873a101b3c973681bc0017e4 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001305632_334241792.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78f07936d8424cd3e7e12779b1398b6ef67317cc789252b3a09385a0808f3987 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001318432_337518592.pth b/checkpoint_p0/milestones/checkpoint_001318432_337518592.pth new file mode 100644 index 0000000000000000000000000000000000000000..6d5b47a5d4e481d468f57449856b73fa0d67351c --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001318432_337518592.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:405658df9eb95669602dd03c638b49cca03a495feecb8decca8b14acd7121583 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001331296_340811776.pth b/checkpoint_p0/milestones/checkpoint_001331296_340811776.pth new file mode 100644 index 0000000000000000000000000000000000000000..933caf3fb50a2d0eb5d71a88c829e236ece94a46 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001331296_340811776.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6328effdb5598c28d7638825bfd30c9776c93d2751eaf910ee70d970b23b67c1 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001344096_344088576.pth b/checkpoint_p0/milestones/checkpoint_001344096_344088576.pth new file mode 100644 index 0000000000000000000000000000000000000000..202b2ddd0ad86169757aa79adda1463e05017478 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001344096_344088576.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47ace91711559e249133b431a3b0fdf06fdc621c9da66b13d975a5154b67ac76 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001356960_347381760.pth b/checkpoint_p0/milestones/checkpoint_001356960_347381760.pth new file mode 100644 index 0000000000000000000000000000000000000000..c5607d42df1615757e14326f3ab28c38f61d00de --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001356960_347381760.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98a859f3ae9273d2619504b1c9ce636edab967d5c6189580c6af8415eca05aa1 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001369760_350658560.pth b/checkpoint_p0/milestones/checkpoint_001369760_350658560.pth new file mode 100644 index 0000000000000000000000000000000000000000..2ed1df03ea27ae4946233e0dbebe999a054f719d --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001369760_350658560.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f705876f13fab627fb9081e39165e0947652ee8b1b184e48e899f0a1dba74258 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001382528_353927168.pth b/checkpoint_p0/milestones/checkpoint_001382528_353927168.pth new file mode 100644 index 0000000000000000000000000000000000000000..a6899b5b7de4d10cd2f97dc69b40ca295a94f322 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001382528_353927168.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b05d562f539bb50240d57eec6431a8d329fb2720e5d18eadc2ce6d3e2c08ffcd +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001395328_357203968.pth b/checkpoint_p0/milestones/checkpoint_001395328_357203968.pth new file mode 100644 index 0000000000000000000000000000000000000000..28c9f62f718b00cc461e08a0f549ba4c61894cb9 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001395328_357203968.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f0db9c5baefbe099de2087e5d418a3edb9f17654ed25e01c78c720ee8b99274 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001408256_360513536.pth b/checkpoint_p0/milestones/checkpoint_001408256_360513536.pth new file mode 100644 index 0000000000000000000000000000000000000000..b0a43936c1c5a8a179e253a8b51be80a70bab396 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001408256_360513536.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dca861dcc11e35659ab2497db7863093d2fe018ccf7627bc1228f27121cf2c5b +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001421024_363782144.pth b/checkpoint_p0/milestones/checkpoint_001421024_363782144.pth new file mode 100644 index 0000000000000000000000000000000000000000..cbdcd561bb51523351df2b208b48124cca909475 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001421024_363782144.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3cc64763ad6935d60b13ca4e8ec3cca83e59b6ef0edea15af2985295480ce729 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001433856_367067136.pth b/checkpoint_p0/milestones/checkpoint_001433856_367067136.pth new file mode 100644 index 0000000000000000000000000000000000000000..da0fcb6fe517fb546cc156f40043dd5f16d29ba7 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001433856_367067136.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:365580379c8cfd2bee44182aa2c562e5deef40b34afca40f34eba926c3385e05 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001446752_370368512.pth b/checkpoint_p0/milestones/checkpoint_001446752_370368512.pth new file mode 100644 index 0000000000000000000000000000000000000000..c4102cbb0a66e936996f75701b8845e8dbe6df12 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001446752_370368512.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0831930537297c51129abc3c6bd4ed8ae427777e0e9a599072e62433a03b7fd1 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001459520_373637120.pth b/checkpoint_p0/milestones/checkpoint_001459520_373637120.pth new file mode 100644 index 0000000000000000000000000000000000000000..b6f4afbf28e4cd7e34fb2cd4b81897736fee09ab --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001459520_373637120.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0cd6a8604e82a1a1289b9f784b0322609c458cd63544577ac7dc4bfc7a8cf7b +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001472352_376922112.pth b/checkpoint_p0/milestones/checkpoint_001472352_376922112.pth new file mode 100644 index 0000000000000000000000000000000000000000..34b3cd1a2f441d1af548021ae545da88825afe2d --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001472352_376922112.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:029e92be4198f91c7201c037a3cfe49f12f94514e5bce45561cb25636f0a56c1 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001485088_380182528.pth b/checkpoint_p0/milestones/checkpoint_001485088_380182528.pth new file mode 100644 index 0000000000000000000000000000000000000000..702be72c9340eb0fb7b79f5aea98582904d1a6e3 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001485088_380182528.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71feb2568da1c8f05afd5e08e187e5ec45234c946681e6cf1d3506607e6c4954 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001497792_383434752.pth b/checkpoint_p0/milestones/checkpoint_001497792_383434752.pth new file mode 100644 index 0000000000000000000000000000000000000000..965beff5f21cd2f0a7ac4eb13ea807cce1596af8 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001497792_383434752.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca3fc84d2992e758f4afd33a00fe1ee63982c1e1b2214c81d3d214298144eb92 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001510624_386719744.pth b/checkpoint_p0/milestones/checkpoint_001510624_386719744.pth new file mode 100644 index 0000000000000000000000000000000000000000..98c656c205dd0e0912f76106ad89ac0b190478fb --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001510624_386719744.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76f8ad7a1fa5f5eb3887e78d4948884a7c4c3e0565ebec5c9261e715ec01f33e +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001523456_390004736.pth b/checkpoint_p0/milestones/checkpoint_001523456_390004736.pth new file mode 100644 index 0000000000000000000000000000000000000000..8a272a35202c3f70b954e0faf1f4188d5638803e --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001523456_390004736.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e24d1730a0dc9436a798fcc187c0eafcad55a1001a7016f13ed23b09f2352ae +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001536160_393256960.pth b/checkpoint_p0/milestones/checkpoint_001536160_393256960.pth new file mode 100644 index 0000000000000000000000000000000000000000..9266f0c413d3e5d2d5d1bcc7b9b7667999e29d24 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001536160_393256960.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60b4718a20e38b995f9a25bd4da2414ebd3c6dca8545f15312da474502b39c67 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001549024_396550144.pth b/checkpoint_p0/milestones/checkpoint_001549024_396550144.pth new file mode 100644 index 0000000000000000000000000000000000000000..5300874cc9873cbd63bd092317dee631af32e67c --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001549024_396550144.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:830db475ef6baa65f526aba0b3c93285d125ac999c21ec6aa19d526fcda350bc +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001561856_399835136.pth b/checkpoint_p0/milestones/checkpoint_001561856_399835136.pth new file mode 100644 index 0000000000000000000000000000000000000000..4db9418a7759d1e5546a7e04de40f9847fea1bc9 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001561856_399835136.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6cd46994605a98b575790b421defa6be270d6846e98190332c413200e5255ce4 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001574656_403111936.pth b/checkpoint_p0/milestones/checkpoint_001574656_403111936.pth new file mode 100644 index 0000000000000000000000000000000000000000..95e5ff1a4f59bbc27fdd7376a33058d19a86a6cc --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001574656_403111936.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b801831eda9830ccfe9636ae0ff6304a53e19bae0250c3d8eff28073af6fb3ec +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001587424_406380544.pth b/checkpoint_p0/milestones/checkpoint_001587424_406380544.pth new file mode 100644 index 0000000000000000000000000000000000000000..af1de6984e8b0b9abd51bede0d7b88a539c97e80 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001587424_406380544.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:885c1690d1981a989a2df726ea9a1a66d0d229204e4e722d219258c6577f1181 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001600256_409665536.pth b/checkpoint_p0/milestones/checkpoint_001600256_409665536.pth new file mode 100644 index 0000000000000000000000000000000000000000..ef3ac16207ac96566f3f1298ca794eb1c34f5c7f --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001600256_409665536.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1443f60ae3f7726f9b469564ab3519848e23f5e88fe56eaddc29edd782a2391a +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001613056_412942336.pth b/checkpoint_p0/milestones/checkpoint_001613056_412942336.pth new file mode 100644 index 0000000000000000000000000000000000000000..717083bbc6037fed4af03ce513ad79e92c283882 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001613056_412942336.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c7fbd7b1ff59e755365d87b25bb70355813b565373fd3abac418b970b484dad +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001625920_416235520.pth b/checkpoint_p0/milestones/checkpoint_001625920_416235520.pth new file mode 100644 index 0000000000000000000000000000000000000000..dcb87e98cfe651726a6dc0a12d52f1a0b1ea774f --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001625920_416235520.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:075e9715a73683ffb1fba0827ca3572005216ddd28b5ffc7f56127aa49ca2716 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001638720_419512320.pth b/checkpoint_p0/milestones/checkpoint_001638720_419512320.pth new file mode 100644 index 0000000000000000000000000000000000000000..91fb11bd620e0c966739bb02ec514a56bbe053cd --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001638720_419512320.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8961e86fa758441c36e626963cc741f5a544323db68da1d9b5ab9321c5aed26b +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001651520_422789120.pth b/checkpoint_p0/milestones/checkpoint_001651520_422789120.pth new file mode 100644 index 0000000000000000000000000000000000000000..aedd3d8c0a6373cd9fe3d88f5ffc4c11a39af4a4 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001651520_422789120.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5650173df9281c52568c76fcfdf4398af1cf2a050506a3076464856fe6c75d8a +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001664384_426082304.pth b/checkpoint_p0/milestones/checkpoint_001664384_426082304.pth new file mode 100644 index 0000000000000000000000000000000000000000..9adda265347f58740556c3db022309c2194e50e4 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001664384_426082304.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f170dccefa87eed2b4fb91b5f53d46d578ea16a8f5b923f14e8d81e987f595b +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001677248_429375488.pth b/checkpoint_p0/milestones/checkpoint_001677248_429375488.pth new file mode 100644 index 0000000000000000000000000000000000000000..a13526dd7cbce30f2abb13a3a2ff8849ba34efad --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001677248_429375488.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fa6c3fbac078b7b6a5ca010c1c937a4f186c78b116c543b8c064c71ca555d4f +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001689952_432627712.pth b/checkpoint_p0/milestones/checkpoint_001689952_432627712.pth new file mode 100644 index 0000000000000000000000000000000000000000..5f76cfdd5092f94402a0f23abdb10b411124ce2f --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001689952_432627712.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fc6d0cef2fd1e0f6e2f6e28399eb918bb38cccfc626a6b8c4140be5a944847f +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001702720_435896320.pth b/checkpoint_p0/milestones/checkpoint_001702720_435896320.pth new file mode 100644 index 0000000000000000000000000000000000000000..974776dcc694c3174580e4d8c4909fb062bacc00 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001702720_435896320.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e34a53fe2dc8e9a99c64ad941efbff5831129306fd68850e01965baacf8dd504 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001715552_439181312.pth b/checkpoint_p0/milestones/checkpoint_001715552_439181312.pth new file mode 100644 index 0000000000000000000000000000000000000000..2b0a01004835fbb2082f8a4c86d4a47097a195aa --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001715552_439181312.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da668c980c4b7d52db684b2650be4745158fe08508d50519346dbec9bbd23a59 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001728512_442499072.pth b/checkpoint_p0/milestones/checkpoint_001728512_442499072.pth new file mode 100644 index 0000000000000000000000000000000000000000..41b44a31fd0f25216a357bc9db7dba8870f40a2e --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001728512_442499072.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3031c687466d4dece1c2e118c28eef7b62f83f4a98feca73b2bcc9ca23f6484b +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001741376_445792256.pth b/checkpoint_p0/milestones/checkpoint_001741376_445792256.pth new file mode 100644 index 0000000000000000000000000000000000000000..acbe9532b9be1117212c1073a3ccc85f299d20fa --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001741376_445792256.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e52b8b5ee9014f77d0dcde3ec1b3875037b60759b401e884779e54ba57eff1d +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001754144_449060864.pth b/checkpoint_p0/milestones/checkpoint_001754144_449060864.pth new file mode 100644 index 0000000000000000000000000000000000000000..9089ed4b13e41042e6d21454553cd072da4f44a3 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001754144_449060864.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df9372021006d507e34c55f65131b7f5360051dabb6798d2382468e7167eeca9 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001766912_452329472.pth b/checkpoint_p0/milestones/checkpoint_001766912_452329472.pth new file mode 100644 index 0000000000000000000000000000000000000000..1ce1876e50356532121eb24ed5859f7b42c69db5 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001766912_452329472.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf2f1ba09f105a2ad12c22b1246c4243a8f71189d9836511235234d3abd661db +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001779808_455630848.pth b/checkpoint_p0/milestones/checkpoint_001779808_455630848.pth new file mode 100644 index 0000000000000000000000000000000000000000..2f15e4d041a6bcd07aa135b4000a9f79578a237f --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001779808_455630848.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15fade164f84e8eb3cd4d8e88e8dd59ba33bfa8fbadf568098b6b4701a72ec4b +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001792544_458891264.pth b/checkpoint_p0/milestones/checkpoint_001792544_458891264.pth new file mode 100644 index 0000000000000000000000000000000000000000..f6a270c58de8161259eb5ce241052a3ed7b22594 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001792544_458891264.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b17965d91773d243e1b68a1b042caba27db1db3189209c21b375b50e0b7a222b +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001805312_462159872.pth b/checkpoint_p0/milestones/checkpoint_001805312_462159872.pth new file mode 100644 index 0000000000000000000000000000000000000000..3c643892148ac06eb95d9398ce6ae481fee800f5 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001805312_462159872.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c58fb361a828b08b97efdde02acb15611c70b3db8c5df8a4b337d09118c3855e +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001818112_465436672.pth b/checkpoint_p0/milestones/checkpoint_001818112_465436672.pth new file mode 100644 index 0000000000000000000000000000000000000000..3f593c7691ae256b70117b43554a0fd7a1ba30ea --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001818112_465436672.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3aabeb96312c694f7afa7b8f428acafbf8fcd75dbacf80a433bbf8b85b3bf4a +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001830944_468721664.pth b/checkpoint_p0/milestones/checkpoint_001830944_468721664.pth new file mode 100644 index 0000000000000000000000000000000000000000..e15ccfc0d3f52d0f121fa364c4c7a57c3ab2b6c2 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001830944_468721664.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:787213aaff32cfac6649eb0c47ebe7595ce9659fc462bb60ea2d36efab453739 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001843648_471973888.pth b/checkpoint_p0/milestones/checkpoint_001843648_471973888.pth new file mode 100644 index 0000000000000000000000000000000000000000..2c41a3f812b559d75c6fa62df5e8becf35d32fd3 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001843648_471973888.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ff2bd4d9b9984bcb6c43458b0eb6c08893d68601d82b927addd87c8e4544278 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001856512_475267072.pth b/checkpoint_p0/milestones/checkpoint_001856512_475267072.pth new file mode 100644 index 0000000000000000000000000000000000000000..7e8c7b8621924e8853ddd8d518f6ee25afad6e5b --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001856512_475267072.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b61c3a4aca2f9529a79a47e99a4970fda9ae8f45fa04ac3198a06ecf88bc239 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001869408_478568448.pth b/checkpoint_p0/milestones/checkpoint_001869408_478568448.pth new file mode 100644 index 0000000000000000000000000000000000000000..195ca0f9e5698079abff125e3a6b62bd23d5eea0 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001869408_478568448.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9774c68f0d698e47cb9769489a56d0de69133d6cc3ca64452044e9ecabc8025b +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001882208_481845248.pth b/checkpoint_p0/milestones/checkpoint_001882208_481845248.pth new file mode 100644 index 0000000000000000000000000000000000000000..fe6f160b3e3d10dfa53ad19d9d9ea2fa03d5def9 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001882208_481845248.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e3b4775014e891e9f4c5260baa0a4798fe3e31e6750ae185a5b71c8997082ae +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001894944_485105664.pth b/checkpoint_p0/milestones/checkpoint_001894944_485105664.pth new file mode 100644 index 0000000000000000000000000000000000000000..934b226da1b3a8dc5fa888b7180d1c218cd96187 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001894944_485105664.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cb6cdbb1137cd167cc1497cc62e57fe0a825272f1da1212a07d542071dbfc75 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001907744_488382464.pth b/checkpoint_p0/milestones/checkpoint_001907744_488382464.pth new file mode 100644 index 0000000000000000000000000000000000000000..3a6d7824f80a3cfd58cbba80c2fb77b5bbbbad70 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001907744_488382464.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:165883ea8327b890bb6e77a9242cfa27c708bd0eb77c99fd0858788fecd4d50e +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001920416_491626496.pth b/checkpoint_p0/milestones/checkpoint_001920416_491626496.pth new file mode 100644 index 0000000000000000000000000000000000000000..71ccc397951f0fc6cafdba64e1f8fc7a3ad0f474 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001920416_491626496.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6971e31889a0097f53e74b7f46eae55c44d5ea1a354488bf327c0021d5368717 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001933216_494903296.pth b/checkpoint_p0/milestones/checkpoint_001933216_494903296.pth new file mode 100644 index 0000000000000000000000000000000000000000..8dd959e75a02f9568806ef053f9ce7e3c4427fc1 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001933216_494903296.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9963a727da39cc9d44c91e79ca3ecc6a3a0df709ba9bb593ee544d43431bdb9 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001946080_498196480.pth b/checkpoint_p0/milestones/checkpoint_001946080_498196480.pth new file mode 100644 index 0000000000000000000000000000000000000000..c2df6e3439f90950d486de24373fb5990c9da98d --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001946080_498196480.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2dcb306e43175a86cb1f3b95c61da3883d7ea7bf5bda77f95409633d8a70ef95 +size 20797195 diff --git a/checkpoint_p0/milestones/checkpoint_001958944_501489664.pth b/checkpoint_p0/milestones/checkpoint_001958944_501489664.pth new file mode 100644 index 0000000000000000000000000000000000000000..d4e34438f07ca161af1a5ded24ce46e4e66e6ecc --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001958944_501489664.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a160e9fd2ead96ae303336de95520b26f69c85c119bc8d02ac073b4a66c09410 +size 20797195 diff --git a/checkpoint_p1/best_000562112_143900672_reward_17.255.pth b/checkpoint_p1/best_000562112_143900672_reward_17.255.pth new file mode 100644 index 0000000000000000000000000000000000000000..0d2d83d326d87088d994f10a0f9748bbb65a7f35 --- /dev/null +++ b/checkpoint_p1/best_000562112_143900672_reward_17.255.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce89b64b6135819cea0ec23f2d79d4fd8d90e776cac0c8ee022c2bac70287fd3 +size 20795955 diff --git a/checkpoint_p1/checkpoint_001952288_499785728.pth b/checkpoint_p1/checkpoint_001952288_499785728.pth new file mode 100644 index 0000000000000000000000000000000000000000..9f626bfe4db5c2a58e8e1aca02f2c3da7be53c7e --- /dev/null +++ b/checkpoint_p1/checkpoint_001952288_499785728.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f6aebdb53229d502e83cf3da0aa014565affbced7150b76c0779fde4877ef97 +size 20796291 diff --git a/checkpoint_p1/checkpoint_001953184_500015104.pth b/checkpoint_p1/checkpoint_001953184_500015104.pth new file mode 100644 index 0000000000000000000000000000000000000000..f2146d7db95e761dfac4c2caf7cedf3bd715a5e9 --- /dev/null +++ b/checkpoint_p1/checkpoint_001953184_500015104.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59ebce9fa8000031fa16ba858feff39635fc35b27eba558033d92216a58b59b4 +size 20796291 diff --git a/checkpoint_p1/milestones/checkpoint_000012480_3194880.pth b/checkpoint_p1/milestones/checkpoint_000012480_3194880.pth new file mode 100644 index 0000000000000000000000000000000000000000..7fcd23b6f05e405b7474046cd0d68680baac3ad3 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000012480_3194880.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82c88a4b955c494b5dd1e9bc2e81e442328510a183d5357dea578eabf48f7725 +size 20797083 diff --git a/checkpoint_p1/milestones/checkpoint_000025152_6438912.pth b/checkpoint_p1/milestones/checkpoint_000025152_6438912.pth new file mode 100644 index 0000000000000000000000000000000000000000..0b849cec03620a5306f0b46709f522d369b4bc4a --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000025152_6438912.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0e77f540b7848857f8ce0857df05f7c698807285ba22bd72e7f9a747f799397 +size 20797083 diff --git a/checkpoint_p1/milestones/checkpoint_000037888_9699328.pth b/checkpoint_p1/milestones/checkpoint_000037888_9699328.pth new file mode 100644 index 0000000000000000000000000000000000000000..d20d5199b2706201d8a8660d0d030cc43ebea4b8 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000037888_9699328.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62889b879d0a9b6c3aaf93ea99ce1143e64fb0811e1c6f17bca2e711f87bbe7f +size 20797083 diff --git a/checkpoint_p1/milestones/checkpoint_000056992_14589952.pth b/checkpoint_p1/milestones/checkpoint_000056992_14589952.pth new file mode 100644 index 0000000000000000000000000000000000000000..6fd0e313424cb467e0fd2257cf30b078bbcc8ac7 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000056992_14589952.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2533dd1cccc7736f9a97f092399378eb726c20226a232f56d9def50c8b2d1a8 +size 20797139 diff --git a/checkpoint_p1/milestones/checkpoint_000069856_17883136.pth b/checkpoint_p1/milestones/checkpoint_000069856_17883136.pth new file mode 100644 index 0000000000000000000000000000000000000000..004c857516c7c6241ed8f40dfa3bc4a1f4def842 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000069856_17883136.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c09b2919af76a7fc51e270d4c404a98a25f1fd64702150dce037ebe3d60a62c2 +size 20797139 diff --git a/checkpoint_p1/milestones/checkpoint_000082496_21118976.pth b/checkpoint_p1/milestones/checkpoint_000082496_21118976.pth new file mode 100644 index 0000000000000000000000000000000000000000..5c0c797dd242ba2dc6f89459fda7290cfcdde475 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000082496_21118976.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56528628dbc8b29b501fb84f15c4250256e6cb34afd8631e4d90f5b3061716b0 +size 20797139 diff --git a/checkpoint_p1/milestones/checkpoint_000095264_24387584.pth b/checkpoint_p1/milestones/checkpoint_000095264_24387584.pth new file mode 100644 index 0000000000000000000000000000000000000000..d712da3a4f9383b068732a9ad1161b8c3fd5942f --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000095264_24387584.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:debd1b00c0f0f28feb83356ed9570a005efcec09818c7f88ddea1ad3edc0de66 +size 20797139 diff --git a/checkpoint_p1/milestones/checkpoint_000107904_27623424.pth b/checkpoint_p1/milestones/checkpoint_000107904_27623424.pth new file mode 100644 index 0000000000000000000000000000000000000000..bee680029017abda9190796bad59759dc19e1cbf --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000107904_27623424.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6c119701029101fc3739214b3a968f181a7a2188a26be6b028921f491612876 +size 20797139 diff --git a/checkpoint_p1/milestones/checkpoint_000120608_30875648.pth b/checkpoint_p1/milestones/checkpoint_000120608_30875648.pth new file mode 100644 index 0000000000000000000000000000000000000000..89a31a6bd00939d9de9bdbfbdd6a4dffe07984f6 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000120608_30875648.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8f73acabe8b2552fa0601d0fd440632a48befe1b8c02ba44faf376cc7003d72 +size 20797139 diff --git a/checkpoint_p1/milestones/checkpoint_000133312_34127872.pth b/checkpoint_p1/milestones/checkpoint_000133312_34127872.pth new file mode 100644 index 0000000000000000000000000000000000000000..4d0e8ac3d434e0164862c4a750da3d24a6566741 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000133312_34127872.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:471708b85e2b72c8cf025cb1182d74f86bcf2dcdf76a3161c3f712562596f084 +size 20797139 diff --git a/checkpoint_p1/milestones/checkpoint_000145952_37363712.pth b/checkpoint_p1/milestones/checkpoint_000145952_37363712.pth new file mode 100644 index 0000000000000000000000000000000000000000..f0d873a7449a1db9c78d3ebcafa4cb6d97dcdd89 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000145952_37363712.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c92532b27b116187790c1e41b7c297ccf16bc4f181f25c2316632b3f6e944ea +size 20797139 diff --git a/checkpoint_p1/milestones/checkpoint_000158688_40624128.pth b/checkpoint_p1/milestones/checkpoint_000158688_40624128.pth new file mode 100644 index 0000000000000000000000000000000000000000..10f3c81a37009dde85be453d3b3ca5c5d10688e9 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000158688_40624128.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1530c6a7f39f049c24f1510755f09fc60b314670eefe5e977e47c5441e1e5597 +size 20797139 diff --git a/checkpoint_p1/milestones/checkpoint_000171392_43876352.pth b/checkpoint_p1/milestones/checkpoint_000171392_43876352.pth new file mode 100644 index 0000000000000000000000000000000000000000..ab131da481f91c3d5ac538fd5e9d5a474d4e5c95 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000171392_43876352.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb1aae3db501898048c06ec56e759dcb2c0892f6a0855ac6f6fe59abd939f5c1 +size 20797139 diff --git a/checkpoint_p1/milestones/checkpoint_000184064_47120384.pth b/checkpoint_p1/milestones/checkpoint_000184064_47120384.pth new file mode 100644 index 0000000000000000000000000000000000000000..c7c4ff6e65d9de1e454b7d16fde7716544c3f124 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000184064_47120384.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89616d148fb160c7a8f13684ba5b41e167ea6da77bb172a0774f7d9388becbac +size 20797139 diff --git a/checkpoint_p1/milestones/checkpoint_000196800_50380800.pth b/checkpoint_p1/milestones/checkpoint_000196800_50380800.pth new file mode 100644 index 0000000000000000000000000000000000000000..ceca6111d6b32a0e219b7394348f0c40f7799d79 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000196800_50380800.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afd3f82b15bb185ab6f37561b43b82af3a3586b0e3480ff7650db462c7c31455 +size 20797139 diff --git a/checkpoint_p1/milestones/checkpoint_000209408_53608448.pth b/checkpoint_p1/milestones/checkpoint_000209408_53608448.pth new file mode 100644 index 0000000000000000000000000000000000000000..162f1aba92da33792fa74cf2ab19258e2ed145c0 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000209408_53608448.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:227b3c24ec2e18b6159ff61fdaaf67e403dc237413b2650da42f17a8d9febec9 +size 20797139 diff --git a/checkpoint_p1/milestones/checkpoint_000222080_56852480.pth b/checkpoint_p1/milestones/checkpoint_000222080_56852480.pth new file mode 100644 index 0000000000000000000000000000000000000000..657639a30d00cd9fa30ef8b236ca6e9608737624 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000222080_56852480.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:272e3ccf0e451f37b6d19468649b232a038fda6016a70eb3c9f6b310a49d6a20 +size 20797139 diff --git a/checkpoint_p1/milestones/checkpoint_000234848_60121088.pth b/checkpoint_p1/milestones/checkpoint_000234848_60121088.pth new file mode 100644 index 0000000000000000000000000000000000000000..c9ff49c0bbfad8945cb7f9e09bda8cb12beec67a --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000234848_60121088.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c602fc6c53c287e1188a0e57bb4a2379617dc172d0cdf38cd4433c0bf60dc11 +size 20797139 diff --git a/checkpoint_p1/milestones/checkpoint_000247552_63373312.pth b/checkpoint_p1/milestones/checkpoint_000247552_63373312.pth new file mode 100644 index 0000000000000000000000000000000000000000..06dd8190728fa1cc8f08068483b55f365fadca5e --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000247552_63373312.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e1dfed73dda298b6032cfde05345949458d31fa1f090c2cb98f6be97cb7987b +size 20797139 diff --git a/checkpoint_p1/milestones/checkpoint_000260288_66633728.pth b/checkpoint_p1/milestones/checkpoint_000260288_66633728.pth new file mode 100644 index 0000000000000000000000000000000000000000..15323cc19c559537607f72eff21fb65a469bcd2e --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000260288_66633728.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7b95d73a202d9344f280e2a196a5d29e09fc777b06a1ca61caec0d5502f24e1 +size 20797139 diff --git a/checkpoint_p1/milestones/checkpoint_000273024_69894144.pth b/checkpoint_p1/milestones/checkpoint_000273024_69894144.pth new file mode 100644 index 0000000000000000000000000000000000000000..871439a2a398c0b156dc1c55c772af8cceefd762 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000273024_69894144.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5404e7acc087c5790cf190b1b00a47f5d29c38df07edcf85dac7bdd034715e1 +size 20797139 diff --git a/checkpoint_p1/milestones/checkpoint_000285760_73154560.pth b/checkpoint_p1/milestones/checkpoint_000285760_73154560.pth new file mode 100644 index 0000000000000000000000000000000000000000..011c984b545d42c8966a5f8fa96763298f2631a6 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000285760_73154560.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1af7e637e64c30b8b70e169c95cd29a5c67af80f71da97266393c86f70c4d5a7 +size 20797139 diff --git a/checkpoint_p1/milestones/checkpoint_000298400_76390400.pth b/checkpoint_p1/milestones/checkpoint_000298400_76390400.pth new file mode 100644 index 0000000000000000000000000000000000000000..789b2a759c929a101bd82ed5f21097690b95b6ef --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000298400_76390400.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dda237101276237081dba147966e363b9f4bc5c0f2a6371cd4efd8773d478075 +size 20797139 diff --git a/checkpoint_p1/milestones/checkpoint_000311072_79634432.pth b/checkpoint_p1/milestones/checkpoint_000311072_79634432.pth new file mode 100644 index 0000000000000000000000000000000000000000..90dae07a94f1a0b0c94db8c7cd4c93090309d858 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000311072_79634432.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e59211be709495c14c83a2978d22d59c35dd91ce0568510768c7fe867740906 +size 20797139 diff --git a/checkpoint_p1/milestones/checkpoint_000323840_82903040.pth b/checkpoint_p1/milestones/checkpoint_000323840_82903040.pth new file mode 100644 index 0000000000000000000000000000000000000000..cf8b22cfed69cd863b1ae0d1fc2785587c2f82a4 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000323840_82903040.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ceb24488f7ed1bae74a39d4d573cfd8965b947560ce8e7b7b6fd2e45c3798a28 +size 20797139 diff --git a/checkpoint_p1/milestones/checkpoint_000336640_86179840.pth b/checkpoint_p1/milestones/checkpoint_000336640_86179840.pth new file mode 100644 index 0000000000000000000000000000000000000000..3325777c0d3e84fc35919a369b212902edccad2f --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000336640_86179840.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d9f0f0839f384062474402edb5a5575e396f880ee292cdd53f6918af45c451e +size 20797139 diff --git a/checkpoint_p1/milestones/checkpoint_000349376_89440256.pth b/checkpoint_p1/milestones/checkpoint_000349376_89440256.pth new file mode 100644 index 0000000000000000000000000000000000000000..44ea2d88a7776822ebce29901c961a3ddbc42672 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000349376_89440256.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:939c0091e1d2743f2e80d4f2e3e4c0d21721a1c939b77f4d17e5bfe5b61ac046 +size 20797139 diff --git a/checkpoint_p1/milestones/checkpoint_000362144_92708864.pth b/checkpoint_p1/milestones/checkpoint_000362144_92708864.pth new file mode 100644 index 0000000000000000000000000000000000000000..11d9d87504fa90f70499a7f701b04c95453eaeec --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000362144_92708864.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88eed36a07828f064a3230c56c650567d1fcce198128266dbe0bcf586c7cd635 +size 20797139 diff --git a/checkpoint_p1/milestones/checkpoint_000375008_96002048.pth b/checkpoint_p1/milestones/checkpoint_000375008_96002048.pth new file mode 100644 index 0000000000000000000000000000000000000000..9bdbfcb59591d69885b8caabb1517833ef4f1c9b --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000375008_96002048.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1448efda1306124c7d68370dd9439dfdab04c9856404598976ae52cba03993b7 +size 20797139 diff --git a/checkpoint_p1/milestones/checkpoint_000387680_99246080.pth b/checkpoint_p1/milestones/checkpoint_000387680_99246080.pth new file mode 100644 index 0000000000000000000000000000000000000000..df314e54a7ba03992a9e524cf13aff16afad2910 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000387680_99246080.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd2ed27b64b76117f4f34a9adb2066f8d5945a0a6a5a656df3a55b297883142d +size 20797139 diff --git a/checkpoint_p1/milestones/checkpoint_000400416_102506496.pth b/checkpoint_p1/milestones/checkpoint_000400416_102506496.pth new file mode 100644 index 0000000000000000000000000000000000000000..c38d20e914d2fe8199a742382eea4e2544e36643 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000400416_102506496.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9821791bcfa7eada3730d4981b9cc709f50037e0ba868e4211e4a5b4f76c2366 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_000413120_105758720.pth b/checkpoint_p1/milestones/checkpoint_000413120_105758720.pth new file mode 100644 index 0000000000000000000000000000000000000000..b3b0eb794c2942ce82bd9eccab50547730b01473 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000413120_105758720.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea3305f6e8934991454c37a59b89ffe8a3dbf9f9bede86d2f38e5dcd03693896 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_000425792_109002752.pth b/checkpoint_p1/milestones/checkpoint_000425792_109002752.pth new file mode 100644 index 0000000000000000000000000000000000000000..c507042402d118fca51a7e0f6622acf47a904d9e --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000425792_109002752.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e1dea06104e2ecb7fc287ba909bd19f53e0fa9f9bea4f187acf1eac719f0867 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_000438528_112263168.pth b/checkpoint_p1/milestones/checkpoint_000438528_112263168.pth new file mode 100644 index 0000000000000000000000000000000000000000..5d6f603f69db51e6a5fe9c9048bea8efe7aabcbe --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000438528_112263168.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ffb511d53ab42c3ebab8a9c4cc4e602947844071654e94a5f1f670e37a0fdc5 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_000451328_115539968.pth b/checkpoint_p1/milestones/checkpoint_000451328_115539968.pth new file mode 100644 index 0000000000000000000000000000000000000000..df7c1ef1f9c7f46c981cd65c4d6f95aa8ab7af69 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000451328_115539968.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:795e7dad783756765f902b0723c09ff61734362b3acd32531e380fc4dffd7bdb +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_000464032_118792192.pth b/checkpoint_p1/milestones/checkpoint_000464032_118792192.pth new file mode 100644 index 0000000000000000000000000000000000000000..ab47bccfc9acd861ea9ea6e509d682b885b48633 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000464032_118792192.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0712bca0f80b476555fb7a51471557595e99d31fd1b50fb81afe074965a5849 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_000476800_122060800.pth b/checkpoint_p1/milestones/checkpoint_000476800_122060800.pth new file mode 100644 index 0000000000000000000000000000000000000000..ac3f5f0e70467389dc64d1af17b74d0ce8e2c095 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000476800_122060800.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d3013aa6ae047d739f8e854fd5ed121163aac9bbf62b52ad45ab8f5d18c6405 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_000489440_125296640.pth b/checkpoint_p1/milestones/checkpoint_000489440_125296640.pth new file mode 100644 index 0000000000000000000000000000000000000000..7e93ed66011aba55825fd31cf10b8d26e9cf9cd3 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000489440_125296640.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a77e7563984caf8fad08c877303ede3795cfe9bc9df81aede13ce980f68ce8b +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_000502112_128540672.pth b/checkpoint_p1/milestones/checkpoint_000502112_128540672.pth new file mode 100644 index 0000000000000000000000000000000000000000..cd4cd3a2673e0b6a4fd341dc40c55da3fbc19c1c --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000502112_128540672.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7135430e8964265685bb3d50a87688e0225386e67b722e73cc71f2b2acdfdea7 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_000514880_131809280.pth b/checkpoint_p1/milestones/checkpoint_000514880_131809280.pth new file mode 100644 index 0000000000000000000000000000000000000000..8af8b9aebd3ab1e8cfa71cf04ece0ce92dcffb87 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000514880_131809280.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a4a0b67025eacabcb9d939754236c731f953b97b12424b9eab443d86d1c707a +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_000527616_135069696.pth b/checkpoint_p1/milestones/checkpoint_000527616_135069696.pth new file mode 100644 index 0000000000000000000000000000000000000000..900cdb3620eb071f3bf5a5cf4e7684a7fa51b507 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000527616_135069696.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03d5c0d8d1e09fbc8115e3f73bb2c2fd6bd9af65d7f82dc974f40bf9c3d80f52 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_000540384_138338304.pth b/checkpoint_p1/milestones/checkpoint_000540384_138338304.pth new file mode 100644 index 0000000000000000000000000000000000000000..9857aed088dc3238dd34798ee12c8c02182013ff --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000540384_138338304.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fd954b4ed6af3e6a813bd77aa3fae494af5ed8e5a4937afd975ec264adc1352 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_000553024_141574144.pth b/checkpoint_p1/milestones/checkpoint_000553024_141574144.pth new file mode 100644 index 0000000000000000000000000000000000000000..4040cab9df942ad50e1d6c700324bb64322b320f --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000553024_141574144.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0288efafd2dd948f44a99ca092251a507692996259ca5414f4f58f1a59e53266 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_000574272_147013632.pth b/checkpoint_p1/milestones/checkpoint_000574272_147013632.pth new file mode 100644 index 0000000000000000000000000000000000000000..7b7bf06b10f90a49d18a95f3ac1a905f25335a98 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000574272_147013632.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:736a4760ff79df6bdf8f4dab4844bb893e0ef71cc9cca8a884ae2d82cb3a8724 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_000587040_150282240.pth b/checkpoint_p1/milestones/checkpoint_000587040_150282240.pth new file mode 100644 index 0000000000000000000000000000000000000000..35ff7cac7d540b79908d2b3d967690091e1b5f9e --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000587040_150282240.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8df37c66e625b4c2b41812aeaf9c88887c25d02ddf955bd48d22f312817c7a77 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_000599712_153526272.pth b/checkpoint_p1/milestones/checkpoint_000599712_153526272.pth new file mode 100644 index 0000000000000000000000000000000000000000..4c4ea70f493a820666f7ff784ce970e5e0a3bafa --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000599712_153526272.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d4298fcac3e4262f8e4bb409e98f3a808bbac9025784da18042e7256ec28882 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_000612320_156753920.pth b/checkpoint_p1/milestones/checkpoint_000612320_156753920.pth new file mode 100644 index 0000000000000000000000000000000000000000..54361b185b15abd2b50003eed299ced621ab2267 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000612320_156753920.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe27004fe5a6e2fef8d57b2695cacd5b2e96c110c7a7fa1714e4e2993fd8215c +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_000625056_160014336.pth b/checkpoint_p1/milestones/checkpoint_000625056_160014336.pth new file mode 100644 index 0000000000000000000000000000000000000000..5836152e42a78eb7f3158e49ff24886339cd79ab --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000625056_160014336.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cf5b614362afe33c8975ced763cbdab11089221e0b9d9cce8607bb9091477f8 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_000637824_163282944.pth b/checkpoint_p1/milestones/checkpoint_000637824_163282944.pth new file mode 100644 index 0000000000000000000000000000000000000000..ded93844bd4fc2ead800ad03794b5ca8c3701ec0 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000637824_163282944.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd1538d106dc5cd2e3049de0a82f2ee2eaef96b232ff4873bff3892c9451a04c +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_000650496_166526976.pth b/checkpoint_p1/milestones/checkpoint_000650496_166526976.pth new file mode 100644 index 0000000000000000000000000000000000000000..ed3753291bb820134274e50b56287af1c5a9bcfc --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000650496_166526976.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e07cbc149801cd9b44a769c0c074332b4c74434849acb796b2448b180cdf2267 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_000663264_169795584.pth b/checkpoint_p1/milestones/checkpoint_000663264_169795584.pth new file mode 100644 index 0000000000000000000000000000000000000000..651bceb1d39a93dcf44bcbbb4080919206f54ca7 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000663264_169795584.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:adcfb73dd6549fee0bdd61664dccf4596b7e5295339a5cc5b01117ef941eb1b6 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_000675904_173031424.pth b/checkpoint_p1/milestones/checkpoint_000675904_173031424.pth new file mode 100644 index 0000000000000000000000000000000000000000..68b311718fb2783855f8e25ce01c032ed1b56194 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000675904_173031424.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09f26a4a9c03cada386462a9b3aef7d6db4b989fe4944089828bc9b0c7d07f07 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_000688608_176283648.pth b/checkpoint_p1/milestones/checkpoint_000688608_176283648.pth new file mode 100644 index 0000000000000000000000000000000000000000..741d6bfbcc4ad4f64207823e2e311a3055d66541 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000688608_176283648.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d53572307e5c1453ac70be76a250c140afe10bd576e60d1cbb6eb22a01e2f921 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_000701376_179552256.pth b/checkpoint_p1/milestones/checkpoint_000701376_179552256.pth new file mode 100644 index 0000000000000000000000000000000000000000..c6347243753d37abfb99733a0bbf49ca29d4744b --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000701376_179552256.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bad4180070c87eb241fe527f627ca13f0870f531d87f5325a79ea3edd99c77e +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_000713984_182779904.pth b/checkpoint_p1/milestones/checkpoint_000713984_182779904.pth new file mode 100644 index 0000000000000000000000000000000000000000..78dd07fc82218b692515f1cf6db7606622ecbe26 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000713984_182779904.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63f6b6684ba05f2204d438cba54cd6bd92db7be3004d13692cc3269f6156fcbb +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_000726720_186040320.pth b/checkpoint_p1/milestones/checkpoint_000726720_186040320.pth new file mode 100644 index 0000000000000000000000000000000000000000..816292db3042453bf00bb225f1b710798abf1879 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000726720_186040320.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ba4c9968d0f29e11d087071f0548ca403efa73b2305e604a09d48945a5aea8a +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_000739488_189308928.pth b/checkpoint_p1/milestones/checkpoint_000739488_189308928.pth new file mode 100644 index 0000000000000000000000000000000000000000..df0033afa2b837d4831ac2f21ffcd9592afbc05d --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000739488_189308928.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e069b5bc826abc31d26f1d42adf917b4b84451c895cf7e0a2d34488696d5c28 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_000752160_192552960.pth b/checkpoint_p1/milestones/checkpoint_000752160_192552960.pth new file mode 100644 index 0000000000000000000000000000000000000000..e9bb1567c7bb970d6709509f7e309c8232ab823a --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000752160_192552960.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:611a2990deebc966a8b91f04261d3b1d600baaae5ff0c7019238ecb0f97acb80 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_000764896_195813376.pth b/checkpoint_p1/milestones/checkpoint_000764896_195813376.pth new file mode 100644 index 0000000000000000000000000000000000000000..d99720110f74e97f54164261d8cc1a42220daaac --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000764896_195813376.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6156598b0469ae2229454c9caa59307d6b08083bf96b892960d1088c587c562b +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_000777664_199081984.pth b/checkpoint_p1/milestones/checkpoint_000777664_199081984.pth new file mode 100644 index 0000000000000000000000000000000000000000..4e1d277025e6f3bb1d20fcf779da3cca8b1270c7 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000777664_199081984.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4ce5d9138224574a833fc733fefcb9de5020d54a59926c73ad662765abc35db +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_000790304_202317824.pth b/checkpoint_p1/milestones/checkpoint_000790304_202317824.pth new file mode 100644 index 0000000000000000000000000000000000000000..456e0b8f7050f3ff9aeafb17ff3169b61826d3b2 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000790304_202317824.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12e90da31965a5952cc92dfe36ea5bb467b869ac0054c1ce7096e065cc66b6cc +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_000803040_205578240.pth b/checkpoint_p1/milestones/checkpoint_000803040_205578240.pth new file mode 100644 index 0000000000000000000000000000000000000000..85532e5e2b408802ad2664e0dc6047ba9cf60616 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000803040_205578240.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cb5f971e96335f36b0e1295938d56f3fabb0fccf1c00e07af23aa88da81984d +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_000815776_208838656.pth b/checkpoint_p1/milestones/checkpoint_000815776_208838656.pth new file mode 100644 index 0000000000000000000000000000000000000000..d5668463569efebd3cc614d8623f7d2053b4ab0e --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000815776_208838656.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b793a7545f514c5d2754bc923c3bb2002af6ac939ffcf3e286ebd56f868b333 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_000828448_212082688.pth b/checkpoint_p1/milestones/checkpoint_000828448_212082688.pth new file mode 100644 index 0000000000000000000000000000000000000000..869ebd1175f06911fae2f3911340069d02035bff --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000828448_212082688.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8960b6394f27e28c0d5b71749f5fb19d8ef610c574799582f9fac29d8d2f7cd6 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_000841248_215359488.pth b/checkpoint_p1/milestones/checkpoint_000841248_215359488.pth new file mode 100644 index 0000000000000000000000000000000000000000..5dc26035aab086228600f520bcd76ba902f63783 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000841248_215359488.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebd5eaf04af3f04f535215e9cef2d21cb0ffceb9cb83ad288129aef01ae932e8 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_000853984_218619904.pth b/checkpoint_p1/milestones/checkpoint_000853984_218619904.pth new file mode 100644 index 0000000000000000000000000000000000000000..b85ba165a03beb5faaa24b43a4064247816afb23 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000853984_218619904.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1454a8d0ad8367a1317c1cfa7bc2b4c05d90583466d24876855862d80c15e4bf +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_000866656_221863936.pth b/checkpoint_p1/milestones/checkpoint_000866656_221863936.pth new file mode 100644 index 0000000000000000000000000000000000000000..01ff2ac8f12a716e6e54c14f8d2c3e656e7c99b3 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000866656_221863936.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e43b0abbe506076a1453db9d4a8616a1247246269aa8fef4bce4c7a4636a81ae +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_000879360_225116160.pth b/checkpoint_p1/milestones/checkpoint_000879360_225116160.pth new file mode 100644 index 0000000000000000000000000000000000000000..54ad652d2b2adf23b94346e380e0f04e634bc331 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000879360_225116160.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fbbbd3eda1ec772b7a5cdffdfaa8bf19a4d18a8c096b4a2af2d3f5409b9c0b5 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_000892064_228368384.pth b/checkpoint_p1/milestones/checkpoint_000892064_228368384.pth new file mode 100644 index 0000000000000000000000000000000000000000..98f1a85830742ec41b7246601073ecd178a476de --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000892064_228368384.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d16ebae7cf65bf3cda6d046832b4cb4f6197b756410901e888d62553a647236b +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_000904672_231596032.pth b/checkpoint_p1/milestones/checkpoint_000904672_231596032.pth new file mode 100644 index 0000000000000000000000000000000000000000..ffd2725cf4f8f4381fe8da4607ea3220fc1de26b --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000904672_231596032.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d0ea4cafd2665ee38b754142c22c937db5ad9055a3b4edaf290e59f3f023b09 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_000917280_234823680.pth b/checkpoint_p1/milestones/checkpoint_000917280_234823680.pth new file mode 100644 index 0000000000000000000000000000000000000000..be42c141d2c33bbd52b46e14331e369d693bf1c2 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000917280_234823680.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:479552ff65760697d8febf4fdfb08ebc94e4ab71126cfccbed876be86c396e61 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_000929920_238059520.pth b/checkpoint_p1/milestones/checkpoint_000929920_238059520.pth new file mode 100644 index 0000000000000000000000000000000000000000..89a1fdd3f11e1b49ff7b06ca79ab6d20ffcd4717 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000929920_238059520.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32d864f2f08fea62e8917374266a8c2a2ffce1ec37d682dbe23a34965fc36d63 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_000942560_241295360.pth b/checkpoint_p1/milestones/checkpoint_000942560_241295360.pth new file mode 100644 index 0000000000000000000000000000000000000000..026ac9f169654db9035dce2b82c3be95fd67bf3a --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000942560_241295360.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0372cd27e1e269b8486c01837b3778f08e9cf4f56aa3e73b22caba746e72abbb +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_000955168_244523008.pth b/checkpoint_p1/milestones/checkpoint_000955168_244523008.pth new file mode 100644 index 0000000000000000000000000000000000000000..c6ef53cef5216c89fa2a95cfa07d0c9381b74345 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000955168_244523008.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66bc13f18523087d4aca43fdd213daca736777f55034482b2f443b6169123bf4 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_000967808_247758848.pth b/checkpoint_p1/milestones/checkpoint_000967808_247758848.pth new file mode 100644 index 0000000000000000000000000000000000000000..25e10debfcf9aafa8f09c5e3119556cb279e9403 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000967808_247758848.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d646923b3b646ae8c61a88ea2777fbb41df61ff76f8f0d83634e5232c67cb6aa +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_000980352_250970112.pth b/checkpoint_p1/milestones/checkpoint_000980352_250970112.pth new file mode 100644 index 0000000000000000000000000000000000000000..17845e7a820ddcf2bd2d32ab0fefc5d8080fc534 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000980352_250970112.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee5b20ccc52ccd17c49e0100110e63be39e163868371b081706d395a883e103e +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_000993024_254214144.pth b/checkpoint_p1/milestones/checkpoint_000993024_254214144.pth new file mode 100644 index 0000000000000000000000000000000000000000..ee41051abd5d48f93f75aed458c4ef51adc9409a --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000993024_254214144.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea701d3ebdcefda815049ff32b05cea06431f8f053e51b2fe10fbfc91d4f1eb5 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001005760_257474560.pth b/checkpoint_p1/milestones/checkpoint_001005760_257474560.pth new file mode 100644 index 0000000000000000000000000000000000000000..1b626f44085c7afba3507667226ff35760014284 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001005760_257474560.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5edbb30614fdddb0f143680920cffee02dbe8aad49ea179a9c992f23fc545dc +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001018400_260710400.pth b/checkpoint_p1/milestones/checkpoint_001018400_260710400.pth new file mode 100644 index 0000000000000000000000000000000000000000..5f5eaa6013fd2644be1e27ecaf16f8fb3c66e73d --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001018400_260710400.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:554cbebc04aa319440661d22bc01d0438fcf68555cb4a074f935a41195fe0f20 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001031040_263946240.pth b/checkpoint_p1/milestones/checkpoint_001031040_263946240.pth new file mode 100644 index 0000000000000000000000000000000000000000..4b6ec13a64d3647b1f22c2f52da5835a32cc608d --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001031040_263946240.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94295d8aa017f51beb4c8641b25b5d129b42c55b554f04848cb9e104dfbf5bc2 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001043648_267173888.pth b/checkpoint_p1/milestones/checkpoint_001043648_267173888.pth new file mode 100644 index 0000000000000000000000000000000000000000..9dc79302951698c7f9756e4ca7b8c73678e8e558 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001043648_267173888.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b535064af884746785620caccb8e4da6063f1d930b27cab8d9185c0f18f2a8d7 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001056288_270409728.pth b/checkpoint_p1/milestones/checkpoint_001056288_270409728.pth new file mode 100644 index 0000000000000000000000000000000000000000..bc6b6b22167d1b8707609c1c6cb69b91f3865ab1 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001056288_270409728.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d6e042b97c0af2b4f6fc2dccd06280a96f21f41d81cc96a303de04d66ab7535 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001068928_273645568.pth b/checkpoint_p1/milestones/checkpoint_001068928_273645568.pth new file mode 100644 index 0000000000000000000000000000000000000000..591ce2477e1515e1b0126ab433506bdb12574cb6 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001068928_273645568.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b261ecd0bc381898d142f7e31f513ff7286091b493ad12800eebc51c24396fcd +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001081216_276791296.pth b/checkpoint_p1/milestones/checkpoint_001081216_276791296.pth new file mode 100644 index 0000000000000000000000000000000000000000..ee74972ad74dd54bb2dbbbd62ad4d388a9632d49 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001081216_276791296.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:732b3135a29cec216a9ac087f7a5320e78545d855f1a7ede52d782cb25f6abba +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001093920_280043520.pth b/checkpoint_p1/milestones/checkpoint_001093920_280043520.pth new file mode 100644 index 0000000000000000000000000000000000000000..b7aaddb61e591fad6e0f34cee3c7ae96357d86e0 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001093920_280043520.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fca14d17bbada7429de0b8a0efb0374f84982c5ca5e8bad29405b873b2c9687 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001106624_283295744.pth b/checkpoint_p1/milestones/checkpoint_001106624_283295744.pth new file mode 100644 index 0000000000000000000000000000000000000000..482e89f21e4943439d8e15ecdd4b3d1b9f1d2af5 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001106624_283295744.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9877be94f002dce08b5e197ab8e02ead22b0aa67f9fc0d7a4b04437f8e6da0f5 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001119328_286547968.pth b/checkpoint_p1/milestones/checkpoint_001119328_286547968.pth new file mode 100644 index 0000000000000000000000000000000000000000..b349299cdd3c64b883f0b1d88ab4053ebf41f644 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001119328_286547968.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:098c6f7cc714a9f89a71351a8b8ebf703a8a0c27a19f54f181dab6e72bc50ee8 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001131968_289783808.pth b/checkpoint_p1/milestones/checkpoint_001131968_289783808.pth new file mode 100644 index 0000000000000000000000000000000000000000..0682ceed7bca782a2570864bd4b0aaa352da5874 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001131968_289783808.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93b15565ffc5e7c3e73093c053102cd67d0162d831a99793c7df35b6a14f9546 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001144640_293027840.pth b/checkpoint_p1/milestones/checkpoint_001144640_293027840.pth new file mode 100644 index 0000000000000000000000000000000000000000..6fbe945e6e55b8a03616dfaf24d783046633815f --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001144640_293027840.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:216428d8a4d9073cc4f47fc9d8a436624bd8e991b1d9925c0335fc1b248b02b2 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001157344_296280064.pth b/checkpoint_p1/milestones/checkpoint_001157344_296280064.pth new file mode 100644 index 0000000000000000000000000000000000000000..aa00ee556a04b57795a728d259bbc9fb456253a8 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001157344_296280064.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:136e631a1d25b262c3c5e1467d2f922453ac713bc361016414e06677511adaf1 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001169952_299507712.pth b/checkpoint_p1/milestones/checkpoint_001169952_299507712.pth new file mode 100644 index 0000000000000000000000000000000000000000..7ea656a97a2a8c7dc6cbe1b28ec5303facccd505 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001169952_299507712.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8153566a32ea2e1b1f57214bcd14d9a3f881b44257e64e18277eda2f1832b88a +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001182592_302743552.pth b/checkpoint_p1/milestones/checkpoint_001182592_302743552.pth new file mode 100644 index 0000000000000000000000000000000000000000..70beb0f4136f26f93a6767edc2b90f4a222ef081 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001182592_302743552.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bac822edaaf8e898002ac08c680b27c9b1d7ea0e6c803cef5f3608c75071675c +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001195360_306012160.pth b/checkpoint_p1/milestones/checkpoint_001195360_306012160.pth new file mode 100644 index 0000000000000000000000000000000000000000..8f34483a2724881ab5172de056e1a476935492ab --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001195360_306012160.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45675c6d9e6bbc31b3dab43a3705be2597a0aa586df2933b88cb89f622b28713 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001208064_309264384.pth b/checkpoint_p1/milestones/checkpoint_001208064_309264384.pth new file mode 100644 index 0000000000000000000000000000000000000000..22bba427a6cb026354e47aa6d579d492f4f69166 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001208064_309264384.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fac538efe82e647e38bb98d6c2cc708fbf81a19ada206781c499c2784b270e5d +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001220832_312532992.pth b/checkpoint_p1/milestones/checkpoint_001220832_312532992.pth new file mode 100644 index 0000000000000000000000000000000000000000..61619209d17d48f54cf76f140e41d39162cdb9cd --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001220832_312532992.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:068de3826e3f43958b28106770e05bf9e5464151878447af79162b68abe4c3bc +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001233376_315744256.pth b/checkpoint_p1/milestones/checkpoint_001233376_315744256.pth new file mode 100644 index 0000000000000000000000000000000000000000..05706a4b24024af86fb2a31f5d8c036eb38188a2 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001233376_315744256.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:497875c09bdcc79e217eeb9477eb1c39594ff7e00adf637bf6637f9e8b930255 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001246016_318980096.pth b/checkpoint_p1/milestones/checkpoint_001246016_318980096.pth new file mode 100644 index 0000000000000000000000000000000000000000..97b2bbd8632e974d4df8724b692c40839f550c58 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001246016_318980096.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d299848a73ee9cc14c93240f15d218d4af5c3157859af435841d081809f80e6 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001258656_322215936.pth b/checkpoint_p1/milestones/checkpoint_001258656_322215936.pth new file mode 100644 index 0000000000000000000000000000000000000000..ca68cfdf52918a188cb9d57df48ac7eb3ecf6a45 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001258656_322215936.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d72baa9ef0884ba4ab5de7da6a785feb8b7bd84d21bd057d31136dcf5eae4be +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001271456_325492736.pth b/checkpoint_p1/milestones/checkpoint_001271456_325492736.pth new file mode 100644 index 0000000000000000000000000000000000000000..0e94009262a6984c6949da14356eea3a8266134f --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001271456_325492736.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2555ea42decb8d61c4db485d712501dd66cc631e7ec29da5ea9c746bae1787a8 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001284128_328736768.pth b/checkpoint_p1/milestones/checkpoint_001284128_328736768.pth new file mode 100644 index 0000000000000000000000000000000000000000..cad32baa704d8dc7a8b7da581ed0a0ee885568b3 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001284128_328736768.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d98a530ea951d4bce898fa2959273648a9e0b78785e2db3228a2269fd85bcfc1 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001296736_331964416.pth b/checkpoint_p1/milestones/checkpoint_001296736_331964416.pth new file mode 100644 index 0000000000000000000000000000000000000000..e425e44f760182fda9822796c13b6f5fd4c5e32c --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001296736_331964416.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:000beae10b9720adcee5f64800b18ecd3e37c33255083323e2c629c1c88a0d9f +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001309472_335224832.pth b/checkpoint_p1/milestones/checkpoint_001309472_335224832.pth new file mode 100644 index 0000000000000000000000000000000000000000..ea744263069dab3e616e167ae2593a19da0296d6 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001309472_335224832.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb02cf9e59bf3fe64f1b648e5b416f46e7fb5dd34159f01aefb969ea3f0a1809 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001322176_338477056.pth b/checkpoint_p1/milestones/checkpoint_001322176_338477056.pth new file mode 100644 index 0000000000000000000000000000000000000000..6ad4ea1ba3bc93de979b46bdc47882a60169e090 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001322176_338477056.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc2efc60b8d7f11d9d05aa2e0aaeb7dadf3902d1b5ccd63f66daf4c6efa9e3b9 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001334848_341721088.pth b/checkpoint_p1/milestones/checkpoint_001334848_341721088.pth new file mode 100644 index 0000000000000000000000000000000000000000..d05527d9902ba1a7785f49095b831f98da3e7b1a --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001334848_341721088.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b00788aa4863cc19aa374b6353b8753d45b623732b6659b4aabd41ff905c962 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001347488_344956928.pth b/checkpoint_p1/milestones/checkpoint_001347488_344956928.pth new file mode 100644 index 0000000000000000000000000000000000000000..5d472ba3a9a596ae7ffade1c0af6bad664b0fb82 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001347488_344956928.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:759fef106dfcf838275e45f0d0d358d15462331d0004d9fc89978f5329b912f3 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001360128_348192768.pth b/checkpoint_p1/milestones/checkpoint_001360128_348192768.pth new file mode 100644 index 0000000000000000000000000000000000000000..8b2a16523f6b3df7a334975f37281d2d29717b2b --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001360128_348192768.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb6cab17c969355c5c268609306a5e8801a896384976b34250d7eb43f4bdbf9d +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001372704_351412224.pth b/checkpoint_p1/milestones/checkpoint_001372704_351412224.pth new file mode 100644 index 0000000000000000000000000000000000000000..7542d79dad8bc6a8763ca0ec8c1d9d16ce087efd --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001372704_351412224.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7866dc89920de33291aaa9f58b16842ab4cf5d026f7a900f87d80ba249d7c60 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001385536_354697216.pth b/checkpoint_p1/milestones/checkpoint_001385536_354697216.pth new file mode 100644 index 0000000000000000000000000000000000000000..773a4519db83e8233fb6c843dd4f5f434bfa39f7 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001385536_354697216.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e8aa5b7f8e5ccbc76c69106c79649816beee8f66a6b63e7f13925ed68a87407 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001398208_357941248.pth b/checkpoint_p1/milestones/checkpoint_001398208_357941248.pth new file mode 100644 index 0000000000000000000000000000000000000000..7e7ccd7b4496abc63c2432f9b4c57d8c5e9d787d --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001398208_357941248.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9d5b870fe405eba1de59383d47381cf9670929def39136b2c9af189048b0740 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001410816_361168896.pth b/checkpoint_p1/milestones/checkpoint_001410816_361168896.pth new file mode 100644 index 0000000000000000000000000000000000000000..987e40d9e01b32ed3854d6e49350aa4948214f49 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001410816_361168896.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:446e78d933b70fb2382cf9c881f542ad5c68e6400e91c88c510a0babc564bfbd +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001423488_364412928.pth b/checkpoint_p1/milestones/checkpoint_001423488_364412928.pth new file mode 100644 index 0000000000000000000000000000000000000000..b6b490f0c7ced1d800e4ec1db8c8445e625f3941 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001423488_364412928.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5906bf946eedd98b3647b460136981f1868192b96c8dcb2f23e023cd69098d7c +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001436096_367640576.pth b/checkpoint_p1/milestones/checkpoint_001436096_367640576.pth new file mode 100644 index 0000000000000000000000000000000000000000..ae6f993c0419ec1c119acc0dffffcd17af50ebdc --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001436096_367640576.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71b67e013313e123a8f2e3b322cc6fda2ac7b6b476a3c068b334b562fd58cc92 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001448672_370860032.pth b/checkpoint_p1/milestones/checkpoint_001448672_370860032.pth new file mode 100644 index 0000000000000000000000000000000000000000..cf43a651e36463a4ab334fda5dc91511872e1589 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001448672_370860032.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e80821987214f19691770b10108c5b55a8859f256c11fc3ee691f1a276749a37 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001461312_374095872.pth b/checkpoint_p1/milestones/checkpoint_001461312_374095872.pth new file mode 100644 index 0000000000000000000000000000000000000000..44054eb657538aa5ce768af35b94c12b73989048 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001461312_374095872.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32c7a40bf29458dd983623d557164dd82888bd831e66d57181ec48eb267aee56 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001473984_377339904.pth b/checkpoint_p1/milestones/checkpoint_001473984_377339904.pth new file mode 100644 index 0000000000000000000000000000000000000000..fc9cc569af168484357a5f105e00aab734b241e0 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001473984_377339904.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d09579f7e1d283fbaa989f0c83b134f19628ea6014bf18810817d82f3bf914e5 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001486720_380600320.pth b/checkpoint_p1/milestones/checkpoint_001486720_380600320.pth new file mode 100644 index 0000000000000000000000000000000000000000..65d89c1ceabe403800628ba968b30284f1d344a2 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001486720_380600320.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1797a8f61d4ba6362b825824f71ccab6dbe86af90a848c000326d02a3860b732 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001499328_383827968.pth b/checkpoint_p1/milestones/checkpoint_001499328_383827968.pth new file mode 100644 index 0000000000000000000000000000000000000000..804b4a84d0122cb2ec667e1cab4d43a80e679339 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001499328_383827968.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d39a383ec24440e2c826c50a248b5bdcfd1738082d231dbc8a1bd3622a9958e +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001512064_387088384.pth b/checkpoint_p1/milestones/checkpoint_001512064_387088384.pth new file mode 100644 index 0000000000000000000000000000000000000000..a1aebc931142e65fe066e97f114714cc23cbda55 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001512064_387088384.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:867ab4ed4615695971efec5e855b831025496ca9befa007a8afab4ee3dfc4351 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001524736_390332416.pth b/checkpoint_p1/milestones/checkpoint_001524736_390332416.pth new file mode 100644 index 0000000000000000000000000000000000000000..31b83d0bba2862321620b95d2bc592865a41600e --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001524736_390332416.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f4fe7a83508ef91bee3df1177be3cee4d6b5130cf6d760d58fbe8f821ac0015 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001537376_393568256.pth b/checkpoint_p1/milestones/checkpoint_001537376_393568256.pth new file mode 100644 index 0000000000000000000000000000000000000000..837ff6cf10735998e284d985dd95c714d66d925a --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001537376_393568256.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae23704d437925926551fcacb3b9bc949fe6b4f90dff0f2815944fdd818c2f4a +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001550048_396812288.pth b/checkpoint_p1/milestones/checkpoint_001550048_396812288.pth new file mode 100644 index 0000000000000000000000000000000000000000..496a36b9983f80a15b7f1a475939430ffa82b417 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001550048_396812288.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54442ba19f6e1c40c9d25471099f31cbba8deb76ac43a261c98b50c70e566c3f +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001562656_400039936.pth b/checkpoint_p1/milestones/checkpoint_001562656_400039936.pth new file mode 100644 index 0000000000000000000000000000000000000000..7543afaf49e8a6b5b9d2a11fbd78c0eae5a9bab2 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001562656_400039936.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eafcddcfaa6c3abfb8150b3f293aeeae9dd72b7013a7f1a80dcdf080b47c1b83 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001575488_403324928.pth b/checkpoint_p1/milestones/checkpoint_001575488_403324928.pth new file mode 100644 index 0000000000000000000000000000000000000000..fc0218ccf9820fab0675302facc741799375fddf --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001575488_403324928.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:354b69e48a2b72457ff748488a22d6765c68af914cece5379fc5b0b05681370c +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001588192_406577152.pth b/checkpoint_p1/milestones/checkpoint_001588192_406577152.pth new file mode 100644 index 0000000000000000000000000000000000000000..5241bcf7674b1ff58cc4448491bb0287a8f3ce59 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001588192_406577152.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11a0b76a5a12f2907e7f7f1b6de8d5ec5a63e571a3cdc2c103ec9c94d13ad5b5 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001600864_409821184.pth b/checkpoint_p1/milestones/checkpoint_001600864_409821184.pth new file mode 100644 index 0000000000000000000000000000000000000000..d744b950d2755727b4187b3c881de09e35e5b50d --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001600864_409821184.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:498d939f31ddecdc90575c3ac7492bae6169e1e6e53de93f5038918fea8cfab5 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001613632_413089792.pth b/checkpoint_p1/milestones/checkpoint_001613632_413089792.pth new file mode 100644 index 0000000000000000000000000000000000000000..3f1a23dd1e62cb6f1438be8befb5d489241150ec --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001613632_413089792.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd6056b9d3c9c05907b7c027e970c47227a377f9b15c881313545a50f4c40f63 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001626336_416342016.pth b/checkpoint_p1/milestones/checkpoint_001626336_416342016.pth new file mode 100644 index 0000000000000000000000000000000000000000..2ceaff32979a23ada36ff0916eef0dc6ffc8ad2c --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001626336_416342016.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c4d815db9de1be1a2cbfadcaad21e17fca6af861d3a675c5a80292c3d9d8130 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001639008_419586048.pth b/checkpoint_p1/milestones/checkpoint_001639008_419586048.pth new file mode 100644 index 0000000000000000000000000000000000000000..b2d47aa81a449a8bbb7e60e6c52aa0c34cd5f09b --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001639008_419586048.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b4034fb8bedaace8d266b9830ec6675c1c14fb02543361db8c8f67559bdbb24 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001651744_422846464.pth b/checkpoint_p1/milestones/checkpoint_001651744_422846464.pth new file mode 100644 index 0000000000000000000000000000000000000000..a3556820cec191c1ef0dadc4c7e834049773f2ab --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001651744_422846464.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a905ae7928c46ad298d82fade44ad5bd36c8c33c5334cc3909e4bbc22f47af56 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001664512_426115072.pth b/checkpoint_p1/milestones/checkpoint_001664512_426115072.pth new file mode 100644 index 0000000000000000000000000000000000000000..e3466cdc62942a56381d5a8161aef64dd39bee2a --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001664512_426115072.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c18702da91f16caf9f3a61062f966692d6305def8e15a97613e389e099a2f55 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001677440_429424640.pth b/checkpoint_p1/milestones/checkpoint_001677440_429424640.pth new file mode 100644 index 0000000000000000000000000000000000000000..c4802d511610e11e70e7afdbc044c5378a21aacb --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001677440_429424640.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75114bcb69421bf1201ebf8176d77b520d0bf0807eebec335a29c21002114b90 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001690208_432693248.pth b/checkpoint_p1/milestones/checkpoint_001690208_432693248.pth new file mode 100644 index 0000000000000000000000000000000000000000..5fb0cec84ba1f1b9e79f752f6aa17a44db0992bb --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001690208_432693248.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e2f85dce373005d854cd7c7f6fbbd66970af166bea661dc6b8a20e39ee33cbd +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001703008_435970048.pth b/checkpoint_p1/milestones/checkpoint_001703008_435970048.pth new file mode 100644 index 0000000000000000000000000000000000000000..9f9c8e7372500be3fbebd48301a1e792961a622a --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001703008_435970048.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:861c85344fb3f4fb017b5aef4032bffe1147a91ace6d213c0be4937f8280fe9d +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001715616_439197696.pth b/checkpoint_p1/milestones/checkpoint_001715616_439197696.pth new file mode 100644 index 0000000000000000000000000000000000000000..3cd52949a8e5618efd5fdab4c875f772124c70b8 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001715616_439197696.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cb3db4f080f67c095ae041a958d4a52ac1c4a30489f9acaf95668919df03b86 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001728256_442433536.pth b/checkpoint_p1/milestones/checkpoint_001728256_442433536.pth new file mode 100644 index 0000000000000000000000000000000000000000..d687fc5772ebd1d66263739bc0000a4b582ae5f4 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001728256_442433536.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f281c3a2573255d2602e7e4899ca777349be64ba0be57c884a6d55cac11a4f3 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001740736_445628416.pth b/checkpoint_p1/milestones/checkpoint_001740736_445628416.pth new file mode 100644 index 0000000000000000000000000000000000000000..a3b2c7f1f8ad33c848db99dd7c143f1a1efa9289 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001740736_445628416.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2438b44b99da9c68ee51b6419336fc0adfb76fc9c55db447c87cc0ff9fa33475 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001753344_448856064.pth b/checkpoint_p1/milestones/checkpoint_001753344_448856064.pth new file mode 100644 index 0000000000000000000000000000000000000000..7a1dc29e3563e24d164d9e7a7c65a4f7ec09fbe5 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001753344_448856064.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d70479c7c2eaeff8d3db993193ea0978b5c22f619a296c0da573166c21486f29 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001766048_452108288.pth b/checkpoint_p1/milestones/checkpoint_001766048_452108288.pth new file mode 100644 index 0000000000000000000000000000000000000000..fad803f20ed9036b2bed549ed94512ecc849f6f6 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001766048_452108288.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf4c7f7e5092f54ccb8f25eb1cf7bb2ea36ac5ce568c6d787078372266af1b89 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001778624_455327744.pth b/checkpoint_p1/milestones/checkpoint_001778624_455327744.pth new file mode 100644 index 0000000000000000000000000000000000000000..afa67297c6b3f3842db480f615d77f214227b5df --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001778624_455327744.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c71c4f53be4806d76aa0815a687e4d9823106343ff36e65ae37c7d06189d53b +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001791392_458596352.pth b/checkpoint_p1/milestones/checkpoint_001791392_458596352.pth new file mode 100644 index 0000000000000000000000000000000000000000..a4cf33c5796123986797c0df7675d57bfa35c1c9 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001791392_458596352.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0c15a2762b735500470f60a5bcba2b7261cecf56b863fc9baf43171b2cbac7e +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001804096_461848576.pth b/checkpoint_p1/milestones/checkpoint_001804096_461848576.pth new file mode 100644 index 0000000000000000000000000000000000000000..bb05c507ce55d086012eb1a74dfb518fdf7e323b --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001804096_461848576.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4a9c4c5d8cc1511a63beae6f50dec46e9f44d8a8b273e5c129c659dfbae982c +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001816864_465117184.pth b/checkpoint_p1/milestones/checkpoint_001816864_465117184.pth new file mode 100644 index 0000000000000000000000000000000000000000..9f2427d85366ca8f0659b3fdf2d6de39bd99cb41 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001816864_465117184.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58d0a7c4172dcf858a18caa063b5a619ed9bce1070ab693fc675a8a4ed7ee86e +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001829632_468385792.pth b/checkpoint_p1/milestones/checkpoint_001829632_468385792.pth new file mode 100644 index 0000000000000000000000000000000000000000..c843617b48eb5b401553aa253fce1cc951162301 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001829632_468385792.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98330159ce7ab77addd7f905e881c19bc6b990c4d7262c55c38fa754e1a72666 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001842432_471662592.pth b/checkpoint_p1/milestones/checkpoint_001842432_471662592.pth new file mode 100644 index 0000000000000000000000000000000000000000..0d9e81b3a878b02ef95c576f127d1f54776aca06 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001842432_471662592.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:658299b0271a19d447f1d4f4c225eaa01e7ae07a4d9c7e93f86fd7d1cf1ec6d1 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001854976_474873856.pth b/checkpoint_p1/milestones/checkpoint_001854976_474873856.pth new file mode 100644 index 0000000000000000000000000000000000000000..f614d4387e837e859adb20435219b50d400f143d --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001854976_474873856.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee2abc52586c283e7265110cdbe7e9cd64f45f0c6500294f5f3865b18fd4dcf8 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001867712_478134272.pth b/checkpoint_p1/milestones/checkpoint_001867712_478134272.pth new file mode 100644 index 0000000000000000000000000000000000000000..0e02619b9dd8863245ceba580ee5613f87eadc03 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001867712_478134272.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:747135eddbab2141a3175160b774e7ff27d417963457b3f0abd5a9774bb95459 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001880352_481370112.pth b/checkpoint_p1/milestones/checkpoint_001880352_481370112.pth new file mode 100644 index 0000000000000000000000000000000000000000..33cd35b17bc221934571eac7338a2dd854055853 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001880352_481370112.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9e680fbb288df00ee544731c706256d1e1f7178f4772bff2557d3406de0fdb6 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001892992_484605952.pth b/checkpoint_p1/milestones/checkpoint_001892992_484605952.pth new file mode 100644 index 0000000000000000000000000000000000000000..d7ddfcd3103a5ee9c9ef5511dba89f83c0b1e3cc --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001892992_484605952.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ba9bf73919c45822550838022acf5dc01572c2d3d372a21cd580d80bc7b31dc +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001905632_487841792.pth b/checkpoint_p1/milestones/checkpoint_001905632_487841792.pth new file mode 100644 index 0000000000000000000000000000000000000000..6031f55a5e11dd95dbf8d597c39798f5924d03ee --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001905632_487841792.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa462c0877f0f8109fc57446be39cdd511e91c1ac39e86a4ed440bbb0b509ce3 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001918272_491077632.pth b/checkpoint_p1/milestones/checkpoint_001918272_491077632.pth new file mode 100644 index 0000000000000000000000000000000000000000..27f64e38f13abc8d2c62cf02287f11b1ff4db0fe --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001918272_491077632.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce3f4383735e06ceeb39832a603198671270ae60860d9d47345769a30efb0d8a +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001930912_494313472.pth b/checkpoint_p1/milestones/checkpoint_001930912_494313472.pth new file mode 100644 index 0000000000000000000000000000000000000000..cc2859fbda9169c2775d75e889bebc7dc4cc6521 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001930912_494313472.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3b7bf79c12503c958ec0ae1b5c760a958fd6fc5564bfef9218a49a50f012db1 +size 20797195 diff --git a/checkpoint_p1/milestones/checkpoint_001943488_497532928.pth b/checkpoint_p1/milestones/checkpoint_001943488_497532928.pth new file mode 100644 index 0000000000000000000000000000000000000000..296e89de682022cf037de544f9c000050d91bd80 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001943488_497532928.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61b1cfb04a7c44dfca31b444e5db7781b6693718ce0f5b82e4fb2a2de70c5e5e +size 20797195 diff --git a/config.json b/config.json index 6e900a65fa76f71f8431c175bd2bcfdc329a11c7..901f5e8c83a91f5f3b5abd2da88f901983d5ecb0 100644 --- a/config.json +++ b/config.json @@ -4,7 +4,7 @@ "env": "atari_battlezone", "experiment": "atari_battlezone_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_battlezone --experiment=atari_battlezone_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_battlezone --wandb_job_type=SF --wandb_tags=atari", + "command_line": "--algo=APPO --env=atari_battlezone --experiment=atari_battlezone_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_battlezone --wandb_job_type=SF --wandb_tags=atari", "cli_args": { "algo": "APPO", "env": "atari_battlezone", "experiment": "atari_battlezone_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_battlezone_APPO_20231008_235831_461686" + "wandb_unique_id": "atari_battlezone_APPO_20231017_133154_234556" } \ No newline at end of file diff --git a/git.diff b/git.diff index 960bf7b013feefe7b56842bffdcf222f0bdf7dbd..04d6106ed29e6d5533f1bb411d2f14b9e03d4cf0 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 sha256:9e9ff00161b722fb8ea75da0cfd25893247cd6348202e29ae3a6028f21deb877 +size 83373149 diff --git a/replay.mp4 b/replay.mp4 index 996f6a138cab7969d0cc5c97d6e80a54a8f351f6..e3fcee4807d2cbd4c7256c586e9c68a1d6a0ff19 100644 --- a/replay.mp4 +++ b/replay.mp4 @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:388e40f9fa08a14742da4e926dc9a83ab3aefe3421407e8f42a432243a45fe93 -size 8995184 +oid sha256:8e32a00c85ba54cd0f242ae2bcd13a28b2e738f15e8aed35a44e5d9a268e355c +size 15250724 diff --git a/sf_log.txt b/sf_log.txt index b07ccb86ba0db0a48cba24e6b8ce098eed690847..2149c21481564a80fba7b0399bac364dc96961d9 100644 --- a/sf_log.txt +++ b/sf_log.txt @@ -1,26491 +1,3 @@ -[2023-10-08 23:58:37,865][87372] Saving configuration to ./train_atari/atari_battlezone_APPO/config.json... -[2023-10-08 23:58:38,182][87372] Rollout worker 0 uses device cpu -[2023-10-08 23:58:38,183][87372] Rollout worker 1 uses device cpu -[2023-10-08 23:58:38,183][87372] Rollout worker 2 uses device cpu -[2023-10-08 23:58:38,184][87372] Rollout worker 3 uses device cpu -[2023-10-08 23:58:38,184][87372] Rollout worker 4 uses device cpu -[2023-10-08 23:58:38,185][87372] Rollout worker 5 uses device cpu -[2023-10-08 23:58:38,185][87372] Rollout worker 6 uses device cpu -[2023-10-08 23:58:38,186][87372] Rollout worker 7 uses device cpu -[2023-10-08 23:58:38,186][87372] Rollout worker 8 uses device cpu -[2023-10-08 23:58:38,187][87372] Rollout worker 9 uses device cpu -[2023-10-08 23:58:38,187][87372] Rollout worker 10 uses device cpu -[2023-10-08 23:58:38,188][87372] Rollout worker 11 uses device cpu -[2023-10-08 23:58:38,188][87372] Rollout worker 12 uses device cpu -[2023-10-08 23:58:38,189][87372] Rollout worker 13 uses device cpu -[2023-10-08 23:58:38,189][87372] Rollout worker 14 uses device cpu -[2023-10-08 23:58:38,189][87372] Rollout worker 15 uses device cpu -[2023-10-08 23:58:38,481][87372] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2023-10-08 23:58:38,482][87372] InferenceWorker_p0-w0: min num requests: 2 -[2023-10-08 23:58:38,485][87372] Using GPUs [1] for process 1 (actually maps to GPUs [1]) -[2023-10-08 23:58:38,485][87372] InferenceWorker_p1-w0: min num requests: 2 -[2023-10-08 23:58:38,532][87372] Starting all processes... -[2023-10-08 23:58:38,532][87372] Starting process learner_proc0 -[2023-10-08 23:58:40,185][87372] Starting process learner_proc1 -[2023-10-08 23:58:40,190][88088] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2023-10-08 23:58:40,190][88088] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0 -[2023-10-08 23:58:40,209][88088] Num visible devices: 1 -[2023-10-08 23:58:40,266][88088] Setting fixed seed 1234 -[2023-10-08 23:58:40,267][88088] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2023-10-08 23:58:40,267][88088] Initializing actor-critic model on device cuda:0 -[2023-10-08 23:58:40,268][88088] RunningMeanStd input shape: (4, 84, 84) -[2023-10-08 23:58:40,268][88088] RunningMeanStd input shape: (1,) -[2023-10-08 23:58:40,280][88088] ConvEncoder: input_channels=4 -[2023-10-08 23:58:40,417][88088] Conv encoder output size: 512 -[2023-10-08 23:58:40,419][88088] Created Actor Critic model with architecture: -[2023-10-08 23:58:40,419][88088] 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) - ) -) -[2023-10-08 23:58:40,981][88088] Using optimizer -[2023-10-08 23:58:40,981][88088] No checkpoints found -[2023-10-08 23:58:40,982][88088] Did not load from checkpoint, starting from scratch! -[2023-10-08 23:58:40,982][88088] Initialized policy 0 weights for model version 0 -[2023-10-08 23:58:40,983][88088] LearnerWorker_p0 finished initialization! -[2023-10-08 23:58:40,984][88088] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2023-10-08 23:58:41,877][87372] Starting all processes... -[2023-10-08 23:58:41,881][88168] Using GPUs [1] for process 1 (actually maps to GPUs [1]) -[2023-10-08 23:58:41,881][88168] Set environment var CUDA_VISIBLE_DEVICES to '1' (GPU indices [1]) for learning process 1 -[2023-10-08 23:58:41,886][87372] Starting process inference_proc0-0 -[2023-10-08 23:58:41,886][87372] Starting process inference_proc1-0 -[2023-10-08 23:58:41,887][87372] Starting process rollout_proc0 -[2023-10-08 23:58:41,899][88168] Num visible devices: 1 -[2023-10-08 23:58:41,887][87372] Starting process rollout_proc1 -[2023-10-08 23:58:41,887][87372] Starting process rollout_proc2 -[2023-10-08 23:58:41,916][88168] Setting fixed seed 1234 -[2023-10-08 23:58:41,917][88168] Using GPUs [0] for process 1 (actually maps to GPUs [1]) -[2023-10-08 23:58:41,917][88168] Initializing actor-critic model on device cuda:0 -[2023-10-08 23:58:41,888][87372] Starting process rollout_proc3 -[2023-10-08 23:58:41,918][88168] RunningMeanStd input shape: (4, 84, 84) -[2023-10-08 23:58:41,918][88168] RunningMeanStd input shape: (1,) -[2023-10-08 23:58:41,892][87372] Starting process rollout_proc4 -[2023-10-08 23:58:41,894][87372] Starting process rollout_proc5 -[2023-10-08 23:58:41,894][87372] Starting process rollout_proc6 -[2023-10-08 23:58:41,894][87372] Starting process rollout_proc7 -[2023-10-08 23:58:41,899][87372] Starting process rollout_proc8 -[2023-10-08 23:58:41,930][88168] ConvEncoder: input_channels=4 -[2023-10-08 23:58:41,899][87372] Starting process rollout_proc9 -[2023-10-08 23:58:41,900][87372] Starting process rollout_proc10 -[2023-10-08 23:58:41,911][87372] Starting process rollout_proc11 -[2023-10-08 23:58:41,911][87372] Starting process rollout_proc12 -[2023-10-08 23:58:41,911][87372] Starting process rollout_proc13 -[2023-10-08 23:58:42,232][88168] Conv encoder output size: 512 -[2023-10-08 23:58:42,235][88168] Created Actor Critic model with architecture: -[2023-10-08 23:58:42,235][88168] 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) - ) -) -[2023-10-08 23:58:43,079][88168] Using optimizer -[2023-10-08 23:58:43,079][88168] No checkpoints found -[2023-10-08 23:58:43,079][88168] Did not load from checkpoint, starting from scratch! -[2023-10-08 23:58:43,080][88168] Initialized policy 1 weights for model version 0 -[2023-10-08 23:58:43,081][88168] LearnerWorker_p1 finished initialization! -[2023-10-08 23:58:43,081][88168] Using GPUs [0] for process 1 (actually maps to GPUs [1]) -[2023-10-08 23:58:44,107][87372] Starting process rollout_proc14 -[2023-10-08 23:58:44,113][88326] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2023-10-08 23:58:44,113][88326] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0 -[2023-10-08 23:58:44,131][88326] Num visible devices: 1 -[2023-10-08 23:58:44,142][87372] Starting process rollout_proc15 -[2023-10-08 23:58:44,151][88327] Using GPUs [1] for process 1 (actually maps to GPUs [1]) -[2023-10-08 23:58:44,151][88327] Set environment var CUDA_VISIBLE_DEVICES to '1' (GPU indices [1]) for inference process 1 -[2023-10-08 23:58:44,167][88371] Worker 9 uses CPU cores [18, 19] -[2023-10-08 23:58:44,169][88372] Worker 12 uses CPU cores [24, 25] -[2023-10-08 23:58:44,170][88327] Num visible devices: 1 -[2023-10-08 23:58:44,203][88359] Worker 0 uses CPU cores [0, 1] -[2023-10-08 23:58:44,224][88360] Worker 1 uses CPU cores [2, 3] -[2023-10-08 23:58:44,250][88365] Worker 4 uses CPU cores [8, 9] -[2023-10-08 23:58:44,374][88362] Worker 2 uses CPU cores [4, 5] -[2023-10-08 23:58:44,389][88370] Worker 11 uses CPU cores [22, 23] -[2023-10-08 23:58:44,508][88366] Worker 6 uses CPU cores [12, 13] -[2023-10-08 23:58:44,539][88363] Worker 3 uses CPU cores [6, 7] -[2023-10-08 23:58:44,647][88364] Worker 5 uses CPU cores [10, 11] -[2023-10-08 23:58:44,680][88369] Worker 10 uses CPU cores [20, 21] -[2023-10-08 23:58:44,743][88368] Worker 8 uses CPU cores [16, 17] -[2023-10-08 23:58:44,797][88367] Worker 7 uses CPU cores [14, 15] -[2023-10-08 23:58:44,843][88373] Worker 13 uses CPU cores [26, 27] -[2023-10-08 23:58:44,943][88327] RunningMeanStd input shape: (4, 84, 84) -[2023-10-08 23:58:44,943][88327] RunningMeanStd input shape: (1,) -[2023-10-08 23:58:44,955][88327] ConvEncoder: input_channels=4 -[2023-10-08 23:58:45,025][88326] RunningMeanStd input shape: (4, 84, 84) -[2023-10-08 23:58:45,026][88326] RunningMeanStd input shape: (1,) -[2023-10-08 23:58:45,037][88326] ConvEncoder: input_channels=4 -[2023-10-08 23:58:45,062][88327] Conv encoder output size: 512 -[2023-10-08 23:58:45,142][88326] Conv encoder output size: 512 -[2023-10-08 23:58:46,013][89058] Worker 14 uses CPU cores [28, 29] -[2023-10-08 23:58:46,127][87372] Inference worker 1-0 is ready! -[2023-10-08 23:58:46,128][87372] Inference worker 0-0 is ready! -[2023-10-08 23:58:46,129][89096] Worker 15 uses CPU cores [30, 31] -[2023-10-08 23:58:46,129][87372] All inference workers are ready! Signal rollout workers to start! -[2023-10-08 23:58:46,130][88367] EnvRunner 7-0 uses policy 1 -[2023-10-08 23:58:46,130][88366] EnvRunner 6-0 uses policy 0 -[2023-10-08 23:58:46,131][88365] EnvRunner 4-0 uses policy 0 -[2023-10-08 23:58:46,131][88362] EnvRunner 2-0 uses policy 0 -[2023-10-08 23:58:46,131][88373] EnvRunner 13-0 uses policy 1 -[2023-10-08 23:58:46,131][88368] EnvRunner 8-0 uses policy 0 -[2023-10-08 23:58:46,131][88371] EnvRunner 9-0 uses policy 1 -[2023-10-08 23:58:46,131][87372] 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) -[2023-10-08 23:58:46,131][88359] EnvRunner 0-0 uses policy 0 -[2023-10-08 23:58:46,131][88363] EnvRunner 3-0 uses policy 1 -[2023-10-08 23:58:46,131][88364] EnvRunner 5-0 uses policy 1 -[2023-10-08 23:58:46,131][88369] EnvRunner 10-0 uses policy 0 -[2023-10-08 23:58:46,131][88370] EnvRunner 11-0 uses policy 1 -[2023-10-08 23:58:46,131][88372] EnvRunner 12-0 uses policy 0 -[2023-10-08 23:58:46,131][88360] EnvRunner 1-0 uses policy 1 -[2023-10-08 23:58:46,208][89058] EnvRunner 14-0 uses policy 0 -[2023-10-08 23:58:46,252][89096] EnvRunner 15-0 uses policy 1 -[2023-10-08 23:58:48,470][87372] Heartbeat connected on Batcher_0 -[2023-10-08 23:58:48,472][87372] Heartbeat connected on LearnerWorker_p0 -[2023-10-08 23:58:48,475][87372] Heartbeat connected on Batcher_1 -[2023-10-08 23:58:48,478][87372] Heartbeat connected on LearnerWorker_p1 -[2023-10-08 23:58:48,485][87372] Heartbeat connected on InferenceWorker_p0-w0 -[2023-10-08 23:58:48,490][87372] Heartbeat connected on InferenceWorker_p1-w0 -[2023-10-08 23:58:48,491][87372] Heartbeat connected on RolloutWorker_w0 -[2023-10-08 23:58:48,492][87372] Heartbeat connected on RolloutWorker_w1 -[2023-10-08 23:58:48,497][87372] Heartbeat connected on RolloutWorker_w3 -[2023-10-08 23:58:48,499][87372] Heartbeat connected on RolloutWorker_w2 -[2023-10-08 23:58:48,504][87372] Heartbeat connected on RolloutWorker_w5 -[2023-10-08 23:58:48,505][87372] Heartbeat connected on RolloutWorker_w4 -[2023-10-08 23:58:48,507][87372] Heartbeat connected on RolloutWorker_w6 -[2023-10-08 23:58:48,508][87372] Heartbeat connected on RolloutWorker_w7 -[2023-10-08 23:58:48,513][87372] Heartbeat connected on RolloutWorker_w8 -[2023-10-08 23:58:48,514][87372] Heartbeat connected on RolloutWorker_w9 -[2023-10-08 23:58:48,521][87372] Heartbeat connected on RolloutWorker_w10 -[2023-10-08 23:58:48,522][87372] Heartbeat connected on RolloutWorker_w12 -[2023-10-08 23:58:48,523][87372] Heartbeat connected on RolloutWorker_w11 -[2023-10-08 23:58:48,526][87372] Heartbeat connected on RolloutWorker_w13 -[2023-10-08 23:58:48,530][87372] Heartbeat connected on RolloutWorker_w15 -[2023-10-08 23:58:48,532][87372] Heartbeat connected on RolloutWorker_w14 -[2023-10-08 23:58:48,974][87372] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 403.0, 1: 251.1. Samples: 1860. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) -[2023-10-08 23:58:48,975][87372] Avg episode reward: [(0, '1.000'), (1, '1.250')] -[2023-10-08 23:58:53,974][87372] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 888.9, 1: 830.5. Samples: 13486. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) -[2023-10-08 23:58:53,975][87372] Avg episode reward: [(0, '0.302'), (1, '0.296')] -[2023-10-08 23:58:56,090][88326] Updated weights for policy 0, policy_version 10 (0.0007) -[2023-10-08 23:58:56,452][88326] Updated weights for policy 0, policy_version 20 (0.0007) -[2023-10-08 23:58:56,655][88327] Updated weights for policy 1, policy_version 10 (0.0009) -[2023-10-08 23:58:56,815][88326] Updated weights for policy 0, policy_version 30 (0.0007) -[2023-10-08 23:58:57,013][88327] Updated weights for policy 1, policy_version 20 (0.0007) -[2023-10-08 23:58:57,388][88327] Updated weights for policy 1, policy_version 30 (0.0008) -[2023-10-08 23:58:58,974][87372] Fps is (10 sec: 6553.6, 60 sec: 5102.7, 300 sec: 5102.7). Total num frames: 65536. Throughput: 0: 1189.6, 1: 1187.1. Samples: 30524. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-08 23:58:58,975][87372] Avg episode reward: [(0, '0.354'), (1, '0.271')] -[2023-10-08 23:58:59,483][88326] Updated weights for policy 0, policy_version 40 (0.0008) -[2023-10-08 23:58:59,699][88327] Updated weights for policy 1, policy_version 40 (0.0008) -[2023-10-08 23:58:59,849][88326] Updated weights for policy 0, policy_version 50 (0.0007) -[2023-10-08 23:59:00,068][88327] Updated weights for policy 1, policy_version 50 (0.0007) -[2023-10-08 23:59:00,228][88326] Updated weights for policy 0, policy_version 60 (0.0008) -[2023-10-08 23:59:00,426][88327] Updated weights for policy 1, policy_version 60 (0.0009) -[2023-10-08 23:59:03,484][88326] Updated weights for policy 0, policy_version 70 (0.0008) -[2023-10-08 23:59:03,859][88326] Updated weights for policy 0, policy_version 80 (0.0009) -[2023-10-08 23:59:03,974][87372] Fps is (10 sec: 13107.3, 60 sec: 7345.7, 300 sec: 7345.7). Total num frames: 131072. Throughput: 0: 1442.0, 1: 1416.9. Samples: 51012. Policy #0 lag: (min: 33.0, avg: 33.0, max: 33.0) -[2023-10-08 23:59:03,975][87372] Avg episode reward: [(0, '0.330'), (1, '0.270')] -[2023-10-08 23:59:04,074][88327] Updated weights for policy 1, policy_version 70 (0.0008) -[2023-10-08 23:59:04,223][88326] Updated weights for policy 0, policy_version 90 (0.0008) -[2023-10-08 23:59:04,425][88327] Updated weights for policy 1, policy_version 80 (0.0007) -[2023-10-08 23:59:04,797][88327] Updated weights for policy 1, policy_version 90 (0.0008) -[2023-10-08 23:59:07,706][88326] Updated weights for policy 0, policy_version 100 (0.0007) -[2023-10-08 23:59:08,078][88326] Updated weights for policy 0, policy_version 110 (0.0009) -[2023-10-08 23:59:08,362][88327] Updated weights for policy 1, policy_version 100 (0.0010) -[2023-10-08 23:59:08,453][88326] Updated weights for policy 0, policy_version 120 (0.0008) -[2023-10-08 23:59:08,722][88327] Updated weights for policy 1, policy_version 110 (0.0008) -[2023-10-08 23:59:08,974][87372] Fps is (10 sec: 16384.0, 60 sec: 10041.2, 300 sec: 10041.2). Total num frames: 229376. Throughput: 0: 1336.1, 1: 1305.1. Samples: 60334. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-08 23:59:08,975][87372] Avg episode reward: [(0, '0.410'), (1, '0.390')] -[2023-10-08 23:59:08,976][88088] Saving new best policy, reward=0.410! -[2023-10-08 23:59:09,091][88327] Updated weights for policy 1, policy_version 120 (0.0008) -[2023-10-08 23:59:12,661][88326] Updated weights for policy 0, policy_version 130 (0.0008) -[2023-10-08 23:59:13,027][88326] Updated weights for policy 0, policy_version 140 (0.0007) -[2023-10-08 23:59:13,274][88327] Updated weights for policy 1, policy_version 130 (0.0009) -[2023-10-08 23:59:13,411][88326] Updated weights for policy 0, policy_version 150 (0.0007) -[2023-10-08 23:59:13,639][88327] Updated weights for policy 1, policy_version 140 (0.0008) -[2023-10-08 23:59:13,775][88326] Updated weights for policy 0, policy_version 160 (0.0009) -[2023-10-08 23:59:13,975][87372] Fps is (10 sec: 16383.4, 60 sec: 10591.7, 300 sec: 10591.7). Total num frames: 294912. Throughput: 0: 1471.7, 1: 1446.1. Samples: 81244. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) -[2023-10-08 23:59:13,976][87372] Avg episode reward: [(0, '0.410'), (1, '0.450')] -[2023-10-08 23:59:14,004][88327] Updated weights for policy 1, policy_version 150 (0.0009) -[2023-10-08 23:59:14,369][88168] Saving new best policy, reward=0.450! -[2023-10-08 23:59:14,371][88327] Updated weights for policy 1, policy_version 160 (0.0008) -[2023-10-08 23:59:17,900][88326] Updated weights for policy 0, policy_version 170 (0.0008) -[2023-10-08 23:59:18,229][88327] Updated weights for policy 1, policy_version 170 (0.0008) -[2023-10-08 23:59:18,259][88326] Updated weights for policy 0, policy_version 180 (0.0008) -[2023-10-08 23:59:18,601][88327] Updated weights for policy 1, policy_version 180 (0.0009) -[2023-10-08 23:59:18,640][88326] Updated weights for policy 0, policy_version 190 (0.0007) -[2023-10-08 23:59:18,966][88327] Updated weights for policy 1, policy_version 190 (0.0011) -[2023-10-08 23:59:18,974][87372] Fps is (10 sec: 13106.8, 60 sec: 10974.7, 300 sec: 10974.7). Total num frames: 360448. Throughput: 0: 1540.0, 1: 1540.8. Samples: 101186. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-08 23:59:18,975][87372] Avg episode reward: [(0, '0.420'), (1, '0.420')] -[2023-10-08 23:59:18,982][88088] Saving new best policy, reward=0.420! -[2023-10-08 23:59:22,645][88326] Updated weights for policy 0, policy_version 200 (0.0007) -[2023-10-08 23:59:22,904][88327] Updated weights for policy 1, policy_version 200 (0.0008) -[2023-10-08 23:59:23,019][88326] Updated weights for policy 0, policy_version 210 (0.0008) -[2023-10-08 23:59:23,265][88327] Updated weights for policy 1, policy_version 210 (0.0008) -[2023-10-08 23:59:23,396][88326] Updated weights for policy 0, policy_version 220 (0.0008) -[2023-10-08 23:59:23,629][88327] Updated weights for policy 1, policy_version 220 (0.0008) -[2023-10-08 23:59:23,974][87372] Fps is (10 sec: 16384.7, 60 sec: 12122.4, 300 sec: 12122.4). Total num frames: 458752. Throughput: 0: 1477.9, 1: 1468.0. Samples: 111480. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-08 23:59:23,974][87372] Avg episode reward: [(0, '0.500'), (1, '0.370')] -[2023-10-08 23:59:23,975][88088] Saving new best policy, reward=0.500! -[2023-10-08 23:59:27,613][88327] Updated weights for policy 1, policy_version 230 (0.0009) -[2023-10-08 23:59:27,646][88326] Updated weights for policy 0, policy_version 230 (0.0008) -[2023-10-08 23:59:27,979][88327] Updated weights for policy 1, policy_version 240 (0.0009) -[2023-10-08 23:59:28,006][88326] Updated weights for policy 0, policy_version 240 (0.0009) -[2023-10-08 23:59:28,346][88327] Updated weights for policy 1, policy_version 250 (0.0007) -[2023-10-08 23:59:28,380][88326] Updated weights for policy 0, policy_version 250 (0.0007) -[2023-10-08 23:59:28,974][87372] Fps is (10 sec: 16384.6, 60 sec: 12237.3, 300 sec: 12237.3). Total num frames: 524288. Throughput: 0: 1548.4, 1: 1544.8. Samples: 132524. Policy #0 lag: (min: 4.0, avg: 8.8, max: 36.0) -[2023-10-08 23:59:28,975][87372] Avg episode reward: [(0, '0.600'), (1, '0.530')] -[2023-10-08 23:59:28,976][88088] Saving new best policy, reward=0.600! -[2023-10-08 23:59:28,976][88168] Saving new best policy, reward=0.530! -[2023-10-08 23:59:32,401][88327] Updated weights for policy 1, policy_version 260 (0.0008) -[2023-10-08 23:59:32,580][88326] Updated weights for policy 0, policy_version 260 (0.0009) -[2023-10-08 23:59:32,762][88327] Updated weights for policy 1, policy_version 270 (0.0008) -[2023-10-08 23:59:32,951][88326] Updated weights for policy 0, policy_version 270 (0.0008) -[2023-10-08 23:59:33,123][88327] Updated weights for policy 1, policy_version 280 (0.0008) -[2023-10-08 23:59:33,320][88326] Updated weights for policy 0, policy_version 280 (0.0007) -[2023-10-08 23:59:33,974][87372] Fps is (10 sec: 13106.7, 60 sec: 12328.2, 300 sec: 12328.2). Total num frames: 589824. Throughput: 0: 1660.3, 1: 1669.0. Samples: 151678. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-08 23:59:33,975][87372] Avg episode reward: [(0, '0.570'), (1, '0.640')] -[2023-10-08 23:59:33,984][88168] Saving new best policy, reward=0.640! -[2023-10-08 23:59:37,291][88327] Updated weights for policy 1, policy_version 290 (0.0009) -[2023-10-08 23:59:37,401][88326] Updated weights for policy 0, policy_version 290 (0.0009) -[2023-10-08 23:59:37,681][88327] Updated weights for policy 1, policy_version 300 (0.0008) -[2023-10-08 23:59:37,796][88326] Updated weights for policy 0, policy_version 300 (0.0007) -[2023-10-08 23:59:38,042][88327] Updated weights for policy 1, policy_version 310 (0.0008) -[2023-10-08 23:59:38,165][88326] Updated weights for policy 0, policy_version 310 (0.0007) -[2023-10-08 23:59:38,402][88327] Updated weights for policy 1, policy_version 320 (0.0009) -[2023-10-08 23:59:38,527][88326] Updated weights for policy 0, policy_version 320 (0.0007) -[2023-10-08 23:59:38,974][87372] Fps is (10 sec: 13107.1, 60 sec: 12401.9, 300 sec: 12401.9). Total num frames: 655360. Throughput: 0: 1644.7, 1: 1660.3. Samples: 162212. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-08 23:59:38,975][87372] Avg episode reward: [(0, '0.630'), (1, '0.830')] -[2023-10-08 23:59:38,975][88088] Saving new best policy, reward=0.630! -[2023-10-08 23:59:38,976][88168] Saving new best policy, reward=0.830! -[2023-10-08 23:59:42,529][88327] Updated weights for policy 1, policy_version 330 (0.0009) -[2023-10-08 23:59:42,629][88326] Updated weights for policy 0, policy_version 330 (0.0009) -[2023-10-08 23:59:42,889][88327] Updated weights for policy 1, policy_version 340 (0.0007) -[2023-10-08 23:59:42,999][88326] Updated weights for policy 0, policy_version 340 (0.0009) -[2023-10-08 23:59:43,262][88327] Updated weights for policy 1, policy_version 350 (0.0008) -[2023-10-08 23:59:43,359][88326] Updated weights for policy 0, policy_version 350 (0.0007) -[2023-10-08 23:59:43,974][87372] Fps is (10 sec: 13107.7, 60 sec: 12462.9, 300 sec: 12462.9). Total num frames: 720896. Throughput: 0: 1688.8, 1: 1698.0. Samples: 182932. Policy #0 lag: (min: 26.0, avg: 27.7, max: 54.0) -[2023-10-08 23:59:43,975][87372] Avg episode reward: [(0, '0.760'), (1, '0.770')] -[2023-10-08 23:59:43,975][88088] Saving new best policy, reward=0.760! -[2023-10-08 23:59:47,181][88327] Updated weights for policy 1, policy_version 360 (0.0008) -[2023-10-08 23:59:47,370][88326] Updated weights for policy 0, policy_version 360 (0.0009) -[2023-10-08 23:59:47,547][88327] Updated weights for policy 1, policy_version 370 (0.0008) -[2023-10-08 23:59:47,741][88326] Updated weights for policy 0, policy_version 370 (0.0011) -[2023-10-08 23:59:47,910][88327] Updated weights for policy 1, policy_version 380 (0.0008) -[2023-10-08 23:59:48,110][88326] Updated weights for policy 0, policy_version 380 (0.0008) -[2023-10-08 23:59:48,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12514.2). Total num frames: 786432. Throughput: 0: 1661.7, 1: 1679.2. Samples: 201354. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-08 23:59:48,975][87372] Avg episode reward: [(0, '0.880'), (1, '0.800')] -[2023-10-08 23:59:48,982][88088] Saving new best policy, reward=0.880! -[2023-10-08 23:59:51,744][88327] Updated weights for policy 1, policy_version 390 (0.0008) -[2023-10-08 23:59:52,114][88327] Updated weights for policy 1, policy_version 400 (0.0009) -[2023-10-08 23:59:52,221][88326] Updated weights for policy 0, policy_version 390 (0.0008) -[2023-10-08 23:59:52,478][88327] Updated weights for policy 1, policy_version 410 (0.0009) -[2023-10-08 23:59:52,592][88326] Updated weights for policy 0, policy_version 400 (0.0008) -[2023-10-08 23:59:52,971][88326] Updated weights for policy 0, policy_version 410 (0.0010) -[2023-10-08 23:59:53,974][87372] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 12557.9). Total num frames: 851968. Throughput: 0: 1679.0, 1: 1710.0. Samples: 212836. Policy #0 lag: (min: 22.0, avg: 27.2, max: 54.0) -[2023-10-08 23:59:53,974][87372] Avg episode reward: [(0, '0.960'), (1, '0.800')] -[2023-10-08 23:59:53,975][88088] Saving new best policy, reward=0.960! -[2023-10-08 23:59:56,630][88327] Updated weights for policy 1, policy_version 420 (0.0007) -[2023-10-08 23:59:56,999][88327] Updated weights for policy 1, policy_version 430 (0.0007) -[2023-10-08 23:59:57,046][88326] Updated weights for policy 0, policy_version 420 (0.0009) -[2023-10-08 23:59:57,370][88327] Updated weights for policy 1, policy_version 440 (0.0008) -[2023-10-08 23:59:57,411][88326] Updated weights for policy 0, policy_version 430 (0.0008) -[2023-10-08 23:59:57,777][88326] Updated weights for policy 0, policy_version 440 (0.0009) -[2023-10-08 23:59:58,974][87372] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 12595.6). Total num frames: 917504. Throughput: 0: 1669.4, 1: 1692.7. Samples: 232538. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-08 23:59:58,975][87372] Avg episode reward: [(0, '0.950'), (1, '0.770')] -[2023-10-09 00:00:01,363][88327] Updated weights for policy 1, policy_version 450 (0.0009) -[2023-10-09 00:00:01,725][88327] Updated weights for policy 1, policy_version 460 (0.0009) -[2023-10-09 00:00:01,948][88326] Updated weights for policy 0, policy_version 450 (0.0011) -[2023-10-09 00:00:02,093][88327] Updated weights for policy 1, policy_version 470 (0.0009) -[2023-10-09 00:00:02,306][88326] Updated weights for policy 0, policy_version 460 (0.0007) -[2023-10-09 00:00:02,452][88327] Updated weights for policy 1, policy_version 480 (0.0009) -[2023-10-09 00:00:02,673][88326] Updated weights for policy 0, policy_version 470 (0.0007) -[2023-10-09 00:00:03,045][88326] Updated weights for policy 0, policy_version 480 (0.0009) -[2023-10-09 00:00:03,974][87372] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 12628.5). Total num frames: 983040. Throughput: 0: 1662.6, 1: 1685.6. Samples: 251854. Policy #0 lag: (min: 1.0, avg: 12.8, max: 33.0) -[2023-10-09 00:00:03,975][87372] Avg episode reward: [(0, '0.980'), (1, '0.720')] -[2023-10-09 00:00:03,984][88088] Saving new best policy, reward=0.980! -[2023-10-09 00:00:06,368][88327] Updated weights for policy 1, policy_version 490 (0.0009) -[2023-10-09 00:00:06,732][88327] Updated weights for policy 1, policy_version 500 (0.0008) -[2023-10-09 00:00:07,070][88326] Updated weights for policy 0, policy_version 490 (0.0008) -[2023-10-09 00:00:07,103][88327] Updated weights for policy 1, policy_version 510 (0.0008) -[2023-10-09 00:00:07,444][88326] Updated weights for policy 0, policy_version 500 (0.0008) -[2023-10-09 00:00:07,807][88326] Updated weights for policy 0, policy_version 510 (0.0008) -[2023-10-09 00:00:08,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 12657.3). Total num frames: 1048576. Throughput: 0: 1671.8, 1: 1706.7. Samples: 263514. Policy #0 lag: (min: 26.0, avg: 46.0, max: 58.0) -[2023-10-09 00:00:08,975][87372] Avg episode reward: [(0, '0.930'), (1, '0.780')] -[2023-10-09 00:00:11,161][88327] Updated weights for policy 1, policy_version 520 (0.0008) -[2023-10-09 00:00:11,531][88327] Updated weights for policy 1, policy_version 530 (0.0008) -[2023-10-09 00:00:11,801][88326] Updated weights for policy 0, policy_version 520 (0.0009) -[2023-10-09 00:00:11,898][88327] Updated weights for policy 1, policy_version 540 (0.0010) -[2023-10-09 00:00:12,182][88326] Updated weights for policy 0, policy_version 530 (0.0009) -[2023-10-09 00:00:12,558][88326] Updated weights for policy 0, policy_version 540 (0.0008) -[2023-10-09 00:00:13,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 12682.9). Total num frames: 1114112. Throughput: 0: 1653.5, 1: 1680.1. Samples: 282534. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-09 00:00:13,975][87372] Avg episode reward: [(0, '0.950'), (1, '0.940')] -[2023-10-09 00:00:13,977][88168] Saving new best policy, reward=0.940! -[2023-10-09 00:00:15,897][88327] Updated weights for policy 1, policy_version 550 (0.0009) -[2023-10-09 00:00:16,260][88327] Updated weights for policy 1, policy_version 560 (0.0007) -[2023-10-09 00:00:16,472][88326] Updated weights for policy 0, policy_version 550 (0.0008) -[2023-10-09 00:00:16,626][88327] Updated weights for policy 1, policy_version 570 (0.0007) -[2023-10-09 00:00:16,848][88326] Updated weights for policy 0, policy_version 560 (0.0008) -[2023-10-09 00:00:17,213][88326] Updated weights for policy 0, policy_version 570 (0.0007) -[2023-10-09 00:00:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 12705.8). Total num frames: 1179648. Throughput: 0: 1661.2, 1: 1701.5. Samples: 302998. Policy #0 lag: (min: 31.0, avg: 35.1, max: 63.0) -[2023-10-09 00:00:18,975][87372] Avg episode reward: [(0, '0.990'), (1, '1.080')] -[2023-10-09 00:00:18,984][88088] Saving new best policy, reward=0.990! -[2023-10-09 00:00:18,985][88168] Saving new best policy, reward=1.080! -[2023-10-09 00:00:20,615][88327] Updated weights for policy 1, policy_version 580 (0.0008) -[2023-10-09 00:00:20,980][88327] Updated weights for policy 1, policy_version 590 (0.0009) -[2023-10-09 00:00:21,252][88326] Updated weights for policy 0, policy_version 580 (0.0007) -[2023-10-09 00:00:21,345][88327] Updated weights for policy 1, policy_version 600 (0.0008) -[2023-10-09 00:00:21,628][88326] Updated weights for policy 0, policy_version 590 (0.0008) -[2023-10-09 00:00:21,990][88326] Updated weights for policy 0, policy_version 600 (0.0011) -[2023-10-09 00:00:23,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12726.3). Total num frames: 1245184. Throughput: 0: 1676.0, 1: 1697.2. Samples: 314002. Policy #0 lag: (min: 17.0, avg: 24.3, max: 49.0) -[2023-10-09 00:00:23,975][87372] Avg episode reward: [(0, '0.970'), (1, '1.160')] -[2023-10-09 00:00:23,977][88168] Saving new best policy, reward=1.160! -[2023-10-09 00:00:25,480][88327] Updated weights for policy 1, policy_version 610 (0.0008) -[2023-10-09 00:00:25,865][88327] Updated weights for policy 1, policy_version 620 (0.0009) -[2023-10-09 00:00:26,093][88326] Updated weights for policy 0, policy_version 610 (0.0010) -[2023-10-09 00:00:26,224][88327] Updated weights for policy 1, policy_version 630 (0.0008) -[2023-10-09 00:00:26,494][88326] Updated weights for policy 0, policy_version 620 (0.0008) -[2023-10-09 00:00:26,587][88327] Updated weights for policy 1, policy_version 640 (0.0007) -[2023-10-09 00:00:26,857][88326] Updated weights for policy 0, policy_version 630 (0.0009) -[2023-10-09 00:00:27,236][88326] Updated weights for policy 0, policy_version 640 (0.0008) -[2023-10-09 00:00:28,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12744.8). Total num frames: 1310720. Throughput: 0: 1654.2, 1: 1683.5. Samples: 333132. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-09 00:00:28,975][87372] Avg episode reward: [(0, '1.130'), (1, '1.160')] -[2023-10-09 00:00:28,977][88088] Saving new best policy, reward=1.130! -[2023-10-09 00:00:30,493][88327] Updated weights for policy 1, policy_version 650 (0.0011) -[2023-10-09 00:00:30,859][88327] Updated weights for policy 1, policy_version 660 (0.0009) -[2023-10-09 00:00:31,221][88327] Updated weights for policy 1, policy_version 670 (0.0008) -[2023-10-09 00:00:31,239][88326] Updated weights for policy 0, policy_version 650 (0.0008) -[2023-10-09 00:00:31,616][88326] Updated weights for policy 0, policy_version 660 (0.0008) -[2023-10-09 00:00:31,974][88326] Updated weights for policy 0, policy_version 670 (0.0009) -[2023-10-09 00:00:33,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.3, 300 sec: 12761.6). Total num frames: 1376256. Throughput: 0: 1682.5, 1: 1710.8. Samples: 354056. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) -[2023-10-09 00:00:33,975][87372] Avg episode reward: [(0, '1.060'), (1, '1.150')] -[2023-10-09 00:00:33,985][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000000672_688128.pth... -[2023-10-09 00:00:33,985][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000000672_688128.pth... -[2023-10-09 00:00:35,190][88327] Updated weights for policy 1, policy_version 680 (0.0009) -[2023-10-09 00:00:35,551][88327] Updated weights for policy 1, policy_version 690 (0.0011) -[2023-10-09 00:00:35,920][88327] Updated weights for policy 1, policy_version 700 (0.0010) -[2023-10-09 00:00:36,055][88326] Updated weights for policy 0, policy_version 680 (0.0007) -[2023-10-09 00:00:36,425][88326] Updated weights for policy 0, policy_version 690 (0.0008) -[2023-10-09 00:00:36,808][88326] Updated weights for policy 0, policy_version 700 (0.0009) -[2023-10-09 00:00:38,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12776.9). Total num frames: 1441792. Throughput: 0: 1678.6, 1: 1680.3. Samples: 363986. Policy #0 lag: (min: 15.0, avg: 18.5, max: 47.0) -[2023-10-09 00:00:38,975][87372] Avg episode reward: [(0, '1.020'), (1, '1.400')] -[2023-10-09 00:00:38,976][88168] Saving new best policy, reward=1.400! -[2023-10-09 00:00:40,106][88327] Updated weights for policy 1, policy_version 710 (0.0008) -[2023-10-09 00:00:40,471][88327] Updated weights for policy 1, policy_version 720 (0.0008) -[2023-10-09 00:00:40,842][88327] Updated weights for policy 1, policy_version 730 (0.0009) -[2023-10-09 00:00:40,886][88326] Updated weights for policy 0, policy_version 710 (0.0008) -[2023-10-09 00:00:41,256][88326] Updated weights for policy 0, policy_version 720 (0.0008) -[2023-10-09 00:00:41,617][88326] Updated weights for policy 0, policy_version 730 (0.0009) -[2023-10-09 00:00:43,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.1, 300 sec: 12790.9). Total num frames: 1507328. Throughput: 0: 1670.0, 1: 1697.1. Samples: 384058. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-09 00:00:43,975][87372] Avg episode reward: [(0, '1.000'), (1, '1.520')] -[2023-10-09 00:00:43,977][88168] Saving new best policy, reward=1.520! -[2023-10-09 00:00:44,840][88327] Updated weights for policy 1, policy_version 740 (0.0008) -[2023-10-09 00:00:45,199][88327] Updated weights for policy 1, policy_version 750 (0.0007) -[2023-10-09 00:00:45,567][88327] Updated weights for policy 1, policy_version 760 (0.0008) -[2023-10-09 00:00:45,815][88326] Updated weights for policy 0, policy_version 740 (0.0008) -[2023-10-09 00:00:46,178][88326] Updated weights for policy 0, policy_version 750 (0.0009) -[2023-10-09 00:00:46,550][88326] Updated weights for policy 0, policy_version 760 (0.0009) -[2023-10-09 00:00:48,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12803.8). Total num frames: 1572864. Throughput: 0: 1695.0, 1: 1704.4. Samples: 404824. Policy #0 lag: (min: 31.0, avg: 31.4, max: 45.0) -[2023-10-09 00:00:48,975][87372] Avg episode reward: [(0, '0.960'), (1, '1.520')] -[2023-10-09 00:00:49,636][88327] Updated weights for policy 1, policy_version 770 (0.0007) -[2023-10-09 00:00:49,997][88327] Updated weights for policy 1, policy_version 780 (0.0009) -[2023-10-09 00:00:50,363][88327] Updated weights for policy 1, policy_version 790 (0.0011) -[2023-10-09 00:00:50,734][88327] Updated weights for policy 1, policy_version 800 (0.0008) -[2023-10-09 00:00:50,770][88326] Updated weights for policy 0, policy_version 770 (0.0009) -[2023-10-09 00:00:51,132][88326] Updated weights for policy 0, policy_version 780 (0.0009) -[2023-10-09 00:00:51,511][88326] Updated weights for policy 0, policy_version 790 (0.0010) -[2023-10-09 00:00:51,885][88326] Updated weights for policy 0, policy_version 800 (0.0008) -[2023-10-09 00:00:53,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12815.7). Total num frames: 1638400. Throughput: 0: 1683.1, 1: 1674.5. Samples: 414604. Policy #0 lag: (min: 15.0, avg: 30.8, max: 47.0) -[2023-10-09 00:00:53,975][87372] Avg episode reward: [(0, '1.070'), (1, '1.270')] -[2023-10-09 00:00:54,892][88327] Updated weights for policy 1, policy_version 810 (0.0008) -[2023-10-09 00:00:55,250][88327] Updated weights for policy 1, policy_version 820 (0.0009) -[2023-10-09 00:00:55,614][88327] Updated weights for policy 1, policy_version 830 (0.0011) -[2023-10-09 00:00:56,020][88326] Updated weights for policy 0, policy_version 810 (0.0009) -[2023-10-09 00:00:56,398][88326] Updated weights for policy 0, policy_version 820 (0.0008) -[2023-10-09 00:00:56,768][88326] Updated weights for policy 0, policy_version 830 (0.0007) -[2023-10-09 00:00:58,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12826.7). Total num frames: 1703936. Throughput: 0: 1678.9, 1: 1692.3. Samples: 434238. Policy #0 lag: (min: 12.0, avg: 15.6, max: 44.0) -[2023-10-09 00:00:58,975][87372] Avg episode reward: [(0, '1.210'), (1, '1.150')] -[2023-10-09 00:00:58,976][88088] Saving new best policy, reward=1.210! -[2023-10-09 00:00:59,769][88327] Updated weights for policy 1, policy_version 840 (0.0009) -[2023-10-09 00:01:00,146][88327] Updated weights for policy 1, policy_version 850 (0.0009) -[2023-10-09 00:01:00,509][88327] Updated weights for policy 1, policy_version 860 (0.0010) -[2023-10-09 00:01:00,733][88326] Updated weights for policy 0, policy_version 840 (0.0009) -[2023-10-09 00:01:01,096][88326] Updated weights for policy 0, policy_version 850 (0.0009) -[2023-10-09 00:01:01,483][88326] Updated weights for policy 0, policy_version 860 (0.0010) -[2023-10-09 00:01:03,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.1, 300 sec: 12836.8). Total num frames: 1769472. Throughput: 0: 1699.1, 1: 1683.0. Samples: 455194. Policy #0 lag: (min: 29.0, avg: 39.3, max: 40.0) -[2023-10-09 00:01:03,975][87372] Avg episode reward: [(0, '1.360'), (1, '1.100')] -[2023-10-09 00:01:03,987][88088] Saving new best policy, reward=1.360! -[2023-10-09 00:01:04,589][88327] Updated weights for policy 1, policy_version 870 (0.0007) -[2023-10-09 00:01:04,961][88327] Updated weights for policy 1, policy_version 880 (0.0007) -[2023-10-09 00:01:05,334][88327] Updated weights for policy 1, policy_version 890 (0.0008) -[2023-10-09 00:01:05,371][88326] Updated weights for policy 0, policy_version 870 (0.0008) -[2023-10-09 00:01:05,731][88326] Updated weights for policy 0, policy_version 880 (0.0007) -[2023-10-09 00:01:06,104][88326] Updated weights for policy 0, policy_version 890 (0.0008) -[2023-10-09 00:01:08,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12846.3). Total num frames: 1835008. Throughput: 0: 1673.7, 1: 1670.5. Samples: 464486. Policy #0 lag: (min: 42.0, avg: 47.9, max: 48.0) -[2023-10-09 00:01:08,975][87372] Avg episode reward: [(0, '1.310'), (1, '1.080')] -[2023-10-09 00:01:09,157][88327] Updated weights for policy 1, policy_version 900 (0.0008) -[2023-10-09 00:01:09,522][88327] Updated weights for policy 1, policy_version 910 (0.0008) -[2023-10-09 00:01:09,888][88327] Updated weights for policy 1, policy_version 920 (0.0012) -[2023-10-09 00:01:10,099][88326] Updated weights for policy 0, policy_version 900 (0.0007) -[2023-10-09 00:01:10,478][88326] Updated weights for policy 0, policy_version 910 (0.0007) -[2023-10-09 00:01:10,850][88326] Updated weights for policy 0, policy_version 920 (0.0008) -[2023-10-09 00:01:13,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12855.1). Total num frames: 1900544. Throughput: 0: 1695.2, 1: 1687.7. Samples: 485360. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-10-09 00:01:13,975][87372] Avg episode reward: [(0, '1.260'), (1, '1.070')] -[2023-10-09 00:01:14,045][88327] Updated weights for policy 1, policy_version 930 (0.0008) -[2023-10-09 00:01:14,409][88327] Updated weights for policy 1, policy_version 940 (0.0009) -[2023-10-09 00:01:14,776][88327] Updated weights for policy 1, policy_version 950 (0.0009) -[2023-10-09 00:01:14,899][88326] Updated weights for policy 0, policy_version 930 (0.0009) -[2023-10-09 00:01:15,143][88327] Updated weights for policy 1, policy_version 960 (0.0008) -[2023-10-09 00:01:15,304][88326] Updated weights for policy 0, policy_version 940 (0.0009) -[2023-10-09 00:01:15,676][88326] Updated weights for policy 0, policy_version 950 (0.0010) -[2023-10-09 00:01:16,049][88326] Updated weights for policy 0, policy_version 960 (0.0009) -[2023-10-09 00:01:18,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12863.4). Total num frames: 1966080. Throughput: 0: 1689.2, 1: 1686.3. Samples: 505952. Policy #0 lag: (min: 31.0, avg: 31.2, max: 41.0) -[2023-10-09 00:01:18,975][87372] Avg episode reward: [(0, '1.260'), (1, '1.100')] -[2023-10-09 00:01:19,071][88327] Updated weights for policy 1, policy_version 970 (0.0010) -[2023-10-09 00:01:19,453][88327] Updated weights for policy 1, policy_version 980 (0.0010) -[2023-10-09 00:01:19,824][88327] Updated weights for policy 1, policy_version 990 (0.0008) -[2023-10-09 00:01:20,153][88326] Updated weights for policy 0, policy_version 970 (0.0007) -[2023-10-09 00:01:20,527][88326] Updated weights for policy 0, policy_version 980 (0.0007) -[2023-10-09 00:01:20,901][88326] Updated weights for policy 0, policy_version 990 (0.0007) -[2023-10-09 00:01:23,902][88327] Updated weights for policy 1, policy_version 1000 (0.0008) -[2023-10-09 00:01:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12871.1). Total num frames: 2031616. Throughput: 0: 1670.3, 1: 1685.8. Samples: 515008. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-09 00:01:23,975][87372] Avg episode reward: [(0, '1.160'), (1, '1.140')] -[2023-10-09 00:01:24,278][88327] Updated weights for policy 1, policy_version 1010 (0.0007) -[2023-10-09 00:01:24,647][88327] Updated weights for policy 1, policy_version 1020 (0.0009) -[2023-10-09 00:01:24,779][88326] Updated weights for policy 0, policy_version 1000 (0.0008) -[2023-10-09 00:01:25,157][88326] Updated weights for policy 0, policy_version 1010 (0.0009) -[2023-10-09 00:01:25,519][88326] Updated weights for policy 0, policy_version 1020 (0.0008) -[2023-10-09 00:01:28,752][88327] Updated weights for policy 1, policy_version 1030 (0.0008) -[2023-10-09 00:01:28,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 12878.3). Total num frames: 2097152. Throughput: 0: 1694.0, 1: 1685.6. Samples: 536142. Policy #0 lag: (min: 13.0, avg: 20.3, max: 45.0) -[2023-10-09 00:01:28,975][87372] Avg episode reward: [(0, '1.020'), (1, '1.030')] -[2023-10-09 00:01:29,106][88327] Updated weights for policy 1, policy_version 1040 (0.0011) -[2023-10-09 00:01:29,482][88327] Updated weights for policy 1, policy_version 1050 (0.0010) -[2023-10-09 00:01:29,578][88326] Updated weights for policy 0, policy_version 1030 (0.0010) -[2023-10-09 00:01:29,946][88326] Updated weights for policy 0, policy_version 1040 (0.0009) -[2023-10-09 00:01:30,316][88326] Updated weights for policy 0, policy_version 1050 (0.0010) -[2023-10-09 00:01:33,664][88327] Updated weights for policy 1, policy_version 1060 (0.0008) -[2023-10-09 00:01:33,974][87372] Fps is (10 sec: 13106.7, 60 sec: 13107.1, 300 sec: 12885.1). Total num frames: 2162688. Throughput: 0: 1692.0, 1: 1692.3. Samples: 557118. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-09 00:01:33,976][87372] Avg episode reward: [(0, '1.010'), (1, '1.150')] -[2023-10-09 00:01:34,026][88327] Updated weights for policy 1, policy_version 1070 (0.0010) -[2023-10-09 00:01:34,295][88326] Updated weights for policy 0, policy_version 1060 (0.0008) -[2023-10-09 00:01:34,391][88327] Updated weights for policy 1, policy_version 1080 (0.0007) -[2023-10-09 00:01:34,666][88326] Updated weights for policy 0, policy_version 1070 (0.0009) -[2023-10-09 00:01:35,036][88326] Updated weights for policy 0, policy_version 1080 (0.0007) -[2023-10-09 00:01:38,381][88327] Updated weights for policy 1, policy_version 1090 (0.0007) -[2023-10-09 00:01:38,756][88327] Updated weights for policy 1, policy_version 1100 (0.0010) -[2023-10-09 00:01:38,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12891.6). Total num frames: 2228224. Throughput: 0: 1677.8, 1: 1691.1. Samples: 566206. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:01:38,975][87372] Avg episode reward: [(0, '1.090'), (1, '1.270')] -[2023-10-09 00:01:39,078][88326] Updated weights for policy 0, policy_version 1090 (0.0008) -[2023-10-09 00:01:39,116][88327] Updated weights for policy 1, policy_version 1110 (0.0009) -[2023-10-09 00:01:39,455][88326] Updated weights for policy 0, policy_version 1100 (0.0010) -[2023-10-09 00:01:39,495][88327] Updated weights for policy 1, policy_version 1120 (0.0008) -[2023-10-09 00:01:39,820][88326] Updated weights for policy 0, policy_version 1110 (0.0008) -[2023-10-09 00:01:40,193][88326] Updated weights for policy 0, policy_version 1120 (0.0009) -[2023-10-09 00:01:43,481][88327] Updated weights for policy 1, policy_version 1130 (0.0008) -[2023-10-09 00:01:43,853][88327] Updated weights for policy 1, policy_version 1140 (0.0009) -[2023-10-09 00:01:43,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 12897.6). Total num frames: 2293760. Throughput: 0: 1701.4, 1: 1695.1. Samples: 587078. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-09 00:01:43,975][87372] Avg episode reward: [(0, '1.340'), (1, '1.320')] -[2023-10-09 00:01:44,225][88327] Updated weights for policy 1, policy_version 1150 (0.0009) -[2023-10-09 00:01:44,283][88326] Updated weights for policy 0, policy_version 1130 (0.0007) -[2023-10-09 00:01:44,665][88326] Updated weights for policy 0, policy_version 1140 (0.0008) -[2023-10-09 00:01:45,043][88326] Updated weights for policy 0, policy_version 1150 (0.0008) -[2023-10-09 00:01:48,121][88327] Updated weights for policy 1, policy_version 1160 (0.0010) -[2023-10-09 00:01:48,500][88327] Updated weights for policy 1, policy_version 1170 (0.0009) -[2023-10-09 00:01:48,861][88327] Updated weights for policy 1, policy_version 1180 (0.0009) -[2023-10-09 00:01:48,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12903.4). Total num frames: 2359296. Throughput: 0: 1694.6, 1: 1694.4. Samples: 607698. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:01:48,975][87372] Avg episode reward: [(0, '1.470'), (1, '1.310')] -[2023-10-09 00:01:49,104][88326] Updated weights for policy 0, policy_version 1160 (0.0007) -[2023-10-09 00:01:49,478][88326] Updated weights for policy 0, policy_version 1170 (0.0007) -[2023-10-09 00:01:49,851][88326] Updated weights for policy 0, policy_version 1180 (0.0007) -[2023-10-09 00:01:49,999][88088] Saving new best policy, reward=1.470! -[2023-10-09 00:01:52,930][88327] Updated weights for policy 1, policy_version 1190 (0.0009) -[2023-10-09 00:01:53,292][88327] Updated weights for policy 1, policy_version 1200 (0.0010) -[2023-10-09 00:01:53,660][88327] Updated weights for policy 1, policy_version 1210 (0.0009) -[2023-10-09 00:01:53,771][88326] Updated weights for policy 0, policy_version 1190 (0.0008) -[2023-10-09 00:01:53,974][87372] Fps is (10 sec: 16384.3, 60 sec: 13653.4, 300 sec: 13083.2). Total num frames: 2457600. Throughput: 0: 1694.3, 1: 1702.9. Samples: 617360. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:01:53,975][87372] Avg episode reward: [(0, '1.400'), (1, '1.270')] -[2023-10-09 00:01:54,128][88326] Updated weights for policy 0, policy_version 1200 (0.0009) -[2023-10-09 00:01:54,493][88326] Updated weights for policy 0, policy_version 1210 (0.0010) -[2023-10-09 00:01:57,875][88327] Updated weights for policy 1, policy_version 1220 (0.0008) -[2023-10-09 00:01:58,237][88327] Updated weights for policy 1, policy_version 1230 (0.0008) -[2023-10-09 00:01:58,355][88326] Updated weights for policy 0, policy_version 1220 (0.0007) -[2023-10-09 00:01:58,610][88327] Updated weights for policy 1, policy_version 1240 (0.0007) -[2023-10-09 00:01:58,721][88326] Updated weights for policy 0, policy_version 1230 (0.0010) -[2023-10-09 00:01:58,974][87372] Fps is (10 sec: 16384.2, 60 sec: 13653.3, 300 sec: 13083.9). Total num frames: 2523136. Throughput: 0: 1698.0, 1: 1692.5. Samples: 637934. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-09 00:01:58,975][87372] Avg episode reward: [(0, '1.210'), (1, '1.240')] -[2023-10-09 00:01:59,093][88326] Updated weights for policy 0, policy_version 1240 (0.0010) -[2023-10-09 00:02:02,594][88327] Updated weights for policy 1, policy_version 1250 (0.0009) -[2023-10-09 00:02:02,987][88327] Updated weights for policy 1, policy_version 1260 (0.0007) -[2023-10-09 00:02:03,206][88326] Updated weights for policy 0, policy_version 1250 (0.0008) -[2023-10-09 00:02:03,340][88327] Updated weights for policy 1, policy_version 1270 (0.0008) -[2023-10-09 00:02:03,605][88326] Updated weights for policy 0, policy_version 1260 (0.0008) -[2023-10-09 00:02:03,724][88327] Updated weights for policy 1, policy_version 1280 (0.0009) -[2023-10-09 00:02:03,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13084.4). Total num frames: 2588672. Throughput: 0: 1699.1, 1: 1676.7. Samples: 657860. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:02:03,975][87372] Avg episode reward: [(0, '1.190'), (1, '1.250')] -[2023-10-09 00:02:03,979][88326] Updated weights for policy 0, policy_version 1270 (0.0008) -[2023-10-09 00:02:04,347][88326] Updated weights for policy 0, policy_version 1280 (0.0010) -[2023-10-09 00:02:07,807][88327] Updated weights for policy 1, policy_version 1290 (0.0008) -[2023-10-09 00:02:08,171][88327] Updated weights for policy 1, policy_version 1300 (0.0007) -[2023-10-09 00:02:08,425][88326] Updated weights for policy 0, policy_version 1290 (0.0009) -[2023-10-09 00:02:08,542][88327] Updated weights for policy 1, policy_version 1310 (0.0007) -[2023-10-09 00:02:08,787][88326] Updated weights for policy 0, policy_version 1300 (0.0010) -[2023-10-09 00:02:08,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13085.0). Total num frames: 2654208. Throughput: 0: 1699.5, 1: 1690.1. Samples: 667542. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-10-09 00:02:08,975][87372] Avg episode reward: [(0, '1.280'), (1, '1.330')] -[2023-10-09 00:02:09,171][88326] Updated weights for policy 0, policy_version 1310 (0.0011) -[2023-10-09 00:02:12,834][88327] Updated weights for policy 1, policy_version 1320 (0.0009) -[2023-10-09 00:02:13,191][88326] Updated weights for policy 0, policy_version 1320 (0.0008) -[2023-10-09 00:02:13,197][88327] Updated weights for policy 1, policy_version 1330 (0.0010) -[2023-10-09 00:02:13,552][88326] Updated weights for policy 0, policy_version 1330 (0.0008) -[2023-10-09 00:02:13,565][88327] Updated weights for policy 1, policy_version 1340 (0.0007) -[2023-10-09 00:02:13,927][88326] Updated weights for policy 0, policy_version 1340 (0.0009) -[2023-10-09 00:02:13,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13085.6). Total num frames: 2719744. Throughput: 0: 1697.7, 1: 1689.5. Samples: 688566. Policy #0 lag: (min: 26.0, avg: 26.7, max: 41.0) -[2023-10-09 00:02:13,974][87372] Avg episode reward: [(0, '1.550'), (1, '1.290')] -[2023-10-09 00:02:14,073][88088] Saving new best policy, reward=1.550! -[2023-10-09 00:02:17,603][88327] Updated weights for policy 1, policy_version 1350 (0.0009) -[2023-10-09 00:02:17,864][88326] Updated weights for policy 0, policy_version 1350 (0.0008) -[2023-10-09 00:02:17,973][88327] Updated weights for policy 1, policy_version 1360 (0.0009) -[2023-10-09 00:02:18,229][88326] Updated weights for policy 0, policy_version 1360 (0.0009) -[2023-10-09 00:02:18,342][88327] Updated weights for policy 1, policy_version 1370 (0.0008) -[2023-10-09 00:02:18,591][88326] Updated weights for policy 0, policy_version 1370 (0.0009) -[2023-10-09 00:02:18,974][87372] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 13240.0). Total num frames: 2818048. Throughput: 0: 1686.6, 1: 1665.8. Samples: 707976. Policy #0 lag: (min: 10.0, avg: 24.4, max: 42.0) -[2023-10-09 00:02:18,975][87372] Avg episode reward: [(0, '1.500'), (1, '1.380')] -[2023-10-09 00:02:22,471][88327] Updated weights for policy 1, policy_version 1380 (0.0010) -[2023-10-09 00:02:22,663][88326] Updated weights for policy 0, policy_version 1380 (0.0008) -[2023-10-09 00:02:22,846][88327] Updated weights for policy 1, policy_version 1390 (0.0007) -[2023-10-09 00:02:23,045][88326] Updated weights for policy 0, policy_version 1390 (0.0009) -[2023-10-09 00:02:23,217][88327] Updated weights for policy 1, policy_version 1400 (0.0007) -[2023-10-09 00:02:23,411][88326] Updated weights for policy 0, policy_version 1400 (0.0008) -[2023-10-09 00:02:23,974][87372] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13237.0). Total num frames: 2883584. Throughput: 0: 1699.0, 1: 1682.3. Samples: 718364. Policy #0 lag: (min: 10.0, avg: 10.0, max: 10.0) -[2023-10-09 00:02:23,975][87372] Avg episode reward: [(0, '1.460'), (1, '1.300')] -[2023-10-09 00:02:27,288][88327] Updated weights for policy 1, policy_version 1410 (0.0008) -[2023-10-09 00:02:27,583][88326] Updated weights for policy 0, policy_version 1410 (0.0009) -[2023-10-09 00:02:27,655][88327] Updated weights for policy 1, policy_version 1420 (0.0010) -[2023-10-09 00:02:27,946][88326] Updated weights for policy 0, policy_version 1420 (0.0009) -[2023-10-09 00:02:28,026][88327] Updated weights for policy 1, policy_version 1430 (0.0008) -[2023-10-09 00:02:28,323][88326] Updated weights for policy 0, policy_version 1430 (0.0009) -[2023-10-09 00:02:28,392][88327] Updated weights for policy 1, policy_version 1440 (0.0008) -[2023-10-09 00:02:28,694][88326] Updated weights for policy 0, policy_version 1440 (0.0009) -[2023-10-09 00:02:28,974][87372] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13234.1). Total num frames: 2949120. Throughput: 0: 1697.9, 1: 1680.4. Samples: 739102. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-09 00:02:28,975][87372] Avg episode reward: [(0, '1.380'), (1, '1.230')] -[2023-10-09 00:02:32,319][88327] Updated weights for policy 1, policy_version 1450 (0.0007) -[2023-10-09 00:02:32,683][88327] Updated weights for policy 1, policy_version 1460 (0.0007) -[2023-10-09 00:02:32,737][88326] Updated weights for policy 0, policy_version 1450 (0.0010) -[2023-10-09 00:02:33,047][88327] Updated weights for policy 1, policy_version 1470 (0.0009) -[2023-10-09 00:02:33,112][88326] Updated weights for policy 0, policy_version 1460 (0.0007) -[2023-10-09 00:02:33,482][88326] Updated weights for policy 0, policy_version 1470 (0.0007) -[2023-10-09 00:02:33,974][87372] Fps is (10 sec: 13107.2, 60 sec: 14199.6, 300 sec: 13231.3). Total num frames: 3014656. Throughput: 0: 1677.4, 1: 1660.9. Samples: 757922. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-09 00:02:33,975][87372] Avg episode reward: [(0, '1.380'), (1, '1.200')] -[2023-10-09 00:02:33,984][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000001472_1507328.pth... -[2023-10-09 00:02:33,984][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000001472_1507328.pth... -[2023-10-09 00:02:36,860][88327] Updated weights for policy 1, policy_version 1480 (0.0010) -[2023-10-09 00:02:37,219][88327] Updated weights for policy 1, policy_version 1490 (0.0010) -[2023-10-09 00:02:37,440][88326] Updated weights for policy 0, policy_version 1480 (0.0008) -[2023-10-09 00:02:37,586][88327] Updated weights for policy 1, policy_version 1500 (0.0008) -[2023-10-09 00:02:37,812][88326] Updated weights for policy 0, policy_version 1490 (0.0008) -[2023-10-09 00:02:38,180][88326] Updated weights for policy 0, policy_version 1500 (0.0009) -[2023-10-09 00:02:38,974][87372] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13228.6). Total num frames: 3080192. Throughput: 0: 1696.0, 1: 1682.7. Samples: 769404. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:02:38,975][87372] Avg episode reward: [(0, '1.430'), (1, '1.230')] -[2023-10-09 00:02:41,757][88327] Updated weights for policy 1, policy_version 1510 (0.0009) -[2023-10-09 00:02:42,111][88327] Updated weights for policy 1, policy_version 1520 (0.0008) -[2023-10-09 00:02:42,392][88326] Updated weights for policy 0, policy_version 1510 (0.0007) -[2023-10-09 00:02:42,471][88327] Updated weights for policy 1, policy_version 1530 (0.0007) -[2023-10-09 00:02:42,775][88326] Updated weights for policy 0, policy_version 1520 (0.0007) -[2023-10-09 00:02:43,153][88326] Updated weights for policy 0, policy_version 1530 (0.0008) -[2023-10-09 00:02:43,974][87372] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13226.0). Total num frames: 3145728. Throughput: 0: 1689.7, 1: 1671.1. Samples: 789168. Policy #0 lag: (min: 5.0, avg: 12.8, max: 37.0) -[2023-10-09 00:02:43,975][87372] Avg episode reward: [(0, '1.580'), (1, '1.190')] -[2023-10-09 00:02:43,976][88088] Saving new best policy, reward=1.580! -[2023-10-09 00:02:46,685][88327] Updated weights for policy 1, policy_version 1540 (0.0008) -[2023-10-09 00:02:47,045][88327] Updated weights for policy 1, policy_version 1550 (0.0009) -[2023-10-09 00:02:47,125][88326] Updated weights for policy 0, policy_version 1540 (0.0007) -[2023-10-09 00:02:47,411][88327] Updated weights for policy 1, policy_version 1560 (0.0009) -[2023-10-09 00:02:47,491][88326] Updated weights for policy 0, policy_version 1550 (0.0009) -[2023-10-09 00:02:47,867][88326] Updated weights for policy 0, policy_version 1560 (0.0009) -[2023-10-09 00:02:48,974][87372] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13223.6). Total num frames: 3211264. Throughput: 0: 1665.7, 1: 1671.5. Samples: 808032. Policy #0 lag: (min: 17.0, avg: 31.2, max: 49.0) -[2023-10-09 00:02:48,975][87372] Avg episode reward: [(0, '1.590'), (1, '1.150')] -[2023-10-09 00:02:48,988][88088] Saving new best policy, reward=1.590! -[2023-10-09 00:02:51,317][88327] Updated weights for policy 1, policy_version 1570 (0.0008) -[2023-10-09 00:02:51,743][88327] Updated weights for policy 1, policy_version 1580 (0.0010) -[2023-10-09 00:02:51,961][88326] Updated weights for policy 0, policy_version 1570 (0.0007) -[2023-10-09 00:02:52,112][88327] Updated weights for policy 1, policy_version 1590 (0.0010) -[2023-10-09 00:02:52,356][88326] Updated weights for policy 0, policy_version 1580 (0.0008) -[2023-10-09 00:02:52,478][88327] Updated weights for policy 1, policy_version 1600 (0.0009) -[2023-10-09 00:02:52,730][88326] Updated weights for policy 0, policy_version 1590 (0.0008) -[2023-10-09 00:02:53,109][88326] Updated weights for policy 0, policy_version 1600 (0.0008) -[2023-10-09 00:02:53,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13221.2). Total num frames: 3276800. Throughput: 0: 1695.6, 1: 1689.8. Samples: 819884. Policy #0 lag: (min: 30.0, avg: 30.9, max: 45.0) -[2023-10-09 00:02:53,975][87372] Avg episode reward: [(0, '1.730'), (1, '1.300')] -[2023-10-09 00:02:53,977][88088] Saving new best policy, reward=1.730! -[2023-10-09 00:02:56,627][88327] Updated weights for policy 1, policy_version 1610 (0.0009) -[2023-10-09 00:02:56,992][88327] Updated weights for policy 1, policy_version 1620 (0.0009) -[2023-10-09 00:02:57,029][88326] Updated weights for policy 0, policy_version 1610 (0.0007) -[2023-10-09 00:02:57,366][88327] Updated weights for policy 1, policy_version 1630 (0.0008) -[2023-10-09 00:02:57,395][88326] Updated weights for policy 0, policy_version 1620 (0.0007) -[2023-10-09 00:02:57,760][88326] Updated weights for policy 0, policy_version 1630 (0.0007) -[2023-10-09 00:02:58,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13219.0). Total num frames: 3342336. Throughput: 0: 1680.2, 1: 1666.3. Samples: 839156. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-09 00:02:58,975][87372] Avg episode reward: [(0, '1.640'), (1, '1.290')] -[2023-10-09 00:03:01,321][88327] Updated weights for policy 1, policy_version 1640 (0.0009) -[2023-10-09 00:03:01,677][88327] Updated weights for policy 1, policy_version 1650 (0.0008) -[2023-10-09 00:03:01,911][88326] Updated weights for policy 0, policy_version 1640 (0.0008) -[2023-10-09 00:03:02,052][88327] Updated weights for policy 1, policy_version 1660 (0.0008) -[2023-10-09 00:03:02,271][88326] Updated weights for policy 0, policy_version 1650 (0.0010) -[2023-10-09 00:03:02,643][88326] Updated weights for policy 0, policy_version 1660 (0.0009) -[2023-10-09 00:03:03,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13216.8). Total num frames: 3407872. Throughput: 0: 1673.6, 1: 1680.7. Samples: 858920. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-09 00:03:03,975][87372] Avg episode reward: [(0, '1.620'), (1, '1.280')] -[2023-10-09 00:03:05,833][88327] Updated weights for policy 1, policy_version 1670 (0.0009) -[2023-10-09 00:03:06,204][88327] Updated weights for policy 1, policy_version 1680 (0.0007) -[2023-10-09 00:03:06,560][88327] Updated weights for policy 1, policy_version 1690 (0.0008) -[2023-10-09 00:03:06,703][88326] Updated weights for policy 0, policy_version 1670 (0.0008) -[2023-10-09 00:03:07,069][88326] Updated weights for policy 0, policy_version 1680 (0.0009) -[2023-10-09 00:03:07,440][88326] Updated weights for policy 0, policy_version 1690 (0.0007) -[2023-10-09 00:03:08,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13214.8). Total num frames: 3473408. Throughput: 0: 1688.5, 1: 1687.3. Samples: 870278. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-09 00:03:08,975][87372] Avg episode reward: [(0, '1.530'), (1, '1.420')] -[2023-10-09 00:03:10,569][88327] Updated weights for policy 1, policy_version 1700 (0.0009) -[2023-10-09 00:03:10,927][88327] Updated weights for policy 1, policy_version 1710 (0.0009) -[2023-10-09 00:03:11,302][88327] Updated weights for policy 1, policy_version 1720 (0.0009) -[2023-10-09 00:03:11,448][88326] Updated weights for policy 0, policy_version 1700 (0.0010) -[2023-10-09 00:03:11,826][88326] Updated weights for policy 0, policy_version 1710 (0.0010) -[2023-10-09 00:03:12,187][88326] Updated weights for policy 0, policy_version 1720 (0.0009) -[2023-10-09 00:03:13,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13212.7). Total num frames: 3538944. Throughput: 0: 1667.4, 1: 1673.0. Samples: 889420. Policy #0 lag: (min: 31.0, avg: 32.6, max: 58.0) -[2023-10-09 00:03:13,975][87372] Avg episode reward: [(0, '1.700'), (1, '1.550')] -[2023-10-09 00:03:13,976][88168] Saving new best policy, reward=1.550! -[2023-10-09 00:03:15,522][88327] Updated weights for policy 1, policy_version 1730 (0.0010) -[2023-10-09 00:03:15,899][88327] Updated weights for policy 1, policy_version 1740 (0.0009) -[2023-10-09 00:03:16,260][88327] Updated weights for policy 1, policy_version 1750 (0.0007) -[2023-10-09 00:03:16,333][88326] Updated weights for policy 0, policy_version 1730 (0.0009) -[2023-10-09 00:03:16,629][88327] Updated weights for policy 1, policy_version 1760 (0.0007) -[2023-10-09 00:03:16,713][88326] Updated weights for policy 0, policy_version 1740 (0.0008) -[2023-10-09 00:03:17,081][88326] Updated weights for policy 0, policy_version 1750 (0.0009) -[2023-10-09 00:03:17,453][88326] Updated weights for policy 0, policy_version 1760 (0.0011) -[2023-10-09 00:03:18,974][87372] Fps is (10 sec: 13106.8, 60 sec: 13107.2, 300 sec: 13210.8). Total num frames: 3604480. Throughput: 0: 1676.7, 1: 1699.9. Samples: 909870. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-09 00:03:18,976][87372] Avg episode reward: [(0, '1.810'), (1, '1.590')] -[2023-10-09 00:03:18,988][88168] Saving new best policy, reward=1.590! -[2023-10-09 00:03:18,988][88088] Saving new best policy, reward=1.810! -[2023-10-09 00:03:20,710][88327] Updated weights for policy 1, policy_version 1770 (0.0008) -[2023-10-09 00:03:21,079][88327] Updated weights for policy 1, policy_version 1780 (0.0007) -[2023-10-09 00:03:21,438][88327] Updated weights for policy 1, policy_version 1790 (0.0007) -[2023-10-09 00:03:21,483][88326] Updated weights for policy 0, policy_version 1770 (0.0007) -[2023-10-09 00:03:21,851][88326] Updated weights for policy 0, policy_version 1780 (0.0007) -[2023-10-09 00:03:22,223][88326] Updated weights for policy 0, policy_version 1790 (0.0008) -[2023-10-09 00:03:23,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13208.9). Total num frames: 3670016. Throughput: 0: 1683.6, 1: 1673.9. Samples: 920488. Policy #0 lag: (min: 8.0, avg: 33.7, max: 40.0) -[2023-10-09 00:03:23,975][87372] Avg episode reward: [(0, '1.880'), (1, '1.480')] -[2023-10-09 00:03:23,976][88088] Saving new best policy, reward=1.880! -[2023-10-09 00:03:25,539][88327] Updated weights for policy 1, policy_version 1800 (0.0007) -[2023-10-09 00:03:25,903][88327] Updated weights for policy 1, policy_version 1810 (0.0009) -[2023-10-09 00:03:26,279][88327] Updated weights for policy 1, policy_version 1820 (0.0007) -[2023-10-09 00:03:26,346][88326] Updated weights for policy 0, policy_version 1800 (0.0008) -[2023-10-09 00:03:26,721][88326] Updated weights for policy 0, policy_version 1810 (0.0010) -[2023-10-09 00:03:27,101][88326] Updated weights for policy 0, policy_version 1820 (0.0008) -[2023-10-09 00:03:28,974][87372] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 13207.1). Total num frames: 3735552. Throughput: 0: 1660.1, 1: 1683.0. Samples: 939608. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-09 00:03:28,974][87372] Avg episode reward: [(0, '1.890'), (1, '1.310')] -[2023-10-09 00:03:28,975][88088] Saving new best policy, reward=1.890! -[2023-10-09 00:03:30,271][88327] Updated weights for policy 1, policy_version 1830 (0.0008) -[2023-10-09 00:03:30,637][88327] Updated weights for policy 1, policy_version 1840 (0.0008) -[2023-10-09 00:03:31,000][88327] Updated weights for policy 1, policy_version 1850 (0.0007) -[2023-10-09 00:03:31,015][88326] Updated weights for policy 0, policy_version 1830 (0.0009) -[2023-10-09 00:03:31,372][88326] Updated weights for policy 0, policy_version 1840 (0.0007) -[2023-10-09 00:03:31,741][88326] Updated weights for policy 0, policy_version 1850 (0.0010) -[2023-10-09 00:03:33,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13205.4). Total num frames: 3801088. Throughput: 0: 1687.8, 1: 1698.9. Samples: 960434. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-09 00:03:33,975][87372] Avg episode reward: [(0, '1.780'), (1, '1.270')] -[2023-10-09 00:03:35,074][88327] Updated weights for policy 1, policy_version 1860 (0.0009) -[2023-10-09 00:03:35,448][88327] Updated weights for policy 1, policy_version 1870 (0.0011) -[2023-10-09 00:03:35,692][88326] Updated weights for policy 0, policy_version 1860 (0.0009) -[2023-10-09 00:03:35,812][88327] Updated weights for policy 1, policy_version 1880 (0.0008) -[2023-10-09 00:03:36,049][88326] Updated weights for policy 0, policy_version 1870 (0.0007) -[2023-10-09 00:03:36,417][88326] Updated weights for policy 0, policy_version 1880 (0.0011) -[2023-10-09 00:03:38,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13203.7). Total num frames: 3866624. Throughput: 0: 1675.2, 1: 1670.2. Samples: 970426. Policy #0 lag: (min: 26.0, avg: 29.3, max: 58.0) -[2023-10-09 00:03:38,975][87372] Avg episode reward: [(0, '1.840'), (1, '1.430')] -[2023-10-09 00:03:39,815][88327] Updated weights for policy 1, policy_version 1890 (0.0007) -[2023-10-09 00:03:40,192][88327] Updated weights for policy 1, policy_version 1900 (0.0009) -[2023-10-09 00:03:40,423][88326] Updated weights for policy 0, policy_version 1890 (0.0010) -[2023-10-09 00:03:40,555][88327] Updated weights for policy 1, policy_version 1910 (0.0008) -[2023-10-09 00:03:40,801][88326] Updated weights for policy 0, policy_version 1900 (0.0007) -[2023-10-09 00:03:40,918][88327] Updated weights for policy 1, policy_version 1920 (0.0007) -[2023-10-09 00:03:41,166][88326] Updated weights for policy 0, policy_version 1910 (0.0008) -[2023-10-09 00:03:41,542][88326] Updated weights for policy 0, policy_version 1920 (0.0007) -[2023-10-09 00:03:43,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 3932160. Throughput: 0: 1673.9, 1: 1695.1. Samples: 990762. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:03:43,975][87372] Avg episode reward: [(0, '1.800'), (1, '1.340')] -[2023-10-09 00:03:44,894][88327] Updated weights for policy 1, policy_version 1930 (0.0007) -[2023-10-09 00:03:45,266][88327] Updated weights for policy 1, policy_version 1940 (0.0008) -[2023-10-09 00:03:45,498][88326] Updated weights for policy 0, policy_version 1930 (0.0008) -[2023-10-09 00:03:45,622][88327] Updated weights for policy 1, policy_version 1950 (0.0009) -[2023-10-09 00:03:45,865][88326] Updated weights for policy 0, policy_version 1940 (0.0010) -[2023-10-09 00:03:46,230][88326] Updated weights for policy 0, policy_version 1950 (0.0009) -[2023-10-09 00:03:48,974][87372] Fps is (10 sec: 13106.8, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 3997696. Throughput: 0: 1695.0, 1: 1700.4. Samples: 1011712. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:03:48,975][87372] Avg episode reward: [(0, '1.740'), (1, '1.330')] -[2023-10-09 00:03:49,563][88327] Updated weights for policy 1, policy_version 1960 (0.0009) -[2023-10-09 00:03:49,924][88327] Updated weights for policy 1, policy_version 1970 (0.0007) -[2023-10-09 00:03:50,285][88326] Updated weights for policy 0, policy_version 1960 (0.0007) -[2023-10-09 00:03:50,292][88327] Updated weights for policy 1, policy_version 1980 (0.0007) -[2023-10-09 00:03:50,650][88326] Updated weights for policy 0, policy_version 1970 (0.0008) -[2023-10-09 00:03:51,015][88326] Updated weights for policy 0, policy_version 1980 (0.0007) -[2023-10-09 00:03:53,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 4063232. Throughput: 0: 1669.0, 1: 1681.0. Samples: 1021030. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 00:03:53,975][87372] Avg episode reward: [(0, '1.840'), (1, '1.370')] -[2023-10-09 00:03:54,223][88327] Updated weights for policy 1, policy_version 1990 (0.0010) -[2023-10-09 00:03:54,595][88327] Updated weights for policy 1, policy_version 2000 (0.0009) -[2023-10-09 00:03:54,932][88326] Updated weights for policy 0, policy_version 1990 (0.0007) -[2023-10-09 00:03:54,956][88327] Updated weights for policy 1, policy_version 2010 (0.0007) -[2023-10-09 00:03:55,294][88326] Updated weights for policy 0, policy_version 2000 (0.0008) -[2023-10-09 00:03:55,662][88326] Updated weights for policy 0, policy_version 2010 (0.0009) -[2023-10-09 00:03:58,939][88327] Updated weights for policy 1, policy_version 2020 (0.0008) -[2023-10-09 00:03:58,974][87372] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 4128768. Throughput: 0: 1695.6, 1: 1702.4. Samples: 1042332. Policy #0 lag: (min: 1.0, avg: 13.6, max: 33.0) -[2023-10-09 00:03:58,975][87372] Avg episode reward: [(0, '1.950'), (1, '1.270')] -[2023-10-09 00:03:58,975][88088] Saving new best policy, reward=1.950! -[2023-10-09 00:03:59,307][88327] Updated weights for policy 1, policy_version 2030 (0.0009) -[2023-10-09 00:03:59,673][88327] Updated weights for policy 1, policy_version 2040 (0.0007) -[2023-10-09 00:03:59,718][88326] Updated weights for policy 0, policy_version 2020 (0.0008) -[2023-10-09 00:04:00,087][88326] Updated weights for policy 0, policy_version 2030 (0.0008) -[2023-10-09 00:04:00,458][88326] Updated weights for policy 0, policy_version 2040 (0.0009) -[2023-10-09 00:04:03,700][88327] Updated weights for policy 1, policy_version 2050 (0.0008) -[2023-10-09 00:04:03,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 4194304. Throughput: 0: 1704.5, 1: 1704.3. Samples: 1063262. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-10-09 00:04:03,975][87372] Avg episode reward: [(0, '1.960'), (1, '1.370')] -[2023-10-09 00:04:03,983][88088] Saving new best policy, reward=1.960! -[2023-10-09 00:04:04,077][88327] Updated weights for policy 1, policy_version 2060 (0.0009) -[2023-10-09 00:04:04,458][88327] Updated weights for policy 1, policy_version 2070 (0.0008) -[2023-10-09 00:04:04,603][88326] Updated weights for policy 0, policy_version 2050 (0.0008) -[2023-10-09 00:04:04,821][88327] Updated weights for policy 1, policy_version 2080 (0.0009) -[2023-10-09 00:04:04,978][88326] Updated weights for policy 0, policy_version 2060 (0.0007) -[2023-10-09 00:04:05,336][88326] Updated weights for policy 0, policy_version 2070 (0.0008) -[2023-10-09 00:04:05,713][88326] Updated weights for policy 0, policy_version 2080 (0.0008) -[2023-10-09 00:04:08,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 4259840. Throughput: 0: 1678.3, 1: 1699.7. Samples: 1072498. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-10-09 00:04:08,975][87372] Avg episode reward: [(0, '1.780'), (1, '1.510')] -[2023-10-09 00:04:09,039][88327] Updated weights for policy 1, policy_version 2090 (0.0010) -[2023-10-09 00:04:09,410][88327] Updated weights for policy 1, policy_version 2100 (0.0008) -[2023-10-09 00:04:09,721][88326] Updated weights for policy 0, policy_version 2090 (0.0008) -[2023-10-09 00:04:09,777][88327] Updated weights for policy 1, policy_version 2110 (0.0007) -[2023-10-09 00:04:10,103][88326] Updated weights for policy 0, policy_version 2100 (0.0009) -[2023-10-09 00:04:10,467][88326] Updated weights for policy 0, policy_version 2110 (0.0008) -[2023-10-09 00:04:13,891][88327] Updated weights for policy 1, policy_version 2120 (0.0009) -[2023-10-09 00:04:13,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 4325376. Throughput: 0: 1708.8, 1: 1703.9. Samples: 1093180. Policy #0 lag: (min: 26.0, avg: 33.7, max: 58.0) -[2023-10-09 00:04:13,975][87372] Avg episode reward: [(0, '1.880'), (1, '1.460')] -[2023-10-09 00:04:14,265][88327] Updated weights for policy 1, policy_version 2130 (0.0009) -[2023-10-09 00:04:14,461][88326] Updated weights for policy 0, policy_version 2120 (0.0008) -[2023-10-09 00:04:14,628][88327] Updated weights for policy 1, policy_version 2140 (0.0008) -[2023-10-09 00:04:14,843][88326] Updated weights for policy 0, policy_version 2130 (0.0009) -[2023-10-09 00:04:15,200][88326] Updated weights for policy 0, policy_version 2140 (0.0008) -[2023-10-09 00:04:18,646][88327] Updated weights for policy 1, policy_version 2150 (0.0008) -[2023-10-09 00:04:18,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.3, 300 sec: 13329.4). Total num frames: 4390912. Throughput: 0: 1705.3, 1: 1708.6. Samples: 1114060. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:04:18,975][87372] Avg episode reward: [(0, '2.030'), (1, '1.490')] -[2023-10-09 00:04:19,009][88327] Updated weights for policy 1, policy_version 2160 (0.0008) -[2023-10-09 00:04:19,244][88326] Updated weights for policy 0, policy_version 2150 (0.0010) -[2023-10-09 00:04:19,366][88327] Updated weights for policy 1, policy_version 2170 (0.0009) -[2023-10-09 00:04:19,616][88326] Updated weights for policy 0, policy_version 2160 (0.0007) -[2023-10-09 00:04:19,993][88326] Updated weights for policy 0, policy_version 2170 (0.0008) -[2023-10-09 00:04:20,222][88088] Saving new best policy, reward=2.030! -[2023-10-09 00:04:23,425][88327] Updated weights for policy 1, policy_version 2180 (0.0008) -[2023-10-09 00:04:23,798][88327] Updated weights for policy 1, policy_version 2190 (0.0009) -[2023-10-09 00:04:23,974][87372] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 4456448. Throughput: 0: 1687.9, 1: 1705.2. Samples: 1123112. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-10-09 00:04:23,974][87372] Avg episode reward: [(0, '2.370'), (1, '1.430')] -[2023-10-09 00:04:24,069][88326] Updated weights for policy 0, policy_version 2180 (0.0008) -[2023-10-09 00:04:24,161][88327] Updated weights for policy 1, policy_version 2200 (0.0008) -[2023-10-09 00:04:24,431][88326] Updated weights for policy 0, policy_version 2190 (0.0007) -[2023-10-09 00:04:24,809][88326] Updated weights for policy 0, policy_version 2200 (0.0009) -[2023-10-09 00:04:25,114][88088] Saving new best policy, reward=2.370! -[2023-10-09 00:04:28,179][88327] Updated weights for policy 1, policy_version 2210 (0.0008) -[2023-10-09 00:04:28,599][88327] Updated weights for policy 1, policy_version 2220 (0.0009) -[2023-10-09 00:04:28,779][88326] Updated weights for policy 0, policy_version 2210 (0.0009) -[2023-10-09 00:04:28,963][88327] Updated weights for policy 1, policy_version 2230 (0.0008) -[2023-10-09 00:04:28,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 4521984. Throughput: 0: 1704.4, 1: 1709.9. Samples: 1144402. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:04:28,975][87372] Avg episode reward: [(0, '2.310'), (1, '1.520')] -[2023-10-09 00:04:29,142][88326] Updated weights for policy 0, policy_version 2220 (0.0008) -[2023-10-09 00:04:29,334][88327] Updated weights for policy 1, policy_version 2240 (0.0008) -[2023-10-09 00:04:29,506][88326] Updated weights for policy 0, policy_version 2230 (0.0010) -[2023-10-09 00:04:29,877][88326] Updated weights for policy 0, policy_version 2240 (0.0007) -[2023-10-09 00:04:33,329][88327] Updated weights for policy 1, policy_version 2250 (0.0008) -[2023-10-09 00:04:33,702][88327] Updated weights for policy 1, policy_version 2260 (0.0007) -[2023-10-09 00:04:33,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 4587520. Throughput: 0: 1704.3, 1: 1701.3. Samples: 1164966. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) -[2023-10-09 00:04:33,974][87372] Avg episode reward: [(0, '2.260'), (1, '1.580')] -[2023-10-09 00:04:34,064][88327] Updated weights for policy 1, policy_version 2270 (0.0008) -[2023-10-09 00:04:34,066][88326] Updated weights for policy 0, policy_version 2250 (0.0007) -[2023-10-09 00:04:34,138][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000002272_2326528.pth... -[2023-10-09 00:04:34,171][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000000672_688128.pth -[2023-10-09 00:04:34,435][88326] Updated weights for policy 0, policy_version 2260 (0.0009) -[2023-10-09 00:04:34,808][88326] Updated weights for policy 0, policy_version 2270 (0.0009) -[2023-10-09 00:04:34,883][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000002272_2326528.pth... -[2023-10-09 00:04:34,916][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000000672_688128.pth -[2023-10-09 00:04:37,982][88327] Updated weights for policy 1, policy_version 2280 (0.0008) -[2023-10-09 00:04:38,355][88327] Updated weights for policy 1, policy_version 2290 (0.0008) -[2023-10-09 00:04:38,730][88327] Updated weights for policy 1, policy_version 2300 (0.0008) -[2023-10-09 00:04:38,818][88326] Updated weights for policy 0, policy_version 2280 (0.0009) -[2023-10-09 00:04:38,974][87372] Fps is (10 sec: 16383.5, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 4685824. Throughput: 0: 1698.4, 1: 1704.3. Samples: 1174154. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-09 00:04:38,976][87372] Avg episode reward: [(0, '2.330'), (1, '1.520')] -[2023-10-09 00:04:39,196][88326] Updated weights for policy 0, policy_version 2290 (0.0007) -[2023-10-09 00:04:39,559][88326] Updated weights for policy 0, policy_version 2300 (0.0007) -[2023-10-09 00:04:42,851][88327] Updated weights for policy 1, policy_version 2310 (0.0009) -[2023-10-09 00:04:43,225][88327] Updated weights for policy 1, policy_version 2320 (0.0009) -[2023-10-09 00:04:43,553][88326] Updated weights for policy 0, policy_version 2310 (0.0008) -[2023-10-09 00:04:43,592][88327] Updated weights for policy 1, policy_version 2330 (0.0008) -[2023-10-09 00:04:43,922][88326] Updated weights for policy 0, policy_version 2320 (0.0008) -[2023-10-09 00:04:43,974][87372] Fps is (10 sec: 16383.9, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 4751360. Throughput: 0: 1694.2, 1: 1699.2. Samples: 1195032. Policy #0 lag: (min: 9.0, avg: 16.0, max: 41.0) -[2023-10-09 00:04:43,975][87372] Avg episode reward: [(0, '2.160'), (1, '1.680')] -[2023-10-09 00:04:43,976][88168] Saving new best policy, reward=1.680! -[2023-10-09 00:04:44,293][88326] Updated weights for policy 0, policy_version 2330 (0.0010) -[2023-10-09 00:04:47,559][88327] Updated weights for policy 1, policy_version 2340 (0.0009) -[2023-10-09 00:04:47,927][88327] Updated weights for policy 1, policy_version 2350 (0.0008) -[2023-10-09 00:04:48,251][88326] Updated weights for policy 0, policy_version 2340 (0.0009) -[2023-10-09 00:04:48,297][88327] Updated weights for policy 1, policy_version 2360 (0.0009) -[2023-10-09 00:04:48,619][88326] Updated weights for policy 0, policy_version 2350 (0.0008) -[2023-10-09 00:04:48,974][87372] Fps is (10 sec: 13107.6, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 4816896. Throughput: 0: 1694.4, 1: 1678.6. Samples: 1215046. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:04:48,975][87372] Avg episode reward: [(0, '2.220'), (1, '1.640')] -[2023-10-09 00:04:48,982][88326] Updated weights for policy 0, policy_version 2360 (0.0007) -[2023-10-09 00:04:52,253][88327] Updated weights for policy 1, policy_version 2370 (0.0008) -[2023-10-09 00:04:52,619][88327] Updated weights for policy 1, policy_version 2380 (0.0008) -[2023-10-09 00:04:52,944][88326] Updated weights for policy 0, policy_version 2370 (0.0009) -[2023-10-09 00:04:52,981][88327] Updated weights for policy 1, policy_version 2390 (0.0008) -[2023-10-09 00:04:53,314][88326] Updated weights for policy 0, policy_version 2380 (0.0008) -[2023-10-09 00:04:53,347][88327] Updated weights for policy 1, policy_version 2400 (0.0009) -[2023-10-09 00:04:53,674][88326] Updated weights for policy 0, policy_version 2390 (0.0010) -[2023-10-09 00:04:53,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 4882432. Throughput: 0: 1699.4, 1: 1694.2. Samples: 1225210. Policy #0 lag: (min: 14.0, avg: 18.6, max: 46.0) -[2023-10-09 00:04:53,975][87372] Avg episode reward: [(0, '2.340'), (1, '1.520')] -[2023-10-09 00:04:54,046][88326] Updated weights for policy 0, policy_version 2400 (0.0009) -[2023-10-09 00:04:57,401][88327] Updated weights for policy 1, policy_version 2410 (0.0009) -[2023-10-09 00:04:57,766][88327] Updated weights for policy 1, policy_version 2420 (0.0008) -[2023-10-09 00:04:58,130][88327] Updated weights for policy 1, policy_version 2430 (0.0008) -[2023-10-09 00:04:58,172][88326] Updated weights for policy 0, policy_version 2410 (0.0008) -[2023-10-09 00:04:58,552][88326] Updated weights for policy 0, policy_version 2420 (0.0008) -[2023-10-09 00:04:58,923][88326] Updated weights for policy 0, policy_version 2430 (0.0007) -[2023-10-09 00:04:58,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 4947968. Throughput: 0: 1699.2, 1: 1699.9. Samples: 1246138. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:04:58,974][87372] Avg episode reward: [(0, '2.530'), (1, '1.530')] -[2023-10-09 00:04:58,996][88088] Saving new best policy, reward=2.530! -[2023-10-09 00:05:02,266][88327] Updated weights for policy 1, policy_version 2440 (0.0009) -[2023-10-09 00:05:02,631][88327] Updated weights for policy 1, policy_version 2450 (0.0008) -[2023-10-09 00:05:02,860][88326] Updated weights for policy 0, policy_version 2440 (0.0008) -[2023-10-09 00:05:02,997][88327] Updated weights for policy 1, policy_version 2460 (0.0010) -[2023-10-09 00:05:03,220][88326] Updated weights for policy 0, policy_version 2450 (0.0008) -[2023-10-09 00:05:03,586][88326] Updated weights for policy 0, policy_version 2460 (0.0008) -[2023-10-09 00:05:03,974][87372] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 5046272. Throughput: 0: 1688.8, 1: 1668.5. Samples: 1265138. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:05:03,975][87372] Avg episode reward: [(0, '2.690'), (1, '1.380')] -[2023-10-09 00:05:03,983][88088] Saving new best policy, reward=2.690! -[2023-10-09 00:05:07,078][88327] Updated weights for policy 1, policy_version 2470 (0.0007) -[2023-10-09 00:05:07,435][88327] Updated weights for policy 1, policy_version 2480 (0.0010) -[2023-10-09 00:05:07,664][88326] Updated weights for policy 0, policy_version 2470 (0.0007) -[2023-10-09 00:05:07,801][88327] Updated weights for policy 1, policy_version 2490 (0.0009) -[2023-10-09 00:05:08,028][88326] Updated weights for policy 0, policy_version 2480 (0.0008) -[2023-10-09 00:05:08,405][88326] Updated weights for policy 0, policy_version 2490 (0.0007) -[2023-10-09 00:05:08,974][87372] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 5111808. Throughput: 0: 1701.5, 1: 1697.8. Samples: 1276078. Policy #0 lag: (min: 21.0, avg: 28.6, max: 53.0) -[2023-10-09 00:05:08,975][87372] Avg episode reward: [(0, '2.570'), (1, '1.460')] -[2023-10-09 00:05:11,881][88327] Updated weights for policy 1, policy_version 2500 (0.0008) -[2023-10-09 00:05:12,249][88327] Updated weights for policy 1, policy_version 2510 (0.0007) -[2023-10-09 00:05:12,571][88326] Updated weights for policy 0, policy_version 2500 (0.0007) -[2023-10-09 00:05:12,625][88327] Updated weights for policy 1, policy_version 2520 (0.0008) -[2023-10-09 00:05:12,940][88326] Updated weights for policy 0, policy_version 2510 (0.0007) -[2023-10-09 00:05:13,306][88326] Updated weights for policy 0, policy_version 2520 (0.0008) -[2023-10-09 00:05:13,974][87372] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 5177344. Throughput: 0: 1695.2, 1: 1687.8. Samples: 1296638. Policy #0 lag: (min: 18.0, avg: 21.2, max: 50.0) -[2023-10-09 00:05:13,975][87372] Avg episode reward: [(0, '2.540'), (1, '1.490')] -[2023-10-09 00:05:16,567][88327] Updated weights for policy 1, policy_version 2530 (0.0008) -[2023-10-09 00:05:16,974][88327] Updated weights for policy 1, policy_version 2540 (0.0010) -[2023-10-09 00:05:17,334][88327] Updated weights for policy 1, policy_version 2550 (0.0008) -[2023-10-09 00:05:17,403][88326] Updated weights for policy 0, policy_version 2530 (0.0009) -[2023-10-09 00:05:17,700][88327] Updated weights for policy 1, policy_version 2560 (0.0007) -[2023-10-09 00:05:17,779][88326] Updated weights for policy 0, policy_version 2540 (0.0010) -[2023-10-09 00:05:18,147][88326] Updated weights for policy 0, policy_version 2550 (0.0010) -[2023-10-09 00:05:18,516][88326] Updated weights for policy 0, policy_version 2560 (0.0007) -[2023-10-09 00:05:18,974][87372] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 5242880. Throughput: 0: 1671.2, 1: 1677.3. Samples: 1315650. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 00:05:18,975][87372] Avg episode reward: [(0, '2.600'), (1, '1.680')] -[2023-10-09 00:05:21,671][88327] Updated weights for policy 1, policy_version 2570 (0.0008) -[2023-10-09 00:05:22,040][88327] Updated weights for policy 1, policy_version 2580 (0.0007) -[2023-10-09 00:05:22,401][88327] Updated weights for policy 1, policy_version 2590 (0.0007) -[2023-10-09 00:05:22,780][88326] Updated weights for policy 0, policy_version 2570 (0.0008) -[2023-10-09 00:05:23,150][88326] Updated weights for policy 0, policy_version 2580 (0.0007) -[2023-10-09 00:05:23,509][88326] Updated weights for policy 0, policy_version 2590 (0.0008) -[2023-10-09 00:05:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 5308416. Throughput: 0: 1690.8, 1: 1699.3. Samples: 1326706. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-10-09 00:05:23,975][87372] Avg episode reward: [(0, '2.690'), (1, '1.760')] -[2023-10-09 00:05:23,976][88168] Saving new best policy, reward=1.760! -[2023-10-09 00:05:26,325][88327] Updated weights for policy 1, policy_version 2600 (0.0008) -[2023-10-09 00:05:26,697][88327] Updated weights for policy 1, policy_version 2610 (0.0010) -[2023-10-09 00:05:27,069][88327] Updated weights for policy 1, policy_version 2620 (0.0008) -[2023-10-09 00:05:27,532][88326] Updated weights for policy 0, policy_version 2600 (0.0009) -[2023-10-09 00:05:27,906][88326] Updated weights for policy 0, policy_version 2610 (0.0007) -[2023-10-09 00:05:28,284][88326] Updated weights for policy 0, policy_version 2620 (0.0008) -[2023-10-09 00:05:28,974][87372] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 5373952. Throughput: 0: 1688.5, 1: 1677.2. Samples: 1346488. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-09 00:05:28,974][87372] Avg episode reward: [(0, '2.830'), (1, '1.710')] -[2023-10-09 00:05:28,975][88088] Saving new best policy, reward=2.830! -[2023-10-09 00:05:31,096][88327] Updated weights for policy 1, policy_version 2630 (0.0007) -[2023-10-09 00:05:31,461][88327] Updated weights for policy 1, policy_version 2640 (0.0007) -[2023-10-09 00:05:31,820][88327] Updated weights for policy 1, policy_version 2650 (0.0007) -[2023-10-09 00:05:32,281][88326] Updated weights for policy 0, policy_version 2630 (0.0010) -[2023-10-09 00:05:32,656][88326] Updated weights for policy 0, policy_version 2640 (0.0010) -[2023-10-09 00:05:33,021][88326] Updated weights for policy 0, policy_version 2650 (0.0007) -[2023-10-09 00:05:33,974][87372] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 5439488. Throughput: 0: 1662.3, 1: 1698.9. Samples: 1366302. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) -[2023-10-09 00:05:33,975][87372] Avg episode reward: [(0, '2.390'), (1, '1.840')] -[2023-10-09 00:05:33,986][88168] Saving new best policy, reward=1.840! -[2023-10-09 00:05:35,761][88327] Updated weights for policy 1, policy_version 2660 (0.0009) -[2023-10-09 00:05:36,132][88327] Updated weights for policy 1, policy_version 2670 (0.0009) -[2023-10-09 00:05:36,500][88327] Updated weights for policy 1, policy_version 2680 (0.0010) -[2023-10-09 00:05:37,123][88326] Updated weights for policy 0, policy_version 2660 (0.0007) -[2023-10-09 00:05:37,501][88326] Updated weights for policy 0, policy_version 2670 (0.0008) -[2023-10-09 00:05:37,867][88326] Updated weights for policy 0, policy_version 2680 (0.0009) -[2023-10-09 00:05:38,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 5505024. Throughput: 0: 1681.1, 1: 1700.7. Samples: 1377390. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:05:38,975][87372] Avg episode reward: [(0, '2.470'), (1, '1.870')] -[2023-10-09 00:05:38,975][88168] Saving new best policy, reward=1.870! -[2023-10-09 00:05:40,467][88327] Updated weights for policy 1, policy_version 2690 (0.0008) -[2023-10-09 00:05:40,836][88327] Updated weights for policy 1, policy_version 2700 (0.0008) -[2023-10-09 00:05:41,214][88327] Updated weights for policy 1, policy_version 2710 (0.0009) -[2023-10-09 00:05:41,574][88327] Updated weights for policy 1, policy_version 2720 (0.0008) -[2023-10-09 00:05:41,708][88326] Updated weights for policy 0, policy_version 2690 (0.0008) -[2023-10-09 00:05:42,090][88326] Updated weights for policy 0, policy_version 2700 (0.0007) -[2023-10-09 00:05:42,451][88326] Updated weights for policy 0, policy_version 2710 (0.0008) -[2023-10-09 00:05:42,806][88326] Updated weights for policy 0, policy_version 2720 (0.0008) -[2023-10-09 00:05:43,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 5570560. Throughput: 0: 1666.2, 1: 1685.7. Samples: 1396974. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:05:43,975][87372] Avg episode reward: [(0, '2.670'), (1, '1.780')] -[2023-10-09 00:05:45,656][88327] Updated weights for policy 1, policy_version 2730 (0.0009) -[2023-10-09 00:05:46,025][88327] Updated weights for policy 1, policy_version 2740 (0.0007) -[2023-10-09 00:05:46,399][88327] Updated weights for policy 1, policy_version 2750 (0.0008) -[2023-10-09 00:05:46,931][88326] Updated weights for policy 0, policy_version 2730 (0.0010) -[2023-10-09 00:05:47,293][88326] Updated weights for policy 0, policy_version 2740 (0.0008) -[2023-10-09 00:05:47,669][88326] Updated weights for policy 0, policy_version 2750 (0.0007) -[2023-10-09 00:05:48,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 5636096. Throughput: 0: 1666.0, 1: 1717.2. Samples: 1417382. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-09 00:05:48,975][87372] Avg episode reward: [(0, '2.690'), (1, '1.850')] -[2023-10-09 00:05:50,459][88327] Updated weights for policy 1, policy_version 2760 (0.0008) -[2023-10-09 00:05:50,817][88327] Updated weights for policy 1, policy_version 2770 (0.0008) -[2023-10-09 00:05:51,194][88327] Updated weights for policy 1, policy_version 2780 (0.0007) -[2023-10-09 00:05:51,649][88326] Updated weights for policy 0, policy_version 2760 (0.0009) -[2023-10-09 00:05:52,025][88326] Updated weights for policy 0, policy_version 2770 (0.0007) -[2023-10-09 00:05:52,390][88326] Updated weights for policy 0, policy_version 2780 (0.0007) -[2023-10-09 00:05:53,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 5701632. Throughput: 0: 1684.2, 1: 1696.7. Samples: 1428218. Policy #0 lag: (min: 25.0, avg: 33.8, max: 57.0) -[2023-10-09 00:05:53,975][87372] Avg episode reward: [(0, '2.760'), (1, '1.840')] -[2023-10-09 00:05:55,191][88327] Updated weights for policy 1, policy_version 2790 (0.0009) -[2023-10-09 00:05:55,561][88327] Updated weights for policy 1, policy_version 2800 (0.0008) -[2023-10-09 00:05:55,929][88327] Updated weights for policy 1, policy_version 2810 (0.0009) -[2023-10-09 00:05:56,544][88326] Updated weights for policy 0, policy_version 2790 (0.0007) -[2023-10-09 00:05:56,918][88326] Updated weights for policy 0, policy_version 2800 (0.0007) -[2023-10-09 00:05:57,289][88326] Updated weights for policy 0, policy_version 2810 (0.0009) -[2023-10-09 00:05:58,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 5767168. Throughput: 0: 1666.3, 1: 1695.7. Samples: 1447926. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-09 00:05:58,975][87372] Avg episode reward: [(0, '2.610'), (1, '1.920')] -[2023-10-09 00:05:58,977][88168] Saving new best policy, reward=1.920! -[2023-10-09 00:05:59,914][88327] Updated weights for policy 1, policy_version 2820 (0.0007) -[2023-10-09 00:06:00,283][88327] Updated weights for policy 1, policy_version 2830 (0.0008) -[2023-10-09 00:06:00,647][88327] Updated weights for policy 1, policy_version 2840 (0.0007) -[2023-10-09 00:06:01,381][88326] Updated weights for policy 0, policy_version 2820 (0.0009) -[2023-10-09 00:06:01,751][88326] Updated weights for policy 0, policy_version 2830 (0.0009) -[2023-10-09 00:06:02,117][88326] Updated weights for policy 0, policy_version 2840 (0.0008) -[2023-10-09 00:06:03,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 5832704. Throughput: 0: 1680.2, 1: 1717.2. Samples: 1468534. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-09 00:06:03,975][87372] Avg episode reward: [(0, '2.820'), (1, '1.910')] -[2023-10-09 00:06:04,730][88327] Updated weights for policy 1, policy_version 2850 (0.0010) -[2023-10-09 00:06:05,156][88327] Updated weights for policy 1, policy_version 2860 (0.0009) -[2023-10-09 00:06:05,519][88327] Updated weights for policy 1, policy_version 2870 (0.0009) -[2023-10-09 00:06:05,890][88327] Updated weights for policy 1, policy_version 2880 (0.0009) -[2023-10-09 00:06:06,213][88326] Updated weights for policy 0, policy_version 2850 (0.0009) -[2023-10-09 00:06:06,576][88326] Updated weights for policy 0, policy_version 2860 (0.0009) -[2023-10-09 00:06:06,944][88326] Updated weights for policy 0, policy_version 2870 (0.0011) -[2023-10-09 00:06:07,312][88326] Updated weights for policy 0, policy_version 2880 (0.0007) -[2023-10-09 00:06:08,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 5898240. Throughput: 0: 1690.2, 1: 1685.4. Samples: 1478608. Policy #0 lag: (min: 17.0, avg: 44.7, max: 48.0) -[2023-10-09 00:06:08,976][87372] Avg episode reward: [(0, '2.850'), (1, '1.780')] -[2023-10-09 00:06:08,977][88088] Saving new best policy, reward=2.850! -[2023-10-09 00:06:09,621][88327] Updated weights for policy 1, policy_version 2890 (0.0008) -[2023-10-09 00:06:09,989][88327] Updated weights for policy 1, policy_version 2900 (0.0009) -[2023-10-09 00:06:10,361][88327] Updated weights for policy 1, policy_version 2910 (0.0007) -[2023-10-09 00:06:11,243][88326] Updated weights for policy 0, policy_version 2890 (0.0009) -[2023-10-09 00:06:11,613][88326] Updated weights for policy 0, policy_version 2900 (0.0007) -[2023-10-09 00:06:11,979][88326] Updated weights for policy 0, policy_version 2910 (0.0009) -[2023-10-09 00:06:13,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 5963776. Throughput: 0: 1667.2, 1: 1709.6. Samples: 1498444. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-09 00:06:13,975][87372] Avg episode reward: [(0, '2.500'), (1, '1.770')] -[2023-10-09 00:06:14,322][88327] Updated weights for policy 1, policy_version 2920 (0.0009) -[2023-10-09 00:06:14,686][88327] Updated weights for policy 1, policy_version 2930 (0.0007) -[2023-10-09 00:06:15,048][88327] Updated weights for policy 1, policy_version 2940 (0.0008) -[2023-10-09 00:06:16,127][88326] Updated weights for policy 0, policy_version 2920 (0.0007) -[2023-10-09 00:06:16,503][88326] Updated weights for policy 0, policy_version 2930 (0.0008) -[2023-10-09 00:06:16,880][88326] Updated weights for policy 0, policy_version 2940 (0.0009) -[2023-10-09 00:06:18,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 6029312. Throughput: 0: 1692.4, 1: 1710.3. Samples: 1519424. Policy #0 lag: (min: 3.0, avg: 13.9, max: 35.0) -[2023-10-09 00:06:18,974][87372] Avg episode reward: [(0, '2.600'), (1, '1.690')] -[2023-10-09 00:06:19,033][88327] Updated weights for policy 1, policy_version 2950 (0.0010) -[2023-10-09 00:06:19,403][88327] Updated weights for policy 1, policy_version 2960 (0.0008) -[2023-10-09 00:06:19,776][88327] Updated weights for policy 1, policy_version 2970 (0.0007) -[2023-10-09 00:06:20,780][88326] Updated weights for policy 0, policy_version 2950 (0.0008) -[2023-10-09 00:06:21,154][88326] Updated weights for policy 0, policy_version 2960 (0.0010) -[2023-10-09 00:06:21,535][88326] Updated weights for policy 0, policy_version 2970 (0.0009) -[2023-10-09 00:06:23,900][88327] Updated weights for policy 1, policy_version 2980 (0.0009) -[2023-10-09 00:06:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 6094848. Throughput: 0: 1681.5, 1: 1690.7. Samples: 1529138. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:06:23,975][87372] Avg episode reward: [(0, '2.440'), (1, '1.720')] -[2023-10-09 00:06:24,270][88327] Updated weights for policy 1, policy_version 2990 (0.0007) -[2023-10-09 00:06:24,637][88327] Updated weights for policy 1, policy_version 3000 (0.0007) -[2023-10-09 00:06:25,518][88326] Updated weights for policy 0, policy_version 2980 (0.0008) -[2023-10-09 00:06:25,881][88326] Updated weights for policy 0, policy_version 2990 (0.0010) -[2023-10-09 00:06:26,255][88326] Updated weights for policy 0, policy_version 3000 (0.0009) -[2023-10-09 00:06:28,699][88327] Updated weights for policy 1, policy_version 3010 (0.0007) -[2023-10-09 00:06:28,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 6160384. Throughput: 0: 1683.2, 1: 1705.9. Samples: 1549486. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:06:28,975][87372] Avg episode reward: [(0, '2.620'), (1, '1.830')] -[2023-10-09 00:06:29,063][88327] Updated weights for policy 1, policy_version 3020 (0.0010) -[2023-10-09 00:06:29,431][88327] Updated weights for policy 1, policy_version 3030 (0.0009) -[2023-10-09 00:06:29,798][88327] Updated weights for policy 1, policy_version 3040 (0.0008) -[2023-10-09 00:06:30,227][88326] Updated weights for policy 0, policy_version 3010 (0.0007) -[2023-10-09 00:06:30,599][88326] Updated weights for policy 0, policy_version 3020 (0.0007) -[2023-10-09 00:06:30,964][88326] Updated weights for policy 0, policy_version 3030 (0.0007) -[2023-10-09 00:06:31,335][88326] Updated weights for policy 0, policy_version 3040 (0.0008) -[2023-10-09 00:06:33,937][88327] Updated weights for policy 1, policy_version 3050 (0.0010) -[2023-10-09 00:06:33,974][87372] Fps is (10 sec: 13106.8, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 6225920. Throughput: 0: 1701.6, 1: 1702.7. Samples: 1570578. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:06:33,975][87372] Avg episode reward: [(0, '2.690'), (1, '1.980')] -[2023-10-09 00:06:33,985][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000003040_3112960.pth... -[2023-10-09 00:06:34,021][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000001472_1507328.pth -[2023-10-09 00:06:34,309][88327] Updated weights for policy 1, policy_version 3060 (0.0011) -[2023-10-09 00:06:34,679][88327] Updated weights for policy 1, policy_version 3070 (0.0012) -[2023-10-09 00:06:34,752][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000003072_3145728.pth... -[2023-10-09 00:06:34,782][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000001472_1507328.pth -[2023-10-09 00:06:34,785][88168] Saving new best policy, reward=1.980! -[2023-10-09 00:06:35,314][88326] Updated weights for policy 0, policy_version 3050 (0.0007) -[2023-10-09 00:06:35,693][88326] Updated weights for policy 0, policy_version 3060 (0.0009) -[2023-10-09 00:06:36,065][88326] Updated weights for policy 0, policy_version 3070 (0.0010) -[2023-10-09 00:06:38,939][88327] Updated weights for policy 1, policy_version 3080 (0.0009) -[2023-10-09 00:06:38,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 6291456. Throughput: 0: 1671.5, 1: 1694.6. Samples: 1579692. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:06:38,974][87372] Avg episode reward: [(0, '2.620'), (1, '1.990')] -[2023-10-09 00:06:39,307][88327] Updated weights for policy 1, policy_version 3090 (0.0008) -[2023-10-09 00:06:39,676][88327] Updated weights for policy 1, policy_version 3100 (0.0007) -[2023-10-09 00:06:39,815][88168] Saving new best policy, reward=1.990! -[2023-10-09 00:06:40,056][88326] Updated weights for policy 0, policy_version 3080 (0.0008) -[2023-10-09 00:06:40,427][88326] Updated weights for policy 0, policy_version 3090 (0.0008) -[2023-10-09 00:06:40,796][88326] Updated weights for policy 0, policy_version 3100 (0.0009) -[2023-10-09 00:06:43,690][88327] Updated weights for policy 1, policy_version 3110 (0.0008) -[2023-10-09 00:06:43,974][87372] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 6356992. Throughput: 0: 1690.5, 1: 1697.8. Samples: 1600398. Policy #0 lag: (min: 3.0, avg: 7.0, max: 35.0) -[2023-10-09 00:06:43,975][87372] Avg episode reward: [(0, '2.780'), (1, '2.090')] -[2023-10-09 00:06:44,070][88327] Updated weights for policy 1, policy_version 3120 (0.0010) -[2023-10-09 00:06:44,443][88327] Updated weights for policy 1, policy_version 3130 (0.0009) -[2023-10-09 00:06:44,664][88168] Saving new best policy, reward=2.090! -[2023-10-09 00:06:44,976][88326] Updated weights for policy 0, policy_version 3110 (0.0007) -[2023-10-09 00:06:45,348][88326] Updated weights for policy 0, policy_version 3120 (0.0009) -[2023-10-09 00:06:45,719][88326] Updated weights for policy 0, policy_version 3130 (0.0008) -[2023-10-09 00:06:48,424][88327] Updated weights for policy 1, policy_version 3140 (0.0008) -[2023-10-09 00:06:48,787][88327] Updated weights for policy 1, policy_version 3150 (0.0008) -[2023-10-09 00:06:48,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 6422528. Throughput: 0: 1697.9, 1: 1690.8. Samples: 1621026. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:06:48,974][87372] Avg episode reward: [(0, '2.830'), (1, '2.150')] -[2023-10-09 00:06:49,148][88327] Updated weights for policy 1, policy_version 3160 (0.0011) -[2023-10-09 00:06:49,438][88168] Saving new best policy, reward=2.150! -[2023-10-09 00:06:49,732][88326] Updated weights for policy 0, policy_version 3140 (0.0009) -[2023-10-09 00:06:50,101][88326] Updated weights for policy 0, policy_version 3150 (0.0008) -[2023-10-09 00:06:50,469][88326] Updated weights for policy 0, policy_version 3160 (0.0009) -[2023-10-09 00:06:53,323][88327] Updated weights for policy 1, policy_version 3170 (0.0011) -[2023-10-09 00:06:53,732][88327] Updated weights for policy 1, policy_version 3180 (0.0010) -[2023-10-09 00:06:53,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 6488064. Throughput: 0: 1674.4, 1: 1695.5. Samples: 1630252. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:06:53,975][87372] Avg episode reward: [(0, '2.790'), (1, '2.180')] -[2023-10-09 00:06:54,105][88327] Updated weights for policy 1, policy_version 3190 (0.0007) -[2023-10-09 00:06:54,378][88326] Updated weights for policy 0, policy_version 3170 (0.0008) -[2023-10-09 00:06:54,467][88168] Saving new best policy, reward=2.180! -[2023-10-09 00:06:54,471][88327] Updated weights for policy 1, policy_version 3200 (0.0008) -[2023-10-09 00:06:54,752][88326] Updated weights for policy 0, policy_version 3180 (0.0009) -[2023-10-09 00:06:55,114][88326] Updated weights for policy 0, policy_version 3190 (0.0007) -[2023-10-09 00:06:55,484][88326] Updated weights for policy 0, policy_version 3200 (0.0008) -[2023-10-09 00:06:58,236][88327] Updated weights for policy 1, policy_version 3210 (0.0009) -[2023-10-09 00:06:58,605][88327] Updated weights for policy 1, policy_version 3220 (0.0008) -[2023-10-09 00:06:58,973][88327] Updated weights for policy 1, policy_version 3230 (0.0010) -[2023-10-09 00:06:58,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 6553600. Throughput: 0: 1701.9, 1: 1696.0. Samples: 1651350. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 00:06:58,975][87372] Avg episode reward: [(0, '2.670'), (1, '2.170')] -[2023-10-09 00:06:59,678][88326] Updated weights for policy 0, policy_version 3210 (0.0011) -[2023-10-09 00:07:00,044][88326] Updated weights for policy 0, policy_version 3220 (0.0008) -[2023-10-09 00:07:00,408][88326] Updated weights for policy 0, policy_version 3230 (0.0007) -[2023-10-09 00:07:03,137][88327] Updated weights for policy 1, policy_version 3240 (0.0010) -[2023-10-09 00:07:03,495][88327] Updated weights for policy 1, policy_version 3250 (0.0009) -[2023-10-09 00:07:03,861][88327] Updated weights for policy 1, policy_version 3260 (0.0009) -[2023-10-09 00:07:03,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.1, 300 sec: 13440.4). Total num frames: 6619136. Throughput: 0: 1704.1, 1: 1684.5. Samples: 1671914. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:07:03,975][87372] Avg episode reward: [(0, '2.710'), (1, '2.290')] -[2023-10-09 00:07:04,008][88168] Saving new best policy, reward=2.290! -[2023-10-09 00:07:04,506][88326] Updated weights for policy 0, policy_version 3240 (0.0010) -[2023-10-09 00:07:04,878][88326] Updated weights for policy 0, policy_version 3250 (0.0008) -[2023-10-09 00:07:05,250][88326] Updated weights for policy 0, policy_version 3260 (0.0008) -[2023-10-09 00:07:07,803][88327] Updated weights for policy 1, policy_version 3270 (0.0009) -[2023-10-09 00:07:08,175][88327] Updated weights for policy 1, policy_version 3280 (0.0009) -[2023-10-09 00:07:08,555][88327] Updated weights for policy 1, policy_version 3290 (0.0009) -[2023-10-09 00:07:08,974][87372] Fps is (10 sec: 16384.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 6717440. Throughput: 0: 1689.1, 1: 1693.0. Samples: 1681330. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:07:08,975][87372] Avg episode reward: [(0, '2.600'), (1, '2.340')] -[2023-10-09 00:07:08,976][88168] Saving new best policy, reward=2.340! -[2023-10-09 00:07:09,165][88326] Updated weights for policy 0, policy_version 3270 (0.0009) -[2023-10-09 00:07:09,534][88326] Updated weights for policy 0, policy_version 3280 (0.0009) -[2023-10-09 00:07:09,907][88326] Updated weights for policy 0, policy_version 3290 (0.0010) -[2023-10-09 00:07:12,655][88327] Updated weights for policy 1, policy_version 3300 (0.0009) -[2023-10-09 00:07:13,028][88327] Updated weights for policy 1, policy_version 3310 (0.0011) -[2023-10-09 00:07:13,393][88327] Updated weights for policy 1, policy_version 3320 (0.0012) -[2023-10-09 00:07:13,974][87372] Fps is (10 sec: 16384.3, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 6782976. Throughput: 0: 1699.0, 1: 1692.7. Samples: 1702112. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:07:13,975][87372] Avg episode reward: [(0, '2.830'), (1, '2.200')] -[2023-10-09 00:07:13,992][88326] Updated weights for policy 0, policy_version 3300 (0.0009) -[2023-10-09 00:07:14,369][88326] Updated weights for policy 0, policy_version 3310 (0.0007) -[2023-10-09 00:07:14,731][88326] Updated weights for policy 0, policy_version 3320 (0.0008) -[2023-10-09 00:07:17,485][88327] Updated weights for policy 1, policy_version 3330 (0.0007) -[2023-10-09 00:07:17,843][88327] Updated weights for policy 1, policy_version 3340 (0.0007) -[2023-10-09 00:07:18,203][88327] Updated weights for policy 1, policy_version 3350 (0.0007) -[2023-10-09 00:07:18,559][88327] Updated weights for policy 1, policy_version 3360 (0.0007) -[2023-10-09 00:07:18,768][88326] Updated weights for policy 0, policy_version 3330 (0.0008) -[2023-10-09 00:07:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 6848512. Throughput: 0: 1699.0, 1: 1672.8. Samples: 1722310. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:07:18,975][87372] Avg episode reward: [(0, '2.790'), (1, '2.130')] -[2023-10-09 00:07:19,148][88326] Updated weights for policy 0, policy_version 3340 (0.0008) -[2023-10-09 00:07:19,523][88326] Updated weights for policy 0, policy_version 3350 (0.0008) -[2023-10-09 00:07:19,899][88326] Updated weights for policy 0, policy_version 3360 (0.0010) -[2023-10-09 00:07:22,607][88327] Updated weights for policy 1, policy_version 3370 (0.0007) -[2023-10-09 00:07:22,969][88327] Updated weights for policy 1, policy_version 3380 (0.0009) -[2023-10-09 00:07:23,354][88327] Updated weights for policy 1, policy_version 3390 (0.0009) -[2023-10-09 00:07:23,841][88326] Updated weights for policy 0, policy_version 3370 (0.0009) -[2023-10-09 00:07:23,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 6914048. Throughput: 0: 1697.2, 1: 1693.7. Samples: 1732280. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:07:23,975][87372] Avg episode reward: [(0, '2.830'), (1, '2.360')] -[2023-10-09 00:07:23,975][88168] Saving new best policy, reward=2.360! -[2023-10-09 00:07:24,215][88326] Updated weights for policy 0, policy_version 3380 (0.0007) -[2023-10-09 00:07:24,590][88326] Updated weights for policy 0, policy_version 3390 (0.0008) -[2023-10-09 00:07:27,283][88327] Updated weights for policy 1, policy_version 3400 (0.0007) -[2023-10-09 00:07:27,645][88327] Updated weights for policy 1, policy_version 3410 (0.0007) -[2023-10-09 00:07:28,016][88327] Updated weights for policy 1, policy_version 3420 (0.0008) -[2023-10-09 00:07:28,537][88326] Updated weights for policy 0, policy_version 3400 (0.0007) -[2023-10-09 00:07:28,908][88326] Updated weights for policy 0, policy_version 3410 (0.0007) -[2023-10-09 00:07:28,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 6979584. Throughput: 0: 1706.0, 1: 1693.5. Samples: 1753378. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:07:28,975][87372] Avg episode reward: [(0, '2.720'), (1, '2.370')] -[2023-10-09 00:07:28,976][88168] Saving new best policy, reward=2.370! -[2023-10-09 00:07:29,280][88326] Updated weights for policy 0, policy_version 3420 (0.0007) -[2023-10-09 00:07:31,958][88327] Updated weights for policy 1, policy_version 3430 (0.0008) -[2023-10-09 00:07:32,323][88327] Updated weights for policy 1, policy_version 3440 (0.0007) -[2023-10-09 00:07:32,691][88327] Updated weights for policy 1, policy_version 3450 (0.0007) -[2023-10-09 00:07:33,162][88326] Updated weights for policy 0, policy_version 3430 (0.0009) -[2023-10-09 00:07:33,531][88326] Updated weights for policy 0, policy_version 3440 (0.0010) -[2023-10-09 00:07:33,902][88326] Updated weights for policy 0, policy_version 3450 (0.0008) -[2023-10-09 00:07:33,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 7045120. Throughput: 0: 1706.6, 1: 1672.2. Samples: 1773072. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-09 00:07:33,975][87372] Avg episode reward: [(0, '2.770'), (1, '2.480')] -[2023-10-09 00:07:33,981][88168] Saving new best policy, reward=2.480! -[2023-10-09 00:07:36,927][88327] Updated weights for policy 1, policy_version 3460 (0.0008) -[2023-10-09 00:07:37,298][88327] Updated weights for policy 1, policy_version 3470 (0.0007) -[2023-10-09 00:07:37,681][88327] Updated weights for policy 1, policy_version 3480 (0.0007) -[2023-10-09 00:07:37,875][88326] Updated weights for policy 0, policy_version 3460 (0.0008) -[2023-10-09 00:07:38,258][88326] Updated weights for policy 0, policy_version 3470 (0.0008) -[2023-10-09 00:07:38,625][88326] Updated weights for policy 0, policy_version 3480 (0.0010) -[2023-10-09 00:07:38,974][87372] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 7143424. Throughput: 0: 1711.5, 1: 1698.4. Samples: 1783696. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-09 00:07:38,975][87372] Avg episode reward: [(0, '3.040'), (1, '2.720')] -[2023-10-09 00:07:38,976][88088] Saving new best policy, reward=3.040! -[2023-10-09 00:07:38,976][88168] Saving new best policy, reward=2.720! -[2023-10-09 00:07:41,645][88327] Updated weights for policy 1, policy_version 3490 (0.0008) -[2023-10-09 00:07:42,076][88327] Updated weights for policy 1, policy_version 3500 (0.0008) -[2023-10-09 00:07:42,447][88327] Updated weights for policy 1, policy_version 3510 (0.0009) -[2023-10-09 00:07:42,651][88326] Updated weights for policy 0, policy_version 3490 (0.0009) -[2023-10-09 00:07:42,814][88327] Updated weights for policy 1, policy_version 3520 (0.0010) -[2023-10-09 00:07:43,029][88326] Updated weights for policy 0, policy_version 3500 (0.0007) -[2023-10-09 00:07:43,409][88326] Updated weights for policy 0, policy_version 3510 (0.0007) -[2023-10-09 00:07:43,779][88326] Updated weights for policy 0, policy_version 3520 (0.0007) -[2023-10-09 00:07:43,974][87372] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 7208960. Throughput: 0: 1711.3, 1: 1682.2. Samples: 1804058. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:07:43,975][87372] Avg episode reward: [(0, '2.890'), (1, '2.630')] -[2023-10-09 00:07:46,779][88327] Updated weights for policy 1, policy_version 3530 (0.0008) -[2023-10-09 00:07:47,142][88327] Updated weights for policy 1, policy_version 3540 (0.0008) -[2023-10-09 00:07:47,511][88327] Updated weights for policy 1, policy_version 3550 (0.0009) -[2023-10-09 00:07:47,849][88326] Updated weights for policy 0, policy_version 3530 (0.0007) -[2023-10-09 00:07:48,216][88326] Updated weights for policy 0, policy_version 3540 (0.0007) -[2023-10-09 00:07:48,588][88326] Updated weights for policy 0, policy_version 3550 (0.0010) -[2023-10-09 00:07:48,974][87372] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 7274496. Throughput: 0: 1693.6, 1: 1673.1. Samples: 1823416. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:07:48,975][87372] Avg episode reward: [(0, '2.890'), (1, '2.610')] -[2023-10-09 00:07:51,595][88327] Updated weights for policy 1, policy_version 3560 (0.0010) -[2023-10-09 00:07:51,965][88327] Updated weights for policy 1, policy_version 3570 (0.0010) -[2023-10-09 00:07:52,326][88327] Updated weights for policy 1, policy_version 3580 (0.0009) -[2023-10-09 00:07:52,517][88326] Updated weights for policy 0, policy_version 3560 (0.0010) -[2023-10-09 00:07:52,892][88326] Updated weights for policy 0, policy_version 3570 (0.0010) -[2023-10-09 00:07:53,276][88326] Updated weights for policy 0, policy_version 3580 (0.0009) -[2023-10-09 00:07:53,974][87372] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 7340032. Throughput: 0: 1709.7, 1: 1693.2. Samples: 1834460. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-09 00:07:53,975][87372] Avg episode reward: [(0, '2.980'), (1, '2.730')] -[2023-10-09 00:07:53,976][88168] Saving new best policy, reward=2.730! -[2023-10-09 00:07:56,461][88327] Updated weights for policy 1, policy_version 3590 (0.0009) -[2023-10-09 00:07:56,833][88327] Updated weights for policy 1, policy_version 3600 (0.0007) -[2023-10-09 00:07:57,206][88327] Updated weights for policy 1, policy_version 3610 (0.0008) -[2023-10-09 00:07:57,328][88326] Updated weights for policy 0, policy_version 3590 (0.0007) -[2023-10-09 00:07:57,695][88326] Updated weights for policy 0, policy_version 3600 (0.0007) -[2023-10-09 00:07:58,070][88326] Updated weights for policy 0, policy_version 3610 (0.0007) -[2023-10-09 00:07:58,974][87372] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 7405568. Throughput: 0: 1711.8, 1: 1670.9. Samples: 1854332. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-09 00:07:58,975][87372] Avg episode reward: [(0, '2.850'), (1, '2.720')] -[2023-10-09 00:08:01,404][88327] Updated weights for policy 1, policy_version 3620 (0.0007) -[2023-10-09 00:08:01,783][88327] Updated weights for policy 1, policy_version 3630 (0.0007) -[2023-10-09 00:08:02,013][88326] Updated weights for policy 0, policy_version 3620 (0.0009) -[2023-10-09 00:08:02,157][88327] Updated weights for policy 1, policy_version 3640 (0.0009) -[2023-10-09 00:08:02,381][88326] Updated weights for policy 0, policy_version 3630 (0.0007) -[2023-10-09 00:08:02,749][88326] Updated weights for policy 0, policy_version 3640 (0.0007) -[2023-10-09 00:08:03,974][87372] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 7471104. Throughput: 0: 1681.1, 1: 1678.4. Samples: 1873486. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-10-09 00:08:03,974][87372] Avg episode reward: [(0, '2.870'), (1, '2.490')] -[2023-10-09 00:08:05,986][88327] Updated weights for policy 1, policy_version 3650 (0.0008) -[2023-10-09 00:08:06,347][88327] Updated weights for policy 1, policy_version 3660 (0.0008) -[2023-10-09 00:08:06,725][88327] Updated weights for policy 1, policy_version 3670 (0.0008) -[2023-10-09 00:08:06,785][88326] Updated weights for policy 0, policy_version 3650 (0.0007) -[2023-10-09 00:08:07,090][88327] Updated weights for policy 1, policy_version 3680 (0.0007) -[2023-10-09 00:08:07,153][88326] Updated weights for policy 0, policy_version 3660 (0.0007) -[2023-10-09 00:08:07,515][88326] Updated weights for policy 0, policy_version 3670 (0.0007) -[2023-10-09 00:08:07,883][88326] Updated weights for policy 0, policy_version 3680 (0.0007) -[2023-10-09 00:08:08,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 7536640. Throughput: 0: 1712.6, 1: 1683.1. Samples: 1885088. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-10-09 00:08:08,975][87372] Avg episode reward: [(0, '2.780'), (1, '2.560')] -[2023-10-09 00:08:11,279][88327] Updated weights for policy 1, policy_version 3690 (0.0008) -[2023-10-09 00:08:11,639][88327] Updated weights for policy 1, policy_version 3700 (0.0009) -[2023-10-09 00:08:11,885][88326] Updated weights for policy 0, policy_version 3690 (0.0007) -[2023-10-09 00:08:12,007][88327] Updated weights for policy 1, policy_version 3710 (0.0009) -[2023-10-09 00:08:12,256][88326] Updated weights for policy 0, policy_version 3700 (0.0008) -[2023-10-09 00:08:12,626][88326] Updated weights for policy 0, policy_version 3710 (0.0011) -[2023-10-09 00:08:13,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 7602176. Throughput: 0: 1689.7, 1: 1664.9. Samples: 1904334. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:08:13,974][87372] Avg episode reward: [(0, '2.930'), (1, '2.640')] -[2023-10-09 00:08:15,985][88327] Updated weights for policy 1, policy_version 3720 (0.0009) -[2023-10-09 00:08:16,343][88327] Updated weights for policy 1, policy_version 3730 (0.0011) -[2023-10-09 00:08:16,707][88327] Updated weights for policy 1, policy_version 3740 (0.0007) -[2023-10-09 00:08:16,865][88326] Updated weights for policy 0, policy_version 3720 (0.0007) -[2023-10-09 00:08:17,228][88326] Updated weights for policy 0, policy_version 3730 (0.0011) -[2023-10-09 00:08:17,615][88326] Updated weights for policy 0, policy_version 3740 (0.0008) -[2023-10-09 00:08:18,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 7667712. Throughput: 0: 1674.7, 1: 1687.8. Samples: 1924388. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:08:18,975][87372] Avg episode reward: [(0, '3.000'), (1, '2.660')] -[2023-10-09 00:08:20,793][88327] Updated weights for policy 1, policy_version 3750 (0.0008) -[2023-10-09 00:08:21,167][88327] Updated weights for policy 1, policy_version 3760 (0.0007) -[2023-10-09 00:08:21,540][88327] Updated weights for policy 1, policy_version 3770 (0.0007) -[2023-10-09 00:08:21,751][88326] Updated weights for policy 0, policy_version 3750 (0.0009) -[2023-10-09 00:08:22,120][88326] Updated weights for policy 0, policy_version 3760 (0.0008) -[2023-10-09 00:08:22,491][88326] Updated weights for policy 0, policy_version 3770 (0.0007) -[2023-10-09 00:08:23,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 7733248. Throughput: 0: 1694.0, 1: 1677.6. Samples: 1935418. Policy #0 lag: (min: 22.0, avg: 44.7, max: 48.0) -[2023-10-09 00:08:23,975][87372] Avg episode reward: [(0, '3.170'), (1, '2.750')] -[2023-10-09 00:08:23,976][88168] Saving new best policy, reward=2.750! -[2023-10-09 00:08:23,976][88088] Saving new best policy, reward=3.170! -[2023-10-09 00:08:25,544][88327] Updated weights for policy 1, policy_version 3780 (0.0009) -[2023-10-09 00:08:25,922][88327] Updated weights for policy 1, policy_version 3790 (0.0010) -[2023-10-09 00:08:26,283][88327] Updated weights for policy 1, policy_version 3800 (0.0008) -[2023-10-09 00:08:26,472][88326] Updated weights for policy 0, policy_version 3780 (0.0008) -[2023-10-09 00:08:26,838][88326] Updated weights for policy 0, policy_version 3790 (0.0007) -[2023-10-09 00:08:27,211][88326] Updated weights for policy 0, policy_version 3800 (0.0008) -[2023-10-09 00:08:28,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 7798784. Throughput: 0: 1670.6, 1: 1674.0. Samples: 1954566. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-10-09 00:08:28,975][87372] Avg episode reward: [(0, '3.100'), (1, '2.610')] -[2023-10-09 00:08:30,370][88327] Updated weights for policy 1, policy_version 3810 (0.0008) -[2023-10-09 00:08:30,790][88327] Updated weights for policy 1, policy_version 3820 (0.0008) -[2023-10-09 00:08:31,163][88327] Updated weights for policy 1, policy_version 3830 (0.0008) -[2023-10-09 00:08:31,206][88326] Updated weights for policy 0, policy_version 3810 (0.0008) -[2023-10-09 00:08:31,528][88327] Updated weights for policy 1, policy_version 3840 (0.0010) -[2023-10-09 00:08:31,567][88326] Updated weights for policy 0, policy_version 3820 (0.0009) -[2023-10-09 00:08:31,936][88326] Updated weights for policy 0, policy_version 3830 (0.0008) -[2023-10-09 00:08:32,309][88326] Updated weights for policy 0, policy_version 3840 (0.0008) -[2023-10-09 00:08:33,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 7864320. Throughput: 0: 1685.8, 1: 1687.5. Samples: 1975214. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-10-09 00:08:33,975][87372] Avg episode reward: [(0, '2.900'), (1, '2.610')] -[2023-10-09 00:08:33,983][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000003840_3932160.pth... -[2023-10-09 00:08:33,984][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000003840_3932160.pth... -[2023-10-09 00:08:34,013][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000002272_2326528.pth -[2023-10-09 00:08:34,020][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000002272_2326528.pth -[2023-10-09 00:08:35,425][88327] Updated weights for policy 1, policy_version 3850 (0.0010) -[2023-10-09 00:08:35,804][88327] Updated weights for policy 1, policy_version 3860 (0.0009) -[2023-10-09 00:08:36,162][88327] Updated weights for policy 1, policy_version 3870 (0.0007) -[2023-10-09 00:08:36,427][88326] Updated weights for policy 0, policy_version 3850 (0.0007) -[2023-10-09 00:08:36,803][88326] Updated weights for policy 0, policy_version 3860 (0.0010) -[2023-10-09 00:08:37,181][88326] Updated weights for policy 0, policy_version 3870 (0.0010) -[2023-10-09 00:08:38,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 7929856. Throughput: 0: 1694.8, 1: 1665.1. Samples: 1985654. Policy #0 lag: (min: 17.0, avg: 25.4, max: 49.0) -[2023-10-09 00:08:38,974][87372] Avg episode reward: [(0, '2.980'), (1, '2.700')] -[2023-10-09 00:08:40,209][88327] Updated weights for policy 1, policy_version 3880 (0.0010) -[2023-10-09 00:08:40,572][88327] Updated weights for policy 1, policy_version 3890 (0.0011) -[2023-10-09 00:08:40,945][88327] Updated weights for policy 1, policy_version 3900 (0.0009) -[2023-10-09 00:08:41,170][88326] Updated weights for policy 0, policy_version 3880 (0.0009) -[2023-10-09 00:08:41,549][88326] Updated weights for policy 0, policy_version 3890 (0.0010) -[2023-10-09 00:08:41,913][88326] Updated weights for policy 0, policy_version 3900 (0.0010) -[2023-10-09 00:08:43,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 7995392. Throughput: 0: 1667.0, 1: 1686.5. Samples: 2005238. Policy #0 lag: (min: 17.0, avg: 25.4, max: 49.0) -[2023-10-09 00:08:43,975][87372] Avg episode reward: [(0, '2.920'), (1, '2.680')] -[2023-10-09 00:08:44,937][88327] Updated weights for policy 1, policy_version 3910 (0.0008) -[2023-10-09 00:08:45,304][88327] Updated weights for policy 1, policy_version 3920 (0.0008) -[2023-10-09 00:08:45,679][88327] Updated weights for policy 1, policy_version 3930 (0.0009) -[2023-10-09 00:08:45,943][88326] Updated weights for policy 0, policy_version 3910 (0.0007) -[2023-10-09 00:08:46,309][88326] Updated weights for policy 0, policy_version 3920 (0.0008) -[2023-10-09 00:08:46,672][88326] Updated weights for policy 0, policy_version 3930 (0.0008) -[2023-10-09 00:08:48,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 8060928. Throughput: 0: 1692.5, 1: 1702.4. Samples: 2026260. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-09 00:08:48,975][87372] Avg episode reward: [(0, '2.880'), (1, '2.550')] -[2023-10-09 00:08:49,826][88327] Updated weights for policy 1, policy_version 3940 (0.0008) -[2023-10-09 00:08:50,186][88327] Updated weights for policy 1, policy_version 3950 (0.0008) -[2023-10-09 00:08:50,556][88327] Updated weights for policy 1, policy_version 3960 (0.0010) -[2023-10-09 00:08:50,663][88326] Updated weights for policy 0, policy_version 3940 (0.0009) -[2023-10-09 00:08:51,038][88326] Updated weights for policy 0, policy_version 3950 (0.0007) -[2023-10-09 00:08:51,410][88326] Updated weights for policy 0, policy_version 3960 (0.0007) -[2023-10-09 00:08:53,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 8126464. Throughput: 0: 1677.6, 1: 1676.7. Samples: 2036028. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-09 00:08:53,975][87372] Avg episode reward: [(0, '2.950'), (1, '2.680')] -[2023-10-09 00:08:54,523][88327] Updated weights for policy 1, policy_version 3970 (0.0007) -[2023-10-09 00:08:54,885][88327] Updated weights for policy 1, policy_version 3980 (0.0009) -[2023-10-09 00:08:55,260][88327] Updated weights for policy 1, policy_version 3990 (0.0009) -[2023-10-09 00:08:55,313][88326] Updated weights for policy 0, policy_version 3970 (0.0007) -[2023-10-09 00:08:55,623][88327] Updated weights for policy 1, policy_version 4000 (0.0009) -[2023-10-09 00:08:55,672][88326] Updated weights for policy 0, policy_version 3980 (0.0007) -[2023-10-09 00:08:56,049][88326] Updated weights for policy 0, policy_version 3990 (0.0009) -[2023-10-09 00:08:56,425][88326] Updated weights for policy 0, policy_version 4000 (0.0007) -[2023-10-09 00:08:58,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 8192000. Throughput: 0: 1681.1, 1: 1692.4. Samples: 2056142. Policy #0 lag: (min: 21.0, avg: 22.5, max: 47.0) -[2023-10-09 00:08:58,975][87372] Avg episode reward: [(0, '2.780'), (1, '2.720')] -[2023-10-09 00:08:59,894][88327] Updated weights for policy 1, policy_version 4010 (0.0007) -[2023-10-09 00:09:00,251][88327] Updated weights for policy 1, policy_version 4020 (0.0008) -[2023-10-09 00:09:00,440][88326] Updated weights for policy 0, policy_version 4010 (0.0009) -[2023-10-09 00:09:00,620][88327] Updated weights for policy 1, policy_version 4030 (0.0007) -[2023-10-09 00:09:00,806][88326] Updated weights for policy 0, policy_version 4020 (0.0010) -[2023-10-09 00:09:01,180][88326] Updated weights for policy 0, policy_version 4030 (0.0010) -[2023-10-09 00:09:03,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 8257536. Throughput: 0: 1701.9, 1: 1690.5. Samples: 2077046. Policy #0 lag: (min: 21.0, avg: 22.5, max: 47.0) -[2023-10-09 00:09:03,975][87372] Avg episode reward: [(0, '3.080'), (1, '3.150')] -[2023-10-09 00:09:03,986][88168] Saving new best policy, reward=3.150! -[2023-10-09 00:09:04,569][88327] Updated weights for policy 1, policy_version 4040 (0.0007) -[2023-10-09 00:09:04,933][88327] Updated weights for policy 1, policy_version 4050 (0.0007) -[2023-10-09 00:09:05,157][88326] Updated weights for policy 0, policy_version 4040 (0.0008) -[2023-10-09 00:09:05,299][88327] Updated weights for policy 1, policy_version 4060 (0.0008) -[2023-10-09 00:09:05,520][88326] Updated weights for policy 0, policy_version 4050 (0.0008) -[2023-10-09 00:09:05,892][88326] Updated weights for policy 0, policy_version 4060 (0.0007) -[2023-10-09 00:09:08,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 8323072. Throughput: 0: 1675.7, 1: 1673.6. Samples: 2086138. Policy #0 lag: (min: 9.0, avg: 20.4, max: 41.0) -[2023-10-09 00:09:08,975][87372] Avg episode reward: [(0, '2.910'), (1, '3.140')] -[2023-10-09 00:09:09,394][88327] Updated weights for policy 1, policy_version 4070 (0.0010) -[2023-10-09 00:09:09,759][88327] Updated weights for policy 1, policy_version 4080 (0.0008) -[2023-10-09 00:09:09,842][88326] Updated weights for policy 0, policy_version 4070 (0.0007) -[2023-10-09 00:09:10,130][88327] Updated weights for policy 1, policy_version 4090 (0.0008) -[2023-10-09 00:09:10,205][88326] Updated weights for policy 0, policy_version 4080 (0.0008) -[2023-10-09 00:09:10,575][88326] Updated weights for policy 0, policy_version 4090 (0.0011) -[2023-10-09 00:09:13,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 8388608. Throughput: 0: 1699.0, 1: 1693.1. Samples: 2107208. Policy #0 lag: (min: 2.0, avg: 9.0, max: 34.0) -[2023-10-09 00:09:13,975][87372] Avg episode reward: [(0, '2.870'), (1, '3.190')] -[2023-10-09 00:09:14,015][88327] Updated weights for policy 1, policy_version 4100 (0.0009) -[2023-10-09 00:09:14,374][88327] Updated weights for policy 1, policy_version 4110 (0.0010) -[2023-10-09 00:09:14,739][88327] Updated weights for policy 1, policy_version 4120 (0.0008) -[2023-10-09 00:09:14,795][88326] Updated weights for policy 0, policy_version 4100 (0.0011) -[2023-10-09 00:09:15,027][88168] Saving new best policy, reward=3.190! -[2023-10-09 00:09:15,171][88326] Updated weights for policy 0, policy_version 4110 (0.0008) -[2023-10-09 00:09:15,537][88326] Updated weights for policy 0, policy_version 4120 (0.0008) -[2023-10-09 00:09:18,886][88327] Updated weights for policy 1, policy_version 4130 (0.0008) -[2023-10-09 00:09:18,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 8454144. Throughput: 0: 1701.0, 1: 1699.3. Samples: 2128228. Policy #0 lag: (min: 7.0, avg: 17.2, max: 39.0) -[2023-10-09 00:09:18,975][87372] Avg episode reward: [(0, '3.000'), (1, '3.120')] -[2023-10-09 00:09:19,276][88327] Updated weights for policy 1, policy_version 4140 (0.0009) -[2023-10-09 00:09:19,606][88326] Updated weights for policy 0, policy_version 4130 (0.0007) -[2023-10-09 00:09:19,640][88327] Updated weights for policy 1, policy_version 4150 (0.0008) -[2023-10-09 00:09:19,969][88326] Updated weights for policy 0, policy_version 4140 (0.0009) -[2023-10-09 00:09:20,002][88327] Updated weights for policy 1, policy_version 4160 (0.0008) -[2023-10-09 00:09:20,344][88326] Updated weights for policy 0, policy_version 4150 (0.0009) -[2023-10-09 00:09:20,716][88326] Updated weights for policy 0, policy_version 4160 (0.0008) -[2023-10-09 00:09:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 8519680. Throughput: 0: 1677.6, 1: 1693.2. Samples: 2137340. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:09:23,975][87372] Avg episode reward: [(0, '2.980'), (1, '3.270')] -[2023-10-09 00:09:24,064][88327] Updated weights for policy 1, policy_version 4170 (0.0009) -[2023-10-09 00:09:24,428][88327] Updated weights for policy 1, policy_version 4180 (0.0008) -[2023-10-09 00:09:24,793][88327] Updated weights for policy 1, policy_version 4190 (0.0007) -[2023-10-09 00:09:24,806][88326] Updated weights for policy 0, policy_version 4170 (0.0007) -[2023-10-09 00:09:24,857][88168] Saving new best policy, reward=3.270! -[2023-10-09 00:09:25,174][88326] Updated weights for policy 0, policy_version 4180 (0.0007) -[2023-10-09 00:09:25,544][88326] Updated weights for policy 0, policy_version 4190 (0.0009) -[2023-10-09 00:09:28,744][88327] Updated weights for policy 1, policy_version 4200 (0.0010) -[2023-10-09 00:09:28,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 8585216. Throughput: 0: 1707.0, 1: 1693.7. Samples: 2158266. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:09:28,975][87372] Avg episode reward: [(0, '2.990'), (1, '3.040')] -[2023-10-09 00:09:29,111][88327] Updated weights for policy 1, policy_version 4210 (0.0010) -[2023-10-09 00:09:29,405][88326] Updated weights for policy 0, policy_version 4200 (0.0009) -[2023-10-09 00:09:29,476][88327] Updated weights for policy 1, policy_version 4220 (0.0010) -[2023-10-09 00:09:29,779][88326] Updated weights for policy 0, policy_version 4210 (0.0008) -[2023-10-09 00:09:30,151][88326] Updated weights for policy 0, policy_version 4220 (0.0007) -[2023-10-09 00:09:33,751][88327] Updated weights for policy 1, policy_version 4230 (0.0009) -[2023-10-09 00:09:33,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.3, 300 sec: 13440.4). Total num frames: 8650752. Throughput: 0: 1710.6, 1: 1683.9. Samples: 2179012. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:09:33,975][87372] Avg episode reward: [(0, '3.200'), (1, '2.960')] -[2023-10-09 00:09:34,108][88327] Updated weights for policy 1, policy_version 4240 (0.0009) -[2023-10-09 00:09:34,140][88326] Updated weights for policy 0, policy_version 4230 (0.0008) -[2023-10-09 00:09:34,480][88327] Updated weights for policy 1, policy_version 4250 (0.0007) -[2023-10-09 00:09:34,512][88326] Updated weights for policy 0, policy_version 4240 (0.0007) -[2023-10-09 00:09:34,874][88326] Updated weights for policy 0, policy_version 4250 (0.0009) -[2023-10-09 00:09:35,094][88088] Saving new best policy, reward=3.200! -[2023-10-09 00:09:38,451][88327] Updated weights for policy 1, policy_version 4260 (0.0008) -[2023-10-09 00:09:38,817][88327] Updated weights for policy 1, policy_version 4270 (0.0008) -[2023-10-09 00:09:38,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 8716288. Throughput: 0: 1695.6, 1: 1686.0. Samples: 2188198. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:09:38,975][87372] Avg episode reward: [(0, '3.190'), (1, '3.080')] -[2023-10-09 00:09:39,023][88326] Updated weights for policy 0, policy_version 4260 (0.0008) -[2023-10-09 00:09:39,175][88327] Updated weights for policy 1, policy_version 4280 (0.0011) -[2023-10-09 00:09:39,400][88326] Updated weights for policy 0, policy_version 4270 (0.0009) -[2023-10-09 00:09:39,769][88326] Updated weights for policy 0, policy_version 4280 (0.0009) -[2023-10-09 00:09:43,360][88327] Updated weights for policy 1, policy_version 4290 (0.0009) -[2023-10-09 00:09:43,737][88327] Updated weights for policy 1, policy_version 4300 (0.0009) -[2023-10-09 00:09:43,780][88326] Updated weights for policy 0, policy_version 4290 (0.0007) -[2023-10-09 00:09:43,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 8781824. Throughput: 0: 1707.8, 1: 1684.3. Samples: 2208784. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:09:43,975][87372] Avg episode reward: [(0, '3.300'), (1, '3.220')] -[2023-10-09 00:09:44,103][88327] Updated weights for policy 1, policy_version 4310 (0.0007) -[2023-10-09 00:09:44,153][88326] Updated weights for policy 0, policy_version 4300 (0.0008) -[2023-10-09 00:09:44,461][88327] Updated weights for policy 1, policy_version 4320 (0.0008) -[2023-10-09 00:09:44,525][88326] Updated weights for policy 0, policy_version 4310 (0.0007) -[2023-10-09 00:09:44,891][88088] Saving new best policy, reward=3.300! -[2023-10-09 00:09:44,896][88326] Updated weights for policy 0, policy_version 4320 (0.0007) -[2023-10-09 00:09:48,529][88327] Updated weights for policy 1, policy_version 4330 (0.0007) -[2023-10-09 00:09:48,904][88327] Updated weights for policy 1, policy_version 4340 (0.0007) -[2023-10-09 00:09:48,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 8847360. Throughput: 0: 1701.7, 1: 1691.6. Samples: 2229744. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:09:48,975][87372] Avg episode reward: [(0, '3.120'), (1, '3.170')] -[2023-10-09 00:09:49,030][88326] Updated weights for policy 0, policy_version 4330 (0.0008) -[2023-10-09 00:09:49,270][88327] Updated weights for policy 1, policy_version 4350 (0.0008) -[2023-10-09 00:09:49,403][88326] Updated weights for policy 0, policy_version 4340 (0.0008) -[2023-10-09 00:09:49,771][88326] Updated weights for policy 0, policy_version 4350 (0.0007) -[2023-10-09 00:09:53,206][88327] Updated weights for policy 1, policy_version 4360 (0.0008) -[2023-10-09 00:09:53,579][88327] Updated weights for policy 1, policy_version 4370 (0.0009) -[2023-10-09 00:09:53,795][88326] Updated weights for policy 0, policy_version 4360 (0.0008) -[2023-10-09 00:09:53,957][88327] Updated weights for policy 1, policy_version 4380 (0.0010) -[2023-10-09 00:09:53,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 8912896. Throughput: 0: 1700.4, 1: 1693.4. Samples: 2238858. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:09:53,975][87372] Avg episode reward: [(0, '3.050'), (1, '3.100')] -[2023-10-09 00:09:54,162][88326] Updated weights for policy 0, policy_version 4370 (0.0009) -[2023-10-09 00:09:54,539][88326] Updated weights for policy 0, policy_version 4380 (0.0010) -[2023-10-09 00:09:58,057][88327] Updated weights for policy 1, policy_version 4390 (0.0010) -[2023-10-09 00:09:58,430][88327] Updated weights for policy 1, policy_version 4400 (0.0010) -[2023-10-09 00:09:58,597][88326] Updated weights for policy 0, policy_version 4390 (0.0009) -[2023-10-09 00:09:58,787][88327] Updated weights for policy 1, policy_version 4410 (0.0008) -[2023-10-09 00:09:58,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 8978432. Throughput: 0: 1693.7, 1: 1694.8. Samples: 2259688. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:09:58,974][88326] Updated weights for policy 0, policy_version 4400 (0.0008) -[2023-10-09 00:09:58,975][87372] Avg episode reward: [(0, '3.170'), (1, '3.140')] -[2023-10-09 00:09:59,340][88326] Updated weights for policy 0, policy_version 4410 (0.0010) -[2023-10-09 00:10:02,668][88327] Updated weights for policy 1, policy_version 4420 (0.0009) -[2023-10-09 00:10:03,039][88327] Updated weights for policy 1, policy_version 4430 (0.0010) -[2023-10-09 00:10:03,190][88326] Updated weights for policy 0, policy_version 4420 (0.0008) -[2023-10-09 00:10:03,397][88327] Updated weights for policy 1, policy_version 4440 (0.0007) -[2023-10-09 00:10:03,558][88326] Updated weights for policy 0, policy_version 4430 (0.0008) -[2023-10-09 00:10:03,922][88326] Updated weights for policy 0, policy_version 4440 (0.0007) -[2023-10-09 00:10:03,974][87372] Fps is (10 sec: 16384.0, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 9076736. Throughput: 0: 1692.2, 1: 1678.9. Samples: 2279928. Policy #0 lag: (min: 31.0, avg: 31.8, max: 51.0) -[2023-10-09 00:10:03,975][87372] Avg episode reward: [(0, '3.270'), (1, '3.020')] -[2023-10-09 00:10:07,482][88327] Updated weights for policy 1, policy_version 4450 (0.0007) -[2023-10-09 00:10:07,906][88327] Updated weights for policy 1, policy_version 4460 (0.0007) -[2023-10-09 00:10:08,045][88326] Updated weights for policy 0, policy_version 4450 (0.0008) -[2023-10-09 00:10:08,283][88327] Updated weights for policy 1, policy_version 4470 (0.0008) -[2023-10-09 00:10:08,420][88326] Updated weights for policy 0, policy_version 4460 (0.0008) -[2023-10-09 00:10:08,645][88327] Updated weights for policy 1, policy_version 4480 (0.0009) -[2023-10-09 00:10:08,786][88326] Updated weights for policy 0, policy_version 4470 (0.0008) -[2023-10-09 00:10:08,974][87372] Fps is (10 sec: 16383.7, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 9142272. Throughput: 0: 1694.6, 1: 1697.9. Samples: 2290002. Policy #0 lag: (min: 31.0, avg: 31.8, max: 51.0) -[2023-10-09 00:10:08,975][87372] Avg episode reward: [(0, '3.150'), (1, '3.230')] -[2023-10-09 00:10:09,152][88326] Updated weights for policy 0, policy_version 4480 (0.0009) -[2023-10-09 00:10:12,772][88327] Updated weights for policy 1, policy_version 4490 (0.0010) -[2023-10-09 00:10:13,139][88327] Updated weights for policy 1, policy_version 4500 (0.0008) -[2023-10-09 00:10:13,315][88326] Updated weights for policy 0, policy_version 4490 (0.0008) -[2023-10-09 00:10:13,500][88327] Updated weights for policy 1, policy_version 4510 (0.0009) -[2023-10-09 00:10:13,683][88326] Updated weights for policy 0, policy_version 4500 (0.0008) -[2023-10-09 00:10:13,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 9207808. Throughput: 0: 1697.0, 1: 1687.3. Samples: 2310560. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) -[2023-10-09 00:10:13,975][87372] Avg episode reward: [(0, '3.320'), (1, '3.000')] -[2023-10-09 00:10:14,055][88326] Updated weights for policy 0, policy_version 4510 (0.0009) -[2023-10-09 00:10:14,126][88088] Saving new best policy, reward=3.320! -[2023-10-09 00:10:17,544][88327] Updated weights for policy 1, policy_version 4520 (0.0007) -[2023-10-09 00:10:17,907][88327] Updated weights for policy 1, policy_version 4530 (0.0009) -[2023-10-09 00:10:18,069][88326] Updated weights for policy 0, policy_version 4520 (0.0008) -[2023-10-09 00:10:18,278][88327] Updated weights for policy 1, policy_version 4540 (0.0007) -[2023-10-09 00:10:18,440][88326] Updated weights for policy 0, policy_version 4530 (0.0008) -[2023-10-09 00:10:18,805][88326] Updated weights for policy 0, policy_version 4540 (0.0008) -[2023-10-09 00:10:18,974][87372] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 9306112. Throughput: 0: 1679.6, 1: 1673.3. Samples: 2329894. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:10:18,975][87372] Avg episode reward: [(0, '3.390'), (1, '2.850')] -[2023-10-09 00:10:18,985][88088] Saving new best policy, reward=3.390! -[2023-10-09 00:10:22,376][88327] Updated weights for policy 1, policy_version 4550 (0.0008) -[2023-10-09 00:10:22,750][88327] Updated weights for policy 1, policy_version 4560 (0.0008) -[2023-10-09 00:10:22,815][88326] Updated weights for policy 0, policy_version 4550 (0.0009) -[2023-10-09 00:10:23,112][88327] Updated weights for policy 1, policy_version 4570 (0.0007) -[2023-10-09 00:10:23,190][88326] Updated weights for policy 0, policy_version 4560 (0.0008) -[2023-10-09 00:10:23,556][88326] Updated weights for policy 0, policy_version 4570 (0.0009) -[2023-10-09 00:10:23,974][87372] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 9371648. Throughput: 0: 1687.9, 1: 1690.6. Samples: 2340230. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:10:23,975][87372] Avg episode reward: [(0, '3.640'), (1, '2.550')] -[2023-10-09 00:10:23,976][88088] Saving new best policy, reward=3.640! -[2023-10-09 00:10:27,281][88327] Updated weights for policy 1, policy_version 4580 (0.0007) -[2023-10-09 00:10:27,561][88326] Updated weights for policy 0, policy_version 4580 (0.0008) -[2023-10-09 00:10:27,647][88327] Updated weights for policy 1, policy_version 4590 (0.0007) -[2023-10-09 00:10:27,928][88326] Updated weights for policy 0, policy_version 4590 (0.0007) -[2023-10-09 00:10:28,007][88327] Updated weights for policy 1, policy_version 4600 (0.0007) -[2023-10-09 00:10:28,300][88326] Updated weights for policy 0, policy_version 4600 (0.0007) -[2023-10-09 00:10:28,974][87372] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 9437184. Throughput: 0: 1686.7, 1: 1692.9. Samples: 2360864. Policy #0 lag: (min: 10.0, avg: 13.4, max: 42.0) -[2023-10-09 00:10:28,975][87372] Avg episode reward: [(0, '3.590'), (1, '2.640')] -[2023-10-09 00:10:32,161][88327] Updated weights for policy 1, policy_version 4610 (0.0009) -[2023-10-09 00:10:32,352][88326] Updated weights for policy 0, policy_version 4610 (0.0008) -[2023-10-09 00:10:32,523][88327] Updated weights for policy 1, policy_version 4620 (0.0010) -[2023-10-09 00:10:32,717][88326] Updated weights for policy 0, policy_version 4620 (0.0007) -[2023-10-09 00:10:32,883][88327] Updated weights for policy 1, policy_version 4630 (0.0009) -[2023-10-09 00:10:33,080][88326] Updated weights for policy 0, policy_version 4630 (0.0007) -[2023-10-09 00:10:33,252][88327] Updated weights for policy 1, policy_version 4640 (0.0007) -[2023-10-09 00:10:33,448][88326] Updated weights for policy 0, policy_version 4640 (0.0008) -[2023-10-09 00:10:33,974][87372] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 9502720. Throughput: 0: 1667.6, 1: 1661.7. Samples: 2379564. Policy #0 lag: (min: 10.0, avg: 13.4, max: 42.0) -[2023-10-09 00:10:33,975][87372] Avg episode reward: [(0, '3.800'), (1, '2.950')] -[2023-10-09 00:10:33,986][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000004640_4751360.pth... -[2023-10-09 00:10:33,986][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000004640_4751360.pth... -[2023-10-09 00:10:34,025][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000003040_3112960.pth -[2023-10-09 00:10:34,028][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000003072_3145728.pth -[2023-10-09 00:10:34,029][88088] Saving new best policy, reward=3.800! -[2023-10-09 00:10:37,229][88327] Updated weights for policy 1, policy_version 4650 (0.0008) -[2023-10-09 00:10:37,565][88326] Updated weights for policy 0, policy_version 4650 (0.0009) -[2023-10-09 00:10:37,596][88327] Updated weights for policy 1, policy_version 4660 (0.0009) -[2023-10-09 00:10:37,927][88326] Updated weights for policy 0, policy_version 4660 (0.0007) -[2023-10-09 00:10:37,961][88327] Updated weights for policy 1, policy_version 4670 (0.0009) -[2023-10-09 00:10:38,293][88326] Updated weights for policy 0, policy_version 4670 (0.0008) -[2023-10-09 00:10:38,974][87372] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 9568256. Throughput: 0: 1690.0, 1: 1685.7. Samples: 2390764. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-09 00:10:38,975][87372] Avg episode reward: [(0, '3.140'), (1, '3.070')] -[2023-10-09 00:10:42,072][88327] Updated weights for policy 1, policy_version 4680 (0.0008) -[2023-10-09 00:10:42,373][88326] Updated weights for policy 0, policy_version 4680 (0.0007) -[2023-10-09 00:10:42,444][88327] Updated weights for policy 1, policy_version 4690 (0.0009) -[2023-10-09 00:10:42,747][88326] Updated weights for policy 0, policy_version 4690 (0.0008) -[2023-10-09 00:10:42,809][88327] Updated weights for policy 1, policy_version 4700 (0.0007) -[2023-10-09 00:10:43,131][88326] Updated weights for policy 0, policy_version 4700 (0.0007) -[2023-10-09 00:10:43,974][87372] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 9633792. Throughput: 0: 1687.7, 1: 1672.7. Samples: 2410908. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-10-09 00:10:43,975][87372] Avg episode reward: [(0, '3.120'), (1, '3.190')] -[2023-10-09 00:10:46,895][88327] Updated weights for policy 1, policy_version 4710 (0.0008) -[2023-10-09 00:10:46,968][88326] Updated weights for policy 0, policy_version 4710 (0.0009) -[2023-10-09 00:10:47,258][88327] Updated weights for policy 1, policy_version 4720 (0.0007) -[2023-10-09 00:10:47,333][88326] Updated weights for policy 0, policy_version 4720 (0.0010) -[2023-10-09 00:10:47,628][88327] Updated weights for policy 1, policy_version 4730 (0.0008) -[2023-10-09 00:10:47,702][88326] Updated weights for policy 0, policy_version 4730 (0.0009) -[2023-10-09 00:10:48,974][87372] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 9699328. Throughput: 0: 1667.5, 1: 1664.5. Samples: 2429868. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:10:48,974][87372] Avg episode reward: [(0, '3.110'), (1, '2.950')] -[2023-10-09 00:10:51,631][88327] Updated weights for policy 1, policy_version 4740 (0.0009) -[2023-10-09 00:10:51,840][88326] Updated weights for policy 0, policy_version 4740 (0.0008) -[2023-10-09 00:10:51,996][88327] Updated weights for policy 1, policy_version 4750 (0.0008) -[2023-10-09 00:10:52,204][88326] Updated weights for policy 0, policy_version 4750 (0.0007) -[2023-10-09 00:10:52,363][88327] Updated weights for policy 1, policy_version 4760 (0.0008) -[2023-10-09 00:10:52,569][88326] Updated weights for policy 0, policy_version 4760 (0.0008) -[2023-10-09 00:10:53,974][87372] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 9764864. Throughput: 0: 1690.5, 1: 1678.5. Samples: 2441608. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:10:53,975][87372] Avg episode reward: [(0, '3.150'), (1, '2.910')] -[2023-10-09 00:10:56,502][88327] Updated weights for policy 1, policy_version 4770 (0.0008) -[2023-10-09 00:10:56,657][88326] Updated weights for policy 0, policy_version 4770 (0.0007) -[2023-10-09 00:10:56,927][88327] Updated weights for policy 1, policy_version 4780 (0.0010) -[2023-10-09 00:10:57,027][88326] Updated weights for policy 0, policy_version 4780 (0.0008) -[2023-10-09 00:10:57,298][88327] Updated weights for policy 1, policy_version 4790 (0.0008) -[2023-10-09 00:10:57,396][88326] Updated weights for policy 0, policy_version 4790 (0.0007) -[2023-10-09 00:10:57,653][88327] Updated weights for policy 1, policy_version 4800 (0.0007) -[2023-10-09 00:10:57,762][88326] Updated weights for policy 0, policy_version 4800 (0.0009) -[2023-10-09 00:10:58,974][87372] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 9830400. Throughput: 0: 1666.2, 1: 1668.8. Samples: 2460632. Policy #0 lag: (min: 7.0, avg: 13.4, max: 39.0) -[2023-10-09 00:10:58,975][87372] Avg episode reward: [(0, '3.300'), (1, '2.820')] -[2023-10-09 00:11:01,609][88327] Updated weights for policy 1, policy_version 4810 (0.0008) -[2023-10-09 00:11:01,930][88326] Updated weights for policy 0, policy_version 4810 (0.0009) -[2023-10-09 00:11:01,981][88327] Updated weights for policy 1, policy_version 4820 (0.0009) -[2023-10-09 00:11:02,300][88326] Updated weights for policy 0, policy_version 4820 (0.0008) -[2023-10-09 00:11:02,349][88327] Updated weights for policy 1, policy_version 4830 (0.0008) -[2023-10-09 00:11:02,687][88326] Updated weights for policy 0, policy_version 4830 (0.0009) -[2023-10-09 00:11:03,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 9895936. Throughput: 0: 1662.1, 1: 1676.0. Samples: 2480106. Policy #0 lag: (min: 7.0, avg: 13.4, max: 39.0) -[2023-10-09 00:11:03,975][87372] Avg episode reward: [(0, '3.230'), (1, '3.020')] -[2023-10-09 00:11:06,387][88327] Updated weights for policy 1, policy_version 4840 (0.0009) -[2023-10-09 00:11:06,743][88327] Updated weights for policy 1, policy_version 4850 (0.0009) -[2023-10-09 00:11:06,883][88326] Updated weights for policy 0, policy_version 4840 (0.0007) -[2023-10-09 00:11:07,117][88327] Updated weights for policy 1, policy_version 4860 (0.0008) -[2023-10-09 00:11:07,259][88326] Updated weights for policy 0, policy_version 4850 (0.0008) -[2023-10-09 00:11:07,636][88326] Updated weights for policy 0, policy_version 4860 (0.0009) -[2023-10-09 00:11:08,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 9961472. Throughput: 0: 1683.0, 1: 1683.8. Samples: 2491736. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-09 00:11:08,975][87372] Avg episode reward: [(0, '3.350'), (1, '3.290')] -[2023-10-09 00:11:08,976][88168] Saving new best policy, reward=3.290! -[2023-10-09 00:11:11,149][88327] Updated weights for policy 1, policy_version 4870 (0.0007) -[2023-10-09 00:11:11,519][88327] Updated weights for policy 1, policy_version 4880 (0.0009) -[2023-10-09 00:11:11,873][88326] Updated weights for policy 0, policy_version 4870 (0.0009) -[2023-10-09 00:11:11,877][88327] Updated weights for policy 1, policy_version 4890 (0.0007) -[2023-10-09 00:11:12,229][88326] Updated weights for policy 0, policy_version 4880 (0.0008) -[2023-10-09 00:11:12,615][88326] Updated weights for policy 0, policy_version 4890 (0.0007) -[2023-10-09 00:11:13,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 10027008. Throughput: 0: 1666.5, 1: 1656.7. Samples: 2510408. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-09 00:11:13,975][87372] Avg episode reward: [(0, '3.420'), (1, '3.350')] -[2023-10-09 00:11:13,977][88168] Saving new best policy, reward=3.350! -[2023-10-09 00:11:15,940][88327] Updated weights for policy 1, policy_version 4900 (0.0008) -[2023-10-09 00:11:16,300][88327] Updated weights for policy 1, policy_version 4910 (0.0009) -[2023-10-09 00:11:16,663][88327] Updated weights for policy 1, policy_version 4920 (0.0008) -[2023-10-09 00:11:16,707][88326] Updated weights for policy 0, policy_version 4900 (0.0007) -[2023-10-09 00:11:17,084][88326] Updated weights for policy 0, policy_version 4910 (0.0007) -[2023-10-09 00:11:17,445][88326] Updated weights for policy 0, policy_version 4920 (0.0009) -[2023-10-09 00:11:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 10092544. Throughput: 0: 1669.7, 1: 1686.6. Samples: 2530598. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:11:18,975][87372] Avg episode reward: [(0, '3.500'), (1, '3.110')] -[2023-10-09 00:11:20,701][88327] Updated weights for policy 1, policy_version 4930 (0.0009) -[2023-10-09 00:11:21,072][88327] Updated weights for policy 1, policy_version 4940 (0.0009) -[2023-10-09 00:11:21,451][88327] Updated weights for policy 1, policy_version 4950 (0.0009) -[2023-10-09 00:11:21,474][88326] Updated weights for policy 0, policy_version 4930 (0.0009) -[2023-10-09 00:11:21,818][88327] Updated weights for policy 1, policy_version 4960 (0.0009) -[2023-10-09 00:11:21,845][88326] Updated weights for policy 0, policy_version 4940 (0.0009) -[2023-10-09 00:11:22,217][88326] Updated weights for policy 0, policy_version 4950 (0.0008) -[2023-10-09 00:11:22,581][88326] Updated weights for policy 0, policy_version 4960 (0.0008) -[2023-10-09 00:11:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 10158080. Throughput: 0: 1677.2, 1: 1677.0. Samples: 2541700. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:11:23,975][87372] Avg episode reward: [(0, '3.710'), (1, '3.050')] -[2023-10-09 00:11:25,941][88327] Updated weights for policy 1, policy_version 4970 (0.0009) -[2023-10-09 00:11:26,296][88327] Updated weights for policy 1, policy_version 4980 (0.0008) -[2023-10-09 00:11:26,521][88326] Updated weights for policy 0, policy_version 4970 (0.0009) -[2023-10-09 00:11:26,662][88327] Updated weights for policy 1, policy_version 4990 (0.0007) -[2023-10-09 00:11:26,889][88326] Updated weights for policy 0, policy_version 4980 (0.0009) -[2023-10-09 00:11:27,262][88326] Updated weights for policy 0, policy_version 4990 (0.0009) -[2023-10-09 00:11:28,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 10223616. Throughput: 0: 1657.2, 1: 1671.7. Samples: 2560710. Policy #0 lag: (min: 11.0, avg: 36.0, max: 40.0) -[2023-10-09 00:11:28,975][87372] Avg episode reward: [(0, '3.650'), (1, '2.990')] -[2023-10-09 00:11:30,613][88327] Updated weights for policy 1, policy_version 5000 (0.0011) -[2023-10-09 00:11:30,977][88327] Updated weights for policy 1, policy_version 5010 (0.0009) -[2023-10-09 00:11:31,209][88326] Updated weights for policy 0, policy_version 5000 (0.0008) -[2023-10-09 00:11:31,342][88327] Updated weights for policy 1, policy_version 5020 (0.0008) -[2023-10-09 00:11:31,581][88326] Updated weights for policy 0, policy_version 5010 (0.0009) -[2023-10-09 00:11:31,951][88326] Updated weights for policy 0, policy_version 5020 (0.0009) -[2023-10-09 00:11:33,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 10289152. Throughput: 0: 1676.4, 1: 1694.4. Samples: 2581554. Policy #0 lag: (min: 11.0, avg: 36.0, max: 40.0) -[2023-10-09 00:11:33,975][87372] Avg episode reward: [(0, '3.320'), (1, '3.070')] -[2023-10-09 00:11:35,430][88327] Updated weights for policy 1, policy_version 5030 (0.0007) -[2023-10-09 00:11:35,798][88327] Updated weights for policy 1, policy_version 5040 (0.0007) -[2023-10-09 00:11:35,968][88326] Updated weights for policy 0, policy_version 5030 (0.0008) -[2023-10-09 00:11:36,158][88327] Updated weights for policy 1, policy_version 5050 (0.0008) -[2023-10-09 00:11:36,344][88326] Updated weights for policy 0, policy_version 5040 (0.0007) -[2023-10-09 00:11:36,718][88326] Updated weights for policy 0, policy_version 5050 (0.0009) -[2023-10-09 00:11:38,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 10354688. Throughput: 0: 1670.7, 1: 1668.6. Samples: 2591878. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-09 00:11:38,974][87372] Avg episode reward: [(0, '3.320'), (1, '3.280')] -[2023-10-09 00:11:40,132][88327] Updated weights for policy 1, policy_version 5060 (0.0008) -[2023-10-09 00:11:40,507][88327] Updated weights for policy 1, policy_version 5070 (0.0011) -[2023-10-09 00:11:40,816][88326] Updated weights for policy 0, policy_version 5060 (0.0009) -[2023-10-09 00:11:40,863][88327] Updated weights for policy 1, policy_version 5080 (0.0009) -[2023-10-09 00:11:41,188][88326] Updated weights for policy 0, policy_version 5070 (0.0007) -[2023-10-09 00:11:41,550][88326] Updated weights for policy 0, policy_version 5080 (0.0007) -[2023-10-09 00:11:43,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 10420224. Throughput: 0: 1673.0, 1: 1684.6. Samples: 2611726. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-09 00:11:43,975][87372] Avg episode reward: [(0, '3.040'), (1, '3.230')] -[2023-10-09 00:11:44,942][88327] Updated weights for policy 1, policy_version 5090 (0.0008) -[2023-10-09 00:11:45,354][88327] Updated weights for policy 1, policy_version 5100 (0.0010) -[2023-10-09 00:11:45,635][88326] Updated weights for policy 0, policy_version 5090 (0.0008) -[2023-10-09 00:11:45,710][88327] Updated weights for policy 1, policy_version 5110 (0.0009) -[2023-10-09 00:11:46,000][88326] Updated weights for policy 0, policy_version 5100 (0.0008) -[2023-10-09 00:11:46,074][88327] Updated weights for policy 1, policy_version 5120 (0.0007) -[2023-10-09 00:11:46,374][88326] Updated weights for policy 0, policy_version 5110 (0.0009) -[2023-10-09 00:11:46,742][88326] Updated weights for policy 0, policy_version 5120 (0.0010) -[2023-10-09 00:11:48,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 10485760. Throughput: 0: 1688.2, 1: 1696.2. Samples: 2632404. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) -[2023-10-09 00:11:48,975][87372] Avg episode reward: [(0, '3.190'), (1, '3.440')] -[2023-10-09 00:11:48,985][88168] Saving new best policy, reward=3.440! -[2023-10-09 00:11:50,141][88327] Updated weights for policy 1, policy_version 5130 (0.0009) -[2023-10-09 00:11:50,507][88327] Updated weights for policy 1, policy_version 5140 (0.0010) -[2023-10-09 00:11:50,868][88327] Updated weights for policy 1, policy_version 5150 (0.0009) -[2023-10-09 00:11:50,905][88326] Updated weights for policy 0, policy_version 5130 (0.0009) -[2023-10-09 00:11:51,280][88326] Updated weights for policy 0, policy_version 5140 (0.0009) -[2023-10-09 00:11:51,646][88326] Updated weights for policy 0, policy_version 5150 (0.0008) -[2023-10-09 00:11:53,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 10551296. Throughput: 0: 1672.2, 1: 1667.6. Samples: 2642030. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) -[2023-10-09 00:11:53,975][87372] Avg episode reward: [(0, '3.270'), (1, '3.560')] -[2023-10-09 00:11:53,976][88168] Saving new best policy, reward=3.560! -[2023-10-09 00:11:54,885][88327] Updated weights for policy 1, policy_version 5160 (0.0008) -[2023-10-09 00:11:55,251][88327] Updated weights for policy 1, policy_version 5170 (0.0008) -[2023-10-09 00:11:55,629][88327] Updated weights for policy 1, policy_version 5180 (0.0010) -[2023-10-09 00:11:55,633][88326] Updated weights for policy 0, policy_version 5160 (0.0009) -[2023-10-09 00:11:56,010][88326] Updated weights for policy 0, policy_version 5170 (0.0010) -[2023-10-09 00:11:56,387][88326] Updated weights for policy 0, policy_version 5180 (0.0010) -[2023-10-09 00:11:58,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 10616832. Throughput: 0: 1676.6, 1: 1701.4. Samples: 2662416. Policy #0 lag: (min: 26.0, avg: 31.3, max: 58.0) -[2023-10-09 00:11:58,975][87372] Avg episode reward: [(0, '3.330'), (1, '3.420')] -[2023-10-09 00:11:59,696][88327] Updated weights for policy 1, policy_version 5190 (0.0008) -[2023-10-09 00:12:00,064][88327] Updated weights for policy 1, policy_version 5200 (0.0007) -[2023-10-09 00:12:00,424][88327] Updated weights for policy 1, policy_version 5210 (0.0009) -[2023-10-09 00:12:00,487][88326] Updated weights for policy 0, policy_version 5190 (0.0010) -[2023-10-09 00:12:00,860][88326] Updated weights for policy 0, policy_version 5200 (0.0008) -[2023-10-09 00:12:01,226][88326] Updated weights for policy 0, policy_version 5210 (0.0008) -[2023-10-09 00:12:03,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 10682368. Throughput: 0: 1694.3, 1: 1698.0. Samples: 2683254. Policy #0 lag: (min: 26.0, avg: 31.3, max: 58.0) -[2023-10-09 00:12:03,975][87372] Avg episode reward: [(0, '3.520'), (1, '3.250')] -[2023-10-09 00:12:04,480][88327] Updated weights for policy 1, policy_version 5220 (0.0008) -[2023-10-09 00:12:04,849][88327] Updated weights for policy 1, policy_version 5230 (0.0009) -[2023-10-09 00:12:05,212][88327] Updated weights for policy 1, policy_version 5240 (0.0007) -[2023-10-09 00:12:05,224][88326] Updated weights for policy 0, policy_version 5220 (0.0008) -[2023-10-09 00:12:05,586][88326] Updated weights for policy 0, policy_version 5230 (0.0009) -[2023-10-09 00:12:05,954][88326] Updated weights for policy 0, policy_version 5240 (0.0008) -[2023-10-09 00:12:08,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 10747904. Throughput: 0: 1670.2, 1: 1681.6. Samples: 2692532. Policy #0 lag: (min: 1.0, avg: 3.0, max: 29.0) -[2023-10-09 00:12:08,975][87372] Avg episode reward: [(0, '3.480'), (1, '3.150')] -[2023-10-09 00:12:09,193][88327] Updated weights for policy 1, policy_version 5250 (0.0008) -[2023-10-09 00:12:09,559][88327] Updated weights for policy 1, policy_version 5260 (0.0007) -[2023-10-09 00:12:09,892][88326] Updated weights for policy 0, policy_version 5250 (0.0009) -[2023-10-09 00:12:09,915][88327] Updated weights for policy 1, policy_version 5270 (0.0007) -[2023-10-09 00:12:10,275][88326] Updated weights for policy 0, policy_version 5260 (0.0008) -[2023-10-09 00:12:10,288][88327] Updated weights for policy 1, policy_version 5280 (0.0007) -[2023-10-09 00:12:10,647][88326] Updated weights for policy 0, policy_version 5270 (0.0011) -[2023-10-09 00:12:11,003][88326] Updated weights for policy 0, policy_version 5280 (0.0008) -[2023-10-09 00:12:13,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 10813440. Throughput: 0: 1697.3, 1: 1697.5. Samples: 2713474. Policy #0 lag: (min: 1.0, avg: 3.0, max: 29.0) -[2023-10-09 00:12:13,975][87372] Avg episode reward: [(0, '3.840'), (1, '3.070')] -[2023-10-09 00:12:13,976][88088] Saving new best policy, reward=3.840! -[2023-10-09 00:12:14,221][88327] Updated weights for policy 1, policy_version 5290 (0.0007) -[2023-10-09 00:12:14,592][88327] Updated weights for policy 1, policy_version 5300 (0.0007) -[2023-10-09 00:12:14,960][88327] Updated weights for policy 1, policy_version 5310 (0.0008) -[2023-10-09 00:12:15,026][88326] Updated weights for policy 0, policy_version 5290 (0.0009) -[2023-10-09 00:12:15,393][88326] Updated weights for policy 0, policy_version 5300 (0.0008) -[2023-10-09 00:12:15,767][88326] Updated weights for policy 0, policy_version 5310 (0.0008) -[2023-10-09 00:12:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 10878976. Throughput: 0: 1697.6, 1: 1699.3. Samples: 2734416. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:12:18,975][87372] Avg episode reward: [(0, '3.610'), (1, '3.140')] -[2023-10-09 00:12:19,061][88327] Updated weights for policy 1, policy_version 5320 (0.0007) -[2023-10-09 00:12:19,427][88327] Updated weights for policy 1, policy_version 5330 (0.0008) -[2023-10-09 00:12:19,790][88327] Updated weights for policy 1, policy_version 5340 (0.0008) -[2023-10-09 00:12:19,845][88326] Updated weights for policy 0, policy_version 5320 (0.0009) -[2023-10-09 00:12:20,203][88326] Updated weights for policy 0, policy_version 5330 (0.0011) -[2023-10-09 00:12:20,577][88326] Updated weights for policy 0, policy_version 5340 (0.0007) -[2023-10-09 00:12:23,807][88327] Updated weights for policy 1, policy_version 5350 (0.0009) -[2023-10-09 00:12:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 10944512. Throughput: 0: 1677.8, 1: 1692.1. Samples: 2743524. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:12:23,975][87372] Avg episode reward: [(0, '3.520'), (1, '3.330')] -[2023-10-09 00:12:24,172][88327] Updated weights for policy 1, policy_version 5360 (0.0010) -[2023-10-09 00:12:24,525][88327] Updated weights for policy 1, policy_version 5370 (0.0009) -[2023-10-09 00:12:24,569][88326] Updated weights for policy 0, policy_version 5350 (0.0008) -[2023-10-09 00:12:24,938][88326] Updated weights for policy 0, policy_version 5360 (0.0007) -[2023-10-09 00:12:25,309][88326] Updated weights for policy 0, policy_version 5370 (0.0009) -[2023-10-09 00:12:28,495][88327] Updated weights for policy 1, policy_version 5380 (0.0007) -[2023-10-09 00:12:28,870][88327] Updated weights for policy 1, policy_version 5390 (0.0008) -[2023-10-09 00:12:28,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 11010048. Throughput: 0: 1700.2, 1: 1696.1. Samples: 2764562. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-09 00:12:28,975][87372] Avg episode reward: [(0, '3.240'), (1, '3.210')] -[2023-10-09 00:12:29,239][88327] Updated weights for policy 1, policy_version 5400 (0.0009) -[2023-10-09 00:12:29,321][88326] Updated weights for policy 0, policy_version 5380 (0.0011) -[2023-10-09 00:12:29,691][88326] Updated weights for policy 0, policy_version 5390 (0.0009) -[2023-10-09 00:12:30,051][88326] Updated weights for policy 0, policy_version 5400 (0.0007) -[2023-10-09 00:12:33,288][88327] Updated weights for policy 1, policy_version 5410 (0.0009) -[2023-10-09 00:12:33,707][88327] Updated weights for policy 1, policy_version 5420 (0.0010) -[2023-10-09 00:12:33,953][88326] Updated weights for policy 0, policy_version 5410 (0.0008) -[2023-10-09 00:12:33,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13329.3). Total num frames: 11075584. Throughput: 0: 1703.1, 1: 1700.8. Samples: 2785578. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-09 00:12:33,975][87372] Avg episode reward: [(0, '3.750'), (1, '3.130')] -[2023-10-09 00:12:34,077][88327] Updated weights for policy 1, policy_version 5430 (0.0008) -[2023-10-09 00:12:34,330][88326] Updated weights for policy 0, policy_version 5420 (0.0009) -[2023-10-09 00:12:34,443][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000005440_5570560.pth... -[2023-10-09 00:12:34,446][88327] Updated weights for policy 1, policy_version 5440 (0.0008) -[2023-10-09 00:12:34,484][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000003840_3932160.pth -[2023-10-09 00:12:34,708][88326] Updated weights for policy 0, policy_version 5430 (0.0010) -[2023-10-09 00:12:35,067][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000005440_5570560.pth... -[2023-10-09 00:12:35,074][88326] Updated weights for policy 0, policy_version 5440 (0.0009) -[2023-10-09 00:12:35,096][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000003840_3932160.pth -[2023-10-09 00:12:38,354][88327] Updated weights for policy 1, policy_version 5450 (0.0009) -[2023-10-09 00:12:38,727][88327] Updated weights for policy 1, policy_version 5460 (0.0010) -[2023-10-09 00:12:38,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13329.3). Total num frames: 11141120. Throughput: 0: 1691.1, 1: 1699.6. Samples: 2794612. Policy #0 lag: (min: 2.0, avg: 4.9, max: 34.0) -[2023-10-09 00:12:38,975][87372] Avg episode reward: [(0, '3.560'), (1, '3.210')] -[2023-10-09 00:12:39,091][88327] Updated weights for policy 1, policy_version 5470 (0.0007) -[2023-10-09 00:12:39,265][88326] Updated weights for policy 0, policy_version 5450 (0.0007) -[2023-10-09 00:12:39,637][88326] Updated weights for policy 0, policy_version 5460 (0.0010) -[2023-10-09 00:12:39,997][88326] Updated weights for policy 0, policy_version 5470 (0.0009) -[2023-10-09 00:12:43,100][88327] Updated weights for policy 1, policy_version 5480 (0.0008) -[2023-10-09 00:12:43,466][88327] Updated weights for policy 1, policy_version 5490 (0.0009) -[2023-10-09 00:12:43,834][88327] Updated weights for policy 1, policy_version 5500 (0.0009) -[2023-10-09 00:12:43,974][87372] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 11206656. Throughput: 0: 1696.4, 1: 1702.3. Samples: 2815358. Policy #0 lag: (min: 2.0, avg: 4.9, max: 34.0) -[2023-10-09 00:12:43,975][87372] Avg episode reward: [(0, '3.440'), (1, '3.140')] -[2023-10-09 00:12:44,069][88326] Updated weights for policy 0, policy_version 5480 (0.0008) -[2023-10-09 00:12:44,446][88326] Updated weights for policy 0, policy_version 5490 (0.0008) -[2023-10-09 00:12:44,828][88326] Updated weights for policy 0, policy_version 5500 (0.0007) -[2023-10-09 00:12:47,888][88327] Updated weights for policy 1, policy_version 5510 (0.0007) -[2023-10-09 00:12:48,261][88327] Updated weights for policy 1, policy_version 5520 (0.0008) -[2023-10-09 00:12:48,630][88327] Updated weights for policy 1, policy_version 5530 (0.0009) -[2023-10-09 00:12:48,800][88326] Updated weights for policy 0, policy_version 5510 (0.0007) -[2023-10-09 00:12:48,974][87372] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 11304960. Throughput: 0: 1698.5, 1: 1693.1. Samples: 2835876. Policy #0 lag: (min: 17.0, avg: 27.0, max: 49.0) -[2023-10-09 00:12:48,975][87372] Avg episode reward: [(0, '3.110'), (1, '3.010')] -[2023-10-09 00:12:49,164][88326] Updated weights for policy 0, policy_version 5520 (0.0008) -[2023-10-09 00:12:49,536][88326] Updated weights for policy 0, policy_version 5530 (0.0007) -[2023-10-09 00:12:52,744][88327] Updated weights for policy 1, policy_version 5540 (0.0009) -[2023-10-09 00:12:53,102][88327] Updated weights for policy 1, policy_version 5550 (0.0009) -[2023-10-09 00:12:53,466][88327] Updated weights for policy 1, policy_version 5560 (0.0008) -[2023-10-09 00:12:53,519][88326] Updated weights for policy 0, policy_version 5540 (0.0008) -[2023-10-09 00:12:53,887][88326] Updated weights for policy 0, policy_version 5550 (0.0009) -[2023-10-09 00:12:53,974][87372] Fps is (10 sec: 16384.1, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 11370496. Throughput: 0: 1690.9, 1: 1706.9. Samples: 2845434. Policy #0 lag: (min: 17.0, avg: 27.0, max: 49.0) -[2023-10-09 00:12:53,975][87372] Avg episode reward: [(0, '3.380'), (1, '3.060')] -[2023-10-09 00:12:54,265][88326] Updated weights for policy 0, policy_version 5560 (0.0007) -[2023-10-09 00:12:57,570][88327] Updated weights for policy 1, policy_version 5570 (0.0011) -[2023-10-09 00:12:57,954][88327] Updated weights for policy 1, policy_version 5580 (0.0007) -[2023-10-09 00:12:58,311][88327] Updated weights for policy 1, policy_version 5590 (0.0007) -[2023-10-09 00:12:58,380][88326] Updated weights for policy 0, policy_version 5570 (0.0008) -[2023-10-09 00:12:58,681][88327] Updated weights for policy 1, policy_version 5600 (0.0008) -[2023-10-09 00:12:58,748][88326] Updated weights for policy 0, policy_version 5580 (0.0009) -[2023-10-09 00:12:58,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 11436032. Throughput: 0: 1688.5, 1: 1701.6. Samples: 2866030. Policy #0 lag: (min: 17.0, avg: 18.6, max: 44.0) -[2023-10-09 00:12:58,975][87372] Avg episode reward: [(0, '3.460'), (1, '3.340')] -[2023-10-09 00:12:59,116][88326] Updated weights for policy 0, policy_version 5590 (0.0009) -[2023-10-09 00:12:59,485][88326] Updated weights for policy 0, policy_version 5600 (0.0011) -[2023-10-09 00:13:02,664][88327] Updated weights for policy 1, policy_version 5610 (0.0008) -[2023-10-09 00:13:03,026][88327] Updated weights for policy 1, policy_version 5620 (0.0007) -[2023-10-09 00:13:03,392][88327] Updated weights for policy 1, policy_version 5630 (0.0007) -[2023-10-09 00:13:03,751][88326] Updated weights for policy 0, policy_version 5610 (0.0009) -[2023-10-09 00:13:03,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 11501568. Throughput: 0: 1686.1, 1: 1676.9. Samples: 2885754. Policy #0 lag: (min: 17.0, avg: 18.6, max: 44.0) -[2023-10-09 00:13:03,974][87372] Avg episode reward: [(0, '3.700'), (1, '3.420')] -[2023-10-09 00:13:04,118][88326] Updated weights for policy 0, policy_version 5620 (0.0009) -[2023-10-09 00:13:04,491][88326] Updated weights for policy 0, policy_version 5630 (0.0011) -[2023-10-09 00:13:07,522][88327] Updated weights for policy 1, policy_version 5640 (0.0009) -[2023-10-09 00:13:07,885][88327] Updated weights for policy 1, policy_version 5650 (0.0007) -[2023-10-09 00:13:08,249][88327] Updated weights for policy 1, policy_version 5660 (0.0009) -[2023-10-09 00:13:08,609][88326] Updated weights for policy 0, policy_version 5640 (0.0008) -[2023-10-09 00:13:08,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 11567104. Throughput: 0: 1681.3, 1: 1700.7. Samples: 2895714. Policy #0 lag: (min: 31.0, avg: 35.1, max: 63.0) -[2023-10-09 00:13:08,975][87372] Avg episode reward: [(0, '3.670'), (1, '3.410')] -[2023-10-09 00:13:08,990][88326] Updated weights for policy 0, policy_version 5650 (0.0007) -[2023-10-09 00:13:09,361][88326] Updated weights for policy 0, policy_version 5660 (0.0009) -[2023-10-09 00:13:12,351][88327] Updated weights for policy 1, policy_version 5670 (0.0008) -[2023-10-09 00:13:12,715][88327] Updated weights for policy 1, policy_version 5680 (0.0008) -[2023-10-09 00:13:13,083][88327] Updated weights for policy 1, policy_version 5690 (0.0009) -[2023-10-09 00:13:13,364][88326] Updated weights for policy 0, policy_version 5670 (0.0009) -[2023-10-09 00:13:13,741][88326] Updated weights for policy 0, policy_version 5680 (0.0010) -[2023-10-09 00:13:13,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 11632640. Throughput: 0: 1680.6, 1: 1698.0. Samples: 2916600. Policy #0 lag: (min: 31.0, avg: 35.1, max: 63.0) -[2023-10-09 00:13:13,975][87372] Avg episode reward: [(0, '3.460'), (1, '3.400')] -[2023-10-09 00:13:14,118][88326] Updated weights for policy 0, policy_version 5690 (0.0010) -[2023-10-09 00:13:17,188][88327] Updated weights for policy 1, policy_version 5700 (0.0009) -[2023-10-09 00:13:17,557][88327] Updated weights for policy 1, policy_version 5710 (0.0007) -[2023-10-09 00:13:17,919][88327] Updated weights for policy 1, policy_version 5720 (0.0009) -[2023-10-09 00:13:18,144][88326] Updated weights for policy 0, policy_version 5700 (0.0009) -[2023-10-09 00:13:18,515][88326] Updated weights for policy 0, policy_version 5710 (0.0009) -[2023-10-09 00:13:18,882][88326] Updated weights for policy 0, policy_version 5720 (0.0011) -[2023-10-09 00:13:18,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 11698176. Throughput: 0: 1672.9, 1: 1671.9. Samples: 2936094. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) -[2023-10-09 00:13:18,975][87372] Avg episode reward: [(0, '3.440'), (1, '3.560')] -[2023-10-09 00:13:21,890][88327] Updated weights for policy 1, policy_version 5730 (0.0010) -[2023-10-09 00:13:22,301][88327] Updated weights for policy 1, policy_version 5740 (0.0010) -[2023-10-09 00:13:22,666][88327] Updated weights for policy 1, policy_version 5750 (0.0011) -[2023-10-09 00:13:22,889][88326] Updated weights for policy 0, policy_version 5730 (0.0007) -[2023-10-09 00:13:23,029][88327] Updated weights for policy 1, policy_version 5760 (0.0009) -[2023-10-09 00:13:23,292][88326] Updated weights for policy 0, policy_version 5740 (0.0008) -[2023-10-09 00:13:23,664][88326] Updated weights for policy 0, policy_version 5750 (0.0009) -[2023-10-09 00:13:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 11763712. Throughput: 0: 1674.3, 1: 1702.0. Samples: 2946548. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) -[2023-10-09 00:13:23,975][87372] Avg episode reward: [(0, '3.560'), (1, '3.470')] -[2023-10-09 00:13:24,035][88326] Updated weights for policy 0, policy_version 5760 (0.0009) -[2023-10-09 00:13:27,071][88327] Updated weights for policy 1, policy_version 5770 (0.0008) -[2023-10-09 00:13:27,434][88327] Updated weights for policy 1, policy_version 5780 (0.0008) -[2023-10-09 00:13:27,800][88327] Updated weights for policy 1, policy_version 5790 (0.0008) -[2023-10-09 00:13:28,108][88326] Updated weights for policy 0, policy_version 5770 (0.0009) -[2023-10-09 00:13:28,471][88326] Updated weights for policy 0, policy_version 5780 (0.0009) -[2023-10-09 00:13:28,843][88326] Updated weights for policy 0, policy_version 5790 (0.0011) -[2023-10-09 00:13:28,974][87372] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 11862016. Throughput: 0: 1682.1, 1: 1684.1. Samples: 2966840. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-09 00:13:28,975][87372] Avg episode reward: [(0, '3.290'), (1, '3.670')] -[2023-10-09 00:13:28,977][88168] Saving new best policy, reward=3.670! -[2023-10-09 00:13:31,882][88327] Updated weights for policy 1, policy_version 5800 (0.0007) -[2023-10-09 00:13:32,255][88327] Updated weights for policy 1, policy_version 5810 (0.0009) -[2023-10-09 00:13:32,629][88327] Updated weights for policy 1, policy_version 5820 (0.0007) -[2023-10-09 00:13:32,853][88326] Updated weights for policy 0, policy_version 5800 (0.0008) -[2023-10-09 00:13:33,221][88326] Updated weights for policy 0, policy_version 5810 (0.0010) -[2023-10-09 00:13:33,591][88326] Updated weights for policy 0, policy_version 5820 (0.0008) -[2023-10-09 00:13:33,974][87372] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 11927552. Throughput: 0: 1665.6, 1: 1677.4. Samples: 2986310. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:13:33,975][87372] Avg episode reward: [(0, '3.460'), (1, '3.350')] -[2023-10-09 00:13:36,525][88327] Updated weights for policy 1, policy_version 5830 (0.0008) -[2023-10-09 00:13:36,899][88327] Updated weights for policy 1, policy_version 5840 (0.0007) -[2023-10-09 00:13:37,268][88327] Updated weights for policy 1, policy_version 5850 (0.0007) -[2023-10-09 00:13:37,722][88326] Updated weights for policy 0, policy_version 5830 (0.0010) -[2023-10-09 00:13:38,089][88326] Updated weights for policy 0, policy_version 5840 (0.0010) -[2023-10-09 00:13:38,467][88326] Updated weights for policy 0, policy_version 5850 (0.0008) -[2023-10-09 00:13:38,974][87372] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 11993088. Throughput: 0: 1684.3, 1: 1694.7. Samples: 2997490. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:13:38,975][87372] Avg episode reward: [(0, '3.720'), (1, '3.280')] -[2023-10-09 00:13:41,263][88327] Updated weights for policy 1, policy_version 5860 (0.0008) -[2023-10-09 00:13:41,622][88327] Updated weights for policy 1, policy_version 5870 (0.0008) -[2023-10-09 00:13:41,987][88327] Updated weights for policy 1, policy_version 5880 (0.0009) -[2023-10-09 00:13:42,493][88326] Updated weights for policy 0, policy_version 5860 (0.0007) -[2023-10-09 00:13:42,864][88326] Updated weights for policy 0, policy_version 5870 (0.0007) -[2023-10-09 00:13:43,243][88326] Updated weights for policy 0, policy_version 5880 (0.0009) -[2023-10-09 00:13:43,974][87372] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 12058624. Throughput: 0: 1685.3, 1: 1673.9. Samples: 3017198. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:13:43,976][87372] Avg episode reward: [(0, '3.870'), (1, '3.260')] -[2023-10-09 00:13:43,977][88088] Saving new best policy, reward=3.870! -[2023-10-09 00:13:46,034][88327] Updated weights for policy 1, policy_version 5890 (0.0009) -[2023-10-09 00:13:46,391][88327] Updated weights for policy 1, policy_version 5900 (0.0011) -[2023-10-09 00:13:46,756][88327] Updated weights for policy 1, policy_version 5910 (0.0009) -[2023-10-09 00:13:47,127][88327] Updated weights for policy 1, policy_version 5920 (0.0008) -[2023-10-09 00:13:47,348][88326] Updated weights for policy 0, policy_version 5890 (0.0008) -[2023-10-09 00:13:47,724][88326] Updated weights for policy 0, policy_version 5900 (0.0009) -[2023-10-09 00:13:48,087][88326] Updated weights for policy 0, policy_version 5910 (0.0009) -[2023-10-09 00:13:48,446][88326] Updated weights for policy 0, policy_version 5920 (0.0008) -[2023-10-09 00:13:48,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 12124160. Throughput: 0: 1667.3, 1: 1689.2. Samples: 3036798. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:13:48,975][87372] Avg episode reward: [(0, '3.470'), (1, '3.150')] -[2023-10-09 00:13:51,301][88327] Updated weights for policy 1, policy_version 5930 (0.0011) -[2023-10-09 00:13:51,663][88327] Updated weights for policy 1, policy_version 5940 (0.0011) -[2023-10-09 00:13:52,028][88327] Updated weights for policy 1, policy_version 5950 (0.0009) -[2023-10-09 00:13:52,325][88326] Updated weights for policy 0, policy_version 5930 (0.0007) -[2023-10-09 00:13:52,697][88326] Updated weights for policy 0, policy_version 5940 (0.0007) -[2023-10-09 00:13:53,073][88326] Updated weights for policy 0, policy_version 5950 (0.0007) -[2023-10-09 00:13:53,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 12189696. Throughput: 0: 1693.9, 1: 1687.3. Samples: 3047868. Policy #0 lag: (min: 17.0, avg: 28.7, max: 49.0) -[2023-10-09 00:13:53,975][87372] Avg episode reward: [(0, '3.590'), (1, '3.000')] -[2023-10-09 00:13:56,215][88327] Updated weights for policy 1, policy_version 5960 (0.0009) -[2023-10-09 00:13:56,587][88327] Updated weights for policy 1, policy_version 5970 (0.0009) -[2023-10-09 00:13:56,942][88327] Updated weights for policy 1, policy_version 5980 (0.0007) -[2023-10-09 00:13:57,049][88326] Updated weights for policy 0, policy_version 5960 (0.0007) -[2023-10-09 00:13:57,423][88326] Updated weights for policy 0, policy_version 5970 (0.0009) -[2023-10-09 00:13:57,792][88326] Updated weights for policy 0, policy_version 5980 (0.0007) -[2023-10-09 00:13:58,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 12255232. Throughput: 0: 1682.5, 1: 1661.8. Samples: 3067094. Policy #0 lag: (min: 17.0, avg: 28.7, max: 49.0) -[2023-10-09 00:13:58,975][87372] Avg episode reward: [(0, '3.780'), (1, '2.940')] -[2023-10-09 00:14:01,159][88327] Updated weights for policy 1, policy_version 5990 (0.0007) -[2023-10-09 00:14:01,521][88327] Updated weights for policy 1, policy_version 6000 (0.0008) -[2023-10-09 00:14:01,881][88327] Updated weights for policy 1, policy_version 6010 (0.0007) -[2023-10-09 00:14:01,928][88326] Updated weights for policy 0, policy_version 5990 (0.0008) -[2023-10-09 00:14:02,293][88326] Updated weights for policy 0, policy_version 6000 (0.0007) -[2023-10-09 00:14:02,658][88326] Updated weights for policy 0, policy_version 6010 (0.0007) -[2023-10-09 00:14:03,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 12320768. Throughput: 0: 1672.4, 1: 1680.4. Samples: 3086968. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:14:03,974][87372] Avg episode reward: [(0, '3.640'), (1, '3.130')] -[2023-10-09 00:14:05,870][88327] Updated weights for policy 1, policy_version 6020 (0.0008) -[2023-10-09 00:14:06,234][88327] Updated weights for policy 1, policy_version 6030 (0.0011) -[2023-10-09 00:14:06,597][88327] Updated weights for policy 1, policy_version 6040 (0.0007) -[2023-10-09 00:14:06,684][88326] Updated weights for policy 0, policy_version 6020 (0.0009) -[2023-10-09 00:14:07,063][88326] Updated weights for policy 0, policy_version 6030 (0.0009) -[2023-10-09 00:14:07,433][88326] Updated weights for policy 0, policy_version 6040 (0.0009) -[2023-10-09 00:14:08,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 12386304. Throughput: 0: 1698.8, 1: 1672.9. Samples: 3098278. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:14:08,975][87372] Avg episode reward: [(0, '3.630'), (1, '3.380')] -[2023-10-09 00:14:10,428][88327] Updated weights for policy 1, policy_version 6050 (0.0007) -[2023-10-09 00:14:10,790][88327] Updated weights for policy 1, policy_version 6060 (0.0008) -[2023-10-09 00:14:11,156][88327] Updated weights for policy 1, policy_version 6070 (0.0007) -[2023-10-09 00:14:11,522][88327] Updated weights for policy 1, policy_version 6080 (0.0007) -[2023-10-09 00:14:11,551][88326] Updated weights for policy 0, policy_version 6050 (0.0007) -[2023-10-09 00:14:11,919][88326] Updated weights for policy 0, policy_version 6060 (0.0009) -[2023-10-09 00:14:12,299][88326] Updated weights for policy 0, policy_version 6070 (0.0009) -[2023-10-09 00:14:12,669][88326] Updated weights for policy 0, policy_version 6080 (0.0007) -[2023-10-09 00:14:13,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 12451840. Throughput: 0: 1681.2, 1: 1670.1. Samples: 3117652. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-10-09 00:14:13,975][87372] Avg episode reward: [(0, '3.350'), (1, '3.610')] -[2023-10-09 00:14:15,631][88327] Updated weights for policy 1, policy_version 6090 (0.0007) -[2023-10-09 00:14:16,003][88327] Updated weights for policy 1, policy_version 6100 (0.0008) -[2023-10-09 00:14:16,364][88327] Updated weights for policy 1, policy_version 6110 (0.0008) -[2023-10-09 00:14:16,652][88326] Updated weights for policy 0, policy_version 6090 (0.0009) -[2023-10-09 00:14:17,023][88326] Updated weights for policy 0, policy_version 6100 (0.0008) -[2023-10-09 00:14:17,394][88326] Updated weights for policy 0, policy_version 6110 (0.0008) -[2023-10-09 00:14:18,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 12517376. Throughput: 0: 1684.8, 1: 1693.4. Samples: 3138328. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-10-09 00:14:18,975][87372] Avg episode reward: [(0, '3.430'), (1, '3.220')] -[2023-10-09 00:14:20,336][88327] Updated weights for policy 1, policy_version 6120 (0.0011) -[2023-10-09 00:14:20,707][88327] Updated weights for policy 1, policy_version 6130 (0.0008) -[2023-10-09 00:14:21,079][88327] Updated weights for policy 1, policy_version 6140 (0.0010) -[2023-10-09 00:14:21,330][88326] Updated weights for policy 0, policy_version 6120 (0.0008) -[2023-10-09 00:14:21,701][88326] Updated weights for policy 0, policy_version 6130 (0.0009) -[2023-10-09 00:14:22,066][88326] Updated weights for policy 0, policy_version 6140 (0.0008) -[2023-10-09 00:14:23,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 12582912. Throughput: 0: 1697.4, 1: 1666.0. Samples: 3148846. Policy #0 lag: (min: 10.0, avg: 17.6, max: 42.0) -[2023-10-09 00:14:23,974][87372] Avg episode reward: [(0, '3.720'), (1, '3.220')] -[2023-10-09 00:14:25,152][88327] Updated weights for policy 1, policy_version 6150 (0.0008) -[2023-10-09 00:14:25,516][88327] Updated weights for policy 1, policy_version 6160 (0.0008) -[2023-10-09 00:14:25,884][88327] Updated weights for policy 1, policy_version 6170 (0.0008) -[2023-10-09 00:14:26,185][88326] Updated weights for policy 0, policy_version 6150 (0.0010) -[2023-10-09 00:14:26,550][88326] Updated weights for policy 0, policy_version 6160 (0.0008) -[2023-10-09 00:14:26,928][88326] Updated weights for policy 0, policy_version 6170 (0.0008) -[2023-10-09 00:14:28,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 12648448. Throughput: 0: 1670.7, 1: 1693.9. Samples: 3168602. Policy #0 lag: (min: 10.0, avg: 17.6, max: 42.0) -[2023-10-09 00:14:28,975][87372] Avg episode reward: [(0, '3.630'), (1, '2.990')] -[2023-10-09 00:14:29,806][88327] Updated weights for policy 1, policy_version 6180 (0.0008) -[2023-10-09 00:14:30,162][88327] Updated weights for policy 1, policy_version 6190 (0.0009) -[2023-10-09 00:14:30,530][88327] Updated weights for policy 1, policy_version 6200 (0.0010) -[2023-10-09 00:14:31,016][88326] Updated weights for policy 0, policy_version 6180 (0.0010) -[2023-10-09 00:14:31,397][88326] Updated weights for policy 0, policy_version 6190 (0.0008) -[2023-10-09 00:14:31,758][88326] Updated weights for policy 0, policy_version 6200 (0.0010) -[2023-10-09 00:14:33,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 12713984. Throughput: 0: 1695.0, 1: 1698.4. Samples: 3189502. Policy #0 lag: (min: 30.0, avg: 35.2, max: 62.0) -[2023-10-09 00:14:33,975][87372] Avg episode reward: [(0, '3.550'), (1, '3.450')] -[2023-10-09 00:14:33,984][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000006208_6356992.pth... -[2023-10-09 00:14:33,984][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000006208_6356992.pth... -[2023-10-09 00:14:34,026][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000004640_4751360.pth -[2023-10-09 00:14:34,026][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000004640_4751360.pth -[2023-10-09 00:14:34,534][88327] Updated weights for policy 1, policy_version 6210 (0.0009) -[2023-10-09 00:14:34,897][88327] Updated weights for policy 1, policy_version 6220 (0.0010) -[2023-10-09 00:14:35,271][88327] Updated weights for policy 1, policy_version 6230 (0.0008) -[2023-10-09 00:14:35,638][88327] Updated weights for policy 1, policy_version 6240 (0.0009) -[2023-10-09 00:14:35,756][88326] Updated weights for policy 0, policy_version 6210 (0.0009) -[2023-10-09 00:14:36,133][88326] Updated weights for policy 0, policy_version 6220 (0.0007) -[2023-10-09 00:14:36,507][88326] Updated weights for policy 0, policy_version 6230 (0.0007) -[2023-10-09 00:14:36,872][88326] Updated weights for policy 0, policy_version 6240 (0.0007) -[2023-10-09 00:14:38,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 12779520. Throughput: 0: 1690.9, 1: 1677.3. Samples: 3199440. Policy #0 lag: (min: 30.0, avg: 35.2, max: 62.0) -[2023-10-09 00:14:38,974][87372] Avg episode reward: [(0, '3.470'), (1, '3.280')] -[2023-10-09 00:14:39,808][88327] Updated weights for policy 1, policy_version 6250 (0.0008) -[2023-10-09 00:14:40,178][88327] Updated weights for policy 1, policy_version 6260 (0.0010) -[2023-10-09 00:14:40,548][88327] Updated weights for policy 1, policy_version 6270 (0.0008) -[2023-10-09 00:14:40,836][88326] Updated weights for policy 0, policy_version 6250 (0.0009) -[2023-10-09 00:14:41,205][88326] Updated weights for policy 0, policy_version 6260 (0.0007) -[2023-10-09 00:14:41,580][88326] Updated weights for policy 0, policy_version 6270 (0.0007) -[2023-10-09 00:14:43,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 12845056. Throughput: 0: 1681.6, 1: 1706.7. Samples: 3219570. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:14:43,975][87372] Avg episode reward: [(0, '3.370'), (1, '3.380')] -[2023-10-09 00:14:44,716][88327] Updated weights for policy 1, policy_version 6280 (0.0008) -[2023-10-09 00:14:45,077][88327] Updated weights for policy 1, policy_version 6290 (0.0009) -[2023-10-09 00:14:45,449][88327] Updated weights for policy 1, policy_version 6300 (0.0008) -[2023-10-09 00:14:45,601][88326] Updated weights for policy 0, policy_version 6280 (0.0008) -[2023-10-09 00:14:45,977][88326] Updated weights for policy 0, policy_version 6290 (0.0009) -[2023-10-09 00:14:46,349][88326] Updated weights for policy 0, policy_version 6300 (0.0008) -[2023-10-09 00:14:48,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 12910592. Throughput: 0: 1699.7, 1: 1706.8. Samples: 3240262. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:14:48,975][87372] Avg episode reward: [(0, '3.610'), (1, '3.430')] -[2023-10-09 00:14:49,565][88327] Updated weights for policy 1, policy_version 6310 (0.0009) -[2023-10-09 00:14:49,933][88327] Updated weights for policy 1, policy_version 6320 (0.0008) -[2023-10-09 00:14:50,299][88327] Updated weights for policy 1, policy_version 6330 (0.0008) -[2023-10-09 00:14:50,432][88326] Updated weights for policy 0, policy_version 6310 (0.0010) -[2023-10-09 00:14:50,810][88326] Updated weights for policy 0, policy_version 6320 (0.0008) -[2023-10-09 00:14:51,176][88326] Updated weights for policy 0, policy_version 6330 (0.0011) -[2023-10-09 00:14:53,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 12976128. Throughput: 0: 1674.4, 1: 1684.2. Samples: 3249412. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:14:53,975][87372] Avg episode reward: [(0, '3.490'), (1, '3.350')] -[2023-10-09 00:14:54,254][88327] Updated weights for policy 1, policy_version 6340 (0.0008) -[2023-10-09 00:14:54,619][88327] Updated weights for policy 1, policy_version 6350 (0.0007) -[2023-10-09 00:14:54,985][88327] Updated weights for policy 1, policy_version 6360 (0.0009) -[2023-10-09 00:14:55,316][88326] Updated weights for policy 0, policy_version 6340 (0.0008) -[2023-10-09 00:14:55,686][88326] Updated weights for policy 0, policy_version 6350 (0.0008) -[2023-10-09 00:14:56,059][88326] Updated weights for policy 0, policy_version 6360 (0.0008) -[2023-10-09 00:14:58,962][88327] Updated weights for policy 1, policy_version 6370 (0.0008) -[2023-10-09 00:14:58,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 13041664. Throughput: 0: 1683.3, 1: 1700.1. Samples: 3269902. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:14:58,975][87372] Avg episode reward: [(0, '3.610'), (1, '3.180')] -[2023-10-09 00:14:59,333][88327] Updated weights for policy 1, policy_version 6380 (0.0007) -[2023-10-09 00:14:59,702][88327] Updated weights for policy 1, policy_version 6390 (0.0008) -[2023-10-09 00:15:00,064][88327] Updated weights for policy 1, policy_version 6400 (0.0007) -[2023-10-09 00:15:00,093][88326] Updated weights for policy 0, policy_version 6370 (0.0009) -[2023-10-09 00:15:00,485][88326] Updated weights for policy 0, policy_version 6380 (0.0007) -[2023-10-09 00:15:00,868][88326] Updated weights for policy 0, policy_version 6390 (0.0008) -[2023-10-09 00:15:01,231][88326] Updated weights for policy 0, policy_version 6400 (0.0009) -[2023-10-09 00:15:03,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 13107200. Throughput: 0: 1691.7, 1: 1691.2. Samples: 3290558. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:15:03,974][87372] Avg episode reward: [(0, '3.680'), (1, '3.350')] -[2023-10-09 00:15:04,272][88327] Updated weights for policy 1, policy_version 6410 (0.0007) -[2023-10-09 00:15:04,636][88327] Updated weights for policy 1, policy_version 6420 (0.0008) -[2023-10-09 00:15:04,998][88327] Updated weights for policy 1, policy_version 6430 (0.0008) -[2023-10-09 00:15:05,281][88326] Updated weights for policy 0, policy_version 6410 (0.0010) -[2023-10-09 00:15:05,649][88326] Updated weights for policy 0, policy_version 6420 (0.0011) -[2023-10-09 00:15:06,021][88326] Updated weights for policy 0, policy_version 6430 (0.0009) -[2023-10-09 00:15:08,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.3, 300 sec: 13440.4). Total num frames: 13172736. Throughput: 0: 1664.6, 1: 1687.5. Samples: 3299690. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:15:08,974][87372] Avg episode reward: [(0, '4.000'), (1, '3.350')] -[2023-10-09 00:15:08,975][88088] Saving new best policy, reward=4.000! -[2023-10-09 00:15:09,137][88327] Updated weights for policy 1, policy_version 6440 (0.0010) -[2023-10-09 00:15:09,503][88327] Updated weights for policy 1, policy_version 6450 (0.0008) -[2023-10-09 00:15:09,865][88327] Updated weights for policy 1, policy_version 6460 (0.0007) -[2023-10-09 00:15:09,995][88326] Updated weights for policy 0, policy_version 6440 (0.0008) -[2023-10-09 00:15:10,372][88326] Updated weights for policy 0, policy_version 6450 (0.0008) -[2023-10-09 00:15:10,742][88326] Updated weights for policy 0, policy_version 6460 (0.0011) -[2023-10-09 00:15:13,817][88327] Updated weights for policy 1, policy_version 6470 (0.0008) -[2023-10-09 00:15:13,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 13238272. Throughput: 0: 1693.2, 1: 1681.6. Samples: 3320472. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:15:13,974][87372] Avg episode reward: [(0, '3.900'), (1, '3.350')] -[2023-10-09 00:15:14,198][88327] Updated weights for policy 1, policy_version 6480 (0.0008) -[2023-10-09 00:15:14,571][88327] Updated weights for policy 1, policy_version 6490 (0.0009) -[2023-10-09 00:15:14,842][88326] Updated weights for policy 0, policy_version 6470 (0.0009) -[2023-10-09 00:15:15,212][88326] Updated weights for policy 0, policy_version 6480 (0.0008) -[2023-10-09 00:15:15,584][88326] Updated weights for policy 0, policy_version 6490 (0.0008) -[2023-10-09 00:15:18,660][88327] Updated weights for policy 1, policy_version 6500 (0.0010) -[2023-10-09 00:15:18,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 13303808. Throughput: 0: 1693.6, 1: 1683.1. Samples: 3341454. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:15:18,975][87372] Avg episode reward: [(0, '3.690'), (1, '3.200')] -[2023-10-09 00:15:19,020][88327] Updated weights for policy 1, policy_version 6510 (0.0008) -[2023-10-09 00:15:19,385][88327] Updated weights for policy 1, policy_version 6520 (0.0007) -[2023-10-09 00:15:19,600][88326] Updated weights for policy 0, policy_version 6500 (0.0008) -[2023-10-09 00:15:19,981][88326] Updated weights for policy 0, policy_version 6510 (0.0008) -[2023-10-09 00:15:20,357][88326] Updated weights for policy 0, policy_version 6520 (0.0009) -[2023-10-09 00:15:23,262][88327] Updated weights for policy 1, policy_version 6530 (0.0008) -[2023-10-09 00:15:23,632][88327] Updated weights for policy 1, policy_version 6540 (0.0008) -[2023-10-09 00:15:23,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 13369344. Throughput: 0: 1675.3, 1: 1682.8. Samples: 3350558. Policy #0 lag: (min: 0.0, avg: 25.0, max: 32.0) -[2023-10-09 00:15:23,975][87372] Avg episode reward: [(0, '3.490'), (1, '3.250')] -[2023-10-09 00:15:24,001][88327] Updated weights for policy 1, policy_version 6550 (0.0009) -[2023-10-09 00:15:24,358][88327] Updated weights for policy 1, policy_version 6560 (0.0009) -[2023-10-09 00:15:24,387][88326] Updated weights for policy 0, policy_version 6530 (0.0007) -[2023-10-09 00:15:24,758][88326] Updated weights for policy 0, policy_version 6540 (0.0008) -[2023-10-09 00:15:25,124][88326] Updated weights for policy 0, policy_version 6550 (0.0009) -[2023-10-09 00:15:25,491][88326] Updated weights for policy 0, policy_version 6560 (0.0007) -[2023-10-09 00:15:28,378][88327] Updated weights for policy 1, policy_version 6570 (0.0009) -[2023-10-09 00:15:28,750][88327] Updated weights for policy 1, policy_version 6580 (0.0008) -[2023-10-09 00:15:28,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 13434880. Throughput: 0: 1695.0, 1: 1686.8. Samples: 3371748. Policy #0 lag: (min: 0.0, avg: 25.0, max: 32.0) -[2023-10-09 00:15:28,975][87372] Avg episode reward: [(0, '3.690'), (1, '3.310')] -[2023-10-09 00:15:29,111][88327] Updated weights for policy 1, policy_version 6590 (0.0010) -[2023-10-09 00:15:29,530][88326] Updated weights for policy 0, policy_version 6570 (0.0008) -[2023-10-09 00:15:29,892][88326] Updated weights for policy 0, policy_version 6580 (0.0009) -[2023-10-09 00:15:30,267][88326] Updated weights for policy 0, policy_version 6590 (0.0008) -[2023-10-09 00:15:33,129][88327] Updated weights for policy 1, policy_version 6600 (0.0010) -[2023-10-09 00:15:33,496][88327] Updated weights for policy 1, policy_version 6610 (0.0010) -[2023-10-09 00:15:33,863][88327] Updated weights for policy 1, policy_version 6620 (0.0008) -[2023-10-09 00:15:33,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 13500416. Throughput: 0: 1693.1, 1: 1687.7. Samples: 3392396. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:15:33,975][87372] Avg episode reward: [(0, '3.400'), (1, '3.300')] -[2023-10-09 00:15:34,238][88326] Updated weights for policy 0, policy_version 6600 (0.0009) -[2023-10-09 00:15:34,615][88326] Updated weights for policy 0, policy_version 6610 (0.0009) -[2023-10-09 00:15:34,994][88326] Updated weights for policy 0, policy_version 6620 (0.0009) -[2023-10-09 00:15:37,927][88327] Updated weights for policy 1, policy_version 6630 (0.0007) -[2023-10-09 00:15:38,292][88327] Updated weights for policy 1, policy_version 6640 (0.0007) -[2023-10-09 00:15:38,660][88327] Updated weights for policy 1, policy_version 6650 (0.0008) -[2023-10-09 00:15:38,974][87372] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 13598720. Throughput: 0: 1690.7, 1: 1699.3. Samples: 3401960. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:15:38,975][87372] Avg episode reward: [(0, '3.350'), (1, '3.390')] -[2023-10-09 00:15:39,078][88326] Updated weights for policy 0, policy_version 6630 (0.0010) -[2023-10-09 00:15:39,455][88326] Updated weights for policy 0, policy_version 6640 (0.0007) -[2023-10-09 00:15:39,817][88326] Updated weights for policy 0, policy_version 6650 (0.0007) -[2023-10-09 00:15:42,757][88327] Updated weights for policy 1, policy_version 6660 (0.0009) -[2023-10-09 00:15:43,124][88327] Updated weights for policy 1, policy_version 6670 (0.0010) -[2023-10-09 00:15:43,490][88327] Updated weights for policy 1, policy_version 6680 (0.0009) -[2023-10-09 00:15:43,757][88326] Updated weights for policy 0, policy_version 6660 (0.0008) -[2023-10-09 00:15:43,974][87372] Fps is (10 sec: 16384.2, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 13664256. Throughput: 0: 1698.5, 1: 1695.6. Samples: 3422638. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) -[2023-10-09 00:15:43,974][87372] Avg episode reward: [(0, '3.480'), (1, '3.500')] -[2023-10-09 00:15:44,127][88326] Updated weights for policy 0, policy_version 6670 (0.0009) -[2023-10-09 00:15:44,495][88326] Updated weights for policy 0, policy_version 6680 (0.0008) -[2023-10-09 00:15:47,586][88327] Updated weights for policy 1, policy_version 6690 (0.0009) -[2023-10-09 00:15:47,954][88327] Updated weights for policy 1, policy_version 6700 (0.0009) -[2023-10-09 00:15:48,310][88327] Updated weights for policy 1, policy_version 6710 (0.0010) -[2023-10-09 00:15:48,622][88326] Updated weights for policy 0, policy_version 6690 (0.0008) -[2023-10-09 00:15:48,684][88327] Updated weights for policy 1, policy_version 6720 (0.0008) -[2023-10-09 00:15:48,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 13729792. Throughput: 0: 1702.4, 1: 1682.0. Samples: 3442856. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) -[2023-10-09 00:15:48,974][87372] Avg episode reward: [(0, '3.880'), (1, '3.810')] -[2023-10-09 00:15:48,982][88168] Saving new best policy, reward=3.810! -[2023-10-09 00:15:49,010][88326] Updated weights for policy 0, policy_version 6700 (0.0009) -[2023-10-09 00:15:49,373][88326] Updated weights for policy 0, policy_version 6710 (0.0009) -[2023-10-09 00:15:49,739][88326] Updated weights for policy 0, policy_version 6720 (0.0007) -[2023-10-09 00:15:52,816][88327] Updated weights for policy 1, policy_version 6730 (0.0008) -[2023-10-09 00:15:53,188][88327] Updated weights for policy 1, policy_version 6740 (0.0007) -[2023-10-09 00:15:53,555][88327] Updated weights for policy 1, policy_version 6750 (0.0010) -[2023-10-09 00:15:53,654][88326] Updated weights for policy 0, policy_version 6730 (0.0007) -[2023-10-09 00:15:53,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 13795328. Throughput: 0: 1700.8, 1: 1695.0. Samples: 3452502. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-10-09 00:15:53,975][87372] Avg episode reward: [(0, '3.850'), (1, '3.480')] -[2023-10-09 00:15:54,026][88326] Updated weights for policy 0, policy_version 6740 (0.0009) -[2023-10-09 00:15:54,393][88326] Updated weights for policy 0, policy_version 6750 (0.0008) -[2023-10-09 00:15:57,542][88327] Updated weights for policy 1, policy_version 6760 (0.0010) -[2023-10-09 00:15:57,918][88327] Updated weights for policy 1, policy_version 6770 (0.0010) -[2023-10-09 00:15:58,275][88327] Updated weights for policy 1, policy_version 6780 (0.0008) -[2023-10-09 00:15:58,385][88326] Updated weights for policy 0, policy_version 6760 (0.0009) -[2023-10-09 00:15:58,757][88326] Updated weights for policy 0, policy_version 6770 (0.0009) -[2023-10-09 00:15:58,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 13860864. Throughput: 0: 1703.6, 1: 1696.1. Samples: 3473456. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-10-09 00:15:58,975][87372] Avg episode reward: [(0, '3.980'), (1, '3.360')] -[2023-10-09 00:15:59,127][88326] Updated weights for policy 0, policy_version 6780 (0.0008) -[2023-10-09 00:16:02,319][88327] Updated weights for policy 1, policy_version 6790 (0.0009) -[2023-10-09 00:16:02,686][88327] Updated weights for policy 1, policy_version 6800 (0.0009) -[2023-10-09 00:16:03,058][88327] Updated weights for policy 1, policy_version 6810 (0.0010) -[2023-10-09 00:16:03,209][88326] Updated weights for policy 0, policy_version 6790 (0.0008) -[2023-10-09 00:16:03,582][88326] Updated weights for policy 0, policy_version 6800 (0.0008) -[2023-10-09 00:16:03,947][88326] Updated weights for policy 0, policy_version 6810 (0.0009) -[2023-10-09 00:16:03,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 13926400. Throughput: 0: 1698.8, 1: 1670.2. Samples: 3493060. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:16:03,975][87372] Avg episode reward: [(0, '3.790'), (1, '3.130')] -[2023-10-09 00:16:07,048][88327] Updated weights for policy 1, policy_version 6820 (0.0009) -[2023-10-09 00:16:07,428][88327] Updated weights for policy 1, policy_version 6830 (0.0008) -[2023-10-09 00:16:07,792][88327] Updated weights for policy 1, policy_version 6840 (0.0009) -[2023-10-09 00:16:08,102][88326] Updated weights for policy 0, policy_version 6820 (0.0010) -[2023-10-09 00:16:08,470][88326] Updated weights for policy 0, policy_version 6830 (0.0007) -[2023-10-09 00:16:08,827][88326] Updated weights for policy 0, policy_version 6840 (0.0009) -[2023-10-09 00:16:08,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 13991936. Throughput: 0: 1703.2, 1: 1699.0. Samples: 3503658. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:16:08,974][87372] Avg episode reward: [(0, '3.890'), (1, '3.250')] -[2023-10-09 00:16:11,737][88327] Updated weights for policy 1, policy_version 6850 (0.0008) -[2023-10-09 00:16:12,105][88327] Updated weights for policy 1, policy_version 6860 (0.0011) -[2023-10-09 00:16:12,471][88327] Updated weights for policy 1, policy_version 6870 (0.0008) -[2023-10-09 00:16:12,793][88326] Updated weights for policy 0, policy_version 6850 (0.0007) -[2023-10-09 00:16:12,839][88327] Updated weights for policy 1, policy_version 6880 (0.0008) -[2023-10-09 00:16:13,170][88326] Updated weights for policy 0, policy_version 6860 (0.0009) -[2023-10-09 00:16:13,537][88326] Updated weights for policy 0, policy_version 6870 (0.0008) -[2023-10-09 00:16:13,904][88326] Updated weights for policy 0, policy_version 6880 (0.0009) -[2023-10-09 00:16:13,974][87372] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 14090240. Throughput: 0: 1706.5, 1: 1680.3. Samples: 3524158. Policy #0 lag: (min: 14.0, avg: 20.1, max: 46.0) -[2023-10-09 00:16:13,975][87372] Avg episode reward: [(0, '3.810'), (1, '3.410')] -[2023-10-09 00:16:17,056][88327] Updated weights for policy 1, policy_version 6890 (0.0007) -[2023-10-09 00:16:17,425][88327] Updated weights for policy 1, policy_version 6900 (0.0007) -[2023-10-09 00:16:17,789][88327] Updated weights for policy 1, policy_version 6910 (0.0007) -[2023-10-09 00:16:17,920][88326] Updated weights for policy 0, policy_version 6890 (0.0007) -[2023-10-09 00:16:18,292][88326] Updated weights for policy 0, policy_version 6900 (0.0009) -[2023-10-09 00:16:18,665][88326] Updated weights for policy 0, policy_version 6910 (0.0009) -[2023-10-09 00:16:18,974][87372] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 14155776. Throughput: 0: 1694.3, 1: 1667.0. Samples: 3543656. Policy #0 lag: (min: 42.0, avg: 54.9, max: 56.0) -[2023-10-09 00:16:18,975][87372] Avg episode reward: [(0, '3.820'), (1, '3.700')] -[2023-10-09 00:16:21,915][88327] Updated weights for policy 1, policy_version 6920 (0.0008) -[2023-10-09 00:16:22,283][88327] Updated weights for policy 1, policy_version 6930 (0.0007) -[2023-10-09 00:16:22,619][88326] Updated weights for policy 0, policy_version 6920 (0.0009) -[2023-10-09 00:16:22,656][88327] Updated weights for policy 1, policy_version 6940 (0.0009) -[2023-10-09 00:16:22,991][88326] Updated weights for policy 0, policy_version 6930 (0.0008) -[2023-10-09 00:16:23,367][88326] Updated weights for policy 0, policy_version 6940 (0.0008) -[2023-10-09 00:16:23,974][87372] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 14221312. Throughput: 0: 1706.8, 1: 1687.1. Samples: 3554686. Policy #0 lag: (min: 42.0, avg: 54.9, max: 56.0) -[2023-10-09 00:16:23,975][87372] Avg episode reward: [(0, '3.830'), (1, '3.730')] -[2023-10-09 00:16:26,563][88327] Updated weights for policy 1, policy_version 6950 (0.0007) -[2023-10-09 00:16:26,935][88327] Updated weights for policy 1, policy_version 6960 (0.0007) -[2023-10-09 00:16:27,304][88327] Updated weights for policy 1, policy_version 6970 (0.0008) -[2023-10-09 00:16:27,321][88326] Updated weights for policy 0, policy_version 6950 (0.0007) -[2023-10-09 00:16:27,689][88326] Updated weights for policy 0, policy_version 6960 (0.0007) -[2023-10-09 00:16:28,066][88326] Updated weights for policy 0, policy_version 6970 (0.0007) -[2023-10-09 00:16:28,974][87372] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 14286848. Throughput: 0: 1707.3, 1: 1677.5. Samples: 3574956. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:16:28,975][87372] Avg episode reward: [(0, '3.770'), (1, '3.560')] -[2023-10-09 00:16:31,336][88327] Updated weights for policy 1, policy_version 6980 (0.0008) -[2023-10-09 00:16:31,703][88327] Updated weights for policy 1, policy_version 6990 (0.0009) -[2023-10-09 00:16:32,048][88326] Updated weights for policy 0, policy_version 6980 (0.0007) -[2023-10-09 00:16:32,069][88327] Updated weights for policy 1, policy_version 7000 (0.0009) -[2023-10-09 00:16:32,422][88326] Updated weights for policy 0, policy_version 6990 (0.0007) -[2023-10-09 00:16:32,803][88326] Updated weights for policy 0, policy_version 7000 (0.0007) -[2023-10-09 00:16:33,974][87372] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 14352384. Throughput: 0: 1679.3, 1: 1688.7. Samples: 3594414. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:16:33,975][87372] Avg episode reward: [(0, '3.580'), (1, '3.510')] -[2023-10-09 00:16:33,982][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000007008_7176192.pth... -[2023-10-09 00:16:33,982][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000007008_7176192.pth... -[2023-10-09 00:16:34,020][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000005440_5570560.pth -[2023-10-09 00:16:34,024][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000005440_5570560.pth -[2023-10-09 00:16:36,110][88327] Updated weights for policy 1, policy_version 7010 (0.0007) -[2023-10-09 00:16:36,478][88327] Updated weights for policy 1, policy_version 7020 (0.0007) -[2023-10-09 00:16:36,838][88327] Updated weights for policy 1, policy_version 7030 (0.0008) -[2023-10-09 00:16:37,016][88326] Updated weights for policy 0, policy_version 7010 (0.0008) -[2023-10-09 00:16:37,211][88327] Updated weights for policy 1, policy_version 7040 (0.0009) -[2023-10-09 00:16:37,404][88326] Updated weights for policy 0, policy_version 7020 (0.0007) -[2023-10-09 00:16:37,784][88326] Updated weights for policy 0, policy_version 7030 (0.0008) -[2023-10-09 00:16:38,148][88326] Updated weights for policy 0, policy_version 7040 (0.0007) -[2023-10-09 00:16:38,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 14417920. Throughput: 0: 1706.2, 1: 1701.5. Samples: 3605848. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 00:16:38,975][87372] Avg episode reward: [(0, '3.790'), (1, '3.540')] -[2023-10-09 00:16:41,077][88327] Updated weights for policy 1, policy_version 7050 (0.0009) -[2023-10-09 00:16:41,440][88327] Updated weights for policy 1, policy_version 7060 (0.0007) -[2023-10-09 00:16:41,809][88327] Updated weights for policy 1, policy_version 7070 (0.0009) -[2023-10-09 00:16:42,211][88326] Updated weights for policy 0, policy_version 7050 (0.0008) -[2023-10-09 00:16:42,590][88326] Updated weights for policy 0, policy_version 7060 (0.0009) -[2023-10-09 00:16:42,969][88326] Updated weights for policy 0, policy_version 7070 (0.0008) -[2023-10-09 00:16:43,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 14483456. Throughput: 0: 1688.7, 1: 1681.1. Samples: 3625094. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 00:16:43,975][87372] Avg episode reward: [(0, '3.740'), (1, '3.410')] -[2023-10-09 00:16:45,985][88327] Updated weights for policy 1, policy_version 7080 (0.0008) -[2023-10-09 00:16:46,365][88327] Updated weights for policy 1, policy_version 7090 (0.0009) -[2023-10-09 00:16:46,726][88327] Updated weights for policy 1, policy_version 7100 (0.0008) -[2023-10-09 00:16:46,873][88326] Updated weights for policy 0, policy_version 7080 (0.0008) -[2023-10-09 00:16:47,254][88326] Updated weights for policy 0, policy_version 7090 (0.0008) -[2023-10-09 00:16:47,618][88326] Updated weights for policy 0, policy_version 7100 (0.0009) -[2023-10-09 00:16:48,974][87372] Fps is (10 sec: 13106.6, 60 sec: 13653.2, 300 sec: 13551.5). Total num frames: 14548992. Throughput: 0: 1672.1, 1: 1703.2. Samples: 3644950. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:16:48,976][87372] Avg episode reward: [(0, '3.670'), (1, '3.340')] -[2023-10-09 00:16:50,850][88327] Updated weights for policy 1, policy_version 7110 (0.0008) -[2023-10-09 00:16:51,206][88327] Updated weights for policy 1, policy_version 7120 (0.0008) -[2023-10-09 00:16:51,550][88326] Updated weights for policy 0, policy_version 7110 (0.0009) -[2023-10-09 00:16:51,563][88327] Updated weights for policy 1, policy_version 7130 (0.0007) -[2023-10-09 00:16:51,916][88326] Updated weights for policy 0, policy_version 7120 (0.0010) -[2023-10-09 00:16:52,286][88326] Updated weights for policy 0, policy_version 7130 (0.0007) -[2023-10-09 00:16:53,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 14614528. Throughput: 0: 1698.1, 1: 1688.3. Samples: 3656048. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:16:53,975][87372] Avg episode reward: [(0, '3.730'), (1, '3.590')] -[2023-10-09 00:16:55,517][88327] Updated weights for policy 1, policy_version 7140 (0.0008) -[2023-10-09 00:16:55,880][88327] Updated weights for policy 1, policy_version 7150 (0.0009) -[2023-10-09 00:16:56,242][88327] Updated weights for policy 1, policy_version 7160 (0.0008) -[2023-10-09 00:16:56,272][88326] Updated weights for policy 0, policy_version 7140 (0.0007) -[2023-10-09 00:16:56,642][88326] Updated weights for policy 0, policy_version 7150 (0.0008) -[2023-10-09 00:16:57,020][88326] Updated weights for policy 0, policy_version 7160 (0.0011) -[2023-10-09 00:16:58,974][87372] Fps is (10 sec: 13107.8, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 14680064. Throughput: 0: 1671.3, 1: 1686.1. Samples: 3675240. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:16:58,975][87372] Avg episode reward: [(0, '3.770'), (1, '3.730')] -[2023-10-09 00:17:00,077][88327] Updated weights for policy 1, policy_version 7170 (0.0009) -[2023-10-09 00:17:00,449][88327] Updated weights for policy 1, policy_version 7180 (0.0009) -[2023-10-09 00:17:00,814][88327] Updated weights for policy 1, policy_version 7190 (0.0009) -[2023-10-09 00:17:01,087][88326] Updated weights for policy 0, policy_version 7170 (0.0009) -[2023-10-09 00:17:01,170][88327] Updated weights for policy 1, policy_version 7200 (0.0009) -[2023-10-09 00:17:01,459][88326] Updated weights for policy 0, policy_version 7180 (0.0008) -[2023-10-09 00:17:01,824][88326] Updated weights for policy 0, policy_version 7190 (0.0009) -[2023-10-09 00:17:02,186][88326] Updated weights for policy 0, policy_version 7200 (0.0008) -[2023-10-09 00:17:03,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 14745600. Throughput: 0: 1678.0, 1: 1712.1. Samples: 3696212. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:17:03,975][87372] Avg episode reward: [(0, '3.760'), (1, '3.600')] -[2023-10-09 00:17:05,078][88327] Updated weights for policy 1, policy_version 7210 (0.0010) -[2023-10-09 00:17:05,441][88327] Updated weights for policy 1, policy_version 7220 (0.0009) -[2023-10-09 00:17:05,808][88327] Updated weights for policy 1, policy_version 7230 (0.0010) -[2023-10-09 00:17:06,178][88326] Updated weights for policy 0, policy_version 7210 (0.0007) -[2023-10-09 00:17:06,542][88326] Updated weights for policy 0, policy_version 7220 (0.0007) -[2023-10-09 00:17:06,919][88326] Updated weights for policy 0, policy_version 7230 (0.0007) -[2023-10-09 00:17:08,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 14811136. Throughput: 0: 1688.2, 1: 1685.6. Samples: 3706510. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 00:17:08,975][87372] Avg episode reward: [(0, '3.900'), (1, '3.560')] -[2023-10-09 00:17:09,803][88327] Updated weights for policy 1, policy_version 7240 (0.0008) -[2023-10-09 00:17:10,174][88327] Updated weights for policy 1, policy_version 7250 (0.0009) -[2023-10-09 00:17:10,540][88327] Updated weights for policy 1, policy_version 7260 (0.0008) -[2023-10-09 00:17:11,021][88326] Updated weights for policy 0, policy_version 7240 (0.0010) -[2023-10-09 00:17:11,390][88326] Updated weights for policy 0, policy_version 7250 (0.0011) -[2023-10-09 00:17:11,764][88326] Updated weights for policy 0, policy_version 7260 (0.0010) -[2023-10-09 00:17:13,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 14876672. Throughput: 0: 1667.1, 1: 1700.4. Samples: 3726492. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 00:17:13,975][87372] Avg episode reward: [(0, '4.030'), (1, '3.530')] -[2023-10-09 00:17:13,975][88088] Saving new best policy, reward=4.030! -[2023-10-09 00:17:14,580][88327] Updated weights for policy 1, policy_version 7270 (0.0008) -[2023-10-09 00:17:14,956][88327] Updated weights for policy 1, policy_version 7280 (0.0008) -[2023-10-09 00:17:15,330][88327] Updated weights for policy 1, policy_version 7290 (0.0008) -[2023-10-09 00:17:15,770][88326] Updated weights for policy 0, policy_version 7270 (0.0010) -[2023-10-09 00:17:16,135][88326] Updated weights for policy 0, policy_version 7280 (0.0007) -[2023-10-09 00:17:16,505][88326] Updated weights for policy 0, policy_version 7290 (0.0007) -[2023-10-09 00:17:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 14942208. Throughput: 0: 1696.4, 1: 1711.2. Samples: 3747758. Policy #0 lag: (min: 1.0, avg: 9.3, max: 33.0) -[2023-10-09 00:17:18,975][87372] Avg episode reward: [(0, '4.300'), (1, '3.470')] -[2023-10-09 00:17:18,985][88088] Saving new best policy, reward=4.300! -[2023-10-09 00:17:19,253][88327] Updated weights for policy 1, policy_version 7300 (0.0008) -[2023-10-09 00:17:19,626][88327] Updated weights for policy 1, policy_version 7310 (0.0009) -[2023-10-09 00:17:19,990][88327] Updated weights for policy 1, policy_version 7320 (0.0008) -[2023-10-09 00:17:20,311][88326] Updated weights for policy 0, policy_version 7300 (0.0007) -[2023-10-09 00:17:20,687][88326] Updated weights for policy 0, policy_version 7310 (0.0008) -[2023-10-09 00:17:21,047][88326] Updated weights for policy 0, policy_version 7320 (0.0009) -[2023-10-09 00:17:23,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 15007744. Throughput: 0: 1675.7, 1: 1686.6. Samples: 3757154. Policy #0 lag: (min: 1.0, avg: 9.3, max: 33.0) -[2023-10-09 00:17:23,975][87372] Avg episode reward: [(0, '4.150'), (1, '3.450')] -[2023-10-09 00:17:24,070][88327] Updated weights for policy 1, policy_version 7330 (0.0008) -[2023-10-09 00:17:24,440][88327] Updated weights for policy 1, policy_version 7340 (0.0007) -[2023-10-09 00:17:24,816][88327] Updated weights for policy 1, policy_version 7350 (0.0010) -[2023-10-09 00:17:25,184][88327] Updated weights for policy 1, policy_version 7360 (0.0008) -[2023-10-09 00:17:25,224][88326] Updated weights for policy 0, policy_version 7330 (0.0010) -[2023-10-09 00:17:25,632][88326] Updated weights for policy 0, policy_version 7340 (0.0010) -[2023-10-09 00:17:26,011][88326] Updated weights for policy 0, policy_version 7350 (0.0009) -[2023-10-09 00:17:26,376][88326] Updated weights for policy 0, policy_version 7360 (0.0007) -[2023-10-09 00:17:28,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 15073280. Throughput: 0: 1684.9, 1: 1709.7. Samples: 3777852. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-09 00:17:28,975][87372] Avg episode reward: [(0, '4.250'), (1, '3.330')] -[2023-10-09 00:17:29,326][88327] Updated weights for policy 1, policy_version 7370 (0.0007) -[2023-10-09 00:17:29,692][88327] Updated weights for policy 1, policy_version 7380 (0.0007) -[2023-10-09 00:17:30,061][88327] Updated weights for policy 1, policy_version 7390 (0.0008) -[2023-10-09 00:17:30,500][88326] Updated weights for policy 0, policy_version 7370 (0.0008) -[2023-10-09 00:17:30,865][88326] Updated weights for policy 0, policy_version 7380 (0.0007) -[2023-10-09 00:17:31,238][88326] Updated weights for policy 0, policy_version 7390 (0.0008) -[2023-10-09 00:17:33,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 15138816. Throughput: 0: 1706.6, 1: 1711.0. Samples: 3798740. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-09 00:17:33,975][87372] Avg episode reward: [(0, '4.320'), (1, '3.630')] -[2023-10-09 00:17:33,982][88088] Saving new best policy, reward=4.320! -[2023-10-09 00:17:34,125][88327] Updated weights for policy 1, policy_version 7400 (0.0007) -[2023-10-09 00:17:34,497][88327] Updated weights for policy 1, policy_version 7410 (0.0008) -[2023-10-09 00:17:34,862][88327] Updated weights for policy 1, policy_version 7420 (0.0007) -[2023-10-09 00:17:35,207][88326] Updated weights for policy 0, policy_version 7400 (0.0009) -[2023-10-09 00:17:35,566][88326] Updated weights for policy 0, policy_version 7410 (0.0008) -[2023-10-09 00:17:35,943][88326] Updated weights for policy 0, policy_version 7420 (0.0009) -[2023-10-09 00:17:38,924][88327] Updated weights for policy 1, policy_version 7430 (0.0007) -[2023-10-09 00:17:38,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 15204352. Throughput: 0: 1676.9, 1: 1695.1. Samples: 3807786. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:17:38,975][87372] Avg episode reward: [(0, '4.450'), (1, '3.730')] -[2023-10-09 00:17:38,976][88088] Saving new best policy, reward=4.450! -[2023-10-09 00:17:39,299][88327] Updated weights for policy 1, policy_version 7440 (0.0007) -[2023-10-09 00:17:39,667][88327] Updated weights for policy 1, policy_version 7450 (0.0007) -[2023-10-09 00:17:40,045][88326] Updated weights for policy 0, policy_version 7430 (0.0009) -[2023-10-09 00:17:40,414][88326] Updated weights for policy 0, policy_version 7440 (0.0009) -[2023-10-09 00:17:40,790][88326] Updated weights for policy 0, policy_version 7450 (0.0010) -[2023-10-09 00:17:43,655][88327] Updated weights for policy 1, policy_version 7460 (0.0008) -[2023-10-09 00:17:43,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 15269888. Throughput: 0: 1696.7, 1: 1712.3. Samples: 3828648. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:17:43,975][87372] Avg episode reward: [(0, '4.100'), (1, '3.830')] -[2023-10-09 00:17:44,019][88327] Updated weights for policy 1, policy_version 7470 (0.0007) -[2023-10-09 00:17:44,376][88327] Updated weights for policy 1, policy_version 7480 (0.0007) -[2023-10-09 00:17:44,672][88168] Saving new best policy, reward=3.830! -[2023-10-09 00:17:44,829][88326] Updated weights for policy 0, policy_version 7460 (0.0009) -[2023-10-09 00:17:45,205][88326] Updated weights for policy 0, policy_version 7470 (0.0010) -[2023-10-09 00:17:45,573][88326] Updated weights for policy 0, policy_version 7480 (0.0010) -[2023-10-09 00:17:48,320][88327] Updated weights for policy 1, policy_version 7490 (0.0007) -[2023-10-09 00:17:48,683][88327] Updated weights for policy 1, policy_version 7500 (0.0007) -[2023-10-09 00:17:48,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.3, 300 sec: 13440.4). Total num frames: 15335424. Throughput: 0: 1706.1, 1: 1704.5. Samples: 3849690. Policy #0 lag: (min: 31.0, avg: 32.3, max: 55.0) -[2023-10-09 00:17:48,974][87372] Avg episode reward: [(0, '4.170'), (1, '3.760')] -[2023-10-09 00:17:49,052][88327] Updated weights for policy 1, policy_version 7510 (0.0008) -[2023-10-09 00:17:49,414][88327] Updated weights for policy 1, policy_version 7520 (0.0011) -[2023-10-09 00:17:49,500][88326] Updated weights for policy 0, policy_version 7490 (0.0008) -[2023-10-09 00:17:49,868][88326] Updated weights for policy 0, policy_version 7500 (0.0010) -[2023-10-09 00:17:50,244][88326] Updated weights for policy 0, policy_version 7510 (0.0009) -[2023-10-09 00:17:50,614][88326] Updated weights for policy 0, policy_version 7520 (0.0007) -[2023-10-09 00:17:53,447][88327] Updated weights for policy 1, policy_version 7530 (0.0009) -[2023-10-09 00:17:53,809][88327] Updated weights for policy 1, policy_version 7540 (0.0009) -[2023-10-09 00:17:53,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.3, 300 sec: 13440.4). Total num frames: 15400960. Throughput: 0: 1682.6, 1: 1705.3. Samples: 3858966. Policy #0 lag: (min: 31.0, avg: 32.3, max: 55.0) -[2023-10-09 00:17:53,975][87372] Avg episode reward: [(0, '3.960'), (1, '3.940')] -[2023-10-09 00:17:54,179][88327] Updated weights for policy 1, policy_version 7550 (0.0010) -[2023-10-09 00:17:54,251][88168] Saving new best policy, reward=3.940! -[2023-10-09 00:17:54,562][88326] Updated weights for policy 0, policy_version 7530 (0.0010) -[2023-10-09 00:17:54,928][88326] Updated weights for policy 0, policy_version 7540 (0.0011) -[2023-10-09 00:17:55,302][88326] Updated weights for policy 0, policy_version 7550 (0.0009) -[2023-10-09 00:17:58,098][88327] Updated weights for policy 1, policy_version 7560 (0.0009) -[2023-10-09 00:17:58,463][88327] Updated weights for policy 1, policy_version 7570 (0.0010) -[2023-10-09 00:17:58,829][88327] Updated weights for policy 1, policy_version 7580 (0.0010) -[2023-10-09 00:17:58,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 15466496. Throughput: 0: 1706.4, 1: 1702.5. Samples: 3879892. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:17:58,975][87372] Avg episode reward: [(0, '3.940'), (1, '3.710')] -[2023-10-09 00:17:59,336][88326] Updated weights for policy 0, policy_version 7560 (0.0009) -[2023-10-09 00:17:59,702][88326] Updated weights for policy 0, policy_version 7570 (0.0009) -[2023-10-09 00:18:00,070][88326] Updated weights for policy 0, policy_version 7580 (0.0007) -[2023-10-09 00:18:02,820][88327] Updated weights for policy 1, policy_version 7590 (0.0009) -[2023-10-09 00:18:03,184][88327] Updated weights for policy 1, policy_version 7600 (0.0009) -[2023-10-09 00:18:03,548][88327] Updated weights for policy 1, policy_version 7610 (0.0010) -[2023-10-09 00:18:03,974][87372] Fps is (10 sec: 16383.8, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 15564800. Throughput: 0: 1706.5, 1: 1688.1. Samples: 3900514. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:18:03,975][87372] Avg episode reward: [(0, '3.900'), (1, '3.420')] -[2023-10-09 00:18:04,001][88326] Updated weights for policy 0, policy_version 7590 (0.0008) -[2023-10-09 00:18:04,372][88326] Updated weights for policy 0, policy_version 7600 (0.0009) -[2023-10-09 00:18:04,747][88326] Updated weights for policy 0, policy_version 7610 (0.0009) -[2023-10-09 00:18:07,473][88327] Updated weights for policy 1, policy_version 7620 (0.0009) -[2023-10-09 00:18:07,841][88327] Updated weights for policy 1, policy_version 7630 (0.0009) -[2023-10-09 00:18:08,200][88327] Updated weights for policy 1, policy_version 7640 (0.0011) -[2023-10-09 00:18:08,798][88326] Updated weights for policy 0, policy_version 7620 (0.0008) -[2023-10-09 00:18:08,974][87372] Fps is (10 sec: 16384.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 15630336. Throughput: 0: 1702.6, 1: 1701.5. Samples: 3910338. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-09 00:18:08,975][87372] Avg episode reward: [(0, '3.730'), (1, '3.360')] -[2023-10-09 00:18:09,174][88326] Updated weights for policy 0, policy_version 7630 (0.0011) -[2023-10-09 00:18:09,541][88326] Updated weights for policy 0, policy_version 7640 (0.0008) -[2023-10-09 00:18:12,600][88327] Updated weights for policy 1, policy_version 7650 (0.0010) -[2023-10-09 00:18:12,968][88327] Updated weights for policy 1, policy_version 7660 (0.0010) -[2023-10-09 00:18:13,337][88327] Updated weights for policy 1, policy_version 7670 (0.0008) -[2023-10-09 00:18:13,719][88327] Updated weights for policy 1, policy_version 7680 (0.0009) -[2023-10-09 00:18:13,787][88326] Updated weights for policy 0, policy_version 7650 (0.0008) -[2023-10-09 00:18:13,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 15695872. Throughput: 0: 1702.3, 1: 1702.9. Samples: 3931090. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-09 00:18:13,975][87372] Avg episode reward: [(0, '3.670'), (1, '3.270')] -[2023-10-09 00:18:14,175][88326] Updated weights for policy 0, policy_version 7660 (0.0011) -[2023-10-09 00:18:14,544][88326] Updated weights for policy 0, policy_version 7670 (0.0011) -[2023-10-09 00:18:14,913][88326] Updated weights for policy 0, policy_version 7680 (0.0010) -[2023-10-09 00:18:17,693][88327] Updated weights for policy 1, policy_version 7690 (0.0007) -[2023-10-09 00:18:18,066][88327] Updated weights for policy 1, policy_version 7700 (0.0008) -[2023-10-09 00:18:18,435][88327] Updated weights for policy 1, policy_version 7710 (0.0009) -[2023-10-09 00:18:18,800][88326] Updated weights for policy 0, policy_version 7690 (0.0008) -[2023-10-09 00:18:18,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 15761408. Throughput: 0: 1703.2, 1: 1684.7. Samples: 3951192. Policy #0 lag: (min: 25.0, avg: 37.3, max: 57.0) -[2023-10-09 00:18:18,974][87372] Avg episode reward: [(0, '3.930'), (1, '3.540')] -[2023-10-09 00:18:19,170][88326] Updated weights for policy 0, policy_version 7700 (0.0007) -[2023-10-09 00:18:19,526][88326] Updated weights for policy 0, policy_version 7710 (0.0009) -[2023-10-09 00:18:22,489][88327] Updated weights for policy 1, policy_version 7720 (0.0008) -[2023-10-09 00:18:22,861][88327] Updated weights for policy 1, policy_version 7730 (0.0007) -[2023-10-09 00:18:23,231][88327] Updated weights for policy 1, policy_version 7740 (0.0008) -[2023-10-09 00:18:23,559][88326] Updated weights for policy 0, policy_version 7720 (0.0008) -[2023-10-09 00:18:23,928][88326] Updated weights for policy 0, policy_version 7730 (0.0008) -[2023-10-09 00:18:23,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 15826944. Throughput: 0: 1699.0, 1: 1707.8. Samples: 3961092. Policy #0 lag: (min: 25.0, avg: 37.3, max: 57.0) -[2023-10-09 00:18:23,974][87372] Avg episode reward: [(0, '3.730'), (1, '3.890')] -[2023-10-09 00:18:24,308][88326] Updated weights for policy 0, policy_version 7740 (0.0007) -[2023-10-09 00:18:27,323][88327] Updated weights for policy 1, policy_version 7750 (0.0007) -[2023-10-09 00:18:27,685][88327] Updated weights for policy 1, policy_version 7760 (0.0009) -[2023-10-09 00:18:28,055][88327] Updated weights for policy 1, policy_version 7770 (0.0008) -[2023-10-09 00:18:28,310][88326] Updated weights for policy 0, policy_version 7750 (0.0008) -[2023-10-09 00:18:28,681][88326] Updated weights for policy 0, policy_version 7760 (0.0007) -[2023-10-09 00:18:28,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 15892480. Throughput: 0: 1700.6, 1: 1704.4. Samples: 3981872. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:18:28,975][87372] Avg episode reward: [(0, '3.520'), (1, '3.780')] -[2023-10-09 00:18:29,044][88326] Updated weights for policy 0, policy_version 7770 (0.0009) -[2023-10-09 00:18:32,036][88327] Updated weights for policy 1, policy_version 7780 (0.0008) -[2023-10-09 00:18:32,394][88327] Updated weights for policy 1, policy_version 7790 (0.0007) -[2023-10-09 00:18:32,762][88327] Updated weights for policy 1, policy_version 7800 (0.0007) -[2023-10-09 00:18:33,159][88326] Updated weights for policy 0, policy_version 7780 (0.0008) -[2023-10-09 00:18:33,526][88326] Updated weights for policy 0, policy_version 7790 (0.0007) -[2023-10-09 00:18:33,896][88326] Updated weights for policy 0, policy_version 7800 (0.0007) -[2023-10-09 00:18:33,974][87372] Fps is (10 sec: 13106.7, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 15958016. Throughput: 0: 1694.7, 1: 1671.9. Samples: 4001188. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:18:33,976][87372] Avg episode reward: [(0, '3.570'), (1, '3.520')] -[2023-10-09 00:18:33,985][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000007808_7995392.pth... -[2023-10-09 00:18:34,016][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000006208_6356992.pth -[2023-10-09 00:18:34,020][88168] Saving a milestone ./train_atari/atari_battlezone_APPO/checkpoint_p1/milestones/checkpoint_000007808_7995392.pth -[2023-10-09 00:18:34,188][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000007808_7995392.pth... -[2023-10-09 00:18:34,217][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000006208_6356992.pth -[2023-10-09 00:18:34,221][88088] Saving a milestone ./train_atari/atari_battlezone_APPO/checkpoint_p0/milestones/checkpoint_000007808_7995392.pth -[2023-10-09 00:18:36,628][88327] Updated weights for policy 1, policy_version 7810 (0.0007) -[2023-10-09 00:18:36,991][88327] Updated weights for policy 1, policy_version 7820 (0.0010) -[2023-10-09 00:18:37,362][88327] Updated weights for policy 1, policy_version 7830 (0.0007) -[2023-10-09 00:18:37,728][88327] Updated weights for policy 1, policy_version 7840 (0.0010) -[2023-10-09 00:18:37,895][88326] Updated weights for policy 0, policy_version 7810 (0.0009) -[2023-10-09 00:18:38,263][88326] Updated weights for policy 0, policy_version 7820 (0.0010) -[2023-10-09 00:18:38,630][88326] Updated weights for policy 0, policy_version 7830 (0.0007) -[2023-10-09 00:18:38,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 16023552. Throughput: 0: 1697.9, 1: 1702.2. Samples: 4011972. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:18:38,975][87372] Avg episode reward: [(0, '3.710'), (1, '3.370')] -[2023-10-09 00:18:38,998][88326] Updated weights for policy 0, policy_version 7840 (0.0007) -[2023-10-09 00:18:41,779][88327] Updated weights for policy 1, policy_version 7850 (0.0009) -[2023-10-09 00:18:42,158][88327] Updated weights for policy 1, policy_version 7860 (0.0010) -[2023-10-09 00:18:42,531][88327] Updated weights for policy 1, policy_version 7870 (0.0011) -[2023-10-09 00:18:43,084][88326] Updated weights for policy 0, policy_version 7850 (0.0008) -[2023-10-09 00:18:43,460][88326] Updated weights for policy 0, policy_version 7860 (0.0007) -[2023-10-09 00:18:43,834][88326] Updated weights for policy 0, policy_version 7870 (0.0010) -[2023-10-09 00:18:43,974][87372] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 16121856. Throughput: 0: 1693.1, 1: 1686.2. Samples: 4031960. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:18:43,975][87372] Avg episode reward: [(0, '3.650'), (1, '3.320')] -[2023-10-09 00:18:46,615][88327] Updated weights for policy 1, policy_version 7880 (0.0008) -[2023-10-09 00:18:46,971][88327] Updated weights for policy 1, policy_version 7890 (0.0008) -[2023-10-09 00:18:47,330][88327] Updated weights for policy 1, policy_version 7900 (0.0009) -[2023-10-09 00:18:47,734][88326] Updated weights for policy 0, policy_version 7880 (0.0010) -[2023-10-09 00:18:48,099][88326] Updated weights for policy 0, policy_version 7890 (0.0011) -[2023-10-09 00:18:48,470][88326] Updated weights for policy 0, policy_version 7900 (0.0009) -[2023-10-09 00:18:48,974][87372] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 16187392. Throughput: 0: 1675.9, 1: 1680.7. Samples: 4051566. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:18:48,975][87372] Avg episode reward: [(0, '4.210'), (1, '3.450')] -[2023-10-09 00:18:51,571][88327] Updated weights for policy 1, policy_version 7910 (0.0010) -[2023-10-09 00:18:51,934][88327] Updated weights for policy 1, policy_version 7920 (0.0008) -[2023-10-09 00:18:52,311][88327] Updated weights for policy 1, policy_version 7930 (0.0008) -[2023-10-09 00:18:52,550][88326] Updated weights for policy 0, policy_version 7910 (0.0009) -[2023-10-09 00:18:52,936][88326] Updated weights for policy 0, policy_version 7920 (0.0009) -[2023-10-09 00:18:53,315][88326] Updated weights for policy 0, policy_version 7930 (0.0009) -[2023-10-09 00:18:53,974][87372] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 16252928. Throughput: 0: 1686.8, 1: 1695.9. Samples: 4062560. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-09 00:18:53,975][87372] Avg episode reward: [(0, '4.430'), (1, '3.360')] -[2023-10-09 00:18:56,335][88327] Updated weights for policy 1, policy_version 7940 (0.0010) -[2023-10-09 00:18:56,702][88327] Updated weights for policy 1, policy_version 7950 (0.0011) -[2023-10-09 00:18:57,077][88327] Updated weights for policy 1, policy_version 7960 (0.0008) -[2023-10-09 00:18:57,334][88326] Updated weights for policy 0, policy_version 7940 (0.0008) -[2023-10-09 00:18:57,714][88326] Updated weights for policy 0, policy_version 7950 (0.0009) -[2023-10-09 00:18:58,076][88326] Updated weights for policy 0, policy_version 7960 (0.0008) -[2023-10-09 00:18:58,974][87372] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 16318464. Throughput: 0: 1695.9, 1: 1671.7. Samples: 4082632. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-09 00:18:58,975][87372] Avg episode reward: [(0, '3.990'), (1, '3.440')] -[2023-10-09 00:19:01,131][88327] Updated weights for policy 1, policy_version 7970 (0.0008) -[2023-10-09 00:19:01,500][88327] Updated weights for policy 1, policy_version 7980 (0.0007) -[2023-10-09 00:19:01,868][88327] Updated weights for policy 1, policy_version 7990 (0.0008) -[2023-10-09 00:19:01,997][88326] Updated weights for policy 0, policy_version 7970 (0.0010) -[2023-10-09 00:19:02,229][88327] Updated weights for policy 1, policy_version 8000 (0.0008) -[2023-10-09 00:19:02,393][88326] Updated weights for policy 0, policy_version 7980 (0.0009) -[2023-10-09 00:19:02,756][88326] Updated weights for policy 0, policy_version 7990 (0.0009) -[2023-10-09 00:19:03,128][88326] Updated weights for policy 0, policy_version 8000 (0.0008) -[2023-10-09 00:19:03,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 16384000. Throughput: 0: 1668.3, 1: 1686.2. Samples: 4102144. Policy #0 lag: (min: 1.0, avg: 8.8, max: 33.0) -[2023-10-09 00:19:03,975][87372] Avg episode reward: [(0, '4.110'), (1, '3.580')] -[2023-10-09 00:19:06,334][88327] Updated weights for policy 1, policy_version 8010 (0.0010) -[2023-10-09 00:19:06,699][88327] Updated weights for policy 1, policy_version 8020 (0.0009) -[2023-10-09 00:19:07,066][88326] Updated weights for policy 0, policy_version 8010 (0.0010) -[2023-10-09 00:19:07,071][88327] Updated weights for policy 1, policy_version 8030 (0.0010) -[2023-10-09 00:19:07,429][88326] Updated weights for policy 0, policy_version 8020 (0.0010) -[2023-10-09 00:19:07,794][88326] Updated weights for policy 0, policy_version 8030 (0.0007) -[2023-10-09 00:19:08,974][87372] Fps is (10 sec: 13107.6, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 16449536. Throughput: 0: 1702.8, 1: 1689.0. Samples: 4113722. Policy #0 lag: (min: 1.0, avg: 8.8, max: 33.0) -[2023-10-09 00:19:08,975][87372] Avg episode reward: [(0, '4.050'), (1, '3.770')] -[2023-10-09 00:19:11,108][88327] Updated weights for policy 1, policy_version 8040 (0.0009) -[2023-10-09 00:19:11,485][88327] Updated weights for policy 1, policy_version 8050 (0.0008) -[2023-10-09 00:19:11,849][88327] Updated weights for policy 1, policy_version 8060 (0.0008) -[2023-10-09 00:19:11,918][88326] Updated weights for policy 0, policy_version 8040 (0.0009) -[2023-10-09 00:19:12,288][88326] Updated weights for policy 0, policy_version 8050 (0.0007) -[2023-10-09 00:19:12,661][88326] Updated weights for policy 0, policy_version 8060 (0.0008) -[2023-10-09 00:19:13,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 16515072. Throughput: 0: 1689.2, 1: 1664.1. Samples: 4132768. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-09 00:19:13,975][87372] Avg episode reward: [(0, '3.920'), (1, '3.750')] -[2023-10-09 00:19:15,953][88327] Updated weights for policy 1, policy_version 8070 (0.0010) -[2023-10-09 00:19:16,334][88327] Updated weights for policy 1, policy_version 8080 (0.0009) -[2023-10-09 00:19:16,691][88326] Updated weights for policy 0, policy_version 8070 (0.0008) -[2023-10-09 00:19:16,699][88327] Updated weights for policy 1, policy_version 8090 (0.0007) -[2023-10-09 00:19:17,047][88326] Updated weights for policy 0, policy_version 8080 (0.0008) -[2023-10-09 00:19:17,417][88326] Updated weights for policy 0, policy_version 8090 (0.0008) -[2023-10-09 00:19:18,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 16580608. Throughput: 0: 1678.8, 1: 1694.0. Samples: 4152964. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-09 00:19:18,975][87372] Avg episode reward: [(0, '4.190'), (1, '4.270')] -[2023-10-09 00:19:18,988][88168] Saving new best policy, reward=4.270! -[2023-10-09 00:19:20,661][88327] Updated weights for policy 1, policy_version 8100 (0.0008) -[2023-10-09 00:19:21,032][88327] Updated weights for policy 1, policy_version 8110 (0.0008) -[2023-10-09 00:19:21,376][88326] Updated weights for policy 0, policy_version 8100 (0.0009) -[2023-10-09 00:19:21,397][88327] Updated weights for policy 1, policy_version 8120 (0.0007) -[2023-10-09 00:19:21,749][88326] Updated weights for policy 0, policy_version 8110 (0.0008) -[2023-10-09 00:19:22,130][88326] Updated weights for policy 0, policy_version 8120 (0.0008) -[2023-10-09 00:19:23,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 16646144. Throughput: 0: 1705.5, 1: 1673.6. Samples: 4164028. Policy #0 lag: (min: 2.0, avg: 2.7, max: 20.0) -[2023-10-09 00:19:23,975][87372] Avg episode reward: [(0, '3.950'), (1, '4.060')] -[2023-10-09 00:19:25,560][88327] Updated weights for policy 1, policy_version 8130 (0.0008) -[2023-10-09 00:19:25,921][88327] Updated weights for policy 1, policy_version 8140 (0.0007) -[2023-10-09 00:19:26,294][88327] Updated weights for policy 1, policy_version 8150 (0.0007) -[2023-10-09 00:19:26,302][88326] Updated weights for policy 0, policy_version 8130 (0.0007) -[2023-10-09 00:19:26,654][88327] Updated weights for policy 1, policy_version 8160 (0.0007) -[2023-10-09 00:19:26,676][88326] Updated weights for policy 0, policy_version 8140 (0.0008) -[2023-10-09 00:19:27,050][88326] Updated weights for policy 0, policy_version 8150 (0.0008) -[2023-10-09 00:19:27,415][88326] Updated weights for policy 0, policy_version 8160 (0.0010) -[2023-10-09 00:19:28,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 16711680. Throughput: 0: 1683.5, 1: 1677.4. Samples: 4183200. Policy #0 lag: (min: 2.0, avg: 2.7, max: 20.0) -[2023-10-09 00:19:28,975][87372] Avg episode reward: [(0, '3.880'), (1, '4.050')] -[2023-10-09 00:19:30,586][88327] Updated weights for policy 1, policy_version 8170 (0.0008) -[2023-10-09 00:19:30,951][88327] Updated weights for policy 1, policy_version 8180 (0.0008) -[2023-10-09 00:19:31,311][88327] Updated weights for policy 1, policy_version 8190 (0.0008) -[2023-10-09 00:19:31,488][88326] Updated weights for policy 0, policy_version 8170 (0.0008) -[2023-10-09 00:19:31,857][88326] Updated weights for policy 0, policy_version 8180 (0.0008) -[2023-10-09 00:19:32,227][88326] Updated weights for policy 0, policy_version 8190 (0.0007) -[2023-10-09 00:19:33,974][87372] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 16777216. Throughput: 0: 1688.6, 1: 1694.2. Samples: 4203792. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-09 00:19:33,975][87372] Avg episode reward: [(0, '4.550'), (1, '3.970')] -[2023-10-09 00:19:33,988][88088] Saving new best policy, reward=4.550! -[2023-10-09 00:19:35,351][88327] Updated weights for policy 1, policy_version 8200 (0.0007) -[2023-10-09 00:19:35,706][88327] Updated weights for policy 1, policy_version 8210 (0.0008) -[2023-10-09 00:19:36,075][88327] Updated weights for policy 1, policy_version 8220 (0.0008) -[2023-10-09 00:19:36,412][88326] Updated weights for policy 0, policy_version 8200 (0.0008) -[2023-10-09 00:19:36,782][88326] Updated weights for policy 0, policy_version 8210 (0.0010) -[2023-10-09 00:19:37,164][88326] Updated weights for policy 0, policy_version 8220 (0.0009) -[2023-10-09 00:19:38,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 16842752. Throughput: 0: 1702.2, 1: 1668.8. Samples: 4214254. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-09 00:19:38,975][87372] Avg episode reward: [(0, '4.190'), (1, '3.860')] -[2023-10-09 00:19:40,076][88327] Updated weights for policy 1, policy_version 8230 (0.0008) -[2023-10-09 00:19:40,437][88327] Updated weights for policy 1, policy_version 8240 (0.0007) -[2023-10-09 00:19:40,811][88327] Updated weights for policy 1, policy_version 8250 (0.0009) -[2023-10-09 00:19:41,275][88326] Updated weights for policy 0, policy_version 8230 (0.0009) -[2023-10-09 00:19:41,639][88326] Updated weights for policy 0, policy_version 8240 (0.0009) -[2023-10-09 00:19:42,007][88326] Updated weights for policy 0, policy_version 8250 (0.0007) -[2023-10-09 00:19:43,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 16908288. Throughput: 0: 1667.3, 1: 1691.7. Samples: 4233782. Policy #0 lag: (min: 30.0, avg: 37.1, max: 62.0) -[2023-10-09 00:19:43,975][87372] Avg episode reward: [(0, '4.090'), (1, '3.720')] -[2023-10-09 00:19:44,803][88327] Updated weights for policy 1, policy_version 8260 (0.0009) -[2023-10-09 00:19:45,172][88327] Updated weights for policy 1, policy_version 8270 (0.0008) -[2023-10-09 00:19:45,541][88327] Updated weights for policy 1, policy_version 8280 (0.0007) -[2023-10-09 00:19:46,084][88326] Updated weights for policy 0, policy_version 8260 (0.0007) -[2023-10-09 00:19:46,446][88326] Updated weights for policy 0, policy_version 8270 (0.0010) -[2023-10-09 00:19:46,814][88326] Updated weights for policy 0, policy_version 8280 (0.0007) -[2023-10-09 00:19:48,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 16973824. Throughput: 0: 1688.7, 1: 1700.4. Samples: 4254652. Policy #0 lag: (min: 30.0, avg: 37.1, max: 62.0) -[2023-10-09 00:19:48,975][87372] Avg episode reward: [(0, '4.200'), (1, '4.010')] -[2023-10-09 00:19:49,437][88327] Updated weights for policy 1, policy_version 8290 (0.0009) -[2023-10-09 00:19:49,811][88327] Updated weights for policy 1, policy_version 8300 (0.0008) -[2023-10-09 00:19:50,180][88327] Updated weights for policy 1, policy_version 8310 (0.0008) -[2023-10-09 00:19:50,542][88327] Updated weights for policy 1, policy_version 8320 (0.0009) -[2023-10-09 00:19:50,994][88326] Updated weights for policy 0, policy_version 8290 (0.0008) -[2023-10-09 00:19:51,396][88326] Updated weights for policy 0, policy_version 8300 (0.0007) -[2023-10-09 00:19:51,774][88326] Updated weights for policy 0, policy_version 8310 (0.0007) -[2023-10-09 00:19:52,141][88326] Updated weights for policy 0, policy_version 8320 (0.0009) -[2023-10-09 00:19:53,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 17039360. Throughput: 0: 1679.2, 1: 1674.9. Samples: 4264660. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:19:53,975][87372] Avg episode reward: [(0, '3.960'), (1, '3.930')] -[2023-10-09 00:19:54,767][88327] Updated weights for policy 1, policy_version 8330 (0.0009) -[2023-10-09 00:19:55,137][88327] Updated weights for policy 1, policy_version 8340 (0.0009) -[2023-10-09 00:19:55,509][88327] Updated weights for policy 1, policy_version 8350 (0.0007) -[2023-10-09 00:19:56,080][88326] Updated weights for policy 0, policy_version 8330 (0.0008) -[2023-10-09 00:19:56,455][88326] Updated weights for policy 0, policy_version 8340 (0.0007) -[2023-10-09 00:19:56,823][88326] Updated weights for policy 0, policy_version 8350 (0.0007) -[2023-10-09 00:19:58,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 17104896. Throughput: 0: 1670.4, 1: 1703.4. Samples: 4284586. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:19:58,975][87372] Avg episode reward: [(0, '4.350'), (1, '3.910')] -[2023-10-09 00:19:59,466][88327] Updated weights for policy 1, policy_version 8360 (0.0008) -[2023-10-09 00:19:59,836][88327] Updated weights for policy 1, policy_version 8370 (0.0008) -[2023-10-09 00:20:00,212][88327] Updated weights for policy 1, policy_version 8380 (0.0011) -[2023-10-09 00:20:00,552][88326] Updated weights for policy 0, policy_version 8360 (0.0010) -[2023-10-09 00:20:00,921][88326] Updated weights for policy 0, policy_version 8370 (0.0009) -[2023-10-09 00:20:01,299][88326] Updated weights for policy 0, policy_version 8380 (0.0010) -[2023-10-09 00:20:03,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 17170432. Throughput: 0: 1687.6, 1: 1706.3. Samples: 4305690. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-10-09 00:20:03,975][87372] Avg episode reward: [(0, '4.190'), (1, '3.730')] -[2023-10-09 00:20:04,195][88327] Updated weights for policy 1, policy_version 8390 (0.0007) -[2023-10-09 00:20:04,573][88327] Updated weights for policy 1, policy_version 8400 (0.0008) -[2023-10-09 00:20:04,950][88327] Updated weights for policy 1, policy_version 8410 (0.0008) -[2023-10-09 00:20:05,493][88326] Updated weights for policy 0, policy_version 8390 (0.0010) -[2023-10-09 00:20:05,873][88326] Updated weights for policy 0, policy_version 8400 (0.0009) -[2023-10-09 00:20:06,239][88326] Updated weights for policy 0, policy_version 8410 (0.0008) -[2023-10-09 00:20:08,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 17235968. Throughput: 0: 1661.5, 1: 1691.1. Samples: 4314896. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-10-09 00:20:08,975][87372] Avg episode reward: [(0, '4.120'), (1, '3.670')] -[2023-10-09 00:20:09,045][88327] Updated weights for policy 1, policy_version 8420 (0.0007) -[2023-10-09 00:20:09,404][88327] Updated weights for policy 1, policy_version 8430 (0.0009) -[2023-10-09 00:20:09,780][88327] Updated weights for policy 1, policy_version 8440 (0.0007) -[2023-10-09 00:20:10,399][88326] Updated weights for policy 0, policy_version 8420 (0.0007) -[2023-10-09 00:20:10,759][88326] Updated weights for policy 0, policy_version 8430 (0.0009) -[2023-10-09 00:20:11,141][88326] Updated weights for policy 0, policy_version 8440 (0.0010) -[2023-10-09 00:20:13,813][88327] Updated weights for policy 1, policy_version 8450 (0.0008) -[2023-10-09 00:20:13,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 17301504. Throughput: 0: 1674.8, 1: 1703.9. Samples: 4335238. Policy #0 lag: (min: 21.0, avg: 21.1, max: 29.0) -[2023-10-09 00:20:13,975][87372] Avg episode reward: [(0, '3.930'), (1, '3.760')] -[2023-10-09 00:20:14,178][88327] Updated weights for policy 1, policy_version 8460 (0.0007) -[2023-10-09 00:20:14,540][88327] Updated weights for policy 1, policy_version 8470 (0.0011) -[2023-10-09 00:20:14,902][88327] Updated weights for policy 1, policy_version 8480 (0.0009) -[2023-10-09 00:20:15,059][88326] Updated weights for policy 0, policy_version 8450 (0.0008) -[2023-10-09 00:20:15,436][88326] Updated weights for policy 0, policy_version 8460 (0.0008) -[2023-10-09 00:20:15,801][88326] Updated weights for policy 0, policy_version 8470 (0.0008) -[2023-10-09 00:20:16,172][88326] Updated weights for policy 0, policy_version 8480 (0.0009) -[2023-10-09 00:20:18,855][88327] Updated weights for policy 1, policy_version 8490 (0.0009) -[2023-10-09 00:20:18,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 17367040. Throughput: 0: 1685.9, 1: 1705.2. Samples: 4356388. Policy #0 lag: (min: 21.0, avg: 21.1, max: 29.0) -[2023-10-09 00:20:18,975][87372] Avg episode reward: [(0, '4.050'), (1, '3.760')] -[2023-10-09 00:20:19,226][88327] Updated weights for policy 1, policy_version 8500 (0.0009) -[2023-10-09 00:20:19,596][88327] Updated weights for policy 1, policy_version 8510 (0.0011) -[2023-10-09 00:20:20,291][88326] Updated weights for policy 0, policy_version 8490 (0.0009) -[2023-10-09 00:20:20,661][88326] Updated weights for policy 0, policy_version 8500 (0.0010) -[2023-10-09 00:20:21,037][88326] Updated weights for policy 0, policy_version 8510 (0.0010) -[2023-10-09 00:20:23,638][88327] Updated weights for policy 1, policy_version 8520 (0.0009) -[2023-10-09 00:20:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 17432576. Throughput: 0: 1659.7, 1: 1699.6. Samples: 4365420. Policy #0 lag: (min: 26.0, avg: 26.0, max: 26.0) -[2023-10-09 00:20:23,975][87372] Avg episode reward: [(0, '4.250'), (1, '3.520')] -[2023-10-09 00:20:24,000][88327] Updated weights for policy 1, policy_version 8530 (0.0008) -[2023-10-09 00:20:24,365][88327] Updated weights for policy 1, policy_version 8540 (0.0010) -[2023-10-09 00:20:25,125][88326] Updated weights for policy 0, policy_version 8520 (0.0010) -[2023-10-09 00:20:25,496][88326] Updated weights for policy 0, policy_version 8530 (0.0011) -[2023-10-09 00:20:25,870][88326] Updated weights for policy 0, policy_version 8540 (0.0009) -[2023-10-09 00:20:28,345][88327] Updated weights for policy 1, policy_version 8550 (0.0009) -[2023-10-09 00:20:28,706][88327] Updated weights for policy 1, policy_version 8560 (0.0007) -[2023-10-09 00:20:28,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 17498112. Throughput: 0: 1687.3, 1: 1701.3. Samples: 4386272. Policy #0 lag: (min: 26.0, avg: 26.0, max: 26.0) -[2023-10-09 00:20:28,975][87372] Avg episode reward: [(0, '4.360'), (1, '3.660')] -[2023-10-09 00:20:29,070][88327] Updated weights for policy 1, policy_version 8570 (0.0010) -[2023-10-09 00:20:29,787][88326] Updated weights for policy 0, policy_version 8550 (0.0008) -[2023-10-09 00:20:30,163][88326] Updated weights for policy 0, policy_version 8560 (0.0007) -[2023-10-09 00:20:30,540][88326] Updated weights for policy 0, policy_version 8570 (0.0009) -[2023-10-09 00:20:33,161][88327] Updated weights for policy 1, policy_version 8580 (0.0008) -[2023-10-09 00:20:33,529][88327] Updated weights for policy 1, policy_version 8590 (0.0010) -[2023-10-09 00:20:33,889][88327] Updated weights for policy 1, policy_version 8600 (0.0010) -[2023-10-09 00:20:33,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 17563648. Throughput: 0: 1696.6, 1: 1695.1. Samples: 4407278. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:20:33,975][87372] Avg episode reward: [(0, '4.510'), (1, '3.830')] -[2023-10-09 00:20:33,984][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000008576_8781824.pth... -[2023-10-09 00:20:34,023][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000007008_7176192.pth -[2023-10-09 00:20:34,185][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000008608_8814592.pth... -[2023-10-09 00:20:34,214][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000007008_7176192.pth -[2023-10-09 00:20:34,524][88326] Updated weights for policy 0, policy_version 8580 (0.0008) -[2023-10-09 00:20:34,892][88326] Updated weights for policy 0, policy_version 8590 (0.0007) -[2023-10-09 00:20:35,267][88326] Updated weights for policy 0, policy_version 8600 (0.0007) -[2023-10-09 00:20:37,878][88327] Updated weights for policy 1, policy_version 8610 (0.0010) -[2023-10-09 00:20:38,243][88327] Updated weights for policy 1, policy_version 8620 (0.0008) -[2023-10-09 00:20:38,613][88327] Updated weights for policy 1, policy_version 8630 (0.0007) -[2023-10-09 00:20:38,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 17629184. Throughput: 0: 1675.8, 1: 1701.7. Samples: 4416648. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:20:38,975][87372] Avg episode reward: [(0, '4.520'), (1, '4.000')] -[2023-10-09 00:20:38,981][88327] Updated weights for policy 1, policy_version 8640 (0.0009) -[2023-10-09 00:20:39,475][88326] Updated weights for policy 0, policy_version 8610 (0.0008) -[2023-10-09 00:20:39,868][88326] Updated weights for policy 0, policy_version 8620 (0.0008) -[2023-10-09 00:20:40,243][88326] Updated weights for policy 0, policy_version 8630 (0.0007) -[2023-10-09 00:20:40,615][88326] Updated weights for policy 0, policy_version 8640 (0.0008) -[2023-10-09 00:20:43,229][88327] Updated weights for policy 1, policy_version 8650 (0.0007) -[2023-10-09 00:20:43,593][88327] Updated weights for policy 1, policy_version 8660 (0.0008) -[2023-10-09 00:20:43,964][88327] Updated weights for policy 1, policy_version 8670 (0.0007) -[2023-10-09 00:20:43,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 17694720. Throughput: 0: 1693.9, 1: 1698.8. Samples: 4437258. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-09 00:20:43,975][87372] Avg episode reward: [(0, '4.240'), (1, '3.980')] -[2023-10-09 00:20:44,672][88326] Updated weights for policy 0, policy_version 8650 (0.0008) -[2023-10-09 00:20:45,045][88326] Updated weights for policy 0, policy_version 8660 (0.0007) -[2023-10-09 00:20:45,420][88326] Updated weights for policy 0, policy_version 8670 (0.0007) -[2023-10-09 00:20:47,739][88327] Updated weights for policy 1, policy_version 8680 (0.0008) -[2023-10-09 00:20:48,112][88327] Updated weights for policy 1, policy_version 8690 (0.0007) -[2023-10-09 00:20:48,482][88327] Updated weights for policy 1, policy_version 8700 (0.0008) -[2023-10-09 00:20:48,974][87372] Fps is (10 sec: 16384.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 17793024. Throughput: 0: 1694.6, 1: 1685.9. Samples: 4457812. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-09 00:20:48,975][87372] Avg episode reward: [(0, '4.560'), (1, '3.930')] -[2023-10-09 00:20:49,259][88326] Updated weights for policy 0, policy_version 8680 (0.0010) -[2023-10-09 00:20:49,617][88326] Updated weights for policy 0, policy_version 8690 (0.0009) -[2023-10-09 00:20:49,991][88326] Updated weights for policy 0, policy_version 8700 (0.0007) -[2023-10-09 00:20:50,135][88088] Saving new best policy, reward=4.560! -[2023-10-09 00:20:52,499][88327] Updated weights for policy 1, policy_version 8710 (0.0009) -[2023-10-09 00:20:52,884][88327] Updated weights for policy 1, policy_version 8720 (0.0009) -[2023-10-09 00:20:53,255][88327] Updated weights for policy 1, policy_version 8730 (0.0007) -[2023-10-09 00:20:53,951][88326] Updated weights for policy 0, policy_version 8710 (0.0010) -[2023-10-09 00:20:53,974][87372] Fps is (10 sec: 16383.9, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 17858560. Throughput: 0: 1689.3, 1: 1708.5. Samples: 4467796. Policy #0 lag: (min: 15.0, avg: 15.9, max: 34.0) -[2023-10-09 00:20:53,975][87372] Avg episode reward: [(0, '4.120'), (1, '3.830')] -[2023-10-09 00:20:54,331][88326] Updated weights for policy 0, policy_version 8720 (0.0009) -[2023-10-09 00:20:54,699][88326] Updated weights for policy 0, policy_version 8730 (0.0009) -[2023-10-09 00:20:57,223][88327] Updated weights for policy 1, policy_version 8740 (0.0010) -[2023-10-09 00:20:57,597][88327] Updated weights for policy 1, policy_version 8750 (0.0010) -[2023-10-09 00:20:57,965][88327] Updated weights for policy 1, policy_version 8760 (0.0011) -[2023-10-09 00:20:58,581][88326] Updated weights for policy 0, policy_version 8740 (0.0007) -[2023-10-09 00:20:58,946][88326] Updated weights for policy 0, policy_version 8750 (0.0008) -[2023-10-09 00:20:58,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 17924096. Throughput: 0: 1704.1, 1: 1707.6. Samples: 4488766. Policy #0 lag: (min: 15.0, avg: 15.9, max: 34.0) -[2023-10-09 00:20:58,975][87372] Avg episode reward: [(0, '4.050'), (1, '3.800')] -[2023-10-09 00:20:59,315][88326] Updated weights for policy 0, policy_version 8760 (0.0008) -[2023-10-09 00:21:02,046][88327] Updated weights for policy 1, policy_version 8770 (0.0009) -[2023-10-09 00:21:02,414][88327] Updated weights for policy 1, policy_version 8780 (0.0007) -[2023-10-09 00:21:02,784][88327] Updated weights for policy 1, policy_version 8790 (0.0009) -[2023-10-09 00:21:03,146][88327] Updated weights for policy 1, policy_version 8800 (0.0009) -[2023-10-09 00:21:03,174][88326] Updated weights for policy 0, policy_version 8770 (0.0007) -[2023-10-09 00:21:03,544][88326] Updated weights for policy 0, policy_version 8780 (0.0007) -[2023-10-09 00:21:03,917][88326] Updated weights for policy 0, policy_version 8790 (0.0009) -[2023-10-09 00:21:03,974][87372] Fps is (10 sec: 13106.7, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 17989632. Throughput: 0: 1701.4, 1: 1676.2. Samples: 4508378. Policy #0 lag: (min: 9.0, avg: 23.7, max: 41.0) -[2023-10-09 00:21:03,976][87372] Avg episode reward: [(0, '4.480'), (1, '3.890')] -[2023-10-09 00:21:04,285][88326] Updated weights for policy 0, policy_version 8800 (0.0010) -[2023-10-09 00:21:07,100][88327] Updated weights for policy 1, policy_version 8810 (0.0007) -[2023-10-09 00:21:07,474][88327] Updated weights for policy 1, policy_version 8820 (0.0008) -[2023-10-09 00:21:07,832][88327] Updated weights for policy 1, policy_version 8830 (0.0008) -[2023-10-09 00:21:08,435][88326] Updated weights for policy 0, policy_version 8810 (0.0009) -[2023-10-09 00:21:08,805][88326] Updated weights for policy 0, policy_version 8820 (0.0008) -[2023-10-09 00:21:08,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 18055168. Throughput: 0: 1700.2, 1: 1707.1. Samples: 4518748. Policy #0 lag: (min: 9.0, avg: 23.7, max: 41.0) -[2023-10-09 00:21:08,975][87372] Avg episode reward: [(0, '4.300'), (1, '3.720')] -[2023-10-09 00:21:09,177][88326] Updated weights for policy 0, policy_version 8830 (0.0008) -[2023-10-09 00:21:11,908][88327] Updated weights for policy 1, policy_version 8840 (0.0008) -[2023-10-09 00:21:12,280][88327] Updated weights for policy 1, policy_version 8850 (0.0008) -[2023-10-09 00:21:12,649][88327] Updated weights for policy 1, policy_version 8860 (0.0009) -[2023-10-09 00:21:13,349][88326] Updated weights for policy 0, policy_version 8840 (0.0008) -[2023-10-09 00:21:13,729][88326] Updated weights for policy 0, policy_version 8850 (0.0010) -[2023-10-09 00:21:13,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 18120704. Throughput: 0: 1702.0, 1: 1692.8. Samples: 4539034. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-09 00:21:13,975][87372] Avg episode reward: [(0, '4.170'), (1, '3.840')] -[2023-10-09 00:21:14,104][88326] Updated weights for policy 0, policy_version 8860 (0.0009) -[2023-10-09 00:21:16,650][88327] Updated weights for policy 1, policy_version 8870 (0.0008) -[2023-10-09 00:21:17,019][88327] Updated weights for policy 1, policy_version 8880 (0.0008) -[2023-10-09 00:21:17,384][88327] Updated weights for policy 1, policy_version 8890 (0.0009) -[2023-10-09 00:21:18,002][88326] Updated weights for policy 0, policy_version 8870 (0.0011) -[2023-10-09 00:21:18,376][88326] Updated weights for policy 0, policy_version 8880 (0.0009) -[2023-10-09 00:21:18,746][88326] Updated weights for policy 0, policy_version 8890 (0.0009) -[2023-10-09 00:21:18,974][87372] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 18219008. Throughput: 0: 1694.1, 1: 1681.6. Samples: 4559186. Policy #0 lag: (min: 17.0, avg: 25.5, max: 49.0) -[2023-10-09 00:21:18,975][87372] Avg episode reward: [(0, '4.230'), (1, '3.940')] -[2023-10-09 00:21:21,241][88327] Updated weights for policy 1, policy_version 8900 (0.0010) -[2023-10-09 00:21:21,612][88327] Updated weights for policy 1, policy_version 8910 (0.0010) -[2023-10-09 00:21:21,977][88327] Updated weights for policy 1, policy_version 8920 (0.0011) -[2023-10-09 00:21:22,726][88326] Updated weights for policy 0, policy_version 8900 (0.0010) -[2023-10-09 00:21:23,090][88326] Updated weights for policy 0, policy_version 8910 (0.0010) -[2023-10-09 00:21:23,453][88326] Updated weights for policy 0, policy_version 8920 (0.0010) -[2023-10-09 00:21:23,974][87372] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 18284544. Throughput: 0: 1700.3, 1: 1706.9. Samples: 4569974. Policy #0 lag: (min: 17.0, avg: 25.5, max: 49.0) -[2023-10-09 00:21:23,975][87372] Avg episode reward: [(0, '4.220'), (1, '3.780')] -[2023-10-09 00:21:26,159][88327] Updated weights for policy 1, policy_version 8930 (0.0009) -[2023-10-09 00:21:26,517][88327] Updated weights for policy 1, policy_version 8940 (0.0010) -[2023-10-09 00:21:26,889][88327] Updated weights for policy 1, policy_version 8950 (0.0011) -[2023-10-09 00:21:27,264][88327] Updated weights for policy 1, policy_version 8960 (0.0009) -[2023-10-09 00:21:27,658][88326] Updated weights for policy 0, policy_version 8930 (0.0010) -[2023-10-09 00:21:28,052][88326] Updated weights for policy 0, policy_version 8940 (0.0008) -[2023-10-09 00:21:28,420][88326] Updated weights for policy 0, policy_version 8950 (0.0009) -[2023-10-09 00:21:28,794][88326] Updated weights for policy 0, policy_version 8960 (0.0009) -[2023-10-09 00:21:28,974][87372] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 18350080. Throughput: 0: 1702.3, 1: 1685.2. Samples: 4589694. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-09 00:21:28,975][87372] Avg episode reward: [(0, '4.350'), (1, '3.580')] -[2023-10-09 00:21:31,233][88327] Updated weights for policy 1, policy_version 8970 (0.0009) -[2023-10-09 00:21:31,601][88327] Updated weights for policy 1, policy_version 8980 (0.0009) -[2023-10-09 00:21:31,967][88327] Updated weights for policy 1, policy_version 8990 (0.0008) -[2023-10-09 00:21:32,690][88326] Updated weights for policy 0, policy_version 8970 (0.0009) -[2023-10-09 00:21:33,073][88326] Updated weights for policy 0, policy_version 8980 (0.0007) -[2023-10-09 00:21:33,442][88326] Updated weights for policy 0, policy_version 8990 (0.0009) -[2023-10-09 00:21:33,975][87372] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 18415616. Throughput: 0: 1677.9, 1: 1695.9. Samples: 4609630. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-09 00:21:33,976][87372] Avg episode reward: [(0, '4.190'), (1, '3.410')] -[2023-10-09 00:21:35,989][88327] Updated weights for policy 1, policy_version 9000 (0.0008) -[2023-10-09 00:21:36,362][88327] Updated weights for policy 1, policy_version 9010 (0.0009) -[2023-10-09 00:21:36,719][88327] Updated weights for policy 1, policy_version 9020 (0.0010) -[2023-10-09 00:21:37,459][88326] Updated weights for policy 0, policy_version 9000 (0.0007) -[2023-10-09 00:21:37,828][88326] Updated weights for policy 0, policy_version 9010 (0.0009) -[2023-10-09 00:21:38,206][88326] Updated weights for policy 0, policy_version 9020 (0.0008) -[2023-10-09 00:21:38,974][87372] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 18481152. Throughput: 0: 1699.1, 1: 1694.8. Samples: 4620520. Policy #0 lag: (min: 31.0, avg: 34.6, max: 63.0) -[2023-10-09 00:21:38,975][87372] Avg episode reward: [(0, '4.500'), (1, '3.110')] -[2023-10-09 00:21:40,713][88327] Updated weights for policy 1, policy_version 9030 (0.0009) -[2023-10-09 00:21:41,080][88327] Updated weights for policy 1, policy_version 9040 (0.0008) -[2023-10-09 00:21:41,439][88327] Updated weights for policy 1, policy_version 9050 (0.0010) -[2023-10-09 00:21:42,340][88326] Updated weights for policy 0, policy_version 9030 (0.0008) -[2023-10-09 00:21:42,711][88326] Updated weights for policy 0, policy_version 9040 (0.0009) -[2023-10-09 00:21:43,095][88326] Updated weights for policy 0, policy_version 9050 (0.0007) -[2023-10-09 00:21:43,974][87372] Fps is (10 sec: 13107.8, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 18546688. Throughput: 0: 1692.6, 1: 1681.8. Samples: 4640614. Policy #0 lag: (min: 31.0, avg: 34.6, max: 63.0) -[2023-10-09 00:21:43,975][87372] Avg episode reward: [(0, '4.360'), (1, '3.480')] -[2023-10-09 00:21:45,362][88327] Updated weights for policy 1, policy_version 9060 (0.0010) -[2023-10-09 00:21:45,753][88327] Updated weights for policy 1, policy_version 9070 (0.0010) -[2023-10-09 00:21:46,120][88327] Updated weights for policy 1, policy_version 9080 (0.0009) -[2023-10-09 00:21:47,069][88326] Updated weights for policy 0, policy_version 9060 (0.0008) -[2023-10-09 00:21:47,442][88326] Updated weights for policy 0, policy_version 9070 (0.0009) -[2023-10-09 00:21:47,801][88326] Updated weights for policy 0, policy_version 9080 (0.0009) -[2023-10-09 00:21:48,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 18612224. Throughput: 0: 1672.1, 1: 1707.6. Samples: 4660464. Policy #0 lag: (min: 26.0, avg: 28.8, max: 58.0) -[2023-10-09 00:21:48,975][87372] Avg episode reward: [(0, '4.240'), (1, '3.520')] -[2023-10-09 00:21:50,261][88327] Updated weights for policy 1, policy_version 9090 (0.0007) -[2023-10-09 00:21:50,629][88327] Updated weights for policy 1, policy_version 9100 (0.0009) -[2023-10-09 00:21:50,993][88327] Updated weights for policy 1, policy_version 9110 (0.0009) -[2023-10-09 00:21:51,351][88327] Updated weights for policy 1, policy_version 9120 (0.0010) -[2023-10-09 00:21:51,933][88326] Updated weights for policy 0, policy_version 9090 (0.0009) -[2023-10-09 00:21:52,296][88326] Updated weights for policy 0, policy_version 9100 (0.0009) -[2023-10-09 00:21:52,665][88326] Updated weights for policy 0, policy_version 9110 (0.0009) -[2023-10-09 00:21:53,034][88326] Updated weights for policy 0, policy_version 9120 (0.0008) -[2023-10-09 00:21:53,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 18677760. Throughput: 0: 1705.2, 1: 1687.2. Samples: 4671406. Policy #0 lag: (min: 26.0, avg: 28.8, max: 58.0) -[2023-10-09 00:21:53,975][87372] Avg episode reward: [(0, '4.590'), (1, '3.440')] -[2023-10-09 00:21:53,977][88088] Saving new best policy, reward=4.590! -[2023-10-09 00:21:55,364][88327] Updated weights for policy 1, policy_version 9130 (0.0012) -[2023-10-09 00:21:55,733][88327] Updated weights for policy 1, policy_version 9140 (0.0010) -[2023-10-09 00:21:56,108][88327] Updated weights for policy 1, policy_version 9150 (0.0007) -[2023-10-09 00:21:57,040][88326] Updated weights for policy 0, policy_version 9130 (0.0007) -[2023-10-09 00:21:57,417][88326] Updated weights for policy 0, policy_version 9140 (0.0010) -[2023-10-09 00:21:57,782][88326] Updated weights for policy 0, policy_version 9150 (0.0009) -[2023-10-09 00:21:58,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 18743296. Throughput: 0: 1694.6, 1: 1693.4. Samples: 4691494. Policy #0 lag: (min: 31.0, avg: 31.9, max: 52.0) -[2023-10-09 00:21:58,974][87372] Avg episode reward: [(0, '4.740'), (1, '3.980')] -[2023-10-09 00:21:58,975][88088] Saving new best policy, reward=4.740! -[2023-10-09 00:22:00,090][88327] Updated weights for policy 1, policy_version 9160 (0.0009) -[2023-10-09 00:22:00,455][88327] Updated weights for policy 1, policy_version 9170 (0.0009) -[2023-10-09 00:22:00,818][88327] Updated weights for policy 1, policy_version 9180 (0.0009) -[2023-10-09 00:22:01,850][88326] Updated weights for policy 0, policy_version 9160 (0.0008) -[2023-10-09 00:22:02,230][88326] Updated weights for policy 0, policy_version 9170 (0.0008) -[2023-10-09 00:22:02,595][88326] Updated weights for policy 0, policy_version 9180 (0.0007) -[2023-10-09 00:22:03,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 18808832. Throughput: 0: 1681.9, 1: 1708.9. Samples: 4711774. Policy #0 lag: (min: 31.0, avg: 31.9, max: 52.0) -[2023-10-09 00:22:03,975][87372] Avg episode reward: [(0, '4.260'), (1, '3.590')] -[2023-10-09 00:22:04,710][88327] Updated weights for policy 1, policy_version 9190 (0.0008) -[2023-10-09 00:22:05,067][88327] Updated weights for policy 1, policy_version 9200 (0.0008) -[2023-10-09 00:22:05,443][88327] Updated weights for policy 1, policy_version 9210 (0.0009) -[2023-10-09 00:22:06,615][88326] Updated weights for policy 0, policy_version 9190 (0.0007) -[2023-10-09 00:22:06,980][88326] Updated weights for policy 0, policy_version 9200 (0.0010) -[2023-10-09 00:22:07,355][88326] Updated weights for policy 0, policy_version 9210 (0.0010) -[2023-10-09 00:22:08,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 18874368. Throughput: 0: 1704.9, 1: 1680.1. Samples: 4722300. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:22:08,974][87372] Avg episode reward: [(0, '4.550'), (1, '3.870')] -[2023-10-09 00:22:09,499][88327] Updated weights for policy 1, policy_version 9220 (0.0008) -[2023-10-09 00:22:09,864][88327] Updated weights for policy 1, policy_version 9230 (0.0007) -[2023-10-09 00:22:10,238][88327] Updated weights for policy 1, policy_version 9240 (0.0009) -[2023-10-09 00:22:11,476][88326] Updated weights for policy 0, policy_version 9220 (0.0008) -[2023-10-09 00:22:11,856][88326] Updated weights for policy 0, policy_version 9230 (0.0007) -[2023-10-09 00:22:12,220][88326] Updated weights for policy 0, policy_version 9240 (0.0010) -[2023-10-09 00:22:13,974][87372] Fps is (10 sec: 13107.6, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 18939904. Throughput: 0: 1682.3, 1: 1706.4. Samples: 4742184. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:22:13,974][87372] Avg episode reward: [(0, '4.460'), (1, '3.720')] -[2023-10-09 00:22:14,231][88327] Updated weights for policy 1, policy_version 9250 (0.0009) -[2023-10-09 00:22:14,611][88327] Updated weights for policy 1, policy_version 9260 (0.0007) -[2023-10-09 00:22:14,981][88327] Updated weights for policy 1, policy_version 9270 (0.0011) -[2023-10-09 00:22:15,344][88327] Updated weights for policy 1, policy_version 9280 (0.0011) -[2023-10-09 00:22:16,187][88326] Updated weights for policy 0, policy_version 9250 (0.0009) -[2023-10-09 00:22:16,566][88326] Updated weights for policy 0, policy_version 9260 (0.0008) -[2023-10-09 00:22:16,933][88326] Updated weights for policy 0, policy_version 9270 (0.0008) -[2023-10-09 00:22:17,314][88326] Updated weights for policy 0, policy_version 9280 (0.0008) -[2023-10-09 00:22:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 19005440. Throughput: 0: 1693.7, 1: 1707.0. Samples: 4762658. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 00:22:18,974][87372] Avg episode reward: [(0, '4.570'), (1, '3.880')] -[2023-10-09 00:22:19,476][88327] Updated weights for policy 1, policy_version 9290 (0.0011) -[2023-10-09 00:22:19,854][88327] Updated weights for policy 1, policy_version 9300 (0.0008) -[2023-10-09 00:22:20,230][88327] Updated weights for policy 1, policy_version 9310 (0.0008) -[2023-10-09 00:22:21,361][88326] Updated weights for policy 0, policy_version 9290 (0.0008) -[2023-10-09 00:22:21,741][88326] Updated weights for policy 0, policy_version 9300 (0.0010) -[2023-10-09 00:22:22,109][88326] Updated weights for policy 0, policy_version 9310 (0.0009) -[2023-10-09 00:22:23,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 19070976. Throughput: 0: 1696.8, 1: 1687.5. Samples: 4772814. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 00:22:23,975][87372] Avg episode reward: [(0, '4.870'), (1, '4.020')] -[2023-10-09 00:22:23,976][88088] Saving new best policy, reward=4.870! -[2023-10-09 00:22:24,097][88327] Updated weights for policy 1, policy_version 9320 (0.0010) -[2023-10-09 00:22:24,458][88327] Updated weights for policy 1, policy_version 9330 (0.0011) -[2023-10-09 00:22:24,830][88327] Updated weights for policy 1, policy_version 9340 (0.0008) -[2023-10-09 00:22:25,965][88326] Updated weights for policy 0, policy_version 9320 (0.0007) -[2023-10-09 00:22:26,330][88326] Updated weights for policy 0, policy_version 9330 (0.0009) -[2023-10-09 00:22:26,703][88326] Updated weights for policy 0, policy_version 9340 (0.0007) -[2023-10-09 00:22:28,891][88327] Updated weights for policy 1, policy_version 9350 (0.0009) -[2023-10-09 00:22:28,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 19136512. Throughput: 0: 1682.3, 1: 1705.0. Samples: 4793040. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 00:22:28,975][87372] Avg episode reward: [(0, '5.070'), (1, '4.030')] -[2023-10-09 00:22:28,975][88088] Saving new best policy, reward=5.070! -[2023-10-09 00:22:29,252][88327] Updated weights for policy 1, policy_version 9360 (0.0007) -[2023-10-09 00:22:29,629][88327] Updated weights for policy 1, policy_version 9370 (0.0010) -[2023-10-09 00:22:30,700][88326] Updated weights for policy 0, policy_version 9350 (0.0008) -[2023-10-09 00:22:31,059][88326] Updated weights for policy 0, policy_version 9360 (0.0008) -[2023-10-09 00:22:31,446][88326] Updated weights for policy 0, policy_version 9370 (0.0008) -[2023-10-09 00:22:33,768][88327] Updated weights for policy 1, policy_version 9380 (0.0008) -[2023-10-09 00:22:33,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 19202048. Throughput: 0: 1708.0, 1: 1704.2. Samples: 4814016. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 00:22:33,974][87372] Avg episode reward: [(0, '4.810'), (1, '4.190')] -[2023-10-09 00:22:33,982][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000009376_9601024.pth... -[2023-10-09 00:22:34,016][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000007808_7995392.pth -[2023-10-09 00:22:34,167][88327] Updated weights for policy 1, policy_version 9390 (0.0010) -[2023-10-09 00:22:34,542][88327] Updated weights for policy 1, policy_version 9400 (0.0008) -[2023-10-09 00:22:34,833][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000009408_9633792.pth... -[2023-10-09 00:22:34,862][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000007808_7995392.pth -[2023-10-09 00:22:35,320][88326] Updated weights for policy 0, policy_version 9380 (0.0008) -[2023-10-09 00:22:35,687][88326] Updated weights for policy 0, policy_version 9390 (0.0009) -[2023-10-09 00:22:36,057][88326] Updated weights for policy 0, policy_version 9400 (0.0009) -[2023-10-09 00:22:38,529][88327] Updated weights for policy 1, policy_version 9410 (0.0010) -[2023-10-09 00:22:38,901][88327] Updated weights for policy 1, policy_version 9420 (0.0009) -[2023-10-09 00:22:38,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 19267584. Throughput: 0: 1683.6, 1: 1691.9. Samples: 4823302. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:22:38,975][87372] Avg episode reward: [(0, '4.730'), (1, '4.130')] -[2023-10-09 00:22:39,268][88327] Updated weights for policy 1, policy_version 9430 (0.0008) -[2023-10-09 00:22:39,633][88327] Updated weights for policy 1, policy_version 9440 (0.0007) -[2023-10-09 00:22:40,287][88326] Updated weights for policy 0, policy_version 9410 (0.0012) -[2023-10-09 00:22:40,667][88326] Updated weights for policy 0, policy_version 9420 (0.0010) -[2023-10-09 00:22:41,028][88326] Updated weights for policy 0, policy_version 9430 (0.0008) -[2023-10-09 00:22:41,411][88326] Updated weights for policy 0, policy_version 9440 (0.0007) -[2023-10-09 00:22:43,675][88327] Updated weights for policy 1, policy_version 9450 (0.0009) -[2023-10-09 00:22:43,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 19333120. Throughput: 0: 1682.5, 1: 1699.3. Samples: 4843674. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:22:43,975][87372] Avg episode reward: [(0, '4.280'), (1, '4.390')] -[2023-10-09 00:22:44,050][88327] Updated weights for policy 1, policy_version 9460 (0.0009) -[2023-10-09 00:22:44,425][88327] Updated weights for policy 1, policy_version 9470 (0.0010) -[2023-10-09 00:22:44,494][88168] Saving new best policy, reward=4.390! -[2023-10-09 00:22:45,321][88326] Updated weights for policy 0, policy_version 9450 (0.0007) -[2023-10-09 00:22:45,699][88326] Updated weights for policy 0, policy_version 9460 (0.0010) -[2023-10-09 00:22:46,062][88326] Updated weights for policy 0, policy_version 9470 (0.0010) -[2023-10-09 00:22:48,394][88327] Updated weights for policy 1, policy_version 9480 (0.0008) -[2023-10-09 00:22:48,756][88327] Updated weights for policy 1, policy_version 9490 (0.0008) -[2023-10-09 00:22:48,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 19398656. Throughput: 0: 1696.5, 1: 1699.0. Samples: 4864574. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:22:48,974][87372] Avg episode reward: [(0, '4.230'), (1, '4.200')] -[2023-10-09 00:22:49,117][88327] Updated weights for policy 1, policy_version 9500 (0.0010) -[2023-10-09 00:22:50,065][88326] Updated weights for policy 0, policy_version 9480 (0.0007) -[2023-10-09 00:22:50,428][88326] Updated weights for policy 0, policy_version 9490 (0.0007) -[2023-10-09 00:22:50,802][88326] Updated weights for policy 0, policy_version 9500 (0.0007) -[2023-10-09 00:22:53,338][88327] Updated weights for policy 1, policy_version 9510 (0.0009) -[2023-10-09 00:22:53,699][88327] Updated weights for policy 1, policy_version 9520 (0.0010) -[2023-10-09 00:22:53,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 19464192. Throughput: 0: 1669.9, 1: 1697.9. Samples: 4873852. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:22:53,975][87372] Avg episode reward: [(0, '4.680'), (1, '4.160')] -[2023-10-09 00:22:54,071][88327] Updated weights for policy 1, policy_version 9530 (0.0009) -[2023-10-09 00:22:54,941][88326] Updated weights for policy 0, policy_version 9510 (0.0007) -[2023-10-09 00:22:55,315][88326] Updated weights for policy 0, policy_version 9520 (0.0008) -[2023-10-09 00:22:55,688][88326] Updated weights for policy 0, policy_version 9530 (0.0009) -[2023-10-09 00:22:58,085][88327] Updated weights for policy 1, policy_version 9540 (0.0010) -[2023-10-09 00:22:58,455][88327] Updated weights for policy 1, policy_version 9550 (0.0008) -[2023-10-09 00:22:58,823][88327] Updated weights for policy 1, policy_version 9560 (0.0008) -[2023-10-09 00:22:58,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 19529728. Throughput: 0: 1691.9, 1: 1693.6. Samples: 4894530. Policy #0 lag: (min: 9.0, avg: 18.6, max: 41.0) -[2023-10-09 00:22:58,975][87372] Avg episode reward: [(0, '4.710'), (1, '4.010')] -[2023-10-09 00:22:59,775][88326] Updated weights for policy 0, policy_version 9540 (0.0009) -[2023-10-09 00:23:00,155][88326] Updated weights for policy 0, policy_version 9550 (0.0007) -[2023-10-09 00:23:00,525][88326] Updated weights for policy 0, policy_version 9560 (0.0009) -[2023-10-09 00:23:02,954][88327] Updated weights for policy 1, policy_version 9570 (0.0009) -[2023-10-09 00:23:03,321][88327] Updated weights for policy 1, policy_version 9580 (0.0007) -[2023-10-09 00:23:03,687][88327] Updated weights for policy 1, policy_version 9590 (0.0009) -[2023-10-09 00:23:03,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.3, 300 sec: 13440.4). Total num frames: 19595264. Throughput: 0: 1698.0, 1: 1688.7. Samples: 4915058. Policy #0 lag: (min: 9.0, avg: 18.6, max: 41.0) -[2023-10-09 00:23:03,975][87372] Avg episode reward: [(0, '4.590'), (1, '3.750')] -[2023-10-09 00:23:04,052][88327] Updated weights for policy 1, policy_version 9600 (0.0010) -[2023-10-09 00:23:04,564][88326] Updated weights for policy 0, policy_version 9570 (0.0009) -[2023-10-09 00:23:04,931][88326] Updated weights for policy 0, policy_version 9580 (0.0007) -[2023-10-09 00:23:05,303][88326] Updated weights for policy 0, policy_version 9590 (0.0010) -[2023-10-09 00:23:05,676][88326] Updated weights for policy 0, policy_version 9600 (0.0010) -[2023-10-09 00:23:07,912][88327] Updated weights for policy 1, policy_version 9610 (0.0009) -[2023-10-09 00:23:08,269][88327] Updated weights for policy 1, policy_version 9620 (0.0008) -[2023-10-09 00:23:08,636][88327] Updated weights for policy 1, policy_version 9630 (0.0009) -[2023-10-09 00:23:08,974][87372] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 19693568. Throughput: 0: 1676.3, 1: 1702.0. Samples: 4924834. Policy #0 lag: (min: 31.0, avg: 32.9, max: 61.0) -[2023-10-09 00:23:08,975][87372] Avg episode reward: [(0, '4.840'), (1, '4.010')] -[2023-10-09 00:23:09,662][88326] Updated weights for policy 0, policy_version 9610 (0.0008) -[2023-10-09 00:23:10,046][88326] Updated weights for policy 0, policy_version 9620 (0.0010) -[2023-10-09 00:23:10,408][88326] Updated weights for policy 0, policy_version 9630 (0.0009) -[2023-10-09 00:23:12,622][88327] Updated weights for policy 1, policy_version 9640 (0.0008) -[2023-10-09 00:23:12,987][88327] Updated weights for policy 1, policy_version 9650 (0.0009) -[2023-10-09 00:23:13,354][88327] Updated weights for policy 1, policy_version 9660 (0.0010) -[2023-10-09 00:23:13,974][87372] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 19759104. Throughput: 0: 1695.7, 1: 1697.6. Samples: 4945738. Policy #0 lag: (min: 31.0, avg: 32.9, max: 61.0) -[2023-10-09 00:23:13,975][87372] Avg episode reward: [(0, '4.570'), (1, '3.790')] -[2023-10-09 00:23:14,430][88326] Updated weights for policy 0, policy_version 9640 (0.0009) -[2023-10-09 00:23:14,802][88326] Updated weights for policy 0, policy_version 9650 (0.0008) -[2023-10-09 00:23:15,171][88326] Updated weights for policy 0, policy_version 9660 (0.0008) -[2023-10-09 00:23:17,402][88327] Updated weights for policy 1, policy_version 9670 (0.0009) -[2023-10-09 00:23:17,765][88327] Updated weights for policy 1, policy_version 9680 (0.0007) -[2023-10-09 00:23:18,130][88327] Updated weights for policy 1, policy_version 9690 (0.0008) -[2023-10-09 00:23:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 19824640. Throughput: 0: 1691.7, 1: 1678.0. Samples: 4965652. Policy #0 lag: (min: 25.0, avg: 33.4, max: 57.0) -[2023-10-09 00:23:18,975][87372] Avg episode reward: [(0, '4.790'), (1, '3.610')] -[2023-10-09 00:23:19,263][88326] Updated weights for policy 0, policy_version 9670 (0.0008) -[2023-10-09 00:23:19,631][88326] Updated weights for policy 0, policy_version 9680 (0.0007) -[2023-10-09 00:23:20,007][88326] Updated weights for policy 0, policy_version 9690 (0.0008) -[2023-10-09 00:23:22,440][88327] Updated weights for policy 1, policy_version 9700 (0.0009) -[2023-10-09 00:23:22,838][88327] Updated weights for policy 1, policy_version 9710 (0.0008) -[2023-10-09 00:23:23,201][88327] Updated weights for policy 1, policy_version 9720 (0.0008) -[2023-10-09 00:23:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 19890176. Throughput: 0: 1683.2, 1: 1702.8. Samples: 4975670. Policy #0 lag: (min: 25.0, avg: 33.4, max: 57.0) -[2023-10-09 00:23:23,975][87372] Avg episode reward: [(0, '4.710'), (1, '3.370')] -[2023-10-09 00:23:24,103][88326] Updated weights for policy 0, policy_version 9700 (0.0008) -[2023-10-09 00:23:24,483][88326] Updated weights for policy 0, policy_version 9710 (0.0007) -[2023-10-09 00:23:24,863][88326] Updated weights for policy 0, policy_version 9720 (0.0008) -[2023-10-09 00:23:27,143][88327] Updated weights for policy 1, policy_version 9730 (0.0009) -[2023-10-09 00:23:27,502][88327] Updated weights for policy 1, policy_version 9740 (0.0007) -[2023-10-09 00:23:27,864][88327] Updated weights for policy 1, policy_version 9750 (0.0007) -[2023-10-09 00:23:28,227][88327] Updated weights for policy 1, policy_version 9760 (0.0008) -[2023-10-09 00:23:28,866][88326] Updated weights for policy 0, policy_version 9730 (0.0010) -[2023-10-09 00:23:28,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 19955712. Throughput: 0: 1698.8, 1: 1693.9. Samples: 4996344. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:23:28,975][87372] Avg episode reward: [(0, '4.690'), (1, '3.500')] -[2023-10-09 00:23:29,236][88326] Updated weights for policy 0, policy_version 9740 (0.0011) -[2023-10-09 00:23:29,615][88326] Updated weights for policy 0, policy_version 9750 (0.0007) -[2023-10-09 00:23:29,975][88326] Updated weights for policy 0, policy_version 9760 (0.0007) -[2023-10-09 00:23:32,260][88327] Updated weights for policy 1, policy_version 9770 (0.0009) -[2023-10-09 00:23:32,633][88327] Updated weights for policy 1, policy_version 9780 (0.0008) -[2023-10-09 00:23:32,999][88327] Updated weights for policy 1, policy_version 9790 (0.0007) -[2023-10-09 00:23:33,921][88326] Updated weights for policy 0, policy_version 9770 (0.0007) -[2023-10-09 00:23:33,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 20021248. Throughput: 0: 1701.5, 1: 1667.2. Samples: 5016170. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:23:33,975][87372] Avg episode reward: [(0, '4.540'), (1, '3.560')] -[2023-10-09 00:23:34,288][88326] Updated weights for policy 0, policy_version 9780 (0.0009) -[2023-10-09 00:23:34,657][88326] Updated weights for policy 0, policy_version 9790 (0.0009) -[2023-10-09 00:23:37,075][88327] Updated weights for policy 1, policy_version 9800 (0.0009) -[2023-10-09 00:23:37,433][88327] Updated weights for policy 1, policy_version 9810 (0.0010) -[2023-10-09 00:23:37,806][88327] Updated weights for policy 1, policy_version 9820 (0.0009) -[2023-10-09 00:23:38,702][88326] Updated weights for policy 0, policy_version 9800 (0.0009) -[2023-10-09 00:23:38,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 20086784. Throughput: 0: 1697.3, 1: 1696.6. Samples: 5026576. Policy #0 lag: (min: 31.0, avg: 35.5, max: 63.0) -[2023-10-09 00:23:38,975][87372] Avg episode reward: [(0, '4.630'), (1, '3.580')] -[2023-10-09 00:23:39,061][88326] Updated weights for policy 0, policy_version 9810 (0.0010) -[2023-10-09 00:23:39,429][88326] Updated weights for policy 0, policy_version 9820 (0.0008) -[2023-10-09 00:23:41,835][88327] Updated weights for policy 1, policy_version 9830 (0.0010) -[2023-10-09 00:23:42,186][88327] Updated weights for policy 1, policy_version 9840 (0.0009) -[2023-10-09 00:23:42,560][88327] Updated weights for policy 1, policy_version 9850 (0.0009) -[2023-10-09 00:23:43,486][88326] Updated weights for policy 0, policy_version 9830 (0.0008) -[2023-10-09 00:23:43,854][88326] Updated weights for policy 0, policy_version 9840 (0.0008) -[2023-10-09 00:23:43,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 20152320. Throughput: 0: 1702.8, 1: 1683.6. Samples: 5046914. Policy #0 lag: (min: 31.0, avg: 35.5, max: 63.0) -[2023-10-09 00:23:43,975][87372] Avg episode reward: [(0, '5.080'), (1, '3.570')] -[2023-10-09 00:23:44,231][88326] Updated weights for policy 0, policy_version 9850 (0.0008) -[2023-10-09 00:23:44,449][88088] Saving new best policy, reward=5.080! -[2023-10-09 00:23:46,508][88327] Updated weights for policy 1, policy_version 9860 (0.0008) -[2023-10-09 00:23:46,873][88327] Updated weights for policy 1, policy_version 9870 (0.0009) -[2023-10-09 00:23:47,227][88327] Updated weights for policy 1, policy_version 9880 (0.0007) -[2023-10-09 00:23:48,469][88326] Updated weights for policy 0, policy_version 9860 (0.0007) -[2023-10-09 00:23:48,866][88326] Updated weights for policy 0, policy_version 9870 (0.0007) -[2023-10-09 00:23:48,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 20217856. Throughput: 0: 1703.5, 1: 1674.9. Samples: 5067088. Policy #0 lag: (min: 3.0, avg: 3.8, max: 23.0) -[2023-10-09 00:23:48,975][87372] Avg episode reward: [(0, '4.880'), (1, '3.700')] -[2023-10-09 00:23:49,237][88326] Updated weights for policy 0, policy_version 9880 (0.0007) -[2023-10-09 00:23:51,349][88327] Updated weights for policy 1, policy_version 9890 (0.0009) -[2023-10-09 00:23:51,721][88327] Updated weights for policy 1, policy_version 9900 (0.0009) -[2023-10-09 00:23:52,078][88327] Updated weights for policy 1, policy_version 9910 (0.0010) -[2023-10-09 00:23:52,439][88327] Updated weights for policy 1, policy_version 9920 (0.0010) -[2023-10-09 00:23:53,110][88326] Updated weights for policy 0, policy_version 9890 (0.0009) -[2023-10-09 00:23:53,475][88326] Updated weights for policy 0, policy_version 9900 (0.0008) -[2023-10-09 00:23:53,845][88326] Updated weights for policy 0, policy_version 9910 (0.0007) -[2023-10-09 00:23:53,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 20283392. Throughput: 0: 1698.2, 1: 1692.1. Samples: 5077398. Policy #0 lag: (min: 3.0, avg: 3.8, max: 23.0) -[2023-10-09 00:23:53,975][87372] Avg episode reward: [(0, '4.890'), (1, '3.750')] -[2023-10-09 00:23:54,213][88326] Updated weights for policy 0, policy_version 9920 (0.0007) -[2023-10-09 00:23:56,409][88327] Updated weights for policy 1, policy_version 9930 (0.0009) -[2023-10-09 00:23:56,773][88327] Updated weights for policy 1, policy_version 9940 (0.0009) -[2023-10-09 00:23:57,152][88327] Updated weights for policy 1, policy_version 9950 (0.0008) -[2023-10-09 00:23:58,192][88326] Updated weights for policy 0, policy_version 9930 (0.0007) -[2023-10-09 00:23:58,562][88326] Updated weights for policy 0, policy_version 9940 (0.0008) -[2023-10-09 00:23:58,933][88326] Updated weights for policy 0, policy_version 9950 (0.0010) -[2023-10-09 00:23:58,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 20348928. Throughput: 0: 1704.0, 1: 1669.1. Samples: 5097526. Policy #0 lag: (min: 24.0, avg: 50.7, max: 56.0) -[2023-10-09 00:23:58,975][87372] Avg episode reward: [(0, '4.190'), (1, '3.930')] -[2023-10-09 00:24:01,077][88327] Updated weights for policy 1, policy_version 9960 (0.0009) -[2023-10-09 00:24:01,441][88327] Updated weights for policy 1, policy_version 9970 (0.0011) -[2023-10-09 00:24:01,806][88327] Updated weights for policy 1, policy_version 9980 (0.0008) -[2023-10-09 00:24:03,006][88326] Updated weights for policy 0, policy_version 9960 (0.0007) -[2023-10-09 00:24:03,374][88326] Updated weights for policy 0, policy_version 9970 (0.0007) -[2023-10-09 00:24:03,750][88326] Updated weights for policy 0, policy_version 9980 (0.0009) -[2023-10-09 00:24:03,974][87372] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 20447232. Throughput: 0: 1690.5, 1: 1691.4. Samples: 5117838. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:24:03,975][87372] Avg episode reward: [(0, '4.340'), (1, '4.150')] -[2023-10-09 00:24:05,729][88327] Updated weights for policy 1, policy_version 9990 (0.0007) -[2023-10-09 00:24:06,111][88327] Updated weights for policy 1, policy_version 10000 (0.0009) -[2023-10-09 00:24:06,472][88327] Updated weights for policy 1, policy_version 10010 (0.0010) -[2023-10-09 00:24:07,725][88326] Updated weights for policy 0, policy_version 9990 (0.0009) -[2023-10-09 00:24:08,098][88326] Updated weights for policy 0, policy_version 10000 (0.0008) -[2023-10-09 00:24:08,466][88326] Updated weights for policy 0, policy_version 10010 (0.0007) -[2023-10-09 00:24:08,974][87372] Fps is (10 sec: 16384.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 20512768. Throughput: 0: 1704.0, 1: 1687.7. Samples: 5128296. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:24:08,974][87372] Avg episode reward: [(0, '4.530'), (1, '3.930')] -[2023-10-09 00:24:10,723][88327] Updated weights for policy 1, policy_version 10020 (0.0008) -[2023-10-09 00:24:11,087][88327] Updated weights for policy 1, policy_version 10030 (0.0009) -[2023-10-09 00:24:11,463][88327] Updated weights for policy 1, policy_version 10040 (0.0008) -[2023-10-09 00:24:12,208][88326] Updated weights for policy 0, policy_version 10020 (0.0008) -[2023-10-09 00:24:12,591][88326] Updated weights for policy 0, policy_version 10030 (0.0010) -[2023-10-09 00:24:12,960][88326] Updated weights for policy 0, policy_version 10040 (0.0011) -[2023-10-09 00:24:13,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 20578304. Throughput: 0: 1703.7, 1: 1673.7. Samples: 5148330. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:24:13,975][87372] Avg episode reward: [(0, '4.280'), (1, '4.280')] -[2023-10-09 00:24:15,527][88327] Updated weights for policy 1, policy_version 10050 (0.0010) -[2023-10-09 00:24:15,928][88327] Updated weights for policy 1, policy_version 10060 (0.0009) -[2023-10-09 00:24:16,297][88327] Updated weights for policy 1, policy_version 10070 (0.0009) -[2023-10-09 00:24:16,653][88327] Updated weights for policy 1, policy_version 10080 (0.0010) -[2023-10-09 00:24:17,023][88326] Updated weights for policy 0, policy_version 10050 (0.0008) -[2023-10-09 00:24:17,398][88326] Updated weights for policy 0, policy_version 10060 (0.0009) -[2023-10-09 00:24:17,782][88326] Updated weights for policy 0, policy_version 10070 (0.0008) -[2023-10-09 00:24:18,153][88326] Updated weights for policy 0, policy_version 10080 (0.0009) -[2023-10-09 00:24:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 20643840. Throughput: 0: 1677.2, 1: 1702.3. Samples: 5168244. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:24:18,974][87372] Avg episode reward: [(0, '4.590'), (1, '4.050')] -[2023-10-09 00:24:20,683][88327] Updated weights for policy 1, policy_version 10090 (0.0009) -[2023-10-09 00:24:21,044][88327] Updated weights for policy 1, policy_version 10100 (0.0008) -[2023-10-09 00:24:21,420][88327] Updated weights for policy 1, policy_version 10110 (0.0009) -[2023-10-09 00:24:22,047][88326] Updated weights for policy 0, policy_version 10090 (0.0009) -[2023-10-09 00:24:22,410][88326] Updated weights for policy 0, policy_version 10100 (0.0010) -[2023-10-09 00:24:22,784][88326] Updated weights for policy 0, policy_version 10110 (0.0010) -[2023-10-09 00:24:23,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 20709376. Throughput: 0: 1711.9, 1: 1683.5. Samples: 5179372. Policy #0 lag: (min: 31.0, avg: 32.1, max: 53.0) -[2023-10-09 00:24:23,975][87372] Avg episode reward: [(0, '4.550'), (1, '4.150')] -[2023-10-09 00:24:25,468][88327] Updated weights for policy 1, policy_version 10120 (0.0010) -[2023-10-09 00:24:25,833][88327] Updated weights for policy 1, policy_version 10130 (0.0008) -[2023-10-09 00:24:26,200][88327] Updated weights for policy 1, policy_version 10140 (0.0009) -[2023-10-09 00:24:26,706][88326] Updated weights for policy 0, policy_version 10120 (0.0008) -[2023-10-09 00:24:27,074][88326] Updated weights for policy 0, policy_version 10130 (0.0007) -[2023-10-09 00:24:27,443][88326] Updated weights for policy 0, policy_version 10140 (0.0007) -[2023-10-09 00:24:28,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 20774912. Throughput: 0: 1691.3, 1: 1689.7. Samples: 5199062. Policy #0 lag: (min: 31.0, avg: 32.1, max: 53.0) -[2023-10-09 00:24:28,975][87372] Avg episode reward: [(0, '4.520'), (1, '3.750')] -[2023-10-09 00:24:30,108][88327] Updated weights for policy 1, policy_version 10150 (0.0007) -[2023-10-09 00:24:30,478][88327] Updated weights for policy 1, policy_version 10160 (0.0010) -[2023-10-09 00:24:30,841][88327] Updated weights for policy 1, policy_version 10170 (0.0007) -[2023-10-09 00:24:31,494][88326] Updated weights for policy 0, policy_version 10150 (0.0009) -[2023-10-09 00:24:31,860][88326] Updated weights for policy 0, policy_version 10160 (0.0010) -[2023-10-09 00:24:32,228][88326] Updated weights for policy 0, policy_version 10170 (0.0010) -[2023-10-09 00:24:33,974][87372] Fps is (10 sec: 13107.6, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 20840448. Throughput: 0: 1682.3, 1: 1708.5. Samples: 5219674. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:24:33,974][87372] Avg episode reward: [(0, '4.830'), (1, '3.970')] -[2023-10-09 00:24:33,983][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000010176_10420224.pth... -[2023-10-09 00:24:33,983][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000010176_10420224.pth... -[2023-10-09 00:24:34,020][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000008608_8814592.pth -[2023-10-09 00:24:34,023][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000008576_8781824.pth -[2023-10-09 00:24:34,802][88327] Updated weights for policy 1, policy_version 10180 (0.0009) -[2023-10-09 00:24:35,163][88327] Updated weights for policy 1, policy_version 10190 (0.0009) -[2023-10-09 00:24:35,533][88327] Updated weights for policy 1, policy_version 10200 (0.0007) -[2023-10-09 00:24:36,254][88326] Updated weights for policy 0, policy_version 10180 (0.0009) -[2023-10-09 00:24:36,633][88326] Updated weights for policy 0, policy_version 10190 (0.0007) -[2023-10-09 00:24:36,993][88326] Updated weights for policy 0, policy_version 10200 (0.0007) -[2023-10-09 00:24:38,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 20905984. Throughput: 0: 1714.8, 1: 1679.1. Samples: 5230120. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:24:38,975][87372] Avg episode reward: [(0, '4.570'), (1, '3.880')] -[2023-10-09 00:24:39,645][88327] Updated weights for policy 1, policy_version 10210 (0.0008) -[2023-10-09 00:24:40,012][88327] Updated weights for policy 1, policy_version 10220 (0.0007) -[2023-10-09 00:24:40,373][88327] Updated weights for policy 1, policy_version 10230 (0.0007) -[2023-10-09 00:24:40,737][88327] Updated weights for policy 1, policy_version 10240 (0.0009) -[2023-10-09 00:24:40,877][88326] Updated weights for policy 0, policy_version 10210 (0.0007) -[2023-10-09 00:24:41,255][88326] Updated weights for policy 0, policy_version 10220 (0.0007) -[2023-10-09 00:24:41,625][88326] Updated weights for policy 0, policy_version 10230 (0.0007) -[2023-10-09 00:24:41,989][88326] Updated weights for policy 0, policy_version 10240 (0.0007) -[2023-10-09 00:24:43,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 20971520. Throughput: 0: 1685.6, 1: 1704.0. Samples: 5250056. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-09 00:24:43,975][87372] Avg episode reward: [(0, '4.710'), (1, '4.160')] -[2023-10-09 00:24:44,736][88327] Updated weights for policy 1, policy_version 10250 (0.0007) -[2023-10-09 00:24:45,106][88327] Updated weights for policy 1, policy_version 10260 (0.0008) -[2023-10-09 00:24:45,472][88327] Updated weights for policy 1, policy_version 10270 (0.0010) -[2023-10-09 00:24:45,977][88326] Updated weights for policy 0, policy_version 10250 (0.0007) -[2023-10-09 00:24:46,353][88326] Updated weights for policy 0, policy_version 10260 (0.0010) -[2023-10-09 00:24:46,725][88326] Updated weights for policy 0, policy_version 10270 (0.0010) -[2023-10-09 00:24:48,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 21037056. Throughput: 0: 1696.7, 1: 1700.5. Samples: 5270714. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-09 00:24:48,975][87372] Avg episode reward: [(0, '4.840'), (1, '4.200')] -[2023-10-09 00:24:49,672][88327] Updated weights for policy 1, policy_version 10280 (0.0009) -[2023-10-09 00:24:50,043][88327] Updated weights for policy 1, policy_version 10290 (0.0008) -[2023-10-09 00:24:50,404][88327] Updated weights for policy 1, policy_version 10300 (0.0009) -[2023-10-09 00:24:50,939][88326] Updated weights for policy 0, policy_version 10280 (0.0010) -[2023-10-09 00:24:51,323][88326] Updated weights for policy 0, policy_version 10290 (0.0009) -[2023-10-09 00:24:51,691][88326] Updated weights for policy 0, policy_version 10300 (0.0007) -[2023-10-09 00:24:53,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 21102592. Throughput: 0: 1700.0, 1: 1680.8. Samples: 5280434. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-09 00:24:53,975][87372] Avg episode reward: [(0, '4.800'), (1, '4.170')] -[2023-10-09 00:24:54,507][88327] Updated weights for policy 1, policy_version 10310 (0.0010) -[2023-10-09 00:24:54,871][88327] Updated weights for policy 1, policy_version 10320 (0.0009) -[2023-10-09 00:24:55,249][88327] Updated weights for policy 1, policy_version 10330 (0.0009) -[2023-10-09 00:24:55,645][88326] Updated weights for policy 0, policy_version 10310 (0.0007) -[2023-10-09 00:24:56,024][88326] Updated weights for policy 0, policy_version 10320 (0.0009) -[2023-10-09 00:24:56,390][88326] Updated weights for policy 0, policy_version 10330 (0.0008) -[2023-10-09 00:24:58,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 21168128. Throughput: 0: 1685.0, 1: 1705.1. Samples: 5300882. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-09 00:24:58,975][87372] Avg episode reward: [(0, '5.230'), (1, '4.440')] -[2023-10-09 00:24:58,975][88088] Saving new best policy, reward=5.230! -[2023-10-09 00:24:59,176][88327] Updated weights for policy 1, policy_version 10340 (0.0008) -[2023-10-09 00:24:59,539][88327] Updated weights for policy 1, policy_version 10350 (0.0008) -[2023-10-09 00:24:59,918][88327] Updated weights for policy 1, policy_version 10360 (0.0008) -[2023-10-09 00:25:00,204][88168] Saving new best policy, reward=4.440! -[2023-10-09 00:25:00,310][88326] Updated weights for policy 0, policy_version 10340 (0.0009) -[2023-10-09 00:25:00,688][88326] Updated weights for policy 0, policy_version 10350 (0.0009) -[2023-10-09 00:25:01,062][88326] Updated weights for policy 0, policy_version 10360 (0.0009) -[2023-10-09 00:25:03,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 21233664. Throughput: 0: 1715.4, 1: 1701.4. Samples: 5322002. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-09 00:25:03,974][87372] Avg episode reward: [(0, '5.260'), (1, '4.110')] -[2023-10-09 00:25:03,981][88088] Saving new best policy, reward=5.260! -[2023-10-09 00:25:04,016][88327] Updated weights for policy 1, policy_version 10370 (0.0008) -[2023-10-09 00:25:04,435][88327] Updated weights for policy 1, policy_version 10380 (0.0007) -[2023-10-09 00:25:04,806][88327] Updated weights for policy 1, policy_version 10390 (0.0008) -[2023-10-09 00:25:05,000][88326] Updated weights for policy 0, policy_version 10370 (0.0007) -[2023-10-09 00:25:05,168][88327] Updated weights for policy 1, policy_version 10400 (0.0007) -[2023-10-09 00:25:05,373][88326] Updated weights for policy 0, policy_version 10380 (0.0007) -[2023-10-09 00:25:05,738][88326] Updated weights for policy 0, policy_version 10390 (0.0007) -[2023-10-09 00:25:06,108][88326] Updated weights for policy 0, policy_version 10400 (0.0007) -[2023-10-09 00:25:08,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 21299200. Throughput: 0: 1684.1, 1: 1688.1. Samples: 5331124. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-09 00:25:08,975][87372] Avg episode reward: [(0, '4.580'), (1, '4.300')] -[2023-10-09 00:25:09,178][88327] Updated weights for policy 1, policy_version 10410 (0.0010) -[2023-10-09 00:25:09,539][88327] Updated weights for policy 1, policy_version 10420 (0.0008) -[2023-10-09 00:25:09,905][88327] Updated weights for policy 1, policy_version 10430 (0.0008) -[2023-10-09 00:25:10,278][88326] Updated weights for policy 0, policy_version 10410 (0.0008) -[2023-10-09 00:25:10,648][88326] Updated weights for policy 0, policy_version 10420 (0.0008) -[2023-10-09 00:25:11,009][88326] Updated weights for policy 0, policy_version 10430 (0.0007) -[2023-10-09 00:25:13,831][88327] Updated weights for policy 1, policy_version 10440 (0.0010) -[2023-10-09 00:25:13,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 21364736. Throughput: 0: 1700.5, 1: 1700.6. Samples: 5352110. Policy #0 lag: (min: 31.0, avg: 35.5, max: 63.0) -[2023-10-09 00:25:13,975][87372] Avg episode reward: [(0, '4.780'), (1, '4.130')] -[2023-10-09 00:25:14,200][88327] Updated weights for policy 1, policy_version 10450 (0.0007) -[2023-10-09 00:25:14,570][88327] Updated weights for policy 1, policy_version 10460 (0.0009) -[2023-10-09 00:25:15,011][88326] Updated weights for policy 0, policy_version 10440 (0.0009) -[2023-10-09 00:25:15,374][88326] Updated weights for policy 0, policy_version 10450 (0.0009) -[2023-10-09 00:25:15,750][88326] Updated weights for policy 0, policy_version 10460 (0.0009) -[2023-10-09 00:25:18,539][88327] Updated weights for policy 1, policy_version 10470 (0.0007) -[2023-10-09 00:25:18,906][88327] Updated weights for policy 1, policy_version 10480 (0.0008) -[2023-10-09 00:25:18,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 21430272. Throughput: 0: 1714.8, 1: 1695.6. Samples: 5373144. Policy #0 lag: (min: 31.0, avg: 35.5, max: 63.0) -[2023-10-09 00:25:18,975][87372] Avg episode reward: [(0, '4.260'), (1, '3.910')] -[2023-10-09 00:25:19,287][88327] Updated weights for policy 1, policy_version 10490 (0.0010) -[2023-10-09 00:25:19,840][88326] Updated weights for policy 0, policy_version 10470 (0.0007) -[2023-10-09 00:25:20,213][88326] Updated weights for policy 0, policy_version 10480 (0.0009) -[2023-10-09 00:25:20,577][88326] Updated weights for policy 0, policy_version 10490 (0.0008) -[2023-10-09 00:25:23,290][88327] Updated weights for policy 1, policy_version 10500 (0.0009) -[2023-10-09 00:25:23,653][88327] Updated weights for policy 1, policy_version 10510 (0.0008) -[2023-10-09 00:25:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 21495808. Throughput: 0: 1686.3, 1: 1695.0. Samples: 5382282. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-09 00:25:23,975][87372] Avg episode reward: [(0, '4.400'), (1, '3.850')] -[2023-10-09 00:25:24,012][88327] Updated weights for policy 1, policy_version 10520 (0.0008) -[2023-10-09 00:25:24,611][88326] Updated weights for policy 0, policy_version 10500 (0.0008) -[2023-10-09 00:25:24,999][88326] Updated weights for policy 0, policy_version 10510 (0.0010) -[2023-10-09 00:25:25,379][88326] Updated weights for policy 0, policy_version 10520 (0.0009) -[2023-10-09 00:25:27,886][88327] Updated weights for policy 1, policy_version 10530 (0.0008) -[2023-10-09 00:25:28,256][88327] Updated weights for policy 1, policy_version 10540 (0.0008) -[2023-10-09 00:25:28,618][88327] Updated weights for policy 1, policy_version 10550 (0.0008) -[2023-10-09 00:25:28,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 21561344. Throughput: 0: 1704.3, 1: 1700.5. Samples: 5403270. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-09 00:25:28,975][87372] Avg episode reward: [(0, '4.870'), (1, '3.910')] -[2023-10-09 00:25:28,992][88327] Updated weights for policy 1, policy_version 10560 (0.0009) -[2023-10-09 00:25:29,599][88326] Updated weights for policy 0, policy_version 10530 (0.0010) -[2023-10-09 00:25:29,976][88326] Updated weights for policy 0, policy_version 10540 (0.0009) -[2023-10-09 00:25:30,346][88326] Updated weights for policy 0, policy_version 10550 (0.0010) -[2023-10-09 00:25:30,707][88326] Updated weights for policy 0, policy_version 10560 (0.0009) -[2023-10-09 00:25:33,017][88327] Updated weights for policy 1, policy_version 10570 (0.0007) -[2023-10-09 00:25:33,396][88327] Updated weights for policy 1, policy_version 10580 (0.0009) -[2023-10-09 00:25:33,762][88327] Updated weights for policy 1, policy_version 10590 (0.0008) -[2023-10-09 00:25:33,974][87372] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 21659648. Throughput: 0: 1703.6, 1: 1693.6. Samples: 5423590. Policy #0 lag: (min: 25.0, avg: 36.9, max: 57.0) -[2023-10-09 00:25:33,975][87372] Avg episode reward: [(0, '4.460'), (1, '3.820')] -[2023-10-09 00:25:34,670][88326] Updated weights for policy 0, policy_version 10570 (0.0009) -[2023-10-09 00:25:35,050][88326] Updated weights for policy 0, policy_version 10580 (0.0008) -[2023-10-09 00:25:35,424][88326] Updated weights for policy 0, policy_version 10590 (0.0007) -[2023-10-09 00:25:37,710][88327] Updated weights for policy 1, policy_version 10600 (0.0007) -[2023-10-09 00:25:38,078][88327] Updated weights for policy 1, policy_version 10610 (0.0008) -[2023-10-09 00:25:38,438][88327] Updated weights for policy 1, policy_version 10620 (0.0009) -[2023-10-09 00:25:38,974][87372] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 21725184. Throughput: 0: 1688.0, 1: 1709.7. Samples: 5433332. Policy #0 lag: (min: 25.0, avg: 36.9, max: 57.0) -[2023-10-09 00:25:38,975][87372] Avg episode reward: [(0, '4.720'), (1, '4.040')] -[2023-10-09 00:25:39,125][88326] Updated weights for policy 0, policy_version 10600 (0.0009) -[2023-10-09 00:25:39,491][88326] Updated weights for policy 0, policy_version 10610 (0.0009) -[2023-10-09 00:25:39,859][88326] Updated weights for policy 0, policy_version 10620 (0.0007) -[2023-10-09 00:25:42,647][88327] Updated weights for policy 1, policy_version 10630 (0.0008) -[2023-10-09 00:25:43,013][88327] Updated weights for policy 1, policy_version 10640 (0.0008) -[2023-10-09 00:25:43,391][88327] Updated weights for policy 1, policy_version 10650 (0.0008) -[2023-10-09 00:25:43,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 21790720. Throughput: 0: 1701.5, 1: 1704.5. Samples: 5454152. Policy #0 lag: (min: 30.0, avg: 35.7, max: 62.0) -[2023-10-09 00:25:43,975][87372] Avg episode reward: [(0, '4.540'), (1, '4.120')] -[2023-10-09 00:25:44,056][88326] Updated weights for policy 0, policy_version 10630 (0.0010) -[2023-10-09 00:25:44,421][88326] Updated weights for policy 0, policy_version 10640 (0.0009) -[2023-10-09 00:25:44,791][88326] Updated weights for policy 0, policy_version 10650 (0.0009) -[2023-10-09 00:25:47,584][88327] Updated weights for policy 1, policy_version 10660 (0.0007) -[2023-10-09 00:25:47,955][88327] Updated weights for policy 1, policy_version 10670 (0.0008) -[2023-10-09 00:25:48,323][88327] Updated weights for policy 1, policy_version 10680 (0.0007) -[2023-10-09 00:25:48,915][88326] Updated weights for policy 0, policy_version 10660 (0.0009) -[2023-10-09 00:25:48,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 21856256. Throughput: 0: 1696.8, 1: 1690.6. Samples: 5474438. Policy #0 lag: (min: 30.0, avg: 35.7, max: 62.0) -[2023-10-09 00:25:48,975][87372] Avg episode reward: [(0, '4.730'), (1, '4.250')] -[2023-10-09 00:25:49,274][88326] Updated weights for policy 0, policy_version 10670 (0.0008) -[2023-10-09 00:25:49,645][88326] Updated weights for policy 0, policy_version 10680 (0.0007) -[2023-10-09 00:25:52,428][88327] Updated weights for policy 1, policy_version 10690 (0.0008) -[2023-10-09 00:25:52,840][88327] Updated weights for policy 1, policy_version 10700 (0.0009) -[2023-10-09 00:25:53,219][88327] Updated weights for policy 1, policy_version 10710 (0.0010) -[2023-10-09 00:25:53,580][88327] Updated weights for policy 1, policy_version 10720 (0.0011) -[2023-10-09 00:25:53,756][88326] Updated weights for policy 0, policy_version 10690 (0.0007) -[2023-10-09 00:25:53,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 21921792. Throughput: 0: 1691.7, 1: 1709.2. Samples: 5484166. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-09 00:25:53,975][87372] Avg episode reward: [(0, '4.620'), (1, '4.500')] -[2023-10-09 00:25:53,975][88168] Saving new best policy, reward=4.500! -[2023-10-09 00:25:54,130][88326] Updated weights for policy 0, policy_version 10700 (0.0007) -[2023-10-09 00:25:54,500][88326] Updated weights for policy 0, policy_version 10710 (0.0009) -[2023-10-09 00:25:54,866][88326] Updated weights for policy 0, policy_version 10720 (0.0009) -[2023-10-09 00:25:57,559][88327] Updated weights for policy 1, policy_version 10730 (0.0008) -[2023-10-09 00:25:57,924][88327] Updated weights for policy 1, policy_version 10740 (0.0007) -[2023-10-09 00:25:58,293][88327] Updated weights for policy 1, policy_version 10750 (0.0008) -[2023-10-09 00:25:58,731][88326] Updated weights for policy 0, policy_version 10730 (0.0007) -[2023-10-09 00:25:58,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 21987328. Throughput: 0: 1697.8, 1: 1699.6. Samples: 5504994. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-09 00:25:58,975][87372] Avg episode reward: [(0, '4.790'), (1, '4.210')] -[2023-10-09 00:25:59,110][88326] Updated weights for policy 0, policy_version 10740 (0.0009) -[2023-10-09 00:25:59,492][88326] Updated weights for policy 0, policy_version 10750 (0.0008) -[2023-10-09 00:26:02,380][88327] Updated weights for policy 1, policy_version 10760 (0.0011) -[2023-10-09 00:26:02,751][88327] Updated weights for policy 1, policy_version 10770 (0.0010) -[2023-10-09 00:26:03,110][88327] Updated weights for policy 1, policy_version 10780 (0.0009) -[2023-10-09 00:26:03,259][88326] Updated weights for policy 0, policy_version 10760 (0.0007) -[2023-10-09 00:26:03,624][88326] Updated weights for policy 0, policy_version 10770 (0.0007) -[2023-10-09 00:26:03,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 22052864. Throughput: 0: 1695.2, 1: 1673.4. Samples: 5524730. Policy #0 lag: (min: 2.0, avg: 2.1, max: 7.0) -[2023-10-09 00:26:03,975][87372] Avg episode reward: [(0, '4.830'), (1, '3.650')] -[2023-10-09 00:26:03,999][88326] Updated weights for policy 0, policy_version 10780 (0.0007) -[2023-10-09 00:26:07,088][88327] Updated weights for policy 1, policy_version 10790 (0.0008) -[2023-10-09 00:26:07,456][88327] Updated weights for policy 1, policy_version 10800 (0.0008) -[2023-10-09 00:26:07,818][88327] Updated weights for policy 1, policy_version 10810 (0.0008) -[2023-10-09 00:26:08,137][88326] Updated weights for policy 0, policy_version 10790 (0.0007) -[2023-10-09 00:26:08,510][88326] Updated weights for policy 0, policy_version 10800 (0.0010) -[2023-10-09 00:26:08,875][88326] Updated weights for policy 0, policy_version 10810 (0.0008) -[2023-10-09 00:26:08,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 22118400. Throughput: 0: 1702.2, 1: 1701.1. Samples: 5535432. Policy #0 lag: (min: 2.0, avg: 2.1, max: 7.0) -[2023-10-09 00:26:08,976][87372] Avg episode reward: [(0, '4.710'), (1, '3.750')] -[2023-10-09 00:26:11,828][88327] Updated weights for policy 1, policy_version 10820 (0.0009) -[2023-10-09 00:26:12,201][88327] Updated weights for policy 1, policy_version 10830 (0.0010) -[2023-10-09 00:26:12,565][88327] Updated weights for policy 1, policy_version 10840 (0.0007) -[2023-10-09 00:26:12,978][88326] Updated weights for policy 0, policy_version 10820 (0.0007) -[2023-10-09 00:26:13,364][88326] Updated weights for policy 0, policy_version 10830 (0.0008) -[2023-10-09 00:26:13,740][88326] Updated weights for policy 0, policy_version 10840 (0.0009) -[2023-10-09 00:26:13,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 22183936. Throughput: 0: 1700.7, 1: 1682.7. Samples: 5555524. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 00:26:13,974][87372] Avg episode reward: [(0, '4.750'), (1, '3.990')] -[2023-10-09 00:26:16,442][88327] Updated weights for policy 1, policy_version 10850 (0.0008) -[2023-10-09 00:26:16,806][88327] Updated weights for policy 1, policy_version 10860 (0.0008) -[2023-10-09 00:26:17,166][88327] Updated weights for policy 1, policy_version 10870 (0.0007) -[2023-10-09 00:26:17,532][88327] Updated weights for policy 1, policy_version 10880 (0.0007) -[2023-10-09 00:26:17,595][88326] Updated weights for policy 0, policy_version 10850 (0.0008) -[2023-10-09 00:26:17,961][88326] Updated weights for policy 0, policy_version 10860 (0.0007) -[2023-10-09 00:26:18,333][88326] Updated weights for policy 0, policy_version 10870 (0.0008) -[2023-10-09 00:26:18,701][88326] Updated weights for policy 0, policy_version 10880 (0.0008) -[2023-10-09 00:26:18,974][87372] Fps is (10 sec: 16384.1, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 22282240. Throughput: 0: 1692.0, 1: 1676.3. Samples: 5575162. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:26:18,975][87372] Avg episode reward: [(0, '4.580'), (1, '3.960')] -[2023-10-09 00:26:21,591][88327] Updated weights for policy 1, policy_version 10890 (0.0008) -[2023-10-09 00:26:21,955][88327] Updated weights for policy 1, policy_version 10900 (0.0007) -[2023-10-09 00:26:22,319][88327] Updated weights for policy 1, policy_version 10910 (0.0008) -[2023-10-09 00:26:22,812][88326] Updated weights for policy 0, policy_version 10890 (0.0009) -[2023-10-09 00:26:23,186][88326] Updated weights for policy 0, policy_version 10900 (0.0008) -[2023-10-09 00:26:23,552][88326] Updated weights for policy 0, policy_version 10910 (0.0007) -[2023-10-09 00:26:23,974][87372] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 22347776. Throughput: 0: 1703.3, 1: 1689.4. Samples: 5586004. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:26:23,975][87372] Avg episode reward: [(0, '4.300'), (1, '4.260')] -[2023-10-09 00:26:26,318][88327] Updated weights for policy 1, policy_version 10920 (0.0008) -[2023-10-09 00:26:26,691][88327] Updated weights for policy 1, policy_version 10930 (0.0008) -[2023-10-09 00:26:27,052][88327] Updated weights for policy 1, policy_version 10940 (0.0008) -[2023-10-09 00:26:27,702][88326] Updated weights for policy 0, policy_version 10920 (0.0007) -[2023-10-09 00:26:28,084][88326] Updated weights for policy 0, policy_version 10930 (0.0010) -[2023-10-09 00:26:28,453][88326] Updated weights for policy 0, policy_version 10940 (0.0007) -[2023-10-09 00:26:28,974][87372] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 22413312. Throughput: 0: 1704.4, 1: 1671.2. Samples: 5606056. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) -[2023-10-09 00:26:28,974][87372] Avg episode reward: [(0, '4.370'), (1, '4.080')] -[2023-10-09 00:26:31,172][88327] Updated weights for policy 1, policy_version 10950 (0.0007) -[2023-10-09 00:26:31,540][88327] Updated weights for policy 1, policy_version 10960 (0.0007) -[2023-10-09 00:26:31,905][88327] Updated weights for policy 1, policy_version 10970 (0.0008) -[2023-10-09 00:26:32,495][88326] Updated weights for policy 0, policy_version 10950 (0.0007) -[2023-10-09 00:26:32,870][88326] Updated weights for policy 0, policy_version 10960 (0.0008) -[2023-10-09 00:26:33,254][88326] Updated weights for policy 0, policy_version 10970 (0.0009) -[2023-10-09 00:26:33,975][87372] Fps is (10 sec: 13106.6, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 22478848. Throughput: 0: 1682.8, 1: 1681.4. Samples: 5625830. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) -[2023-10-09 00:26:33,976][87372] Avg episode reward: [(0, '4.590'), (1, '3.990')] -[2023-10-09 00:26:33,986][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000010976_11239424.pth... -[2023-10-09 00:26:33,987][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000010976_11239424.pth... -[2023-10-09 00:26:34,022][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000009408_9633792.pth -[2023-10-09 00:26:34,026][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000009376_9601024.pth -[2023-10-09 00:26:36,043][88327] Updated weights for policy 1, policy_version 10980 (0.0007) -[2023-10-09 00:26:36,422][88327] Updated weights for policy 1, policy_version 10990 (0.0009) -[2023-10-09 00:26:36,791][88327] Updated weights for policy 1, policy_version 11000 (0.0008) -[2023-10-09 00:26:37,140][88326] Updated weights for policy 0, policy_version 10980 (0.0009) -[2023-10-09 00:26:37,509][88326] Updated weights for policy 0, policy_version 10990 (0.0007) -[2023-10-09 00:26:37,884][88326] Updated weights for policy 0, policy_version 11000 (0.0007) -[2023-10-09 00:26:38,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 22544384. Throughput: 0: 1706.9, 1: 1689.2. Samples: 5636992. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:26:38,975][87372] Avg episode reward: [(0, '4.570'), (1, '4.110')] -[2023-10-09 00:26:40,863][88327] Updated weights for policy 1, policy_version 11010 (0.0009) -[2023-10-09 00:26:41,231][88327] Updated weights for policy 1, policy_version 11020 (0.0007) -[2023-10-09 00:26:41,595][88327] Updated weights for policy 1, policy_version 11030 (0.0008) -[2023-10-09 00:26:41,961][88327] Updated weights for policy 1, policy_version 11040 (0.0009) -[2023-10-09 00:26:41,996][88326] Updated weights for policy 0, policy_version 11010 (0.0008) -[2023-10-09 00:26:42,355][88326] Updated weights for policy 0, policy_version 11020 (0.0009) -[2023-10-09 00:26:42,726][88326] Updated weights for policy 0, policy_version 11030 (0.0007) -[2023-10-09 00:26:43,099][88326] Updated weights for policy 0, policy_version 11040 (0.0007) -[2023-10-09 00:26:43,974][87372] Fps is (10 sec: 13107.9, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 22609920. Throughput: 0: 1694.0, 1: 1672.5. Samples: 5656488. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:26:43,975][87372] Avg episode reward: [(0, '4.940'), (1, '3.750')] -[2023-10-09 00:26:46,169][88327] Updated weights for policy 1, policy_version 11050 (0.0007) -[2023-10-09 00:26:46,534][88327] Updated weights for policy 1, policy_version 11060 (0.0007) -[2023-10-09 00:26:46,904][88327] Updated weights for policy 1, policy_version 11070 (0.0009) -[2023-10-09 00:26:47,070][88326] Updated weights for policy 0, policy_version 11050 (0.0007) -[2023-10-09 00:26:47,433][88326] Updated weights for policy 0, policy_version 11060 (0.0007) -[2023-10-09 00:26:47,800][88326] Updated weights for policy 0, policy_version 11070 (0.0009) -[2023-10-09 00:26:48,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 22675456. Throughput: 0: 1671.2, 1: 1695.6. Samples: 5676240. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:26:48,975][87372] Avg episode reward: [(0, '4.900'), (1, '3.810')] -[2023-10-09 00:26:50,903][88327] Updated weights for policy 1, policy_version 11080 (0.0008) -[2023-10-09 00:26:51,272][88327] Updated weights for policy 1, policy_version 11090 (0.0008) -[2023-10-09 00:26:51,631][88327] Updated weights for policy 1, policy_version 11100 (0.0008) -[2023-10-09 00:26:51,854][88326] Updated weights for policy 0, policy_version 11080 (0.0007) -[2023-10-09 00:26:52,226][88326] Updated weights for policy 0, policy_version 11090 (0.0008) -[2023-10-09 00:26:52,590][88326] Updated weights for policy 0, policy_version 11100 (0.0009) -[2023-10-09 00:26:53,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 22740992. Throughput: 0: 1693.8, 1: 1683.2. Samples: 5687396. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:26:53,975][87372] Avg episode reward: [(0, '4.540'), (1, '3.930')] -[2023-10-09 00:26:55,556][88327] Updated weights for policy 1, policy_version 11110 (0.0009) -[2023-10-09 00:26:55,931][88327] Updated weights for policy 1, policy_version 11120 (0.0009) -[2023-10-09 00:26:56,298][88327] Updated weights for policy 1, policy_version 11130 (0.0007) -[2023-10-09 00:26:56,725][88326] Updated weights for policy 0, policy_version 11110 (0.0009) -[2023-10-09 00:26:57,095][88326] Updated weights for policy 0, policy_version 11120 (0.0010) -[2023-10-09 00:26:57,461][88326] Updated weights for policy 0, policy_version 11130 (0.0007) -[2023-10-09 00:26:58,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 22806528. Throughput: 0: 1679.6, 1: 1681.2. Samples: 5706762. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:26:58,975][87372] Avg episode reward: [(0, '4.850'), (1, '3.670')] -[2023-10-09 00:27:00,304][88327] Updated weights for policy 1, policy_version 11140 (0.0007) -[2023-10-09 00:27:00,668][88327] Updated weights for policy 1, policy_version 11150 (0.0009) -[2023-10-09 00:27:01,038][88327] Updated weights for policy 1, policy_version 11160 (0.0009) -[2023-10-09 00:27:01,394][88326] Updated weights for policy 0, policy_version 11140 (0.0009) -[2023-10-09 00:27:01,766][88326] Updated weights for policy 0, policy_version 11150 (0.0009) -[2023-10-09 00:27:02,130][88326] Updated weights for policy 0, policy_version 11160 (0.0007) -[2023-10-09 00:27:03,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 22872064. Throughput: 0: 1680.2, 1: 1702.7. Samples: 5727394. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:27:03,975][87372] Avg episode reward: [(0, '4.390'), (1, '4.100')] -[2023-10-09 00:27:04,910][88327] Updated weights for policy 1, policy_version 11170 (0.0008) -[2023-10-09 00:27:05,275][88327] Updated weights for policy 1, policy_version 11180 (0.0008) -[2023-10-09 00:27:05,645][88327] Updated weights for policy 1, policy_version 11190 (0.0008) -[2023-10-09 00:27:06,003][88327] Updated weights for policy 1, policy_version 11200 (0.0010) -[2023-10-09 00:27:06,275][88326] Updated weights for policy 0, policy_version 11170 (0.0008) -[2023-10-09 00:27:06,651][88326] Updated weights for policy 0, policy_version 11180 (0.0009) -[2023-10-09 00:27:07,037][88326] Updated weights for policy 0, policy_version 11190 (0.0009) -[2023-10-09 00:27:07,409][88326] Updated weights for policy 0, policy_version 11200 (0.0009) -[2023-10-09 00:27:08,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 22937600. Throughput: 0: 1696.0, 1: 1674.3. Samples: 5737666. Policy #0 lag: (min: 10.0, avg: 10.3, max: 21.0) -[2023-10-09 00:27:08,975][87372] Avg episode reward: [(0, '4.750'), (1, '4.200')] -[2023-10-09 00:27:09,976][88327] Updated weights for policy 1, policy_version 11210 (0.0011) -[2023-10-09 00:27:10,338][88327] Updated weights for policy 1, policy_version 11220 (0.0009) -[2023-10-09 00:27:10,715][88327] Updated weights for policy 1, policy_version 11230 (0.0008) -[2023-10-09 00:27:11,423][88326] Updated weights for policy 0, policy_version 11210 (0.0012) -[2023-10-09 00:27:11,790][88326] Updated weights for policy 0, policy_version 11220 (0.0010) -[2023-10-09 00:27:12,166][88326] Updated weights for policy 0, policy_version 11230 (0.0008) -[2023-10-09 00:27:13,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 23003136. Throughput: 0: 1664.8, 1: 1693.5. Samples: 5757182. Policy #0 lag: (min: 10.0, avg: 10.3, max: 21.0) -[2023-10-09 00:27:13,975][87372] Avg episode reward: [(0, '4.640'), (1, '4.150')] -[2023-10-09 00:27:14,905][88327] Updated weights for policy 1, policy_version 11240 (0.0011) -[2023-10-09 00:27:15,268][88327] Updated weights for policy 1, policy_version 11250 (0.0009) -[2023-10-09 00:27:15,639][88327] Updated weights for policy 1, policy_version 11260 (0.0009) -[2023-10-09 00:27:16,360][88326] Updated weights for policy 0, policy_version 11240 (0.0008) -[2023-10-09 00:27:16,726][88326] Updated weights for policy 0, policy_version 11250 (0.0008) -[2023-10-09 00:27:17,099][88326] Updated weights for policy 0, policy_version 11260 (0.0007) -[2023-10-09 00:27:18,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 23068672. Throughput: 0: 1684.1, 1: 1697.9. Samples: 5778016. Policy #0 lag: (min: 28.0, avg: 37.0, max: 60.0) -[2023-10-09 00:27:18,975][87372] Avg episode reward: [(0, '4.980'), (1, '4.390')] -[2023-10-09 00:27:19,647][88327] Updated weights for policy 1, policy_version 11270 (0.0007) -[2023-10-09 00:27:20,010][88327] Updated weights for policy 1, policy_version 11280 (0.0008) -[2023-10-09 00:27:20,377][88327] Updated weights for policy 1, policy_version 11290 (0.0007) -[2023-10-09 00:27:20,930][88326] Updated weights for policy 0, policy_version 11270 (0.0009) -[2023-10-09 00:27:21,294][88326] Updated weights for policy 0, policy_version 11280 (0.0009) -[2023-10-09 00:27:21,663][88326] Updated weights for policy 0, policy_version 11290 (0.0008) -[2023-10-09 00:27:23,974][87372] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 23134208. Throughput: 0: 1685.1, 1: 1673.6. Samples: 5788130. Policy #0 lag: (min: 28.0, avg: 37.0, max: 60.0) -[2023-10-09 00:27:23,974][87372] Avg episode reward: [(0, '4.850'), (1, '4.770')] -[2023-10-09 00:27:23,975][88168] Saving new best policy, reward=4.770! -[2023-10-09 00:27:24,340][88327] Updated weights for policy 1, policy_version 11300 (0.0007) -[2023-10-09 00:27:24,710][88327] Updated weights for policy 1, policy_version 11310 (0.0008) -[2023-10-09 00:27:25,083][88327] Updated weights for policy 1, policy_version 11320 (0.0009) -[2023-10-09 00:27:25,837][88326] Updated weights for policy 0, policy_version 11300 (0.0012) -[2023-10-09 00:27:26,216][88326] Updated weights for policy 0, policy_version 11310 (0.0009) -[2023-10-09 00:27:26,585][88326] Updated weights for policy 0, policy_version 11320 (0.0009) -[2023-10-09 00:27:28,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 23199744. Throughput: 0: 1673.9, 1: 1697.7. Samples: 5808210. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-09 00:27:28,975][87372] Avg episode reward: [(0, '4.460'), (1, '4.300')] -[2023-10-09 00:27:29,139][88327] Updated weights for policy 1, policy_version 11330 (0.0008) -[2023-10-09 00:27:29,505][88327] Updated weights for policy 1, policy_version 11340 (0.0008) -[2023-10-09 00:27:29,866][88327] Updated weights for policy 1, policy_version 11350 (0.0008) -[2023-10-09 00:27:30,236][88327] Updated weights for policy 1, policy_version 11360 (0.0009) -[2023-10-09 00:27:30,498][88326] Updated weights for policy 0, policy_version 11330 (0.0010) -[2023-10-09 00:27:30,874][88326] Updated weights for policy 0, policy_version 11340 (0.0010) -[2023-10-09 00:27:31,239][88326] Updated weights for policy 0, policy_version 11350 (0.0008) -[2023-10-09 00:27:33,974][87372] Fps is (10 sec: 13106.7, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 23265280. Throughput: 0: 1699.1, 1: 1697.8. Samples: 5829100. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-09 00:27:33,976][87372] Avg episode reward: [(0, '4.620'), (1, '4.310')] -[2023-10-09 00:27:34,537][88327] Updated weights for policy 1, policy_version 11370 (0.0010) -[2023-10-09 00:27:34,912][88327] Updated weights for policy 1, policy_version 11380 (0.0009) -[2023-10-09 00:27:35,218][88326] Updated weights for policy 0, policy_version 11362 (0.0010) -[2023-10-09 00:27:35,272][88327] Updated weights for policy 1, policy_version 11390 (0.0010) -[2023-10-09 00:27:35,592][88326] Updated weights for policy 0, policy_version 11372 (0.0010) -[2023-10-09 00:27:35,966][88326] Updated weights for policy 0, policy_version 11382 (0.0008) -[2023-10-09 00:27:36,320][88326] Updated weights for policy 0, policy_version 11392 (0.0009) -[2023-10-09 00:27:38,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 23330816. Throughput: 0: 1677.6, 1: 1679.1. Samples: 5838448. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-09 00:27:38,974][87372] Avg episode reward: [(0, '4.450'), (1, '3.800')] -[2023-10-09 00:27:39,129][88327] Updated weights for policy 1, policy_version 11400 (0.0010) -[2023-10-09 00:27:39,488][88327] Updated weights for policy 1, policy_version 11410 (0.0009) -[2023-10-09 00:27:39,866][88327] Updated weights for policy 1, policy_version 11420 (0.0008) -[2023-10-09 00:27:40,441][88326] Updated weights for policy 0, policy_version 11402 (0.0008) -[2023-10-09 00:27:40,806][88326] Updated weights for policy 0, policy_version 11412 (0.0007) -[2023-10-09 00:27:41,193][88326] Updated weights for policy 0, policy_version 11422 (0.0009) -[2023-10-09 00:27:43,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 23396352. Throughput: 0: 1692.2, 1: 1695.1. Samples: 5859192. Policy #0 lag: (min: 24.0, avg: 44.9, max: 56.0) -[2023-10-09 00:27:43,975][87372] Avg episode reward: [(0, '4.470'), (1, '3.730')] -[2023-10-09 00:27:44,034][88327] Updated weights for policy 1, policy_version 11430 (0.0010) -[2023-10-09 00:27:44,393][88327] Updated weights for policy 1, policy_version 11440 (0.0009) -[2023-10-09 00:27:44,758][88327] Updated weights for policy 1, policy_version 11450 (0.0009) -[2023-10-09 00:27:45,094][88326] Updated weights for policy 0, policy_version 11432 (0.0008) -[2023-10-09 00:27:45,465][88326] Updated weights for policy 0, policy_version 11442 (0.0010) -[2023-10-09 00:27:45,839][88326] Updated weights for policy 0, policy_version 11452 (0.0009) -[2023-10-09 00:27:48,739][88327] Updated weights for policy 1, policy_version 11460 (0.0008) -[2023-10-09 00:27:48,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 23461888. Throughput: 0: 1706.3, 1: 1690.1. Samples: 5880230. Policy #0 lag: (min: 24.0, avg: 44.9, max: 56.0) -[2023-10-09 00:27:48,975][87372] Avg episode reward: [(0, '4.800'), (1, '3.890')] -[2023-10-09 00:27:49,106][88327] Updated weights for policy 1, policy_version 11470 (0.0009) -[2023-10-09 00:27:49,474][88327] Updated weights for policy 1, policy_version 11480 (0.0011) -[2023-10-09 00:27:49,899][88326] Updated weights for policy 0, policy_version 11462 (0.0008) -[2023-10-09 00:27:50,275][88326] Updated weights for policy 0, policy_version 11472 (0.0011) -[2023-10-09 00:27:50,647][88326] Updated weights for policy 0, policy_version 11482 (0.0009) -[2023-10-09 00:27:53,499][88327] Updated weights for policy 1, policy_version 11490 (0.0008) -[2023-10-09 00:27:53,862][88327] Updated weights for policy 1, policy_version 11500 (0.0007) -[2023-10-09 00:27:53,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 23527424. Throughput: 0: 1676.2, 1: 1691.8. Samples: 5889228. Policy #0 lag: (min: 31.0, avg: 32.4, max: 56.0) -[2023-10-09 00:27:53,975][87372] Avg episode reward: [(0, '4.400'), (1, '4.040')] -[2023-10-09 00:27:54,238][88327] Updated weights for policy 1, policy_version 11510 (0.0008) -[2023-10-09 00:27:54,595][88326] Updated weights for policy 0, policy_version 11492 (0.0008) -[2023-10-09 00:27:54,605][88327] Updated weights for policy 1, policy_version 11520 (0.0007) -[2023-10-09 00:27:54,954][88326] Updated weights for policy 0, policy_version 11502 (0.0009) -[2023-10-09 00:27:55,333][88326] Updated weights for policy 0, policy_version 11512 (0.0009) -[2023-10-09 00:27:58,662][88327] Updated weights for policy 1, policy_version 11530 (0.0011) -[2023-10-09 00:27:58,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 23592960. Throughput: 0: 1706.2, 1: 1692.9. Samples: 5910142. Policy #0 lag: (min: 31.0, avg: 32.4, max: 56.0) -[2023-10-09 00:27:58,974][87372] Avg episode reward: [(0, '4.870'), (1, '3.830')] -[2023-10-09 00:27:59,027][88327] Updated weights for policy 1, policy_version 11540 (0.0010) -[2023-10-09 00:27:59,355][88326] Updated weights for policy 0, policy_version 11522 (0.0008) -[2023-10-09 00:27:59,394][88327] Updated weights for policy 1, policy_version 11550 (0.0009) -[2023-10-09 00:27:59,732][88326] Updated weights for policy 0, policy_version 11532 (0.0008) -[2023-10-09 00:28:00,100][88326] Updated weights for policy 0, policy_version 11542 (0.0008) -[2023-10-09 00:28:00,464][88326] Updated weights for policy 0, policy_version 11552 (0.0007) -[2023-10-09 00:28:03,519][88327] Updated weights for policy 1, policy_version 11560 (0.0008) -[2023-10-09 00:28:03,897][88327] Updated weights for policy 1, policy_version 11570 (0.0008) -[2023-10-09 00:28:03,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 23658496. Throughput: 0: 1711.9, 1: 1693.3. Samples: 5931248. Policy #0 lag: (min: 31.0, avg: 32.4, max: 56.0) -[2023-10-09 00:28:03,974][87372] Avg episode reward: [(0, '5.130'), (1, '4.220')] -[2023-10-09 00:28:04,260][88327] Updated weights for policy 1, policy_version 11580 (0.0009) -[2023-10-09 00:28:04,436][88326] Updated weights for policy 0, policy_version 11562 (0.0008) -[2023-10-09 00:28:04,812][88326] Updated weights for policy 0, policy_version 11572 (0.0009) -[2023-10-09 00:28:05,176][88326] Updated weights for policy 0, policy_version 11582 (0.0009) -[2023-10-09 00:28:08,329][88327] Updated weights for policy 1, policy_version 11590 (0.0009) -[2023-10-09 00:28:08,706][88327] Updated weights for policy 1, policy_version 11600 (0.0010) -[2023-10-09 00:28:08,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 23724032. Throughput: 0: 1691.0, 1: 1693.9. Samples: 5940450. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-10-09 00:28:08,974][87372] Avg episode reward: [(0, '4.630'), (1, '4.160')] -[2023-10-09 00:28:09,077][88327] Updated weights for policy 1, policy_version 11610 (0.0010) -[2023-10-09 00:28:09,220][88326] Updated weights for policy 0, policy_version 11592 (0.0007) -[2023-10-09 00:28:09,590][88326] Updated weights for policy 0, policy_version 11602 (0.0012) -[2023-10-09 00:28:09,963][88326] Updated weights for policy 0, policy_version 11612 (0.0008) -[2023-10-09 00:28:13,154][88327] Updated weights for policy 1, policy_version 11620 (0.0009) -[2023-10-09 00:28:13,521][88327] Updated weights for policy 1, policy_version 11630 (0.0007) -[2023-10-09 00:28:13,884][88327] Updated weights for policy 1, policy_version 11640 (0.0008) -[2023-10-09 00:28:13,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 23789568. Throughput: 0: 1710.6, 1: 1686.8. Samples: 5961096. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-10-09 00:28:13,975][87372] Avg episode reward: [(0, '5.090'), (1, '4.270')] -[2023-10-09 00:28:13,995][88326] Updated weights for policy 0, policy_version 11622 (0.0008) -[2023-10-09 00:28:14,371][88326] Updated weights for policy 0, policy_version 11632 (0.0009) -[2023-10-09 00:28:14,743][88326] Updated weights for policy 0, policy_version 11642 (0.0008) -[2023-10-09 00:28:17,926][88327] Updated weights for policy 1, policy_version 11650 (0.0008) -[2023-10-09 00:28:18,299][88327] Updated weights for policy 1, policy_version 11660 (0.0009) -[2023-10-09 00:28:18,659][88327] Updated weights for policy 1, policy_version 11670 (0.0007) -[2023-10-09 00:28:18,794][88326] Updated weights for policy 0, policy_version 11652 (0.0007) -[2023-10-09 00:28:18,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 23855104. Throughput: 0: 1709.2, 1: 1684.9. Samples: 5981832. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-10-09 00:28:18,975][87372] Avg episode reward: [(0, '4.730'), (1, '4.170')] -[2023-10-09 00:28:19,021][88327] Updated weights for policy 1, policy_version 11680 (0.0008) -[2023-10-09 00:28:19,166][88326] Updated weights for policy 0, policy_version 11662 (0.0008) -[2023-10-09 00:28:19,543][88326] Updated weights for policy 0, policy_version 11672 (0.0008) -[2023-10-09 00:28:23,089][88327] Updated weights for policy 1, policy_version 11690 (0.0008) -[2023-10-09 00:28:23,468][88327] Updated weights for policy 1, policy_version 11700 (0.0010) -[2023-10-09 00:28:23,628][88326] Updated weights for policy 0, policy_version 11682 (0.0008) -[2023-10-09 00:28:23,838][88327] Updated weights for policy 1, policy_version 11710 (0.0009) -[2023-10-09 00:28:23,974][87372] Fps is (10 sec: 16384.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 23953408. Throughput: 0: 1700.7, 1: 1697.8. Samples: 5991380. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-09 00:28:23,974][87372] Avg episode reward: [(0, '4.160'), (1, '3.740')] -[2023-10-09 00:28:23,999][88326] Updated weights for policy 0, policy_version 11692 (0.0008) -[2023-10-09 00:28:24,367][88326] Updated weights for policy 0, policy_version 11702 (0.0009) -[2023-10-09 00:28:24,730][88326] Updated weights for policy 0, policy_version 11712 (0.0008) -[2023-10-09 00:28:27,879][88327] Updated weights for policy 1, policy_version 11720 (0.0007) -[2023-10-09 00:28:28,245][88327] Updated weights for policy 1, policy_version 11730 (0.0008) -[2023-10-09 00:28:28,610][88327] Updated weights for policy 1, policy_version 11740 (0.0009) -[2023-10-09 00:28:28,768][88326] Updated weights for policy 0, policy_version 11722 (0.0009) -[2023-10-09 00:28:28,974][87372] Fps is (10 sec: 16384.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 24018944. Throughput: 0: 1706.0, 1: 1690.1. Samples: 6012016. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-09 00:28:28,974][87372] Avg episode reward: [(0, '4.410'), (1, '4.020')] -[2023-10-09 00:28:29,135][88326] Updated weights for policy 0, policy_version 11732 (0.0008) -[2023-10-09 00:28:29,506][88326] Updated weights for policy 0, policy_version 11742 (0.0009) -[2023-10-09 00:28:32,700][88327] Updated weights for policy 1, policy_version 11750 (0.0009) -[2023-10-09 00:28:33,072][88327] Updated weights for policy 1, policy_version 11760 (0.0009) -[2023-10-09 00:28:33,437][88327] Updated weights for policy 1, policy_version 11770 (0.0009) -[2023-10-09 00:28:33,454][88326] Updated weights for policy 0, policy_version 11752 (0.0008) -[2023-10-09 00:28:33,822][88326] Updated weights for policy 0, policy_version 11762 (0.0007) -[2023-10-09 00:28:33,974][87372] Fps is (10 sec: 13106.8, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 24084480. Throughput: 0: 1701.2, 1: 1676.4. Samples: 6032224. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-09 00:28:33,975][87372] Avg episode reward: [(0, '4.120'), (1, '4.020')] -[2023-10-09 00:28:33,987][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000011776_12058624.pth... -[2023-10-09 00:28:34,025][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000010176_10420224.pth -[2023-10-09 00:28:34,194][88326] Updated weights for policy 0, policy_version 11772 (0.0008) -[2023-10-09 00:28:34,339][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000011776_12058624.pth... -[2023-10-09 00:28:34,379][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000010176_10420224.pth -[2023-10-09 00:28:37,358][88327] Updated weights for policy 1, policy_version 11780 (0.0007) -[2023-10-09 00:28:37,727][88327] Updated weights for policy 1, policy_version 11790 (0.0007) -[2023-10-09 00:28:38,086][88327] Updated weights for policy 1, policy_version 11800 (0.0008) -[2023-10-09 00:28:38,198][88326] Updated weights for policy 0, policy_version 11782 (0.0007) -[2023-10-09 00:28:38,576][88326] Updated weights for policy 0, policy_version 11792 (0.0007) -[2023-10-09 00:28:38,950][88326] Updated weights for policy 0, policy_version 11802 (0.0009) -[2023-10-09 00:28:38,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 24150016. Throughput: 0: 1706.7, 1: 1690.3. Samples: 6042094. Policy #0 lag: (min: 9.0, avg: 15.0, max: 41.0) -[2023-10-09 00:28:38,974][87372] Avg episode reward: [(0, '4.150'), (1, '4.090')] -[2023-10-09 00:28:42,190][88327] Updated weights for policy 1, policy_version 11810 (0.0008) -[2023-10-09 00:28:42,552][88327] Updated weights for policy 1, policy_version 11820 (0.0008) -[2023-10-09 00:28:42,914][88327] Updated weights for policy 1, policy_version 11830 (0.0010) -[2023-10-09 00:28:43,049][88326] Updated weights for policy 0, policy_version 11812 (0.0009) -[2023-10-09 00:28:43,276][88327] Updated weights for policy 1, policy_version 11840 (0.0008) -[2023-10-09 00:28:43,413][88326] Updated weights for policy 0, policy_version 11822 (0.0007) -[2023-10-09 00:28:43,797][88326] Updated weights for policy 0, policy_version 11832 (0.0009) -[2023-10-09 00:28:43,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 24215552. Throughput: 0: 1703.0, 1: 1691.2. Samples: 6062882. Policy #0 lag: (min: 9.0, avg: 15.0, max: 41.0) -[2023-10-09 00:28:43,975][87372] Avg episode reward: [(0, '4.270'), (1, '4.360')] -[2023-10-09 00:28:47,380][88327] Updated weights for policy 1, policy_version 11850 (0.0007) -[2023-10-09 00:28:47,745][88327] Updated weights for policy 1, policy_version 11860 (0.0009) -[2023-10-09 00:28:47,762][88326] Updated weights for policy 0, policy_version 11842 (0.0009) -[2023-10-09 00:28:48,105][88327] Updated weights for policy 1, policy_version 11870 (0.0008) -[2023-10-09 00:28:48,129][88326] Updated weights for policy 0, policy_version 11852 (0.0009) -[2023-10-09 00:28:48,504][88326] Updated weights for policy 0, policy_version 11862 (0.0007) -[2023-10-09 00:28:48,873][88326] Updated weights for policy 0, policy_version 11872 (0.0007) -[2023-10-09 00:28:48,974][87372] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 24313856. Throughput: 0: 1688.4, 1: 1663.2. Samples: 6082072. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:28:48,975][87372] Avg episode reward: [(0, '4.640'), (1, '4.080')] -[2023-10-09 00:28:52,026][88327] Updated weights for policy 1, policy_version 11880 (0.0009) -[2023-10-09 00:28:52,396][88327] Updated weights for policy 1, policy_version 11890 (0.0009) -[2023-10-09 00:28:52,766][88327] Updated weights for policy 1, policy_version 11900 (0.0008) -[2023-10-09 00:28:52,893][88326] Updated weights for policy 0, policy_version 11882 (0.0007) -[2023-10-09 00:28:53,262][88326] Updated weights for policy 0, policy_version 11892 (0.0008) -[2023-10-09 00:28:53,635][88326] Updated weights for policy 0, policy_version 11902 (0.0009) -[2023-10-09 00:28:53,974][87372] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 24379392. Throughput: 0: 1697.8, 1: 1696.4. Samples: 6093190. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:28:53,975][87372] Avg episode reward: [(0, '4.660'), (1, '4.220')] -[2023-10-09 00:28:56,907][88327] Updated weights for policy 1, policy_version 11910 (0.0007) -[2023-10-09 00:28:57,273][88327] Updated weights for policy 1, policy_version 11920 (0.0010) -[2023-10-09 00:28:57,643][88327] Updated weights for policy 1, policy_version 11930 (0.0010) -[2023-10-09 00:28:57,673][88326] Updated weights for policy 0, policy_version 11912 (0.0008) -[2023-10-09 00:28:58,040][88326] Updated weights for policy 0, policy_version 11922 (0.0009) -[2023-10-09 00:28:58,411][88326] Updated weights for policy 0, policy_version 11932 (0.0007) -[2023-10-09 00:28:58,974][87372] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 24444928. Throughput: 0: 1702.1, 1: 1688.7. Samples: 6113680. Policy #0 lag: (min: 1.0, avg: 9.5, max: 33.0) -[2023-10-09 00:28:58,975][87372] Avg episode reward: [(0, '4.700'), (1, '4.340')] -[2023-10-09 00:29:01,706][88327] Updated weights for policy 1, policy_version 11940 (0.0008) -[2023-10-09 00:29:02,076][88327] Updated weights for policy 1, policy_version 11950 (0.0010) -[2023-10-09 00:29:02,305][88326] Updated weights for policy 0, policy_version 11942 (0.0007) -[2023-10-09 00:29:02,440][88327] Updated weights for policy 1, policy_version 11960 (0.0008) -[2023-10-09 00:29:02,673][88326] Updated weights for policy 0, policy_version 11952 (0.0009) -[2023-10-09 00:29:03,041][88326] Updated weights for policy 0, policy_version 11962 (0.0009) -[2023-10-09 00:29:03,974][87372] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 24510464. Throughput: 0: 1677.0, 1: 1672.7. Samples: 6132568. Policy #0 lag: (min: 1.0, avg: 9.5, max: 33.0) -[2023-10-09 00:29:03,975][87372] Avg episode reward: [(0, '4.690'), (1, '4.300')] -[2023-10-09 00:29:06,484][88327] Updated weights for policy 1, policy_version 11970 (0.0009) -[2023-10-09 00:29:06,849][88327] Updated weights for policy 1, policy_version 11980 (0.0007) -[2023-10-09 00:29:07,184][88326] Updated weights for policy 0, policy_version 11972 (0.0010) -[2023-10-09 00:29:07,210][88327] Updated weights for policy 1, policy_version 11990 (0.0008) -[2023-10-09 00:29:07,554][88326] Updated weights for policy 0, policy_version 11982 (0.0009) -[2023-10-09 00:29:07,582][88327] Updated weights for policy 1, policy_version 12000 (0.0007) -[2023-10-09 00:29:07,917][88326] Updated weights for policy 0, policy_version 11992 (0.0011) -[2023-10-09 00:29:08,974][87372] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 24576000. Throughput: 0: 1703.2, 1: 1689.1. Samples: 6144038. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:29:08,975][87372] Avg episode reward: [(0, '4.700'), (1, '4.450')] -[2023-10-09 00:29:11,844][88326] Updated weights for policy 0, policy_version 12002 (0.0009) -[2023-10-09 00:29:12,017][88327] Updated weights for policy 1, policy_version 12010 (0.0010) -[2023-10-09 00:29:12,208][88326] Updated weights for policy 0, policy_version 12012 (0.0007) -[2023-10-09 00:29:12,396][88327] Updated weights for policy 1, policy_version 12020 (0.0010) -[2023-10-09 00:29:12,578][88326] Updated weights for policy 0, policy_version 12022 (0.0007) -[2023-10-09 00:29:12,764][88327] Updated weights for policy 1, policy_version 12030 (0.0008) -[2023-10-09 00:29:12,939][88326] Updated weights for policy 0, policy_version 12032 (0.0007) -[2023-10-09 00:29:13,974][87372] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 24641536. Throughput: 0: 1698.0, 1: 1672.6. Samples: 6163696. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:29:13,975][87372] Avg episode reward: [(0, '4.820'), (1, '4.650')] -[2023-10-09 00:29:16,847][88327] Updated weights for policy 1, policy_version 12040 (0.0007) -[2023-10-09 00:29:17,013][88326] Updated weights for policy 0, policy_version 12042 (0.0007) -[2023-10-09 00:29:17,217][88327] Updated weights for policy 1, policy_version 12050 (0.0007) -[2023-10-09 00:29:17,389][88326] Updated weights for policy 0, policy_version 12052 (0.0007) -[2023-10-09 00:29:17,574][88327] Updated weights for policy 1, policy_version 12060 (0.0009) -[2023-10-09 00:29:17,765][88326] Updated weights for policy 0, policy_version 12062 (0.0010) -[2023-10-09 00:29:18,974][87372] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 24707072. Throughput: 0: 1680.9, 1: 1667.5. Samples: 6182900. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:29:18,975][87372] Avg episode reward: [(0, '4.970'), (1, '4.470')] -[2023-10-09 00:29:21,624][88327] Updated weights for policy 1, policy_version 12070 (0.0008) -[2023-10-09 00:29:21,685][88326] Updated weights for policy 0, policy_version 12072 (0.0008) -[2023-10-09 00:29:22,000][88327] Updated weights for policy 1, policy_version 12080 (0.0009) -[2023-10-09 00:29:22,049][88326] Updated weights for policy 0, policy_version 12082 (0.0008) -[2023-10-09 00:29:22,363][88327] Updated weights for policy 1, policy_version 12090 (0.0008) -[2023-10-09 00:29:22,412][88326] Updated weights for policy 0, policy_version 12092 (0.0008) -[2023-10-09 00:29:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 24772608. Throughput: 0: 1710.9, 1: 1678.6. Samples: 6194622. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-09 00:29:23,975][87372] Avg episode reward: [(0, '4.780'), (1, '4.440')] -[2023-10-09 00:29:26,435][88327] Updated weights for policy 1, policy_version 12100 (0.0009) -[2023-10-09 00:29:26,602][88326] Updated weights for policy 0, policy_version 12102 (0.0008) -[2023-10-09 00:29:26,801][88327] Updated weights for policy 1, policy_version 12110 (0.0007) -[2023-10-09 00:29:26,977][88326] Updated weights for policy 0, policy_version 12112 (0.0007) -[2023-10-09 00:29:27,163][88327] Updated weights for policy 1, policy_version 12120 (0.0007) -[2023-10-09 00:29:27,344][88326] Updated weights for policy 0, policy_version 12122 (0.0007) -[2023-10-09 00:29:28,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 24838144. Throughput: 0: 1688.2, 1: 1657.6. Samples: 6213440. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-09 00:29:28,975][87372] Avg episode reward: [(0, '4.410'), (1, '4.400')] -[2023-10-09 00:29:31,130][88327] Updated weights for policy 1, policy_version 12130 (0.0007) -[2023-10-09 00:29:31,309][88326] Updated weights for policy 0, policy_version 12132 (0.0010) -[2023-10-09 00:29:31,494][88327] Updated weights for policy 1, policy_version 12140 (0.0008) -[2023-10-09 00:29:31,685][88326] Updated weights for policy 0, policy_version 12142 (0.0007) -[2023-10-09 00:29:31,855][88327] Updated weights for policy 1, policy_version 12150 (0.0007) -[2023-10-09 00:29:32,048][88326] Updated weights for policy 0, policy_version 12152 (0.0007) -[2023-10-09 00:29:32,222][88327] Updated weights for policy 1, policy_version 12160 (0.0007) -[2023-10-09 00:29:33,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 24903680. Throughput: 0: 1690.2, 1: 1679.5. Samples: 6233710. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-09 00:29:33,975][87372] Avg episode reward: [(0, '4.940'), (1, '4.290')] -[2023-10-09 00:29:36,156][88326] Updated weights for policy 0, policy_version 12162 (0.0008) -[2023-10-09 00:29:36,190][88327] Updated weights for policy 1, policy_version 12170 (0.0008) -[2023-10-09 00:29:36,524][88326] Updated weights for policy 0, policy_version 12172 (0.0008) -[2023-10-09 00:29:36,559][88327] Updated weights for policy 1, policy_version 12180 (0.0008) -[2023-10-09 00:29:36,895][88326] Updated weights for policy 0, policy_version 12182 (0.0009) -[2023-10-09 00:29:36,919][88327] Updated weights for policy 1, policy_version 12190 (0.0008) -[2023-10-09 00:29:37,270][88326] Updated weights for policy 0, policy_version 12192 (0.0010) -[2023-10-09 00:29:38,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 24969216. Throughput: 0: 1703.4, 1: 1671.2. Samples: 6245046. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) -[2023-10-09 00:29:38,975][87372] Avg episode reward: [(0, '4.500'), (1, '4.120')] -[2023-10-09 00:29:40,935][88327] Updated weights for policy 1, policy_version 12200 (0.0010) -[2023-10-09 00:29:41,290][88326] Updated weights for policy 0, policy_version 12202 (0.0008) -[2023-10-09 00:29:41,298][88327] Updated weights for policy 1, policy_version 12210 (0.0007) -[2023-10-09 00:29:41,655][88326] Updated weights for policy 0, policy_version 12212 (0.0007) -[2023-10-09 00:29:41,668][88327] Updated weights for policy 1, policy_version 12220 (0.0008) -[2023-10-09 00:29:42,035][88326] Updated weights for policy 0, policy_version 12222 (0.0009) -[2023-10-09 00:29:43,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 25034752. Throughput: 0: 1670.8, 1: 1662.8. Samples: 6263692. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) -[2023-10-09 00:29:43,975][87372] Avg episode reward: [(0, '4.630'), (1, '4.480')] -[2023-10-09 00:29:45,574][88327] Updated weights for policy 1, policy_version 12230 (0.0008) -[2023-10-09 00:29:45,941][88327] Updated weights for policy 1, policy_version 12240 (0.0009) -[2023-10-09 00:29:46,134][88326] Updated weights for policy 0, policy_version 12232 (0.0008) -[2023-10-09 00:29:46,313][88327] Updated weights for policy 1, policy_version 12250 (0.0010) -[2023-10-09 00:29:46,509][88326] Updated weights for policy 0, policy_version 12242 (0.0009) -[2023-10-09 00:29:46,878][88326] Updated weights for policy 0, policy_version 12252 (0.0008) -[2023-10-09 00:29:48,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 25100288. Throughput: 0: 1693.9, 1: 1684.7. Samples: 6284606. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) -[2023-10-09 00:29:48,975][87372] Avg episode reward: [(0, '5.110'), (1, '4.190')] -[2023-10-09 00:29:50,466][88327] Updated weights for policy 1, policy_version 12260 (0.0009) -[2023-10-09 00:29:50,818][88327] Updated weights for policy 1, policy_version 12270 (0.0009) -[2023-10-09 00:29:50,830][88326] Updated weights for policy 0, policy_version 12262 (0.0008) -[2023-10-09 00:29:51,185][88327] Updated weights for policy 1, policy_version 12280 (0.0009) -[2023-10-09 00:29:51,188][88326] Updated weights for policy 0, policy_version 12272 (0.0009) -[2023-10-09 00:29:51,570][88326] Updated weights for policy 0, policy_version 12282 (0.0009) -[2023-10-09 00:29:53,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 25165824. Throughput: 0: 1685.0, 1: 1668.3. Samples: 6294934. Policy #0 lag: (min: 31.0, avg: 44.4, max: 63.0) -[2023-10-09 00:29:53,975][87372] Avg episode reward: [(0, '4.440'), (1, '4.660')] -[2023-10-09 00:29:55,203][88327] Updated weights for policy 1, policy_version 12290 (0.0008) -[2023-10-09 00:29:55,564][88327] Updated weights for policy 1, policy_version 12300 (0.0010) -[2023-10-09 00:29:55,642][88326] Updated weights for policy 0, policy_version 12292 (0.0009) -[2023-10-09 00:29:55,921][88327] Updated weights for policy 1, policy_version 12310 (0.0008) -[2023-10-09 00:29:56,018][88326] Updated weights for policy 0, policy_version 12302 (0.0009) -[2023-10-09 00:29:56,289][88327] Updated weights for policy 1, policy_version 12320 (0.0008) -[2023-10-09 00:29:56,395][88326] Updated weights for policy 0, policy_version 12312 (0.0007) -[2023-10-09 00:29:58,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 25231360. Throughput: 0: 1671.3, 1: 1683.1. Samples: 6314644. Policy #0 lag: (min: 31.0, avg: 44.4, max: 63.0) -[2023-10-09 00:29:58,976][87372] Avg episode reward: [(0, '4.810'), (1, '4.670')] -[2023-10-09 00:30:00,286][88326] Updated weights for policy 0, policy_version 12322 (0.0008) -[2023-10-09 00:30:00,472][88327] Updated weights for policy 1, policy_version 12330 (0.0010) -[2023-10-09 00:30:00,657][88326] Updated weights for policy 0, policy_version 12332 (0.0008) -[2023-10-09 00:30:00,839][88327] Updated weights for policy 1, policy_version 12340 (0.0009) -[2023-10-09 00:30:01,015][88326] Updated weights for policy 0, policy_version 12342 (0.0009) -[2023-10-09 00:30:01,215][88327] Updated weights for policy 1, policy_version 12350 (0.0009) -[2023-10-09 00:30:01,384][88326] Updated weights for policy 0, policy_version 12352 (0.0008) -[2023-10-09 00:30:03,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 25296896. Throughput: 0: 1690.3, 1: 1698.9. Samples: 6335414. Policy #0 lag: (min: 31.0, avg: 44.4, max: 63.0) -[2023-10-09 00:30:03,975][87372] Avg episode reward: [(0, '5.010'), (1, '4.240')] -[2023-10-09 00:30:05,306][88327] Updated weights for policy 1, policy_version 12360 (0.0008) -[2023-10-09 00:30:05,384][88326] Updated weights for policy 0, policy_version 12362 (0.0009) -[2023-10-09 00:30:05,671][88327] Updated weights for policy 1, policy_version 12370 (0.0008) -[2023-10-09 00:30:05,745][88326] Updated weights for policy 0, policy_version 12372 (0.0008) -[2023-10-09 00:30:06,035][88327] Updated weights for policy 1, policy_version 12380 (0.0009) -[2023-10-09 00:30:06,126][88326] Updated weights for policy 0, policy_version 12382 (0.0009) -[2023-10-09 00:30:08,974][87372] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 25362432. Throughput: 0: 1658.2, 1: 1674.7. Samples: 6344600. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-09 00:30:08,974][87372] Avg episode reward: [(0, '4.290'), (1, '4.310')] -[2023-10-09 00:30:10,089][88327] Updated weights for policy 1, policy_version 12390 (0.0010) -[2023-10-09 00:30:10,289][88326] Updated weights for policy 0, policy_version 12392 (0.0008) -[2023-10-09 00:30:10,451][88327] Updated weights for policy 1, policy_version 12400 (0.0010) -[2023-10-09 00:30:10,655][88326] Updated weights for policy 0, policy_version 12402 (0.0007) -[2023-10-09 00:30:10,819][88327] Updated weights for policy 1, policy_version 12410 (0.0007) -[2023-10-09 00:30:11,023][88326] Updated weights for policy 0, policy_version 12412 (0.0009) -[2023-10-09 00:30:13,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 25427968. Throughput: 0: 1678.8, 1: 1692.5. Samples: 6365148. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-09 00:30:13,975][87372] Avg episode reward: [(0, '4.680'), (1, '3.830')] -[2023-10-09 00:30:14,777][88327] Updated weights for policy 1, policy_version 12420 (0.0008) -[2023-10-09 00:30:15,133][88327] Updated weights for policy 1, policy_version 12430 (0.0008) -[2023-10-09 00:30:15,238][88326] Updated weights for policy 0, policy_version 12422 (0.0009) -[2023-10-09 00:30:15,501][88327] Updated weights for policy 1, policy_version 12440 (0.0009) -[2023-10-09 00:30:15,618][88326] Updated weights for policy 0, policy_version 12432 (0.0008) -[2023-10-09 00:30:15,993][88326] Updated weights for policy 0, policy_version 12442 (0.0009) -[2023-10-09 00:30:18,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 25493504. Throughput: 0: 1681.2, 1: 1700.2. Samples: 6385872. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-09 00:30:18,975][87372] Avg episode reward: [(0, '4.970'), (1, '3.920')] -[2023-10-09 00:30:19,511][88327] Updated weights for policy 1, policy_version 12450 (0.0007) -[2023-10-09 00:30:19,869][88327] Updated weights for policy 1, policy_version 12460 (0.0009) -[2023-10-09 00:30:20,028][88326] Updated weights for policy 0, policy_version 12452 (0.0007) -[2023-10-09 00:30:20,240][88327] Updated weights for policy 1, policy_version 12470 (0.0008) -[2023-10-09 00:30:20,391][88326] Updated weights for policy 0, policy_version 12462 (0.0008) -[2023-10-09 00:30:20,600][88327] Updated weights for policy 1, policy_version 12480 (0.0009) -[2023-10-09 00:30:20,763][88326] Updated weights for policy 0, policy_version 12472 (0.0009) -[2023-10-09 00:30:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 25559040. Throughput: 0: 1657.3, 1: 1676.7. Samples: 6395076. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-09 00:30:23,975][87372] Avg episode reward: [(0, '4.460'), (1, '4.290')] -[2023-10-09 00:30:24,720][88327] Updated weights for policy 1, policy_version 12490 (0.0008) -[2023-10-09 00:30:24,884][88326] Updated weights for policy 0, policy_version 12482 (0.0007) -[2023-10-09 00:30:25,080][88327] Updated weights for policy 1, policy_version 12500 (0.0008) -[2023-10-09 00:30:25,247][88326] Updated weights for policy 0, policy_version 12492 (0.0007) -[2023-10-09 00:30:25,449][88327] Updated weights for policy 1, policy_version 12510 (0.0009) -[2023-10-09 00:30:25,610][88326] Updated weights for policy 0, policy_version 12502 (0.0008) -[2023-10-09 00:30:25,989][88326] Updated weights for policy 0, policy_version 12512 (0.0009) -[2023-10-09 00:30:28,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 25624576. Throughput: 0: 1687.6, 1: 1697.3. Samples: 6416014. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-09 00:30:28,975][87372] Avg episode reward: [(0, '4.790'), (1, '4.270')] -[2023-10-09 00:30:29,481][88327] Updated weights for policy 1, policy_version 12520 (0.0010) -[2023-10-09 00:30:29,844][88327] Updated weights for policy 1, policy_version 12530 (0.0007) -[2023-10-09 00:30:30,016][88326] Updated weights for policy 0, policy_version 12522 (0.0007) -[2023-10-09 00:30:30,207][88327] Updated weights for policy 1, policy_version 12540 (0.0009) -[2023-10-09 00:30:30,384][88326] Updated weights for policy 0, policy_version 12532 (0.0008) -[2023-10-09 00:30:30,759][88326] Updated weights for policy 0, policy_version 12542 (0.0008) -[2023-10-09 00:30:33,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 25690112. Throughput: 0: 1688.7, 1: 1692.4. Samples: 6436756. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-09 00:30:33,975][87372] Avg episode reward: [(0, '4.850'), (1, '4.650')] -[2023-10-09 00:30:33,986][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000012544_12845056.pth... -[2023-10-09 00:30:33,987][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000012544_12845056.pth... -[2023-10-09 00:30:34,024][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000010976_11239424.pth -[2023-10-09 00:30:34,027][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000010976_11239424.pth -[2023-10-09 00:30:34,351][88327] Updated weights for policy 1, policy_version 12550 (0.0007) -[2023-10-09 00:30:34,718][88327] Updated weights for policy 1, policy_version 12560 (0.0007) -[2023-10-09 00:30:34,844][88326] Updated weights for policy 0, policy_version 12552 (0.0008) -[2023-10-09 00:30:35,086][88327] Updated weights for policy 1, policy_version 12570 (0.0009) -[2023-10-09 00:30:35,218][88326] Updated weights for policy 0, policy_version 12562 (0.0010) -[2023-10-09 00:30:35,582][88326] Updated weights for policy 0, policy_version 12572 (0.0008) -[2023-10-09 00:30:38,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 25755648. Throughput: 0: 1670.7, 1: 1683.2. Samples: 6445856. Policy #0 lag: (min: 12.0, avg: 24.6, max: 44.0) -[2023-10-09 00:30:38,975][87372] Avg episode reward: [(0, '4.760'), (1, '4.410')] -[2023-10-09 00:30:39,022][88327] Updated weights for policy 1, policy_version 12580 (0.0009) -[2023-10-09 00:30:39,393][88327] Updated weights for policy 1, policy_version 12590 (0.0008) -[2023-10-09 00:30:39,544][88326] Updated weights for policy 0, policy_version 12582 (0.0009) -[2023-10-09 00:30:39,755][88327] Updated weights for policy 1, policy_version 12600 (0.0008) -[2023-10-09 00:30:39,907][88326] Updated weights for policy 0, policy_version 12592 (0.0008) -[2023-10-09 00:30:40,275][88326] Updated weights for policy 0, policy_version 12602 (0.0009) -[2023-10-09 00:30:43,848][88327] Updated weights for policy 1, policy_version 12610 (0.0010) -[2023-10-09 00:30:43,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 25821184. Throughput: 0: 1689.1, 1: 1688.3. Samples: 6466624. Policy #0 lag: (min: 12.0, avg: 24.6, max: 44.0) -[2023-10-09 00:30:43,975][87372] Avg episode reward: [(0, '4.990'), (1, '4.310')] -[2023-10-09 00:30:44,215][88327] Updated weights for policy 1, policy_version 12620 (0.0008) -[2023-10-09 00:30:44,356][88326] Updated weights for policy 0, policy_version 12612 (0.0008) -[2023-10-09 00:30:44,582][88327] Updated weights for policy 1, policy_version 12630 (0.0007) -[2023-10-09 00:30:44,725][88326] Updated weights for policy 0, policy_version 12622 (0.0008) -[2023-10-09 00:30:44,952][88327] Updated weights for policy 1, policy_version 12640 (0.0008) -[2023-10-09 00:30:45,103][88326] Updated weights for policy 0, policy_version 12632 (0.0009) -[2023-10-09 00:30:48,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 25886720. Throughput: 0: 1682.6, 1: 1690.5. Samples: 6487206. Policy #0 lag: (min: 12.0, avg: 24.6, max: 44.0) -[2023-10-09 00:30:48,975][87372] Avg episode reward: [(0, '4.860'), (1, '4.190')] -[2023-10-09 00:30:49,174][88327] Updated weights for policy 1, policy_version 12650 (0.0010) -[2023-10-09 00:30:49,302][88326] Updated weights for policy 0, policy_version 12642 (0.0010) -[2023-10-09 00:30:49,544][88327] Updated weights for policy 1, policy_version 12660 (0.0007) -[2023-10-09 00:30:49,661][88326] Updated weights for policy 0, policy_version 12652 (0.0008) -[2023-10-09 00:30:49,915][88327] Updated weights for policy 1, policy_version 12670 (0.0007) -[2023-10-09 00:30:50,027][88326] Updated weights for policy 0, policy_version 12662 (0.0009) -[2023-10-09 00:30:50,399][88326] Updated weights for policy 0, policy_version 12672 (0.0008) -[2023-10-09 00:30:53,777][88327] Updated weights for policy 1, policy_version 12680 (0.0008) -[2023-10-09 00:30:53,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 25952256. Throughput: 0: 1682.7, 1: 1686.9. Samples: 6496236. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-09 00:30:53,975][87372] Avg episode reward: [(0, '5.140'), (1, '4.110')] -[2023-10-09 00:30:54,143][88327] Updated weights for policy 1, policy_version 12690 (0.0007) -[2023-10-09 00:30:54,438][88326] Updated weights for policy 0, policy_version 12682 (0.0008) -[2023-10-09 00:30:54,504][88327] Updated weights for policy 1, policy_version 12700 (0.0010) -[2023-10-09 00:30:54,808][88326] Updated weights for policy 0, policy_version 12692 (0.0007) -[2023-10-09 00:30:55,183][88326] Updated weights for policy 0, policy_version 12702 (0.0008) -[2023-10-09 00:30:58,583][88327] Updated weights for policy 1, policy_version 12710 (0.0008) -[2023-10-09 00:30:58,948][88327] Updated weights for policy 1, policy_version 12720 (0.0009) -[2023-10-09 00:30:58,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 26017792. Throughput: 0: 1685.3, 1: 1692.2. Samples: 6517136. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-09 00:30:58,975][87372] Avg episode reward: [(0, '4.390'), (1, '4.200')] -[2023-10-09 00:30:59,314][88327] Updated weights for policy 1, policy_version 12730 (0.0008) -[2023-10-09 00:30:59,334][88326] Updated weights for policy 0, policy_version 12712 (0.0008) -[2023-10-09 00:30:59,719][88326] Updated weights for policy 0, policy_version 12722 (0.0008) -[2023-10-09 00:31:00,080][88326] Updated weights for policy 0, policy_version 12732 (0.0008) -[2023-10-09 00:31:03,494][88327] Updated weights for policy 1, policy_version 12740 (0.0008) -[2023-10-09 00:31:03,856][88326] Updated weights for policy 0, policy_version 12742 (0.0008) -[2023-10-09 00:31:03,857][88327] Updated weights for policy 1, policy_version 12750 (0.0009) -[2023-10-09 00:31:03,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 26083328. Throughput: 0: 1690.7, 1: 1684.9. Samples: 6537772. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-09 00:31:03,975][87372] Avg episode reward: [(0, '4.660'), (1, '4.310')] -[2023-10-09 00:31:04,224][88326] Updated weights for policy 0, policy_version 12752 (0.0008) -[2023-10-09 00:31:04,228][88327] Updated weights for policy 1, policy_version 12760 (0.0007) -[2023-10-09 00:31:04,589][88326] Updated weights for policy 0, policy_version 12762 (0.0007) -[2023-10-09 00:31:08,256][88327] Updated weights for policy 1, policy_version 12770 (0.0010) -[2023-10-09 00:31:08,613][88327] Updated weights for policy 1, policy_version 12780 (0.0009) -[2023-10-09 00:31:08,697][88326] Updated weights for policy 0, policy_version 12772 (0.0009) -[2023-10-09 00:31:08,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.1, 300 sec: 13440.4). Total num frames: 26148864. Throughput: 0: 1691.9, 1: 1682.5. Samples: 6546922. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:31:08,975][87372] Avg episode reward: [(0, '4.810'), (1, '4.110')] -[2023-10-09 00:31:08,980][88327] Updated weights for policy 1, policy_version 12790 (0.0008) -[2023-10-09 00:31:09,064][88326] Updated weights for policy 0, policy_version 12782 (0.0008) -[2023-10-09 00:31:09,340][88327] Updated weights for policy 1, policy_version 12800 (0.0008) -[2023-10-09 00:31:09,429][88326] Updated weights for policy 0, policy_version 12792 (0.0008) -[2023-10-09 00:31:13,326][88326] Updated weights for policy 0, policy_version 12802 (0.0009) -[2023-10-09 00:31:13,516][88327] Updated weights for policy 1, policy_version 12810 (0.0009) -[2023-10-09 00:31:13,693][88326] Updated weights for policy 0, policy_version 12812 (0.0007) -[2023-10-09 00:31:13,880][88327] Updated weights for policy 1, policy_version 12820 (0.0009) -[2023-10-09 00:31:13,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 26214400. Throughput: 0: 1685.2, 1: 1682.9. Samples: 6567580. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:31:13,975][87372] Avg episode reward: [(0, '4.870'), (1, '3.980')] -[2023-10-09 00:31:14,073][88326] Updated weights for policy 0, policy_version 12822 (0.0008) -[2023-10-09 00:31:14,243][88327] Updated weights for policy 1, policy_version 12830 (0.0008) -[2023-10-09 00:31:14,434][88326] Updated weights for policy 0, policy_version 12832 (0.0008) -[2023-10-09 00:31:18,259][88327] Updated weights for policy 1, policy_version 12840 (0.0008) -[2023-10-09 00:31:18,548][88326] Updated weights for policy 0, policy_version 12842 (0.0007) -[2023-10-09 00:31:18,628][88327] Updated weights for policy 1, policy_version 12850 (0.0007) -[2023-10-09 00:31:18,915][88326] Updated weights for policy 0, policy_version 12852 (0.0008) -[2023-10-09 00:31:18,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 26279936. Throughput: 0: 1686.6, 1: 1683.1. Samples: 6588392. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:31:18,975][87372] Avg episode reward: [(0, '4.910'), (1, '4.350')] -[2023-10-09 00:31:19,002][88327] Updated weights for policy 1, policy_version 12860 (0.0008) -[2023-10-09 00:31:19,296][88326] Updated weights for policy 0, policy_version 12862 (0.0007) -[2023-10-09 00:31:23,063][88327] Updated weights for policy 1, policy_version 12870 (0.0008) -[2023-10-09 00:31:23,327][88326] Updated weights for policy 0, policy_version 12872 (0.0007) -[2023-10-09 00:31:23,425][88327] Updated weights for policy 1, policy_version 12880 (0.0008) -[2023-10-09 00:31:23,689][88326] Updated weights for policy 0, policy_version 12882 (0.0007) -[2023-10-09 00:31:23,777][88327] Updated weights for policy 1, policy_version 12890 (0.0009) -[2023-10-09 00:31:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 26345472. Throughput: 0: 1687.7, 1: 1686.7. Samples: 6597706. Policy #0 lag: (min: 24.0, avg: 42.8, max: 56.0) -[2023-10-09 00:31:23,975][87372] Avg episode reward: [(0, '4.720'), (1, '3.930')] -[2023-10-09 00:31:24,063][88326] Updated weights for policy 0, policy_version 12892 (0.0007) -[2023-10-09 00:31:27,745][88327] Updated weights for policy 1, policy_version 12900 (0.0008) -[2023-10-09 00:31:28,024][88326] Updated weights for policy 0, policy_version 12902 (0.0008) -[2023-10-09 00:31:28,110][88327] Updated weights for policy 1, policy_version 12910 (0.0008) -[2023-10-09 00:31:28,397][88326] Updated weights for policy 0, policy_version 12912 (0.0009) -[2023-10-09 00:31:28,472][88327] Updated weights for policy 1, policy_version 12920 (0.0009) -[2023-10-09 00:31:28,761][88326] Updated weights for policy 0, policy_version 12922 (0.0007) -[2023-10-09 00:31:28,974][87372] Fps is (10 sec: 16384.1, 60 sec: 13653.3, 300 sec: 13440.5). Total num frames: 26443776. Throughput: 0: 1688.2, 1: 1687.4. Samples: 6618526. Policy #0 lag: (min: 24.0, avg: 42.8, max: 56.0) -[2023-10-09 00:31:28,975][87372] Avg episode reward: [(0, '4.700'), (1, '4.540')] -[2023-10-09 00:31:32,582][88327] Updated weights for policy 1, policy_version 12930 (0.0009) -[2023-10-09 00:31:32,908][88326] Updated weights for policy 0, policy_version 12932 (0.0009) -[2023-10-09 00:31:32,952][88327] Updated weights for policy 1, policy_version 12940 (0.0008) -[2023-10-09 00:31:33,280][88326] Updated weights for policy 0, policy_version 12942 (0.0010) -[2023-10-09 00:31:33,318][88327] Updated weights for policy 1, policy_version 12950 (0.0007) -[2023-10-09 00:31:33,663][88326] Updated weights for policy 0, policy_version 12952 (0.0007) -[2023-10-09 00:31:33,689][88327] Updated weights for policy 1, policy_version 12960 (0.0010) -[2023-10-09 00:31:33,974][87372] Fps is (10 sec: 19660.4, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 26542080. Throughput: 0: 1684.7, 1: 1672.8. Samples: 6638296. Policy #0 lag: (min: 1.0, avg: 6.9, max: 33.0) -[2023-10-09 00:31:33,975][87372] Avg episode reward: [(0, '4.710'), (1, '4.470')] -[2023-10-09 00:31:37,589][88326] Updated weights for policy 0, policy_version 12962 (0.0009) -[2023-10-09 00:31:37,911][88327] Updated weights for policy 1, policy_version 12970 (0.0008) -[2023-10-09 00:31:37,960][88326] Updated weights for policy 0, policy_version 12972 (0.0008) -[2023-10-09 00:31:38,283][88327] Updated weights for policy 1, policy_version 12980 (0.0009) -[2023-10-09 00:31:38,331][88326] Updated weights for policy 0, policy_version 12982 (0.0008) -[2023-10-09 00:31:38,653][88327] Updated weights for policy 1, policy_version 12990 (0.0008) -[2023-10-09 00:31:38,694][88326] Updated weights for policy 0, policy_version 12992 (0.0008) -[2023-10-09 00:31:38,974][87372] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 26607616. Throughput: 0: 1694.9, 1: 1690.8. Samples: 6648588. Policy #0 lag: (min: 1.0, avg: 6.9, max: 33.0) -[2023-10-09 00:31:38,975][87372] Avg episode reward: [(0, '5.150'), (1, '4.310')] -[2023-10-09 00:31:42,702][88326] Updated weights for policy 0, policy_version 13002 (0.0008) -[2023-10-09 00:31:42,761][88327] Updated weights for policy 1, policy_version 13000 (0.0009) -[2023-10-09 00:31:43,073][88326] Updated weights for policy 0, policy_version 13012 (0.0009) -[2023-10-09 00:31:43,131][88327] Updated weights for policy 1, policy_version 13010 (0.0007) -[2023-10-09 00:31:43,433][88326] Updated weights for policy 0, policy_version 13022 (0.0007) -[2023-10-09 00:31:43,499][88327] Updated weights for policy 1, policy_version 13020 (0.0009) -[2023-10-09 00:31:43,974][87372] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 26673152. Throughput: 0: 1702.1, 1: 1680.6. Samples: 6669358. Policy #0 lag: (min: 1.0, avg: 6.9, max: 33.0) -[2023-10-09 00:31:43,975][87372] Avg episode reward: [(0, '5.260'), (1, '4.740')] -[2023-10-09 00:31:47,591][88327] Updated weights for policy 1, policy_version 13030 (0.0009) -[2023-10-09 00:31:47,592][88326] Updated weights for policy 0, policy_version 13032 (0.0007) -[2023-10-09 00:31:47,964][88327] Updated weights for policy 1, policy_version 13040 (0.0010) -[2023-10-09 00:31:47,967][88326] Updated weights for policy 0, policy_version 13042 (0.0007) -[2023-10-09 00:31:48,321][88327] Updated weights for policy 1, policy_version 13050 (0.0008) -[2023-10-09 00:31:48,335][88326] Updated weights for policy 0, policy_version 13052 (0.0007) -[2023-10-09 00:31:48,974][87372] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 26738688. Throughput: 0: 1675.1, 1: 1662.8. Samples: 6687976. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:31:48,975][87372] Avg episode reward: [(0, '5.220'), (1, '4.450')] -[2023-10-09 00:31:52,345][88326] Updated weights for policy 0, policy_version 13062 (0.0007) -[2023-10-09 00:31:52,535][88327] Updated weights for policy 1, policy_version 13060 (0.0008) -[2023-10-09 00:31:52,719][88326] Updated weights for policy 0, policy_version 13072 (0.0008) -[2023-10-09 00:31:52,901][88327] Updated weights for policy 1, policy_version 13070 (0.0008) -[2023-10-09 00:31:53,079][88326] Updated weights for policy 0, policy_version 13082 (0.0009) -[2023-10-09 00:31:53,270][88327] Updated weights for policy 1, policy_version 13080 (0.0007) -[2023-10-09 00:31:53,974][87372] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 26804224. Throughput: 0: 1696.1, 1: 1680.4. Samples: 6698866. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:31:53,975][87372] Avg episode reward: [(0, '4.980'), (1, '4.400')] -[2023-10-09 00:31:57,108][88326] Updated weights for policy 0, policy_version 13092 (0.0007) -[2023-10-09 00:31:57,332][88327] Updated weights for policy 1, policy_version 13090 (0.0007) -[2023-10-09 00:31:57,474][88326] Updated weights for policy 0, policy_version 13102 (0.0009) -[2023-10-09 00:31:57,702][88327] Updated weights for policy 1, policy_version 13100 (0.0009) -[2023-10-09 00:31:57,836][88326] Updated weights for policy 0, policy_version 13112 (0.0008) -[2023-10-09 00:31:58,062][88327] Updated weights for policy 1, policy_version 13110 (0.0009) -[2023-10-09 00:31:58,426][88327] Updated weights for policy 1, policy_version 13120 (0.0007) -[2023-10-09 00:31:58,974][87372] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 26869760. Throughput: 0: 1695.9, 1: 1677.9. Samples: 6719398. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:31:58,974][87372] Avg episode reward: [(0, '4.420'), (1, '4.600')] -[2023-10-09 00:32:01,972][88326] Updated weights for policy 0, policy_version 13122 (0.0008) -[2023-10-09 00:32:02,344][88326] Updated weights for policy 0, policy_version 13132 (0.0007) -[2023-10-09 00:32:02,465][88327] Updated weights for policy 1, policy_version 13130 (0.0008) -[2023-10-09 00:32:02,712][88326] Updated weights for policy 0, policy_version 13142 (0.0007) -[2023-10-09 00:32:02,825][88327] Updated weights for policy 1, policy_version 13140 (0.0009) -[2023-10-09 00:32:03,074][88326] Updated weights for policy 0, policy_version 13152 (0.0008) -[2023-10-09 00:32:03,182][88327] Updated weights for policy 1, policy_version 13150 (0.0009) -[2023-10-09 00:32:03,974][87372] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 26935296. Throughput: 0: 1674.7, 1: 1656.5. Samples: 6738298. Policy #0 lag: (min: 13.0, avg: 18.0, max: 45.0) -[2023-10-09 00:32:03,975][87372] Avg episode reward: [(0, '4.780'), (1, '4.400')] -[2023-10-09 00:32:07,136][88326] Updated weights for policy 0, policy_version 13162 (0.0009) -[2023-10-09 00:32:07,171][88327] Updated weights for policy 1, policy_version 13160 (0.0008) -[2023-10-09 00:32:07,511][88326] Updated weights for policy 0, policy_version 13172 (0.0007) -[2023-10-09 00:32:07,533][88327] Updated weights for policy 1, policy_version 13170 (0.0008) -[2023-10-09 00:32:07,866][88326] Updated weights for policy 0, policy_version 13182 (0.0009) -[2023-10-09 00:32:07,901][88327] Updated weights for policy 1, policy_version 13180 (0.0009) -[2023-10-09 00:32:08,974][87372] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 27000832. Throughput: 0: 1704.4, 1: 1680.8. Samples: 6750040. Policy #0 lag: (min: 13.0, avg: 18.0, max: 45.0) -[2023-10-09 00:32:08,975][87372] Avg episode reward: [(0, '4.710'), (1, '4.380')] -[2023-10-09 00:32:11,773][88327] Updated weights for policy 1, policy_version 13190 (0.0008) -[2023-10-09 00:32:12,039][88326] Updated weights for policy 0, policy_version 13192 (0.0007) -[2023-10-09 00:32:12,141][88327] Updated weights for policy 1, policy_version 13200 (0.0007) -[2023-10-09 00:32:12,405][88326] Updated weights for policy 0, policy_version 13202 (0.0008) -[2023-10-09 00:32:12,508][88327] Updated weights for policy 1, policy_version 13210 (0.0007) -[2023-10-09 00:32:12,773][88326] Updated weights for policy 0, policy_version 13212 (0.0007) -[2023-10-09 00:32:13,974][87372] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 27066368. Throughput: 0: 1692.2, 1: 1673.6. Samples: 6769984. Policy #0 lag: (min: 13.0, avg: 18.0, max: 45.0) -[2023-10-09 00:32:13,975][87372] Avg episode reward: [(0, '4.910'), (1, '4.280')] -[2023-10-09 00:32:16,547][88327] Updated weights for policy 1, policy_version 13220 (0.0008) -[2023-10-09 00:32:16,709][88326] Updated weights for policy 0, policy_version 13222 (0.0007) -[2023-10-09 00:32:16,915][88327] Updated weights for policy 1, policy_version 13230 (0.0008) -[2023-10-09 00:32:17,083][88326] Updated weights for policy 0, policy_version 13232 (0.0008) -[2023-10-09 00:32:17,271][88327] Updated weights for policy 1, policy_version 13240 (0.0007) -[2023-10-09 00:32:17,452][88326] Updated weights for policy 0, policy_version 13242 (0.0008) -[2023-10-09 00:32:18,974][87372] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 27131904. Throughput: 0: 1683.8, 1: 1672.8. Samples: 6789342. Policy #0 lag: (min: 8.0, avg: 32.9, max: 40.0) -[2023-10-09 00:32:18,975][87372] Avg episode reward: [(0, '4.800'), (1, '4.230')] -[2023-10-09 00:32:21,451][88326] Updated weights for policy 0, policy_version 13252 (0.0008) -[2023-10-09 00:32:21,474][88327] Updated weights for policy 1, policy_version 13250 (0.0007) -[2023-10-09 00:32:21,827][88326] Updated weights for policy 0, policy_version 13262 (0.0008) -[2023-10-09 00:32:21,835][88327] Updated weights for policy 1, policy_version 13260 (0.0009) -[2023-10-09 00:32:22,196][88326] Updated weights for policy 0, policy_version 13272 (0.0007) -[2023-10-09 00:32:22,203][88327] Updated weights for policy 1, policy_version 13270 (0.0007) -[2023-10-09 00:32:22,567][88327] Updated weights for policy 1, policy_version 13280 (0.0009) -[2023-10-09 00:32:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 27197440. Throughput: 0: 1700.8, 1: 1682.6. Samples: 6800840. Policy #0 lag: (min: 8.0, avg: 32.9, max: 40.0) -[2023-10-09 00:32:23,975][87372] Avg episode reward: [(0, '4.780'), (1, '4.040')] -[2023-10-09 00:32:26,319][88326] Updated weights for policy 0, policy_version 13282 (0.0007) -[2023-10-09 00:32:26,642][88327] Updated weights for policy 1, policy_version 13290 (0.0007) -[2023-10-09 00:32:26,692][88326] Updated weights for policy 0, policy_version 13292 (0.0009) -[2023-10-09 00:32:27,006][88327] Updated weights for policy 1, policy_version 13300 (0.0007) -[2023-10-09 00:32:27,061][88326] Updated weights for policy 0, policy_version 13302 (0.0007) -[2023-10-09 00:32:27,378][88327] Updated weights for policy 1, policy_version 13310 (0.0008) -[2023-10-09 00:32:27,425][88326] Updated weights for policy 0, policy_version 13312 (0.0009) -[2023-10-09 00:32:28,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 27262976. Throughput: 0: 1669.9, 1: 1668.1. Samples: 6819568. Policy #0 lag: (min: 8.0, avg: 32.9, max: 40.0) -[2023-10-09 00:32:28,975][87372] Avg episode reward: [(0, '5.030'), (1, '4.280')] -[2023-10-09 00:32:31,392][88326] Updated weights for policy 0, policy_version 13322 (0.0008) -[2023-10-09 00:32:31,412][88327] Updated weights for policy 1, policy_version 13320 (0.0009) -[2023-10-09 00:32:31,764][88326] Updated weights for policy 0, policy_version 13332 (0.0009) -[2023-10-09 00:32:31,767][88327] Updated weights for policy 1, policy_version 13330 (0.0009) -[2023-10-09 00:32:32,134][88326] Updated weights for policy 0, policy_version 13342 (0.0010) -[2023-10-09 00:32:32,135][88327] Updated weights for policy 1, policy_version 13340 (0.0009) -[2023-10-09 00:32:33,974][87372] Fps is (10 sec: 13106.8, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 27328512. Throughput: 0: 1689.3, 1: 1684.7. Samples: 6839808. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-09 00:32:33,976][87372] Avg episode reward: [(0, '5.210'), (1, '4.340')] -[2023-10-09 00:32:33,990][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000013344_13664256.pth... -[2023-10-09 00:32:33,990][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000013344_13664256.pth... -[2023-10-09 00:32:34,026][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000011776_12058624.pth -[2023-10-09 00:32:34,027][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000011776_12058624.pth -[2023-10-09 00:32:36,237][88327] Updated weights for policy 1, policy_version 13350 (0.0007) -[2023-10-09 00:32:36,295][88326] Updated weights for policy 0, policy_version 13352 (0.0008) -[2023-10-09 00:32:36,603][88327] Updated weights for policy 1, policy_version 13360 (0.0009) -[2023-10-09 00:32:36,673][88326] Updated weights for policy 0, policy_version 13362 (0.0008) -[2023-10-09 00:32:36,960][88327] Updated weights for policy 1, policy_version 13370 (0.0009) -[2023-10-09 00:32:37,036][88326] Updated weights for policy 0, policy_version 13372 (0.0007) -[2023-10-09 00:32:38,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 27394048. Throughput: 0: 1685.6, 1: 1691.7. Samples: 6850848. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-09 00:32:38,975][87372] Avg episode reward: [(0, '5.060'), (1, '4.260')] -[2023-10-09 00:32:41,027][88327] Updated weights for policy 1, policy_version 13380 (0.0010) -[2023-10-09 00:32:41,191][88326] Updated weights for policy 0, policy_version 13382 (0.0009) -[2023-10-09 00:32:41,400][88327] Updated weights for policy 1, policy_version 13390 (0.0007) -[2023-10-09 00:32:41,554][88326] Updated weights for policy 0, policy_version 13392 (0.0008) -[2023-10-09 00:32:41,774][88327] Updated weights for policy 1, policy_version 13400 (0.0009) -[2023-10-09 00:32:41,925][88326] Updated weights for policy 0, policy_version 13402 (0.0008) -[2023-10-09 00:32:43,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 27459584. Throughput: 0: 1662.7, 1: 1667.7. Samples: 6869268. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-09 00:32:43,975][87372] Avg episode reward: [(0, '4.980'), (1, '4.430')] -[2023-10-09 00:32:45,805][88327] Updated weights for policy 1, policy_version 13410 (0.0009) -[2023-10-09 00:32:46,019][88326] Updated weights for policy 0, policy_version 13412 (0.0009) -[2023-10-09 00:32:46,166][88327] Updated weights for policy 1, policy_version 13420 (0.0008) -[2023-10-09 00:32:46,396][88326] Updated weights for policy 0, policy_version 13422 (0.0008) -[2023-10-09 00:32:46,535][88327] Updated weights for policy 1, policy_version 13430 (0.0009) -[2023-10-09 00:32:46,770][88326] Updated weights for policy 0, policy_version 13432 (0.0009) -[2023-10-09 00:32:46,893][88327] Updated weights for policy 1, policy_version 13440 (0.0009) -[2023-10-09 00:32:48,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 27525120. Throughput: 0: 1675.5, 1: 1687.0. Samples: 6889610. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-09 00:32:48,975][87372] Avg episode reward: [(0, '5.190'), (1, '4.510')] -[2023-10-09 00:32:50,777][88326] Updated weights for policy 0, policy_version 13442 (0.0008) -[2023-10-09 00:32:50,974][88327] Updated weights for policy 1, policy_version 13450 (0.0008) -[2023-10-09 00:32:51,145][88326] Updated weights for policy 0, policy_version 13452 (0.0007) -[2023-10-09 00:32:51,334][88327] Updated weights for policy 1, policy_version 13460 (0.0008) -[2023-10-09 00:32:51,508][88326] Updated weights for policy 0, policy_version 13462 (0.0007) -[2023-10-09 00:32:51,700][88327] Updated weights for policy 1, policy_version 13470 (0.0009) -[2023-10-09 00:32:51,879][88326] Updated weights for policy 0, policy_version 13472 (0.0008) -[2023-10-09 00:32:53,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 27590656. Throughput: 0: 1662.1, 1: 1677.5. Samples: 6900320. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-09 00:32:53,975][87372] Avg episode reward: [(0, '4.780'), (1, '4.350')] -[2023-10-09 00:32:55,640][88327] Updated weights for policy 1, policy_version 13480 (0.0008) -[2023-10-09 00:32:55,969][88326] Updated weights for policy 0, policy_version 13482 (0.0009) -[2023-10-09 00:32:56,018][88327] Updated weights for policy 1, policy_version 13490 (0.0009) -[2023-10-09 00:32:56,341][88326] Updated weights for policy 0, policy_version 13492 (0.0008) -[2023-10-09 00:32:56,384][88327] Updated weights for policy 1, policy_version 13500 (0.0009) -[2023-10-09 00:32:56,705][88326] Updated weights for policy 0, policy_version 13502 (0.0009) -[2023-10-09 00:32:58,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 27656192. Throughput: 0: 1653.4, 1: 1673.0. Samples: 6919674. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-09 00:32:58,975][87372] Avg episode reward: [(0, '5.020'), (1, '4.620')] -[2023-10-09 00:33:00,562][88327] Updated weights for policy 1, policy_version 13510 (0.0009) -[2023-10-09 00:33:00,741][88326] Updated weights for policy 0, policy_version 13512 (0.0009) -[2023-10-09 00:33:00,922][88327] Updated weights for policy 1, policy_version 13520 (0.0010) -[2023-10-09 00:33:01,104][88326] Updated weights for policy 0, policy_version 13522 (0.0009) -[2023-10-09 00:33:01,277][88327] Updated weights for policy 1, policy_version 13530 (0.0009) -[2023-10-09 00:33:01,468][88326] Updated weights for policy 0, policy_version 13532 (0.0007) -[2023-10-09 00:33:03,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 27721728. Throughput: 0: 1671.6, 1: 1686.4. Samples: 6940454. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:33:03,975][87372] Avg episode reward: [(0, '5.060'), (1, '4.560')] -[2023-10-09 00:33:05,345][88327] Updated weights for policy 1, policy_version 13540 (0.0008) -[2023-10-09 00:33:05,670][88326] Updated weights for policy 0, policy_version 13542 (0.0008) -[2023-10-09 00:33:05,705][88327] Updated weights for policy 1, policy_version 13550 (0.0008) -[2023-10-09 00:33:06,042][88326] Updated weights for policy 0, policy_version 13552 (0.0007) -[2023-10-09 00:33:06,070][88327] Updated weights for policy 1, policy_version 13560 (0.0009) -[2023-10-09 00:33:06,411][88326] Updated weights for policy 0, policy_version 13562 (0.0007) -[2023-10-09 00:33:08,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 27787264. Throughput: 0: 1655.5, 1: 1669.8. Samples: 6950480. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:33:08,975][87372] Avg episode reward: [(0, '4.820'), (1, '3.990')] -[2023-10-09 00:33:10,058][88327] Updated weights for policy 1, policy_version 13570 (0.0010) -[2023-10-09 00:33:10,434][88327] Updated weights for policy 1, policy_version 13580 (0.0007) -[2023-10-09 00:33:10,546][88326] Updated weights for policy 0, policy_version 13572 (0.0008) -[2023-10-09 00:33:10,790][88327] Updated weights for policy 1, policy_version 13590 (0.0010) -[2023-10-09 00:33:10,910][88326] Updated weights for policy 0, policy_version 13582 (0.0008) -[2023-10-09 00:33:11,165][88327] Updated weights for policy 1, policy_version 13600 (0.0009) -[2023-10-09 00:33:11,281][88326] Updated weights for policy 0, policy_version 13592 (0.0009) -[2023-10-09 00:33:13,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 27852800. Throughput: 0: 1667.4, 1: 1683.8. Samples: 6970372. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:33:13,975][87372] Avg episode reward: [(0, '5.220'), (1, '4.350')] -[2023-10-09 00:33:15,397][88326] Updated weights for policy 0, policy_version 13602 (0.0009) -[2023-10-09 00:33:15,402][88327] Updated weights for policy 1, policy_version 13610 (0.0009) -[2023-10-09 00:33:15,766][88326] Updated weights for policy 0, policy_version 13612 (0.0007) -[2023-10-09 00:33:15,777][88327] Updated weights for policy 1, policy_version 13620 (0.0010) -[2023-10-09 00:33:16,142][88326] Updated weights for policy 0, policy_version 13622 (0.0009) -[2023-10-09 00:33:16,143][88327] Updated weights for policy 1, policy_version 13630 (0.0008) -[2023-10-09 00:33:16,515][88326] Updated weights for policy 0, policy_version 13632 (0.0009) -[2023-10-09 00:33:18,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 27918336. Throughput: 0: 1674.2, 1: 1683.3. Samples: 6990896. Policy #0 lag: (min: 13.0, avg: 14.5, max: 40.0) -[2023-10-09 00:33:18,974][87372] Avg episode reward: [(0, '4.900'), (1, '4.590')] -[2023-10-09 00:33:20,266][88327] Updated weights for policy 1, policy_version 13640 (0.0010) -[2023-10-09 00:33:20,628][88327] Updated weights for policy 1, policy_version 13650 (0.0009) -[2023-10-09 00:33:20,657][88326] Updated weights for policy 0, policy_version 13642 (0.0007) -[2023-10-09 00:33:20,981][88327] Updated weights for policy 1, policy_version 13660 (0.0009) -[2023-10-09 00:33:21,024][88326] Updated weights for policy 0, policy_version 13652 (0.0009) -[2023-10-09 00:33:21,399][88326] Updated weights for policy 0, policy_version 13662 (0.0007) -[2023-10-09 00:33:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 27983872. Throughput: 0: 1660.4, 1: 1660.8. Samples: 7000302. Policy #0 lag: (min: 13.0, avg: 14.5, max: 40.0) -[2023-10-09 00:33:23,975][87372] Avg episode reward: [(0, '4.610'), (1, '4.660')] -[2023-10-09 00:33:25,010][88327] Updated weights for policy 1, policy_version 13670 (0.0010) -[2023-10-09 00:33:25,311][88326] Updated weights for policy 0, policy_version 13672 (0.0008) -[2023-10-09 00:33:25,380][88327] Updated weights for policy 1, policy_version 13680 (0.0008) -[2023-10-09 00:33:25,673][88326] Updated weights for policy 0, policy_version 13682 (0.0008) -[2023-10-09 00:33:25,741][88327] Updated weights for policy 1, policy_version 13690 (0.0010) -[2023-10-09 00:33:26,041][88326] Updated weights for policy 0, policy_version 13692 (0.0009) -[2023-10-09 00:33:28,974][87372] Fps is (10 sec: 13106.8, 60 sec: 13107.1, 300 sec: 13440.4). Total num frames: 28049408. Throughput: 0: 1684.9, 1: 1687.9. Samples: 7021046. Policy #0 lag: (min: 13.0, avg: 14.5, max: 40.0) -[2023-10-09 00:33:28,975][87372] Avg episode reward: [(0, '4.890'), (1, '4.780')] -[2023-10-09 00:33:28,977][88168] Saving new best policy, reward=4.780! -[2023-10-09 00:33:29,630][88327] Updated weights for policy 1, policy_version 13700 (0.0008) -[2023-10-09 00:33:29,998][88327] Updated weights for policy 1, policy_version 13710 (0.0008) -[2023-10-09 00:33:30,009][88326] Updated weights for policy 0, policy_version 13702 (0.0009) -[2023-10-09 00:33:30,369][88327] Updated weights for policy 1, policy_version 13720 (0.0009) -[2023-10-09 00:33:30,378][88326] Updated weights for policy 0, policy_version 13712 (0.0008) -[2023-10-09 00:33:30,740][88326] Updated weights for policy 0, policy_version 13722 (0.0008) -[2023-10-09 00:33:33,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 28114944. Throughput: 0: 1692.5, 1: 1692.1. Samples: 7041918. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-09 00:33:33,975][87372] Avg episode reward: [(0, '4.650'), (1, '4.940')] -[2023-10-09 00:33:33,982][88168] Saving new best policy, reward=4.940! -[2023-10-09 00:33:34,327][88327] Updated weights for policy 1, policy_version 13730 (0.0009) -[2023-10-09 00:33:34,704][88327] Updated weights for policy 1, policy_version 13740 (0.0008) -[2023-10-09 00:33:34,754][88326] Updated weights for policy 0, policy_version 13732 (0.0008) -[2023-10-09 00:33:35,074][88327] Updated weights for policy 1, policy_version 13750 (0.0008) -[2023-10-09 00:33:35,125][88326] Updated weights for policy 0, policy_version 13742 (0.0009) -[2023-10-09 00:33:35,432][88327] Updated weights for policy 1, policy_version 13760 (0.0009) -[2023-10-09 00:33:35,493][88326] Updated weights for policy 0, policy_version 13752 (0.0007) -[2023-10-09 00:33:38,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 28180480. Throughput: 0: 1675.2, 1: 1675.8. Samples: 7051112. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-09 00:33:38,975][87372] Avg episode reward: [(0, '4.390'), (1, '4.650')] -[2023-10-09 00:33:39,386][88326] Updated weights for policy 0, policy_version 13762 (0.0007) -[2023-10-09 00:33:39,497][88327] Updated weights for policy 1, policy_version 13770 (0.0007) -[2023-10-09 00:33:39,758][88326] Updated weights for policy 0, policy_version 13772 (0.0009) -[2023-10-09 00:33:39,867][88327] Updated weights for policy 1, policy_version 13780 (0.0007) -[2023-10-09 00:33:40,123][88326] Updated weights for policy 0, policy_version 13782 (0.0008) -[2023-10-09 00:33:40,230][88327] Updated weights for policy 1, policy_version 13790 (0.0007) -[2023-10-09 00:33:40,490][88326] Updated weights for policy 0, policy_version 13792 (0.0008) -[2023-10-09 00:33:43,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 28246016. Throughput: 0: 1700.1, 1: 1687.3. Samples: 7072106. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-09 00:33:43,974][87372] Avg episode reward: [(0, '5.260'), (1, '4.390')] -[2023-10-09 00:33:44,293][88327] Updated weights for policy 1, policy_version 13800 (0.0007) -[2023-10-09 00:33:44,550][88326] Updated weights for policy 0, policy_version 13802 (0.0007) -[2023-10-09 00:33:44,659][88327] Updated weights for policy 1, policy_version 13810 (0.0007) -[2023-10-09 00:33:44,915][88326] Updated weights for policy 0, policy_version 13812 (0.0009) -[2023-10-09 00:33:45,027][88327] Updated weights for policy 1, policy_version 13820 (0.0007) -[2023-10-09 00:33:45,283][88326] Updated weights for policy 0, policy_version 13822 (0.0009) -[2023-10-09 00:33:48,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 28311552. Throughput: 0: 1700.7, 1: 1686.7. Samples: 7092884. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-09 00:33:48,975][87372] Avg episode reward: [(0, '4.760'), (1, '4.550')] -[2023-10-09 00:33:49,230][88327] Updated weights for policy 1, policy_version 13830 (0.0008) -[2023-10-09 00:33:49,414][88326] Updated weights for policy 0, policy_version 13832 (0.0007) -[2023-10-09 00:33:49,588][88327] Updated weights for policy 1, policy_version 13840 (0.0008) -[2023-10-09 00:33:49,783][88326] Updated weights for policy 0, policy_version 13842 (0.0007) -[2023-10-09 00:33:49,947][88327] Updated weights for policy 1, policy_version 13850 (0.0008) -[2023-10-09 00:33:50,149][88326] Updated weights for policy 0, policy_version 13852 (0.0007) -[2023-10-09 00:33:53,963][88327] Updated weights for policy 1, policy_version 13860 (0.0008) -[2023-10-09 00:33:53,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 28377088. Throughput: 0: 1688.2, 1: 1678.9. Samples: 7102000. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-09 00:33:53,975][87372] Avg episode reward: [(0, '4.650'), (1, '4.110')] -[2023-10-09 00:33:54,052][88326] Updated weights for policy 0, policy_version 13862 (0.0008) -[2023-10-09 00:33:54,328][88327] Updated weights for policy 1, policy_version 13870 (0.0008) -[2023-10-09 00:33:54,427][88326] Updated weights for policy 0, policy_version 13872 (0.0009) -[2023-10-09 00:33:54,692][88327] Updated weights for policy 1, policy_version 13880 (0.0007) -[2023-10-09 00:33:54,797][88326] Updated weights for policy 0, policy_version 13882 (0.0007) -[2023-10-09 00:33:58,724][88326] Updated weights for policy 0, policy_version 13892 (0.0008) -[2023-10-09 00:33:58,736][88327] Updated weights for policy 1, policy_version 13890 (0.0008) -[2023-10-09 00:33:58,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 28442624. Throughput: 0: 1706.7, 1: 1688.0. Samples: 7123134. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-09 00:33:58,975][87372] Avg episode reward: [(0, '5.100'), (1, '4.240')] -[2023-10-09 00:33:59,098][88326] Updated weights for policy 0, policy_version 13902 (0.0007) -[2023-10-09 00:33:59,107][88327] Updated weights for policy 1, policy_version 13900 (0.0009) -[2023-10-09 00:33:59,455][88326] Updated weights for policy 0, policy_version 13912 (0.0007) -[2023-10-09 00:33:59,467][88327] Updated weights for policy 1, policy_version 13910 (0.0007) -[2023-10-09 00:33:59,824][88327] Updated weights for policy 1, policy_version 13920 (0.0009) -[2023-10-09 00:34:03,513][88326] Updated weights for policy 0, policy_version 13922 (0.0008) -[2023-10-09 00:34:03,878][88326] Updated weights for policy 0, policy_version 13932 (0.0009) -[2023-10-09 00:34:03,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 28508160. Throughput: 0: 1707.1, 1: 1695.7. Samples: 7144022. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:34:03,975][87372] Avg episode reward: [(0, '5.310'), (1, '4.710')] -[2023-10-09 00:34:04,038][88327] Updated weights for policy 1, policy_version 13930 (0.0009) -[2023-10-09 00:34:04,244][88326] Updated weights for policy 0, policy_version 13942 (0.0007) -[2023-10-09 00:34:04,408][88327] Updated weights for policy 1, policy_version 13940 (0.0008) -[2023-10-09 00:34:04,615][88088] Saving new best policy, reward=5.310! -[2023-10-09 00:34:04,621][88326] Updated weights for policy 0, policy_version 13952 (0.0008) -[2023-10-09 00:34:04,773][88327] Updated weights for policy 1, policy_version 13950 (0.0008) -[2023-10-09 00:34:08,832][88327] Updated weights for policy 1, policy_version 13960 (0.0008) -[2023-10-09 00:34:08,841][88326] Updated weights for policy 0, policy_version 13962 (0.0007) -[2023-10-09 00:34:08,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 28573696. Throughput: 0: 1700.5, 1: 1690.1. Samples: 7152882. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:34:08,974][87372] Avg episode reward: [(0, '4.900'), (1, '4.590')] -[2023-10-09 00:34:09,197][88327] Updated weights for policy 1, policy_version 13970 (0.0009) -[2023-10-09 00:34:09,206][88326] Updated weights for policy 0, policy_version 13972 (0.0007) -[2023-10-09 00:34:09,574][88326] Updated weights for policy 0, policy_version 13982 (0.0007) -[2023-10-09 00:34:09,576][88327] Updated weights for policy 1, policy_version 13980 (0.0009) -[2023-10-09 00:34:13,636][88326] Updated weights for policy 0, policy_version 13992 (0.0009) -[2023-10-09 00:34:13,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 28639232. Throughput: 0: 1698.5, 1: 1683.2. Samples: 7173220. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:34:13,975][87372] Avg episode reward: [(0, '5.000'), (1, '4.740')] -[2023-10-09 00:34:14,003][88327] Updated weights for policy 1, policy_version 13990 (0.0009) -[2023-10-09 00:34:14,006][88326] Updated weights for policy 0, policy_version 14002 (0.0008) -[2023-10-09 00:34:14,367][88327] Updated weights for policy 1, policy_version 14000 (0.0008) -[2023-10-09 00:34:14,375][88326] Updated weights for policy 0, policy_version 14012 (0.0007) -[2023-10-09 00:34:14,734][88327] Updated weights for policy 1, policy_version 14010 (0.0007) -[2023-10-09 00:34:18,362][88326] Updated weights for policy 0, policy_version 14022 (0.0011) -[2023-10-09 00:34:18,721][88326] Updated weights for policy 0, policy_version 14032 (0.0008) -[2023-10-09 00:34:18,883][88327] Updated weights for policy 1, policy_version 14020 (0.0009) -[2023-10-09 00:34:18,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 28704768. Throughput: 0: 1695.8, 1: 1681.3. Samples: 7193890. Policy #0 lag: (min: 20.0, avg: 27.8, max: 52.0) -[2023-10-09 00:34:18,975][87372] Avg episode reward: [(0, '4.710'), (1, '4.590')] -[2023-10-09 00:34:19,092][88326] Updated weights for policy 0, policy_version 14042 (0.0008) -[2023-10-09 00:34:19,251][88327] Updated weights for policy 1, policy_version 14030 (0.0008) -[2023-10-09 00:34:19,608][88327] Updated weights for policy 1, policy_version 14040 (0.0008) -[2023-10-09 00:34:23,029][88326] Updated weights for policy 0, policy_version 14052 (0.0007) -[2023-10-09 00:34:23,398][88326] Updated weights for policy 0, policy_version 14062 (0.0010) -[2023-10-09 00:34:23,559][88327] Updated weights for policy 1, policy_version 14050 (0.0009) -[2023-10-09 00:34:23,763][88326] Updated weights for policy 0, policy_version 14072 (0.0010) -[2023-10-09 00:34:23,925][88327] Updated weights for policy 1, policy_version 14060 (0.0008) -[2023-10-09 00:34:23,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 28770304. Throughput: 0: 1697.1, 1: 1679.2. Samples: 7203042. Policy #0 lag: (min: 20.0, avg: 27.8, max: 52.0) -[2023-10-09 00:34:23,975][87372] Avg episode reward: [(0, '4.300'), (1, '4.320')] -[2023-10-09 00:34:24,293][88327] Updated weights for policy 1, policy_version 14070 (0.0007) -[2023-10-09 00:34:24,662][88327] Updated weights for policy 1, policy_version 14080 (0.0008) -[2023-10-09 00:34:27,833][88326] Updated weights for policy 0, policy_version 14082 (0.0008) -[2023-10-09 00:34:28,208][88326] Updated weights for policy 0, policy_version 14092 (0.0007) -[2023-10-09 00:34:28,580][88326] Updated weights for policy 0, policy_version 14102 (0.0009) -[2023-10-09 00:34:28,614][88327] Updated weights for policy 1, policy_version 14090 (0.0008) -[2023-10-09 00:34:28,940][88326] Updated weights for policy 0, policy_version 14112 (0.0008) -[2023-10-09 00:34:28,974][87372] Fps is (10 sec: 16384.0, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 28868608. Throughput: 0: 1694.7, 1: 1680.7. Samples: 7223996. Policy #0 lag: (min: 17.0, avg: 17.0, max: 18.0) -[2023-10-09 00:34:28,975][87372] Avg episode reward: [(0, '4.630'), (1, '4.230')] -[2023-10-09 00:34:28,981][88327] Updated weights for policy 1, policy_version 14100 (0.0008) -[2023-10-09 00:34:29,346][88327] Updated weights for policy 1, policy_version 14110 (0.0010) -[2023-10-09 00:34:32,961][88326] Updated weights for policy 0, policy_version 14122 (0.0009) -[2023-10-09 00:34:33,294][88327] Updated weights for policy 1, policy_version 14120 (0.0008) -[2023-10-09 00:34:33,336][88326] Updated weights for policy 0, policy_version 14132 (0.0008) -[2023-10-09 00:34:33,656][88327] Updated weights for policy 1, policy_version 14130 (0.0008) -[2023-10-09 00:34:33,696][88326] Updated weights for policy 0, policy_version 14142 (0.0010) -[2023-10-09 00:34:33,974][87372] Fps is (10 sec: 16384.0, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 28934144. Throughput: 0: 1677.6, 1: 1684.8. Samples: 7244192. Policy #0 lag: (min: 17.0, avg: 17.0, max: 18.0) -[2023-10-09 00:34:33,975][87372] Avg episode reward: [(0, '5.380'), (1, '4.260')] -[2023-10-09 00:34:33,982][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000014144_14483456.pth... -[2023-10-09 00:34:34,020][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000012544_12845056.pth -[2023-10-09 00:34:34,024][88088] Saving new best policy, reward=5.380! -[2023-10-09 00:34:34,034][88327] Updated weights for policy 1, policy_version 14140 (0.0009) -[2023-10-09 00:34:34,168][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000014144_14483456.pth... -[2023-10-09 00:34:34,197][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000012544_12845056.pth -[2023-10-09 00:34:37,718][88326] Updated weights for policy 0, policy_version 14152 (0.0008) -[2023-10-09 00:34:38,083][88326] Updated weights for policy 0, policy_version 14162 (0.0007) -[2023-10-09 00:34:38,160][88327] Updated weights for policy 1, policy_version 14150 (0.0008) -[2023-10-09 00:34:38,453][88326] Updated weights for policy 0, policy_version 14172 (0.0007) -[2023-10-09 00:34:38,524][88327] Updated weights for policy 1, policy_version 14160 (0.0009) -[2023-10-09 00:34:38,886][88327] Updated weights for policy 1, policy_version 14170 (0.0009) -[2023-10-09 00:34:38,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 28999680. Throughput: 0: 1698.2, 1: 1685.1. Samples: 7254248. Policy #0 lag: (min: 17.0, avg: 17.0, max: 18.0) -[2023-10-09 00:34:38,975][87372] Avg episode reward: [(0, '5.100'), (1, '4.250')] -[2023-10-09 00:34:42,569][88326] Updated weights for policy 0, policy_version 14182 (0.0007) -[2023-10-09 00:34:42,935][88326] Updated weights for policy 0, policy_version 14192 (0.0008) -[2023-10-09 00:34:43,013][88327] Updated weights for policy 1, policy_version 14180 (0.0008) -[2023-10-09 00:34:43,297][88326] Updated weights for policy 0, policy_version 14202 (0.0009) -[2023-10-09 00:34:43,369][88327] Updated weights for policy 1, policy_version 14190 (0.0007) -[2023-10-09 00:34:43,743][88327] Updated weights for policy 1, policy_version 14200 (0.0007) -[2023-10-09 00:34:43,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 29065216. Throughput: 0: 1692.2, 1: 1678.3. Samples: 7274806. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) -[2023-10-09 00:34:43,975][87372] Avg episode reward: [(0, '4.930'), (1, '4.230')] -[2023-10-09 00:34:47,249][88326] Updated weights for policy 0, policy_version 14212 (0.0008) -[2023-10-09 00:34:47,607][88326] Updated weights for policy 0, policy_version 14222 (0.0007) -[2023-10-09 00:34:47,871][88327] Updated weights for policy 1, policy_version 14210 (0.0008) -[2023-10-09 00:34:47,979][88326] Updated weights for policy 0, policy_version 14232 (0.0010) -[2023-10-09 00:34:48,240][88327] Updated weights for policy 1, policy_version 14220 (0.0009) -[2023-10-09 00:34:48,604][88327] Updated weights for policy 1, policy_version 14230 (0.0010) -[2023-10-09 00:34:48,972][88327] Updated weights for policy 1, policy_version 14240 (0.0008) -[2023-10-09 00:34:48,974][87372] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 29163520. Throughput: 0: 1674.2, 1: 1669.0. Samples: 7294466. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) -[2023-10-09 00:34:48,975][87372] Avg episode reward: [(0, '5.130'), (1, '4.500')] -[2023-10-09 00:34:52,006][88326] Updated weights for policy 0, policy_version 14242 (0.0010) -[2023-10-09 00:34:52,389][88326] Updated weights for policy 0, policy_version 14252 (0.0008) -[2023-10-09 00:34:52,751][88326] Updated weights for policy 0, policy_version 14262 (0.0009) -[2023-10-09 00:34:52,852][88327] Updated weights for policy 1, policy_version 14250 (0.0007) -[2023-10-09 00:34:53,115][88326] Updated weights for policy 0, policy_version 14272 (0.0008) -[2023-10-09 00:34:53,209][88327] Updated weights for policy 1, policy_version 14260 (0.0008) -[2023-10-09 00:34:53,576][88327] Updated weights for policy 1, policy_version 14270 (0.0008) -[2023-10-09 00:34:53,974][87372] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 29229056. Throughput: 0: 1705.0, 1: 1681.6. Samples: 7305282. Policy #0 lag: (min: 31.0, avg: 33.4, max: 63.0) -[2023-10-09 00:34:53,975][87372] Avg episode reward: [(0, '5.000'), (1, '4.410')] -[2023-10-09 00:34:57,241][88326] Updated weights for policy 0, policy_version 14282 (0.0008) -[2023-10-09 00:34:57,611][88326] Updated weights for policy 0, policy_version 14292 (0.0008) -[2023-10-09 00:34:57,750][88327] Updated weights for policy 1, policy_version 14280 (0.0008) -[2023-10-09 00:34:57,981][88326] Updated weights for policy 0, policy_version 14302 (0.0008) -[2023-10-09 00:34:58,110][88327] Updated weights for policy 1, policy_version 14290 (0.0009) -[2023-10-09 00:34:58,480][88327] Updated weights for policy 1, policy_version 14300 (0.0009) -[2023-10-09 00:34:58,974][87372] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 29294592. Throughput: 0: 1702.0, 1: 1687.0. Samples: 7325726. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:34:58,975][87372] Avg episode reward: [(0, '5.130'), (1, '4.560')] -[2023-10-09 00:35:01,913][88326] Updated weights for policy 0, policy_version 14312 (0.0008) -[2023-10-09 00:35:02,284][88326] Updated weights for policy 0, policy_version 14322 (0.0007) -[2023-10-09 00:35:02,479][88327] Updated weights for policy 1, policy_version 14310 (0.0008) -[2023-10-09 00:35:02,647][88326] Updated weights for policy 0, policy_version 14332 (0.0008) -[2023-10-09 00:35:02,852][88327] Updated weights for policy 1, policy_version 14320 (0.0009) -[2023-10-09 00:35:03,215][88327] Updated weights for policy 1, policy_version 14330 (0.0007) -[2023-10-09 00:35:03,974][87372] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 29360128. Throughput: 0: 1683.8, 1: 1670.4. Samples: 7344826. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:35:03,975][87372] Avg episode reward: [(0, '5.540'), (1, '4.670')] -[2023-10-09 00:35:03,984][88088] Saving new best policy, reward=5.540! -[2023-10-09 00:35:06,762][88326] Updated weights for policy 0, policy_version 14342 (0.0008) -[2023-10-09 00:35:07,130][88326] Updated weights for policy 0, policy_version 14352 (0.0008) -[2023-10-09 00:35:07,189][88327] Updated weights for policy 1, policy_version 14340 (0.0008) -[2023-10-09 00:35:07,504][88326] Updated weights for policy 0, policy_version 14362 (0.0008) -[2023-10-09 00:35:07,555][88327] Updated weights for policy 1, policy_version 14350 (0.0009) -[2023-10-09 00:35:07,918][88327] Updated weights for policy 1, policy_version 14360 (0.0007) -[2023-10-09 00:35:08,974][87372] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 29425664. Throughput: 0: 1711.4, 1: 1693.5. Samples: 7356262. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:35:08,975][87372] Avg episode reward: [(0, '5.060'), (1, '3.970')] -[2023-10-09 00:35:11,544][88326] Updated weights for policy 0, policy_version 14372 (0.0009) -[2023-10-09 00:35:11,912][88326] Updated weights for policy 0, policy_version 14382 (0.0011) -[2023-10-09 00:35:12,005][88327] Updated weights for policy 1, policy_version 14370 (0.0009) -[2023-10-09 00:35:12,290][88326] Updated weights for policy 0, policy_version 14392 (0.0008) -[2023-10-09 00:35:12,363][88327] Updated weights for policy 1, policy_version 14380 (0.0008) -[2023-10-09 00:35:12,731][88327] Updated weights for policy 1, policy_version 14390 (0.0008) -[2023-10-09 00:35:13,110][88327] Updated weights for policy 1, policy_version 14400 (0.0007) -[2023-10-09 00:35:13,974][87372] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 29491200. Throughput: 0: 1686.8, 1: 1691.2. Samples: 7376004. Policy #0 lag: (min: 12.0, avg: 35.6, max: 40.0) -[2023-10-09 00:35:13,975][87372] Avg episode reward: [(0, '4.600'), (1, '4.540')] -[2023-10-09 00:35:16,446][88326] Updated weights for policy 0, policy_version 14402 (0.0009) -[2023-10-09 00:35:16,813][88326] Updated weights for policy 0, policy_version 14412 (0.0009) -[2023-10-09 00:35:17,152][88327] Updated weights for policy 1, policy_version 14410 (0.0008) -[2023-10-09 00:35:17,194][88326] Updated weights for policy 0, policy_version 14422 (0.0008) -[2023-10-09 00:35:17,518][88327] Updated weights for policy 1, policy_version 14420 (0.0007) -[2023-10-09 00:35:17,557][88326] Updated weights for policy 0, policy_version 14432 (0.0007) -[2023-10-09 00:35:17,880][88327] Updated weights for policy 1, policy_version 14430 (0.0007) -[2023-10-09 00:35:18,974][87372] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 29556736. Throughput: 0: 1691.1, 1: 1663.6. Samples: 7395156. Policy #0 lag: (min: 12.0, avg: 35.6, max: 40.0) -[2023-10-09 00:35:18,975][87372] Avg episode reward: [(0, '5.230'), (1, '4.570')] -[2023-10-09 00:35:21,492][88326] Updated weights for policy 0, policy_version 14442 (0.0010) -[2023-10-09 00:35:21,869][88326] Updated weights for policy 0, policy_version 14452 (0.0008) -[2023-10-09 00:35:22,011][88327] Updated weights for policy 1, policy_version 14440 (0.0008) -[2023-10-09 00:35:22,231][88326] Updated weights for policy 0, policy_version 14462 (0.0007) -[2023-10-09 00:35:22,376][88327] Updated weights for policy 1, policy_version 14450 (0.0009) -[2023-10-09 00:35:22,748][88327] Updated weights for policy 1, policy_version 14460 (0.0009) -[2023-10-09 00:35:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 29622272. Throughput: 0: 1698.3, 1: 1688.8. Samples: 7406670. Policy #0 lag: (min: 12.0, avg: 35.6, max: 40.0) -[2023-10-09 00:35:23,975][87372] Avg episode reward: [(0, '4.970'), (1, '4.200')] -[2023-10-09 00:35:26,337][88326] Updated weights for policy 0, policy_version 14472 (0.0008) -[2023-10-09 00:35:26,700][88326] Updated weights for policy 0, policy_version 14482 (0.0009) -[2023-10-09 00:35:26,951][88327] Updated weights for policy 1, policy_version 14470 (0.0007) -[2023-10-09 00:35:27,073][88326] Updated weights for policy 0, policy_version 14492 (0.0007) -[2023-10-09 00:35:27,317][88327] Updated weights for policy 1, policy_version 14480 (0.0009) -[2023-10-09 00:35:27,686][88327] Updated weights for policy 1, policy_version 14490 (0.0010) -[2023-10-09 00:35:28,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 29687808. Throughput: 0: 1674.5, 1: 1686.2. Samples: 7426036. Policy #0 lag: (min: 31.0, avg: 32.1, max: 54.0) -[2023-10-09 00:35:28,975][87372] Avg episode reward: [(0, '4.750'), (1, '4.850')] -[2023-10-09 00:35:31,067][88326] Updated weights for policy 0, policy_version 14502 (0.0007) -[2023-10-09 00:35:31,437][88326] Updated weights for policy 0, policy_version 14512 (0.0007) -[2023-10-09 00:35:31,814][88326] Updated weights for policy 0, policy_version 14522 (0.0008) -[2023-10-09 00:35:31,866][88327] Updated weights for policy 1, policy_version 14500 (0.0010) -[2023-10-09 00:35:32,219][88327] Updated weights for policy 1, policy_version 14510 (0.0009) -[2023-10-09 00:35:32,590][88327] Updated weights for policy 1, policy_version 14520 (0.0010) -[2023-10-09 00:35:33,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 29753344. Throughput: 0: 1698.7, 1: 1671.7. Samples: 7446134. Policy #0 lag: (min: 31.0, avg: 32.1, max: 54.0) -[2023-10-09 00:35:33,975][87372] Avg episode reward: [(0, '5.190'), (1, '4.440')] -[2023-10-09 00:35:35,701][88326] Updated weights for policy 0, policy_version 14532 (0.0010) -[2023-10-09 00:35:36,071][88326] Updated weights for policy 0, policy_version 14542 (0.0009) -[2023-10-09 00:35:36,452][88326] Updated weights for policy 0, policy_version 14552 (0.0008) -[2023-10-09 00:35:36,613][88327] Updated weights for policy 1, policy_version 14530 (0.0010) -[2023-10-09 00:35:36,980][88327] Updated weights for policy 1, policy_version 14540 (0.0007) -[2023-10-09 00:35:37,349][88327] Updated weights for policy 1, policy_version 14550 (0.0010) -[2023-10-09 00:35:37,711][88327] Updated weights for policy 1, policy_version 14560 (0.0009) -[2023-10-09 00:35:38,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 29818880. Throughput: 0: 1684.1, 1: 1689.2. Samples: 7457080. Policy #0 lag: (min: 31.0, avg: 32.1, max: 54.0) -[2023-10-09 00:35:38,975][87372] Avg episode reward: [(0, '5.050'), (1, '4.670')] -[2023-10-09 00:35:40,425][88326] Updated weights for policy 0, policy_version 14562 (0.0008) -[2023-10-09 00:35:40,799][88326] Updated weights for policy 0, policy_version 14572 (0.0008) -[2023-10-09 00:35:41,159][88326] Updated weights for policy 0, policy_version 14582 (0.0010) -[2023-10-09 00:35:41,531][88326] Updated weights for policy 0, policy_version 14592 (0.0009) -[2023-10-09 00:35:41,870][88327] Updated weights for policy 1, policy_version 14570 (0.0010) -[2023-10-09 00:35:42,247][88327] Updated weights for policy 1, policy_version 14580 (0.0008) -[2023-10-09 00:35:42,615][88327] Updated weights for policy 1, policy_version 14590 (0.0007) -[2023-10-09 00:35:43,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 29884416. Throughput: 0: 1680.4, 1: 1670.2. Samples: 7476504. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-09 00:35:43,975][87372] Avg episode reward: [(0, '4.990'), (1, '4.910')] -[2023-10-09 00:35:45,667][88326] Updated weights for policy 0, policy_version 14602 (0.0010) -[2023-10-09 00:35:46,027][88326] Updated weights for policy 0, policy_version 14612 (0.0008) -[2023-10-09 00:35:46,398][88326] Updated weights for policy 0, policy_version 14622 (0.0007) -[2023-10-09 00:35:46,490][88327] Updated weights for policy 1, policy_version 14600 (0.0007) -[2023-10-09 00:35:46,861][88327] Updated weights for policy 1, policy_version 14610 (0.0007) -[2023-10-09 00:35:47,230][88327] Updated weights for policy 1, policy_version 14620 (0.0009) -[2023-10-09 00:35:48,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 29949952. Throughput: 0: 1697.0, 1: 1674.1. Samples: 7496528. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-09 00:35:48,975][87372] Avg episode reward: [(0, '4.810'), (1, '4.330')] -[2023-10-09 00:35:50,258][88326] Updated weights for policy 0, policy_version 14632 (0.0007) -[2023-10-09 00:35:50,626][88326] Updated weights for policy 0, policy_version 14642 (0.0009) -[2023-10-09 00:35:50,991][88326] Updated weights for policy 0, policy_version 14652 (0.0008) -[2023-10-09 00:35:51,371][88327] Updated weights for policy 1, policy_version 14630 (0.0009) -[2023-10-09 00:35:51,731][88327] Updated weights for policy 1, policy_version 14640 (0.0008) -[2023-10-09 00:35:52,100][88327] Updated weights for policy 1, policy_version 14650 (0.0008) -[2023-10-09 00:35:53,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 30015488. Throughput: 0: 1670.2, 1: 1679.2. Samples: 7506984. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-09 00:35:53,975][87372] Avg episode reward: [(0, '4.920'), (1, '4.200')] -[2023-10-09 00:35:55,013][88326] Updated weights for policy 0, policy_version 14662 (0.0008) -[2023-10-09 00:35:55,380][88326] Updated weights for policy 0, policy_version 14672 (0.0009) -[2023-10-09 00:35:55,745][88326] Updated weights for policy 0, policy_version 14682 (0.0007) -[2023-10-09 00:35:56,116][88327] Updated weights for policy 1, policy_version 14660 (0.0007) -[2023-10-09 00:35:56,478][88327] Updated weights for policy 1, policy_version 14670 (0.0012) -[2023-10-09 00:35:56,850][88327] Updated weights for policy 1, policy_version 14680 (0.0008) -[2023-10-09 00:35:58,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 30081024. Throughput: 0: 1696.4, 1: 1654.8. Samples: 7526806. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:35:58,975][87372] Avg episode reward: [(0, '4.680'), (1, '3.910')] -[2023-10-09 00:35:59,831][88326] Updated weights for policy 0, policy_version 14692 (0.0008) -[2023-10-09 00:36:00,197][88326] Updated weights for policy 0, policy_version 14702 (0.0008) -[2023-10-09 00:36:00,569][88326] Updated weights for policy 0, policy_version 14712 (0.0009) -[2023-10-09 00:36:00,882][88327] Updated weights for policy 1, policy_version 14690 (0.0008) -[2023-10-09 00:36:01,245][88327] Updated weights for policy 1, policy_version 14700 (0.0009) -[2023-10-09 00:36:01,607][88327] Updated weights for policy 1, policy_version 14710 (0.0008) -[2023-10-09 00:36:01,969][88327] Updated weights for policy 1, policy_version 14720 (0.0011) -[2023-10-09 00:36:03,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 30146560. Throughput: 0: 1707.5, 1: 1685.8. Samples: 7547852. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:36:03,975][87372] Avg episode reward: [(0, '4.890'), (1, '3.850')] -[2023-10-09 00:36:04,643][88326] Updated weights for policy 0, policy_version 14722 (0.0008) -[2023-10-09 00:36:05,020][88326] Updated weights for policy 0, policy_version 14732 (0.0009) -[2023-10-09 00:36:05,387][88326] Updated weights for policy 0, policy_version 14742 (0.0009) -[2023-10-09 00:36:05,752][88326] Updated weights for policy 0, policy_version 14752 (0.0009) -[2023-10-09 00:36:05,936][88327] Updated weights for policy 1, policy_version 14730 (0.0008) -[2023-10-09 00:36:06,307][88327] Updated weights for policy 1, policy_version 14740 (0.0011) -[2023-10-09 00:36:06,679][88327] Updated weights for policy 1, policy_version 14750 (0.0009) -[2023-10-09 00:36:08,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 30212096. Throughput: 0: 1679.2, 1: 1676.6. Samples: 7557684. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:36:08,975][87372] Avg episode reward: [(0, '5.170'), (1, '3.950')] -[2023-10-09 00:36:09,775][88326] Updated weights for policy 0, policy_version 14762 (0.0008) -[2023-10-09 00:36:10,138][88326] Updated weights for policy 0, policy_version 14772 (0.0009) -[2023-10-09 00:36:10,503][88326] Updated weights for policy 0, policy_version 14782 (0.0011) -[2023-10-09 00:36:10,608][88327] Updated weights for policy 1, policy_version 14760 (0.0011) -[2023-10-09 00:36:10,980][88327] Updated weights for policy 1, policy_version 14770 (0.0009) -[2023-10-09 00:36:11,341][88327] Updated weights for policy 1, policy_version 14780 (0.0008) -[2023-10-09 00:36:13,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 30277632. Throughput: 0: 1712.5, 1: 1669.2. Samples: 7578214. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-09 00:36:13,975][87372] Avg episode reward: [(0, '5.250'), (1, '4.140')] -[2023-10-09 00:36:14,426][88326] Updated weights for policy 0, policy_version 14792 (0.0008) -[2023-10-09 00:36:14,791][88326] Updated weights for policy 0, policy_version 14802 (0.0007) -[2023-10-09 00:36:15,154][88326] Updated weights for policy 0, policy_version 14812 (0.0008) -[2023-10-09 00:36:15,408][88327] Updated weights for policy 1, policy_version 14790 (0.0009) -[2023-10-09 00:36:15,772][88327] Updated weights for policy 1, policy_version 14800 (0.0010) -[2023-10-09 00:36:16,135][88327] Updated weights for policy 1, policy_version 14810 (0.0008) -[2023-10-09 00:36:18,848][88326] Updated weights for policy 0, policy_version 14822 (0.0007) -[2023-10-09 00:36:18,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 30343168. Throughput: 0: 1715.5, 1: 1697.8. Samples: 7599732. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-09 00:36:18,975][87372] Avg episode reward: [(0, '5.380'), (1, '4.130')] -[2023-10-09 00:36:19,220][88326] Updated weights for policy 0, policy_version 14832 (0.0008) -[2023-10-09 00:36:19,585][88326] Updated weights for policy 0, policy_version 14842 (0.0007) -[2023-10-09 00:36:20,158][88327] Updated weights for policy 1, policy_version 14820 (0.0010) -[2023-10-09 00:36:20,524][88327] Updated weights for policy 1, policy_version 14830 (0.0007) -[2023-10-09 00:36:20,895][88327] Updated weights for policy 1, policy_version 14840 (0.0010) -[2023-10-09 00:36:23,560][88326] Updated weights for policy 0, policy_version 14852 (0.0007) -[2023-10-09 00:36:23,938][88326] Updated weights for policy 0, policy_version 14862 (0.0009) -[2023-10-09 00:36:23,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 30408704. Throughput: 0: 1700.7, 1: 1675.3. Samples: 7609002. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-09 00:36:23,974][87372] Avg episode reward: [(0, '4.990'), (1, '4.040')] -[2023-10-09 00:36:24,307][88326] Updated weights for policy 0, policy_version 14872 (0.0009) -[2023-10-09 00:36:24,824][88327] Updated weights for policy 1, policy_version 14850 (0.0008) -[2023-10-09 00:36:25,189][88327] Updated weights for policy 1, policy_version 14860 (0.0010) -[2023-10-09 00:36:25,553][88327] Updated weights for policy 1, policy_version 14870 (0.0010) -[2023-10-09 00:36:25,914][88327] Updated weights for policy 1, policy_version 14880 (0.0011) -[2023-10-09 00:36:28,384][88326] Updated weights for policy 0, policy_version 14882 (0.0009) -[2023-10-09 00:36:28,752][88326] Updated weights for policy 0, policy_version 14892 (0.0010) -[2023-10-09 00:36:28,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 30474240. Throughput: 0: 1716.4, 1: 1693.4. Samples: 7629946. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:36:28,975][87372] Avg episode reward: [(0, '5.080'), (1, '4.230')] -[2023-10-09 00:36:29,131][88326] Updated weights for policy 0, policy_version 14902 (0.0008) -[2023-10-09 00:36:29,497][88326] Updated weights for policy 0, policy_version 14912 (0.0008) -[2023-10-09 00:36:30,162][88327] Updated weights for policy 1, policy_version 14890 (0.0007) -[2023-10-09 00:36:30,527][88327] Updated weights for policy 1, policy_version 14900 (0.0010) -[2023-10-09 00:36:30,894][88327] Updated weights for policy 1, policy_version 14910 (0.0010) -[2023-10-09 00:36:33,645][88326] Updated weights for policy 0, policy_version 14922 (0.0008) -[2023-10-09 00:36:33,974][87372] Fps is (10 sec: 13106.7, 60 sec: 13107.2, 300 sec: 13329.3). Total num frames: 30539776. Throughput: 0: 1721.4, 1: 1709.4. Samples: 7650914. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:36:33,975][87372] Avg episode reward: [(0, '5.230'), (1, '4.140')] -[2023-10-09 00:36:33,986][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000014912_15269888.pth... -[2023-10-09 00:36:33,999][88326] Updated weights for policy 0, policy_version 14932 (0.0009) -[2023-10-09 00:36:34,030][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000013344_13664256.pth -[2023-10-09 00:36:34,372][88326] Updated weights for policy 0, policy_version 14942 (0.0011) -[2023-10-09 00:36:34,443][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000014944_15302656.pth... -[2023-10-09 00:36:34,477][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000013344_13664256.pth -[2023-10-09 00:36:34,677][88327] Updated weights for policy 1, policy_version 14920 (0.0007) -[2023-10-09 00:36:35,045][88327] Updated weights for policy 1, policy_version 14930 (0.0010) -[2023-10-09 00:36:35,411][88327] Updated weights for policy 1, policy_version 14940 (0.0009) -[2023-10-09 00:36:38,411][88326] Updated weights for policy 0, policy_version 14952 (0.0008) -[2023-10-09 00:36:38,773][88326] Updated weights for policy 0, policy_version 14962 (0.0008) -[2023-10-09 00:36:38,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 30605312. Throughput: 0: 1719.3, 1: 1681.2. Samples: 7660006. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:36:38,975][87372] Avg episode reward: [(0, '4.890'), (1, '4.410')] -[2023-10-09 00:36:39,143][88326] Updated weights for policy 0, policy_version 14972 (0.0007) -[2023-10-09 00:36:39,564][88327] Updated weights for policy 1, policy_version 14950 (0.0008) -[2023-10-09 00:36:39,941][88327] Updated weights for policy 1, policy_version 14960 (0.0007) -[2023-10-09 00:36:40,303][88327] Updated weights for policy 1, policy_version 14970 (0.0011) -[2023-10-09 00:36:43,196][88326] Updated weights for policy 0, policy_version 14982 (0.0009) -[2023-10-09 00:36:43,554][88326] Updated weights for policy 0, policy_version 14992 (0.0007) -[2023-10-09 00:36:43,921][88326] Updated weights for policy 0, policy_version 15002 (0.0008) -[2023-10-09 00:36:43,974][87372] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 30670848. Throughput: 0: 1715.1, 1: 1709.1. Samples: 7680894. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-09 00:36:43,975][87372] Avg episode reward: [(0, '5.020'), (1, '4.370')] -[2023-10-09 00:36:44,386][88327] Updated weights for policy 1, policy_version 14980 (0.0009) -[2023-10-09 00:36:44,750][88327] Updated weights for policy 1, policy_version 14990 (0.0009) -[2023-10-09 00:36:45,123][88327] Updated weights for policy 1, policy_version 15000 (0.0010) -[2023-10-09 00:36:47,906][88326] Updated weights for policy 0, policy_version 15012 (0.0009) -[2023-10-09 00:36:48,274][88326] Updated weights for policy 0, policy_version 15022 (0.0008) -[2023-10-09 00:36:48,643][88326] Updated weights for policy 0, policy_version 15032 (0.0008) -[2023-10-09 00:36:48,974][87372] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 30769152. Throughput: 0: 1707.2, 1: 1704.7. Samples: 7701390. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-09 00:36:48,975][87372] Avg episode reward: [(0, '5.460'), (1, '4.250')] -[2023-10-09 00:36:49,109][88327] Updated weights for policy 1, policy_version 15010 (0.0008) -[2023-10-09 00:36:49,481][88327] Updated weights for policy 1, policy_version 15020 (0.0008) -[2023-10-09 00:36:49,844][88327] Updated weights for policy 1, policy_version 15030 (0.0007) -[2023-10-09 00:36:50,204][88327] Updated weights for policy 1, policy_version 15040 (0.0009) -[2023-10-09 00:36:52,639][88326] Updated weights for policy 0, policy_version 15042 (0.0008) -[2023-10-09 00:36:53,006][88326] Updated weights for policy 0, policy_version 15052 (0.0007) -[2023-10-09 00:36:53,378][88326] Updated weights for policy 0, policy_version 15062 (0.0009) -[2023-10-09 00:36:53,749][88326] Updated weights for policy 0, policy_version 15072 (0.0009) -[2023-10-09 00:36:53,974][87372] Fps is (10 sec: 16383.7, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 30834688. Throughput: 0: 1720.1, 1: 1689.6. Samples: 7711124. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-09 00:36:53,975][87372] Avg episode reward: [(0, '5.120'), (1, '4.460')] -[2023-10-09 00:36:54,343][88327] Updated weights for policy 1, policy_version 15050 (0.0008) -[2023-10-09 00:36:54,713][88327] Updated weights for policy 1, policy_version 15060 (0.0009) -[2023-10-09 00:36:55,077][88327] Updated weights for policy 1, policy_version 15070 (0.0011) -[2023-10-09 00:36:57,627][88326] Updated weights for policy 0, policy_version 15082 (0.0012) -[2023-10-09 00:36:57,988][88326] Updated weights for policy 0, policy_version 15092 (0.0008) -[2023-10-09 00:36:58,369][88326] Updated weights for policy 0, policy_version 15102 (0.0009) -[2023-10-09 00:36:58,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 30900224. Throughput: 0: 1717.1, 1: 1701.8. Samples: 7732062. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-09 00:36:58,975][87372] Avg episode reward: [(0, '5.090'), (1, '4.120')] -[2023-10-09 00:36:59,134][88327] Updated weights for policy 1, policy_version 15080 (0.0008) -[2023-10-09 00:36:59,492][88327] Updated weights for policy 1, policy_version 15090 (0.0007) -[2023-10-09 00:36:59,867][88327] Updated weights for policy 1, policy_version 15100 (0.0008) -[2023-10-09 00:37:02,446][88326] Updated weights for policy 0, policy_version 15112 (0.0007) -[2023-10-09 00:37:02,820][88326] Updated weights for policy 0, policy_version 15122 (0.0008) -[2023-10-09 00:37:03,197][88326] Updated weights for policy 0, policy_version 15132 (0.0007) -[2023-10-09 00:37:03,830][88327] Updated weights for policy 1, policy_version 15110 (0.0010) -[2023-10-09 00:37:03,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 30965760. Throughput: 0: 1686.7, 1: 1695.1. Samples: 7751918. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-09 00:37:03,975][87372] Avg episode reward: [(0, '5.050'), (1, '4.460')] -[2023-10-09 00:37:04,210][88327] Updated weights for policy 1, policy_version 15120 (0.0009) -[2023-10-09 00:37:04,582][88327] Updated weights for policy 1, policy_version 15130 (0.0009) -[2023-10-09 00:37:07,232][88326] Updated weights for policy 0, policy_version 15142 (0.0008) -[2023-10-09 00:37:07,600][88326] Updated weights for policy 0, policy_version 15152 (0.0009) -[2023-10-09 00:37:07,968][88326] Updated weights for policy 0, policy_version 15162 (0.0008) -[2023-10-09 00:37:08,770][88327] Updated weights for policy 1, policy_version 15140 (0.0010) -[2023-10-09 00:37:08,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 31031296. Throughput: 0: 1713.9, 1: 1689.2. Samples: 7762140. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:37:08,975][87372] Avg episode reward: [(0, '4.740'), (1, '4.600')] -[2023-10-09 00:37:09,145][88327] Updated weights for policy 1, policy_version 15150 (0.0007) -[2023-10-09 00:37:09,509][88327] Updated weights for policy 1, policy_version 15160 (0.0007) -[2023-10-09 00:37:12,067][88326] Updated weights for policy 0, policy_version 15172 (0.0008) -[2023-10-09 00:37:12,439][88326] Updated weights for policy 0, policy_version 15182 (0.0008) -[2023-10-09 00:37:12,804][88326] Updated weights for policy 0, policy_version 15192 (0.0007) -[2023-10-09 00:37:13,279][88327] Updated weights for policy 1, policy_version 15170 (0.0009) -[2023-10-09 00:37:13,655][88327] Updated weights for policy 1, policy_version 15180 (0.0009) -[2023-10-09 00:37:13,974][87372] Fps is (10 sec: 13107.6, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 31096832. Throughput: 0: 1701.1, 1: 1691.3. Samples: 7782606. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:37:13,975][87372] Avg episode reward: [(0, '5.060'), (1, '4.600')] -[2023-10-09 00:37:14,019][88327] Updated weights for policy 1, policy_version 15190 (0.0010) -[2023-10-09 00:37:14,383][88327] Updated weights for policy 1, policy_version 15200 (0.0008) -[2023-10-09 00:37:16,736][88326] Updated weights for policy 0, policy_version 15202 (0.0007) -[2023-10-09 00:37:17,100][88326] Updated weights for policy 0, policy_version 15212 (0.0009) -[2023-10-09 00:37:17,478][88326] Updated weights for policy 0, policy_version 15222 (0.0010) -[2023-10-09 00:37:17,843][88326] Updated weights for policy 0, policy_version 15232 (0.0008) -[2023-10-09 00:37:18,621][88327] Updated weights for policy 1, policy_version 15210 (0.0007) -[2023-10-09 00:37:18,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 31162368. Throughput: 0: 1680.5, 1: 1689.7. Samples: 7802572. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:37:18,975][87372] Avg episode reward: [(0, '5.200'), (1, '4.110')] -[2023-10-09 00:37:18,990][88327] Updated weights for policy 1, policy_version 15220 (0.0009) -[2023-10-09 00:37:19,353][88327] Updated weights for policy 1, policy_version 15230 (0.0009) -[2023-10-09 00:37:21,862][88326] Updated weights for policy 0, policy_version 15242 (0.0009) -[2023-10-09 00:37:22,228][88326] Updated weights for policy 0, policy_version 15252 (0.0008) -[2023-10-09 00:37:22,592][88326] Updated weights for policy 0, policy_version 15262 (0.0008) -[2023-10-09 00:37:23,366][88327] Updated weights for policy 1, policy_version 15240 (0.0009) -[2023-10-09 00:37:23,731][88327] Updated weights for policy 1, policy_version 15250 (0.0010) -[2023-10-09 00:37:23,974][87372] Fps is (10 sec: 13106.7, 60 sec: 13653.2, 300 sec: 13440.4). Total num frames: 31227904. Throughput: 0: 1710.9, 1: 1688.1. Samples: 7812964. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:37:23,975][87372] Avg episode reward: [(0, '4.910'), (1, '4.350')] -[2023-10-09 00:37:24,103][88327] Updated weights for policy 1, policy_version 15260 (0.0009) -[2023-10-09 00:37:26,529][88326] Updated weights for policy 0, policy_version 15272 (0.0007) -[2023-10-09 00:37:26,907][88326] Updated weights for policy 0, policy_version 15282 (0.0011) -[2023-10-09 00:37:27,276][88326] Updated weights for policy 0, policy_version 15292 (0.0010) -[2023-10-09 00:37:28,155][88327] Updated weights for policy 1, policy_version 15270 (0.0010) -[2023-10-09 00:37:28,528][88327] Updated weights for policy 1, policy_version 15280 (0.0008) -[2023-10-09 00:37:28,890][88327] Updated weights for policy 1, policy_version 15290 (0.0008) -[2023-10-09 00:37:28,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13440.5). Total num frames: 31293440. Throughput: 0: 1685.5, 1: 1696.0. Samples: 7833058. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:37:28,975][87372] Avg episode reward: [(0, '4.800'), (1, '4.310')] -[2023-10-09 00:37:31,236][88326] Updated weights for policy 0, policy_version 15302 (0.0008) -[2023-10-09 00:37:31,613][88326] Updated weights for policy 0, policy_version 15312 (0.0008) -[2023-10-09 00:37:31,976][88326] Updated weights for policy 0, policy_version 15322 (0.0007) -[2023-10-09 00:37:32,829][88327] Updated weights for policy 1, policy_version 15300 (0.0010) -[2023-10-09 00:37:33,191][88327] Updated weights for policy 1, policy_version 15310 (0.0007) -[2023-10-09 00:37:33,554][88327] Updated weights for policy 1, policy_version 15320 (0.0010) -[2023-10-09 00:37:33,974][87372] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 31391744. Throughput: 0: 1688.0, 1: 1688.5. Samples: 7853334. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:37:33,975][87372] Avg episode reward: [(0, '4.440'), (1, '4.440')] -[2023-10-09 00:37:36,012][88326] Updated weights for policy 0, policy_version 15332 (0.0008) -[2023-10-09 00:37:36,391][88326] Updated weights for policy 0, policy_version 15342 (0.0007) -[2023-10-09 00:37:36,752][88326] Updated weights for policy 0, policy_version 15352 (0.0008) -[2023-10-09 00:37:37,561][88327] Updated weights for policy 1, policy_version 15330 (0.0008) -[2023-10-09 00:37:37,935][88327] Updated weights for policy 1, policy_version 15340 (0.0010) -[2023-10-09 00:37:38,301][88327] Updated weights for policy 1, policy_version 15350 (0.0007) -[2023-10-09 00:37:38,676][88327] Updated weights for policy 1, policy_version 15360 (0.0007) -[2023-10-09 00:37:38,974][87372] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 31457280. Throughput: 0: 1697.0, 1: 1697.1. Samples: 7863856. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-09 00:37:38,975][87372] Avg episode reward: [(0, '4.620'), (1, '4.440')] -[2023-10-09 00:37:40,871][88326] Updated weights for policy 0, policy_version 15362 (0.0009) -[2023-10-09 00:37:41,233][88326] Updated weights for policy 0, policy_version 15372 (0.0007) -[2023-10-09 00:37:41,610][88326] Updated weights for policy 0, policy_version 15382 (0.0010) -[2023-10-09 00:37:41,978][88326] Updated weights for policy 0, policy_version 15392 (0.0009) -[2023-10-09 00:37:42,701][88327] Updated weights for policy 1, policy_version 15370 (0.0009) -[2023-10-09 00:37:43,061][88327] Updated weights for policy 1, policy_version 15380 (0.0011) -[2023-10-09 00:37:43,427][88327] Updated weights for policy 1, policy_version 15390 (0.0010) -[2023-10-09 00:37:43,974][87372] Fps is (10 sec: 13107.5, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 31522816. Throughput: 0: 1667.6, 1: 1701.2. Samples: 7883654. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-09 00:37:43,975][87372] Avg episode reward: [(0, '4.540'), (1, '4.240')] -[2023-10-09 00:37:45,977][88326] Updated weights for policy 0, policy_version 15402 (0.0010) -[2023-10-09 00:37:46,346][88326] Updated weights for policy 0, policy_version 15412 (0.0009) -[2023-10-09 00:37:46,715][88326] Updated weights for policy 0, policy_version 15422 (0.0010) -[2023-10-09 00:37:47,490][88327] Updated weights for policy 1, policy_version 15400 (0.0008) -[2023-10-09 00:37:47,857][88327] Updated weights for policy 1, policy_version 15410 (0.0009) -[2023-10-09 00:37:48,230][88327] Updated weights for policy 1, policy_version 15420 (0.0010) -[2023-10-09 00:37:48,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 31588352. Throughput: 0: 1691.0, 1: 1680.9. Samples: 7903652. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-09 00:37:48,975][87372] Avg episode reward: [(0, '4.750'), (1, '4.660')] -[2023-10-09 00:37:50,836][88326] Updated weights for policy 0, policy_version 15432 (0.0010) -[2023-10-09 00:37:51,213][88326] Updated weights for policy 0, policy_version 15442 (0.0008) -[2023-10-09 00:37:51,582][88326] Updated weights for policy 0, policy_version 15452 (0.0008) -[2023-10-09 00:37:52,121][88327] Updated weights for policy 1, policy_version 15430 (0.0009) -[2023-10-09 00:37:52,489][88327] Updated weights for policy 1, policy_version 15440 (0.0009) -[2023-10-09 00:37:52,857][88327] Updated weights for policy 1, policy_version 15450 (0.0009) -[2023-10-09 00:37:53,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 31653888. Throughput: 0: 1675.2, 1: 1706.8. Samples: 7914330. Policy #0 lag: (min: 30.0, avg: 33.1, max: 62.0) -[2023-10-09 00:37:53,975][87372] Avg episode reward: [(0, '4.810'), (1, '4.330')] -[2023-10-09 00:37:55,730][88326] Updated weights for policy 0, policy_version 15462 (0.0009) -[2023-10-09 00:37:56,101][88326] Updated weights for policy 0, policy_version 15472 (0.0007) -[2023-10-09 00:37:56,471][88326] Updated weights for policy 0, policy_version 15482 (0.0007) -[2023-10-09 00:37:56,867][88327] Updated weights for policy 1, policy_version 15460 (0.0008) -[2023-10-09 00:37:57,230][88327] Updated weights for policy 1, policy_version 15470 (0.0008) -[2023-10-09 00:37:57,595][88327] Updated weights for policy 1, policy_version 15480 (0.0008) -[2023-10-09 00:37:58,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 31719424. Throughput: 0: 1669.1, 1: 1697.7. Samples: 7934112. Policy #0 lag: (min: 30.0, avg: 33.1, max: 62.0) -[2023-10-09 00:37:58,975][87372] Avg episode reward: [(0, '5.280'), (1, '4.500')] -[2023-10-09 00:38:00,544][88326] Updated weights for policy 0, policy_version 15492 (0.0008) -[2023-10-09 00:38:00,912][88326] Updated weights for policy 0, policy_version 15502 (0.0008) -[2023-10-09 00:38:01,276][88326] Updated weights for policy 0, policy_version 15512 (0.0007) -[2023-10-09 00:38:01,671][88327] Updated weights for policy 1, policy_version 15490 (0.0008) -[2023-10-09 00:38:02,037][88327] Updated weights for policy 1, policy_version 15500 (0.0009) -[2023-10-09 00:38:02,410][88327] Updated weights for policy 1, policy_version 15510 (0.0009) -[2023-10-09 00:38:02,769][88327] Updated weights for policy 1, policy_version 15520 (0.0008) -[2023-10-09 00:38:03,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 31784960. Throughput: 0: 1690.6, 1: 1680.0. Samples: 7954250. Policy #0 lag: (min: 30.0, avg: 33.1, max: 62.0) -[2023-10-09 00:38:03,975][87372] Avg episode reward: [(0, '5.490'), (1, '4.330')] -[2023-10-09 00:38:05,183][88326] Updated weights for policy 0, policy_version 15522 (0.0009) -[2023-10-09 00:38:05,550][88326] Updated weights for policy 0, policy_version 15532 (0.0010) -[2023-10-09 00:38:05,939][88326] Updated weights for policy 0, policy_version 15542 (0.0011) -[2023-10-09 00:38:06,308][88326] Updated weights for policy 0, policy_version 15552 (0.0009) -[2023-10-09 00:38:06,807][88327] Updated weights for policy 1, policy_version 15530 (0.0008) -[2023-10-09 00:38:07,179][88327] Updated weights for policy 1, policy_version 15540 (0.0008) -[2023-10-09 00:38:07,538][88327] Updated weights for policy 1, policy_version 15550 (0.0009) -[2023-10-09 00:38:08,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 31850496. Throughput: 0: 1666.5, 1: 1713.5. Samples: 7965062. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-10-09 00:38:08,975][87372] Avg episode reward: [(0, '5.230'), (1, '4.450')] -[2023-10-09 00:38:10,320][88326] Updated weights for policy 0, policy_version 15562 (0.0009) -[2023-10-09 00:38:10,697][88326] Updated weights for policy 0, policy_version 15572 (0.0009) -[2023-10-09 00:38:11,062][88326] Updated weights for policy 0, policy_version 15582 (0.0009) -[2023-10-09 00:38:11,614][88327] Updated weights for policy 1, policy_version 15560 (0.0008) -[2023-10-09 00:38:11,978][88327] Updated weights for policy 1, policy_version 15570 (0.0007) -[2023-10-09 00:38:12,340][88327] Updated weights for policy 1, policy_version 15580 (0.0009) -[2023-10-09 00:38:13,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 31916032. Throughput: 0: 1687.9, 1: 1684.1. Samples: 7984798. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-10-09 00:38:13,975][87372] Avg episode reward: [(0, '5.020'), (1, '4.380')] -[2023-10-09 00:38:15,353][88326] Updated weights for policy 0, policy_version 15592 (0.0009) -[2023-10-09 00:38:15,716][88326] Updated weights for policy 0, policy_version 15602 (0.0009) -[2023-10-09 00:38:16,095][88326] Updated weights for policy 0, policy_version 15612 (0.0008) -[2023-10-09 00:38:16,382][88327] Updated weights for policy 1, policy_version 15590 (0.0011) -[2023-10-09 00:38:16,753][88327] Updated weights for policy 1, policy_version 15600 (0.0007) -[2023-10-09 00:38:17,124][88327] Updated weights for policy 1, policy_version 15610 (0.0009) -[2023-10-09 00:38:18,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 31981568. Throughput: 0: 1697.9, 1: 1680.4. Samples: 8005358. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-10-09 00:38:18,975][87372] Avg episode reward: [(0, '4.900'), (1, '4.580')] -[2023-10-09 00:38:19,932][88326] Updated weights for policy 0, policy_version 15622 (0.0008) -[2023-10-09 00:38:20,307][88326] Updated weights for policy 0, policy_version 15632 (0.0008) -[2023-10-09 00:38:20,680][88326] Updated weights for policy 0, policy_version 15642 (0.0009) -[2023-10-09 00:38:21,180][88327] Updated weights for policy 1, policy_version 15620 (0.0009) -[2023-10-09 00:38:21,553][88327] Updated weights for policy 1, policy_version 15630 (0.0008) -[2023-10-09 00:38:21,920][88327] Updated weights for policy 1, policy_version 15640 (0.0008) -[2023-10-09 00:38:23,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 32047104. Throughput: 0: 1679.2, 1: 1696.0. Samples: 8015740. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-09 00:38:23,975][87372] Avg episode reward: [(0, '5.040'), (1, '5.200')] -[2023-10-09 00:38:23,976][88168] Saving new best policy, reward=5.200! -[2023-10-09 00:38:24,569][88326] Updated weights for policy 0, policy_version 15652 (0.0007) -[2023-10-09 00:38:24,939][88326] Updated weights for policy 0, policy_version 15662 (0.0009) -[2023-10-09 00:38:25,298][88326] Updated weights for policy 0, policy_version 15672 (0.0007) -[2023-10-09 00:38:25,875][88327] Updated weights for policy 1, policy_version 15650 (0.0008) -[2023-10-09 00:38:26,241][88327] Updated weights for policy 1, policy_version 15660 (0.0007) -[2023-10-09 00:38:26,611][88327] Updated weights for policy 1, policy_version 15670 (0.0007) -[2023-10-09 00:38:26,976][88327] Updated weights for policy 1, policy_version 15680 (0.0007) -[2023-10-09 00:38:28,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 32112640. Throughput: 0: 1711.3, 1: 1676.3. Samples: 8036098. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-09 00:38:28,975][87372] Avg episode reward: [(0, '5.230'), (1, '4.670')] -[2023-10-09 00:38:29,125][88326] Updated weights for policy 0, policy_version 15682 (0.0009) -[2023-10-09 00:38:29,493][88326] Updated weights for policy 0, policy_version 15692 (0.0007) -[2023-10-09 00:38:29,869][88326] Updated weights for policy 0, policy_version 15702 (0.0008) -[2023-10-09 00:38:30,249][88326] Updated weights for policy 0, policy_version 15712 (0.0008) -[2023-10-09 00:38:30,922][88327] Updated weights for policy 1, policy_version 15690 (0.0011) -[2023-10-09 00:38:31,290][88327] Updated weights for policy 1, policy_version 15700 (0.0009) -[2023-10-09 00:38:31,658][88327] Updated weights for policy 1, policy_version 15710 (0.0008) -[2023-10-09 00:38:33,974][87372] Fps is (10 sec: 13106.8, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 32178176. Throughput: 0: 1709.1, 1: 1702.9. Samples: 8057194. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-09 00:38:33,976][87372] Avg episode reward: [(0, '4.990'), (1, '4.760')] -[2023-10-09 00:38:33,986][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000015712_16089088.pth... -[2023-10-09 00:38:33,986][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000015712_16089088.pth... -[2023-10-09 00:38:34,019][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000014144_14483456.pth -[2023-10-09 00:38:34,023][88088] Saving a milestone ./train_atari/atari_battlezone_APPO/checkpoint_p0/milestones/checkpoint_000015712_16089088.pth -[2023-10-09 00:38:34,025][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000014144_14483456.pth -[2023-10-09 00:38:34,032][88168] Saving a milestone ./train_atari/atari_battlezone_APPO/checkpoint_p1/milestones/checkpoint_000015712_16089088.pth -[2023-10-09 00:38:34,545][88326] Updated weights for policy 0, policy_version 15722 (0.0009) -[2023-10-09 00:38:34,919][88326] Updated weights for policy 0, policy_version 15732 (0.0010) -[2023-10-09 00:38:35,279][88326] Updated weights for policy 0, policy_version 15742 (0.0009) -[2023-10-09 00:38:35,655][88327] Updated weights for policy 1, policy_version 15720 (0.0008) -[2023-10-09 00:38:36,021][88327] Updated weights for policy 1, policy_version 15730 (0.0008) -[2023-10-09 00:38:36,398][88327] Updated weights for policy 1, policy_version 15740 (0.0009) -[2023-10-09 00:38:38,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 32243712. Throughput: 0: 1695.5, 1: 1694.2. Samples: 8066868. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:38:38,975][87372] Avg episode reward: [(0, '5.280'), (1, '4.680')] -[2023-10-09 00:38:39,246][88326] Updated weights for policy 0, policy_version 15752 (0.0008) -[2023-10-09 00:38:39,612][88326] Updated weights for policy 0, policy_version 15762 (0.0007) -[2023-10-09 00:38:39,983][88326] Updated weights for policy 0, policy_version 15772 (0.0007) -[2023-10-09 00:38:40,488][88327] Updated weights for policy 1, policy_version 15750 (0.0009) -[2023-10-09 00:38:40,856][88327] Updated weights for policy 1, policy_version 15760 (0.0010) -[2023-10-09 00:38:41,228][88327] Updated weights for policy 1, policy_version 15770 (0.0008) -[2023-10-09 00:38:43,974][87372] Fps is (10 sec: 13107.7, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 32309248. Throughput: 0: 1712.7, 1: 1689.8. Samples: 8087226. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:38:43,975][87372] Avg episode reward: [(0, '5.250'), (1, '4.520')] -[2023-10-09 00:38:44,124][88326] Updated weights for policy 0, policy_version 15782 (0.0008) -[2023-10-09 00:38:44,489][88326] Updated weights for policy 0, policy_version 15792 (0.0011) -[2023-10-09 00:38:44,857][88326] Updated weights for policy 0, policy_version 15802 (0.0007) -[2023-10-09 00:38:45,224][88327] Updated weights for policy 1, policy_version 15780 (0.0008) -[2023-10-09 00:38:45,582][88327] Updated weights for policy 1, policy_version 15790 (0.0010) -[2023-10-09 00:38:45,947][88327] Updated weights for policy 1, policy_version 15800 (0.0007) -[2023-10-09 00:38:48,788][88326] Updated weights for policy 0, policy_version 15812 (0.0007) -[2023-10-09 00:38:48,974][87372] Fps is (10 sec: 13106.8, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 32374784. Throughput: 0: 1711.5, 1: 1714.4. Samples: 8108420. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:38:48,976][87372] Avg episode reward: [(0, '5.060'), (1, '4.770')] -[2023-10-09 00:38:49,160][88326] Updated weights for policy 0, policy_version 15822 (0.0009) -[2023-10-09 00:38:49,521][88326] Updated weights for policy 0, policy_version 15832 (0.0007) -[2023-10-09 00:38:49,982][88327] Updated weights for policy 1, policy_version 15810 (0.0008) -[2023-10-09 00:38:50,353][88327] Updated weights for policy 1, policy_version 15820 (0.0008) -[2023-10-09 00:38:50,717][88327] Updated weights for policy 1, policy_version 15830 (0.0008) -[2023-10-09 00:38:51,080][88327] Updated weights for policy 1, policy_version 15840 (0.0007) -[2023-10-09 00:38:53,482][88326] Updated weights for policy 0, policy_version 15842 (0.0007) -[2023-10-09 00:38:53,851][88326] Updated weights for policy 0, policy_version 15852 (0.0007) -[2023-10-09 00:38:53,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 32440320. Throughput: 0: 1706.2, 1: 1682.9. Samples: 8117574. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-10-09 00:38:53,975][87372] Avg episode reward: [(0, '5.290'), (1, '4.300')] -[2023-10-09 00:38:54,218][88326] Updated weights for policy 0, policy_version 15862 (0.0007) -[2023-10-09 00:38:54,583][88326] Updated weights for policy 0, policy_version 15872 (0.0008) -[2023-10-09 00:38:55,081][88327] Updated weights for policy 1, policy_version 15850 (0.0009) -[2023-10-09 00:38:55,446][88327] Updated weights for policy 1, policy_version 15860 (0.0007) -[2023-10-09 00:38:55,808][88327] Updated weights for policy 1, policy_version 15870 (0.0010) -[2023-10-09 00:38:58,480][88326] Updated weights for policy 0, policy_version 15882 (0.0007) -[2023-10-09 00:38:58,853][88326] Updated weights for policy 0, policy_version 15892 (0.0007) -[2023-10-09 00:38:58,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 32505856. Throughput: 0: 1712.1, 1: 1695.5. Samples: 8138140. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-10-09 00:38:58,975][87372] Avg episode reward: [(0, '5.020'), (1, '4.070')] -[2023-10-09 00:38:59,220][88326] Updated weights for policy 0, policy_version 15902 (0.0009) -[2023-10-09 00:38:59,786][88327] Updated weights for policy 1, policy_version 15880 (0.0008) -[2023-10-09 00:39:00,156][88327] Updated weights for policy 1, policy_version 15890 (0.0008) -[2023-10-09 00:39:00,523][88327] Updated weights for policy 1, policy_version 15900 (0.0009) -[2023-10-09 00:39:03,340][88326] Updated weights for policy 0, policy_version 15912 (0.0009) -[2023-10-09 00:39:03,717][88326] Updated weights for policy 0, policy_version 15922 (0.0009) -[2023-10-09 00:39:03,975][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 32571392. Throughput: 0: 1698.4, 1: 1707.2. Samples: 8158612. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-10-09 00:39:03,976][87372] Avg episode reward: [(0, '4.650'), (1, '4.030')] -[2023-10-09 00:39:04,092][88326] Updated weights for policy 0, policy_version 15932 (0.0009) -[2023-10-09 00:39:04,489][88327] Updated weights for policy 1, policy_version 15910 (0.0009) -[2023-10-09 00:39:04,851][88327] Updated weights for policy 1, policy_version 15920 (0.0009) -[2023-10-09 00:39:05,231][88327] Updated weights for policy 1, policy_version 15930 (0.0008) -[2023-10-09 00:39:08,151][88326] Updated weights for policy 0, policy_version 15942 (0.0010) -[2023-10-09 00:39:08,531][88326] Updated weights for policy 0, policy_version 15952 (0.0011) -[2023-10-09 00:39:08,900][88326] Updated weights for policy 0, policy_version 15962 (0.0008) -[2023-10-09 00:39:08,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 32636928. Throughput: 0: 1700.1, 1: 1683.0. Samples: 8167980. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:39:08,974][87372] Avg episode reward: [(0, '4.700'), (1, '4.050')] -[2023-10-09 00:39:09,306][88327] Updated weights for policy 1, policy_version 15940 (0.0009) -[2023-10-09 00:39:09,662][88327] Updated weights for policy 1, policy_version 15950 (0.0009) -[2023-10-09 00:39:10,032][88327] Updated weights for policy 1, policy_version 15960 (0.0008) -[2023-10-09 00:39:13,073][88326] Updated weights for policy 0, policy_version 15972 (0.0008) -[2023-10-09 00:39:13,436][88326] Updated weights for policy 0, policy_version 15982 (0.0009) -[2023-10-09 00:39:13,806][88326] Updated weights for policy 0, policy_version 15992 (0.0008) -[2023-10-09 00:39:13,974][87372] Fps is (10 sec: 13107.7, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 32702464. Throughput: 0: 1694.0, 1: 1700.5. Samples: 8188850. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:39:13,975][87372] Avg episode reward: [(0, '4.840'), (1, '4.110')] -[2023-10-09 00:39:14,238][88327] Updated weights for policy 1, policy_version 15970 (0.0009) -[2023-10-09 00:39:14,608][88327] Updated weights for policy 1, policy_version 15980 (0.0011) -[2023-10-09 00:39:14,976][88327] Updated weights for policy 1, policy_version 15990 (0.0011) -[2023-10-09 00:39:15,346][88327] Updated weights for policy 1, policy_version 16000 (0.0011) -[2023-10-09 00:39:17,691][88326] Updated weights for policy 0, policy_version 16002 (0.0007) -[2023-10-09 00:39:18,063][88326] Updated weights for policy 0, policy_version 16012 (0.0008) -[2023-10-09 00:39:18,427][88326] Updated weights for policy 0, policy_version 16022 (0.0010) -[2023-10-09 00:39:18,793][88326] Updated weights for policy 0, policy_version 16032 (0.0010) -[2023-10-09 00:39:18,974][87372] Fps is (10 sec: 16383.8, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 32800768. Throughput: 0: 1682.4, 1: 1695.7. Samples: 8209206. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-09 00:39:18,975][87372] Avg episode reward: [(0, '4.900'), (1, '4.590')] -[2023-10-09 00:39:19,536][88327] Updated weights for policy 1, policy_version 16010 (0.0009) -[2023-10-09 00:39:19,917][88327] Updated weights for policy 1, policy_version 16020 (0.0008) -[2023-10-09 00:39:20,282][88327] Updated weights for policy 1, policy_version 16030 (0.0008) -[2023-10-09 00:39:22,811][88326] Updated weights for policy 0, policy_version 16042 (0.0007) -[2023-10-09 00:39:23,176][88326] Updated weights for policy 0, policy_version 16052 (0.0010) -[2023-10-09 00:39:23,545][88326] Updated weights for policy 0, policy_version 16062 (0.0009) -[2023-10-09 00:39:23,974][87372] Fps is (10 sec: 16383.8, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 32866304. Throughput: 0: 1701.2, 1: 1679.1. Samples: 8218984. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-09 00:39:23,975][87372] Avg episode reward: [(0, '4.760'), (1, '4.350')] -[2023-10-09 00:39:24,420][88327] Updated weights for policy 1, policy_version 16040 (0.0008) -[2023-10-09 00:39:24,786][88327] Updated weights for policy 1, policy_version 16050 (0.0011) -[2023-10-09 00:39:25,154][88327] Updated weights for policy 1, policy_version 16060 (0.0011) -[2023-10-09 00:39:27,659][88326] Updated weights for policy 0, policy_version 16072 (0.0008) -[2023-10-09 00:39:28,023][88326] Updated weights for policy 0, policy_version 16082 (0.0008) -[2023-10-09 00:39:28,391][88326] Updated weights for policy 0, policy_version 16092 (0.0008) -[2023-10-09 00:39:28,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 32931840. Throughput: 0: 1697.8, 1: 1690.8. Samples: 8239716. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-09 00:39:28,975][87372] Avg episode reward: [(0, '5.130'), (1, '4.150')] -[2023-10-09 00:39:29,083][88327] Updated weights for policy 1, policy_version 16070 (0.0011) -[2023-10-09 00:39:29,449][88327] Updated weights for policy 1, policy_version 16080 (0.0011) -[2023-10-09 00:39:29,822][88327] Updated weights for policy 1, policy_version 16090 (0.0007) -[2023-10-09 00:39:32,310][88326] Updated weights for policy 0, policy_version 16102 (0.0007) -[2023-10-09 00:39:32,669][88326] Updated weights for policy 0, policy_version 16112 (0.0010) -[2023-10-09 00:39:33,043][88326] Updated weights for policy 0, policy_version 16122 (0.0008) -[2023-10-09 00:39:33,875][88327] Updated weights for policy 1, policy_version 16100 (0.0008) -[2023-10-09 00:39:33,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 32997376. Throughput: 0: 1670.9, 1: 1687.2. Samples: 8259532. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:39:33,975][87372] Avg episode reward: [(0, '5.010'), (1, '4.160')] -[2023-10-09 00:39:34,240][88327] Updated weights for policy 1, policy_version 16110 (0.0007) -[2023-10-09 00:39:34,605][88327] Updated weights for policy 1, policy_version 16120 (0.0009) -[2023-10-09 00:39:37,008][88326] Updated weights for policy 0, policy_version 16132 (0.0008) -[2023-10-09 00:39:37,381][88326] Updated weights for policy 0, policy_version 16142 (0.0008) -[2023-10-09 00:39:37,750][88326] Updated weights for policy 0, policy_version 16152 (0.0008) -[2023-10-09 00:39:38,574][88327] Updated weights for policy 1, policy_version 16130 (0.0009) -[2023-10-09 00:39:38,932][88327] Updated weights for policy 1, policy_version 16140 (0.0009) -[2023-10-09 00:39:38,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 33062912. Throughput: 0: 1696.9, 1: 1686.5. Samples: 8269826. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:39:38,974][87372] Avg episode reward: [(0, '4.880'), (1, '4.150')] -[2023-10-09 00:39:39,302][88327] Updated weights for policy 1, policy_version 16150 (0.0010) -[2023-10-09 00:39:39,669][88327] Updated weights for policy 1, policy_version 16160 (0.0010) -[2023-10-09 00:39:41,879][88326] Updated weights for policy 0, policy_version 16162 (0.0008) -[2023-10-09 00:39:42,245][88326] Updated weights for policy 0, policy_version 16172 (0.0008) -[2023-10-09 00:39:42,620][88326] Updated weights for policy 0, policy_version 16182 (0.0007) -[2023-10-09 00:39:42,996][88326] Updated weights for policy 0, policy_version 16192 (0.0009) -[2023-10-09 00:39:43,832][88327] Updated weights for policy 1, policy_version 16170 (0.0008) -[2023-10-09 00:39:43,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 33128448. Throughput: 0: 1683.1, 1: 1698.8. Samples: 8290324. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:39:43,974][87372] Avg episode reward: [(0, '5.420'), (1, '4.380')] -[2023-10-09 00:39:44,203][88327] Updated weights for policy 1, policy_version 16180 (0.0008) -[2023-10-09 00:39:44,577][88327] Updated weights for policy 1, policy_version 16190 (0.0009) -[2023-10-09 00:39:47,102][88326] Updated weights for policy 0, policy_version 16202 (0.0007) -[2023-10-09 00:39:47,485][88326] Updated weights for policy 0, policy_version 16212 (0.0007) -[2023-10-09 00:39:47,850][88326] Updated weights for policy 0, policy_version 16222 (0.0009) -[2023-10-09 00:39:48,546][88327] Updated weights for policy 1, policy_version 16200 (0.0009) -[2023-10-09 00:39:48,908][88327] Updated weights for policy 1, policy_version 16210 (0.0010) -[2023-10-09 00:39:48,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 33193984. Throughput: 0: 1672.0, 1: 1696.6. Samples: 8310198. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:39:48,975][87372] Avg episode reward: [(0, '4.950'), (1, '4.480')] -[2023-10-09 00:39:49,271][88327] Updated weights for policy 1, policy_version 16220 (0.0008) -[2023-10-09 00:39:51,993][88326] Updated weights for policy 0, policy_version 16232 (0.0009) -[2023-10-09 00:39:52,375][88326] Updated weights for policy 0, policy_version 16242 (0.0007) -[2023-10-09 00:39:52,745][88326] Updated weights for policy 0, policy_version 16252 (0.0008) -[2023-10-09 00:39:53,373][88327] Updated weights for policy 1, policy_version 16230 (0.0010) -[2023-10-09 00:39:53,747][88327] Updated weights for policy 1, policy_version 16240 (0.0009) -[2023-10-09 00:39:53,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 33259520. Throughput: 0: 1696.6, 1: 1693.0. Samples: 8320512. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:39:53,975][87372] Avg episode reward: [(0, '4.860'), (1, '4.520')] -[2023-10-09 00:39:54,107][88327] Updated weights for policy 1, policy_version 16250 (0.0007) -[2023-10-09 00:39:56,698][88326] Updated weights for policy 0, policy_version 16262 (0.0008) -[2023-10-09 00:39:57,070][88326] Updated weights for policy 0, policy_version 16272 (0.0007) -[2023-10-09 00:39:57,440][88326] Updated weights for policy 0, policy_version 16282 (0.0007) -[2023-10-09 00:39:58,219][88327] Updated weights for policy 1, policy_version 16260 (0.0007) -[2023-10-09 00:39:58,598][88327] Updated weights for policy 1, policy_version 16270 (0.0008) -[2023-10-09 00:39:58,962][88327] Updated weights for policy 1, policy_version 16280 (0.0009) -[2023-10-09 00:39:58,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 33325056. Throughput: 0: 1680.4, 1: 1698.6. Samples: 8340904. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:39:58,975][87372] Avg episode reward: [(0, '5.310'), (1, '4.730')] -[2023-10-09 00:40:01,497][88326] Updated weights for policy 0, policy_version 16292 (0.0009) -[2023-10-09 00:40:01,869][88326] Updated weights for policy 0, policy_version 16302 (0.0011) -[2023-10-09 00:40:02,232][88326] Updated weights for policy 0, policy_version 16312 (0.0011) -[2023-10-09 00:40:02,811][88327] Updated weights for policy 1, policy_version 16290 (0.0008) -[2023-10-09 00:40:03,178][88327] Updated weights for policy 1, policy_version 16300 (0.0007) -[2023-10-09 00:40:03,537][88327] Updated weights for policy 1, policy_version 16310 (0.0007) -[2023-10-09 00:40:03,906][88327] Updated weights for policy 1, policy_version 16320 (0.0009) -[2023-10-09 00:40:03,974][87372] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 33423360. Throughput: 0: 1678.4, 1: 1690.9. Samples: 8360826. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) -[2023-10-09 00:40:03,975][87372] Avg episode reward: [(0, '4.990'), (1, '4.640')] -[2023-10-09 00:40:06,211][88326] Updated weights for policy 0, policy_version 16322 (0.0010) -[2023-10-09 00:40:06,580][88326] Updated weights for policy 0, policy_version 16332 (0.0007) -[2023-10-09 00:40:06,954][88326] Updated weights for policy 0, policy_version 16342 (0.0007) -[2023-10-09 00:40:07,323][88326] Updated weights for policy 0, policy_version 16352 (0.0007) -[2023-10-09 00:40:07,884][88327] Updated weights for policy 1, policy_version 16330 (0.0010) -[2023-10-09 00:40:08,257][88327] Updated weights for policy 1, policy_version 16340 (0.0011) -[2023-10-09 00:40:08,614][88327] Updated weights for policy 1, policy_version 16350 (0.0010) -[2023-10-09 00:40:08,974][87372] Fps is (10 sec: 16384.1, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 33488896. Throughput: 0: 1692.4, 1: 1702.5. Samples: 8371756. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) -[2023-10-09 00:40:08,975][87372] Avg episode reward: [(0, '5.160'), (1, '4.860')] -[2023-10-09 00:40:11,305][88326] Updated weights for policy 0, policy_version 16362 (0.0009) -[2023-10-09 00:40:11,671][88326] Updated weights for policy 0, policy_version 16372 (0.0007) -[2023-10-09 00:40:12,039][88326] Updated weights for policy 0, policy_version 16382 (0.0008) -[2023-10-09 00:40:12,574][88327] Updated weights for policy 1, policy_version 16360 (0.0010) -[2023-10-09 00:40:12,941][88327] Updated weights for policy 1, policy_version 16370 (0.0009) -[2023-10-09 00:40:13,306][88327] Updated weights for policy 1, policy_version 16380 (0.0007) -[2023-10-09 00:40:13,974][87372] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 33554432. Throughput: 0: 1668.7, 1: 1704.2. Samples: 8391498. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) -[2023-10-09 00:40:13,975][87372] Avg episode reward: [(0, '5.320'), (1, '5.120')] -[2023-10-09 00:40:16,105][88326] Updated weights for policy 0, policy_version 16392 (0.0008) -[2023-10-09 00:40:16,480][88326] Updated weights for policy 0, policy_version 16402 (0.0008) -[2023-10-09 00:40:16,841][88326] Updated weights for policy 0, policy_version 16412 (0.0008) -[2023-10-09 00:40:17,355][88327] Updated weights for policy 1, policy_version 16390 (0.0008) -[2023-10-09 00:40:17,730][88327] Updated weights for policy 1, policy_version 16400 (0.0007) -[2023-10-09 00:40:18,091][88327] Updated weights for policy 1, policy_version 16410 (0.0008) -[2023-10-09 00:40:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 33619968. Throughput: 0: 1695.7, 1: 1680.7. Samples: 8411472. Policy #0 lag: (min: 31.0, avg: 31.7, max: 49.0) -[2023-10-09 00:40:18,975][87372] Avg episode reward: [(0, '5.150'), (1, '4.870')] -[2023-10-09 00:40:20,773][88326] Updated weights for policy 0, policy_version 16422 (0.0010) -[2023-10-09 00:40:21,151][88326] Updated weights for policy 0, policy_version 16432 (0.0011) -[2023-10-09 00:40:21,527][88326] Updated weights for policy 0, policy_version 16442 (0.0007) -[2023-10-09 00:40:22,162][88327] Updated weights for policy 1, policy_version 16420 (0.0009) -[2023-10-09 00:40:22,527][88327] Updated weights for policy 1, policy_version 16430 (0.0008) -[2023-10-09 00:40:22,900][88327] Updated weights for policy 1, policy_version 16440 (0.0008) -[2023-10-09 00:40:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 33685504. Throughput: 0: 1680.7, 1: 1702.5. Samples: 8422068. Policy #0 lag: (min: 31.0, avg: 31.7, max: 49.0) -[2023-10-09 00:40:23,975][87372] Avg episode reward: [(0, '5.010'), (1, '4.520')] -[2023-10-09 00:40:25,308][88326] Updated weights for policy 0, policy_version 16452 (0.0007) -[2023-10-09 00:40:25,677][88326] Updated weights for policy 0, policy_version 16462 (0.0008) -[2023-10-09 00:40:26,047][88326] Updated weights for policy 0, policy_version 16472 (0.0009) -[2023-10-09 00:40:26,793][88327] Updated weights for policy 1, policy_version 16450 (0.0007) -[2023-10-09 00:40:27,163][88327] Updated weights for policy 1, policy_version 16460 (0.0008) -[2023-10-09 00:40:27,536][88327] Updated weights for policy 1, policy_version 16470 (0.0009) -[2023-10-09 00:40:27,905][88327] Updated weights for policy 1, policy_version 16480 (0.0010) -[2023-10-09 00:40:28,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 33751040. Throughput: 0: 1690.0, 1: 1690.6. Samples: 8442450. Policy #0 lag: (min: 31.0, avg: 31.7, max: 49.0) -[2023-10-09 00:40:28,975][87372] Avg episode reward: [(0, '4.750'), (1, '4.440')] -[2023-10-09 00:40:30,031][88326] Updated weights for policy 0, policy_version 16482 (0.0009) -[2023-10-09 00:40:30,408][88326] Updated weights for policy 0, policy_version 16492 (0.0010) -[2023-10-09 00:40:30,770][88326] Updated weights for policy 0, policy_version 16502 (0.0008) -[2023-10-09 00:40:31,150][88326] Updated weights for policy 0, policy_version 16512 (0.0009) -[2023-10-09 00:40:31,960][88327] Updated weights for policy 1, policy_version 16490 (0.0008) -[2023-10-09 00:40:32,343][88327] Updated weights for policy 1, policy_version 16500 (0.0009) -[2023-10-09 00:40:32,712][88327] Updated weights for policy 1, policy_version 16510 (0.0009) -[2023-10-09 00:40:33,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 33816576. Throughput: 0: 1714.0, 1: 1674.2. Samples: 8462670. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:40:33,975][87372] Avg episode reward: [(0, '4.600'), (1, '4.380')] -[2023-10-09 00:40:33,987][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000016512_16908288.pth... -[2023-10-09 00:40:33,987][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000016512_16908288.pth... -[2023-10-09 00:40:34,030][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000014944_15302656.pth -[2023-10-09 00:40:34,030][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000014912_15269888.pth -[2023-10-09 00:40:35,167][88326] Updated weights for policy 0, policy_version 16522 (0.0010) -[2023-10-09 00:40:35,540][88326] Updated weights for policy 0, policy_version 16532 (0.0011) -[2023-10-09 00:40:35,903][88326] Updated weights for policy 0, policy_version 16542 (0.0010) -[2023-10-09 00:40:36,862][88327] Updated weights for policy 1, policy_version 16520 (0.0008) -[2023-10-09 00:40:37,234][88327] Updated weights for policy 1, policy_version 16530 (0.0007) -[2023-10-09 00:40:37,617][88327] Updated weights for policy 1, policy_version 16540 (0.0010) -[2023-10-09 00:40:38,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 33882112. Throughput: 0: 1683.4, 1: 1700.2. Samples: 8472774. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:40:38,975][87372] Avg episode reward: [(0, '4.850'), (1, '4.500')] -[2023-10-09 00:40:40,070][88326] Updated weights for policy 0, policy_version 16552 (0.0009) -[2023-10-09 00:40:40,437][88326] Updated weights for policy 0, policy_version 16562 (0.0009) -[2023-10-09 00:40:40,798][88326] Updated weights for policy 0, policy_version 16572 (0.0010) -[2023-10-09 00:40:41,828][88327] Updated weights for policy 1, policy_version 16550 (0.0007) -[2023-10-09 00:40:42,204][88327] Updated weights for policy 1, policy_version 16560 (0.0007) -[2023-10-09 00:40:42,569][88327] Updated weights for policy 1, policy_version 16570 (0.0007) -[2023-10-09 00:40:43,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 33947648. Throughput: 0: 1692.5, 1: 1684.0. Samples: 8492850. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:40:43,975][87372] Avg episode reward: [(0, '4.910'), (1, '4.300')] -[2023-10-09 00:40:44,883][88326] Updated weights for policy 0, policy_version 16582 (0.0009) -[2023-10-09 00:40:45,274][88326] Updated weights for policy 0, policy_version 16592 (0.0007) -[2023-10-09 00:40:45,636][88326] Updated weights for policy 0, policy_version 16602 (0.0010) -[2023-10-09 00:40:46,625][88327] Updated weights for policy 1, policy_version 16580 (0.0009) -[2023-10-09 00:40:47,001][88327] Updated weights for policy 1, policy_version 16590 (0.0007) -[2023-10-09 00:40:47,370][88327] Updated weights for policy 1, policy_version 16600 (0.0007) -[2023-10-09 00:40:48,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 34013184. Throughput: 0: 1711.6, 1: 1672.4. Samples: 8513106. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:40:48,975][87372] Avg episode reward: [(0, '5.670'), (1, '4.160')] -[2023-10-09 00:40:48,988][88088] Saving new best policy, reward=5.670! -[2023-10-09 00:40:49,589][88326] Updated weights for policy 0, policy_version 16612 (0.0009) -[2023-10-09 00:40:49,966][88326] Updated weights for policy 0, policy_version 16622 (0.0007) -[2023-10-09 00:40:50,338][88326] Updated weights for policy 0, policy_version 16632 (0.0009) -[2023-10-09 00:40:51,438][88327] Updated weights for policy 1, policy_version 16610 (0.0009) -[2023-10-09 00:40:51,794][88327] Updated weights for policy 1, policy_version 16620 (0.0011) -[2023-10-09 00:40:52,158][88327] Updated weights for policy 1, policy_version 16630 (0.0008) -[2023-10-09 00:40:52,525][88327] Updated weights for policy 1, policy_version 16640 (0.0009) -[2023-10-09 00:40:53,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 34078720. Throughput: 0: 1680.4, 1: 1690.0. Samples: 8523420. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:40:53,975][87372] Avg episode reward: [(0, '5.200'), (1, '4.550')] -[2023-10-09 00:40:54,321][88326] Updated weights for policy 0, policy_version 16642 (0.0008) -[2023-10-09 00:40:54,690][88326] Updated weights for policy 0, policy_version 16652 (0.0009) -[2023-10-09 00:40:55,067][88326] Updated weights for policy 0, policy_version 16662 (0.0010) -[2023-10-09 00:40:55,426][88326] Updated weights for policy 0, policy_version 16672 (0.0010) -[2023-10-09 00:40:56,625][88327] Updated weights for policy 1, policy_version 16650 (0.0010) -[2023-10-09 00:40:56,996][88327] Updated weights for policy 1, policy_version 16660 (0.0008) -[2023-10-09 00:40:57,370][88327] Updated weights for policy 1, policy_version 16670 (0.0007) -[2023-10-09 00:40:58,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 34144256. Throughput: 0: 1708.5, 1: 1672.5. Samples: 8543642. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:40:58,975][87372] Avg episode reward: [(0, '5.430'), (1, '4.480')] -[2023-10-09 00:40:59,548][88326] Updated weights for policy 0, policy_version 16682 (0.0008) -[2023-10-09 00:40:59,916][88326] Updated weights for policy 0, policy_version 16692 (0.0008) -[2023-10-09 00:41:00,286][88326] Updated weights for policy 0, policy_version 16702 (0.0008) -[2023-10-09 00:41:01,187][88327] Updated weights for policy 1, policy_version 16680 (0.0007) -[2023-10-09 00:41:01,554][88327] Updated weights for policy 1, policy_version 16690 (0.0007) -[2023-10-09 00:41:01,916][88327] Updated weights for policy 1, policy_version 16700 (0.0008) -[2023-10-09 00:41:03,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 34209792. Throughput: 0: 1703.6, 1: 1693.1. Samples: 8564320. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-09 00:41:03,975][87372] Avg episode reward: [(0, '5.350'), (1, '4.670')] -[2023-10-09 00:41:04,451][88326] Updated weights for policy 0, policy_version 16712 (0.0010) -[2023-10-09 00:41:04,828][88326] Updated weights for policy 0, policy_version 16722 (0.0010) -[2023-10-09 00:41:05,199][88326] Updated weights for policy 0, policy_version 16732 (0.0008) -[2023-10-09 00:41:05,783][88327] Updated weights for policy 1, policy_version 16710 (0.0010) -[2023-10-09 00:41:06,156][88327] Updated weights for policy 1, policy_version 16720 (0.0010) -[2023-10-09 00:41:06,527][88327] Updated weights for policy 1, policy_version 16730 (0.0009) -[2023-10-09 00:41:08,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 34275328. Throughput: 0: 1690.6, 1: 1692.5. Samples: 8574304. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-09 00:41:08,974][87372] Avg episode reward: [(0, '4.820'), (1, '4.260')] -[2023-10-09 00:41:09,325][88326] Updated weights for policy 0, policy_version 16742 (0.0009) -[2023-10-09 00:41:09,688][88326] Updated weights for policy 0, policy_version 16752 (0.0009) -[2023-10-09 00:41:10,069][88326] Updated weights for policy 0, policy_version 16762 (0.0009) -[2023-10-09 00:41:10,483][88327] Updated weights for policy 1, policy_version 16740 (0.0009) -[2023-10-09 00:41:10,847][88327] Updated weights for policy 1, policy_version 16750 (0.0008) -[2023-10-09 00:41:11,224][88327] Updated weights for policy 1, policy_version 16760 (0.0008) -[2023-10-09 00:41:13,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 34340864. Throughput: 0: 1692.4, 1: 1685.7. Samples: 8594466. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-09 00:41:13,975][87372] Avg episode reward: [(0, '5.160'), (1, '4.590')] -[2023-10-09 00:41:14,235][88326] Updated weights for policy 0, policy_version 16772 (0.0007) -[2023-10-09 00:41:14,595][88326] Updated weights for policy 0, policy_version 16782 (0.0008) -[2023-10-09 00:41:14,967][88326] Updated weights for policy 0, policy_version 16792 (0.0009) -[2023-10-09 00:41:15,188][88327] Updated weights for policy 1, policy_version 16770 (0.0008) -[2023-10-09 00:41:15,555][88327] Updated weights for policy 1, policy_version 16780 (0.0009) -[2023-10-09 00:41:15,917][88327] Updated weights for policy 1, policy_version 16790 (0.0010) -[2023-10-09 00:41:16,287][88327] Updated weights for policy 1, policy_version 16800 (0.0008) -[2023-10-09 00:41:18,943][88326] Updated weights for policy 0, policy_version 16802 (0.0007) -[2023-10-09 00:41:18,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 34406400. Throughput: 0: 1690.4, 1: 1710.2. Samples: 8615696. Policy #0 lag: (min: 29.0, avg: 29.9, max: 50.0) -[2023-10-09 00:41:18,975][87372] Avg episode reward: [(0, '5.440'), (1, '4.600')] -[2023-10-09 00:41:19,321][88326] Updated weights for policy 0, policy_version 16812 (0.0008) -[2023-10-09 00:41:19,699][88326] Updated weights for policy 0, policy_version 16822 (0.0007) -[2023-10-09 00:41:20,061][88326] Updated weights for policy 0, policy_version 16832 (0.0007) -[2023-10-09 00:41:20,237][88327] Updated weights for policy 1, policy_version 16810 (0.0010) -[2023-10-09 00:41:20,602][88327] Updated weights for policy 1, policy_version 16820 (0.0008) -[2023-10-09 00:41:20,974][88327] Updated weights for policy 1, policy_version 16830 (0.0008) -[2023-10-09 00:41:23,728][88326] Updated weights for policy 0, policy_version 16842 (0.0008) -[2023-10-09 00:41:23,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 34471936. Throughput: 0: 1693.7, 1: 1684.6. Samples: 8624800. Policy #0 lag: (min: 29.0, avg: 29.9, max: 50.0) -[2023-10-09 00:41:23,975][87372] Avg episode reward: [(0, '5.010'), (1, '4.360')] -[2023-10-09 00:41:24,095][88326] Updated weights for policy 0, policy_version 16852 (0.0009) -[2023-10-09 00:41:24,469][88326] Updated weights for policy 0, policy_version 16862 (0.0008) -[2023-10-09 00:41:25,029][88327] Updated weights for policy 1, policy_version 16840 (0.0008) -[2023-10-09 00:41:25,393][88327] Updated weights for policy 1, policy_version 16850 (0.0010) -[2023-10-09 00:41:25,756][88327] Updated weights for policy 1, policy_version 16860 (0.0010) -[2023-10-09 00:41:28,440][88326] Updated weights for policy 0, policy_version 16872 (0.0009) -[2023-10-09 00:41:28,808][88326] Updated weights for policy 0, policy_version 16882 (0.0008) -[2023-10-09 00:41:28,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 34537472. Throughput: 0: 1702.6, 1: 1695.3. Samples: 8645756. Policy #0 lag: (min: 29.0, avg: 29.9, max: 50.0) -[2023-10-09 00:41:28,975][87372] Avg episode reward: [(0, '5.100'), (1, '4.550')] -[2023-10-09 00:41:29,179][88326] Updated weights for policy 0, policy_version 16892 (0.0011) -[2023-10-09 00:41:29,730][88327] Updated weights for policy 1, policy_version 16870 (0.0007) -[2023-10-09 00:41:30,092][88327] Updated weights for policy 1, policy_version 16880 (0.0008) -[2023-10-09 00:41:30,466][88327] Updated weights for policy 1, policy_version 16890 (0.0010) -[2023-10-09 00:41:33,322][88326] Updated weights for policy 0, policy_version 16902 (0.0009) -[2023-10-09 00:41:33,694][88326] Updated weights for policy 0, policy_version 16912 (0.0010) -[2023-10-09 00:41:33,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 34603008. Throughput: 0: 1693.4, 1: 1715.4. Samples: 8666502. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) -[2023-10-09 00:41:33,975][87372] Avg episode reward: [(0, '5.170'), (1, '4.580')] -[2023-10-09 00:41:34,070][88326] Updated weights for policy 0, policy_version 16922 (0.0009) -[2023-10-09 00:41:34,513][88327] Updated weights for policy 1, policy_version 16900 (0.0008) -[2023-10-09 00:41:34,882][88327] Updated weights for policy 1, policy_version 16910 (0.0007) -[2023-10-09 00:41:35,239][88327] Updated weights for policy 1, policy_version 16920 (0.0008) -[2023-10-09 00:41:38,090][88326] Updated weights for policy 0, policy_version 16932 (0.0010) -[2023-10-09 00:41:38,464][88326] Updated weights for policy 0, policy_version 16942 (0.0008) -[2023-10-09 00:41:38,837][88326] Updated weights for policy 0, policy_version 16952 (0.0009) -[2023-10-09 00:41:38,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 34668544. Throughput: 0: 1697.8, 1: 1691.6. Samples: 8675942. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) -[2023-10-09 00:41:38,975][87372] Avg episode reward: [(0, '4.810'), (1, '4.670')] -[2023-10-09 00:41:39,307][88327] Updated weights for policy 1, policy_version 16930 (0.0009) -[2023-10-09 00:41:39,668][88327] Updated weights for policy 1, policy_version 16940 (0.0007) -[2023-10-09 00:41:40,028][88327] Updated weights for policy 1, policy_version 16950 (0.0008) -[2023-10-09 00:41:40,393][88327] Updated weights for policy 1, policy_version 16960 (0.0011) -[2023-10-09 00:41:43,008][88326] Updated weights for policy 0, policy_version 16962 (0.0010) -[2023-10-09 00:41:43,381][88326] Updated weights for policy 0, policy_version 16972 (0.0009) -[2023-10-09 00:41:43,744][88326] Updated weights for policy 0, policy_version 16982 (0.0011) -[2023-10-09 00:41:43,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 34734080. Throughput: 0: 1690.9, 1: 1713.4. Samples: 8696836. Policy #0 lag: (min: 31.0, avg: 34.8, max: 63.0) -[2023-10-09 00:41:43,975][87372] Avg episode reward: [(0, '5.040'), (1, '4.920')] -[2023-10-09 00:41:44,105][88326] Updated weights for policy 0, policy_version 16992 (0.0010) -[2023-10-09 00:41:44,414][88327] Updated weights for policy 1, policy_version 16970 (0.0008) -[2023-10-09 00:41:44,786][88327] Updated weights for policy 1, policy_version 16980 (0.0010) -[2023-10-09 00:41:45,151][88327] Updated weights for policy 1, policy_version 16990 (0.0008) -[2023-10-09 00:41:48,132][88326] Updated weights for policy 0, policy_version 17002 (0.0007) -[2023-10-09 00:41:48,500][88326] Updated weights for policy 0, policy_version 17012 (0.0007) -[2023-10-09 00:41:48,876][88326] Updated weights for policy 0, policy_version 17022 (0.0008) -[2023-10-09 00:41:48,974][87372] Fps is (10 sec: 16384.0, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 34832384. Throughput: 0: 1685.7, 1: 1713.7. Samples: 8717296. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:41:48,975][87372] Avg episode reward: [(0, '4.750'), (1, '4.790')] -[2023-10-09 00:41:49,290][88327] Updated weights for policy 1, policy_version 17000 (0.0010) -[2023-10-09 00:41:49,664][88327] Updated weights for policy 1, policy_version 17010 (0.0008) -[2023-10-09 00:41:50,028][88327] Updated weights for policy 1, policy_version 17020 (0.0008) -[2023-10-09 00:41:52,985][88326] Updated weights for policy 0, policy_version 17032 (0.0009) -[2023-10-09 00:41:53,353][88326] Updated weights for policy 0, policy_version 17042 (0.0008) -[2023-10-09 00:41:53,720][88326] Updated weights for policy 0, policy_version 17052 (0.0009) -[2023-10-09 00:41:53,967][88327] Updated weights for policy 1, policy_version 17030 (0.0009) -[2023-10-09 00:41:53,974][87372] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 34897920. Throughput: 0: 1698.5, 1: 1695.6. Samples: 8727042. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:41:53,975][87372] Avg episode reward: [(0, '5.040'), (1, '4.540')] -[2023-10-09 00:41:54,337][88327] Updated weights for policy 1, policy_version 17040 (0.0008) -[2023-10-09 00:41:54,705][88327] Updated weights for policy 1, policy_version 17050 (0.0008) -[2023-10-09 00:41:57,659][88326] Updated weights for policy 0, policy_version 17062 (0.0008) -[2023-10-09 00:41:58,031][88326] Updated weights for policy 0, policy_version 17072 (0.0008) -[2023-10-09 00:41:58,406][88326] Updated weights for policy 0, policy_version 17082 (0.0008) -[2023-10-09 00:41:58,764][88327] Updated weights for policy 1, policy_version 17060 (0.0007) -[2023-10-09 00:41:58,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 34963456. Throughput: 0: 1703.0, 1: 1713.5. Samples: 8748210. Policy #0 lag: (min: 31.0, avg: 31.1, max: 38.0) -[2023-10-09 00:41:58,975][87372] Avg episode reward: [(0, '5.310'), (1, '4.500')] -[2023-10-09 00:41:59,133][88327] Updated weights for policy 1, policy_version 17070 (0.0008) -[2023-10-09 00:41:59,503][88327] Updated weights for policy 1, policy_version 17080 (0.0008) -[2023-10-09 00:42:02,403][88326] Updated weights for policy 0, policy_version 17092 (0.0010) -[2023-10-09 00:42:02,770][88326] Updated weights for policy 0, policy_version 17102 (0.0010) -[2023-10-09 00:42:03,135][88326] Updated weights for policy 0, policy_version 17112 (0.0008) -[2023-10-09 00:42:03,423][88327] Updated weights for policy 1, policy_version 17090 (0.0009) -[2023-10-09 00:42:03,796][88327] Updated weights for policy 1, policy_version 17100 (0.0007) -[2023-10-09 00:42:03,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 35028992. Throughput: 0: 1678.5, 1: 1706.8. Samples: 8768036. Policy #0 lag: (min: 31.0, avg: 31.1, max: 38.0) -[2023-10-09 00:42:03,975][87372] Avg episode reward: [(0, '5.300'), (1, '4.100')] -[2023-10-09 00:42:04,166][88327] Updated weights for policy 1, policy_version 17110 (0.0007) -[2023-10-09 00:42:04,527][88327] Updated weights for policy 1, policy_version 17120 (0.0007) -[2023-10-09 00:42:06,981][88326] Updated weights for policy 0, policy_version 17122 (0.0007) -[2023-10-09 00:42:07,351][88326] Updated weights for policy 0, policy_version 17132 (0.0008) -[2023-10-09 00:42:07,726][88326] Updated weights for policy 0, policy_version 17142 (0.0010) -[2023-10-09 00:42:08,088][88326] Updated weights for policy 0, policy_version 17152 (0.0009) -[2023-10-09 00:42:08,570][88327] Updated weights for policy 1, policy_version 17130 (0.0009) -[2023-10-09 00:42:08,944][88327] Updated weights for policy 1, policy_version 17140 (0.0008) -[2023-10-09 00:42:08,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 35094528. Throughput: 0: 1705.1, 1: 1706.9. Samples: 8778340. Policy #0 lag: (min: 31.0, avg: 31.1, max: 38.0) -[2023-10-09 00:42:08,974][87372] Avg episode reward: [(0, '5.770'), (1, '4.210')] -[2023-10-09 00:42:08,975][88088] Saving new best policy, reward=5.770! -[2023-10-09 00:42:09,321][88327] Updated weights for policy 1, policy_version 17150 (0.0009) -[2023-10-09 00:42:12,222][88326] Updated weights for policy 0, policy_version 17162 (0.0007) -[2023-10-09 00:42:12,577][88326] Updated weights for policy 0, policy_version 17172 (0.0007) -[2023-10-09 00:42:12,948][88326] Updated weights for policy 0, policy_version 17182 (0.0008) -[2023-10-09 00:42:13,188][88327] Updated weights for policy 1, policy_version 17160 (0.0008) -[2023-10-09 00:42:13,556][88327] Updated weights for policy 1, policy_version 17170 (0.0010) -[2023-10-09 00:42:13,920][88327] Updated weights for policy 1, policy_version 17180 (0.0009) -[2023-10-09 00:42:13,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 35160064. Throughput: 0: 1691.8, 1: 1705.1. Samples: 8798618. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-09 00:42:13,975][87372] Avg episode reward: [(0, '5.370'), (1, '4.580')] -[2023-10-09 00:42:16,945][88326] Updated weights for policy 0, policy_version 17192 (0.0008) -[2023-10-09 00:42:17,318][88326] Updated weights for policy 0, policy_version 17202 (0.0009) -[2023-10-09 00:42:17,689][88326] Updated weights for policy 0, policy_version 17212 (0.0008) -[2023-10-09 00:42:18,116][88327] Updated weights for policy 1, policy_version 17190 (0.0008) -[2023-10-09 00:42:18,483][88327] Updated weights for policy 1, policy_version 17200 (0.0009) -[2023-10-09 00:42:18,851][88327] Updated weights for policy 1, policy_version 17210 (0.0008) -[2023-10-09 00:42:18,974][87372] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 35225600. Throughput: 0: 1675.4, 1: 1701.8. Samples: 8818478. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-09 00:42:18,975][87372] Avg episode reward: [(0, '5.650'), (1, '4.450')] -[2023-10-09 00:42:21,835][88326] Updated weights for policy 0, policy_version 17222 (0.0010) -[2023-10-09 00:42:22,216][88326] Updated weights for policy 0, policy_version 17232 (0.0008) -[2023-10-09 00:42:22,586][88326] Updated weights for policy 0, policy_version 17242 (0.0008) -[2023-10-09 00:42:22,909][88327] Updated weights for policy 1, policy_version 17220 (0.0007) -[2023-10-09 00:42:23,270][88327] Updated weights for policy 1, policy_version 17230 (0.0009) -[2023-10-09 00:42:23,638][88327] Updated weights for policy 1, policy_version 17240 (0.0008) -[2023-10-09 00:42:23,974][87372] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 35323904. Throughput: 0: 1702.4, 1: 1702.8. Samples: 8829172. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-09 00:42:23,974][87372] Avg episode reward: [(0, '6.020'), (1, '4.550')] -[2023-10-09 00:42:23,975][88088] Saving new best policy, reward=6.020! -[2023-10-09 00:42:26,735][88326] Updated weights for policy 0, policy_version 17252 (0.0008) -[2023-10-09 00:42:27,094][88326] Updated weights for policy 0, policy_version 17262 (0.0008) -[2023-10-09 00:42:27,463][88326] Updated weights for policy 0, policy_version 17272 (0.0008) -[2023-10-09 00:42:27,744][88327] Updated weights for policy 1, policy_version 17250 (0.0009) -[2023-10-09 00:42:28,116][88327] Updated weights for policy 1, policy_version 17260 (0.0009) -[2023-10-09 00:42:28,478][88327] Updated weights for policy 1, policy_version 17270 (0.0010) -[2023-10-09 00:42:28,840][88327] Updated weights for policy 1, policy_version 17280 (0.0009) -[2023-10-09 00:42:28,974][87372] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 35389440. Throughput: 0: 1689.4, 1: 1695.6. Samples: 8849160. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:42:28,975][87372] Avg episode reward: [(0, '4.960'), (1, '4.560')] -[2023-10-09 00:42:31,462][88326] Updated weights for policy 0, policy_version 17282 (0.0008) -[2023-10-09 00:42:31,824][88326] Updated weights for policy 0, policy_version 17292 (0.0010) -[2023-10-09 00:42:32,191][88326] Updated weights for policy 0, policy_version 17302 (0.0010) -[2023-10-09 00:42:32,566][88326] Updated weights for policy 0, policy_version 17312 (0.0007) -[2023-10-09 00:42:32,905][88327] Updated weights for policy 1, policy_version 17290 (0.0010) -[2023-10-09 00:42:33,279][88327] Updated weights for policy 1, policy_version 17300 (0.0008) -[2023-10-09 00:42:33,644][88327] Updated weights for policy 1, policy_version 17310 (0.0009) -[2023-10-09 00:42:33,974][87372] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 35454976. Throughput: 0: 1683.5, 1: 1686.8. Samples: 8868958. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:42:33,975][87372] Avg episode reward: [(0, '5.190'), (1, '4.710')] -[2023-10-09 00:42:33,983][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000017312_17727488.pth... -[2023-10-09 00:42:33,983][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000017312_17727488.pth... -[2023-10-09 00:42:34,013][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000015712_16089088.pth -[2023-10-09 00:42:34,024][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000015712_16089088.pth -[2023-10-09 00:42:36,583][88326] Updated weights for policy 0, policy_version 17322 (0.0007) -[2023-10-09 00:42:36,949][88326] Updated weights for policy 0, policy_version 17332 (0.0007) -[2023-10-09 00:42:37,324][88326] Updated weights for policy 0, policy_version 17342 (0.0007) -[2023-10-09 00:42:37,740][88327] Updated weights for policy 1, policy_version 17320 (0.0009) -[2023-10-09 00:42:38,118][88327] Updated weights for policy 1, policy_version 17330 (0.0009) -[2023-10-09 00:42:38,484][88327] Updated weights for policy 1, policy_version 17340 (0.0007) -[2023-10-09 00:42:38,974][87372] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 35520512. Throughput: 0: 1702.6, 1: 1695.5. Samples: 8879956. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:42:38,975][87372] Avg episode reward: [(0, '5.180'), (1, '4.760')] -[2023-10-09 00:42:41,233][88326] Updated weights for policy 0, policy_version 17352 (0.0009) -[2023-10-09 00:42:41,600][88326] Updated weights for policy 0, policy_version 17362 (0.0011) -[2023-10-09 00:42:41,965][88326] Updated weights for policy 0, policy_version 17372 (0.0009) -[2023-10-09 00:42:42,451][88327] Updated weights for policy 1, policy_version 17350 (0.0010) -[2023-10-09 00:42:42,819][88327] Updated weights for policy 1, policy_version 17360 (0.0011) -[2023-10-09 00:42:43,190][88327] Updated weights for policy 1, policy_version 17370 (0.0011) -[2023-10-09 00:42:43,974][87372] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 35586048. Throughput: 0: 1672.1, 1: 1694.5. Samples: 8899706. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-10-09 00:42:43,975][87372] Avg episode reward: [(0, '4.720'), (1, '5.080')] -[2023-10-09 00:42:46,073][88326] Updated weights for policy 0, policy_version 17382 (0.0007) -[2023-10-09 00:42:46,443][88326] Updated weights for policy 0, policy_version 17392 (0.0007) -[2023-10-09 00:42:46,812][88326] Updated weights for policy 0, policy_version 17402 (0.0009) -[2023-10-09 00:42:47,325][88327] Updated weights for policy 1, policy_version 17380 (0.0010) -[2023-10-09 00:42:47,678][88327] Updated weights for policy 1, policy_version 17390 (0.0008) -[2023-10-09 00:42:48,049][88327] Updated weights for policy 1, policy_version 17400 (0.0010) -[2023-10-09 00:42:48,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 35651584. Throughput: 0: 1694.4, 1: 1668.1. Samples: 8919348. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-10-09 00:42:48,975][87372] Avg episode reward: [(0, '5.420'), (1, '5.060')] -[2023-10-09 00:42:50,865][88326] Updated weights for policy 0, policy_version 17412 (0.0008) -[2023-10-09 00:42:51,229][88326] Updated weights for policy 0, policy_version 17422 (0.0008) -[2023-10-09 00:42:51,586][88326] Updated weights for policy 0, policy_version 17432 (0.0008) -[2023-10-09 00:42:52,012][88327] Updated weights for policy 1, policy_version 17410 (0.0008) -[2023-10-09 00:42:52,368][88327] Updated weights for policy 1, policy_version 17420 (0.0008) -[2023-10-09 00:42:52,730][88327] Updated weights for policy 1, policy_version 17430 (0.0009) -[2023-10-09 00:42:53,103][88327] Updated weights for policy 1, policy_version 17440 (0.0007) -[2023-10-09 00:42:53,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 35717120. Throughput: 0: 1682.2, 1: 1693.6. Samples: 8930248. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-10-09 00:42:53,975][87372] Avg episode reward: [(0, '5.280'), (1, '4.900')] -[2023-10-09 00:42:55,493][88326] Updated weights for policy 0, policy_version 17442 (0.0008) -[2023-10-09 00:42:55,864][88326] Updated weights for policy 0, policy_version 17452 (0.0011) -[2023-10-09 00:42:56,243][88326] Updated weights for policy 0, policy_version 17462 (0.0009) -[2023-10-09 00:42:56,610][88326] Updated weights for policy 0, policy_version 17472 (0.0009) -[2023-10-09 00:42:57,171][88327] Updated weights for policy 1, policy_version 17450 (0.0010) -[2023-10-09 00:42:57,535][88327] Updated weights for policy 1, policy_version 17460 (0.0007) -[2023-10-09 00:42:57,912][88327] Updated weights for policy 1, policy_version 17470 (0.0009) -[2023-10-09 00:42:58,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 35782656. Throughput: 0: 1675.2, 1: 1689.9. Samples: 8950046. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-09 00:42:58,975][87372] Avg episode reward: [(0, '5.340'), (1, '4.700')] -[2023-10-09 00:43:00,622][88326] Updated weights for policy 0, policy_version 17482 (0.0010) -[2023-10-09 00:43:00,975][88326] Updated weights for policy 0, policy_version 17492 (0.0010) -[2023-10-09 00:43:01,348][88326] Updated weights for policy 0, policy_version 17502 (0.0007) -[2023-10-09 00:43:01,937][88327] Updated weights for policy 1, policy_version 17480 (0.0009) -[2023-10-09 00:43:02,299][88327] Updated weights for policy 1, policy_version 17490 (0.0010) -[2023-10-09 00:43:02,669][88327] Updated weights for policy 1, policy_version 17500 (0.0007) -[2023-10-09 00:43:03,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 35848192. Throughput: 0: 1701.5, 1: 1669.0. Samples: 8970152. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-09 00:43:03,975][87372] Avg episode reward: [(0, '4.910'), (1, '4.660')] -[2023-10-09 00:43:05,389][88326] Updated weights for policy 0, policy_version 17512 (0.0007) -[2023-10-09 00:43:05,764][88326] Updated weights for policy 0, policy_version 17522 (0.0011) -[2023-10-09 00:43:06,134][88326] Updated weights for policy 0, policy_version 17532 (0.0012) -[2023-10-09 00:43:06,799][88327] Updated weights for policy 1, policy_version 17510 (0.0007) -[2023-10-09 00:43:07,169][88327] Updated weights for policy 1, policy_version 17520 (0.0008) -[2023-10-09 00:43:07,540][88327] Updated weights for policy 1, policy_version 17530 (0.0009) -[2023-10-09 00:43:08,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 35913728. Throughput: 0: 1672.7, 1: 1693.6. Samples: 8980656. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-09 00:43:08,975][87372] Avg episode reward: [(0, '4.630'), (1, '4.740')] -[2023-10-09 00:43:10,250][88326] Updated weights for policy 0, policy_version 17542 (0.0008) -[2023-10-09 00:43:10,623][88326] Updated weights for policy 0, policy_version 17552 (0.0009) -[2023-10-09 00:43:10,989][88326] Updated weights for policy 0, policy_version 17562 (0.0008) -[2023-10-09 00:43:11,546][88327] Updated weights for policy 1, policy_version 17540 (0.0010) -[2023-10-09 00:43:11,907][88327] Updated weights for policy 1, policy_version 17550 (0.0009) -[2023-10-09 00:43:12,283][88327] Updated weights for policy 1, policy_version 17560 (0.0008) -[2023-10-09 00:43:13,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 35979264. Throughput: 0: 1686.3, 1: 1679.1. Samples: 9000606. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-09 00:43:13,975][87372] Avg episode reward: [(0, '4.840'), (1, '4.960')] -[2023-10-09 00:43:15,129][88326] Updated weights for policy 0, policy_version 17572 (0.0008) -[2023-10-09 00:43:15,530][88326] Updated weights for policy 0, policy_version 17582 (0.0009) -[2023-10-09 00:43:15,897][88326] Updated weights for policy 0, policy_version 17592 (0.0010) -[2023-10-09 00:43:16,356][88327] Updated weights for policy 1, policy_version 17570 (0.0008) -[2023-10-09 00:43:16,728][88327] Updated weights for policy 1, policy_version 17580 (0.0011) -[2023-10-09 00:43:17,103][88327] Updated weights for policy 1, policy_version 17590 (0.0010) -[2023-10-09 00:43:17,463][88327] Updated weights for policy 1, policy_version 17600 (0.0009) -[2023-10-09 00:43:18,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 36044800. Throughput: 0: 1698.7, 1: 1674.9. Samples: 9020770. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-09 00:43:18,975][87372] Avg episode reward: [(0, '4.650'), (1, '4.900')] -[2023-10-09 00:43:19,910][88326] Updated weights for policy 0, policy_version 17602 (0.0008) -[2023-10-09 00:43:20,278][88326] Updated weights for policy 0, policy_version 17612 (0.0008) -[2023-10-09 00:43:20,646][88326] Updated weights for policy 0, policy_version 17622 (0.0009) -[2023-10-09 00:43:21,016][88326] Updated weights for policy 0, policy_version 17632 (0.0007) -[2023-10-09 00:43:21,458][88327] Updated weights for policy 1, policy_version 17610 (0.0007) -[2023-10-09 00:43:21,827][88327] Updated weights for policy 1, policy_version 17620 (0.0007) -[2023-10-09 00:43:22,194][88327] Updated weights for policy 1, policy_version 17630 (0.0010) -[2023-10-09 00:43:23,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 36110336. Throughput: 0: 1668.6, 1: 1691.6. Samples: 9031162. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-09 00:43:23,974][87372] Avg episode reward: [(0, '5.460'), (1, '5.130')] -[2023-10-09 00:43:24,993][88326] Updated weights for policy 0, policy_version 17642 (0.0010) -[2023-10-09 00:43:25,357][88326] Updated weights for policy 0, policy_version 17652 (0.0007) -[2023-10-09 00:43:25,726][88326] Updated weights for policy 0, policy_version 17662 (0.0008) -[2023-10-09 00:43:26,111][88327] Updated weights for policy 1, policy_version 17640 (0.0010) -[2023-10-09 00:43:26,472][88327] Updated weights for policy 1, policy_version 17650 (0.0009) -[2023-10-09 00:43:26,841][88327] Updated weights for policy 1, policy_version 17660 (0.0009) -[2023-10-09 00:43:28,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 36175872. Throughput: 0: 1697.8, 1: 1665.1. Samples: 9051036. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:43:28,975][87372] Avg episode reward: [(0, '5.160'), (1, '5.100')] -[2023-10-09 00:43:29,715][88326] Updated weights for policy 0, policy_version 17672 (0.0009) -[2023-10-09 00:43:30,085][88326] Updated weights for policy 0, policy_version 17682 (0.0009) -[2023-10-09 00:43:30,460][88326] Updated weights for policy 0, policy_version 17692 (0.0010) -[2023-10-09 00:43:30,873][88327] Updated weights for policy 1, policy_version 17670 (0.0008) -[2023-10-09 00:43:31,240][88327] Updated weights for policy 1, policy_version 17680 (0.0008) -[2023-10-09 00:43:31,601][88327] Updated weights for policy 1, policy_version 17690 (0.0008) -[2023-10-09 00:43:33,974][87372] Fps is (10 sec: 13106.8, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 36241408. Throughput: 0: 1700.0, 1: 1695.6. Samples: 9072150. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:43:33,975][87372] Avg episode reward: [(0, '5.070'), (1, '5.110')] -[2023-10-09 00:43:34,529][88326] Updated weights for policy 0, policy_version 17702 (0.0010) -[2023-10-09 00:43:34,903][88326] Updated weights for policy 0, policy_version 17712 (0.0010) -[2023-10-09 00:43:35,263][88326] Updated weights for policy 0, policy_version 17722 (0.0008) -[2023-10-09 00:43:35,582][88327] Updated weights for policy 1, policy_version 17700 (0.0008) -[2023-10-09 00:43:35,951][88327] Updated weights for policy 1, policy_version 17710 (0.0009) -[2023-10-09 00:43:36,317][88327] Updated weights for policy 1, policy_version 17720 (0.0009) -[2023-10-09 00:43:38,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 36306944. Throughput: 0: 1685.4, 1: 1686.0. Samples: 9081960. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:43:38,975][87372] Avg episode reward: [(0, '5.180'), (1, '5.120')] -[2023-10-09 00:43:39,186][88326] Updated weights for policy 0, policy_version 17732 (0.0008) -[2023-10-09 00:43:39,563][88326] Updated weights for policy 0, policy_version 17742 (0.0008) -[2023-10-09 00:43:39,934][88326] Updated weights for policy 0, policy_version 17752 (0.0008) -[2023-10-09 00:43:40,319][88327] Updated weights for policy 1, policy_version 17730 (0.0009) -[2023-10-09 00:43:40,676][88327] Updated weights for policy 1, policy_version 17740 (0.0008) -[2023-10-09 00:43:41,045][88327] Updated weights for policy 1, policy_version 17750 (0.0010) -[2023-10-09 00:43:41,415][88327] Updated weights for policy 1, policy_version 17760 (0.0009) -[2023-10-09 00:43:43,864][88326] Updated weights for policy 0, policy_version 17762 (0.0008) -[2023-10-09 00:43:43,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 36372480. Throughput: 0: 1704.5, 1: 1681.7. Samples: 9102428. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:43:43,975][87372] Avg episode reward: [(0, '4.990'), (1, '5.050')] -[2023-10-09 00:43:44,240][88326] Updated weights for policy 0, policy_version 17772 (0.0010) -[2023-10-09 00:43:44,614][88326] Updated weights for policy 0, policy_version 17782 (0.0010) -[2023-10-09 00:43:44,975][88326] Updated weights for policy 0, policy_version 17792 (0.0010) -[2023-10-09 00:43:45,617][88327] Updated weights for policy 1, policy_version 17770 (0.0009) -[2023-10-09 00:43:45,986][88327] Updated weights for policy 1, policy_version 17780 (0.0008) -[2023-10-09 00:43:46,356][88327] Updated weights for policy 1, policy_version 17790 (0.0009) -[2023-10-09 00:43:48,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 36438016. Throughput: 0: 1701.9, 1: 1701.7. Samples: 9123314. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:43:48,975][87372] Avg episode reward: [(0, '4.870'), (1, '5.000')] -[2023-10-09 00:43:48,983][88326] Updated weights for policy 0, policy_version 17802 (0.0009) -[2023-10-09 00:43:49,354][88326] Updated weights for policy 0, policy_version 17812 (0.0008) -[2023-10-09 00:43:49,717][88326] Updated weights for policy 0, policy_version 17822 (0.0008) -[2023-10-09 00:43:50,317][88327] Updated weights for policy 1, policy_version 17800 (0.0010) -[2023-10-09 00:43:50,668][88327] Updated weights for policy 1, policy_version 17810 (0.0009) -[2023-10-09 00:43:51,036][88327] Updated weights for policy 1, policy_version 17820 (0.0010) -[2023-10-09 00:43:53,727][88326] Updated weights for policy 0, policy_version 17832 (0.0011) -[2023-10-09 00:43:53,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 36503552. Throughput: 0: 1698.8, 1: 1676.1. Samples: 9132522. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:43:53,974][87372] Avg episode reward: [(0, '4.890'), (1, '5.020')] -[2023-10-09 00:43:54,094][88326] Updated weights for policy 0, policy_version 17842 (0.0009) -[2023-10-09 00:43:54,452][88326] Updated weights for policy 0, policy_version 17852 (0.0011) -[2023-10-09 00:43:54,963][88327] Updated weights for policy 1, policy_version 17830 (0.0008) -[2023-10-09 00:43:55,330][88327] Updated weights for policy 1, policy_version 17840 (0.0009) -[2023-10-09 00:43:55,692][88327] Updated weights for policy 1, policy_version 17850 (0.0010) -[2023-10-09 00:43:58,563][88326] Updated weights for policy 0, policy_version 17862 (0.0009) -[2023-10-09 00:43:58,932][88326] Updated weights for policy 0, policy_version 17872 (0.0010) -[2023-10-09 00:43:58,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 36569088. Throughput: 0: 1700.4, 1: 1694.5. Samples: 9153376. Policy #0 lag: (min: 1.0, avg: 13.6, max: 33.0) -[2023-10-09 00:43:58,975][87372] Avg episode reward: [(0, '4.960'), (1, '5.050')] -[2023-10-09 00:43:59,310][88326] Updated weights for policy 0, policy_version 17882 (0.0009) -[2023-10-09 00:43:59,806][88327] Updated weights for policy 1, policy_version 17860 (0.0011) -[2023-10-09 00:44:00,174][88327] Updated weights for policy 1, policy_version 17870 (0.0010) -[2023-10-09 00:44:00,546][88327] Updated weights for policy 1, policy_version 17880 (0.0009) -[2023-10-09 00:44:03,505][88326] Updated weights for policy 0, policy_version 17892 (0.0009) -[2023-10-09 00:44:03,899][88326] Updated weights for policy 0, policy_version 17902 (0.0008) -[2023-10-09 00:44:03,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 36634624. Throughput: 0: 1701.8, 1: 1707.5. Samples: 9174188. Policy #0 lag: (min: 1.0, avg: 13.6, max: 33.0) -[2023-10-09 00:44:03,975][87372] Avg episode reward: [(0, '4.810'), (1, '4.710')] -[2023-10-09 00:44:04,260][88326] Updated weights for policy 0, policy_version 17912 (0.0008) -[2023-10-09 00:44:04,565][88327] Updated weights for policy 1, policy_version 17890 (0.0009) -[2023-10-09 00:44:04,930][88327] Updated weights for policy 1, policy_version 17900 (0.0010) -[2023-10-09 00:44:05,299][88327] Updated weights for policy 1, policy_version 17910 (0.0009) -[2023-10-09 00:44:05,661][88327] Updated weights for policy 1, policy_version 17920 (0.0009) -[2023-10-09 00:44:08,281][88326] Updated weights for policy 0, policy_version 17922 (0.0008) -[2023-10-09 00:44:08,659][88326] Updated weights for policy 0, policy_version 17932 (0.0007) -[2023-10-09 00:44:08,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 36700160. Throughput: 0: 1700.4, 1: 1679.8. Samples: 9183272. Policy #0 lag: (min: 1.0, avg: 13.6, max: 33.0) -[2023-10-09 00:44:08,975][87372] Avg episode reward: [(0, '4.730'), (1, '4.530')] -[2023-10-09 00:44:09,027][88326] Updated weights for policy 0, policy_version 17942 (0.0009) -[2023-10-09 00:44:09,397][88326] Updated weights for policy 0, policy_version 17952 (0.0007) -[2023-10-09 00:44:09,683][88327] Updated weights for policy 1, policy_version 17930 (0.0008) -[2023-10-09 00:44:10,044][88327] Updated weights for policy 1, policy_version 17940 (0.0009) -[2023-10-09 00:44:10,413][88327] Updated weights for policy 1, policy_version 17950 (0.0007) -[2023-10-09 00:44:13,400][88326] Updated weights for policy 0, policy_version 17962 (0.0008) -[2023-10-09 00:44:13,771][88326] Updated weights for policy 0, policy_version 17972 (0.0009) -[2023-10-09 00:44:13,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 36765696. Throughput: 0: 1695.4, 1: 1703.7. Samples: 9203992. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-09 00:44:13,975][87372] Avg episode reward: [(0, '5.100'), (1, '4.570')] -[2023-10-09 00:44:14,139][88326] Updated weights for policy 0, policy_version 17982 (0.0010) -[2023-10-09 00:44:14,280][88327] Updated weights for policy 1, policy_version 17960 (0.0009) -[2023-10-09 00:44:14,641][88327] Updated weights for policy 1, policy_version 17970 (0.0010) -[2023-10-09 00:44:15,002][88327] Updated weights for policy 1, policy_version 17980 (0.0009) -[2023-10-09 00:44:18,221][88326] Updated weights for policy 0, policy_version 17992 (0.0008) -[2023-10-09 00:44:18,583][88326] Updated weights for policy 0, policy_version 18002 (0.0008) -[2023-10-09 00:44:18,909][88327] Updated weights for policy 1, policy_version 17990 (0.0009) -[2023-10-09 00:44:18,957][88326] Updated weights for policy 0, policy_version 18012 (0.0008) -[2023-10-09 00:44:18,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 36831232. Throughput: 0: 1687.7, 1: 1708.9. Samples: 9224998. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-09 00:44:18,975][87372] Avg episode reward: [(0, '4.950'), (1, '4.650')] -[2023-10-09 00:44:19,267][88327] Updated weights for policy 1, policy_version 18000 (0.0009) -[2023-10-09 00:44:19,641][88327] Updated weights for policy 1, policy_version 18010 (0.0010) -[2023-10-09 00:44:22,727][88326] Updated weights for policy 0, policy_version 18022 (0.0008) -[2023-10-09 00:44:23,105][88326] Updated weights for policy 0, policy_version 18032 (0.0009) -[2023-10-09 00:44:23,471][88326] Updated weights for policy 0, policy_version 18042 (0.0009) -[2023-10-09 00:44:23,649][88327] Updated weights for policy 1, policy_version 18020 (0.0007) -[2023-10-09 00:44:23,974][87372] Fps is (10 sec: 16383.7, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 36929536. Throughput: 0: 1697.9, 1: 1694.1. Samples: 9234598. Policy #0 lag: (min: 9.0, avg: 21.5, max: 41.0) -[2023-10-09 00:44:23,975][87372] Avg episode reward: [(0, '4.810'), (1, '4.740')] -[2023-10-09 00:44:24,018][88327] Updated weights for policy 1, policy_version 18030 (0.0009) -[2023-10-09 00:44:24,398][88327] Updated weights for policy 1, policy_version 18040 (0.0008) -[2023-10-09 00:44:27,642][88326] Updated weights for policy 0, policy_version 18052 (0.0007) -[2023-10-09 00:44:28,017][88326] Updated weights for policy 0, policy_version 18062 (0.0008) -[2023-10-09 00:44:28,390][88326] Updated weights for policy 0, policy_version 18072 (0.0009) -[2023-10-09 00:44:28,701][88327] Updated weights for policy 1, policy_version 18050 (0.0008) -[2023-10-09 00:44:28,974][87372] Fps is (10 sec: 16384.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 36995072. Throughput: 0: 1702.3, 1: 1706.5. Samples: 9255826. Policy #0 lag: (min: 9.0, avg: 21.5, max: 41.0) -[2023-10-09 00:44:28,975][87372] Avg episode reward: [(0, '5.220'), (1, '4.810')] -[2023-10-09 00:44:29,066][88327] Updated weights for policy 1, policy_version 18060 (0.0009) -[2023-10-09 00:44:29,434][88327] Updated weights for policy 1, policy_version 18070 (0.0007) -[2023-10-09 00:44:29,807][88327] Updated weights for policy 1, policy_version 18080 (0.0008) -[2023-10-09 00:44:32,474][88326] Updated weights for policy 0, policy_version 18082 (0.0009) -[2023-10-09 00:44:32,837][88326] Updated weights for policy 0, policy_version 18092 (0.0008) -[2023-10-09 00:44:33,206][88326] Updated weights for policy 0, policy_version 18102 (0.0008) -[2023-10-09 00:44:33,582][88326] Updated weights for policy 0, policy_version 18112 (0.0007) -[2023-10-09 00:44:33,975][87372] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 37060608. Throughput: 0: 1680.2, 1: 1703.4. Samples: 9275574. Policy #0 lag: (min: 9.0, avg: 21.5, max: 41.0) -[2023-10-09 00:44:33,976][87372] Avg episode reward: [(0, '4.760'), (1, '5.000')] -[2023-10-09 00:44:33,983][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000018112_18546688.pth... -[2023-10-09 00:44:34,020][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000016512_16908288.pth -[2023-10-09 00:44:34,206][88327] Updated weights for policy 1, policy_version 18090 (0.0009) -[2023-10-09 00:44:34,582][88327] Updated weights for policy 1, policy_version 18100 (0.0007) -[2023-10-09 00:44:34,950][88327] Updated weights for policy 1, policy_version 18110 (0.0008) -[2023-10-09 00:44:35,020][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000018112_18546688.pth... -[2023-10-09 00:44:35,049][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000016512_16908288.pth -[2023-10-09 00:44:37,562][88326] Updated weights for policy 0, policy_version 18122 (0.0008) -[2023-10-09 00:44:37,928][88326] Updated weights for policy 0, policy_version 18132 (0.0007) -[2023-10-09 00:44:38,302][88326] Updated weights for policy 0, policy_version 18142 (0.0007) -[2023-10-09 00:44:38,957][88327] Updated weights for policy 1, policy_version 18120 (0.0009) -[2023-10-09 00:44:38,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 37126144. Throughput: 0: 1701.3, 1: 1696.6. Samples: 9285430. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:44:38,975][87372] Avg episode reward: [(0, '4.640'), (1, '5.090')] -[2023-10-09 00:44:39,317][88327] Updated weights for policy 1, policy_version 18130 (0.0007) -[2023-10-09 00:44:39,686][88327] Updated weights for policy 1, policy_version 18140 (0.0007) -[2023-10-09 00:44:42,291][88326] Updated weights for policy 0, policy_version 18152 (0.0008) -[2023-10-09 00:44:42,667][88326] Updated weights for policy 0, policy_version 18162 (0.0009) -[2023-10-09 00:44:43,049][88326] Updated weights for policy 0, policy_version 18172 (0.0007) -[2023-10-09 00:44:43,643][88327] Updated weights for policy 1, policy_version 18150 (0.0007) -[2023-10-09 00:44:43,974][87372] Fps is (10 sec: 13107.7, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 37191680. Throughput: 0: 1700.8, 1: 1697.5. Samples: 9306300. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:44:43,975][87372] Avg episode reward: [(0, '4.910'), (1, '4.960')] -[2023-10-09 00:44:44,001][88327] Updated weights for policy 1, policy_version 18160 (0.0007) -[2023-10-09 00:44:44,370][88327] Updated weights for policy 1, policy_version 18170 (0.0007) -[2023-10-09 00:44:46,940][88326] Updated weights for policy 0, policy_version 18182 (0.0007) -[2023-10-09 00:44:47,309][88326] Updated weights for policy 0, policy_version 18192 (0.0008) -[2023-10-09 00:44:47,675][88326] Updated weights for policy 0, policy_version 18202 (0.0009) -[2023-10-09 00:44:48,376][88327] Updated weights for policy 1, policy_version 18180 (0.0008) -[2023-10-09 00:44:48,744][88327] Updated weights for policy 1, policy_version 18190 (0.0009) -[2023-10-09 00:44:48,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 37257216. Throughput: 0: 1679.5, 1: 1699.0. Samples: 9326222. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:44:48,975][87372] Avg episode reward: [(0, '4.510'), (1, '4.340')] -[2023-10-09 00:44:49,116][88327] Updated weights for policy 1, policy_version 18200 (0.0009) -[2023-10-09 00:44:51,795][88326] Updated weights for policy 0, policy_version 18212 (0.0008) -[2023-10-09 00:44:52,180][88326] Updated weights for policy 0, policy_version 18222 (0.0007) -[2023-10-09 00:44:52,546][88326] Updated weights for policy 0, policy_version 18232 (0.0009) -[2023-10-09 00:44:53,094][88327] Updated weights for policy 1, policy_version 18210 (0.0010) -[2023-10-09 00:44:53,459][88327] Updated weights for policy 1, policy_version 18220 (0.0010) -[2023-10-09 00:44:53,832][88327] Updated weights for policy 1, policy_version 18230 (0.0010) -[2023-10-09 00:44:53,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 37322752. Throughput: 0: 1710.5, 1: 1695.5. Samples: 9336540. Policy #0 lag: (min: 0.0, avg: 27.7, max: 32.0) -[2023-10-09 00:44:53,975][87372] Avg episode reward: [(0, '5.130'), (1, '4.310')] -[2023-10-09 00:44:54,189][88327] Updated weights for policy 1, policy_version 18240 (0.0009) -[2023-10-09 00:44:56,628][88326] Updated weights for policy 0, policy_version 18242 (0.0010) -[2023-10-09 00:44:56,990][88326] Updated weights for policy 0, policy_version 18252 (0.0007) -[2023-10-09 00:44:57,361][88326] Updated weights for policy 0, policy_version 18262 (0.0008) -[2023-10-09 00:44:57,725][88326] Updated weights for policy 0, policy_version 18272 (0.0008) -[2023-10-09 00:44:58,128][88327] Updated weights for policy 1, policy_version 18250 (0.0008) -[2023-10-09 00:44:58,489][88327] Updated weights for policy 1, policy_version 18260 (0.0007) -[2023-10-09 00:44:58,855][88327] Updated weights for policy 1, policy_version 18270 (0.0008) -[2023-10-09 00:44:58,974][87372] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 37421056. Throughput: 0: 1692.1, 1: 1702.9. Samples: 9356768. Policy #0 lag: (min: 0.0, avg: 27.7, max: 32.0) -[2023-10-09 00:44:58,975][87372] Avg episode reward: [(0, '5.460'), (1, '4.470')] -[2023-10-09 00:45:01,798][88326] Updated weights for policy 0, policy_version 18282 (0.0008) -[2023-10-09 00:45:02,166][88326] Updated weights for policy 0, policy_version 18292 (0.0007) -[2023-10-09 00:45:02,538][88326] Updated weights for policy 0, policy_version 18302 (0.0008) -[2023-10-09 00:45:02,950][88327] Updated weights for policy 1, policy_version 18280 (0.0008) -[2023-10-09 00:45:03,308][88327] Updated weights for policy 1, policy_version 18290 (0.0009) -[2023-10-09 00:45:03,682][88327] Updated weights for policy 1, policy_version 18300 (0.0010) -[2023-10-09 00:45:03,974][87372] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 37486592. Throughput: 0: 1685.3, 1: 1686.4. Samples: 9376724. Policy #0 lag: (min: 0.0, avg: 27.7, max: 32.0) -[2023-10-09 00:45:03,975][87372] Avg episode reward: [(0, '4.950'), (1, '4.760')] -[2023-10-09 00:45:06,449][88326] Updated weights for policy 0, policy_version 18312 (0.0007) -[2023-10-09 00:45:06,819][88326] Updated weights for policy 0, policy_version 18322 (0.0007) -[2023-10-09 00:45:07,191][88326] Updated weights for policy 0, policy_version 18332 (0.0010) -[2023-10-09 00:45:07,751][88327] Updated weights for policy 1, policy_version 18310 (0.0009) -[2023-10-09 00:45:08,123][88327] Updated weights for policy 1, policy_version 18320 (0.0008) -[2023-10-09 00:45:08,487][88327] Updated weights for policy 1, policy_version 18330 (0.0008) -[2023-10-09 00:45:08,974][87372] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 37552128. Throughput: 0: 1706.4, 1: 1696.0. Samples: 9387706. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:45:08,975][87372] Avg episode reward: [(0, '5.130'), (1, '4.940')] -[2023-10-09 00:45:11,146][88326] Updated weights for policy 0, policy_version 18342 (0.0007) -[2023-10-09 00:45:11,528][88326] Updated weights for policy 0, policy_version 18352 (0.0009) -[2023-10-09 00:45:11,909][88326] Updated weights for policy 0, policy_version 18362 (0.0010) -[2023-10-09 00:45:12,305][88327] Updated weights for policy 1, policy_version 18340 (0.0008) -[2023-10-09 00:45:12,671][88327] Updated weights for policy 1, policy_version 18350 (0.0008) -[2023-10-09 00:45:13,038][88327] Updated weights for policy 1, policy_version 18360 (0.0007) -[2023-10-09 00:45:13,974][87372] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 37617664. Throughput: 0: 1673.5, 1: 1698.1. Samples: 9407546. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:45:13,975][87372] Avg episode reward: [(0, '4.820'), (1, '4.950')] -[2023-10-09 00:45:16,081][88326] Updated weights for policy 0, policy_version 18372 (0.0008) -[2023-10-09 00:45:16,462][88326] Updated weights for policy 0, policy_version 18382 (0.0008) -[2023-10-09 00:45:16,829][88326] Updated weights for policy 0, policy_version 18392 (0.0007) -[2023-10-09 00:45:17,097][88327] Updated weights for policy 1, policy_version 18370 (0.0009) -[2023-10-09 00:45:17,469][88327] Updated weights for policy 1, policy_version 18380 (0.0008) -[2023-10-09 00:45:17,833][88327] Updated weights for policy 1, policy_version 18390 (0.0008) -[2023-10-09 00:45:18,204][88327] Updated weights for policy 1, policy_version 18400 (0.0007) -[2023-10-09 00:45:18,974][87372] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 37683200. Throughput: 0: 1690.8, 1: 1677.8. Samples: 9427162. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:45:18,974][87372] Avg episode reward: [(0, '4.610'), (1, '4.620')] -[2023-10-09 00:45:20,773][88326] Updated weights for policy 0, policy_version 18402 (0.0007) -[2023-10-09 00:45:21,152][88326] Updated weights for policy 0, policy_version 18412 (0.0007) -[2023-10-09 00:45:21,513][88326] Updated weights for policy 0, policy_version 18422 (0.0007) -[2023-10-09 00:45:21,880][88326] Updated weights for policy 0, policy_version 18432 (0.0010) -[2023-10-09 00:45:22,168][88327] Updated weights for policy 1, policy_version 18410 (0.0009) -[2023-10-09 00:45:22,546][88327] Updated weights for policy 1, policy_version 18420 (0.0007) -[2023-10-09 00:45:22,898][88327] Updated weights for policy 1, policy_version 18430 (0.0007) -[2023-10-09 00:45:23,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 37748736. Throughput: 0: 1690.9, 1: 1708.9. Samples: 9438422. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-09 00:45:23,975][87372] Avg episode reward: [(0, '4.980'), (1, '4.590')] -[2023-10-09 00:45:26,011][88326] Updated weights for policy 0, policy_version 18442 (0.0009) -[2023-10-09 00:45:26,378][88326] Updated weights for policy 0, policy_version 18452 (0.0007) -[2023-10-09 00:45:26,745][88326] Updated weights for policy 0, policy_version 18462 (0.0007) -[2023-10-09 00:45:26,914][88327] Updated weights for policy 1, policy_version 18440 (0.0008) -[2023-10-09 00:45:27,284][88327] Updated weights for policy 1, policy_version 18450 (0.0010) -[2023-10-09 00:45:27,657][88327] Updated weights for policy 1, policy_version 18460 (0.0009) -[2023-10-09 00:45:28,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 37814272. Throughput: 0: 1673.3, 1: 1697.3. Samples: 9457974. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-09 00:45:28,975][87372] Avg episode reward: [(0, '4.760'), (1, '4.760')] -[2023-10-09 00:45:30,805][88326] Updated weights for policy 0, policy_version 18472 (0.0009) -[2023-10-09 00:45:31,177][88326] Updated weights for policy 0, policy_version 18482 (0.0008) -[2023-10-09 00:45:31,547][88326] Updated weights for policy 0, policy_version 18492 (0.0008) -[2023-10-09 00:45:31,759][88327] Updated weights for policy 1, policy_version 18470 (0.0010) -[2023-10-09 00:45:32,118][88327] Updated weights for policy 1, policy_version 18480 (0.0011) -[2023-10-09 00:45:32,478][88327] Updated weights for policy 1, policy_version 18490 (0.0010) -[2023-10-09 00:45:33,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 37879808. Throughput: 0: 1695.7, 1: 1680.5. Samples: 9478152. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-09 00:45:33,975][87372] Avg episode reward: [(0, '4.660'), (1, '5.000')] -[2023-10-09 00:45:35,581][88326] Updated weights for policy 0, policy_version 18502 (0.0008) -[2023-10-09 00:45:35,950][88326] Updated weights for policy 0, policy_version 18512 (0.0007) -[2023-10-09 00:45:36,329][88326] Updated weights for policy 0, policy_version 18522 (0.0007) -[2023-10-09 00:45:36,663][88327] Updated weights for policy 1, policy_version 18500 (0.0009) -[2023-10-09 00:45:37,026][88327] Updated weights for policy 1, policy_version 18510 (0.0007) -[2023-10-09 00:45:37,392][88327] Updated weights for policy 1, policy_version 18520 (0.0007) -[2023-10-09 00:45:38,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 37945344. Throughput: 0: 1676.0, 1: 1708.0. Samples: 9488822. Policy #0 lag: (min: 24.0, avg: 50.9, max: 56.0) -[2023-10-09 00:45:38,975][87372] Avg episode reward: [(0, '5.180'), (1, '4.680')] -[2023-10-09 00:45:40,292][88326] Updated weights for policy 0, policy_version 18532 (0.0008) -[2023-10-09 00:45:40,659][88326] Updated weights for policy 0, policy_version 18542 (0.0008) -[2023-10-09 00:45:41,021][88326] Updated weights for policy 0, policy_version 18552 (0.0008) -[2023-10-09 00:45:41,345][88327] Updated weights for policy 1, policy_version 18530 (0.0007) -[2023-10-09 00:45:41,709][88327] Updated weights for policy 1, policy_version 18540 (0.0009) -[2023-10-09 00:45:42,081][88327] Updated weights for policy 1, policy_version 18550 (0.0010) -[2023-10-09 00:45:42,456][88327] Updated weights for policy 1, policy_version 18560 (0.0007) -[2023-10-09 00:45:43,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 38010880. Throughput: 0: 1690.0, 1: 1680.8. Samples: 9508450. Policy #0 lag: (min: 24.0, avg: 50.9, max: 56.0) -[2023-10-09 00:45:43,975][87372] Avg episode reward: [(0, '5.140'), (1, '4.390')] -[2023-10-09 00:45:45,049][88326] Updated weights for policy 0, policy_version 18562 (0.0009) -[2023-10-09 00:45:45,444][88326] Updated weights for policy 0, policy_version 18572 (0.0008) -[2023-10-09 00:45:45,817][88326] Updated weights for policy 0, policy_version 18582 (0.0010) -[2023-10-09 00:45:46,185][88326] Updated weights for policy 0, policy_version 18592 (0.0009) -[2023-10-09 00:45:46,551][88327] Updated weights for policy 1, policy_version 18570 (0.0008) -[2023-10-09 00:45:46,916][88327] Updated weights for policy 1, policy_version 18580 (0.0007) -[2023-10-09 00:45:47,281][88327] Updated weights for policy 1, policy_version 18590 (0.0007) -[2023-10-09 00:45:48,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 38076416. Throughput: 0: 1704.6, 1: 1683.6. Samples: 9529192. Policy #0 lag: (min: 24.0, avg: 50.9, max: 56.0) -[2023-10-09 00:45:48,975][87372] Avg episode reward: [(0, '5.230'), (1, '4.140')] -[2023-10-09 00:45:50,204][88326] Updated weights for policy 0, policy_version 18602 (0.0009) -[2023-10-09 00:45:50,569][88326] Updated weights for policy 0, policy_version 18612 (0.0012) -[2023-10-09 00:45:50,941][88326] Updated weights for policy 0, policy_version 18622 (0.0009) -[2023-10-09 00:45:51,351][88327] Updated weights for policy 1, policy_version 18600 (0.0007) -[2023-10-09 00:45:51,709][88327] Updated weights for policy 1, policy_version 18610 (0.0008) -[2023-10-09 00:45:52,083][88327] Updated weights for policy 1, policy_version 18620 (0.0009) -[2023-10-09 00:45:53,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 38141952. Throughput: 0: 1670.8, 1: 1696.4. Samples: 9539230. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:45:53,974][87372] Avg episode reward: [(0, '5.080'), (1, '4.390')] -[2023-10-09 00:45:54,957][88326] Updated weights for policy 0, policy_version 18632 (0.0010) -[2023-10-09 00:45:55,321][88326] Updated weights for policy 0, policy_version 18642 (0.0009) -[2023-10-09 00:45:55,689][88326] Updated weights for policy 0, policy_version 18652 (0.0010) -[2023-10-09 00:45:56,178][88327] Updated weights for policy 1, policy_version 18630 (0.0008) -[2023-10-09 00:45:56,537][88327] Updated weights for policy 1, policy_version 18640 (0.0010) -[2023-10-09 00:45:56,904][88327] Updated weights for policy 1, policy_version 18650 (0.0009) -[2023-10-09 00:45:58,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 38207488. Throughput: 0: 1700.2, 1: 1664.6. Samples: 9558962. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:45:58,975][87372] Avg episode reward: [(0, '5.230'), (1, '4.980')] -[2023-10-09 00:45:59,565][88326] Updated weights for policy 0, policy_version 18662 (0.0008) -[2023-10-09 00:45:59,935][88326] Updated weights for policy 0, policy_version 18672 (0.0007) -[2023-10-09 00:46:00,304][88326] Updated weights for policy 0, policy_version 18682 (0.0008) -[2023-10-09 00:46:00,988][88327] Updated weights for policy 1, policy_version 18660 (0.0010) -[2023-10-09 00:46:01,359][88327] Updated weights for policy 1, policy_version 18670 (0.0010) -[2023-10-09 00:46:01,731][88327] Updated weights for policy 1, policy_version 18680 (0.0009) -[2023-10-09 00:46:03,975][87372] Fps is (10 sec: 13106.6, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 38273024. Throughput: 0: 1702.8, 1: 1689.9. Samples: 9579836. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:46:03,976][87372] Avg episode reward: [(0, '5.000'), (1, '4.990')] -[2023-10-09 00:46:04,344][88326] Updated weights for policy 0, policy_version 18692 (0.0008) -[2023-10-09 00:46:04,711][88326] Updated weights for policy 0, policy_version 18702 (0.0007) -[2023-10-09 00:46:05,083][88326] Updated weights for policy 0, policy_version 18712 (0.0008) -[2023-10-09 00:46:05,583][88327] Updated weights for policy 1, policy_version 18690 (0.0010) -[2023-10-09 00:46:05,954][88327] Updated weights for policy 1, policy_version 18700 (0.0007) -[2023-10-09 00:46:06,324][88327] Updated weights for policy 1, policy_version 18710 (0.0011) -[2023-10-09 00:46:06,681][88327] Updated weights for policy 1, policy_version 18720 (0.0009) -[2023-10-09 00:46:08,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 38338560. Throughput: 0: 1683.1, 1: 1679.8. Samples: 9589750. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:46:08,975][87372] Avg episode reward: [(0, '5.440'), (1, '5.310')] -[2023-10-09 00:46:08,977][88168] Saving new best policy, reward=5.310! -[2023-10-09 00:46:09,190][88326] Updated weights for policy 0, policy_version 18722 (0.0007) -[2023-10-09 00:46:09,569][88326] Updated weights for policy 0, policy_version 18732 (0.0008) -[2023-10-09 00:46:09,941][88326] Updated weights for policy 0, policy_version 18742 (0.0007) -[2023-10-09 00:46:10,304][88326] Updated weights for policy 0, policy_version 18752 (0.0007) -[2023-10-09 00:46:10,821][88327] Updated weights for policy 1, policy_version 18730 (0.0009) -[2023-10-09 00:46:11,185][88327] Updated weights for policy 1, policy_version 18740 (0.0008) -[2023-10-09 00:46:11,548][88327] Updated weights for policy 1, policy_version 18750 (0.0007) -[2023-10-09 00:46:13,974][87372] Fps is (10 sec: 13107.8, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 38404096. Throughput: 0: 1700.0, 1: 1673.0. Samples: 9609756. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:46:13,974][87372] Avg episode reward: [(0, '5.540'), (1, '4.920')] -[2023-10-09 00:46:14,271][88326] Updated weights for policy 0, policy_version 18762 (0.0008) -[2023-10-09 00:46:14,639][88326] Updated weights for policy 0, policy_version 18772 (0.0010) -[2023-10-09 00:46:15,008][88326] Updated weights for policy 0, policy_version 18782 (0.0008) -[2023-10-09 00:46:15,558][88327] Updated weights for policy 1, policy_version 18760 (0.0008) -[2023-10-09 00:46:15,923][88327] Updated weights for policy 1, policy_version 18770 (0.0008) -[2023-10-09 00:46:16,297][88327] Updated weights for policy 1, policy_version 18780 (0.0008) -[2023-10-09 00:46:18,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 38469632. Throughput: 0: 1701.7, 1: 1687.5. Samples: 9630666. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:46:18,975][87372] Avg episode reward: [(0, '5.240'), (1, '4.710')] -[2023-10-09 00:46:19,181][88326] Updated weights for policy 0, policy_version 18792 (0.0008) -[2023-10-09 00:46:19,553][88326] Updated weights for policy 0, policy_version 18802 (0.0010) -[2023-10-09 00:46:19,924][88326] Updated weights for policy 0, policy_version 18812 (0.0010) -[2023-10-09 00:46:20,314][88327] Updated weights for policy 1, policy_version 18790 (0.0008) -[2023-10-09 00:46:20,677][88327] Updated weights for policy 1, policy_version 18800 (0.0009) -[2023-10-09 00:46:21,040][88327] Updated weights for policy 1, policy_version 18810 (0.0009) -[2023-10-09 00:46:23,936][88326] Updated weights for policy 0, policy_version 18822 (0.0011) -[2023-10-09 00:46:23,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 38535168. Throughput: 0: 1692.4, 1: 1669.3. Samples: 9640096. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-09 00:46:23,975][87372] Avg episode reward: [(0, '5.670'), (1, '4.730')] -[2023-10-09 00:46:24,312][88326] Updated weights for policy 0, policy_version 18832 (0.0009) -[2023-10-09 00:46:24,674][88326] Updated weights for policy 0, policy_version 18842 (0.0009) -[2023-10-09 00:46:25,002][88327] Updated weights for policy 1, policy_version 18820 (0.0009) -[2023-10-09 00:46:25,369][88327] Updated weights for policy 1, policy_version 18830 (0.0008) -[2023-10-09 00:46:25,733][88327] Updated weights for policy 1, policy_version 18840 (0.0011) -[2023-10-09 00:46:28,659][88326] Updated weights for policy 0, policy_version 18852 (0.0008) -[2023-10-09 00:46:28,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 38600704. Throughput: 0: 1697.9, 1: 1694.0. Samples: 9661088. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-09 00:46:28,975][87372] Avg episode reward: [(0, '5.290'), (1, '4.390')] -[2023-10-09 00:46:29,028][88326] Updated weights for policy 0, policy_version 18862 (0.0010) -[2023-10-09 00:46:29,396][88326] Updated weights for policy 0, policy_version 18872 (0.0008) -[2023-10-09 00:46:29,883][88327] Updated weights for policy 1, policy_version 18850 (0.0009) -[2023-10-09 00:46:30,250][88327] Updated weights for policy 1, policy_version 18860 (0.0008) -[2023-10-09 00:46:30,617][88327] Updated weights for policy 1, policy_version 18870 (0.0009) -[2023-10-09 00:46:30,984][88327] Updated weights for policy 1, policy_version 18880 (0.0008) -[2023-10-09 00:46:33,582][88326] Updated weights for policy 0, policy_version 18882 (0.0011) -[2023-10-09 00:46:33,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 38666240. Throughput: 0: 1693.5, 1: 1702.9. Samples: 9682028. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-09 00:46:33,975][87372] Avg episode reward: [(0, '5.500'), (1, '4.650')] -[2023-10-09 00:46:33,985][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000018880_19333120.pth... -[2023-10-09 00:46:33,997][88326] Updated weights for policy 0, policy_version 18892 (0.0010) -[2023-10-09 00:46:34,020][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000017312_17727488.pth -[2023-10-09 00:46:34,368][88326] Updated weights for policy 0, policy_version 18902 (0.0011) -[2023-10-09 00:46:34,736][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000018912_19365888.pth... -[2023-10-09 00:46:34,736][88326] Updated weights for policy 0, policy_version 18912 (0.0010) -[2023-10-09 00:46:34,769][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000017312_17727488.pth -[2023-10-09 00:46:34,952][88327] Updated weights for policy 1, policy_version 18890 (0.0009) -[2023-10-09 00:46:35,316][88327] Updated weights for policy 1, policy_version 18900 (0.0011) -[2023-10-09 00:46:35,684][88327] Updated weights for policy 1, policy_version 18910 (0.0009) -[2023-10-09 00:46:38,918][88326] Updated weights for policy 0, policy_version 18922 (0.0008) -[2023-10-09 00:46:38,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 38731776. Throughput: 0: 1690.9, 1: 1681.8. Samples: 9691002. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:46:38,975][87372] Avg episode reward: [(0, '5.810'), (1, '4.900')] -[2023-10-09 00:46:39,287][88326] Updated weights for policy 0, policy_version 18932 (0.0010) -[2023-10-09 00:46:39,654][88326] Updated weights for policy 0, policy_version 18942 (0.0009) -[2023-10-09 00:46:39,807][88327] Updated weights for policy 1, policy_version 18920 (0.0009) -[2023-10-09 00:46:40,172][88327] Updated weights for policy 1, policy_version 18930 (0.0008) -[2023-10-09 00:46:40,537][88327] Updated weights for policy 1, policy_version 18940 (0.0009) -[2023-10-09 00:46:43,704][88326] Updated weights for policy 0, policy_version 18952 (0.0009) -[2023-10-09 00:46:43,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 38797312. Throughput: 0: 1686.2, 1: 1704.2. Samples: 9711532. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:46:43,975][87372] Avg episode reward: [(0, '5.120'), (1, '4.770')] -[2023-10-09 00:46:44,075][88326] Updated weights for policy 0, policy_version 18962 (0.0007) -[2023-10-09 00:46:44,437][88326] Updated weights for policy 0, policy_version 18972 (0.0007) -[2023-10-09 00:46:44,630][88327] Updated weights for policy 1, policy_version 18950 (0.0009) -[2023-10-09 00:46:44,991][88327] Updated weights for policy 1, policy_version 18960 (0.0010) -[2023-10-09 00:46:45,354][88327] Updated weights for policy 1, policy_version 18970 (0.0008) -[2023-10-09 00:46:48,411][88326] Updated weights for policy 0, policy_version 18982 (0.0007) -[2023-10-09 00:46:48,776][88326] Updated weights for policy 0, policy_version 18992 (0.0007) -[2023-10-09 00:46:48,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 38862848. Throughput: 0: 1685.5, 1: 1701.3. Samples: 9732240. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:46:48,975][87372] Avg episode reward: [(0, '5.540'), (1, '5.100')] -[2023-10-09 00:46:49,136][88326] Updated weights for policy 0, policy_version 19002 (0.0007) -[2023-10-09 00:46:49,545][88327] Updated weights for policy 1, policy_version 18980 (0.0011) -[2023-10-09 00:46:49,906][88327] Updated weights for policy 1, policy_version 18990 (0.0010) -[2023-10-09 00:46:50,274][88327] Updated weights for policy 1, policy_version 19000 (0.0009) -[2023-10-09 00:46:53,057][88326] Updated weights for policy 0, policy_version 19012 (0.0007) -[2023-10-09 00:46:53,422][88326] Updated weights for policy 0, policy_version 19022 (0.0007) -[2023-10-09 00:46:53,783][88326] Updated weights for policy 0, policy_version 19032 (0.0009) -[2023-10-09 00:46:53,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 38928384. Throughput: 0: 1688.0, 1: 1681.3. Samples: 9741368. Policy #0 lag: (min: 27.0, avg: 29.4, max: 59.0) -[2023-10-09 00:46:53,975][87372] Avg episode reward: [(0, '5.160'), (1, '4.910')] -[2023-10-09 00:46:54,176][88327] Updated weights for policy 1, policy_version 19010 (0.0009) -[2023-10-09 00:46:54,540][88327] Updated weights for policy 1, policy_version 19020 (0.0009) -[2023-10-09 00:46:54,905][88327] Updated weights for policy 1, policy_version 19030 (0.0007) -[2023-10-09 00:46:55,276][88327] Updated weights for policy 1, policy_version 19040 (0.0009) -[2023-10-09 00:46:57,906][88326] Updated weights for policy 0, policy_version 19042 (0.0010) -[2023-10-09 00:46:58,283][88326] Updated weights for policy 0, policy_version 19052 (0.0008) -[2023-10-09 00:46:58,650][88326] Updated weights for policy 0, policy_version 19062 (0.0008) -[2023-10-09 00:46:58,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 38993920. Throughput: 0: 1691.9, 1: 1701.2. Samples: 9762444. Policy #0 lag: (min: 27.0, avg: 29.4, max: 59.0) -[2023-10-09 00:46:58,975][87372] Avg episode reward: [(0, '5.660'), (1, '5.010')] -[2023-10-09 00:46:59,031][88326] Updated weights for policy 0, policy_version 19072 (0.0008) -[2023-10-09 00:46:59,166][88327] Updated weights for policy 1, policy_version 19050 (0.0009) -[2023-10-09 00:46:59,531][88327] Updated weights for policy 1, policy_version 19060 (0.0008) -[2023-10-09 00:46:59,902][88327] Updated weights for policy 1, policy_version 19070 (0.0009) -[2023-10-09 00:47:02,947][88326] Updated weights for policy 0, policy_version 19082 (0.0007) -[2023-10-09 00:47:03,311][88326] Updated weights for policy 0, policy_version 19092 (0.0007) -[2023-10-09 00:47:03,677][88326] Updated weights for policy 0, policy_version 19102 (0.0007) -[2023-10-09 00:47:03,839][88327] Updated weights for policy 1, policy_version 19080 (0.0008) -[2023-10-09 00:47:03,974][87372] Fps is (10 sec: 16383.9, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 39092224. Throughput: 0: 1677.5, 1: 1704.6. Samples: 9782860. Policy #0 lag: (min: 26.0, avg: 26.0, max: 26.0) -[2023-10-09 00:47:03,975][87372] Avg episode reward: [(0, '5.230'), (1, '5.090')] -[2023-10-09 00:47:04,197][88327] Updated weights for policy 1, policy_version 19090 (0.0010) -[2023-10-09 00:47:04,565][88327] Updated weights for policy 1, policy_version 19100 (0.0010) -[2023-10-09 00:47:07,679][88326] Updated weights for policy 0, policy_version 19112 (0.0008) -[2023-10-09 00:47:08,056][88326] Updated weights for policy 0, policy_version 19122 (0.0010) -[2023-10-09 00:47:08,421][88326] Updated weights for policy 0, policy_version 19132 (0.0009) -[2023-10-09 00:47:08,753][88327] Updated weights for policy 1, policy_version 19110 (0.0009) -[2023-10-09 00:47:08,974][87372] Fps is (10 sec: 16384.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 39157760. Throughput: 0: 1691.2, 1: 1693.8. Samples: 9792420. Policy #0 lag: (min: 26.0, avg: 26.0, max: 26.0) -[2023-10-09 00:47:08,975][87372] Avg episode reward: [(0, '5.070'), (1, '5.130')] -[2023-10-09 00:47:09,128][88327] Updated weights for policy 1, policy_version 19120 (0.0007) -[2023-10-09 00:47:09,495][88327] Updated weights for policy 1, policy_version 19130 (0.0007) -[2023-10-09 00:47:12,416][88326] Updated weights for policy 0, policy_version 19142 (0.0008) -[2023-10-09 00:47:12,789][88326] Updated weights for policy 0, policy_version 19152 (0.0007) -[2023-10-09 00:47:13,163][88326] Updated weights for policy 0, policy_version 19162 (0.0007) -[2023-10-09 00:47:13,675][88327] Updated weights for policy 1, policy_version 19140 (0.0008) -[2023-10-09 00:47:13,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 39223296. Throughput: 0: 1695.0, 1: 1693.2. Samples: 9813554. Policy #0 lag: (min: 26.0, avg: 26.0, max: 26.0) -[2023-10-09 00:47:13,975][87372] Avg episode reward: [(0, '4.820'), (1, '4.850')] -[2023-10-09 00:47:14,032][88327] Updated weights for policy 1, policy_version 19150 (0.0009) -[2023-10-09 00:47:14,403][88327] Updated weights for policy 1, policy_version 19160 (0.0009) -[2023-10-09 00:47:17,236][88326] Updated weights for policy 0, policy_version 19172 (0.0007) -[2023-10-09 00:47:17,617][88326] Updated weights for policy 0, policy_version 19182 (0.0010) -[2023-10-09 00:47:17,997][88326] Updated weights for policy 0, policy_version 19192 (0.0008) -[2023-10-09 00:47:18,428][88327] Updated weights for policy 1, policy_version 19170 (0.0007) -[2023-10-09 00:47:18,791][88327] Updated weights for policy 1, policy_version 19180 (0.0009) -[2023-10-09 00:47:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 39288832. Throughput: 0: 1669.2, 1: 1692.2. Samples: 9833292. Policy #0 lag: (min: 22.0, avg: 28.2, max: 54.0) -[2023-10-09 00:47:18,975][87372] Avg episode reward: [(0, '4.720'), (1, '4.630')] -[2023-10-09 00:47:19,166][88327] Updated weights for policy 1, policy_version 19190 (0.0007) -[2023-10-09 00:47:19,526][88327] Updated weights for policy 1, policy_version 19200 (0.0008) -[2023-10-09 00:47:21,983][88326] Updated weights for policy 0, policy_version 19202 (0.0008) -[2023-10-09 00:47:22,386][88326] Updated weights for policy 0, policy_version 19212 (0.0010) -[2023-10-09 00:47:22,762][88326] Updated weights for policy 0, policy_version 19222 (0.0010) -[2023-10-09 00:47:23,134][88326] Updated weights for policy 0, policy_version 19232 (0.0008) -[2023-10-09 00:47:23,642][88327] Updated weights for policy 1, policy_version 19210 (0.0009) -[2023-10-09 00:47:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 39354368. Throughput: 0: 1700.5, 1: 1689.8. Samples: 9843566. Policy #0 lag: (min: 22.0, avg: 28.2, max: 54.0) -[2023-10-09 00:47:23,975][87372] Avg episode reward: [(0, '5.140'), (1, '4.560')] -[2023-10-09 00:47:24,011][88327] Updated weights for policy 1, policy_version 19220 (0.0010) -[2023-10-09 00:47:24,376][88327] Updated weights for policy 1, policy_version 19230 (0.0008) -[2023-10-09 00:47:27,229][88326] Updated weights for policy 0, policy_version 19242 (0.0007) -[2023-10-09 00:47:27,599][88326] Updated weights for policy 0, policy_version 19252 (0.0007) -[2023-10-09 00:47:27,971][88326] Updated weights for policy 0, policy_version 19262 (0.0009) -[2023-10-09 00:47:28,375][88327] Updated weights for policy 1, policy_version 19240 (0.0009) -[2023-10-09 00:47:28,742][88327] Updated weights for policy 1, policy_version 19250 (0.0008) -[2023-10-09 00:47:28,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 39419904. Throughput: 0: 1691.2, 1: 1694.1. Samples: 9863874. Policy #0 lag: (min: 22.0, avg: 28.2, max: 54.0) -[2023-10-09 00:47:28,975][87372] Avg episode reward: [(0, '5.140'), (1, '4.440')] -[2023-10-09 00:47:29,105][88327] Updated weights for policy 1, policy_version 19260 (0.0008) -[2023-10-09 00:47:31,813][88326] Updated weights for policy 0, policy_version 19272 (0.0009) -[2023-10-09 00:47:32,183][88326] Updated weights for policy 0, policy_version 19282 (0.0008) -[2023-10-09 00:47:32,549][88326] Updated weights for policy 0, policy_version 19292 (0.0007) -[2023-10-09 00:47:32,862][88327] Updated weights for policy 1, policy_version 19270 (0.0010) -[2023-10-09 00:47:33,230][88327] Updated weights for policy 1, policy_version 19280 (0.0011) -[2023-10-09 00:47:33,597][88327] Updated weights for policy 1, policy_version 19290 (0.0009) -[2023-10-09 00:47:33,974][87372] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 39518208. Throughput: 0: 1674.9, 1: 1691.8. Samples: 9883744. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-09 00:47:33,975][87372] Avg episode reward: [(0, '5.210'), (1, '4.730')] -[2023-10-09 00:47:36,767][88326] Updated weights for policy 0, policy_version 19302 (0.0010) -[2023-10-09 00:47:37,133][88326] Updated weights for policy 0, policy_version 19312 (0.0009) -[2023-10-09 00:47:37,507][88326] Updated weights for policy 0, policy_version 19322 (0.0008) -[2023-10-09 00:47:37,620][88327] Updated weights for policy 1, policy_version 19300 (0.0009) -[2023-10-09 00:47:37,988][88327] Updated weights for policy 1, policy_version 19310 (0.0009) -[2023-10-09 00:47:38,347][88327] Updated weights for policy 1, policy_version 19320 (0.0007) -[2023-10-09 00:47:38,974][87372] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 39583744. Throughput: 0: 1702.8, 1: 1707.6. Samples: 9894836. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-09 00:47:38,975][87372] Avg episode reward: [(0, '4.940'), (1, '4.740')] -[2023-10-09 00:47:41,446][88326] Updated weights for policy 0, policy_version 19332 (0.0008) -[2023-10-09 00:47:41,816][88326] Updated weights for policy 0, policy_version 19342 (0.0007) -[2023-10-09 00:47:42,175][88326] Updated weights for policy 0, policy_version 19352 (0.0008) -[2023-10-09 00:47:42,386][88327] Updated weights for policy 1, policy_version 19330 (0.0008) -[2023-10-09 00:47:42,744][88327] Updated weights for policy 1, policy_version 19340 (0.0008) -[2023-10-09 00:47:43,115][88327] Updated weights for policy 1, policy_version 19350 (0.0010) -[2023-10-09 00:47:43,479][88327] Updated weights for policy 1, policy_version 19360 (0.0008) -[2023-10-09 00:47:43,974][87372] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 39649280. Throughput: 0: 1679.4, 1: 1702.0. Samples: 9914608. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-09 00:47:43,975][87372] Avg episode reward: [(0, '5.290'), (1, '4.570')] -[2023-10-09 00:47:46,129][88326] Updated weights for policy 0, policy_version 19362 (0.0008) -[2023-10-09 00:47:46,501][88326] Updated weights for policy 0, policy_version 19372 (0.0008) -[2023-10-09 00:47:46,860][88326] Updated weights for policy 0, policy_version 19382 (0.0009) -[2023-10-09 00:47:47,233][88326] Updated weights for policy 0, policy_version 19392 (0.0007) -[2023-10-09 00:47:47,543][88327] Updated weights for policy 1, policy_version 19370 (0.0009) -[2023-10-09 00:47:47,902][88327] Updated weights for policy 1, policy_version 19380 (0.0008) -[2023-10-09 00:47:48,270][88327] Updated weights for policy 1, policy_version 19390 (0.0010) -[2023-10-09 00:47:48,974][87372] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 39714816. Throughput: 0: 1692.9, 1: 1674.9. Samples: 9934414. Policy #0 lag: (min: 31.0, avg: 32.4, max: 57.0) -[2023-10-09 00:47:48,975][87372] Avg episode reward: [(0, '5.050'), (1, '4.870')] -[2023-10-09 00:47:51,345][88326] Updated weights for policy 0, policy_version 19402 (0.0008) -[2023-10-09 00:47:51,715][88326] Updated weights for policy 0, policy_version 19412 (0.0008) -[2023-10-09 00:47:52,073][88326] Updated weights for policy 0, policy_version 19422 (0.0009) -[2023-10-09 00:47:52,382][88327] Updated weights for policy 1, policy_version 19400 (0.0009) -[2023-10-09 00:47:52,752][88327] Updated weights for policy 1, policy_version 19410 (0.0010) -[2023-10-09 00:47:53,113][88327] Updated weights for policy 1, policy_version 19420 (0.0007) -[2023-10-09 00:47:53,974][87372] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 39780352. Throughput: 0: 1701.2, 1: 1704.6. Samples: 9945682. Policy #0 lag: (min: 31.0, avg: 32.4, max: 57.0) -[2023-10-09 00:47:53,975][87372] Avg episode reward: [(0, '5.820'), (1, '4.800')] -[2023-10-09 00:47:56,210][88326] Updated weights for policy 0, policy_version 19432 (0.0009) -[2023-10-09 00:47:56,581][88326] Updated weights for policy 0, policy_version 19442 (0.0010) -[2023-10-09 00:47:56,947][88326] Updated weights for policy 0, policy_version 19452 (0.0009) -[2023-10-09 00:47:57,161][88327] Updated weights for policy 1, policy_version 19430 (0.0007) -[2023-10-09 00:47:57,522][88327] Updated weights for policy 1, policy_version 19440 (0.0010) -[2023-10-09 00:47:57,889][88327] Updated weights for policy 1, policy_version 19450 (0.0010) -[2023-10-09 00:47:58,974][87372] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 39845888. Throughput: 0: 1672.8, 1: 1699.9. Samples: 9965322. Policy #0 lag: (min: 31.0, avg: 32.4, max: 57.0) -[2023-10-09 00:47:58,975][87372] Avg episode reward: [(0, '5.760'), (1, '4.910')] -[2023-10-09 00:48:01,089][88326] Updated weights for policy 0, policy_version 19462 (0.0009) -[2023-10-09 00:48:01,458][88326] Updated weights for policy 0, policy_version 19472 (0.0008) -[2023-10-09 00:48:01,831][88326] Updated weights for policy 0, policy_version 19482 (0.0010) -[2023-10-09 00:48:01,956][88327] Updated weights for policy 1, policy_version 19460 (0.0009) -[2023-10-09 00:48:02,315][88327] Updated weights for policy 1, policy_version 19470 (0.0009) -[2023-10-09 00:48:02,686][88327] Updated weights for policy 1, policy_version 19480 (0.0009) -[2023-10-09 00:48:03,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 39911424. Throughput: 0: 1703.4, 1: 1674.1. Samples: 9985282. Policy #0 lag: (min: 31.0, avg: 31.1, max: 36.0) -[2023-10-09 00:48:03,975][87372] Avg episode reward: [(0, '5.780'), (1, '4.930')] -[2023-10-09 00:48:05,824][88326] Updated weights for policy 0, policy_version 19492 (0.0009) -[2023-10-09 00:48:06,199][88326] Updated weights for policy 0, policy_version 19502 (0.0010) -[2023-10-09 00:48:06,560][88326] Updated weights for policy 0, policy_version 19512 (0.0009) -[2023-10-09 00:48:06,627][88327] Updated weights for policy 1, policy_version 19490 (0.0009) -[2023-10-09 00:48:06,985][88327] Updated weights for policy 1, policy_version 19500 (0.0010) -[2023-10-09 00:48:07,353][88327] Updated weights for policy 1, policy_version 19510 (0.0009) -[2023-10-09 00:48:07,728][88327] Updated weights for policy 1, policy_version 19520 (0.0008) -[2023-10-09 00:48:08,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 39976960. Throughput: 0: 1690.4, 1: 1707.3. Samples: 9996466. Policy #0 lag: (min: 31.0, avg: 31.1, max: 36.0) -[2023-10-09 00:48:08,975][87372] Avg episode reward: [(0, '5.360'), (1, '4.640')] -[2023-10-09 00:48:10,443][88326] Updated weights for policy 0, policy_version 19522 (0.0008) -[2023-10-09 00:48:10,819][88326] Updated weights for policy 0, policy_version 19532 (0.0009) -[2023-10-09 00:48:11,181][88326] Updated weights for policy 0, policy_version 19542 (0.0009) -[2023-10-09 00:48:11,555][88326] Updated weights for policy 0, policy_version 19552 (0.0008) -[2023-10-09 00:48:11,833][88327] Updated weights for policy 1, policy_version 19530 (0.0008) -[2023-10-09 00:48:12,206][88327] Updated weights for policy 1, policy_version 19540 (0.0008) -[2023-10-09 00:48:12,575][88327] Updated weights for policy 1, policy_version 19550 (0.0008) -[2023-10-09 00:48:13,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 40042496. Throughput: 0: 1685.0, 1: 1689.7. Samples: 10015734. Policy #0 lag: (min: 31.0, avg: 31.1, max: 36.0) -[2023-10-09 00:48:13,975][87372] Avg episode reward: [(0, '4.760'), (1, '4.740')] -[2023-10-09 00:48:15,594][88326] Updated weights for policy 0, policy_version 19562 (0.0008) -[2023-10-09 00:48:15,954][88326] Updated weights for policy 0, policy_version 19572 (0.0008) -[2023-10-09 00:48:16,332][88326] Updated weights for policy 0, policy_version 19582 (0.0010) -[2023-10-09 00:48:16,639][88327] Updated weights for policy 1, policy_version 19560 (0.0008) -[2023-10-09 00:48:17,004][88327] Updated weights for policy 1, policy_version 19570 (0.0010) -[2023-10-09 00:48:17,373][88327] Updated weights for policy 1, policy_version 19580 (0.0008) -[2023-10-09 00:48:18,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 40108032. Throughput: 0: 1705.1, 1: 1681.9. Samples: 10036160. Policy #0 lag: (min: 31.0, avg: 31.1, max: 36.0) -[2023-10-09 00:48:18,975][87372] Avg episode reward: [(0, '5.360'), (1, '5.160')] -[2023-10-09 00:48:20,402][88326] Updated weights for policy 0, policy_version 19592 (0.0008) -[2023-10-09 00:48:20,771][88326] Updated weights for policy 0, policy_version 19602 (0.0008) -[2023-10-09 00:48:21,140][88326] Updated weights for policy 0, policy_version 19612 (0.0007) -[2023-10-09 00:48:21,290][88327] Updated weights for policy 1, policy_version 19590 (0.0009) -[2023-10-09 00:48:21,658][88327] Updated weights for policy 1, policy_version 19600 (0.0009) -[2023-10-09 00:48:22,024][88327] Updated weights for policy 1, policy_version 19610 (0.0007) -[2023-10-09 00:48:23,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 40173568. Throughput: 0: 1677.3, 1: 1695.0. Samples: 10046592. Policy #0 lag: (min: 41.0, avg: 55.3, max: 56.0) -[2023-10-09 00:48:23,975][87372] Avg episode reward: [(0, '5.350'), (1, '4.840')] -[2023-10-09 00:48:25,269][88326] Updated weights for policy 0, policy_version 19622 (0.0008) -[2023-10-09 00:48:25,637][88326] Updated weights for policy 0, policy_version 19632 (0.0010) -[2023-10-09 00:48:26,015][88326] Updated weights for policy 0, policy_version 19642 (0.0009) -[2023-10-09 00:48:26,178][88327] Updated weights for policy 1, policy_version 19620 (0.0009) -[2023-10-09 00:48:26,552][88327] Updated weights for policy 1, policy_version 19630 (0.0008) -[2023-10-09 00:48:26,915][88327] Updated weights for policy 1, policy_version 19640 (0.0008) -[2023-10-09 00:48:28,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 40239104. Throughput: 0: 1691.8, 1: 1675.9. Samples: 10066152. Policy #0 lag: (min: 41.0, avg: 55.3, max: 56.0) -[2023-10-09 00:48:28,975][87372] Avg episode reward: [(0, '5.540'), (1, '4.940')] -[2023-10-09 00:48:30,109][88326] Updated weights for policy 0, policy_version 19652 (0.0008) -[2023-10-09 00:48:30,464][88326] Updated weights for policy 0, policy_version 19662 (0.0008) -[2023-10-09 00:48:30,826][88326] Updated weights for policy 0, policy_version 19672 (0.0007) -[2023-10-09 00:48:31,025][88327] Updated weights for policy 1, policy_version 19650 (0.0007) -[2023-10-09 00:48:31,392][88327] Updated weights for policy 1, policy_version 19660 (0.0007) -[2023-10-09 00:48:31,759][88327] Updated weights for policy 1, policy_version 19670 (0.0008) -[2023-10-09 00:48:32,120][88327] Updated weights for policy 1, policy_version 19680 (0.0010) -[2023-10-09 00:48:33,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 40304640. Throughput: 0: 1689.2, 1: 1695.9. Samples: 10086742. Policy #0 lag: (min: 41.0, avg: 55.3, max: 56.0) -[2023-10-09 00:48:33,975][87372] Avg episode reward: [(0, '5.520'), (1, '4.510')] -[2023-10-09 00:48:33,982][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000019680_20152320.pth... -[2023-10-09 00:48:33,983][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000019680_20152320.pth... -[2023-10-09 00:48:34,012][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000018112_18546688.pth -[2023-10-09 00:48:34,022][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000018112_18546688.pth -[2023-10-09 00:48:34,728][88326] Updated weights for policy 0, policy_version 19682 (0.0007) -[2023-10-09 00:48:35,109][88326] Updated weights for policy 0, policy_version 19692 (0.0009) -[2023-10-09 00:48:35,469][88326] Updated weights for policy 0, policy_version 19702 (0.0008) -[2023-10-09 00:48:35,840][88326] Updated weights for policy 0, policy_version 19712 (0.0011) -[2023-10-09 00:48:36,111][88327] Updated weights for policy 1, policy_version 19690 (0.0010) -[2023-10-09 00:48:36,476][88327] Updated weights for policy 1, policy_version 19700 (0.0008) -[2023-10-09 00:48:36,835][88327] Updated weights for policy 1, policy_version 19710 (0.0008) -[2023-10-09 00:48:38,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 40370176. Throughput: 0: 1663.8, 1: 1690.8. Samples: 10096640. Policy #0 lag: (min: 2.0, avg: 10.9, max: 34.0) -[2023-10-09 00:48:38,975][87372] Avg episode reward: [(0, '5.570'), (1, '4.320')] -[2023-10-09 00:48:39,946][88326] Updated weights for policy 0, policy_version 19722 (0.0007) -[2023-10-09 00:48:40,324][88326] Updated weights for policy 0, policy_version 19732 (0.0008) -[2023-10-09 00:48:40,692][88326] Updated weights for policy 0, policy_version 19742 (0.0009) -[2023-10-09 00:48:40,768][88327] Updated weights for policy 1, policy_version 19720 (0.0008) -[2023-10-09 00:48:41,137][88327] Updated weights for policy 1, policy_version 19730 (0.0011) -[2023-10-09 00:48:41,504][88327] Updated weights for policy 1, policy_version 19740 (0.0009) -[2023-10-09 00:48:43,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 40435712. Throughput: 0: 1691.6, 1: 1673.5. Samples: 10116752. Policy #0 lag: (min: 2.0, avg: 10.9, max: 34.0) -[2023-10-09 00:48:43,975][87372] Avg episode reward: [(0, '5.160'), (1, '4.420')] -[2023-10-09 00:48:44,757][88326] Updated weights for policy 0, policy_version 19752 (0.0009) -[2023-10-09 00:48:45,128][88326] Updated weights for policy 0, policy_version 19762 (0.0007) -[2023-10-09 00:48:45,499][88326] Updated weights for policy 0, policy_version 19772 (0.0009) -[2023-10-09 00:48:45,685][88327] Updated weights for policy 1, policy_version 19750 (0.0010) -[2023-10-09 00:48:46,072][88327] Updated weights for policy 1, policy_version 19760 (0.0007) -[2023-10-09 00:48:46,445][88327] Updated weights for policy 1, policy_version 19770 (0.0008) -[2023-10-09 00:48:48,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 40501248. Throughput: 0: 1692.3, 1: 1691.8. Samples: 10137566. Policy #0 lag: (min: 2.0, avg: 10.9, max: 34.0) -[2023-10-09 00:48:48,975][87372] Avg episode reward: [(0, '5.170'), (1, '4.400')] -[2023-10-09 00:48:49,473][88326] Updated weights for policy 0, policy_version 19782 (0.0009) -[2023-10-09 00:48:49,842][88326] Updated weights for policy 0, policy_version 19792 (0.0009) -[2023-10-09 00:48:50,210][88326] Updated weights for policy 0, policy_version 19802 (0.0009) -[2023-10-09 00:48:50,565][88327] Updated weights for policy 1, policy_version 19780 (0.0009) -[2023-10-09 00:48:50,926][88327] Updated weights for policy 1, policy_version 19790 (0.0009) -[2023-10-09 00:48:51,297][88327] Updated weights for policy 1, policy_version 19800 (0.0008) -[2023-10-09 00:48:53,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 40566784. Throughput: 0: 1679.7, 1: 1672.1. Samples: 10147298. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 00:48:53,975][87372] Avg episode reward: [(0, '5.120'), (1, '4.030')] -[2023-10-09 00:48:54,024][88326] Updated weights for policy 0, policy_version 19812 (0.0010) -[2023-10-09 00:48:54,399][88326] Updated weights for policy 0, policy_version 19822 (0.0010) -[2023-10-09 00:48:54,777][88326] Updated weights for policy 0, policy_version 19832 (0.0009) -[2023-10-09 00:48:55,390][88327] Updated weights for policy 1, policy_version 19810 (0.0009) -[2023-10-09 00:48:55,754][88327] Updated weights for policy 1, policy_version 19820 (0.0009) -[2023-10-09 00:48:56,132][88327] Updated weights for policy 1, policy_version 19830 (0.0009) -[2023-10-09 00:48:56,493][88327] Updated weights for policy 1, policy_version 19840 (0.0008) -[2023-10-09 00:48:58,802][88326] Updated weights for policy 0, policy_version 19842 (0.0010) -[2023-10-09 00:48:58,974][87372] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 40632320. Throughput: 0: 1699.5, 1: 1676.6. Samples: 10167658. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 00:48:58,974][87372] Avg episode reward: [(0, '4.960'), (1, '4.400')] -[2023-10-09 00:48:59,179][88326] Updated weights for policy 0, policy_version 19852 (0.0009) -[2023-10-09 00:48:59,540][88326] Updated weights for policy 0, policy_version 19862 (0.0007) -[2023-10-09 00:48:59,915][88326] Updated weights for policy 0, policy_version 19872 (0.0008) -[2023-10-09 00:49:00,425][88327] Updated weights for policy 1, policy_version 19850 (0.0009) -[2023-10-09 00:49:00,782][88327] Updated weights for policy 1, policy_version 19860 (0.0008) -[2023-10-09 00:49:01,153][88327] Updated weights for policy 1, policy_version 19870 (0.0007) -[2023-10-09 00:49:03,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 40697856. Throughput: 0: 1695.3, 1: 1693.0. Samples: 10188634. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 00:49:03,975][87372] Avg episode reward: [(0, '5.160'), (1, '4.790')] -[2023-10-09 00:49:04,143][88326] Updated weights for policy 0, policy_version 19882 (0.0007) -[2023-10-09 00:49:04,526][88326] Updated weights for policy 0, policy_version 19892 (0.0009) -[2023-10-09 00:49:04,892][88326] Updated weights for policy 0, policy_version 19902 (0.0008) -[2023-10-09 00:49:05,263][88327] Updated weights for policy 1, policy_version 19880 (0.0009) -[2023-10-09 00:49:05,626][88327] Updated weights for policy 1, policy_version 19890 (0.0009) -[2023-10-09 00:49:05,995][88327] Updated weights for policy 1, policy_version 19900 (0.0008) -[2023-10-09 00:49:08,551][88326] Updated weights for policy 0, policy_version 19912 (0.0007) -[2023-10-09 00:49:08,920][88326] Updated weights for policy 0, policy_version 19922 (0.0008) -[2023-10-09 00:49:08,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 40763392. Throughput: 0: 1691.2, 1: 1666.0. Samples: 10197666. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 00:49:08,975][87372] Avg episode reward: [(0, '5.270'), (1, '5.000')] -[2023-10-09 00:49:09,287][88326] Updated weights for policy 0, policy_version 19932 (0.0010) -[2023-10-09 00:49:10,224][88327] Updated weights for policy 1, policy_version 19910 (0.0010) -[2023-10-09 00:49:10,583][88327] Updated weights for policy 1, policy_version 19920 (0.0008) -[2023-10-09 00:49:10,950][88327] Updated weights for policy 1, policy_version 19930 (0.0008) -[2023-10-09 00:49:13,347][88326] Updated weights for policy 0, policy_version 19942 (0.0009) -[2023-10-09 00:49:13,722][88326] Updated weights for policy 0, policy_version 19952 (0.0008) -[2023-10-09 00:49:13,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 40828928. Throughput: 0: 1703.5, 1: 1685.6. Samples: 10218658. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-09 00:49:13,975][87372] Avg episode reward: [(0, '5.280'), (1, '4.990')] -[2023-10-09 00:49:14,097][88326] Updated weights for policy 0, policy_version 19962 (0.0008) -[2023-10-09 00:49:14,839][88327] Updated weights for policy 1, policy_version 19940 (0.0008) -[2023-10-09 00:49:15,205][88327] Updated weights for policy 1, policy_version 19950 (0.0012) -[2023-10-09 00:49:15,569][88327] Updated weights for policy 1, policy_version 19960 (0.0007) -[2023-10-09 00:49:18,199][88326] Updated weights for policy 0, policy_version 19972 (0.0007) -[2023-10-09 00:49:18,563][88326] Updated weights for policy 0, policy_version 19982 (0.0010) -[2023-10-09 00:49:18,934][88326] Updated weights for policy 0, policy_version 19992 (0.0010) -[2023-10-09 00:49:18,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 40894464. Throughput: 0: 1701.9, 1: 1689.1. Samples: 10239340. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-09 00:49:18,975][87372] Avg episode reward: [(0, '5.030'), (1, '5.010')] -[2023-10-09 00:49:19,733][88327] Updated weights for policy 1, policy_version 19970 (0.0008) -[2023-10-09 00:49:20,096][88327] Updated weights for policy 1, policy_version 19980 (0.0008) -[2023-10-09 00:49:20,465][88327] Updated weights for policy 1, policy_version 19990 (0.0008) -[2023-10-09 00:49:20,832][88327] Updated weights for policy 1, policy_version 20000 (0.0007) -[2023-10-09 00:49:22,965][88326] Updated weights for policy 0, policy_version 20002 (0.0009) -[2023-10-09 00:49:23,329][88326] Updated weights for policy 0, policy_version 20012 (0.0007) -[2023-10-09 00:49:23,707][88326] Updated weights for policy 0, policy_version 20022 (0.0008) -[2023-10-09 00:49:23,974][87372] Fps is (10 sec: 13106.8, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 40960000. Throughput: 0: 1709.5, 1: 1668.7. Samples: 10248656. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-09 00:49:23,975][87372] Avg episode reward: [(0, '4.930'), (1, '4.870')] -[2023-10-09 00:49:24,069][88326] Updated weights for policy 0, policy_version 20032 (0.0009) -[2023-10-09 00:49:25,001][88327] Updated weights for policy 1, policy_version 20010 (0.0009) -[2023-10-09 00:49:25,362][88327] Updated weights for policy 1, policy_version 20020 (0.0009) -[2023-10-09 00:49:25,728][88327] Updated weights for policy 1, policy_version 20030 (0.0009) -[2023-10-09 00:49:28,065][88326] Updated weights for policy 0, policy_version 20042 (0.0007) -[2023-10-09 00:49:28,433][88326] Updated weights for policy 0, policy_version 20052 (0.0009) -[2023-10-09 00:49:28,797][88326] Updated weights for policy 0, policy_version 20062 (0.0009) -[2023-10-09 00:49:28,974][87372] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 41058304. Throughput: 0: 1707.9, 1: 1690.3. Samples: 10269670. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-10-09 00:49:28,975][87372] Avg episode reward: [(0, '5.280'), (1, '4.680')] -[2023-10-09 00:49:29,579][88327] Updated weights for policy 1, policy_version 20040 (0.0007) -[2023-10-09 00:49:29,935][88327] Updated weights for policy 1, policy_version 20050 (0.0008) -[2023-10-09 00:49:30,297][88327] Updated weights for policy 1, policy_version 20060 (0.0009) -[2023-10-09 00:49:32,818][88326] Updated weights for policy 0, policy_version 20072 (0.0010) -[2023-10-09 00:49:33,188][88326] Updated weights for policy 0, policy_version 20082 (0.0010) -[2023-10-09 00:49:33,548][88326] Updated weights for policy 0, policy_version 20092 (0.0007) -[2023-10-09 00:49:33,974][87372] Fps is (10 sec: 16384.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 41123840. Throughput: 0: 1690.0, 1: 1692.4. Samples: 10289776. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-10-09 00:49:33,975][87372] Avg episode reward: [(0, '5.020'), (1, '4.820')] -[2023-10-09 00:49:34,491][88327] Updated weights for policy 1, policy_version 20070 (0.0008) -[2023-10-09 00:49:34,873][88327] Updated weights for policy 1, policy_version 20080 (0.0007) -[2023-10-09 00:49:35,232][88327] Updated weights for policy 1, policy_version 20090 (0.0008) -[2023-10-09 00:49:37,684][88326] Updated weights for policy 0, policy_version 20102 (0.0008) -[2023-10-09 00:49:38,057][88326] Updated weights for policy 0, policy_version 20112 (0.0008) -[2023-10-09 00:49:38,432][88326] Updated weights for policy 0, policy_version 20122 (0.0008) -[2023-10-09 00:49:38,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 41189376. Throughput: 0: 1707.1, 1: 1677.5. Samples: 10299604. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-10-09 00:49:38,975][87372] Avg episode reward: [(0, '5.370'), (1, '4.830')] -[2023-10-09 00:49:39,108][88327] Updated weights for policy 1, policy_version 20100 (0.0011) -[2023-10-09 00:49:39,474][88327] Updated weights for policy 1, policy_version 20110 (0.0008) -[2023-10-09 00:49:39,842][88327] Updated weights for policy 1, policy_version 20120 (0.0009) -[2023-10-09 00:49:42,556][88326] Updated weights for policy 0, policy_version 20132 (0.0009) -[2023-10-09 00:49:42,917][88326] Updated weights for policy 0, policy_version 20142 (0.0007) -[2023-10-09 00:49:43,284][88326] Updated weights for policy 0, policy_version 20152 (0.0010) -[2023-10-09 00:49:43,902][88327] Updated weights for policy 1, policy_version 20130 (0.0010) -[2023-10-09 00:49:43,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 41254912. Throughput: 0: 1700.3, 1: 1690.9. Samples: 10320262. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-10-09 00:49:43,975][87372] Avg episode reward: [(0, '5.810'), (1, '4.850')] -[2023-10-09 00:49:44,261][88327] Updated weights for policy 1, policy_version 20140 (0.0010) -[2023-10-09 00:49:44,627][88327] Updated weights for policy 1, policy_version 20150 (0.0010) -[2023-10-09 00:49:44,996][88327] Updated weights for policy 1, policy_version 20160 (0.0010) -[2023-10-09 00:49:47,369][88326] Updated weights for policy 0, policy_version 20162 (0.0009) -[2023-10-09 00:49:47,741][88326] Updated weights for policy 0, policy_version 20172 (0.0008) -[2023-10-09 00:49:48,113][88326] Updated weights for policy 0, policy_version 20182 (0.0009) -[2023-10-09 00:49:48,472][88326] Updated weights for policy 0, policy_version 20192 (0.0010) -[2023-10-09 00:49:48,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 41320448. Throughput: 0: 1677.5, 1: 1690.2. Samples: 10340178. Policy #0 lag: (min: 10.0, avg: 18.4, max: 42.0) -[2023-10-09 00:49:48,975][87372] Avg episode reward: [(0, '5.330'), (1, '4.470')] -[2023-10-09 00:49:49,040][88327] Updated weights for policy 1, policy_version 20170 (0.0008) -[2023-10-09 00:49:49,412][88327] Updated weights for policy 1, policy_version 20180 (0.0008) -[2023-10-09 00:49:49,777][88327] Updated weights for policy 1, policy_version 20190 (0.0007) -[2023-10-09 00:49:52,600][88326] Updated weights for policy 0, policy_version 20202 (0.0007) -[2023-10-09 00:49:52,960][88326] Updated weights for policy 0, policy_version 20212 (0.0008) -[2023-10-09 00:49:53,325][88326] Updated weights for policy 0, policy_version 20222 (0.0009) -[2023-10-09 00:49:53,828][88327] Updated weights for policy 1, policy_version 20200 (0.0008) -[2023-10-09 00:49:53,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 41385984. Throughput: 0: 1699.4, 1: 1690.3. Samples: 10350202. Policy #0 lag: (min: 10.0, avg: 18.4, max: 42.0) -[2023-10-09 00:49:53,975][87372] Avg episode reward: [(0, '5.720'), (1, '4.410')] -[2023-10-09 00:49:54,204][88327] Updated weights for policy 1, policy_version 20210 (0.0007) -[2023-10-09 00:49:54,572][88327] Updated weights for policy 1, policy_version 20220 (0.0008) -[2023-10-09 00:49:57,281][88326] Updated weights for policy 0, policy_version 20232 (0.0009) -[2023-10-09 00:49:57,645][88326] Updated weights for policy 0, policy_version 20242 (0.0008) -[2023-10-09 00:49:58,010][88326] Updated weights for policy 0, policy_version 20252 (0.0008) -[2023-10-09 00:49:58,708][88327] Updated weights for policy 1, policy_version 20230 (0.0008) -[2023-10-09 00:49:58,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 41451520. Throughput: 0: 1688.9, 1: 1690.6. Samples: 10370736. Policy #0 lag: (min: 10.0, avg: 18.4, max: 42.0) -[2023-10-09 00:49:58,975][87372] Avg episode reward: [(0, '5.690'), (1, '4.150')] -[2023-10-09 00:49:59,065][88327] Updated weights for policy 1, policy_version 20240 (0.0010) -[2023-10-09 00:49:59,431][88327] Updated weights for policy 1, policy_version 20250 (0.0009) -[2023-10-09 00:50:02,004][88326] Updated weights for policy 0, policy_version 20262 (0.0007) -[2023-10-09 00:50:02,377][88326] Updated weights for policy 0, policy_version 20272 (0.0009) -[2023-10-09 00:50:02,751][88326] Updated weights for policy 0, policy_version 20282 (0.0007) -[2023-10-09 00:50:03,459][88327] Updated weights for policy 1, policy_version 20260 (0.0008) -[2023-10-09 00:50:03,828][88327] Updated weights for policy 1, policy_version 20270 (0.0009) -[2023-10-09 00:50:03,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 41517056. Throughput: 0: 1670.1, 1: 1697.6. Samples: 10390890. Policy #0 lag: (min: 7.0, avg: 14.5, max: 39.0) -[2023-10-09 00:50:03,975][87372] Avg episode reward: [(0, '5.060'), (1, '4.350')] -[2023-10-09 00:50:04,194][88327] Updated weights for policy 1, policy_version 20280 (0.0007) -[2023-10-09 00:50:06,854][88326] Updated weights for policy 0, policy_version 20292 (0.0009) -[2023-10-09 00:50:07,218][88326] Updated weights for policy 0, policy_version 20302 (0.0010) -[2023-10-09 00:50:07,590][88326] Updated weights for policy 0, policy_version 20312 (0.0010) -[2023-10-09 00:50:08,119][88327] Updated weights for policy 1, policy_version 20290 (0.0007) -[2023-10-09 00:50:08,484][88327] Updated weights for policy 1, policy_version 20300 (0.0007) -[2023-10-09 00:50:08,861][88327] Updated weights for policy 1, policy_version 20310 (0.0007) -[2023-10-09 00:50:08,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 41582592. Throughput: 0: 1691.6, 1: 1699.0. Samples: 10401234. Policy #0 lag: (min: 7.0, avg: 14.5, max: 39.0) -[2023-10-09 00:50:08,975][87372] Avg episode reward: [(0, '5.250'), (1, '4.850')] -[2023-10-09 00:50:09,219][88327] Updated weights for policy 1, policy_version 20320 (0.0007) -[2023-10-09 00:50:11,672][88326] Updated weights for policy 0, policy_version 20322 (0.0007) -[2023-10-09 00:50:12,044][88326] Updated weights for policy 0, policy_version 20332 (0.0009) -[2023-10-09 00:50:12,411][88326] Updated weights for policy 0, policy_version 20342 (0.0010) -[2023-10-09 00:50:12,779][88326] Updated weights for policy 0, policy_version 20352 (0.0009) -[2023-10-09 00:50:13,280][88327] Updated weights for policy 1, policy_version 20330 (0.0011) -[2023-10-09 00:50:13,650][88327] Updated weights for policy 1, policy_version 20340 (0.0010) -[2023-10-09 00:50:13,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 41648128. Throughput: 0: 1673.4, 1: 1698.4. Samples: 10421400. Policy #0 lag: (min: 7.0, avg: 14.5, max: 39.0) -[2023-10-09 00:50:13,975][87372] Avg episode reward: [(0, '5.000'), (1, '5.040')] -[2023-10-09 00:50:14,017][88327] Updated weights for policy 1, policy_version 20350 (0.0009) -[2023-10-09 00:50:16,609][88326] Updated weights for policy 0, policy_version 20362 (0.0010) -[2023-10-09 00:50:16,982][88326] Updated weights for policy 0, policy_version 20372 (0.0009) -[2023-10-09 00:50:17,344][88326] Updated weights for policy 0, policy_version 20382 (0.0007) -[2023-10-09 00:50:18,005][88327] Updated weights for policy 1, policy_version 20360 (0.0007) -[2023-10-09 00:50:18,374][88327] Updated weights for policy 1, policy_version 20370 (0.0011) -[2023-10-09 00:50:18,737][88327] Updated weights for policy 1, policy_version 20380 (0.0011) -[2023-10-09 00:50:18,974][87372] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 41746432. Throughput: 0: 1672.7, 1: 1695.4. Samples: 10441340. Policy #0 lag: (min: 18.0, avg: 18.0, max: 21.0) -[2023-10-09 00:50:18,975][87372] Avg episode reward: [(0, '5.000'), (1, '5.320')] -[2023-10-09 00:50:18,986][88168] Saving new best policy, reward=5.320! -[2023-10-09 00:50:21,555][88326] Updated weights for policy 0, policy_version 20392 (0.0010) -[2023-10-09 00:50:21,931][88326] Updated weights for policy 0, policy_version 20402 (0.0010) -[2023-10-09 00:50:22,307][88326] Updated weights for policy 0, policy_version 20412 (0.0009) -[2023-10-09 00:50:22,879][88327] Updated weights for policy 1, policy_version 20390 (0.0011) -[2023-10-09 00:50:23,262][88327] Updated weights for policy 1, policy_version 20400 (0.0012) -[2023-10-09 00:50:23,629][88327] Updated weights for policy 1, policy_version 20410 (0.0011) -[2023-10-09 00:50:23,974][87372] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 41811968. Throughput: 0: 1681.9, 1: 1703.9. Samples: 10451966. Policy #0 lag: (min: 18.0, avg: 18.0, max: 21.0) -[2023-10-09 00:50:23,975][87372] Avg episode reward: [(0, '5.320'), (1, '5.230')] -[2023-10-09 00:50:26,243][88326] Updated weights for policy 0, policy_version 20422 (0.0008) -[2023-10-09 00:50:26,611][88326] Updated weights for policy 0, policy_version 20432 (0.0008) -[2023-10-09 00:50:26,990][88326] Updated weights for policy 0, policy_version 20442 (0.0009) -[2023-10-09 00:50:27,559][88327] Updated weights for policy 1, policy_version 20420 (0.0008) -[2023-10-09 00:50:27,932][88327] Updated weights for policy 1, policy_version 20430 (0.0007) -[2023-10-09 00:50:28,290][88327] Updated weights for policy 1, policy_version 20440 (0.0009) -[2023-10-09 00:50:28,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 41877504. Throughput: 0: 1657.7, 1: 1703.5. Samples: 10471520. Policy #0 lag: (min: 18.0, avg: 18.0, max: 21.0) -[2023-10-09 00:50:28,975][87372] Avg episode reward: [(0, '5.710'), (1, '5.160')] -[2023-10-09 00:50:31,211][88326] Updated weights for policy 0, policy_version 20452 (0.0009) -[2023-10-09 00:50:31,573][88326] Updated weights for policy 0, policy_version 20462 (0.0009) -[2023-10-09 00:50:31,945][88326] Updated weights for policy 0, policy_version 20472 (0.0009) -[2023-10-09 00:50:32,442][88327] Updated weights for policy 1, policy_version 20450 (0.0010) -[2023-10-09 00:50:32,818][88327] Updated weights for policy 1, policy_version 20460 (0.0009) -[2023-10-09 00:50:33,177][88327] Updated weights for policy 1, policy_version 20470 (0.0008) -[2023-10-09 00:50:33,545][88327] Updated weights for policy 1, policy_version 20480 (0.0008) -[2023-10-09 00:50:33,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 41943040. Throughput: 0: 1676.9, 1: 1683.6. Samples: 10491400. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:50:33,975][87372] Avg episode reward: [(0, '5.580'), (1, '5.390')] -[2023-10-09 00:50:33,983][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000020480_20971520.pth... -[2023-10-09 00:50:33,984][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000020480_20971520.pth... -[2023-10-09 00:50:34,021][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000018880_19333120.pth -[2023-10-09 00:50:34,022][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000018912_19365888.pth -[2023-10-09 00:50:34,025][88168] Saving new best policy, reward=5.390! -[2023-10-09 00:50:35,971][88326] Updated weights for policy 0, policy_version 20482 (0.0010) -[2023-10-09 00:50:36,338][88326] Updated weights for policy 0, policy_version 20492 (0.0007) -[2023-10-09 00:50:36,716][88326] Updated weights for policy 0, policy_version 20502 (0.0007) -[2023-10-09 00:50:37,084][88326] Updated weights for policy 0, policy_version 20512 (0.0007) -[2023-10-09 00:50:37,486][88327] Updated weights for policy 1, policy_version 20490 (0.0010) -[2023-10-09 00:50:37,855][88327] Updated weights for policy 1, policy_version 20500 (0.0007) -[2023-10-09 00:50:38,214][88327] Updated weights for policy 1, policy_version 20510 (0.0010) -[2023-10-09 00:50:38,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 42008576. Throughput: 0: 1677.9, 1: 1703.8. Samples: 10502378. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:50:38,975][87372] Avg episode reward: [(0, '5.330'), (1, '5.220')] -[2023-10-09 00:50:41,137][88326] Updated weights for policy 0, policy_version 20522 (0.0008) -[2023-10-09 00:50:41,501][88326] Updated weights for policy 0, policy_version 20532 (0.0008) -[2023-10-09 00:50:41,875][88326] Updated weights for policy 0, policy_version 20542 (0.0008) -[2023-10-09 00:50:42,290][88327] Updated weights for policy 1, policy_version 20520 (0.0008) -[2023-10-09 00:50:42,658][88327] Updated weights for policy 1, policy_version 20530 (0.0008) -[2023-10-09 00:50:43,010][88327] Updated weights for policy 1, policy_version 20540 (0.0009) -[2023-10-09 00:50:43,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 42074112. Throughput: 0: 1666.3, 1: 1705.1. Samples: 10522450. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:50:43,975][87372] Avg episode reward: [(0, '4.940'), (1, '5.270')] -[2023-10-09 00:50:46,040][88326] Updated weights for policy 0, policy_version 20552 (0.0009) -[2023-10-09 00:50:46,418][88326] Updated weights for policy 0, policy_version 20562 (0.0010) -[2023-10-09 00:50:46,799][88326] Updated weights for policy 0, policy_version 20572 (0.0009) -[2023-10-09 00:50:47,137][88327] Updated weights for policy 1, policy_version 20550 (0.0007) -[2023-10-09 00:50:47,509][88327] Updated weights for policy 1, policy_version 20560 (0.0008) -[2023-10-09 00:50:47,868][88327] Updated weights for policy 1, policy_version 20570 (0.0007) -[2023-10-09 00:50:48,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 42139648. Throughput: 0: 1691.2, 1: 1673.0. Samples: 10542282. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:50:48,975][87372] Avg episode reward: [(0, '4.900'), (1, '4.740')] -[2023-10-09 00:50:50,802][88326] Updated weights for policy 0, policy_version 20582 (0.0008) -[2023-10-09 00:50:51,173][88326] Updated weights for policy 0, policy_version 20592 (0.0009) -[2023-10-09 00:50:51,549][88326] Updated weights for policy 0, policy_version 20602 (0.0008) -[2023-10-09 00:50:51,987][88327] Updated weights for policy 1, policy_version 20580 (0.0009) -[2023-10-09 00:50:52,359][88327] Updated weights for policy 1, policy_version 20590 (0.0009) -[2023-10-09 00:50:52,725][88327] Updated weights for policy 1, policy_version 20600 (0.0009) -[2023-10-09 00:50:53,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 42205184. Throughput: 0: 1679.1, 1: 1696.5. Samples: 10553138. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-09 00:50:53,975][87372] Avg episode reward: [(0, '5.450'), (1, '4.630')] -[2023-10-09 00:50:55,582][88326] Updated weights for policy 0, policy_version 20612 (0.0008) -[2023-10-09 00:50:55,955][88326] Updated weights for policy 0, policy_version 20622 (0.0009) -[2023-10-09 00:50:56,331][88326] Updated weights for policy 0, policy_version 20632 (0.0008) -[2023-10-09 00:50:56,677][88327] Updated weights for policy 1, policy_version 20610 (0.0007) -[2023-10-09 00:50:57,046][88327] Updated weights for policy 1, policy_version 20620 (0.0010) -[2023-10-09 00:50:57,422][88327] Updated weights for policy 1, policy_version 20630 (0.0007) -[2023-10-09 00:50:57,786][88327] Updated weights for policy 1, policy_version 20640 (0.0007) -[2023-10-09 00:50:58,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 42270720. Throughput: 0: 1683.8, 1: 1679.8. Samples: 10572760. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-09 00:50:58,975][87372] Avg episode reward: [(0, '5.300'), (1, '4.980')] -[2023-10-09 00:51:00,344][88326] Updated weights for policy 0, policy_version 20642 (0.0008) -[2023-10-09 00:51:00,714][88326] Updated weights for policy 0, policy_version 20652 (0.0012) -[2023-10-09 00:51:01,076][88326] Updated weights for policy 0, policy_version 20662 (0.0009) -[2023-10-09 00:51:01,450][88326] Updated weights for policy 0, policy_version 20672 (0.0008) -[2023-10-09 00:51:01,862][88327] Updated weights for policy 1, policy_version 20650 (0.0009) -[2023-10-09 00:51:02,222][88327] Updated weights for policy 1, policy_version 20660 (0.0008) -[2023-10-09 00:51:02,598][88327] Updated weights for policy 1, policy_version 20670 (0.0009) -[2023-10-09 00:51:03,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 42336256. Throughput: 0: 1702.8, 1: 1663.8. Samples: 10592838. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-09 00:51:03,975][87372] Avg episode reward: [(0, '5.140'), (1, '5.130')] -[2023-10-09 00:51:05,446][88326] Updated weights for policy 0, policy_version 20682 (0.0007) -[2023-10-09 00:51:05,820][88326] Updated weights for policy 0, policy_version 20692 (0.0007) -[2023-10-09 00:51:06,188][88326] Updated weights for policy 0, policy_version 20702 (0.0009) -[2023-10-09 00:51:06,720][88327] Updated weights for policy 1, policy_version 20680 (0.0008) -[2023-10-09 00:51:07,091][88327] Updated weights for policy 1, policy_version 20690 (0.0008) -[2023-10-09 00:51:07,461][88327] Updated weights for policy 1, policy_version 20700 (0.0008) -[2023-10-09 00:51:08,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 42401792. Throughput: 0: 1676.4, 1: 1688.3. Samples: 10603378. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-09 00:51:08,975][87372] Avg episode reward: [(0, '5.460'), (1, '5.090')] -[2023-10-09 00:51:10,074][88326] Updated weights for policy 0, policy_version 20712 (0.0007) -[2023-10-09 00:51:10,449][88326] Updated weights for policy 0, policy_version 20722 (0.0007) -[2023-10-09 00:51:10,823][88326] Updated weights for policy 0, policy_version 20732 (0.0008) -[2023-10-09 00:51:11,532][88327] Updated weights for policy 1, policy_version 20710 (0.0007) -[2023-10-09 00:51:11,897][88327] Updated weights for policy 1, policy_version 20720 (0.0011) -[2023-10-09 00:51:12,274][88327] Updated weights for policy 1, policy_version 20730 (0.0008) -[2023-10-09 00:51:13,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 42467328. Throughput: 0: 1706.8, 1: 1668.6. Samples: 10623412. Policy #0 lag: (min: 24.0, avg: 31.9, max: 32.0) -[2023-10-09 00:51:13,975][87372] Avg episode reward: [(0, '5.220'), (1, '5.290')] -[2023-10-09 00:51:14,763][88326] Updated weights for policy 0, policy_version 20742 (0.0008) -[2023-10-09 00:51:15,137][88326] Updated weights for policy 0, policy_version 20752 (0.0007) -[2023-10-09 00:51:15,514][88326] Updated weights for policy 0, policy_version 20762 (0.0008) -[2023-10-09 00:51:16,177][88327] Updated weights for policy 1, policy_version 20740 (0.0008) -[2023-10-09 00:51:16,555][88327] Updated weights for policy 1, policy_version 20750 (0.0009) -[2023-10-09 00:51:16,913][88327] Updated weights for policy 1, policy_version 20760 (0.0009) -[2023-10-09 00:51:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 42532864. Throughput: 0: 1714.1, 1: 1680.5. Samples: 10644156. Policy #0 lag: (min: 24.0, avg: 31.9, max: 32.0) -[2023-10-09 00:51:18,974][87372] Avg episode reward: [(0, '5.580'), (1, '5.130')] -[2023-10-09 00:51:19,483][88326] Updated weights for policy 0, policy_version 20772 (0.0009) -[2023-10-09 00:51:19,850][88326] Updated weights for policy 0, policy_version 20782 (0.0008) -[2023-10-09 00:51:20,217][88326] Updated weights for policy 0, policy_version 20792 (0.0008) -[2023-10-09 00:51:20,955][88327] Updated weights for policy 1, policy_version 20770 (0.0010) -[2023-10-09 00:51:21,326][88327] Updated weights for policy 1, policy_version 20780 (0.0010) -[2023-10-09 00:51:21,695][88327] Updated weights for policy 1, policy_version 20790 (0.0009) -[2023-10-09 00:51:22,065][88327] Updated weights for policy 1, policy_version 20800 (0.0009) -[2023-10-09 00:51:23,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 42598400. Throughput: 0: 1692.5, 1: 1683.2. Samples: 10654286. Policy #0 lag: (min: 24.0, avg: 31.9, max: 32.0) -[2023-10-09 00:51:23,975][87372] Avg episode reward: [(0, '5.950'), (1, '5.070')] -[2023-10-09 00:51:24,107][88326] Updated weights for policy 0, policy_version 20802 (0.0009) -[2023-10-09 00:51:24,477][88326] Updated weights for policy 0, policy_version 20812 (0.0009) -[2023-10-09 00:51:24,858][88326] Updated weights for policy 0, policy_version 20822 (0.0008) -[2023-10-09 00:51:25,224][88326] Updated weights for policy 0, policy_version 20832 (0.0008) -[2023-10-09 00:51:25,878][88327] Updated weights for policy 1, policy_version 20810 (0.0007) -[2023-10-09 00:51:26,244][88327] Updated weights for policy 1, policy_version 20820 (0.0007) -[2023-10-09 00:51:26,615][88327] Updated weights for policy 1, policy_version 20830 (0.0008) -[2023-10-09 00:51:28,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 42663936. Throughput: 0: 1717.1, 1: 1670.4. Samples: 10674888. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-09 00:51:28,975][87372] Avg episode reward: [(0, '5.690'), (1, '5.460')] -[2023-10-09 00:51:28,977][88168] Saving new best policy, reward=5.460! -[2023-10-09 00:51:29,198][88326] Updated weights for policy 0, policy_version 20842 (0.0008) -[2023-10-09 00:51:29,569][88326] Updated weights for policy 0, policy_version 20852 (0.0008) -[2023-10-09 00:51:29,926][88326] Updated weights for policy 0, policy_version 20862 (0.0009) -[2023-10-09 00:51:30,592][88327] Updated weights for policy 1, policy_version 20840 (0.0009) -[2023-10-09 00:51:30,959][88327] Updated weights for policy 1, policy_version 20850 (0.0008) -[2023-10-09 00:51:31,329][88327] Updated weights for policy 1, policy_version 20860 (0.0008) -[2023-10-09 00:51:33,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 42729472. Throughput: 0: 1716.9, 1: 1698.9. Samples: 10695994. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-09 00:51:33,975][87372] Avg episode reward: [(0, '5.280'), (1, '5.560')] -[2023-10-09 00:51:33,984][88168] Saving new best policy, reward=5.560! -[2023-10-09 00:51:34,032][88326] Updated weights for policy 0, policy_version 20872 (0.0009) -[2023-10-09 00:51:34,416][88326] Updated weights for policy 0, policy_version 20882 (0.0009) -[2023-10-09 00:51:34,785][88326] Updated weights for policy 0, policy_version 20892 (0.0007) -[2023-10-09 00:51:35,308][88327] Updated weights for policy 1, policy_version 20870 (0.0008) -[2023-10-09 00:51:35,673][88327] Updated weights for policy 1, policy_version 20880 (0.0009) -[2023-10-09 00:51:36,039][88327] Updated weights for policy 1, policy_version 20890 (0.0008) -[2023-10-09 00:51:38,739][88326] Updated weights for policy 0, policy_version 20902 (0.0007) -[2023-10-09 00:51:38,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 42795008. Throughput: 0: 1702.5, 1: 1678.3. Samples: 10705274. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-09 00:51:38,975][87372] Avg episode reward: [(0, '5.290'), (1, '5.180')] -[2023-10-09 00:51:39,102][88326] Updated weights for policy 0, policy_version 20912 (0.0007) -[2023-10-09 00:51:39,486][88326] Updated weights for policy 0, policy_version 20922 (0.0009) -[2023-10-09 00:51:40,161][88327] Updated weights for policy 1, policy_version 20900 (0.0007) -[2023-10-09 00:51:40,525][88327] Updated weights for policy 1, policy_version 20910 (0.0009) -[2023-10-09 00:51:40,891][88327] Updated weights for policy 1, policy_version 20920 (0.0008) -[2023-10-09 00:51:43,361][88326] Updated weights for policy 0, policy_version 20932 (0.0010) -[2023-10-09 00:51:43,737][88326] Updated weights for policy 0, policy_version 20942 (0.0009) -[2023-10-09 00:51:43,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 42860544. Throughput: 0: 1721.2, 1: 1689.1. Samples: 10726220. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-09 00:51:43,975][87372] Avg episode reward: [(0, '5.300'), (1, '5.310')] -[2023-10-09 00:51:44,097][88326] Updated weights for policy 0, policy_version 20952 (0.0010) -[2023-10-09 00:51:44,786][88327] Updated weights for policy 1, policy_version 20930 (0.0007) -[2023-10-09 00:51:45,151][88327] Updated weights for policy 1, policy_version 20940 (0.0008) -[2023-10-09 00:51:45,522][88327] Updated weights for policy 1, policy_version 20950 (0.0011) -[2023-10-09 00:51:45,882][88327] Updated weights for policy 1, policy_version 20960 (0.0010) -[2023-10-09 00:51:48,114][88326] Updated weights for policy 0, policy_version 20962 (0.0010) -[2023-10-09 00:51:48,487][88326] Updated weights for policy 0, policy_version 20972 (0.0007) -[2023-10-09 00:51:48,860][88326] Updated weights for policy 0, policy_version 20982 (0.0008) -[2023-10-09 00:51:48,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 42926080. Throughput: 0: 1714.5, 1: 1713.6. Samples: 10747102. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) -[2023-10-09 00:51:48,975][87372] Avg episode reward: [(0, '5.820'), (1, '5.290')] -[2023-10-09 00:51:49,230][88326] Updated weights for policy 0, policy_version 20992 (0.0009) -[2023-10-09 00:51:50,001][88327] Updated weights for policy 1, policy_version 20970 (0.0011) -[2023-10-09 00:51:50,367][88327] Updated weights for policy 1, policy_version 20980 (0.0010) -[2023-10-09 00:51:50,741][88327] Updated weights for policy 1, policy_version 20990 (0.0010) -[2023-10-09 00:51:53,214][88326] Updated weights for policy 0, policy_version 21002 (0.0009) -[2023-10-09 00:51:53,595][88326] Updated weights for policy 0, policy_version 21012 (0.0009) -[2023-10-09 00:51:53,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 42991616. Throughput: 0: 1717.2, 1: 1682.7. Samples: 10756372. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) -[2023-10-09 00:51:53,975][87372] Avg episode reward: [(0, '5.710'), (1, '4.900')] -[2023-10-09 00:51:53,977][88326] Updated weights for policy 0, policy_version 21022 (0.0009) -[2023-10-09 00:51:54,667][88327] Updated weights for policy 1, policy_version 21000 (0.0010) -[2023-10-09 00:51:55,035][88327] Updated weights for policy 1, policy_version 21010 (0.0008) -[2023-10-09 00:51:55,398][88327] Updated weights for policy 1, policy_version 21020 (0.0009) -[2023-10-09 00:51:57,966][88326] Updated weights for policy 0, policy_version 21032 (0.0009) -[2023-10-09 00:51:58,339][88326] Updated weights for policy 0, policy_version 21042 (0.0009) -[2023-10-09 00:51:58,703][88326] Updated weights for policy 0, policy_version 21052 (0.0009) -[2023-10-09 00:51:58,974][87372] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 43089920. Throughput: 0: 1717.7, 1: 1705.6. Samples: 10777462. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) -[2023-10-09 00:51:58,975][87372] Avg episode reward: [(0, '5.440'), (1, '5.050')] -[2023-10-09 00:51:59,446][88327] Updated weights for policy 1, policy_version 21030 (0.0009) -[2023-10-09 00:51:59,806][88327] Updated weights for policy 1, policy_version 21040 (0.0009) -[2023-10-09 00:52:00,175][88327] Updated weights for policy 1, policy_version 21050 (0.0009) -[2023-10-09 00:52:02,748][88326] Updated weights for policy 0, policy_version 21062 (0.0009) -[2023-10-09 00:52:03,115][88326] Updated weights for policy 0, policy_version 21072 (0.0009) -[2023-10-09 00:52:03,484][88326] Updated weights for policy 0, policy_version 21082 (0.0007) -[2023-10-09 00:52:03,974][87372] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 43155456. Throughput: 0: 1692.5, 1: 1712.6. Samples: 10797386. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:52:03,975][87372] Avg episode reward: [(0, '6.200'), (1, '5.030')] -[2023-10-09 00:52:03,985][88088] Saving new best policy, reward=6.200! -[2023-10-09 00:52:04,313][88327] Updated weights for policy 1, policy_version 21060 (0.0007) -[2023-10-09 00:52:04,721][88327] Updated weights for policy 1, policy_version 21070 (0.0008) -[2023-10-09 00:52:05,086][88327] Updated weights for policy 1, policy_version 21080 (0.0008) -[2023-10-09 00:52:07,635][88326] Updated weights for policy 0, policy_version 21092 (0.0008) -[2023-10-09 00:52:08,002][88326] Updated weights for policy 0, policy_version 21102 (0.0010) -[2023-10-09 00:52:08,380][88326] Updated weights for policy 0, policy_version 21112 (0.0010) -[2023-10-09 00:52:08,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 43220992. Throughput: 0: 1708.3, 1: 1687.6. Samples: 10807098. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:52:08,975][87372] Avg episode reward: [(0, '5.460'), (1, '4.630')] -[2023-10-09 00:52:09,059][88327] Updated weights for policy 1, policy_version 21090 (0.0008) -[2023-10-09 00:52:09,424][88327] Updated weights for policy 1, policy_version 21100 (0.0008) -[2023-10-09 00:52:09,786][88327] Updated weights for policy 1, policy_version 21110 (0.0007) -[2023-10-09 00:52:10,155][88327] Updated weights for policy 1, policy_version 21120 (0.0008) -[2023-10-09 00:52:12,395][88326] Updated weights for policy 0, policy_version 21122 (0.0010) -[2023-10-09 00:52:12,759][88326] Updated weights for policy 0, policy_version 21132 (0.0008) -[2023-10-09 00:52:13,119][88326] Updated weights for policy 0, policy_version 21142 (0.0009) -[2023-10-09 00:52:13,486][88326] Updated weights for policy 0, policy_version 21152 (0.0007) -[2023-10-09 00:52:13,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 43286528. Throughput: 0: 1699.5, 1: 1704.5. Samples: 10828066. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:52:13,975][87372] Avg episode reward: [(0, '5.170'), (1, '4.980')] -[2023-10-09 00:52:14,233][88327] Updated weights for policy 1, policy_version 21130 (0.0011) -[2023-10-09 00:52:14,599][88327] Updated weights for policy 1, policy_version 21140 (0.0010) -[2023-10-09 00:52:14,956][88327] Updated weights for policy 1, policy_version 21150 (0.0009) -[2023-10-09 00:52:17,508][88326] Updated weights for policy 0, policy_version 21162 (0.0008) -[2023-10-09 00:52:17,879][88326] Updated weights for policy 0, policy_version 21172 (0.0007) -[2023-10-09 00:52:18,237][88326] Updated weights for policy 0, policy_version 21182 (0.0008) -[2023-10-09 00:52:18,860][88327] Updated weights for policy 1, policy_version 21160 (0.0008) -[2023-10-09 00:52:18,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 43352064. Throughput: 0: 1677.0, 1: 1706.7. Samples: 10848262. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:52:18,974][87372] Avg episode reward: [(0, '5.800'), (1, '5.130')] -[2023-10-09 00:52:19,227][88327] Updated weights for policy 1, policy_version 21170 (0.0007) -[2023-10-09 00:52:19,588][88327] Updated weights for policy 1, policy_version 21180 (0.0007) -[2023-10-09 00:52:22,307][88326] Updated weights for policy 0, policy_version 21192 (0.0008) -[2023-10-09 00:52:22,690][88326] Updated weights for policy 0, policy_version 21202 (0.0008) -[2023-10-09 00:52:23,070][88326] Updated weights for policy 0, policy_version 21212 (0.0007) -[2023-10-09 00:52:23,582][88327] Updated weights for policy 1, policy_version 21190 (0.0008) -[2023-10-09 00:52:23,951][88327] Updated weights for policy 1, policy_version 21200 (0.0009) -[2023-10-09 00:52:23,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 43417600. Throughput: 0: 1706.6, 1: 1705.5. Samples: 10858820. Policy #0 lag: (min: 11.0, avg: 11.0, max: 14.0) -[2023-10-09 00:52:23,975][87372] Avg episode reward: [(0, '5.380'), (1, '5.000')] -[2023-10-09 00:52:24,314][88327] Updated weights for policy 1, policy_version 21210 (0.0010) -[2023-10-09 00:52:27,032][88326] Updated weights for policy 0, policy_version 21222 (0.0010) -[2023-10-09 00:52:27,398][88326] Updated weights for policy 0, policy_version 21232 (0.0010) -[2023-10-09 00:52:27,762][88326] Updated weights for policy 0, policy_version 21242 (0.0009) -[2023-10-09 00:52:28,336][88327] Updated weights for policy 1, policy_version 21220 (0.0009) -[2023-10-09 00:52:28,708][88327] Updated weights for policy 1, policy_version 21230 (0.0010) -[2023-10-09 00:52:28,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 43483136. Throughput: 0: 1694.0, 1: 1712.0. Samples: 10879494. Policy #0 lag: (min: 11.0, avg: 11.0, max: 14.0) -[2023-10-09 00:52:28,975][87372] Avg episode reward: [(0, '5.050'), (1, '5.420')] -[2023-10-09 00:52:29,083][88327] Updated weights for policy 1, policy_version 21240 (0.0012) -[2023-10-09 00:52:31,769][88326] Updated weights for policy 0, policy_version 21252 (0.0010) -[2023-10-09 00:52:32,149][88326] Updated weights for policy 0, policy_version 21262 (0.0009) -[2023-10-09 00:52:32,525][88326] Updated weights for policy 0, policy_version 21272 (0.0007) -[2023-10-09 00:52:33,048][88327] Updated weights for policy 1, policy_version 21250 (0.0008) -[2023-10-09 00:52:33,423][88327] Updated weights for policy 1, policy_version 21260 (0.0009) -[2023-10-09 00:52:33,790][88327] Updated weights for policy 1, policy_version 21270 (0.0010) -[2023-10-09 00:52:33,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 43548672. Throughput: 0: 1676.4, 1: 1711.9. Samples: 10899574. Policy #0 lag: (min: 11.0, avg: 11.0, max: 14.0) -[2023-10-09 00:52:33,975][87372] Avg episode reward: [(0, '5.750'), (1, '5.090')] -[2023-10-09 00:52:33,985][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000021280_21790720.pth... -[2023-10-09 00:52:34,023][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000019680_20152320.pth -[2023-10-09 00:52:34,154][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000021280_21790720.pth... -[2023-10-09 00:52:34,154][88327] Updated weights for policy 1, policy_version 21280 (0.0008) -[2023-10-09 00:52:34,183][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000019680_20152320.pth -[2023-10-09 00:52:36,541][88326] Updated weights for policy 0, policy_version 21282 (0.0009) -[2023-10-09 00:52:36,908][88326] Updated weights for policy 0, policy_version 21292 (0.0009) -[2023-10-09 00:52:37,289][88326] Updated weights for policy 0, policy_version 21302 (0.0009) -[2023-10-09 00:52:37,660][88326] Updated weights for policy 0, policy_version 21312 (0.0009) -[2023-10-09 00:52:38,152][88327] Updated weights for policy 1, policy_version 21290 (0.0008) -[2023-10-09 00:52:38,515][88327] Updated weights for policy 1, policy_version 21300 (0.0008) -[2023-10-09 00:52:38,881][88327] Updated weights for policy 1, policy_version 21310 (0.0009) -[2023-10-09 00:52:38,974][87372] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 43646976. Throughput: 0: 1705.5, 1: 1714.1. Samples: 10910254. Policy #0 lag: (min: 11.0, avg: 11.0, max: 14.0) -[2023-10-09 00:52:38,975][87372] Avg episode reward: [(0, '5.520'), (1, '4.850')] -[2023-10-09 00:52:41,642][88326] Updated weights for policy 0, policy_version 21322 (0.0008) -[2023-10-09 00:52:42,014][88326] Updated weights for policy 0, policy_version 21332 (0.0009) -[2023-10-09 00:52:42,391][88326] Updated weights for policy 0, policy_version 21342 (0.0008) -[2023-10-09 00:52:42,829][88327] Updated weights for policy 1, policy_version 21320 (0.0010) -[2023-10-09 00:52:43,194][88327] Updated weights for policy 1, policy_version 21330 (0.0010) -[2023-10-09 00:52:43,575][88327] Updated weights for policy 1, policy_version 21340 (0.0010) -[2023-10-09 00:52:43,974][87372] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 43712512. Throughput: 0: 1682.5, 1: 1717.7. Samples: 10930472. Policy #0 lag: (min: 27.0, avg: 28.0, max: 49.0) -[2023-10-09 00:52:43,975][87372] Avg episode reward: [(0, '5.600'), (1, '4.680')] -[2023-10-09 00:52:46,403][88326] Updated weights for policy 0, policy_version 21352 (0.0008) -[2023-10-09 00:52:46,774][88326] Updated weights for policy 0, policy_version 21362 (0.0007) -[2023-10-09 00:52:47,142][88326] Updated weights for policy 0, policy_version 21372 (0.0007) -[2023-10-09 00:52:47,576][88327] Updated weights for policy 1, policy_version 21350 (0.0008) -[2023-10-09 00:52:47,946][88327] Updated weights for policy 1, policy_version 21360 (0.0008) -[2023-10-09 00:52:48,306][88327] Updated weights for policy 1, policy_version 21370 (0.0008) -[2023-10-09 00:52:48,974][87372] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 43778048. Throughput: 0: 1700.5, 1: 1701.5. Samples: 10950476. Policy #0 lag: (min: 27.0, avg: 28.0, max: 49.0) -[2023-10-09 00:52:48,975][87372] Avg episode reward: [(0, '5.830'), (1, '4.780')] -[2023-10-09 00:52:51,035][88326] Updated weights for policy 0, policy_version 21382 (0.0009) -[2023-10-09 00:52:51,405][88326] Updated weights for policy 0, policy_version 21392 (0.0008) -[2023-10-09 00:52:51,776][88326] Updated weights for policy 0, policy_version 21402 (0.0007) -[2023-10-09 00:52:52,563][88327] Updated weights for policy 1, policy_version 21380 (0.0009) -[2023-10-09 00:52:52,962][88327] Updated weights for policy 1, policy_version 21390 (0.0008) -[2023-10-09 00:52:53,333][88327] Updated weights for policy 1, policy_version 21400 (0.0007) -[2023-10-09 00:52:53,974][87372] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 43843584. Throughput: 0: 1705.9, 1: 1721.1. Samples: 10961310. Policy #0 lag: (min: 27.0, avg: 28.0, max: 49.0) -[2023-10-09 00:52:53,975][87372] Avg episode reward: [(0, '6.040'), (1, '4.890')] -[2023-10-09 00:52:55,721][88326] Updated weights for policy 0, policy_version 21412 (0.0009) -[2023-10-09 00:52:56,090][88326] Updated weights for policy 0, policy_version 21422 (0.0009) -[2023-10-09 00:52:56,454][88326] Updated weights for policy 0, policy_version 21432 (0.0010) -[2023-10-09 00:52:57,210][88327] Updated weights for policy 1, policy_version 21410 (0.0008) -[2023-10-09 00:52:57,583][88327] Updated weights for policy 1, policy_version 21420 (0.0009) -[2023-10-09 00:52:57,945][88327] Updated weights for policy 1, policy_version 21430 (0.0010) -[2023-10-09 00:52:58,316][88327] Updated weights for policy 1, policy_version 21440 (0.0008) -[2023-10-09 00:52:58,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 43909120. Throughput: 0: 1687.9, 1: 1718.0. Samples: 10981332. Policy #0 lag: (min: 27.0, avg: 28.0, max: 49.0) -[2023-10-09 00:52:58,975][87372] Avg episode reward: [(0, '5.930'), (1, '5.160')] -[2023-10-09 00:53:00,600][88326] Updated weights for policy 0, policy_version 21442 (0.0007) -[2023-10-09 00:53:00,971][88326] Updated weights for policy 0, policy_version 21452 (0.0010) -[2023-10-09 00:53:01,343][88326] Updated weights for policy 0, policy_version 21462 (0.0010) -[2023-10-09 00:53:01,711][88326] Updated weights for policy 0, policy_version 21472 (0.0009) -[2023-10-09 00:53:02,405][88327] Updated weights for policy 1, policy_version 21450 (0.0010) -[2023-10-09 00:53:02,780][88327] Updated weights for policy 1, policy_version 21460 (0.0010) -[2023-10-09 00:53:03,156][88327] Updated weights for policy 1, policy_version 21470 (0.0008) -[2023-10-09 00:53:03,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 43974656. Throughput: 0: 1712.5, 1: 1683.3. Samples: 11001074. Policy #0 lag: (min: 17.0, avg: 28.3, max: 49.0) -[2023-10-09 00:53:03,975][87372] Avg episode reward: [(0, '5.620'), (1, '4.820')] -[2023-10-09 00:53:05,551][88326] Updated weights for policy 0, policy_version 21482 (0.0009) -[2023-10-09 00:53:05,919][88326] Updated weights for policy 0, policy_version 21492 (0.0009) -[2023-10-09 00:53:06,288][88326] Updated weights for policy 0, policy_version 21502 (0.0007) -[2023-10-09 00:53:07,253][88327] Updated weights for policy 1, policy_version 21480 (0.0008) -[2023-10-09 00:53:07,621][88327] Updated weights for policy 1, policy_version 21490 (0.0008) -[2023-10-09 00:53:07,983][88327] Updated weights for policy 1, policy_version 21500 (0.0007) -[2023-10-09 00:53:08,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 44040192. Throughput: 0: 1687.2, 1: 1710.3. Samples: 11011706. Policy #0 lag: (min: 17.0, avg: 28.3, max: 49.0) -[2023-10-09 00:53:08,976][87372] Avg episode reward: [(0, '6.070'), (1, '5.180')] -[2023-10-09 00:53:10,219][88326] Updated weights for policy 0, policy_version 21512 (0.0008) -[2023-10-09 00:53:10,585][88326] Updated weights for policy 0, policy_version 21522 (0.0008) -[2023-10-09 00:53:10,963][88326] Updated weights for policy 0, policy_version 21532 (0.0009) -[2023-10-09 00:53:11,920][88327] Updated weights for policy 1, policy_version 21510 (0.0008) -[2023-10-09 00:53:12,290][88327] Updated weights for policy 1, policy_version 21520 (0.0009) -[2023-10-09 00:53:12,667][88327] Updated weights for policy 1, policy_version 21530 (0.0008) -[2023-10-09 00:53:13,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 44105728. Throughput: 0: 1690.8, 1: 1697.6. Samples: 11031970. Policy #0 lag: (min: 17.0, avg: 28.3, max: 49.0) -[2023-10-09 00:53:13,974][87372] Avg episode reward: [(0, '5.680'), (1, '5.030')] -[2023-10-09 00:53:15,086][88326] Updated weights for policy 0, policy_version 21542 (0.0009) -[2023-10-09 00:53:15,475][88326] Updated weights for policy 0, policy_version 21552 (0.0009) -[2023-10-09 00:53:15,847][88326] Updated weights for policy 0, policy_version 21562 (0.0010) -[2023-10-09 00:53:16,809][88327] Updated weights for policy 1, policy_version 21540 (0.0009) -[2023-10-09 00:53:17,171][88327] Updated weights for policy 1, policy_version 21550 (0.0010) -[2023-10-09 00:53:17,536][88327] Updated weights for policy 1, policy_version 21560 (0.0011) -[2023-10-09 00:53:18,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 44171264. Throughput: 0: 1708.8, 1: 1677.6. Samples: 11051964. Policy #0 lag: (min: 17.0, avg: 28.3, max: 49.0) -[2023-10-09 00:53:18,975][87372] Avg episode reward: [(0, '5.570'), (1, '4.930')] -[2023-10-09 00:53:19,976][88326] Updated weights for policy 0, policy_version 21572 (0.0007) -[2023-10-09 00:53:20,340][88326] Updated weights for policy 0, policy_version 21582 (0.0009) -[2023-10-09 00:53:20,711][88326] Updated weights for policy 0, policy_version 21592 (0.0009) -[2023-10-09 00:53:21,413][88327] Updated weights for policy 1, policy_version 21570 (0.0008) -[2023-10-09 00:53:21,777][88327] Updated weights for policy 1, policy_version 21580 (0.0009) -[2023-10-09 00:53:22,142][88327] Updated weights for policy 1, policy_version 21590 (0.0009) -[2023-10-09 00:53:22,508][88327] Updated weights for policy 1, policy_version 21600 (0.0009) -[2023-10-09 00:53:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 44236800. Throughput: 0: 1674.4, 1: 1704.7. Samples: 11062316. Policy #0 lag: (min: 31.0, avg: 34.3, max: 63.0) -[2023-10-09 00:53:23,974][87372] Avg episode reward: [(0, '5.600'), (1, '5.430')] -[2023-10-09 00:53:24,674][88326] Updated weights for policy 0, policy_version 21602 (0.0011) -[2023-10-09 00:53:25,046][88326] Updated weights for policy 0, policy_version 21612 (0.0009) -[2023-10-09 00:53:25,409][88326] Updated weights for policy 0, policy_version 21622 (0.0009) -[2023-10-09 00:53:25,786][88326] Updated weights for policy 0, policy_version 21632 (0.0008) -[2023-10-09 00:53:26,530][88327] Updated weights for policy 1, policy_version 21610 (0.0008) -[2023-10-09 00:53:26,909][88327] Updated weights for policy 1, policy_version 21620 (0.0008) -[2023-10-09 00:53:27,271][88327] Updated weights for policy 1, policy_version 21630 (0.0007) -[2023-10-09 00:53:28,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 44302336. Throughput: 0: 1691.5, 1: 1678.7. Samples: 11082130. Policy #0 lag: (min: 31.0, avg: 34.3, max: 63.0) -[2023-10-09 00:53:28,975][87372] Avg episode reward: [(0, '5.950'), (1, '5.010')] -[2023-10-09 00:53:29,787][88326] Updated weights for policy 0, policy_version 21642 (0.0010) -[2023-10-09 00:53:30,167][88326] Updated weights for policy 0, policy_version 21652 (0.0010) -[2023-10-09 00:53:30,527][88326] Updated weights for policy 0, policy_version 21662 (0.0009) -[2023-10-09 00:53:31,235][88327] Updated weights for policy 1, policy_version 21640 (0.0009) -[2023-10-09 00:53:31,611][88327] Updated weights for policy 1, policy_version 21650 (0.0008) -[2023-10-09 00:53:31,977][88327] Updated weights for policy 1, policy_version 21660 (0.0009) -[2023-10-09 00:53:33,974][87372] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 44367872. Throughput: 0: 1694.4, 1: 1689.4. Samples: 11102748. Policy #0 lag: (min: 31.0, avg: 34.3, max: 63.0) -[2023-10-09 00:53:33,975][87372] Avg episode reward: [(0, '5.810'), (1, '5.300')] -[2023-10-09 00:53:34,787][88326] Updated weights for policy 0, policy_version 21672 (0.0009) -[2023-10-09 00:53:35,155][88326] Updated weights for policy 0, policy_version 21682 (0.0007) -[2023-10-09 00:53:35,529][88326] Updated weights for policy 0, policy_version 21692 (0.0009) -[2023-10-09 00:53:35,950][88327] Updated weights for policy 1, policy_version 21670 (0.0007) -[2023-10-09 00:53:36,320][88327] Updated weights for policy 1, policy_version 21680 (0.0009) -[2023-10-09 00:53:36,686][88327] Updated weights for policy 1, policy_version 21690 (0.0009) -[2023-10-09 00:53:38,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 44433408. Throughput: 0: 1673.9, 1: 1693.0. Samples: 11112820. Policy #0 lag: (min: 31.0, avg: 34.3, max: 63.0) -[2023-10-09 00:53:38,975][87372] Avg episode reward: [(0, '5.890'), (1, '4.820')] -[2023-10-09 00:53:39,626][88326] Updated weights for policy 0, policy_version 21702 (0.0008) -[2023-10-09 00:53:39,987][88326] Updated weights for policy 0, policy_version 21712 (0.0009) -[2023-10-09 00:53:40,344][88326] Updated weights for policy 0, policy_version 21722 (0.0009) -[2023-10-09 00:53:40,440][88327] Updated weights for policy 1, policy_version 21700 (0.0009) -[2023-10-09 00:53:40,809][88327] Updated weights for policy 1, policy_version 21710 (0.0010) -[2023-10-09 00:53:41,179][88327] Updated weights for policy 1, policy_version 21720 (0.0009) -[2023-10-09 00:53:43,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 44498944. Throughput: 0: 1696.7, 1: 1675.3. Samples: 11133072. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) -[2023-10-09 00:53:43,975][87372] Avg episode reward: [(0, '6.340'), (1, '5.000')] -[2023-10-09 00:53:43,976][88088] Saving new best policy, reward=6.340! -[2023-10-09 00:53:44,495][88326] Updated weights for policy 0, policy_version 21732 (0.0009) -[2023-10-09 00:53:44,867][88326] Updated weights for policy 0, policy_version 21742 (0.0010) -[2023-10-09 00:53:45,234][88326] Updated weights for policy 0, policy_version 21752 (0.0008) -[2023-10-09 00:53:45,317][88327] Updated weights for policy 1, policy_version 21730 (0.0008) -[2023-10-09 00:53:45,711][88327] Updated weights for policy 1, policy_version 21740 (0.0009) -[2023-10-09 00:53:46,076][88327] Updated weights for policy 1, policy_version 21750 (0.0009) -[2023-10-09 00:53:46,450][88327] Updated weights for policy 1, policy_version 21760 (0.0008) -[2023-10-09 00:53:48,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 44564480. Throughput: 0: 1687.1, 1: 1704.3. Samples: 11153688. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) -[2023-10-09 00:53:48,975][87372] Avg episode reward: [(0, '5.980'), (1, '4.790')] -[2023-10-09 00:53:49,196][88326] Updated weights for policy 0, policy_version 21762 (0.0008) -[2023-10-09 00:53:49,576][88326] Updated weights for policy 0, policy_version 21772 (0.0009) -[2023-10-09 00:53:49,946][88326] Updated weights for policy 0, policy_version 21782 (0.0009) -[2023-10-09 00:53:50,308][88326] Updated weights for policy 0, policy_version 21792 (0.0009) -[2023-10-09 00:53:50,606][88327] Updated weights for policy 1, policy_version 21770 (0.0007) -[2023-10-09 00:53:50,968][88327] Updated weights for policy 1, policy_version 21780 (0.0007) -[2023-10-09 00:53:51,342][88327] Updated weights for policy 1, policy_version 21790 (0.0009) -[2023-10-09 00:53:53,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 44630016. Throughput: 0: 1683.2, 1: 1684.9. Samples: 11163272. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) -[2023-10-09 00:53:53,975][87372] Avg episode reward: [(0, '5.820'), (1, '5.040')] -[2023-10-09 00:53:54,322][88326] Updated weights for policy 0, policy_version 21802 (0.0009) -[2023-10-09 00:53:54,685][88326] Updated weights for policy 0, policy_version 21812 (0.0008) -[2023-10-09 00:53:55,049][88326] Updated weights for policy 0, policy_version 21822 (0.0007) -[2023-10-09 00:53:55,390][88327] Updated weights for policy 1, policy_version 21800 (0.0010) -[2023-10-09 00:53:55,747][88327] Updated weights for policy 1, policy_version 21810 (0.0010) -[2023-10-09 00:53:56,111][88327] Updated weights for policy 1, policy_version 21820 (0.0011) -[2023-10-09 00:53:58,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 44695552. Throughput: 0: 1689.4, 1: 1686.7. Samples: 11183892. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) -[2023-10-09 00:53:58,975][87372] Avg episode reward: [(0, '5.850'), (1, '4.960')] -[2023-10-09 00:53:59,035][88326] Updated weights for policy 0, policy_version 21832 (0.0009) -[2023-10-09 00:53:59,417][88326] Updated weights for policy 0, policy_version 21842 (0.0009) -[2023-10-09 00:53:59,785][88326] Updated weights for policy 0, policy_version 21852 (0.0010) -[2023-10-09 00:54:00,116][88327] Updated weights for policy 1, policy_version 21830 (0.0008) -[2023-10-09 00:54:00,489][88327] Updated weights for policy 1, policy_version 21840 (0.0008) -[2023-10-09 00:54:00,852][88327] Updated weights for policy 1, policy_version 21850 (0.0010) -[2023-10-09 00:54:03,774][88326] Updated weights for policy 0, policy_version 21862 (0.0008) -[2023-10-09 00:54:03,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 44761088. Throughput: 0: 1693.0, 1: 1704.1. Samples: 11204834. Policy #0 lag: (min: 13.0, avg: 20.5, max: 45.0) -[2023-10-09 00:54:03,975][87372] Avg episode reward: [(0, '5.450'), (1, '4.870')] -[2023-10-09 00:54:04,141][88326] Updated weights for policy 0, policy_version 21872 (0.0008) -[2023-10-09 00:54:04,510][88326] Updated weights for policy 0, policy_version 21882 (0.0007) -[2023-10-09 00:54:04,750][88327] Updated weights for policy 1, policy_version 21860 (0.0011) -[2023-10-09 00:54:05,106][88327] Updated weights for policy 1, policy_version 21870 (0.0011) -[2023-10-09 00:54:05,468][88327] Updated weights for policy 1, policy_version 21880 (0.0009) -[2023-10-09 00:54:08,472][88326] Updated weights for policy 0, policy_version 21892 (0.0007) -[2023-10-09 00:54:08,837][88326] Updated weights for policy 0, policy_version 21902 (0.0009) -[2023-10-09 00:54:08,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 44826624. Throughput: 0: 1696.1, 1: 1677.1. Samples: 11214108. Policy #0 lag: (min: 13.0, avg: 20.5, max: 45.0) -[2023-10-09 00:54:08,974][87372] Avg episode reward: [(0, '5.500'), (1, '5.080')] -[2023-10-09 00:54:09,217][88326] Updated weights for policy 0, policy_version 21912 (0.0010) -[2023-10-09 00:54:09,501][88327] Updated weights for policy 1, policy_version 21890 (0.0008) -[2023-10-09 00:54:09,871][88327] Updated weights for policy 1, policy_version 21900 (0.0008) -[2023-10-09 00:54:10,235][88327] Updated weights for policy 1, policy_version 21910 (0.0009) -[2023-10-09 00:54:10,603][88327] Updated weights for policy 1, policy_version 21920 (0.0009) -[2023-10-09 00:54:13,238][88326] Updated weights for policy 0, policy_version 21922 (0.0008) -[2023-10-09 00:54:13,606][88326] Updated weights for policy 0, policy_version 21932 (0.0009) -[2023-10-09 00:54:13,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 44892160. Throughput: 0: 1703.9, 1: 1696.9. Samples: 11235166. Policy #0 lag: (min: 13.0, avg: 20.5, max: 45.0) -[2023-10-09 00:54:13,975][87372] Avg episode reward: [(0, '5.700'), (1, '5.050')] -[2023-10-09 00:54:13,983][88326] Updated weights for policy 0, policy_version 21942 (0.0007) -[2023-10-09 00:54:14,351][88326] Updated weights for policy 0, policy_version 21952 (0.0007) -[2023-10-09 00:54:14,652][88327] Updated weights for policy 1, policy_version 21930 (0.0011) -[2023-10-09 00:54:15,014][88327] Updated weights for policy 1, policy_version 21940 (0.0010) -[2023-10-09 00:54:15,374][88327] Updated weights for policy 1, policy_version 21950 (0.0010) -[2023-10-09 00:54:18,424][88326] Updated weights for policy 0, policy_version 21962 (0.0007) -[2023-10-09 00:54:18,785][88326] Updated weights for policy 0, policy_version 21972 (0.0010) -[2023-10-09 00:54:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 44957696. Throughput: 0: 1699.7, 1: 1706.2. Samples: 11256012. Policy #0 lag: (min: 13.0, avg: 20.5, max: 45.0) -[2023-10-09 00:54:18,975][87372] Avg episode reward: [(0, '5.980'), (1, '5.100')] -[2023-10-09 00:54:19,155][88326] Updated weights for policy 0, policy_version 21982 (0.0011) -[2023-10-09 00:54:19,532][88327] Updated weights for policy 1, policy_version 21960 (0.0009) -[2023-10-09 00:54:19,909][88327] Updated weights for policy 1, policy_version 21970 (0.0007) -[2023-10-09 00:54:20,270][88327] Updated weights for policy 1, policy_version 21980 (0.0011) -[2023-10-09 00:54:23,218][88326] Updated weights for policy 0, policy_version 21992 (0.0008) -[2023-10-09 00:54:23,583][88326] Updated weights for policy 0, policy_version 22002 (0.0007) -[2023-10-09 00:54:23,960][88326] Updated weights for policy 0, policy_version 22012 (0.0009) -[2023-10-09 00:54:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.1, 300 sec: 13440.4). Total num frames: 45023232. Throughput: 0: 1702.7, 1: 1682.1. Samples: 11265136. Policy #0 lag: (min: 18.0, avg: 18.0, max: 18.0) -[2023-10-09 00:54:23,975][87372] Avg episode reward: [(0, '5.630'), (1, '4.830')] -[2023-10-09 00:54:24,427][88327] Updated weights for policy 1, policy_version 21990 (0.0011) -[2023-10-09 00:54:24,797][88327] Updated weights for policy 1, policy_version 22000 (0.0011) -[2023-10-09 00:54:25,173][88327] Updated weights for policy 1, policy_version 22010 (0.0010) -[2023-10-09 00:54:27,810][88326] Updated weights for policy 0, policy_version 22022 (0.0008) -[2023-10-09 00:54:28,188][88326] Updated weights for policy 0, policy_version 22032 (0.0008) -[2023-10-09 00:54:28,565][88326] Updated weights for policy 0, policy_version 22042 (0.0008) -[2023-10-09 00:54:28,974][87372] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 45121536. Throughput: 0: 1704.0, 1: 1702.0. Samples: 11286344. Policy #0 lag: (min: 18.0, avg: 18.0, max: 18.0) -[2023-10-09 00:54:28,975][87372] Avg episode reward: [(0, '5.780'), (1, '4.580')] -[2023-10-09 00:54:29,241][88327] Updated weights for policy 1, policy_version 22020 (0.0010) -[2023-10-09 00:54:29,610][88327] Updated weights for policy 1, policy_version 22030 (0.0007) -[2023-10-09 00:54:29,979][88327] Updated weights for policy 1, policy_version 22040 (0.0009) -[2023-10-09 00:54:32,712][88326] Updated weights for policy 0, policy_version 22052 (0.0008) -[2023-10-09 00:54:33,076][88326] Updated weights for policy 0, policy_version 22062 (0.0008) -[2023-10-09 00:54:33,449][88326] Updated weights for policy 0, policy_version 22072 (0.0007) -[2023-10-09 00:54:33,974][87372] Fps is (10 sec: 16384.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 45187072. Throughput: 0: 1693.3, 1: 1706.6. Samples: 11306684. Policy #0 lag: (min: 18.0, avg: 18.0, max: 18.0) -[2023-10-09 00:54:33,975][87372] Avg episode reward: [(0, '5.910'), (1, '4.970')] -[2023-10-09 00:54:33,982][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000022080_22609920.pth... -[2023-10-09 00:54:34,011][88327] Updated weights for policy 1, policy_version 22050 (0.0009) -[2023-10-09 00:54:34,015][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000020480_20971520.pth -[2023-10-09 00:54:34,411][88327] Updated weights for policy 1, policy_version 22060 (0.0008) -[2023-10-09 00:54:34,779][88327] Updated weights for policy 1, policy_version 22070 (0.0008) -[2023-10-09 00:54:35,132][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000022080_22609920.pth... -[2023-10-09 00:54:35,133][88327] Updated weights for policy 1, policy_version 22080 (0.0009) -[2023-10-09 00:54:35,170][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000020480_20971520.pth -[2023-10-09 00:54:37,487][88326] Updated weights for policy 0, policy_version 22082 (0.0007) -[2023-10-09 00:54:37,868][88326] Updated weights for policy 0, policy_version 22092 (0.0008) -[2023-10-09 00:54:38,242][88326] Updated weights for policy 0, policy_version 22102 (0.0009) -[2023-10-09 00:54:38,617][88326] Updated weights for policy 0, policy_version 22112 (0.0010) -[2023-10-09 00:54:38,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 45252608. Throughput: 0: 1710.3, 1: 1694.2. Samples: 11316474. Policy #0 lag: (min: 31.0, avg: 32.5, max: 58.0) -[2023-10-09 00:54:38,975][87372] Avg episode reward: [(0, '5.590'), (1, '5.050')] -[2023-10-09 00:54:39,263][88327] Updated weights for policy 1, policy_version 22090 (0.0009) -[2023-10-09 00:54:39,632][88327] Updated weights for policy 1, policy_version 22100 (0.0008) -[2023-10-09 00:54:39,999][88327] Updated weights for policy 1, policy_version 22110 (0.0007) -[2023-10-09 00:54:42,701][88326] Updated weights for policy 0, policy_version 22122 (0.0011) -[2023-10-09 00:54:43,071][88326] Updated weights for policy 0, policy_version 22132 (0.0008) -[2023-10-09 00:54:43,438][88326] Updated weights for policy 0, policy_version 22142 (0.0010) -[2023-10-09 00:54:43,970][88327] Updated weights for policy 1, policy_version 22120 (0.0008) -[2023-10-09 00:54:43,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 45318144. Throughput: 0: 1707.9, 1: 1698.5. Samples: 11337180. Policy #0 lag: (min: 31.0, avg: 32.5, max: 58.0) -[2023-10-09 00:54:43,974][87372] Avg episode reward: [(0, '5.270'), (1, '5.360')] -[2023-10-09 00:54:44,340][88327] Updated weights for policy 1, policy_version 22130 (0.0008) -[2023-10-09 00:54:44,711][88327] Updated weights for policy 1, policy_version 22140 (0.0008) -[2023-10-09 00:54:47,511][88326] Updated weights for policy 0, policy_version 22152 (0.0010) -[2023-10-09 00:54:47,890][88326] Updated weights for policy 0, policy_version 22162 (0.0011) -[2023-10-09 00:54:48,257][88326] Updated weights for policy 0, policy_version 22172 (0.0010) -[2023-10-09 00:54:48,766][88327] Updated weights for policy 1, policy_version 22150 (0.0010) -[2023-10-09 00:54:48,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 45383680. Throughput: 0: 1680.7, 1: 1701.8. Samples: 11357046. Policy #0 lag: (min: 31.0, avg: 32.5, max: 58.0) -[2023-10-09 00:54:48,975][87372] Avg episode reward: [(0, '5.590'), (1, '5.440')] -[2023-10-09 00:54:49,129][88327] Updated weights for policy 1, policy_version 22160 (0.0010) -[2023-10-09 00:54:49,486][88327] Updated weights for policy 1, policy_version 22170 (0.0010) -[2023-10-09 00:54:52,362][88326] Updated weights for policy 0, policy_version 22182 (0.0010) -[2023-10-09 00:54:52,745][88326] Updated weights for policy 0, policy_version 22192 (0.0007) -[2023-10-09 00:54:53,123][88326] Updated weights for policy 0, policy_version 22202 (0.0007) -[2023-10-09 00:54:53,554][88327] Updated weights for policy 1, policy_version 22180 (0.0009) -[2023-10-09 00:54:53,925][88327] Updated weights for policy 1, policy_version 22190 (0.0007) -[2023-10-09 00:54:53,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 45449216. Throughput: 0: 1700.2, 1: 1700.3. Samples: 11367128. Policy #0 lag: (min: 31.0, avg: 32.5, max: 58.0) -[2023-10-09 00:54:53,975][87372] Avg episode reward: [(0, '5.030'), (1, '5.230')] -[2023-10-09 00:54:54,296][88327] Updated weights for policy 1, policy_version 22200 (0.0009) -[2023-10-09 00:54:56,866][88326] Updated weights for policy 0, policy_version 22212 (0.0008) -[2023-10-09 00:54:57,230][88326] Updated weights for policy 0, policy_version 22222 (0.0009) -[2023-10-09 00:54:57,605][88326] Updated weights for policy 0, policy_version 22232 (0.0009) -[2023-10-09 00:54:58,238][88327] Updated weights for policy 1, policy_version 22210 (0.0008) -[2023-10-09 00:54:58,596][88327] Updated weights for policy 1, policy_version 22220 (0.0010) -[2023-10-09 00:54:58,966][88327] Updated weights for policy 1, policy_version 22230 (0.0008) -[2023-10-09 00:54:58,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 45514752. Throughput: 0: 1686.1, 1: 1699.5. Samples: 11387518. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 00:54:58,975][87372] Avg episode reward: [(0, '5.040'), (1, '5.540')] -[2023-10-09 00:54:59,341][88327] Updated weights for policy 1, policy_version 22240 (0.0010) -[2023-10-09 00:55:01,634][88326] Updated weights for policy 0, policy_version 22242 (0.0008) -[2023-10-09 00:55:02,006][88326] Updated weights for policy 0, policy_version 22252 (0.0011) -[2023-10-09 00:55:02,377][88326] Updated weights for policy 0, policy_version 22262 (0.0007) -[2023-10-09 00:55:02,735][88326] Updated weights for policy 0, policy_version 22272 (0.0010) -[2023-10-09 00:55:03,317][88327] Updated weights for policy 1, policy_version 22250 (0.0009) -[2023-10-09 00:55:03,692][88327] Updated weights for policy 1, policy_version 22260 (0.0009) -[2023-10-09 00:55:03,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 45580288. Throughput: 0: 1673.0, 1: 1689.1. Samples: 11407306. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 00:55:03,975][87372] Avg episode reward: [(0, '5.650'), (1, '5.230')] -[2023-10-09 00:55:04,068][88327] Updated weights for policy 1, policy_version 22270 (0.0009) -[2023-10-09 00:55:06,770][88326] Updated weights for policy 0, policy_version 22282 (0.0007) -[2023-10-09 00:55:07,130][88326] Updated weights for policy 0, policy_version 22292 (0.0009) -[2023-10-09 00:55:07,510][88326] Updated weights for policy 0, policy_version 22302 (0.0011) -[2023-10-09 00:55:08,125][88327] Updated weights for policy 1, policy_version 22280 (0.0010) -[2023-10-09 00:55:08,479][88327] Updated weights for policy 1, policy_version 22290 (0.0008) -[2023-10-09 00:55:08,844][88327] Updated weights for policy 1, policy_version 22300 (0.0010) -[2023-10-09 00:55:08,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 45645824. Throughput: 0: 1700.0, 1: 1698.3. Samples: 11418058. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 00:55:08,975][87372] Avg episode reward: [(0, '5.260'), (1, '5.180')] -[2023-10-09 00:55:11,547][88326] Updated weights for policy 0, policy_version 22312 (0.0010) -[2023-10-09 00:55:11,921][88326] Updated weights for policy 0, policy_version 22322 (0.0007) -[2023-10-09 00:55:12,283][88326] Updated weights for policy 0, policy_version 22332 (0.0011) -[2023-10-09 00:55:12,864][88327] Updated weights for policy 1, policy_version 22310 (0.0009) -[2023-10-09 00:55:13,231][88327] Updated weights for policy 1, policy_version 22320 (0.0009) -[2023-10-09 00:55:13,605][88327] Updated weights for policy 1, policy_version 22330 (0.0009) -[2023-10-09 00:55:13,974][87372] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 45744128. Throughput: 0: 1671.8, 1: 1695.9. Samples: 11437888. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 00:55:13,975][87372] Avg episode reward: [(0, '5.490'), (1, '5.500')] -[2023-10-09 00:55:16,153][88326] Updated weights for policy 0, policy_version 22342 (0.0009) -[2023-10-09 00:55:16,526][88326] Updated weights for policy 0, policy_version 22352 (0.0009) -[2023-10-09 00:55:16,900][88326] Updated weights for policy 0, policy_version 22362 (0.0010) -[2023-10-09 00:55:17,638][88327] Updated weights for policy 1, policy_version 22340 (0.0009) -[2023-10-09 00:55:18,009][88327] Updated weights for policy 1, policy_version 22350 (0.0008) -[2023-10-09 00:55:18,379][88327] Updated weights for policy 1, policy_version 22360 (0.0010) -[2023-10-09 00:55:18,974][87372] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 45809664. Throughput: 0: 1686.3, 1: 1680.2. Samples: 11458174. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:55:18,975][87372] Avg episode reward: [(0, '5.880'), (1, '5.240')] -[2023-10-09 00:55:20,984][88326] Updated weights for policy 0, policy_version 22372 (0.0009) -[2023-10-09 00:55:21,350][88326] Updated weights for policy 0, policy_version 22382 (0.0010) -[2023-10-09 00:55:21,715][88326] Updated weights for policy 0, policy_version 22392 (0.0011) -[2023-10-09 00:55:22,301][88327] Updated weights for policy 1, policy_version 22370 (0.0010) -[2023-10-09 00:55:22,728][88327] Updated weights for policy 1, policy_version 22380 (0.0009) -[2023-10-09 00:55:23,085][88327] Updated weights for policy 1, policy_version 22390 (0.0008) -[2023-10-09 00:55:23,455][88327] Updated weights for policy 1, policy_version 22400 (0.0009) -[2023-10-09 00:55:23,974][87372] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 45875200. Throughput: 0: 1687.0, 1: 1699.4. Samples: 11468862. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:55:23,975][87372] Avg episode reward: [(0, '5.690'), (1, '5.440')] -[2023-10-09 00:55:25,777][88326] Updated weights for policy 0, policy_version 22402 (0.0009) -[2023-10-09 00:55:26,145][88326] Updated weights for policy 0, policy_version 22412 (0.0009) -[2023-10-09 00:55:26,513][88326] Updated weights for policy 0, policy_version 22422 (0.0007) -[2023-10-09 00:55:26,882][88326] Updated weights for policy 0, policy_version 22432 (0.0009) -[2023-10-09 00:55:27,446][88327] Updated weights for policy 1, policy_version 22410 (0.0010) -[2023-10-09 00:55:27,809][88327] Updated weights for policy 1, policy_version 22420 (0.0009) -[2023-10-09 00:55:28,169][88327] Updated weights for policy 1, policy_version 22430 (0.0009) -[2023-10-09 00:55:28,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 45940736. Throughput: 0: 1665.7, 1: 1701.5. Samples: 11488706. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:55:28,975][87372] Avg episode reward: [(0, '5.530'), (1, '5.530')] -[2023-10-09 00:55:30,870][88326] Updated weights for policy 0, policy_version 22442 (0.0011) -[2023-10-09 00:55:31,251][88326] Updated weights for policy 0, policy_version 22452 (0.0009) -[2023-10-09 00:55:31,612][88326] Updated weights for policy 0, policy_version 22462 (0.0008) -[2023-10-09 00:55:32,312][88327] Updated weights for policy 1, policy_version 22440 (0.0008) -[2023-10-09 00:55:32,672][88327] Updated weights for policy 1, policy_version 22450 (0.0008) -[2023-10-09 00:55:33,036][88327] Updated weights for policy 1, policy_version 22460 (0.0008) -[2023-10-09 00:55:33,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 46006272. Throughput: 0: 1700.5, 1: 1676.1. Samples: 11508992. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:55:33,975][87372] Avg episode reward: [(0, '5.720'), (1, '5.330')] -[2023-10-09 00:55:35,529][88326] Updated weights for policy 0, policy_version 22472 (0.0008) -[2023-10-09 00:55:35,903][88326] Updated weights for policy 0, policy_version 22482 (0.0008) -[2023-10-09 00:55:36,268][88326] Updated weights for policy 0, policy_version 22492 (0.0010) -[2023-10-09 00:55:37,088][88327] Updated weights for policy 1, policy_version 22470 (0.0008) -[2023-10-09 00:55:37,458][88327] Updated weights for policy 1, policy_version 22480 (0.0007) -[2023-10-09 00:55:37,828][88327] Updated weights for policy 1, policy_version 22490 (0.0008) -[2023-10-09 00:55:38,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 46071808. Throughput: 0: 1684.7, 1: 1701.1. Samples: 11519490. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 00:55:38,975][87372] Avg episode reward: [(0, '5.360'), (1, '5.400')] -[2023-10-09 00:55:40,342][88326] Updated weights for policy 0, policy_version 22502 (0.0008) -[2023-10-09 00:55:40,710][88326] Updated weights for policy 0, policy_version 22512 (0.0007) -[2023-10-09 00:55:41,086][88326] Updated weights for policy 0, policy_version 22522 (0.0007) -[2023-10-09 00:55:41,905][88327] Updated weights for policy 1, policy_version 22500 (0.0009) -[2023-10-09 00:55:42,266][88327] Updated weights for policy 1, policy_version 22510 (0.0009) -[2023-10-09 00:55:42,628][88327] Updated weights for policy 1, policy_version 22520 (0.0010) -[2023-10-09 00:55:43,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 46137344. Throughput: 0: 1690.2, 1: 1690.2. Samples: 11539638. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 00:55:43,975][87372] Avg episode reward: [(0, '5.400'), (1, '5.340')] -[2023-10-09 00:55:45,127][88326] Updated weights for policy 0, policy_version 22532 (0.0007) -[2023-10-09 00:55:45,487][88326] Updated weights for policy 0, policy_version 22542 (0.0009) -[2023-10-09 00:55:45,858][88326] Updated weights for policy 0, policy_version 22552 (0.0011) -[2023-10-09 00:55:46,746][88327] Updated weights for policy 1, policy_version 22530 (0.0010) -[2023-10-09 00:55:47,117][88327] Updated weights for policy 1, policy_version 22540 (0.0009) -[2023-10-09 00:55:47,494][88327] Updated weights for policy 1, policy_version 22550 (0.0010) -[2023-10-09 00:55:47,852][88327] Updated weights for policy 1, policy_version 22560 (0.0010) -[2023-10-09 00:55:48,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 46202880. Throughput: 0: 1709.5, 1: 1674.1. Samples: 11559566. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 00:55:48,975][87372] Avg episode reward: [(0, '5.860'), (1, '5.120')] -[2023-10-09 00:55:49,967][88326] Updated weights for policy 0, policy_version 22562 (0.0010) -[2023-10-09 00:55:50,343][88326] Updated weights for policy 0, policy_version 22572 (0.0011) -[2023-10-09 00:55:50,697][88326] Updated weights for policy 0, policy_version 22582 (0.0011) -[2023-10-09 00:55:51,063][88326] Updated weights for policy 0, policy_version 22592 (0.0008) -[2023-10-09 00:55:51,942][88327] Updated weights for policy 1, policy_version 22570 (0.0010) -[2023-10-09 00:55:52,305][88327] Updated weights for policy 1, policy_version 22580 (0.0009) -[2023-10-09 00:55:52,671][88327] Updated weights for policy 1, policy_version 22590 (0.0009) -[2023-10-09 00:55:53,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 46268416. Throughput: 0: 1677.9, 1: 1697.2. Samples: 11569938. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 00:55:53,975][87372] Avg episode reward: [(0, '5.670'), (1, '5.020')] -[2023-10-09 00:55:55,004][88326] Updated weights for policy 0, policy_version 22602 (0.0008) -[2023-10-09 00:55:55,377][88326] Updated weights for policy 0, policy_version 22612 (0.0008) -[2023-10-09 00:55:55,749][88326] Updated weights for policy 0, policy_version 22622 (0.0009) -[2023-10-09 00:55:56,486][88327] Updated weights for policy 1, policy_version 22600 (0.0009) -[2023-10-09 00:55:56,865][88327] Updated weights for policy 1, policy_version 22610 (0.0007) -[2023-10-09 00:55:57,232][88327] Updated weights for policy 1, policy_version 22620 (0.0007) -[2023-10-09 00:55:58,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 46333952. Throughput: 0: 1706.5, 1: 1676.7. Samples: 11590134. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-09 00:55:58,975][87372] Avg episode reward: [(0, '5.770'), (1, '5.130')] -[2023-10-09 00:55:59,874][88326] Updated weights for policy 0, policy_version 22632 (0.0007) -[2023-10-09 00:56:00,255][88326] Updated weights for policy 0, policy_version 22642 (0.0009) -[2023-10-09 00:56:00,619][88326] Updated weights for policy 0, policy_version 22652 (0.0007) -[2023-10-09 00:56:01,183][88327] Updated weights for policy 1, policy_version 22630 (0.0007) -[2023-10-09 00:56:01,549][88327] Updated weights for policy 1, policy_version 22640 (0.0009) -[2023-10-09 00:56:01,924][88327] Updated weights for policy 1, policy_version 22650 (0.0009) -[2023-10-09 00:56:03,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 46399488. Throughput: 0: 1707.9, 1: 1683.2. Samples: 11610778. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-09 00:56:03,975][87372] Avg episode reward: [(0, '5.730'), (1, '4.690')] -[2023-10-09 00:56:04,675][88326] Updated weights for policy 0, policy_version 22662 (0.0009) -[2023-10-09 00:56:05,039][88326] Updated weights for policy 0, policy_version 22672 (0.0007) -[2023-10-09 00:56:05,411][88326] Updated weights for policy 0, policy_version 22682 (0.0009) -[2023-10-09 00:56:06,102][88327] Updated weights for policy 1, policy_version 22660 (0.0007) -[2023-10-09 00:56:06,464][88327] Updated weights for policy 1, policy_version 22670 (0.0007) -[2023-10-09 00:56:06,830][88327] Updated weights for policy 1, policy_version 22680 (0.0007) -[2023-10-09 00:56:08,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 46465024. Throughput: 0: 1687.3, 1: 1690.4. Samples: 11620860. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-09 00:56:08,975][87372] Avg episode reward: [(0, '5.470'), (1, '4.610')] -[2023-10-09 00:56:09,389][88326] Updated weights for policy 0, policy_version 22692 (0.0009) -[2023-10-09 00:56:09,751][88326] Updated weights for policy 0, policy_version 22702 (0.0007) -[2023-10-09 00:56:10,117][88326] Updated weights for policy 0, policy_version 22712 (0.0009) -[2023-10-09 00:56:10,694][88327] Updated weights for policy 1, policy_version 22690 (0.0008) -[2023-10-09 00:56:11,058][88327] Updated weights for policy 1, policy_version 22700 (0.0009) -[2023-10-09 00:56:11,429][88327] Updated weights for policy 1, policy_version 22710 (0.0007) -[2023-10-09 00:56:11,792][88327] Updated weights for policy 1, policy_version 22720 (0.0009) -[2023-10-09 00:56:13,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 46530560. Throughput: 0: 1716.8, 1: 1668.3. Samples: 11641034. Policy #0 lag: (min: 31.0, avg: 31.3, max: 43.0) -[2023-10-09 00:56:13,975][87372] Avg episode reward: [(0, '5.380'), (1, '5.330')] -[2023-10-09 00:56:14,019][88326] Updated weights for policy 0, policy_version 22722 (0.0009) -[2023-10-09 00:56:14,387][88326] Updated weights for policy 0, policy_version 22732 (0.0008) -[2023-10-09 00:56:14,761][88326] Updated weights for policy 0, policy_version 22742 (0.0008) -[2023-10-09 00:56:15,127][88326] Updated weights for policy 0, policy_version 22752 (0.0009) -[2023-10-09 00:56:15,972][88327] Updated weights for policy 1, policy_version 22730 (0.0009) -[2023-10-09 00:56:16,347][88327] Updated weights for policy 1, policy_version 22740 (0.0008) -[2023-10-09 00:56:16,705][88327] Updated weights for policy 1, policy_version 22750 (0.0011) -[2023-10-09 00:56:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 46596096. Throughput: 0: 1709.0, 1: 1687.4. Samples: 11661830. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:56:18,975][87372] Avg episode reward: [(0, '5.770'), (1, '5.130')] -[2023-10-09 00:56:19,278][88326] Updated weights for policy 0, policy_version 22762 (0.0009) -[2023-10-09 00:56:19,642][88326] Updated weights for policy 0, policy_version 22772 (0.0008) -[2023-10-09 00:56:20,005][88326] Updated weights for policy 0, policy_version 22782 (0.0009) -[2023-10-09 00:56:20,641][88327] Updated weights for policy 1, policy_version 22760 (0.0012) -[2023-10-09 00:56:21,012][88327] Updated weights for policy 1, policy_version 22770 (0.0010) -[2023-10-09 00:56:21,370][88327] Updated weights for policy 1, policy_version 22780 (0.0009) -[2023-10-09 00:56:23,862][88326] Updated weights for policy 0, policy_version 22792 (0.0008) -[2023-10-09 00:56:23,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 46661632. Throughput: 0: 1703.9, 1: 1670.2. Samples: 11671326. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:56:23,975][87372] Avg episode reward: [(0, '5.940'), (1, '5.340')] -[2023-10-09 00:56:24,244][88326] Updated weights for policy 0, policy_version 22802 (0.0010) -[2023-10-09 00:56:24,611][88326] Updated weights for policy 0, policy_version 22812 (0.0009) -[2023-10-09 00:56:25,341][88327] Updated weights for policy 1, policy_version 22790 (0.0007) -[2023-10-09 00:56:25,706][88327] Updated weights for policy 1, policy_version 22800 (0.0008) -[2023-10-09 00:56:26,071][88327] Updated weights for policy 1, policy_version 22810 (0.0007) -[2023-10-09 00:56:28,626][88326] Updated weights for policy 0, policy_version 22822 (0.0009) -[2023-10-09 00:56:28,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 46727168. Throughput: 0: 1707.2, 1: 1675.1. Samples: 11691844. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:56:28,975][87372] Avg episode reward: [(0, '5.890'), (1, '5.670')] -[2023-10-09 00:56:28,977][88168] Saving new best policy, reward=5.670! -[2023-10-09 00:56:29,006][88326] Updated weights for policy 0, policy_version 22832 (0.0008) -[2023-10-09 00:56:29,384][88326] Updated weights for policy 0, policy_version 22842 (0.0009) -[2023-10-09 00:56:30,052][88327] Updated weights for policy 1, policy_version 22820 (0.0008) -[2023-10-09 00:56:30,423][88327] Updated weights for policy 1, policy_version 22830 (0.0008) -[2023-10-09 00:56:30,790][88327] Updated weights for policy 1, policy_version 22840 (0.0010) -[2023-10-09 00:56:33,350][88326] Updated weights for policy 0, policy_version 22852 (0.0010) -[2023-10-09 00:56:33,731][88326] Updated weights for policy 0, policy_version 22862 (0.0011) -[2023-10-09 00:56:33,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 46792704. Throughput: 0: 1710.7, 1: 1699.3. Samples: 11713014. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:56:33,975][87372] Avg episode reward: [(0, '6.090'), (1, '5.210')] -[2023-10-09 00:56:33,986][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000022848_23396352.pth... -[2023-10-09 00:56:34,020][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000021280_21790720.pth -[2023-10-09 00:56:34,096][88326] Updated weights for policy 0, policy_version 22872 (0.0008) -[2023-10-09 00:56:34,396][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000022880_23429120.pth... -[2023-10-09 00:56:34,435][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000021280_21790720.pth -[2023-10-09 00:56:34,846][88327] Updated weights for policy 1, policy_version 22850 (0.0010) -[2023-10-09 00:56:35,206][88327] Updated weights for policy 1, policy_version 22860 (0.0011) -[2023-10-09 00:56:35,570][88327] Updated weights for policy 1, policy_version 22870 (0.0009) -[2023-10-09 00:56:35,930][88327] Updated weights for policy 1, policy_version 22880 (0.0009) -[2023-10-09 00:56:37,974][88326] Updated weights for policy 0, policy_version 22882 (0.0011) -[2023-10-09 00:56:38,340][88326] Updated weights for policy 0, policy_version 22892 (0.0009) -[2023-10-09 00:56:38,713][88326] Updated weights for policy 0, policy_version 22902 (0.0009) -[2023-10-09 00:56:38,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 46858240. Throughput: 0: 1714.9, 1: 1672.7. Samples: 11722382. Policy #0 lag: (min: 16.0, avg: 32.4, max: 48.0) -[2023-10-09 00:56:38,975][87372] Avg episode reward: [(0, '6.350'), (1, '5.440')] -[2023-10-09 00:56:39,073][88088] Saving new best policy, reward=6.350! -[2023-10-09 00:56:39,074][88326] Updated weights for policy 0, policy_version 22912 (0.0008) -[2023-10-09 00:56:39,919][88327] Updated weights for policy 1, policy_version 22890 (0.0009) -[2023-10-09 00:56:40,283][88327] Updated weights for policy 1, policy_version 22900 (0.0009) -[2023-10-09 00:56:40,654][88327] Updated weights for policy 1, policy_version 22910 (0.0011) -[2023-10-09 00:56:43,213][88326] Updated weights for policy 0, policy_version 22922 (0.0007) -[2023-10-09 00:56:43,588][88326] Updated weights for policy 0, policy_version 22932 (0.0008) -[2023-10-09 00:56:43,954][88326] Updated weights for policy 0, policy_version 22942 (0.0008) -[2023-10-09 00:56:43,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 46923776. Throughput: 0: 1710.7, 1: 1698.8. Samples: 11743562. Policy #0 lag: (min: 16.0, avg: 32.4, max: 48.0) -[2023-10-09 00:56:43,975][87372] Avg episode reward: [(0, '5.700'), (1, '5.390')] -[2023-10-09 00:56:44,795][88327] Updated weights for policy 1, policy_version 22920 (0.0009) -[2023-10-09 00:56:45,164][88327] Updated weights for policy 1, policy_version 22930 (0.0010) -[2023-10-09 00:56:45,524][88327] Updated weights for policy 1, policy_version 22940 (0.0009) -[2023-10-09 00:56:48,081][88326] Updated weights for policy 0, policy_version 22952 (0.0009) -[2023-10-09 00:56:48,450][88326] Updated weights for policy 0, policy_version 22962 (0.0008) -[2023-10-09 00:56:48,819][88326] Updated weights for policy 0, policy_version 22972 (0.0009) -[2023-10-09 00:56:48,974][87372] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 47022080. Throughput: 0: 1698.1, 1: 1709.7. Samples: 11764130. Policy #0 lag: (min: 16.0, avg: 32.4, max: 48.0) -[2023-10-09 00:56:48,975][87372] Avg episode reward: [(0, '5.920'), (1, '5.350')] -[2023-10-09 00:56:49,614][88327] Updated weights for policy 1, policy_version 22950 (0.0011) -[2023-10-09 00:56:49,978][88327] Updated weights for policy 1, policy_version 22960 (0.0008) -[2023-10-09 00:56:50,345][88327] Updated weights for policy 1, policy_version 22970 (0.0008) -[2023-10-09 00:56:52,802][88326] Updated weights for policy 0, policy_version 22982 (0.0007) -[2023-10-09 00:56:53,167][88326] Updated weights for policy 0, policy_version 22992 (0.0007) -[2023-10-09 00:56:53,540][88326] Updated weights for policy 0, policy_version 23002 (0.0007) -[2023-10-09 00:56:53,974][87372] Fps is (10 sec: 16384.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 47087616. Throughput: 0: 1711.6, 1: 1686.6. Samples: 11773778. Policy #0 lag: (min: 6.0, avg: 13.9, max: 38.0) -[2023-10-09 00:56:53,974][87372] Avg episode reward: [(0, '5.640'), (1, '5.250')] -[2023-10-09 00:56:54,355][88327] Updated weights for policy 1, policy_version 22980 (0.0010) -[2023-10-09 00:56:54,721][88327] Updated weights for policy 1, policy_version 22990 (0.0008) -[2023-10-09 00:56:55,091][88327] Updated weights for policy 1, policy_version 23000 (0.0007) -[2023-10-09 00:56:57,580][88326] Updated weights for policy 0, policy_version 23012 (0.0008) -[2023-10-09 00:56:57,961][88326] Updated weights for policy 0, policy_version 23022 (0.0008) -[2023-10-09 00:56:58,331][88326] Updated weights for policy 0, policy_version 23032 (0.0008) -[2023-10-09 00:56:58,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 47153152. Throughput: 0: 1707.3, 1: 1711.5. Samples: 11794880. Policy #0 lag: (min: 6.0, avg: 13.9, max: 38.0) -[2023-10-09 00:56:58,975][87372] Avg episode reward: [(0, '5.530'), (1, '5.190')] -[2023-10-09 00:56:59,058][88327] Updated weights for policy 1, policy_version 23010 (0.0009) -[2023-10-09 00:56:59,428][88327] Updated weights for policy 1, policy_version 23020 (0.0009) -[2023-10-09 00:56:59,791][88327] Updated weights for policy 1, policy_version 23030 (0.0008) -[2023-10-09 00:57:00,158][88327] Updated weights for policy 1, policy_version 23040 (0.0007) -[2023-10-09 00:57:02,447][88326] Updated weights for policy 0, policy_version 23042 (0.0009) -[2023-10-09 00:57:02,815][88326] Updated weights for policy 0, policy_version 23052 (0.0008) -[2023-10-09 00:57:03,180][88326] Updated weights for policy 0, policy_version 23062 (0.0008) -[2023-10-09 00:57:03,555][88326] Updated weights for policy 0, policy_version 23072 (0.0008) -[2023-10-09 00:57:03,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 47218688. Throughput: 0: 1684.9, 1: 1714.7. Samples: 11814812. Policy #0 lag: (min: 6.0, avg: 13.9, max: 38.0) -[2023-10-09 00:57:03,975][87372] Avg episode reward: [(0, '6.030'), (1, '5.730')] -[2023-10-09 00:57:04,331][88327] Updated weights for policy 1, policy_version 23050 (0.0010) -[2023-10-09 00:57:04,710][88327] Updated weights for policy 1, policy_version 23060 (0.0008) -[2023-10-09 00:57:05,079][88327] Updated weights for policy 1, policy_version 23070 (0.0007) -[2023-10-09 00:57:05,146][88168] Saving new best policy, reward=5.730! -[2023-10-09 00:57:07,557][88326] Updated weights for policy 0, policy_version 23082 (0.0007) -[2023-10-09 00:57:07,929][88326] Updated weights for policy 0, policy_version 23092 (0.0008) -[2023-10-09 00:57:08,299][88326] Updated weights for policy 0, policy_version 23102 (0.0009) -[2023-10-09 00:57:08,951][88327] Updated weights for policy 1, policy_version 23080 (0.0008) -[2023-10-09 00:57:08,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 47284224. Throughput: 0: 1707.5, 1: 1700.9. Samples: 11824704. Policy #0 lag: (min: 6.0, avg: 13.9, max: 38.0) -[2023-10-09 00:57:08,975][87372] Avg episode reward: [(0, '6.470'), (1, '5.230')] -[2023-10-09 00:57:08,976][88088] Saving new best policy, reward=6.470! -[2023-10-09 00:57:09,316][88327] Updated weights for policy 1, policy_version 23090 (0.0007) -[2023-10-09 00:57:09,683][88327] Updated weights for policy 1, policy_version 23100 (0.0007) -[2023-10-09 00:57:12,303][88326] Updated weights for policy 0, policy_version 23112 (0.0008) -[2023-10-09 00:57:12,674][88326] Updated weights for policy 0, policy_version 23122 (0.0010) -[2023-10-09 00:57:13,048][88326] Updated weights for policy 0, policy_version 23132 (0.0009) -[2023-10-09 00:57:13,588][88327] Updated weights for policy 1, policy_version 23110 (0.0008) -[2023-10-09 00:57:13,951][88327] Updated weights for policy 1, policy_version 23120 (0.0010) -[2023-10-09 00:57:13,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 47349760. Throughput: 0: 1700.5, 1: 1708.8. Samples: 11845262. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 00:57:13,975][87372] Avg episode reward: [(0, '6.260'), (1, '5.290')] -[2023-10-09 00:57:14,321][88327] Updated weights for policy 1, policy_version 23130 (0.0009) -[2023-10-09 00:57:17,108][88326] Updated weights for policy 0, policy_version 23142 (0.0011) -[2023-10-09 00:57:17,488][88326] Updated weights for policy 0, policy_version 23152 (0.0011) -[2023-10-09 00:57:17,846][88326] Updated weights for policy 0, policy_version 23162 (0.0010) -[2023-10-09 00:57:18,457][88327] Updated weights for policy 1, policy_version 23140 (0.0009) -[2023-10-09 00:57:18,827][88327] Updated weights for policy 1, policy_version 23150 (0.0009) -[2023-10-09 00:57:18,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 47415296. Throughput: 0: 1668.1, 1: 1710.3. Samples: 11865040. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 00:57:18,974][87372] Avg episode reward: [(0, '5.720'), (1, '5.440')] -[2023-10-09 00:57:19,189][88327] Updated weights for policy 1, policy_version 23160 (0.0007) -[2023-10-09 00:57:21,829][88326] Updated weights for policy 0, policy_version 23172 (0.0009) -[2023-10-09 00:57:22,195][88326] Updated weights for policy 0, policy_version 23182 (0.0008) -[2023-10-09 00:57:22,576][88326] Updated weights for policy 0, policy_version 23192 (0.0009) -[2023-10-09 00:57:23,312][88327] Updated weights for policy 1, policy_version 23170 (0.0008) -[2023-10-09 00:57:23,682][88327] Updated weights for policy 1, policy_version 23180 (0.0008) -[2023-10-09 00:57:23,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 47480832. Throughput: 0: 1692.8, 1: 1707.2. Samples: 11875380. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 00:57:23,975][87372] Avg episode reward: [(0, '6.090'), (1, '5.010')] -[2023-10-09 00:57:24,049][88327] Updated weights for policy 1, policy_version 23190 (0.0007) -[2023-10-09 00:57:24,423][88327] Updated weights for policy 1, policy_version 23200 (0.0009) -[2023-10-09 00:57:26,726][88326] Updated weights for policy 0, policy_version 23202 (0.0010) -[2023-10-09 00:57:27,097][88326] Updated weights for policy 0, policy_version 23212 (0.0008) -[2023-10-09 00:57:27,466][88326] Updated weights for policy 0, policy_version 23222 (0.0008) -[2023-10-09 00:57:27,844][88326] Updated weights for policy 0, policy_version 23232 (0.0008) -[2023-10-09 00:57:28,439][88327] Updated weights for policy 1, policy_version 23210 (0.0009) -[2023-10-09 00:57:28,803][88327] Updated weights for policy 1, policy_version 23220 (0.0008) -[2023-10-09 00:57:28,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 47546368. Throughput: 0: 1676.6, 1: 1707.2. Samples: 11895830. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 00:57:28,975][87372] Avg episode reward: [(0, '5.670'), (1, '5.080')] -[2023-10-09 00:57:29,162][88327] Updated weights for policy 1, policy_version 23230 (0.0009) -[2023-10-09 00:57:31,979][88326] Updated weights for policy 0, policy_version 23242 (0.0009) -[2023-10-09 00:57:32,342][88326] Updated weights for policy 0, policy_version 23252 (0.0011) -[2023-10-09 00:57:32,705][88326] Updated weights for policy 0, policy_version 23262 (0.0009) -[2023-10-09 00:57:33,082][88327] Updated weights for policy 1, policy_version 23240 (0.0008) -[2023-10-09 00:57:33,438][88327] Updated weights for policy 1, policy_version 23250 (0.0009) -[2023-10-09 00:57:33,800][88327] Updated weights for policy 1, policy_version 23260 (0.0009) -[2023-10-09 00:57:33,974][87372] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 47644672. Throughput: 0: 1668.7, 1: 1694.2. Samples: 11915462. Policy #0 lag: (min: 0.0, avg: 27.1, max: 32.0) -[2023-10-09 00:57:33,975][87372] Avg episode reward: [(0, '5.470'), (1, '5.480')] -[2023-10-09 00:57:36,737][88326] Updated weights for policy 0, policy_version 23272 (0.0010) -[2023-10-09 00:57:37,111][88326] Updated weights for policy 0, policy_version 23282 (0.0009) -[2023-10-09 00:57:37,474][88326] Updated weights for policy 0, policy_version 23292 (0.0009) -[2023-10-09 00:57:37,665][88327] Updated weights for policy 1, policy_version 23270 (0.0008) -[2023-10-09 00:57:38,031][88327] Updated weights for policy 1, policy_version 23280 (0.0008) -[2023-10-09 00:57:38,402][88327] Updated weights for policy 1, policy_version 23290 (0.0008) -[2023-10-09 00:57:38,974][87372] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 47710208. Throughput: 0: 1686.6, 1: 1707.1. Samples: 11926494. Policy #0 lag: (min: 0.0, avg: 27.1, max: 32.0) -[2023-10-09 00:57:38,975][87372] Avg episode reward: [(0, '5.540'), (1, '5.340')] -[2023-10-09 00:57:41,550][88326] Updated weights for policy 0, policy_version 23302 (0.0010) -[2023-10-09 00:57:41,922][88326] Updated weights for policy 0, policy_version 23312 (0.0009) -[2023-10-09 00:57:42,305][88326] Updated weights for policy 0, policy_version 23322 (0.0007) -[2023-10-09 00:57:42,449][88327] Updated weights for policy 1, policy_version 23300 (0.0008) -[2023-10-09 00:57:42,815][88327] Updated weights for policy 1, policy_version 23310 (0.0008) -[2023-10-09 00:57:43,183][88327] Updated weights for policy 1, policy_version 23320 (0.0010) -[2023-10-09 00:57:43,974][87372] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 47775744. Throughput: 0: 1661.1, 1: 1707.6. Samples: 11946472. Policy #0 lag: (min: 0.0, avg: 27.1, max: 32.0) -[2023-10-09 00:57:43,975][87372] Avg episode reward: [(0, '5.610'), (1, '5.350')] -[2023-10-09 00:57:46,439][88326] Updated weights for policy 0, policy_version 23332 (0.0009) -[2023-10-09 00:57:46,819][88326] Updated weights for policy 0, policy_version 23342 (0.0008) -[2023-10-09 00:57:47,189][88326] Updated weights for policy 0, policy_version 23352 (0.0010) -[2023-10-09 00:57:47,228][88327] Updated weights for policy 1, policy_version 23330 (0.0008) -[2023-10-09 00:57:47,606][88327] Updated weights for policy 1, policy_version 23340 (0.0009) -[2023-10-09 00:57:47,963][88327] Updated weights for policy 1, policy_version 23350 (0.0009) -[2023-10-09 00:57:48,338][88327] Updated weights for policy 1, policy_version 23360 (0.0008) -[2023-10-09 00:57:48,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 47841280. Throughput: 0: 1673.0, 1: 1685.8. Samples: 11965958. Policy #0 lag: (min: 0.0, avg: 27.1, max: 32.0) -[2023-10-09 00:57:48,975][87372] Avg episode reward: [(0, '5.740'), (1, '5.510')] -[2023-10-09 00:57:51,316][88326] Updated weights for policy 0, policy_version 23362 (0.0009) -[2023-10-09 00:57:51,680][88326] Updated weights for policy 0, policy_version 23372 (0.0008) -[2023-10-09 00:57:52,044][88326] Updated weights for policy 0, policy_version 23382 (0.0009) -[2023-10-09 00:57:52,351][88327] Updated weights for policy 1, policy_version 23370 (0.0009) -[2023-10-09 00:57:52,413][88326] Updated weights for policy 0, policy_version 23392 (0.0007) -[2023-10-09 00:57:52,726][88327] Updated weights for policy 1, policy_version 23380 (0.0009) -[2023-10-09 00:57:53,091][88327] Updated weights for policy 1, policy_version 23390 (0.0009) -[2023-10-09 00:57:53,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 47906816. Throughput: 0: 1674.5, 1: 1715.1. Samples: 11977234. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) -[2023-10-09 00:57:53,974][87372] Avg episode reward: [(0, '5.630'), (1, '5.750')] -[2023-10-09 00:57:53,975][88168] Saving new best policy, reward=5.750! -[2023-10-09 00:57:56,561][88326] Updated weights for policy 0, policy_version 23402 (0.0008) -[2023-10-09 00:57:56,930][88326] Updated weights for policy 0, policy_version 23412 (0.0008) -[2023-10-09 00:57:57,006][88327] Updated weights for policy 1, policy_version 23400 (0.0007) -[2023-10-09 00:57:57,306][88326] Updated weights for policy 0, policy_version 23422 (0.0008) -[2023-10-09 00:57:57,373][88327] Updated weights for policy 1, policy_version 23410 (0.0008) -[2023-10-09 00:57:57,733][88327] Updated weights for policy 1, policy_version 23420 (0.0010) -[2023-10-09 00:57:58,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 47972352. Throughput: 0: 1658.1, 1: 1704.0. Samples: 11996558. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) -[2023-10-09 00:57:58,975][87372] Avg episode reward: [(0, '5.750'), (1, '5.460')] -[2023-10-09 00:58:01,200][88326] Updated weights for policy 0, policy_version 23432 (0.0008) -[2023-10-09 00:58:01,577][88326] Updated weights for policy 0, policy_version 23442 (0.0008) -[2023-10-09 00:58:01,881][88327] Updated weights for policy 1, policy_version 23430 (0.0007) -[2023-10-09 00:58:01,940][88326] Updated weights for policy 0, policy_version 23452 (0.0007) -[2023-10-09 00:58:02,241][88327] Updated weights for policy 1, policy_version 23440 (0.0007) -[2023-10-09 00:58:02,601][88327] Updated weights for policy 1, policy_version 23450 (0.0010) -[2023-10-09 00:58:03,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 48037888. Throughput: 0: 1684.3, 1: 1677.4. Samples: 12016318. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) -[2023-10-09 00:58:03,975][87372] Avg episode reward: [(0, '5.560'), (1, '5.400')] -[2023-10-09 00:58:06,054][88326] Updated weights for policy 0, policy_version 23462 (0.0008) -[2023-10-09 00:58:06,454][88326] Updated weights for policy 0, policy_version 23472 (0.0010) -[2023-10-09 00:58:06,644][88327] Updated weights for policy 1, policy_version 23460 (0.0008) -[2023-10-09 00:58:06,824][88326] Updated weights for policy 0, policy_version 23482 (0.0007) -[2023-10-09 00:58:07,009][88327] Updated weights for policy 1, policy_version 23470 (0.0007) -[2023-10-09 00:58:07,363][88327] Updated weights for policy 1, policy_version 23480 (0.0009) -[2023-10-09 00:58:08,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 48103424. Throughput: 0: 1675.0, 1: 1708.0. Samples: 12027614. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) -[2023-10-09 00:58:08,975][87372] Avg episode reward: [(0, '5.540'), (1, '5.710')] -[2023-10-09 00:58:10,693][88326] Updated weights for policy 0, policy_version 23492 (0.0009) -[2023-10-09 00:58:11,058][88326] Updated weights for policy 0, policy_version 23502 (0.0010) -[2023-10-09 00:58:11,418][88327] Updated weights for policy 1, policy_version 23490 (0.0009) -[2023-10-09 00:58:11,432][88326] Updated weights for policy 0, policy_version 23512 (0.0009) -[2023-10-09 00:58:11,801][88327] Updated weights for policy 1, policy_version 23500 (0.0007) -[2023-10-09 00:58:12,171][88327] Updated weights for policy 1, policy_version 23510 (0.0007) -[2023-10-09 00:58:12,539][88327] Updated weights for policy 1, policy_version 23520 (0.0007) -[2023-10-09 00:58:13,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 48168960. Throughput: 0: 1669.8, 1: 1683.2. Samples: 12046714. Policy #0 lag: (min: 8.0, avg: 36.6, max: 40.0) -[2023-10-09 00:58:13,974][87372] Avg episode reward: [(0, '5.860'), (1, '5.500')] -[2023-10-09 00:58:15,470][88326] Updated weights for policy 0, policy_version 23522 (0.0009) -[2023-10-09 00:58:15,836][88326] Updated weights for policy 0, policy_version 23532 (0.0010) -[2023-10-09 00:58:16,213][88326] Updated weights for policy 0, policy_version 23542 (0.0009) -[2023-10-09 00:58:16,545][88327] Updated weights for policy 1, policy_version 23530 (0.0007) -[2023-10-09 00:58:16,577][88326] Updated weights for policy 0, policy_version 23552 (0.0007) -[2023-10-09 00:58:16,917][88327] Updated weights for policy 1, policy_version 23540 (0.0007) -[2023-10-09 00:58:17,290][88327] Updated weights for policy 1, policy_version 23550 (0.0008) -[2023-10-09 00:58:18,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 48234496. Throughput: 0: 1692.4, 1: 1680.4. Samples: 12067238. Policy #0 lag: (min: 8.0, avg: 36.6, max: 40.0) -[2023-10-09 00:58:18,975][87372] Avg episode reward: [(0, '5.970'), (1, '5.650')] -[2023-10-09 00:58:20,659][88326] Updated weights for policy 0, policy_version 23562 (0.0008) -[2023-10-09 00:58:21,023][88326] Updated weights for policy 0, policy_version 23572 (0.0008) -[2023-10-09 00:58:21,301][88327] Updated weights for policy 1, policy_version 23560 (0.0008) -[2023-10-09 00:58:21,392][88326] Updated weights for policy 0, policy_version 23582 (0.0008) -[2023-10-09 00:58:21,670][88327] Updated weights for policy 1, policy_version 23570 (0.0008) -[2023-10-09 00:58:22,033][88327] Updated weights for policy 1, policy_version 23580 (0.0009) -[2023-10-09 00:58:23,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 48300032. Throughput: 0: 1670.2, 1: 1694.0. Samples: 12077884. Policy #0 lag: (min: 8.0, avg: 36.6, max: 40.0) -[2023-10-09 00:58:23,975][87372] Avg episode reward: [(0, '5.960'), (1, '5.800')] -[2023-10-09 00:58:23,976][88168] Saving new best policy, reward=5.800! -[2023-10-09 00:58:25,558][88326] Updated weights for policy 0, policy_version 23592 (0.0007) -[2023-10-09 00:58:25,923][88326] Updated weights for policy 0, policy_version 23602 (0.0009) -[2023-10-09 00:58:26,236][88327] Updated weights for policy 1, policy_version 23590 (0.0008) -[2023-10-09 00:58:26,293][88326] Updated weights for policy 0, policy_version 23612 (0.0008) -[2023-10-09 00:58:26,591][88327] Updated weights for policy 1, policy_version 23600 (0.0007) -[2023-10-09 00:58:26,950][88327] Updated weights for policy 1, policy_version 23610 (0.0008) -[2023-10-09 00:58:28,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 48365568. Throughput: 0: 1686.2, 1: 1667.1. Samples: 12097370. Policy #0 lag: (min: 8.0, avg: 36.6, max: 40.0) -[2023-10-09 00:58:28,975][87372] Avg episode reward: [(0, '6.000'), (1, '5.590')] -[2023-10-09 00:58:30,154][88326] Updated weights for policy 0, policy_version 23622 (0.0007) -[2023-10-09 00:58:30,517][88326] Updated weights for policy 0, policy_version 23632 (0.0010) -[2023-10-09 00:58:30,885][88326] Updated weights for policy 0, policy_version 23642 (0.0009) -[2023-10-09 00:58:31,107][88327] Updated weights for policy 1, policy_version 23620 (0.0008) -[2023-10-09 00:58:31,478][88327] Updated weights for policy 1, policy_version 23630 (0.0008) -[2023-10-09 00:58:31,837][88327] Updated weights for policy 1, policy_version 23640 (0.0011) -[2023-10-09 00:58:33,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 48431104. Throughput: 0: 1696.8, 1: 1683.2. Samples: 12118056. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:58:33,975][87372] Avg episode reward: [(0, '5.660'), (1, '5.680')] -[2023-10-09 00:58:33,986][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000023648_24215552.pth... -[2023-10-09 00:58:33,986][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000023648_24215552.pth... -[2023-10-09 00:58:34,015][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000022080_22609920.pth -[2023-10-09 00:58:34,019][88168] Saving a milestone ./train_atari/atari_battlezone_APPO/checkpoint_p1/milestones/checkpoint_000023648_24215552.pth -[2023-10-09 00:58:34,025][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000022080_22609920.pth -[2023-10-09 00:58:34,030][88088] Saving a milestone ./train_atari/atari_battlezone_APPO/checkpoint_p0/milestones/checkpoint_000023648_24215552.pth -[2023-10-09 00:58:34,892][88326] Updated weights for policy 0, policy_version 23652 (0.0009) -[2023-10-09 00:58:35,263][88326] Updated weights for policy 0, policy_version 23662 (0.0008) -[2023-10-09 00:58:35,617][88326] Updated weights for policy 0, policy_version 23672 (0.0009) -[2023-10-09 00:58:35,903][88327] Updated weights for policy 1, policy_version 23650 (0.0009) -[2023-10-09 00:58:36,271][88327] Updated weights for policy 1, policy_version 23660 (0.0009) -[2023-10-09 00:58:36,637][88327] Updated weights for policy 1, policy_version 23670 (0.0009) -[2023-10-09 00:58:36,998][88327] Updated weights for policy 1, policy_version 23680 (0.0009) -[2023-10-09 00:58:38,974][87372] Fps is (10 sec: 13107.6, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 48496640. Throughput: 0: 1677.1, 1: 1680.8. Samples: 12128340. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:58:38,974][87372] Avg episode reward: [(0, '5.460'), (1, '5.460')] -[2023-10-09 00:58:39,640][88326] Updated weights for policy 0, policy_version 23682 (0.0008) -[2023-10-09 00:58:40,002][88326] Updated weights for policy 0, policy_version 23692 (0.0007) -[2023-10-09 00:58:40,369][88326] Updated weights for policy 0, policy_version 23702 (0.0008) -[2023-10-09 00:58:40,730][88326] Updated weights for policy 0, policy_version 23712 (0.0009) -[2023-10-09 00:58:41,121][88327] Updated weights for policy 1, policy_version 23690 (0.0011) -[2023-10-09 00:58:41,486][88327] Updated weights for policy 1, policy_version 23700 (0.0010) -[2023-10-09 00:58:41,841][88327] Updated weights for policy 1, policy_version 23710 (0.0011) -[2023-10-09 00:58:43,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 48562176. Throughput: 0: 1701.1, 1: 1669.9. Samples: 12148254. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:58:43,975][87372] Avg episode reward: [(0, '5.500'), (1, '5.380')] -[2023-10-09 00:58:44,663][88326] Updated weights for policy 0, policy_version 23722 (0.0009) -[2023-10-09 00:58:45,028][88326] Updated weights for policy 0, policy_version 23732 (0.0009) -[2023-10-09 00:58:45,398][88326] Updated weights for policy 0, policy_version 23742 (0.0007) -[2023-10-09 00:58:45,901][88327] Updated weights for policy 1, policy_version 23720 (0.0008) -[2023-10-09 00:58:46,282][88327] Updated weights for policy 1, policy_version 23730 (0.0011) -[2023-10-09 00:58:46,646][88327] Updated weights for policy 1, policy_version 23740 (0.0008) -[2023-10-09 00:58:48,974][87372] Fps is (10 sec: 13106.8, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 48627712. Throughput: 0: 1702.8, 1: 1691.6. Samples: 12169066. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 00:58:48,975][87372] Avg episode reward: [(0, '5.720'), (1, '5.380')] -[2023-10-09 00:58:49,404][88326] Updated weights for policy 0, policy_version 23752 (0.0008) -[2023-10-09 00:58:49,776][88326] Updated weights for policy 0, policy_version 23762 (0.0007) -[2023-10-09 00:58:50,142][88326] Updated weights for policy 0, policy_version 23772 (0.0007) -[2023-10-09 00:58:50,721][88327] Updated weights for policy 1, policy_version 23750 (0.0007) -[2023-10-09 00:58:51,084][88327] Updated weights for policy 1, policy_version 23760 (0.0010) -[2023-10-09 00:58:51,455][88327] Updated weights for policy 1, policy_version 23770 (0.0007) -[2023-10-09 00:58:53,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 48693248. Throughput: 0: 1683.7, 1: 1676.2. Samples: 12178808. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 00:58:53,974][87372] Avg episode reward: [(0, '5.390'), (1, '5.150')] -[2023-10-09 00:58:54,351][88326] Updated weights for policy 0, policy_version 23782 (0.0009) -[2023-10-09 00:58:54,728][88326] Updated weights for policy 0, policy_version 23792 (0.0008) -[2023-10-09 00:58:55,089][88326] Updated weights for policy 0, policy_version 23802 (0.0007) -[2023-10-09 00:58:55,342][88327] Updated weights for policy 1, policy_version 23780 (0.0009) -[2023-10-09 00:58:55,707][88327] Updated weights for policy 1, policy_version 23790 (0.0008) -[2023-10-09 00:58:56,066][88327] Updated weights for policy 1, policy_version 23800 (0.0007) -[2023-10-09 00:58:58,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 48758784. Throughput: 0: 1705.1, 1: 1688.2. Samples: 12199412. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 00:58:58,974][87372] Avg episode reward: [(0, '5.850'), (1, '5.240')] -[2023-10-09 00:58:59,045][88326] Updated weights for policy 0, policy_version 23812 (0.0008) -[2023-10-09 00:58:59,426][88326] Updated weights for policy 0, policy_version 23822 (0.0007) -[2023-10-09 00:58:59,799][88326] Updated weights for policy 0, policy_version 23832 (0.0007) -[2023-10-09 00:59:00,027][88327] Updated weights for policy 1, policy_version 23810 (0.0008) -[2023-10-09 00:59:00,390][88327] Updated weights for policy 1, policy_version 23820 (0.0009) -[2023-10-09 00:59:00,757][88327] Updated weights for policy 1, policy_version 23830 (0.0009) -[2023-10-09 00:59:01,121][88327] Updated weights for policy 1, policy_version 23840 (0.0008) -[2023-10-09 00:59:03,851][88326] Updated weights for policy 0, policy_version 23842 (0.0009) -[2023-10-09 00:59:03,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 48824320. Throughput: 0: 1702.3, 1: 1700.3. Samples: 12220354. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 00:59:03,975][87372] Avg episode reward: [(0, '5.820'), (1, '5.340')] -[2023-10-09 00:59:04,221][88326] Updated weights for policy 0, policy_version 23852 (0.0009) -[2023-10-09 00:59:04,594][88326] Updated weights for policy 0, policy_version 23862 (0.0009) -[2023-10-09 00:59:04,956][88326] Updated weights for policy 0, policy_version 23872 (0.0007) -[2023-10-09 00:59:05,090][88327] Updated weights for policy 1, policy_version 23850 (0.0009) -[2023-10-09 00:59:05,462][88327] Updated weights for policy 1, policy_version 23860 (0.0008) -[2023-10-09 00:59:05,813][88327] Updated weights for policy 1, policy_version 23870 (0.0010) -[2023-10-09 00:59:08,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 48889856. Throughput: 0: 1696.2, 1: 1672.5. Samples: 12229478. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 00:59:08,975][87372] Avg episode reward: [(0, '5.460'), (1, '5.330')] -[2023-10-09 00:59:09,036][88326] Updated weights for policy 0, policy_version 23882 (0.0008) -[2023-10-09 00:59:09,398][88326] Updated weights for policy 0, policy_version 23892 (0.0008) -[2023-10-09 00:59:09,772][88326] Updated weights for policy 0, policy_version 23902 (0.0009) -[2023-10-09 00:59:09,887][88327] Updated weights for policy 1, policy_version 23880 (0.0008) -[2023-10-09 00:59:10,254][88327] Updated weights for policy 1, policy_version 23890 (0.0008) -[2023-10-09 00:59:10,627][88327] Updated weights for policy 1, policy_version 23900 (0.0008) -[2023-10-09 00:59:13,849][88326] Updated weights for policy 0, policy_version 23912 (0.0010) -[2023-10-09 00:59:13,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 48955392. Throughput: 0: 1700.0, 1: 1700.8. Samples: 12250408. Policy #0 lag: (min: 13.0, avg: 21.0, max: 45.0) -[2023-10-09 00:59:13,975][87372] Avg episode reward: [(0, '5.880'), (1, '5.350')] -[2023-10-09 00:59:14,217][88326] Updated weights for policy 0, policy_version 23922 (0.0008) -[2023-10-09 00:59:14,557][88327] Updated weights for policy 1, policy_version 23910 (0.0008) -[2023-10-09 00:59:14,584][88326] Updated weights for policy 0, policy_version 23932 (0.0008) -[2023-10-09 00:59:14,940][88327] Updated weights for policy 1, policy_version 23920 (0.0010) -[2023-10-09 00:59:15,307][88327] Updated weights for policy 1, policy_version 23930 (0.0009) -[2023-10-09 00:59:18,520][88326] Updated weights for policy 0, policy_version 23942 (0.0008) -[2023-10-09 00:59:18,874][88326] Updated weights for policy 0, policy_version 23952 (0.0007) -[2023-10-09 00:59:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 49020928. Throughput: 0: 1701.7, 1: 1707.2. Samples: 12271458. Policy #0 lag: (min: 13.0, avg: 21.0, max: 45.0) -[2023-10-09 00:59:18,975][87372] Avg episode reward: [(0, '5.270'), (1, '5.490')] -[2023-10-09 00:59:19,245][88326] Updated weights for policy 0, policy_version 23962 (0.0007) -[2023-10-09 00:59:19,345][88327] Updated weights for policy 1, policy_version 23940 (0.0009) -[2023-10-09 00:59:19,713][88327] Updated weights for policy 1, policy_version 23950 (0.0010) -[2023-10-09 00:59:20,079][88327] Updated weights for policy 1, policy_version 23960 (0.0009) -[2023-10-09 00:59:23,330][88326] Updated weights for policy 0, policy_version 23972 (0.0008) -[2023-10-09 00:59:23,709][88326] Updated weights for policy 0, policy_version 23982 (0.0009) -[2023-10-09 00:59:23,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 49086464. Throughput: 0: 1696.9, 1: 1686.4. Samples: 12280592. Policy #0 lag: (min: 13.0, avg: 21.0, max: 45.0) -[2023-10-09 00:59:23,975][88327] Updated weights for policy 1, policy_version 23970 (0.0009) -[2023-10-09 00:59:23,975][87372] Avg episode reward: [(0, '5.590'), (1, '5.370')] -[2023-10-09 00:59:24,076][88326] Updated weights for policy 0, policy_version 23992 (0.0009) -[2023-10-09 00:59:24,341][88327] Updated weights for policy 1, policy_version 23980 (0.0007) -[2023-10-09 00:59:24,707][88327] Updated weights for policy 1, policy_version 23990 (0.0008) -[2023-10-09 00:59:25,074][88327] Updated weights for policy 1, policy_version 24000 (0.0008) -[2023-10-09 00:59:28,069][88326] Updated weights for policy 0, policy_version 24002 (0.0009) -[2023-10-09 00:59:28,431][88326] Updated weights for policy 0, policy_version 24012 (0.0008) -[2023-10-09 00:59:28,805][88326] Updated weights for policy 0, policy_version 24022 (0.0007) -[2023-10-09 00:59:28,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 49152000. Throughput: 0: 1695.1, 1: 1711.8. Samples: 12301562. Policy #0 lag: (min: 13.0, avg: 21.0, max: 45.0) -[2023-10-09 00:59:28,975][87372] Avg episode reward: [(0, '5.670'), (1, '5.240')] -[2023-10-09 00:59:29,177][88327] Updated weights for policy 1, policy_version 24010 (0.0010) -[2023-10-09 00:59:29,178][88326] Updated weights for policy 0, policy_version 24032 (0.0007) -[2023-10-09 00:59:29,540][88327] Updated weights for policy 1, policy_version 24020 (0.0010) -[2023-10-09 00:59:29,917][88327] Updated weights for policy 1, policy_version 24030 (0.0007) -[2023-10-09 00:59:33,153][88326] Updated weights for policy 0, policy_version 24042 (0.0007) -[2023-10-09 00:59:33,520][88326] Updated weights for policy 0, policy_version 24052 (0.0007) -[2023-10-09 00:59:33,888][88326] Updated weights for policy 0, policy_version 24062 (0.0009) -[2023-10-09 00:59:33,974][87372] Fps is (10 sec: 16384.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 49250304. Throughput: 0: 1689.2, 1: 1713.2. Samples: 12322172. Policy #0 lag: (min: 21.0, avg: 24.8, max: 53.0) -[2023-10-09 00:59:33,974][87372] Avg episode reward: [(0, '5.370'), (1, '5.220')] -[2023-10-09 00:59:34,024][88327] Updated weights for policy 1, policy_version 24040 (0.0009) -[2023-10-09 00:59:34,408][88327] Updated weights for policy 1, policy_version 24050 (0.0011) -[2023-10-09 00:59:34,779][88327] Updated weights for policy 1, policy_version 24060 (0.0011) -[2023-10-09 00:59:37,864][88326] Updated weights for policy 0, policy_version 24072 (0.0010) -[2023-10-09 00:59:38,228][88326] Updated weights for policy 0, policy_version 24082 (0.0008) -[2023-10-09 00:59:38,607][88326] Updated weights for policy 0, policy_version 24092 (0.0010) -[2023-10-09 00:59:38,877][88327] Updated weights for policy 1, policy_version 24070 (0.0009) -[2023-10-09 00:59:38,974][87372] Fps is (10 sec: 16384.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 49315840. Throughput: 0: 1701.5, 1: 1691.6. Samples: 12331494. Policy #0 lag: (min: 21.0, avg: 24.8, max: 53.0) -[2023-10-09 00:59:38,974][87372] Avg episode reward: [(0, '5.650'), (1, '5.270')] -[2023-10-09 00:59:39,245][88327] Updated weights for policy 1, policy_version 24080 (0.0010) -[2023-10-09 00:59:39,608][88327] Updated weights for policy 1, policy_version 24090 (0.0010) -[2023-10-09 00:59:42,722][88326] Updated weights for policy 0, policy_version 24102 (0.0008) -[2023-10-09 00:59:43,108][88326] Updated weights for policy 0, policy_version 24112 (0.0008) -[2023-10-09 00:59:43,470][88326] Updated weights for policy 0, policy_version 24122 (0.0009) -[2023-10-09 00:59:43,631][88327] Updated weights for policy 1, policy_version 24100 (0.0007) -[2023-10-09 00:59:43,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 49381376. Throughput: 0: 1697.5, 1: 1697.1. Samples: 12352168. Policy #0 lag: (min: 21.0, avg: 24.8, max: 53.0) -[2023-10-09 00:59:43,975][87372] Avg episode reward: [(0, '5.810'), (1, '5.160')] -[2023-10-09 00:59:43,997][88327] Updated weights for policy 1, policy_version 24110 (0.0010) -[2023-10-09 00:59:44,367][88327] Updated weights for policy 1, policy_version 24120 (0.0011) -[2023-10-09 00:59:47,546][88326] Updated weights for policy 0, policy_version 24132 (0.0008) -[2023-10-09 00:59:47,911][88326] Updated weights for policy 0, policy_version 24142 (0.0011) -[2023-10-09 00:59:48,288][88326] Updated weights for policy 0, policy_version 24152 (0.0007) -[2023-10-09 00:59:48,378][88327] Updated weights for policy 1, policy_version 24130 (0.0007) -[2023-10-09 00:59:48,748][88327] Updated weights for policy 1, policy_version 24140 (0.0007) -[2023-10-09 00:59:48,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 49446912. Throughput: 0: 1671.9, 1: 1703.6. Samples: 12372250. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-09 00:59:48,974][87372] Avg episode reward: [(0, '5.700'), (1, '5.450')] -[2023-10-09 00:59:49,115][88327] Updated weights for policy 1, policy_version 24150 (0.0010) -[2023-10-09 00:59:49,481][88327] Updated weights for policy 1, policy_version 24160 (0.0008) -[2023-10-09 00:59:52,396][88326] Updated weights for policy 0, policy_version 24162 (0.0007) -[2023-10-09 00:59:52,775][88326] Updated weights for policy 0, policy_version 24172 (0.0008) -[2023-10-09 00:59:53,138][88326] Updated weights for policy 0, policy_version 24182 (0.0009) -[2023-10-09 00:59:53,502][88326] Updated weights for policy 0, policy_version 24192 (0.0007) -[2023-10-09 00:59:53,581][88327] Updated weights for policy 1, policy_version 24170 (0.0007) -[2023-10-09 00:59:53,947][88327] Updated weights for policy 1, policy_version 24180 (0.0009) -[2023-10-09 00:59:53,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 49512448. Throughput: 0: 1688.2, 1: 1703.2. Samples: 12382092. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-09 00:59:53,975][87372] Avg episode reward: [(0, '5.630'), (1, '5.460')] -[2023-10-09 00:59:54,311][88327] Updated weights for policy 1, policy_version 24190 (0.0008) -[2023-10-09 00:59:57,506][88326] Updated weights for policy 0, policy_version 24202 (0.0009) -[2023-10-09 00:59:57,872][88326] Updated weights for policy 0, policy_version 24212 (0.0009) -[2023-10-09 00:59:58,246][88326] Updated weights for policy 0, policy_version 24222 (0.0008) -[2023-10-09 00:59:58,275][88327] Updated weights for policy 1, policy_version 24200 (0.0008) -[2023-10-09 00:59:58,637][88327] Updated weights for policy 1, policy_version 24210 (0.0008) -[2023-10-09 00:59:58,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 49577984. Throughput: 0: 1689.1, 1: 1702.0. Samples: 12403006. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-09 00:59:58,975][87372] Avg episode reward: [(0, '5.640'), (1, '5.270')] -[2023-10-09 00:59:59,008][88327] Updated weights for policy 1, policy_version 24220 (0.0008) -[2023-10-09 01:00:02,338][88326] Updated weights for policy 0, policy_version 24232 (0.0008) -[2023-10-09 01:00:02,704][88326] Updated weights for policy 0, policy_version 24242 (0.0007) -[2023-10-09 01:00:03,072][88326] Updated weights for policy 0, policy_version 24252 (0.0007) -[2023-10-09 01:00:03,128][88327] Updated weights for policy 1, policy_version 24230 (0.0008) -[2023-10-09 01:00:03,499][88327] Updated weights for policy 1, policy_version 24240 (0.0009) -[2023-10-09 01:00:03,860][88327] Updated weights for policy 1, policy_version 24250 (0.0007) -[2023-10-09 01:00:03,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 49643520. Throughput: 0: 1662.2, 1: 1696.4. Samples: 12422598. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-09 01:00:03,975][87372] Avg episode reward: [(0, '5.230'), (1, '5.250')] -[2023-10-09 01:00:07,056][88326] Updated weights for policy 0, policy_version 24262 (0.0008) -[2023-10-09 01:00:07,425][88326] Updated weights for policy 0, policy_version 24272 (0.0007) -[2023-10-09 01:00:07,786][88327] Updated weights for policy 1, policy_version 24260 (0.0008) -[2023-10-09 01:00:07,799][88326] Updated weights for policy 0, policy_version 24282 (0.0008) -[2023-10-09 01:00:08,136][88327] Updated weights for policy 1, policy_version 24270 (0.0009) -[2023-10-09 01:00:08,503][88327] Updated weights for policy 1, policy_version 24280 (0.0010) -[2023-10-09 01:00:08,974][87372] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 49741824. Throughput: 0: 1691.8, 1: 1701.6. Samples: 12433294. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:00:08,975][87372] Avg episode reward: [(0, '5.170'), (1, '5.320')] -[2023-10-09 01:00:11,817][88326] Updated weights for policy 0, policy_version 24292 (0.0009) -[2023-10-09 01:00:12,180][88326] Updated weights for policy 0, policy_version 24302 (0.0009) -[2023-10-09 01:00:12,557][88326] Updated weights for policy 0, policy_version 24312 (0.0008) -[2023-10-09 01:00:12,658][88327] Updated weights for policy 1, policy_version 24290 (0.0010) -[2023-10-09 01:00:13,028][88327] Updated weights for policy 1, policy_version 24300 (0.0007) -[2023-10-09 01:00:13,396][88327] Updated weights for policy 1, policy_version 24310 (0.0009) -[2023-10-09 01:00:13,764][88327] Updated weights for policy 1, policy_version 24320 (0.0008) -[2023-10-09 01:00:13,974][87372] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 49807360. Throughput: 0: 1679.4, 1: 1698.8. Samples: 12453582. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:00:13,975][87372] Avg episode reward: [(0, '5.600'), (1, '5.620')] -[2023-10-09 01:00:16,602][88326] Updated weights for policy 0, policy_version 24322 (0.0008) -[2023-10-09 01:00:16,973][88326] Updated weights for policy 0, policy_version 24332 (0.0008) -[2023-10-09 01:00:17,349][88326] Updated weights for policy 0, policy_version 24342 (0.0007) -[2023-10-09 01:00:17,719][88326] Updated weights for policy 0, policy_version 24352 (0.0007) -[2023-10-09 01:00:17,802][88327] Updated weights for policy 1, policy_version 24330 (0.0009) -[2023-10-09 01:00:18,169][88327] Updated weights for policy 1, policy_version 24340 (0.0010) -[2023-10-09 01:00:18,539][88327] Updated weights for policy 1, policy_version 24350 (0.0007) -[2023-10-09 01:00:18,974][87372] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 49872896. Throughput: 0: 1672.3, 1: 1681.1. Samples: 12473076. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:00:18,975][87372] Avg episode reward: [(0, '5.420'), (1, '5.580')] -[2023-10-09 01:00:21,739][88326] Updated weights for policy 0, policy_version 24362 (0.0010) -[2023-10-09 01:00:22,099][88326] Updated weights for policy 0, policy_version 24372 (0.0011) -[2023-10-09 01:00:22,471][88326] Updated weights for policy 0, policy_version 24382 (0.0008) -[2023-10-09 01:00:22,537][88327] Updated weights for policy 1, policy_version 24360 (0.0007) -[2023-10-09 01:00:22,898][88327] Updated weights for policy 1, policy_version 24370 (0.0007) -[2023-10-09 01:00:23,256][88327] Updated weights for policy 1, policy_version 24380 (0.0007) -[2023-10-09 01:00:23,974][87372] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 49938432. Throughput: 0: 1689.5, 1: 1706.5. Samples: 12484316. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:00:23,975][87372] Avg episode reward: [(0, '5.530'), (1, '5.660')] -[2023-10-09 01:00:26,506][88326] Updated weights for policy 0, policy_version 24392 (0.0008) -[2023-10-09 01:00:26,876][88326] Updated weights for policy 0, policy_version 24402 (0.0009) -[2023-10-09 01:00:27,242][88326] Updated weights for policy 0, policy_version 24412 (0.0008) -[2023-10-09 01:00:27,423][88327] Updated weights for policy 1, policy_version 24390 (0.0009) -[2023-10-09 01:00:27,796][88327] Updated weights for policy 1, policy_version 24400 (0.0009) -[2023-10-09 01:00:28,170][88327] Updated weights for policy 1, policy_version 24410 (0.0010) -[2023-10-09 01:00:28,974][87372] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 50003968. Throughput: 0: 1672.4, 1: 1705.4. Samples: 12504166. Policy #0 lag: (min: 16.0, avg: 40.7, max: 48.0) -[2023-10-09 01:00:28,974][87372] Avg episode reward: [(0, '5.750'), (1, '5.670')] -[2023-10-09 01:00:31,307][88326] Updated weights for policy 0, policy_version 24422 (0.0008) -[2023-10-09 01:00:31,682][88326] Updated weights for policy 0, policy_version 24432 (0.0009) -[2023-10-09 01:00:32,042][88326] Updated weights for policy 0, policy_version 24442 (0.0008) -[2023-10-09 01:00:32,206][88327] Updated weights for policy 1, policy_version 24420 (0.0009) -[2023-10-09 01:00:32,572][88327] Updated weights for policy 1, policy_version 24430 (0.0011) -[2023-10-09 01:00:32,941][88327] Updated weights for policy 1, policy_version 24440 (0.0008) -[2023-10-09 01:00:33,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 50069504. Throughput: 0: 1695.0, 1: 1672.0. Samples: 12523768. Policy #0 lag: (min: 16.0, avg: 40.7, max: 48.0) -[2023-10-09 01:00:33,975][87372] Avg episode reward: [(0, '5.130'), (1, '5.470')] -[2023-10-09 01:00:33,984][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000024448_25034752.pth... -[2023-10-09 01:00:33,984][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000024448_25034752.pth... -[2023-10-09 01:00:34,014][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000022880_23429120.pth -[2023-10-09 01:00:34,015][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000022848_23396352.pth -[2023-10-09 01:00:36,051][88326] Updated weights for policy 0, policy_version 24452 (0.0007) -[2023-10-09 01:00:36,422][88326] Updated weights for policy 0, policy_version 24462 (0.0007) -[2023-10-09 01:00:36,799][88326] Updated weights for policy 0, policy_version 24472 (0.0007) -[2023-10-09 01:00:36,894][88327] Updated weights for policy 1, policy_version 24450 (0.0009) -[2023-10-09 01:00:37,267][88327] Updated weights for policy 1, policy_version 24460 (0.0008) -[2023-10-09 01:00:37,642][88327] Updated weights for policy 1, policy_version 24470 (0.0008) -[2023-10-09 01:00:37,996][88327] Updated weights for policy 1, policy_version 24480 (0.0008) -[2023-10-09 01:00:38,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 50135040. Throughput: 0: 1697.0, 1: 1694.9. Samples: 12534730. Policy #0 lag: (min: 16.0, avg: 40.7, max: 48.0) -[2023-10-09 01:00:38,975][87372] Avg episode reward: [(0, '5.600'), (1, '5.430')] -[2023-10-09 01:00:40,801][88326] Updated weights for policy 0, policy_version 24482 (0.0008) -[2023-10-09 01:00:41,158][88326] Updated weights for policy 0, policy_version 24492 (0.0009) -[2023-10-09 01:00:41,531][88326] Updated weights for policy 0, policy_version 24502 (0.0010) -[2023-10-09 01:00:41,903][88326] Updated weights for policy 0, policy_version 24512 (0.0008) -[2023-10-09 01:00:42,083][88327] Updated weights for policy 1, policy_version 24490 (0.0007) -[2023-10-09 01:00:42,444][88327] Updated weights for policy 1, policy_version 24500 (0.0010) -[2023-10-09 01:00:42,812][88327] Updated weights for policy 1, policy_version 24510 (0.0009) -[2023-10-09 01:00:43,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 50200576. Throughput: 0: 1679.6, 1: 1684.8. Samples: 12554404. Policy #0 lag: (min: 16.0, avg: 40.7, max: 48.0) -[2023-10-09 01:00:43,975][87372] Avg episode reward: [(0, '5.470'), (1, '5.410')] -[2023-10-09 01:00:45,999][88326] Updated weights for policy 0, policy_version 24522 (0.0008) -[2023-10-09 01:00:46,365][88326] Updated weights for policy 0, policy_version 24532 (0.0010) -[2023-10-09 01:00:46,733][88326] Updated weights for policy 0, policy_version 24542 (0.0008) -[2023-10-09 01:00:46,736][88327] Updated weights for policy 1, policy_version 24520 (0.0009) -[2023-10-09 01:00:47,101][88327] Updated weights for policy 1, policy_version 24530 (0.0010) -[2023-10-09 01:00:47,472][88327] Updated weights for policy 1, policy_version 24540 (0.0009) -[2023-10-09 01:00:48,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 50266112. Throughput: 0: 1705.1, 1: 1673.2. Samples: 12574620. Policy #0 lag: (min: 3.0, avg: 6.9, max: 35.0) -[2023-10-09 01:00:48,975][87372] Avg episode reward: [(0, '5.090'), (1, '5.430')] -[2023-10-09 01:00:50,736][88326] Updated weights for policy 0, policy_version 24552 (0.0008) -[2023-10-09 01:00:51,105][88326] Updated weights for policy 0, policy_version 24562 (0.0007) -[2023-10-09 01:00:51,481][88326] Updated weights for policy 0, policy_version 24572 (0.0007) -[2023-10-09 01:00:51,640][88327] Updated weights for policy 1, policy_version 24550 (0.0009) -[2023-10-09 01:00:52,016][88327] Updated weights for policy 1, policy_version 24560 (0.0009) -[2023-10-09 01:00:52,380][88327] Updated weights for policy 1, policy_version 24570 (0.0009) -[2023-10-09 01:00:53,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 50331648. Throughput: 0: 1685.7, 1: 1694.6. Samples: 12585410. Policy #0 lag: (min: 3.0, avg: 6.9, max: 35.0) -[2023-10-09 01:00:53,975][87372] Avg episode reward: [(0, '5.970'), (1, '5.250')] -[2023-10-09 01:00:55,631][88326] Updated weights for policy 0, policy_version 24582 (0.0010) -[2023-10-09 01:00:56,009][88326] Updated weights for policy 0, policy_version 24592 (0.0009) -[2023-10-09 01:00:56,388][88326] Updated weights for policy 0, policy_version 24602 (0.0010) -[2023-10-09 01:00:56,542][88327] Updated weights for policy 1, policy_version 24580 (0.0008) -[2023-10-09 01:00:56,919][88327] Updated weights for policy 1, policy_version 24590 (0.0008) -[2023-10-09 01:00:57,285][88327] Updated weights for policy 1, policy_version 24600 (0.0009) -[2023-10-09 01:00:58,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 50397184. Throughput: 0: 1687.0, 1: 1673.1. Samples: 12604786. Policy #0 lag: (min: 3.0, avg: 6.9, max: 35.0) -[2023-10-09 01:00:58,975][87372] Avg episode reward: [(0, '5.380'), (1, '5.660')] -[2023-10-09 01:01:00,507][88326] Updated weights for policy 0, policy_version 24612 (0.0009) -[2023-10-09 01:01:00,865][88326] Updated weights for policy 0, policy_version 24622 (0.0008) -[2023-10-09 01:01:01,237][88326] Updated weights for policy 0, policy_version 24632 (0.0009) -[2023-10-09 01:01:01,260][88327] Updated weights for policy 1, policy_version 24610 (0.0010) -[2023-10-09 01:01:01,627][88327] Updated weights for policy 1, policy_version 24620 (0.0008) -[2023-10-09 01:01:01,992][88327] Updated weights for policy 1, policy_version 24630 (0.0009) -[2023-10-09 01:01:02,354][88327] Updated weights for policy 1, policy_version 24640 (0.0010) -[2023-10-09 01:01:03,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 50462720. Throughput: 0: 1697.4, 1: 1681.1. Samples: 12625108. Policy #0 lag: (min: 3.0, avg: 6.9, max: 35.0) -[2023-10-09 01:01:03,975][87372] Avg episode reward: [(0, '5.670'), (1, '5.880')] -[2023-10-09 01:01:03,985][88168] Saving new best policy, reward=5.880! -[2023-10-09 01:01:05,355][88326] Updated weights for policy 0, policy_version 24642 (0.0008) -[2023-10-09 01:01:05,724][88326] Updated weights for policy 0, policy_version 24652 (0.0011) -[2023-10-09 01:01:06,106][88326] Updated weights for policy 0, policy_version 24662 (0.0010) -[2023-10-09 01:01:06,357][88327] Updated weights for policy 1, policy_version 24650 (0.0008) -[2023-10-09 01:01:06,474][88326] Updated weights for policy 0, policy_version 24672 (0.0010) -[2023-10-09 01:01:06,718][88327] Updated weights for policy 1, policy_version 24660 (0.0008) -[2023-10-09 01:01:07,085][88327] Updated weights for policy 1, policy_version 24670 (0.0010) -[2023-10-09 01:01:08,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 50528256. Throughput: 0: 1675.4, 1: 1689.2. Samples: 12635722. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-09 01:01:08,975][87372] Avg episode reward: [(0, '5.970'), (1, '5.260')] -[2023-10-09 01:01:10,561][88326] Updated weights for policy 0, policy_version 24682 (0.0007) -[2023-10-09 01:01:10,925][88326] Updated weights for policy 0, policy_version 24692 (0.0007) -[2023-10-09 01:01:11,128][88327] Updated weights for policy 1, policy_version 24680 (0.0008) -[2023-10-09 01:01:11,296][88326] Updated weights for policy 0, policy_version 24702 (0.0007) -[2023-10-09 01:01:11,493][88327] Updated weights for policy 1, policy_version 24690 (0.0009) -[2023-10-09 01:01:11,867][88327] Updated weights for policy 1, policy_version 24700 (0.0008) -[2023-10-09 01:01:13,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 50593792. Throughput: 0: 1686.7, 1: 1671.2. Samples: 12655274. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-09 01:01:13,975][87372] Avg episode reward: [(0, '5.830'), (1, '5.390')] -[2023-10-09 01:01:15,272][88326] Updated weights for policy 0, policy_version 24712 (0.0008) -[2023-10-09 01:01:15,654][88326] Updated weights for policy 0, policy_version 24722 (0.0008) -[2023-10-09 01:01:15,928][88327] Updated weights for policy 1, policy_version 24710 (0.0008) -[2023-10-09 01:01:16,023][88326] Updated weights for policy 0, policy_version 24732 (0.0008) -[2023-10-09 01:01:16,329][88327] Updated weights for policy 1, policy_version 24720 (0.0007) -[2023-10-09 01:01:16,694][88327] Updated weights for policy 1, policy_version 24730 (0.0009) -[2023-10-09 01:01:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 50659328. Throughput: 0: 1688.3, 1: 1692.9. Samples: 12675920. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-09 01:01:18,975][87372] Avg episode reward: [(0, '5.550'), (1, '5.470')] -[2023-10-09 01:01:20,006][88326] Updated weights for policy 0, policy_version 24742 (0.0008) -[2023-10-09 01:01:20,382][88326] Updated weights for policy 0, policy_version 24752 (0.0008) -[2023-10-09 01:01:20,648][88327] Updated weights for policy 1, policy_version 24740 (0.0009) -[2023-10-09 01:01:20,743][88326] Updated weights for policy 0, policy_version 24762 (0.0008) -[2023-10-09 01:01:21,012][88327] Updated weights for policy 1, policy_version 24750 (0.0007) -[2023-10-09 01:01:21,381][88327] Updated weights for policy 1, policy_version 24760 (0.0008) -[2023-10-09 01:01:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 50724864. Throughput: 0: 1669.3, 1: 1687.2. Samples: 12685774. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-09 01:01:23,975][87372] Avg episode reward: [(0, '5.570'), (1, '5.480')] -[2023-10-09 01:01:24,678][88326] Updated weights for policy 0, policy_version 24772 (0.0008) -[2023-10-09 01:01:25,055][88326] Updated weights for policy 0, policy_version 24782 (0.0007) -[2023-10-09 01:01:25,386][88327] Updated weights for policy 1, policy_version 24770 (0.0008) -[2023-10-09 01:01:25,414][88326] Updated weights for policy 0, policy_version 24792 (0.0008) -[2023-10-09 01:01:25,751][88327] Updated weights for policy 1, policy_version 24780 (0.0010) -[2023-10-09 01:01:26,104][88327] Updated weights for policy 1, policy_version 24790 (0.0008) -[2023-10-09 01:01:26,475][88327] Updated weights for policy 1, policy_version 24800 (0.0010) -[2023-10-09 01:01:28,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 50790400. Throughput: 0: 1691.9, 1: 1681.3. Samples: 12706202. Policy #0 lag: (min: 7.0, avg: 13.9, max: 39.0) -[2023-10-09 01:01:28,975][87372] Avg episode reward: [(0, '5.320'), (1, '5.770')] -[2023-10-09 01:01:29,445][88326] Updated weights for policy 0, policy_version 24802 (0.0009) -[2023-10-09 01:01:29,808][88326] Updated weights for policy 0, policy_version 24812 (0.0008) -[2023-10-09 01:01:30,175][88326] Updated weights for policy 0, policy_version 24822 (0.0008) -[2023-10-09 01:01:30,390][88327] Updated weights for policy 1, policy_version 24810 (0.0009) -[2023-10-09 01:01:30,552][88326] Updated weights for policy 0, policy_version 24832 (0.0008) -[2023-10-09 01:01:30,763][88327] Updated weights for policy 1, policy_version 24820 (0.0009) -[2023-10-09 01:01:31,132][88327] Updated weights for policy 1, policy_version 24830 (0.0008) -[2023-10-09 01:01:33,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 50855936. Throughput: 0: 1688.0, 1: 1701.5. Samples: 12727146. Policy #0 lag: (min: 7.0, avg: 13.9, max: 39.0) -[2023-10-09 01:01:33,975][87372] Avg episode reward: [(0, '5.240'), (1, '5.520')] -[2023-10-09 01:01:34,643][88326] Updated weights for policy 0, policy_version 24842 (0.0008) -[2023-10-09 01:01:35,018][88326] Updated weights for policy 0, policy_version 24852 (0.0009) -[2023-10-09 01:01:35,114][88327] Updated weights for policy 1, policy_version 24840 (0.0008) -[2023-10-09 01:01:35,382][88326] Updated weights for policy 0, policy_version 24862 (0.0009) -[2023-10-09 01:01:35,472][88327] Updated weights for policy 1, policy_version 24850 (0.0009) -[2023-10-09 01:01:35,833][88327] Updated weights for policy 1, policy_version 24860 (0.0008) -[2023-10-09 01:01:38,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 50921472. Throughput: 0: 1677.3, 1: 1677.0. Samples: 12736354. Policy #0 lag: (min: 7.0, avg: 13.9, max: 39.0) -[2023-10-09 01:01:38,975][87372] Avg episode reward: [(0, '5.650'), (1, '5.080')] -[2023-10-09 01:01:39,375][88326] Updated weights for policy 0, policy_version 24872 (0.0008) -[2023-10-09 01:01:39,740][88326] Updated weights for policy 0, policy_version 24882 (0.0011) -[2023-10-09 01:01:39,884][88327] Updated weights for policy 1, policy_version 24870 (0.0009) -[2023-10-09 01:01:40,116][88326] Updated weights for policy 0, policy_version 24892 (0.0008) -[2023-10-09 01:01:40,253][88327] Updated weights for policy 1, policy_version 24880 (0.0009) -[2023-10-09 01:01:40,624][88327] Updated weights for policy 1, policy_version 24890 (0.0011) -[2023-10-09 01:01:43,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 50987008. Throughput: 0: 1689.3, 1: 1696.4. Samples: 12757142. Policy #0 lag: (min: 7.0, avg: 13.9, max: 39.0) -[2023-10-09 01:01:43,975][87372] Avg episode reward: [(0, '5.590'), (1, '5.350')] -[2023-10-09 01:01:44,278][88326] Updated weights for policy 0, policy_version 24902 (0.0007) -[2023-10-09 01:01:44,625][88327] Updated weights for policy 1, policy_version 24900 (0.0008) -[2023-10-09 01:01:44,650][88326] Updated weights for policy 0, policy_version 24912 (0.0009) -[2023-10-09 01:01:44,988][88327] Updated weights for policy 1, policy_version 24910 (0.0008) -[2023-10-09 01:01:45,025][88326] Updated weights for policy 0, policy_version 24922 (0.0008) -[2023-10-09 01:01:45,359][88327] Updated weights for policy 1, policy_version 24920 (0.0008) -[2023-10-09 01:01:48,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.3, 300 sec: 13440.4). Total num frames: 51052544. Throughput: 0: 1690.9, 1: 1705.4. Samples: 12777944. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 01:01:48,975][87372] Avg episode reward: [(0, '5.880'), (1, '5.620')] -[2023-10-09 01:01:48,991][88326] Updated weights for policy 0, policy_version 24932 (0.0009) -[2023-10-09 01:01:49,361][88326] Updated weights for policy 0, policy_version 24942 (0.0009) -[2023-10-09 01:01:49,471][88327] Updated weights for policy 1, policy_version 24930 (0.0008) -[2023-10-09 01:01:49,720][88326] Updated weights for policy 0, policy_version 24952 (0.0007) -[2023-10-09 01:01:49,839][88327] Updated weights for policy 1, policy_version 24940 (0.0009) -[2023-10-09 01:01:50,205][88327] Updated weights for policy 1, policy_version 24950 (0.0007) -[2023-10-09 01:01:50,561][88327] Updated weights for policy 1, policy_version 24960 (0.0008) -[2023-10-09 01:01:53,763][88326] Updated weights for policy 0, policy_version 24962 (0.0008) -[2023-10-09 01:01:53,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 51118080. Throughput: 0: 1683.6, 1: 1680.7. Samples: 12787118. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 01:01:53,975][87372] Avg episode reward: [(0, '5.420'), (1, '5.450')] -[2023-10-09 01:01:54,124][88326] Updated weights for policy 0, policy_version 24972 (0.0008) -[2023-10-09 01:01:54,491][88326] Updated weights for policy 0, policy_version 24982 (0.0009) -[2023-10-09 01:01:54,515][88327] Updated weights for policy 1, policy_version 24970 (0.0008) -[2023-10-09 01:01:54,857][88326] Updated weights for policy 0, policy_version 24992 (0.0007) -[2023-10-09 01:01:54,875][88327] Updated weights for policy 1, policy_version 24980 (0.0007) -[2023-10-09 01:01:55,228][88327] Updated weights for policy 1, policy_version 24990 (0.0008) -[2023-10-09 01:01:58,909][88326] Updated weights for policy 0, policy_version 25002 (0.0010) -[2023-10-09 01:01:58,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 51183616. Throughput: 0: 1691.5, 1: 1705.4. Samples: 12808134. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 01:01:58,975][87372] Avg episode reward: [(0, '5.560'), (1, '5.410')] -[2023-10-09 01:01:59,275][88326] Updated weights for policy 0, policy_version 25012 (0.0009) -[2023-10-09 01:01:59,326][88327] Updated weights for policy 1, policy_version 25000 (0.0009) -[2023-10-09 01:01:59,647][88326] Updated weights for policy 0, policy_version 25022 (0.0010) -[2023-10-09 01:01:59,683][88327] Updated weights for policy 1, policy_version 25010 (0.0008) -[2023-10-09 01:02:00,047][88327] Updated weights for policy 1, policy_version 25020 (0.0010) -[2023-10-09 01:02:03,838][88326] Updated weights for policy 0, policy_version 25032 (0.0009) -[2023-10-09 01:02:03,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 51249152. Throughput: 0: 1692.6, 1: 1707.9. Samples: 12828944. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 01:02:03,975][87372] Avg episode reward: [(0, '5.490'), (1, '5.250')] -[2023-10-09 01:02:04,139][88327] Updated weights for policy 1, policy_version 25030 (0.0008) -[2023-10-09 01:02:04,208][88326] Updated weights for policy 0, policy_version 25042 (0.0007) -[2023-10-09 01:02:04,530][88327] Updated weights for policy 1, policy_version 25040 (0.0008) -[2023-10-09 01:02:04,580][88326] Updated weights for policy 0, policy_version 25052 (0.0007) -[2023-10-09 01:02:04,898][88327] Updated weights for policy 1, policy_version 25050 (0.0009) -[2023-10-09 01:02:08,786][88326] Updated weights for policy 0, policy_version 25062 (0.0008) -[2023-10-09 01:02:08,869][88327] Updated weights for policy 1, policy_version 25060 (0.0010) -[2023-10-09 01:02:08,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 51314688. Throughput: 0: 1693.6, 1: 1687.1. Samples: 12837904. Policy #0 lag: (min: 1.0, avg: 7.6, max: 33.0) -[2023-10-09 01:02:08,975][87372] Avg episode reward: [(0, '5.710'), (1, '4.840')] -[2023-10-09 01:02:09,182][88326] Updated weights for policy 0, policy_version 25072 (0.0009) -[2023-10-09 01:02:09,225][88327] Updated weights for policy 1, policy_version 25070 (0.0007) -[2023-10-09 01:02:09,549][88326] Updated weights for policy 0, policy_version 25082 (0.0008) -[2023-10-09 01:02:09,597][88327] Updated weights for policy 1, policy_version 25080 (0.0007) -[2023-10-09 01:02:13,418][88326] Updated weights for policy 0, policy_version 25092 (0.0008) -[2023-10-09 01:02:13,682][88327] Updated weights for policy 1, policy_version 25090 (0.0008) -[2023-10-09 01:02:13,780][88326] Updated weights for policy 0, policy_version 25102 (0.0008) -[2023-10-09 01:02:13,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 51380224. Throughput: 0: 1680.4, 1: 1702.5. Samples: 12858432. Policy #0 lag: (min: 1.0, avg: 7.6, max: 33.0) -[2023-10-09 01:02:13,974][87372] Avg episode reward: [(0, '5.910'), (1, '5.140')] -[2023-10-09 01:02:14,040][88327] Updated weights for policy 1, policy_version 25100 (0.0009) -[2023-10-09 01:02:14,149][88326] Updated weights for policy 0, policy_version 25112 (0.0009) -[2023-10-09 01:02:14,413][88327] Updated weights for policy 1, policy_version 25110 (0.0008) -[2023-10-09 01:02:14,775][88327] Updated weights for policy 1, policy_version 25120 (0.0007) -[2023-10-09 01:02:18,105][88326] Updated weights for policy 0, policy_version 25122 (0.0007) -[2023-10-09 01:02:18,465][88326] Updated weights for policy 0, policy_version 25132 (0.0009) -[2023-10-09 01:02:18,840][88327] Updated weights for policy 1, policy_version 25130 (0.0007) -[2023-10-09 01:02:18,843][88326] Updated weights for policy 0, policy_version 25142 (0.0008) -[2023-10-09 01:02:18,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 51445760. Throughput: 0: 1678.1, 1: 1696.5. Samples: 12879004. Policy #0 lag: (min: 1.0, avg: 7.6, max: 33.0) -[2023-10-09 01:02:18,975][87372] Avg episode reward: [(0, '5.810'), (1, '5.510')] -[2023-10-09 01:02:19,207][88327] Updated weights for policy 1, policy_version 25140 (0.0008) -[2023-10-09 01:02:19,208][88326] Updated weights for policy 0, policy_version 25152 (0.0008) -[2023-10-09 01:02:19,581][88327] Updated weights for policy 1, policy_version 25150 (0.0009) -[2023-10-09 01:02:23,408][88326] Updated weights for policy 0, policy_version 25162 (0.0008) -[2023-10-09 01:02:23,667][88327] Updated weights for policy 1, policy_version 25160 (0.0008) -[2023-10-09 01:02:23,770][88326] Updated weights for policy 0, policy_version 25172 (0.0008) -[2023-10-09 01:02:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 51511296. Throughput: 0: 1685.2, 1: 1693.4. Samples: 12888390. Policy #0 lag: (min: 1.0, avg: 7.6, max: 33.0) -[2023-10-09 01:02:23,974][87372] Avg episode reward: [(0, '6.020'), (1, '5.090')] -[2023-10-09 01:02:24,033][88327] Updated weights for policy 1, policy_version 25170 (0.0008) -[2023-10-09 01:02:24,144][88326] Updated weights for policy 0, policy_version 25182 (0.0009) -[2023-10-09 01:02:24,404][88327] Updated weights for policy 1, policy_version 25180 (0.0009) -[2023-10-09 01:02:28,126][88326] Updated weights for policy 0, policy_version 25192 (0.0010) -[2023-10-09 01:02:28,359][88327] Updated weights for policy 1, policy_version 25190 (0.0009) -[2023-10-09 01:02:28,505][88326] Updated weights for policy 0, policy_version 25202 (0.0008) -[2023-10-09 01:02:28,726][88327] Updated weights for policy 1, policy_version 25200 (0.0009) -[2023-10-09 01:02:28,870][88326] Updated weights for policy 0, policy_version 25212 (0.0008) -[2023-10-09 01:02:28,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 51576832. Throughput: 0: 1690.1, 1: 1694.5. Samples: 12909450. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:02:28,975][87372] Avg episode reward: [(0, '5.530'), (1, '5.420')] -[2023-10-09 01:02:29,102][88327] Updated weights for policy 1, policy_version 25210 (0.0010) -[2023-10-09 01:02:32,944][88326] Updated weights for policy 0, policy_version 25222 (0.0009) -[2023-10-09 01:02:33,097][88327] Updated weights for policy 1, policy_version 25220 (0.0007) -[2023-10-09 01:02:33,317][88326] Updated weights for policy 0, policy_version 25232 (0.0008) -[2023-10-09 01:02:33,461][88327] Updated weights for policy 1, policy_version 25230 (0.0009) -[2023-10-09 01:02:33,677][88326] Updated weights for policy 0, policy_version 25242 (0.0007) -[2023-10-09 01:02:33,831][88327] Updated weights for policy 1, policy_version 25240 (0.0007) -[2023-10-09 01:02:33,974][87372] Fps is (10 sec: 16383.8, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 51675136. Throughput: 0: 1680.3, 1: 1689.5. Samples: 12929586. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:02:33,975][87372] Avg episode reward: [(0, '5.770'), (1, '5.380')] -[2023-10-09 01:02:33,985][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000025248_25853952.pth... -[2023-10-09 01:02:34,025][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000023648_24215552.pth -[2023-10-09 01:02:34,126][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000025248_25853952.pth... -[2023-10-09 01:02:34,164][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000023648_24215552.pth -[2023-10-09 01:02:37,580][88326] Updated weights for policy 0, policy_version 25252 (0.0008) -[2023-10-09 01:02:37,841][88327] Updated weights for policy 1, policy_version 25250 (0.0008) -[2023-10-09 01:02:37,951][88326] Updated weights for policy 0, policy_version 25262 (0.0008) -[2023-10-09 01:02:38,209][88327] Updated weights for policy 1, policy_version 25260 (0.0008) -[2023-10-09 01:02:38,316][88326] Updated weights for policy 0, policy_version 25272 (0.0007) -[2023-10-09 01:02:38,572][88327] Updated weights for policy 1, policy_version 25270 (0.0009) -[2023-10-09 01:02:38,937][88327] Updated weights for policy 1, policy_version 25280 (0.0010) -[2023-10-09 01:02:38,974][87372] Fps is (10 sec: 19660.8, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 51773440. Throughput: 0: 1690.6, 1: 1696.0. Samples: 12939512. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:02:38,975][87372] Avg episode reward: [(0, '5.690'), (1, '5.160')] -[2023-10-09 01:02:42,244][88326] Updated weights for policy 0, policy_version 25282 (0.0008) -[2023-10-09 01:02:42,621][88326] Updated weights for policy 0, policy_version 25292 (0.0009) -[2023-10-09 01:02:42,979][88326] Updated weights for policy 0, policy_version 25302 (0.0007) -[2023-10-09 01:02:43,050][88327] Updated weights for policy 1, policy_version 25290 (0.0009) -[2023-10-09 01:02:43,346][88326] Updated weights for policy 0, policy_version 25312 (0.0009) -[2023-10-09 01:02:43,418][88327] Updated weights for policy 1, policy_version 25300 (0.0009) -[2023-10-09 01:02:43,781][88327] Updated weights for policy 1, policy_version 25310 (0.0009) -[2023-10-09 01:02:43,974][87372] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 51838976. Throughput: 0: 1697.2, 1: 1691.3. Samples: 12960616. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-09 01:02:43,975][87372] Avg episode reward: [(0, '5.640'), (1, '5.490')] -[2023-10-09 01:02:47,342][88326] Updated weights for policy 0, policy_version 25322 (0.0008) -[2023-10-09 01:02:47,713][88326] Updated weights for policy 0, policy_version 25332 (0.0009) -[2023-10-09 01:02:47,828][88327] Updated weights for policy 1, policy_version 25320 (0.0009) -[2023-10-09 01:02:48,080][88326] Updated weights for policy 0, policy_version 25342 (0.0009) -[2023-10-09 01:02:48,183][88327] Updated weights for policy 1, policy_version 25330 (0.0009) -[2023-10-09 01:02:48,551][88327] Updated weights for policy 1, policy_version 25340 (0.0008) -[2023-10-09 01:02:48,974][87372] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 51904512. Throughput: 0: 1672.9, 1: 1676.4. Samples: 12979664. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-09 01:02:48,975][87372] Avg episode reward: [(0, '5.650'), (1, '4.780')] -[2023-10-09 01:02:52,062][88326] Updated weights for policy 0, policy_version 25352 (0.0011) -[2023-10-09 01:02:52,430][88326] Updated weights for policy 0, policy_version 25362 (0.0009) -[2023-10-09 01:02:52,661][88327] Updated weights for policy 1, policy_version 25350 (0.0008) -[2023-10-09 01:02:52,791][88326] Updated weights for policy 0, policy_version 25372 (0.0007) -[2023-10-09 01:02:53,040][88327] Updated weights for policy 1, policy_version 25360 (0.0008) -[2023-10-09 01:02:53,404][88327] Updated weights for policy 1, policy_version 25370 (0.0007) -[2023-10-09 01:02:53,974][87372] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 51970048. Throughput: 0: 1703.2, 1: 1694.1. Samples: 12990784. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-09 01:02:53,975][87372] Avg episode reward: [(0, '5.470'), (1, '4.900')] -[2023-10-09 01:02:57,037][88326] Updated weights for policy 0, policy_version 25382 (0.0008) -[2023-10-09 01:02:57,258][88327] Updated weights for policy 1, policy_version 25380 (0.0008) -[2023-10-09 01:02:57,427][88326] Updated weights for policy 0, policy_version 25392 (0.0008) -[2023-10-09 01:02:57,617][88327] Updated weights for policy 1, policy_version 25390 (0.0008) -[2023-10-09 01:02:57,794][88326] Updated weights for policy 0, policy_version 25402 (0.0009) -[2023-10-09 01:02:57,979][88327] Updated weights for policy 1, policy_version 25400 (0.0007) -[2023-10-09 01:02:58,974][87372] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 52035584. Throughput: 0: 1699.7, 1: 1695.7. Samples: 13011224. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-09 01:02:58,974][87372] Avg episode reward: [(0, '5.380'), (1, '5.160')] -[2023-10-09 01:03:01,837][88326] Updated weights for policy 0, policy_version 25412 (0.0010) -[2023-10-09 01:03:02,171][88327] Updated weights for policy 1, policy_version 25410 (0.0008) -[2023-10-09 01:03:02,209][88326] Updated weights for policy 0, policy_version 25422 (0.0008) -[2023-10-09 01:03:02,534][88327] Updated weights for policy 1, policy_version 25420 (0.0007) -[2023-10-09 01:03:02,577][88326] Updated weights for policy 0, policy_version 25432 (0.0008) -[2023-10-09 01:03:02,903][88327] Updated weights for policy 1, policy_version 25430 (0.0009) -[2023-10-09 01:03:03,269][88327] Updated weights for policy 1, policy_version 25440 (0.0008) -[2023-10-09 01:03:03,974][87372] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 52101120. Throughput: 0: 1687.4, 1: 1673.8. Samples: 13030258. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:03:03,975][87372] Avg episode reward: [(0, '5.290'), (1, '4.750')] -[2023-10-09 01:03:06,481][88326] Updated weights for policy 0, policy_version 25442 (0.0009) -[2023-10-09 01:03:06,849][88326] Updated weights for policy 0, policy_version 25452 (0.0008) -[2023-10-09 01:03:07,217][88326] Updated weights for policy 0, policy_version 25462 (0.0007) -[2023-10-09 01:03:07,322][88327] Updated weights for policy 1, policy_version 25450 (0.0007) -[2023-10-09 01:03:07,578][88326] Updated weights for policy 0, policy_version 25472 (0.0008) -[2023-10-09 01:03:07,695][88327] Updated weights for policy 1, policy_version 25460 (0.0007) -[2023-10-09 01:03:08,066][88327] Updated weights for policy 1, policy_version 25470 (0.0008) -[2023-10-09 01:03:08,974][87372] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 52166656. Throughput: 0: 1710.2, 1: 1699.7. Samples: 13041836. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:03:08,975][87372] Avg episode reward: [(0, '5.650'), (1, '5.370')] -[2023-10-09 01:03:11,502][88326] Updated weights for policy 0, policy_version 25482 (0.0008) -[2023-10-09 01:03:11,870][88326] Updated weights for policy 0, policy_version 25492 (0.0009) -[2023-10-09 01:03:12,186][88327] Updated weights for policy 1, policy_version 25480 (0.0009) -[2023-10-09 01:03:12,240][88326] Updated weights for policy 0, policy_version 25502 (0.0007) -[2023-10-09 01:03:12,541][88327] Updated weights for policy 1, policy_version 25490 (0.0009) -[2023-10-09 01:03:12,911][88327] Updated weights for policy 1, policy_version 25500 (0.0008) -[2023-10-09 01:03:13,974][87372] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 52232192. Throughput: 0: 1684.3, 1: 1690.3. Samples: 13061306. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:03:13,975][87372] Avg episode reward: [(0, '5.700'), (1, '5.140')] -[2023-10-09 01:03:16,232][88326] Updated weights for policy 0, policy_version 25512 (0.0007) -[2023-10-09 01:03:16,605][88326] Updated weights for policy 0, policy_version 25522 (0.0009) -[2023-10-09 01:03:16,973][88326] Updated weights for policy 0, policy_version 25532 (0.0007) -[2023-10-09 01:03:17,089][88327] Updated weights for policy 1, policy_version 25510 (0.0007) -[2023-10-09 01:03:17,449][88327] Updated weights for policy 1, policy_version 25520 (0.0007) -[2023-10-09 01:03:17,809][88327] Updated weights for policy 1, policy_version 25530 (0.0008) -[2023-10-09 01:03:18,974][87372] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 52297728. Throughput: 0: 1697.0, 1: 1673.4. Samples: 13081254. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:03:18,975][87372] Avg episode reward: [(0, '5.720'), (1, '5.210')] -[2023-10-09 01:03:20,907][88326] Updated weights for policy 0, policy_version 25542 (0.0009) -[2023-10-09 01:03:21,277][88326] Updated weights for policy 0, policy_version 25552 (0.0008) -[2023-10-09 01:03:21,649][88326] Updated weights for policy 0, policy_version 25562 (0.0009) -[2023-10-09 01:03:21,767][88327] Updated weights for policy 1, policy_version 25540 (0.0010) -[2023-10-09 01:03:22,134][88327] Updated weights for policy 1, policy_version 25550 (0.0010) -[2023-10-09 01:03:22,508][88327] Updated weights for policy 1, policy_version 25560 (0.0008) -[2023-10-09 01:03:23,974][87372] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 52363264. Throughput: 0: 1703.3, 1: 1696.8. Samples: 13092518. Policy #0 lag: (min: 15.0, avg: 15.3, max: 26.0) -[2023-10-09 01:03:23,975][87372] Avg episode reward: [(0, '5.610'), (1, '5.600')] -[2023-10-09 01:03:25,398][88326] Updated weights for policy 0, policy_version 25572 (0.0008) -[2023-10-09 01:03:25,771][88326] Updated weights for policy 0, policy_version 25582 (0.0009) -[2023-10-09 01:03:26,131][88326] Updated weights for policy 0, policy_version 25592 (0.0009) -[2023-10-09 01:03:26,521][88327] Updated weights for policy 1, policy_version 25570 (0.0010) -[2023-10-09 01:03:26,890][88327] Updated weights for policy 1, policy_version 25580 (0.0007) -[2023-10-09 01:03:27,254][88327] Updated weights for policy 1, policy_version 25590 (0.0010) -[2023-10-09 01:03:27,628][88327] Updated weights for policy 1, policy_version 25600 (0.0009) -[2023-10-09 01:03:28,974][87372] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 52428800. Throughput: 0: 1691.8, 1: 1685.0. Samples: 13112570. Policy #0 lag: (min: 15.0, avg: 15.3, max: 26.0) -[2023-10-09 01:03:28,975][87372] Avg episode reward: [(0, '5.780'), (1, '5.180')] -[2023-10-09 01:03:30,288][88326] Updated weights for policy 0, policy_version 25602 (0.0009) -[2023-10-09 01:03:30,653][88326] Updated weights for policy 0, policy_version 25612 (0.0009) -[2023-10-09 01:03:31,028][88326] Updated weights for policy 0, policy_version 25622 (0.0007) -[2023-10-09 01:03:31,403][88326] Updated weights for policy 0, policy_version 25632 (0.0007) -[2023-10-09 01:03:31,680][88327] Updated weights for policy 1, policy_version 25610 (0.0009) -[2023-10-09 01:03:32,051][88327] Updated weights for policy 1, policy_version 25620 (0.0009) -[2023-10-09 01:03:32,412][88327] Updated weights for policy 1, policy_version 25630 (0.0008) -[2023-10-09 01:03:33,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 52494336. Throughput: 0: 1716.7, 1: 1689.2. Samples: 13132928. Policy #0 lag: (min: 15.0, avg: 15.3, max: 26.0) -[2023-10-09 01:03:33,975][87372] Avg episode reward: [(0, '5.950'), (1, '5.190')] -[2023-10-09 01:03:35,332][88326] Updated weights for policy 0, policy_version 25642 (0.0007) -[2023-10-09 01:03:35,696][88326] Updated weights for policy 0, policy_version 25652 (0.0008) -[2023-10-09 01:03:36,063][88326] Updated weights for policy 0, policy_version 25662 (0.0009) -[2023-10-09 01:03:36,386][88327] Updated weights for policy 1, policy_version 25640 (0.0009) -[2023-10-09 01:03:36,759][88327] Updated weights for policy 1, policy_version 25650 (0.0007) -[2023-10-09 01:03:37,133][88327] Updated weights for policy 1, policy_version 25660 (0.0007) -[2023-10-09 01:03:38,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 52559872. Throughput: 0: 1688.4, 1: 1701.7. Samples: 13143336. Policy #0 lag: (min: 15.0, avg: 15.3, max: 26.0) -[2023-10-09 01:03:38,975][87372] Avg episode reward: [(0, '6.170'), (1, '5.480')] -[2023-10-09 01:03:40,038][88326] Updated weights for policy 0, policy_version 25672 (0.0008) -[2023-10-09 01:03:40,416][88326] Updated weights for policy 0, policy_version 25682 (0.0009) -[2023-10-09 01:03:40,780][88326] Updated weights for policy 0, policy_version 25692 (0.0010) -[2023-10-09 01:03:41,253][88327] Updated weights for policy 1, policy_version 25670 (0.0010) -[2023-10-09 01:03:41,617][88327] Updated weights for policy 1, policy_version 25680 (0.0009) -[2023-10-09 01:03:41,983][88327] Updated weights for policy 1, policy_version 25690 (0.0009) -[2023-10-09 01:03:43,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 52625408. Throughput: 0: 1701.3, 1: 1673.6. Samples: 13163092. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:03:43,975][87372] Avg episode reward: [(0, '5.750'), (1, '5.910')] -[2023-10-09 01:03:43,976][88168] Saving new best policy, reward=5.910! -[2023-10-09 01:03:44,913][88326] Updated weights for policy 0, policy_version 25702 (0.0007) -[2023-10-09 01:03:45,299][88326] Updated weights for policy 0, policy_version 25712 (0.0008) -[2023-10-09 01:03:45,666][88326] Updated weights for policy 0, policy_version 25722 (0.0009) -[2023-10-09 01:03:46,006][88327] Updated weights for policy 1, policy_version 25700 (0.0009) -[2023-10-09 01:03:46,383][88327] Updated weights for policy 1, policy_version 25710 (0.0011) -[2023-10-09 01:03:46,735][88327] Updated weights for policy 1, policy_version 25720 (0.0009) -[2023-10-09 01:03:48,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 52690944. Throughput: 0: 1712.8, 1: 1695.4. Samples: 13183626. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:03:48,975][87372] Avg episode reward: [(0, '5.830'), (1, '5.820')] -[2023-10-09 01:03:49,682][88326] Updated weights for policy 0, policy_version 25732 (0.0008) -[2023-10-09 01:03:50,049][88326] Updated weights for policy 0, policy_version 25742 (0.0009) -[2023-10-09 01:03:50,419][88326] Updated weights for policy 0, policy_version 25752 (0.0008) -[2023-10-09 01:03:50,732][88327] Updated weights for policy 1, policy_version 25730 (0.0007) -[2023-10-09 01:03:51,095][88327] Updated weights for policy 1, policy_version 25740 (0.0010) -[2023-10-09 01:03:51,472][88327] Updated weights for policy 1, policy_version 25750 (0.0010) -[2023-10-09 01:03:51,839][88327] Updated weights for policy 1, policy_version 25760 (0.0011) -[2023-10-09 01:03:53,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 52756480. Throughput: 0: 1682.7, 1: 1687.2. Samples: 13193484. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:03:53,975][87372] Avg episode reward: [(0, '5.450'), (1, '6.110')] -[2023-10-09 01:03:53,977][88168] Saving new best policy, reward=6.110! -[2023-10-09 01:03:54,389][88326] Updated weights for policy 0, policy_version 25762 (0.0009) -[2023-10-09 01:03:54,754][88326] Updated weights for policy 0, policy_version 25772 (0.0010) -[2023-10-09 01:03:55,122][88326] Updated weights for policy 0, policy_version 25782 (0.0010) -[2023-10-09 01:03:55,490][88326] Updated weights for policy 0, policy_version 25792 (0.0010) -[2023-10-09 01:03:55,995][88327] Updated weights for policy 1, policy_version 25770 (0.0010) -[2023-10-09 01:03:56,363][88327] Updated weights for policy 1, policy_version 25780 (0.0008) -[2023-10-09 01:03:56,733][88327] Updated weights for policy 1, policy_version 25790 (0.0009) -[2023-10-09 01:03:58,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 52822016. Throughput: 0: 1704.0, 1: 1678.4. Samples: 13213516. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:03:58,975][87372] Avg episode reward: [(0, '5.850'), (1, '4.640')] -[2023-10-09 01:03:59,679][88326] Updated weights for policy 0, policy_version 25802 (0.0007) -[2023-10-09 01:04:00,046][88326] Updated weights for policy 0, policy_version 25812 (0.0007) -[2023-10-09 01:04:00,408][88326] Updated weights for policy 0, policy_version 25822 (0.0009) -[2023-10-09 01:04:00,594][88327] Updated weights for policy 1, policy_version 25800 (0.0009) -[2023-10-09 01:04:00,959][88327] Updated weights for policy 1, policy_version 25810 (0.0009) -[2023-10-09 01:04:01,322][88327] Updated weights for policy 1, policy_version 25820 (0.0009) -[2023-10-09 01:04:03,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 52887552. Throughput: 0: 1701.0, 1: 1704.2. Samples: 13234488. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:04:03,975][87372] Avg episode reward: [(0, '6.020'), (1, '4.700')] -[2023-10-09 01:04:04,605][88326] Updated weights for policy 0, policy_version 25832 (0.0010) -[2023-10-09 01:04:04,974][88326] Updated weights for policy 0, policy_version 25842 (0.0007) -[2023-10-09 01:04:05,347][88326] Updated weights for policy 0, policy_version 25852 (0.0007) -[2023-10-09 01:04:05,508][88327] Updated weights for policy 1, policy_version 25830 (0.0008) -[2023-10-09 01:04:05,876][88327] Updated weights for policy 1, policy_version 25840 (0.0009) -[2023-10-09 01:04:06,244][88327] Updated weights for policy 1, policy_version 25850 (0.0011) -[2023-10-09 01:04:08,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 52953088. Throughput: 0: 1684.3, 1: 1681.8. Samples: 13243996. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:04:08,975][87372] Avg episode reward: [(0, '5.640'), (1, '5.150')] -[2023-10-09 01:04:09,605][88326] Updated weights for policy 0, policy_version 25862 (0.0011) -[2023-10-09 01:04:09,969][88326] Updated weights for policy 0, policy_version 25872 (0.0008) -[2023-10-09 01:04:10,184][88327] Updated weights for policy 1, policy_version 25860 (0.0007) -[2023-10-09 01:04:10,339][88326] Updated weights for policy 0, policy_version 25882 (0.0008) -[2023-10-09 01:04:10,562][88327] Updated weights for policy 1, policy_version 25870 (0.0009) -[2023-10-09 01:04:10,921][88327] Updated weights for policy 1, policy_version 25880 (0.0008) -[2023-10-09 01:04:13,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 53018624. Throughput: 0: 1685.4, 1: 1688.6. Samples: 13264402. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:04:13,974][87372] Avg episode reward: [(0, '5.790'), (1, '5.180')] -[2023-10-09 01:04:14,522][88326] Updated weights for policy 0, policy_version 25892 (0.0008) -[2023-10-09 01:04:14,733][88327] Updated weights for policy 1, policy_version 25890 (0.0009) -[2023-10-09 01:04:14,896][88326] Updated weights for policy 0, policy_version 25902 (0.0008) -[2023-10-09 01:04:15,100][88327] Updated weights for policy 1, policy_version 25900 (0.0007) -[2023-10-09 01:04:15,264][88326] Updated weights for policy 0, policy_version 25912 (0.0008) -[2023-10-09 01:04:15,460][88327] Updated weights for policy 1, policy_version 25910 (0.0008) -[2023-10-09 01:04:15,825][88327] Updated weights for policy 1, policy_version 25920 (0.0010) -[2023-10-09 01:04:18,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 53084160. Throughput: 0: 1683.8, 1: 1702.1. Samples: 13285294. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:04:18,975][87372] Avg episode reward: [(0, '5.970'), (1, '5.390')] -[2023-10-09 01:04:19,310][88326] Updated weights for policy 0, policy_version 25922 (0.0008) -[2023-10-09 01:04:19,682][88326] Updated weights for policy 0, policy_version 25932 (0.0009) -[2023-10-09 01:04:19,866][88327] Updated weights for policy 1, policy_version 25930 (0.0009) -[2023-10-09 01:04:20,045][88326] Updated weights for policy 0, policy_version 25942 (0.0008) -[2023-10-09 01:04:20,231][88327] Updated weights for policy 1, policy_version 25940 (0.0009) -[2023-10-09 01:04:20,418][88326] Updated weights for policy 0, policy_version 25952 (0.0010) -[2023-10-09 01:04:20,603][88327] Updated weights for policy 1, policy_version 25950 (0.0008) -[2023-10-09 01:04:23,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 53149696. Throughput: 0: 1679.8, 1: 1674.8. Samples: 13294296. Policy #0 lag: (min: 31.0, avg: 31.6, max: 47.0) -[2023-10-09 01:04:23,975][87372] Avg episode reward: [(0, '5.420'), (1, '5.570')] -[2023-10-09 01:04:24,435][88326] Updated weights for policy 0, policy_version 25962 (0.0009) -[2023-10-09 01:04:24,738][88327] Updated weights for policy 1, policy_version 25960 (0.0009) -[2023-10-09 01:04:24,806][88326] Updated weights for policy 0, policy_version 25972 (0.0007) -[2023-10-09 01:04:25,105][88327] Updated weights for policy 1, policy_version 25970 (0.0008) -[2023-10-09 01:04:25,185][88326] Updated weights for policy 0, policy_version 25982 (0.0007) -[2023-10-09 01:04:25,464][88327] Updated weights for policy 1, policy_version 25980 (0.0011) -[2023-10-09 01:04:28,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 53215232. Throughput: 0: 1682.9, 1: 1700.6. Samples: 13315350. Policy #0 lag: (min: 31.0, avg: 31.6, max: 47.0) -[2023-10-09 01:04:28,975][87372] Avg episode reward: [(0, '5.390'), (1, '5.280')] -[2023-10-09 01:04:29,053][88326] Updated weights for policy 0, policy_version 25992 (0.0008) -[2023-10-09 01:04:29,416][88326] Updated weights for policy 0, policy_version 26002 (0.0007) -[2023-10-09 01:04:29,552][88327] Updated weights for policy 1, policy_version 25990 (0.0009) -[2023-10-09 01:04:29,789][88326] Updated weights for policy 0, policy_version 26012 (0.0008) -[2023-10-09 01:04:29,927][88327] Updated weights for policy 1, policy_version 26000 (0.0007) -[2023-10-09 01:04:30,300][88327] Updated weights for policy 1, policy_version 26010 (0.0008) -[2023-10-09 01:04:33,670][88326] Updated weights for policy 0, policy_version 26022 (0.0009) -[2023-10-09 01:04:33,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 53280768. Throughput: 0: 1693.9, 1: 1700.7. Samples: 13336380. Policy #0 lag: (min: 31.0, avg: 31.6, max: 47.0) -[2023-10-09 01:04:33,975][87372] Avg episode reward: [(0, '5.670'), (1, '5.790')] -[2023-10-09 01:04:33,984][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000026016_26640384.pth... -[2023-10-09 01:04:34,025][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000024448_25034752.pth -[2023-10-09 01:04:34,041][88326] Updated weights for policy 0, policy_version 26032 (0.0010) -[2023-10-09 01:04:34,358][88327] Updated weights for policy 1, policy_version 26020 (0.0008) -[2023-10-09 01:04:34,405][88326] Updated weights for policy 0, policy_version 26042 (0.0007) -[2023-10-09 01:04:34,621][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000026048_26673152.pth... -[2023-10-09 01:04:34,651][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000024448_25034752.pth -[2023-10-09 01:04:34,720][88327] Updated weights for policy 1, policy_version 26030 (0.0009) -[2023-10-09 01:04:35,096][88327] Updated weights for policy 1, policy_version 26040 (0.0009) -[2023-10-09 01:04:38,575][88326] Updated weights for policy 0, policy_version 26052 (0.0008) -[2023-10-09 01:04:38,947][88326] Updated weights for policy 0, policy_version 26062 (0.0009) -[2023-10-09 01:04:38,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 53346304. Throughput: 0: 1692.0, 1: 1681.9. Samples: 13345308. Policy #0 lag: (min: 31.0, avg: 31.6, max: 47.0) -[2023-10-09 01:04:38,975][87372] Avg episode reward: [(0, '5.410'), (1, '5.200')] -[2023-10-09 01:04:39,023][88327] Updated weights for policy 1, policy_version 26050 (0.0010) -[2023-10-09 01:04:39,315][88326] Updated weights for policy 0, policy_version 26072 (0.0009) -[2023-10-09 01:04:39,387][88327] Updated weights for policy 1, policy_version 26060 (0.0008) -[2023-10-09 01:04:39,761][88327] Updated weights for policy 1, policy_version 26070 (0.0008) -[2023-10-09 01:04:40,127][88327] Updated weights for policy 1, policy_version 26080 (0.0010) -[2023-10-09 01:04:43,336][88326] Updated weights for policy 0, policy_version 26082 (0.0009) -[2023-10-09 01:04:43,712][88326] Updated weights for policy 0, policy_version 26092 (0.0008) -[2023-10-09 01:04:43,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 53411840. Throughput: 0: 1693.3, 1: 1699.5. Samples: 13366192. Policy #0 lag: (min: 31.0, avg: 31.0, max: 34.0) -[2023-10-09 01:04:43,974][87372] Avg episode reward: [(0, '5.950'), (1, '5.700')] -[2023-10-09 01:04:44,075][88326] Updated weights for policy 0, policy_version 26102 (0.0007) -[2023-10-09 01:04:44,166][88327] Updated weights for policy 1, policy_version 26090 (0.0009) -[2023-10-09 01:04:44,445][88326] Updated weights for policy 0, policy_version 26112 (0.0009) -[2023-10-09 01:04:44,540][88327] Updated weights for policy 1, policy_version 26100 (0.0008) -[2023-10-09 01:04:44,903][88327] Updated weights for policy 1, policy_version 26110 (0.0007) -[2023-10-09 01:04:48,405][88326] Updated weights for policy 0, policy_version 26122 (0.0009) -[2023-10-09 01:04:48,767][88326] Updated weights for policy 0, policy_version 26132 (0.0009) -[2023-10-09 01:04:48,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 53477376. Throughput: 0: 1690.4, 1: 1696.0. Samples: 13386880. Policy #0 lag: (min: 31.0, avg: 31.0, max: 34.0) -[2023-10-09 01:04:48,975][87372] Avg episode reward: [(0, '5.490'), (1, '5.620')] -[2023-10-09 01:04:49,009][88327] Updated weights for policy 1, policy_version 26120 (0.0009) -[2023-10-09 01:04:49,138][88326] Updated weights for policy 0, policy_version 26142 (0.0008) -[2023-10-09 01:04:49,367][88327] Updated weights for policy 1, policy_version 26130 (0.0009) -[2023-10-09 01:04:49,726][88327] Updated weights for policy 1, policy_version 26140 (0.0008) -[2023-10-09 01:04:53,303][88326] Updated weights for policy 0, policy_version 26152 (0.0008) -[2023-10-09 01:04:53,675][88326] Updated weights for policy 0, policy_version 26162 (0.0008) -[2023-10-09 01:04:53,743][88327] Updated weights for policy 1, policy_version 26150 (0.0008) -[2023-10-09 01:04:53,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 53542912. Throughput: 0: 1697.2, 1: 1685.9. Samples: 13396234. Policy #0 lag: (min: 31.0, avg: 31.0, max: 34.0) -[2023-10-09 01:04:53,975][87372] Avg episode reward: [(0, '5.210'), (1, '5.150')] -[2023-10-09 01:04:54,052][88326] Updated weights for policy 0, policy_version 26172 (0.0009) -[2023-10-09 01:04:54,102][88327] Updated weights for policy 1, policy_version 26160 (0.0008) -[2023-10-09 01:04:54,466][88327] Updated weights for policy 1, policy_version 26170 (0.0011) -[2023-10-09 01:04:58,051][88326] Updated weights for policy 0, policy_version 26182 (0.0007) -[2023-10-09 01:04:58,422][88326] Updated weights for policy 0, policy_version 26192 (0.0008) -[2023-10-09 01:04:58,598][88327] Updated weights for policy 1, policy_version 26180 (0.0009) -[2023-10-09 01:04:58,793][88326] Updated weights for policy 0, policy_version 26202 (0.0007) -[2023-10-09 01:04:58,968][88327] Updated weights for policy 1, policy_version 26190 (0.0007) -[2023-10-09 01:04:58,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 53608448. Throughput: 0: 1696.4, 1: 1695.7. Samples: 13417050. Policy #0 lag: (min: 31.0, avg: 31.0, max: 34.0) -[2023-10-09 01:04:58,975][87372] Avg episode reward: [(0, '5.470'), (1, '5.760')] -[2023-10-09 01:04:59,340][88327] Updated weights for policy 1, policy_version 26200 (0.0011) -[2023-10-09 01:05:02,749][88326] Updated weights for policy 0, policy_version 26212 (0.0008) -[2023-10-09 01:05:03,121][88326] Updated weights for policy 0, policy_version 26222 (0.0009) -[2023-10-09 01:05:03,364][88327] Updated weights for policy 1, policy_version 26210 (0.0009) -[2023-10-09 01:05:03,479][88326] Updated weights for policy 0, policy_version 26232 (0.0008) -[2023-10-09 01:05:03,723][88327] Updated weights for policy 1, policy_version 26220 (0.0008) -[2023-10-09 01:05:03,974][87372] Fps is (10 sec: 16383.4, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 53706752. Throughput: 0: 1683.7, 1: 1693.3. Samples: 13437258. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:05:03,975][87372] Avg episode reward: [(0, '5.240'), (1, '4.960')] -[2023-10-09 01:05:04,087][88327] Updated weights for policy 1, policy_version 26230 (0.0007) -[2023-10-09 01:05:04,460][88327] Updated weights for policy 1, policy_version 26240 (0.0009) -[2023-10-09 01:05:07,490][88326] Updated weights for policy 0, policy_version 26242 (0.0009) -[2023-10-09 01:05:07,858][88326] Updated weights for policy 0, policy_version 26252 (0.0007) -[2023-10-09 01:05:08,223][88326] Updated weights for policy 0, policy_version 26262 (0.0009) -[2023-10-09 01:05:08,475][88327] Updated weights for policy 1, policy_version 26250 (0.0009) -[2023-10-09 01:05:08,590][88326] Updated weights for policy 0, policy_version 26272 (0.0007) -[2023-10-09 01:05:08,843][88327] Updated weights for policy 1, policy_version 26260 (0.0009) -[2023-10-09 01:05:08,974][87372] Fps is (10 sec: 16384.3, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 53772288. Throughput: 0: 1699.7, 1: 1695.4. Samples: 13447078. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:05:08,975][87372] Avg episode reward: [(0, '5.280'), (1, '5.110')] -[2023-10-09 01:05:09,219][88327] Updated weights for policy 1, policy_version 26270 (0.0007) -[2023-10-09 01:05:12,563][88326] Updated weights for policy 0, policy_version 26282 (0.0007) -[2023-10-09 01:05:12,922][88326] Updated weights for policy 0, policy_version 26292 (0.0007) -[2023-10-09 01:05:13,231][88327] Updated weights for policy 1, policy_version 26280 (0.0008) -[2023-10-09 01:05:13,295][88326] Updated weights for policy 0, policy_version 26302 (0.0007) -[2023-10-09 01:05:13,602][88327] Updated weights for policy 1, policy_version 26290 (0.0008) -[2023-10-09 01:05:13,960][88327] Updated weights for policy 1, policy_version 26300 (0.0010) -[2023-10-09 01:05:13,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 53837824. Throughput: 0: 1699.3, 1: 1698.1. Samples: 13468236. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:05:13,975][87372] Avg episode reward: [(0, '5.580'), (1, '5.250')] -[2023-10-09 01:05:17,511][88326] Updated weights for policy 0, policy_version 26312 (0.0009) -[2023-10-09 01:05:17,884][88326] Updated weights for policy 0, policy_version 26322 (0.0009) -[2023-10-09 01:05:18,197][88327] Updated weights for policy 1, policy_version 26310 (0.0009) -[2023-10-09 01:05:18,250][88326] Updated weights for policy 0, policy_version 26332 (0.0009) -[2023-10-09 01:05:18,591][88327] Updated weights for policy 1, policy_version 26320 (0.0010) -[2023-10-09 01:05:18,951][88327] Updated weights for policy 1, policy_version 26330 (0.0010) -[2023-10-09 01:05:18,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 53903360. Throughput: 0: 1671.3, 1: 1692.8. Samples: 13487766. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:05:18,975][87372] Avg episode reward: [(0, '6.300'), (1, '4.650')] -[2023-10-09 01:05:22,314][88326] Updated weights for policy 0, policy_version 26342 (0.0010) -[2023-10-09 01:05:22,696][88326] Updated weights for policy 0, policy_version 26352 (0.0008) -[2023-10-09 01:05:22,764][88327] Updated weights for policy 1, policy_version 26340 (0.0010) -[2023-10-09 01:05:23,066][88326] Updated weights for policy 0, policy_version 26362 (0.0009) -[2023-10-09 01:05:23,130][88327] Updated weights for policy 1, policy_version 26350 (0.0008) -[2023-10-09 01:05:23,502][88327] Updated weights for policy 1, policy_version 26360 (0.0008) -[2023-10-09 01:05:23,974][87372] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 54001664. Throughput: 0: 1696.4, 1: 1696.1. Samples: 13497974. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:05:23,975][87372] Avg episode reward: [(0, '5.610'), (1, '5.110')] -[2023-10-09 01:05:26,916][88326] Updated weights for policy 0, policy_version 26372 (0.0009) -[2023-10-09 01:05:27,292][88326] Updated weights for policy 0, policy_version 26382 (0.0009) -[2023-10-09 01:05:27,547][88327] Updated weights for policy 1, policy_version 26370 (0.0010) -[2023-10-09 01:05:27,659][88326] Updated weights for policy 0, policy_version 26392 (0.0007) -[2023-10-09 01:05:27,922][88327] Updated weights for policy 1, policy_version 26380 (0.0007) -[2023-10-09 01:05:28,294][88327] Updated weights for policy 1, policy_version 26390 (0.0008) -[2023-10-09 01:05:28,652][88327] Updated weights for policy 1, policy_version 26400 (0.0007) -[2023-10-09 01:05:28,974][87372] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 54067200. Throughput: 0: 1685.0, 1: 1697.1. Samples: 13518388. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:05:28,975][87372] Avg episode reward: [(0, '5.910'), (1, '5.700')] -[2023-10-09 01:05:31,713][88326] Updated weights for policy 0, policy_version 26402 (0.0009) -[2023-10-09 01:05:32,092][88326] Updated weights for policy 0, policy_version 26412 (0.0009) -[2023-10-09 01:05:32,458][88326] Updated weights for policy 0, policy_version 26422 (0.0008) -[2023-10-09 01:05:32,808][88327] Updated weights for policy 1, policy_version 26410 (0.0007) -[2023-10-09 01:05:32,832][88326] Updated weights for policy 0, policy_version 26432 (0.0007) -[2023-10-09 01:05:33,179][88327] Updated weights for policy 1, policy_version 26420 (0.0010) -[2023-10-09 01:05:33,550][88327] Updated weights for policy 1, policy_version 26430 (0.0008) -[2023-10-09 01:05:33,974][87372] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 54132736. Throughput: 0: 1672.7, 1: 1681.8. Samples: 13537832. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:05:33,975][87372] Avg episode reward: [(0, '5.400'), (1, '5.510')] -[2023-10-09 01:05:36,818][88326] Updated weights for policy 0, policy_version 26442 (0.0007) -[2023-10-09 01:05:37,190][88326] Updated weights for policy 0, policy_version 26452 (0.0008) -[2023-10-09 01:05:37,563][88326] Updated weights for policy 0, policy_version 26462 (0.0007) -[2023-10-09 01:05:37,567][88327] Updated weights for policy 1, policy_version 26440 (0.0009) -[2023-10-09 01:05:37,936][88327] Updated weights for policy 1, policy_version 26450 (0.0011) -[2023-10-09 01:05:38,301][88327] Updated weights for policy 1, policy_version 26460 (0.0009) -[2023-10-09 01:05:38,974][87372] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 54198272. Throughput: 0: 1697.1, 1: 1698.1. Samples: 13549022. Policy #0 lag: (min: 31.0, avg: 32.9, max: 60.0) -[2023-10-09 01:05:38,975][87372] Avg episode reward: [(0, '4.750'), (1, '5.940')] -[2023-10-09 01:05:41,623][88326] Updated weights for policy 0, policy_version 26472 (0.0009) -[2023-10-09 01:05:41,980][88326] Updated weights for policy 0, policy_version 26482 (0.0008) -[2023-10-09 01:05:42,181][88327] Updated weights for policy 1, policy_version 26470 (0.0008) -[2023-10-09 01:05:42,352][88326] Updated weights for policy 0, policy_version 26492 (0.0007) -[2023-10-09 01:05:42,544][88327] Updated weights for policy 1, policy_version 26480 (0.0009) -[2023-10-09 01:05:42,916][88327] Updated weights for policy 1, policy_version 26490 (0.0009) -[2023-10-09 01:05:43,974][87372] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 54263808. Throughput: 0: 1678.4, 1: 1691.2. Samples: 13568684. Policy #0 lag: (min: 31.0, avg: 32.9, max: 60.0) -[2023-10-09 01:05:43,975][87372] Avg episode reward: [(0, '5.150'), (1, '5.920')] -[2023-10-09 01:05:46,239][88326] Updated weights for policy 0, policy_version 26502 (0.0008) -[2023-10-09 01:05:46,613][88326] Updated weights for policy 0, policy_version 26512 (0.0010) -[2023-10-09 01:05:46,976][88326] Updated weights for policy 0, policy_version 26522 (0.0009) -[2023-10-09 01:05:47,162][88327] Updated weights for policy 1, policy_version 26500 (0.0009) -[2023-10-09 01:05:47,529][88327] Updated weights for policy 1, policy_version 26510 (0.0007) -[2023-10-09 01:05:47,898][88327] Updated weights for policy 1, policy_version 26520 (0.0008) -[2023-10-09 01:05:48,974][87372] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 54329344. Throughput: 0: 1689.8, 1: 1666.8. Samples: 13588306. Policy #0 lag: (min: 31.0, avg: 32.9, max: 60.0) -[2023-10-09 01:05:48,975][87372] Avg episode reward: [(0, '5.170'), (1, '5.800')] -[2023-10-09 01:05:51,172][88326] Updated weights for policy 0, policy_version 26532 (0.0008) -[2023-10-09 01:05:51,538][88326] Updated weights for policy 0, policy_version 26542 (0.0008) -[2023-10-09 01:05:51,766][88327] Updated weights for policy 1, policy_version 26530 (0.0009) -[2023-10-09 01:05:51,908][88326] Updated weights for policy 0, policy_version 26552 (0.0008) -[2023-10-09 01:05:52,134][88327] Updated weights for policy 1, policy_version 26540 (0.0009) -[2023-10-09 01:05:52,503][88327] Updated weights for policy 1, policy_version 26550 (0.0007) -[2023-10-09 01:05:52,871][88327] Updated weights for policy 1, policy_version 26560 (0.0010) -[2023-10-09 01:05:53,974][87372] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 54394880. Throughput: 0: 1696.0, 1: 1692.3. Samples: 13599554. Policy #0 lag: (min: 31.0, avg: 32.9, max: 60.0) -[2023-10-09 01:05:53,975][87372] Avg episode reward: [(0, '4.990'), (1, '5.730')] -[2023-10-09 01:05:55,985][88326] Updated weights for policy 0, policy_version 26562 (0.0009) -[2023-10-09 01:05:56,351][88326] Updated weights for policy 0, policy_version 26572 (0.0007) -[2023-10-09 01:05:56,714][88326] Updated weights for policy 0, policy_version 26582 (0.0008) -[2023-10-09 01:05:56,946][88327] Updated weights for policy 1, policy_version 26570 (0.0007) -[2023-10-09 01:05:57,087][88326] Updated weights for policy 0, policy_version 26592 (0.0009) -[2023-10-09 01:05:57,305][88327] Updated weights for policy 1, policy_version 26580 (0.0007) -[2023-10-09 01:05:57,686][88327] Updated weights for policy 1, policy_version 26590 (0.0008) -[2023-10-09 01:05:58,974][87372] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 54460416. Throughput: 0: 1666.2, 1: 1678.6. Samples: 13618750. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-09 01:05:58,975][87372] Avg episode reward: [(0, '5.610'), (1, '5.490')] -[2023-10-09 01:06:01,096][88326] Updated weights for policy 0, policy_version 26602 (0.0007) -[2023-10-09 01:06:01,461][88326] Updated weights for policy 0, policy_version 26612 (0.0007) -[2023-10-09 01:06:01,671][88327] Updated weights for policy 1, policy_version 26600 (0.0008) -[2023-10-09 01:06:01,833][88326] Updated weights for policy 0, policy_version 26622 (0.0008) -[2023-10-09 01:06:02,032][88327] Updated weights for policy 1, policy_version 26610 (0.0007) -[2023-10-09 01:06:02,397][88327] Updated weights for policy 1, policy_version 26620 (0.0007) -[2023-10-09 01:06:03,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 54525952. Throughput: 0: 1689.6, 1: 1670.3. Samples: 13638964. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-09 01:06:03,975][87372] Avg episode reward: [(0, '5.520'), (1, '5.110')] -[2023-10-09 01:06:05,863][88326] Updated weights for policy 0, policy_version 26632 (0.0009) -[2023-10-09 01:06:06,233][88326] Updated weights for policy 0, policy_version 26642 (0.0008) -[2023-10-09 01:06:06,605][88326] Updated weights for policy 0, policy_version 26652 (0.0007) -[2023-10-09 01:06:06,616][88327] Updated weights for policy 1, policy_version 26630 (0.0008) -[2023-10-09 01:06:07,002][88327] Updated weights for policy 1, policy_version 26640 (0.0007) -[2023-10-09 01:06:07,375][88327] Updated weights for policy 1, policy_version 26650 (0.0007) -[2023-10-09 01:06:08,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 54591488. Throughput: 0: 1679.9, 1: 1697.3. Samples: 13649948. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-09 01:06:08,974][87372] Avg episode reward: [(0, '5.860'), (1, '5.270')] -[2023-10-09 01:06:10,810][88326] Updated weights for policy 0, policy_version 26662 (0.0008) -[2023-10-09 01:06:11,171][88326] Updated weights for policy 0, policy_version 26672 (0.0010) -[2023-10-09 01:06:11,313][88327] Updated weights for policy 1, policy_version 26660 (0.0008) -[2023-10-09 01:06:11,542][88326] Updated weights for policy 0, policy_version 26682 (0.0008) -[2023-10-09 01:06:11,682][88327] Updated weights for policy 1, policy_version 26670 (0.0008) -[2023-10-09 01:06:12,052][88327] Updated weights for policy 1, policy_version 26680 (0.0007) -[2023-10-09 01:06:13,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 54657024. Throughput: 0: 1670.6, 1: 1673.0. Samples: 13668848. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-09 01:06:13,975][87372] Avg episode reward: [(0, '5.770'), (1, '5.150')] -[2023-10-09 01:06:15,735][88326] Updated weights for policy 0, policy_version 26692 (0.0010) -[2023-10-09 01:06:15,986][88327] Updated weights for policy 1, policy_version 26690 (0.0007) -[2023-10-09 01:06:16,117][88326] Updated weights for policy 0, policy_version 26702 (0.0010) -[2023-10-09 01:06:16,352][88327] Updated weights for policy 1, policy_version 26700 (0.0009) -[2023-10-09 01:06:16,479][88326] Updated weights for policy 0, policy_version 26712 (0.0007) -[2023-10-09 01:06:16,721][88327] Updated weights for policy 1, policy_version 26710 (0.0007) -[2023-10-09 01:06:17,083][88327] Updated weights for policy 1, policy_version 26720 (0.0007) -[2023-10-09 01:06:18,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 54722560. Throughput: 0: 1683.9, 1: 1684.6. Samples: 13689414. Policy #0 lag: (min: 25.0, avg: 50.5, max: 56.0) -[2023-10-09 01:06:18,975][87372] Avg episode reward: [(0, '5.330'), (1, '5.400')] -[2023-10-09 01:06:20,733][88326] Updated weights for policy 0, policy_version 26722 (0.0009) -[2023-10-09 01:06:21,105][88326] Updated weights for policy 0, policy_version 26732 (0.0008) -[2023-10-09 01:06:21,113][88327] Updated weights for policy 1, policy_version 26730 (0.0008) -[2023-10-09 01:06:21,477][88326] Updated weights for policy 0, policy_version 26742 (0.0007) -[2023-10-09 01:06:21,480][88327] Updated weights for policy 1, policy_version 26740 (0.0009) -[2023-10-09 01:06:21,841][88326] Updated weights for policy 0, policy_version 26752 (0.0008) -[2023-10-09 01:06:21,846][88327] Updated weights for policy 1, policy_version 26750 (0.0009) -[2023-10-09 01:06:23,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 54788096. Throughput: 0: 1668.5, 1: 1688.2. Samples: 13700074. Policy #0 lag: (min: 25.0, avg: 50.5, max: 56.0) -[2023-10-09 01:06:23,975][87372] Avg episode reward: [(0, '5.560'), (1, '5.500')] -[2023-10-09 01:06:25,785][88326] Updated weights for policy 0, policy_version 26762 (0.0008) -[2023-10-09 01:06:26,013][88327] Updated weights for policy 1, policy_version 26760 (0.0008) -[2023-10-09 01:06:26,155][88326] Updated weights for policy 0, policy_version 26772 (0.0007) -[2023-10-09 01:06:26,387][88327] Updated weights for policy 1, policy_version 26770 (0.0008) -[2023-10-09 01:06:26,529][88326] Updated weights for policy 0, policy_version 26782 (0.0008) -[2023-10-09 01:06:26,753][88327] Updated weights for policy 1, policy_version 26780 (0.0009) -[2023-10-09 01:06:28,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 54853632. Throughput: 0: 1680.5, 1: 1672.3. Samples: 13719560. Policy #0 lag: (min: 25.0, avg: 50.5, max: 56.0) -[2023-10-09 01:06:28,975][87372] Avg episode reward: [(0, '5.090'), (1, '6.200')] -[2023-10-09 01:06:28,976][88168] Saving new best policy, reward=6.200! -[2023-10-09 01:06:30,358][88326] Updated weights for policy 0, policy_version 26792 (0.0007) -[2023-10-09 01:06:30,735][88326] Updated weights for policy 0, policy_version 26802 (0.0007) -[2023-10-09 01:06:30,847][88327] Updated weights for policy 1, policy_version 26790 (0.0009) -[2023-10-09 01:06:31,103][88326] Updated weights for policy 0, policy_version 26812 (0.0007) -[2023-10-09 01:06:31,208][88327] Updated weights for policy 1, policy_version 26800 (0.0009) -[2023-10-09 01:06:31,566][88327] Updated weights for policy 1, policy_version 26810 (0.0009) -[2023-10-09 01:06:33,974][87372] Fps is (10 sec: 13106.8, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 54919168. Throughput: 0: 1689.5, 1: 1695.2. Samples: 13740620. Policy #0 lag: (min: 25.0, avg: 50.5, max: 56.0) -[2023-10-09 01:06:33,975][87372] Avg episode reward: [(0, '5.380'), (1, '5.770')] -[2023-10-09 01:06:33,986][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000026816_27459584.pth... -[2023-10-09 01:06:33,986][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000026816_27459584.pth... -[2023-10-09 01:06:34,021][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000025248_25853952.pth -[2023-10-09 01:06:34,022][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000025248_25853952.pth -[2023-10-09 01:06:34,891][88326] Updated weights for policy 0, policy_version 26822 (0.0008) -[2023-10-09 01:06:35,268][88326] Updated weights for policy 0, policy_version 26832 (0.0008) -[2023-10-09 01:06:35,638][88326] Updated weights for policy 0, policy_version 26842 (0.0011) -[2023-10-09 01:06:35,688][88327] Updated weights for policy 1, policy_version 26820 (0.0008) -[2023-10-09 01:06:36,055][88327] Updated weights for policy 1, policy_version 26830 (0.0009) -[2023-10-09 01:06:36,427][88327] Updated weights for policy 1, policy_version 26840 (0.0008) -[2023-10-09 01:06:38,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 54984704. Throughput: 0: 1668.7, 1: 1685.6. Samples: 13750500. Policy #0 lag: (min: 31.0, avg: 31.6, max: 47.0) -[2023-10-09 01:06:38,975][87372] Avg episode reward: [(0, '5.620'), (1, '5.970')] -[2023-10-09 01:06:39,671][88326] Updated weights for policy 0, policy_version 26852 (0.0009) -[2023-10-09 01:06:40,040][88326] Updated weights for policy 0, policy_version 26862 (0.0010) -[2023-10-09 01:06:40,333][88327] Updated weights for policy 1, policy_version 26850 (0.0007) -[2023-10-09 01:06:40,409][88326] Updated weights for policy 0, policy_version 26872 (0.0010) -[2023-10-09 01:06:40,693][88327] Updated weights for policy 1, policy_version 26860 (0.0009) -[2023-10-09 01:06:41,063][88327] Updated weights for policy 1, policy_version 26870 (0.0010) -[2023-10-09 01:06:41,425][88327] Updated weights for policy 1, policy_version 26880 (0.0007) -[2023-10-09 01:06:43,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 55050240. Throughput: 0: 1702.4, 1: 1681.1. Samples: 13771008. Policy #0 lag: (min: 31.0, avg: 31.6, max: 47.0) -[2023-10-09 01:06:43,975][87372] Avg episode reward: [(0, '5.070'), (1, '5.470')] -[2023-10-09 01:06:44,554][88326] Updated weights for policy 0, policy_version 26882 (0.0007) -[2023-10-09 01:06:44,930][88326] Updated weights for policy 0, policy_version 26892 (0.0009) -[2023-10-09 01:06:45,298][88326] Updated weights for policy 0, policy_version 26902 (0.0009) -[2023-10-09 01:06:45,353][88327] Updated weights for policy 1, policy_version 26890 (0.0008) -[2023-10-09 01:06:45,673][88326] Updated weights for policy 0, policy_version 26912 (0.0008) -[2023-10-09 01:06:45,712][88327] Updated weights for policy 1, policy_version 26900 (0.0010) -[2023-10-09 01:06:46,083][88327] Updated weights for policy 1, policy_version 26910 (0.0008) -[2023-10-09 01:06:48,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 55115776. Throughput: 0: 1698.9, 1: 1699.1. Samples: 13791872. Policy #0 lag: (min: 31.0, avg: 31.6, max: 47.0) -[2023-10-09 01:06:48,975][87372] Avg episode reward: [(0, '5.230'), (1, '4.940')] -[2023-10-09 01:06:49,672][88326] Updated weights for policy 0, policy_version 26922 (0.0009) -[2023-10-09 01:06:50,042][88326] Updated weights for policy 0, policy_version 26932 (0.0009) -[2023-10-09 01:06:50,227][88327] Updated weights for policy 1, policy_version 26920 (0.0009) -[2023-10-09 01:06:50,411][88326] Updated weights for policy 0, policy_version 26942 (0.0010) -[2023-10-09 01:06:50,591][88327] Updated weights for policy 1, policy_version 26930 (0.0010) -[2023-10-09 01:06:50,955][88327] Updated weights for policy 1, policy_version 26940 (0.0007) -[2023-10-09 01:06:53,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 55181312. Throughput: 0: 1685.8, 1: 1672.2. Samples: 13801058. Policy #0 lag: (min: 31.0, avg: 31.6, max: 47.0) -[2023-10-09 01:06:53,975][87372] Avg episode reward: [(0, '5.580'), (1, '5.400')] -[2023-10-09 01:06:54,331][88326] Updated weights for policy 0, policy_version 26952 (0.0007) -[2023-10-09 01:06:54,704][88326] Updated weights for policy 0, policy_version 26962 (0.0007) -[2023-10-09 01:06:55,022][88327] Updated weights for policy 1, policy_version 26950 (0.0007) -[2023-10-09 01:06:55,074][88326] Updated weights for policy 0, policy_version 26972 (0.0007) -[2023-10-09 01:06:55,404][88327] Updated weights for policy 1, policy_version 26960 (0.0008) -[2023-10-09 01:06:55,770][88327] Updated weights for policy 1, policy_version 26970 (0.0008) -[2023-10-09 01:06:58,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 55246848. Throughput: 0: 1711.3, 1: 1696.5. Samples: 13822202. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:06:58,975][87372] Avg episode reward: [(0, '5.300'), (1, '5.610')] -[2023-10-09 01:06:58,981][88326] Updated weights for policy 0, policy_version 26982 (0.0009) -[2023-10-09 01:06:59,352][88326] Updated weights for policy 0, policy_version 26992 (0.0009) -[2023-10-09 01:06:59,727][88326] Updated weights for policy 0, policy_version 27002 (0.0008) -[2023-10-09 01:06:59,858][88327] Updated weights for policy 1, policy_version 26980 (0.0008) -[2023-10-09 01:07:00,220][88327] Updated weights for policy 1, policy_version 26990 (0.0008) -[2023-10-09 01:07:00,581][88327] Updated weights for policy 1, policy_version 27000 (0.0007) -[2023-10-09 01:07:03,818][88326] Updated weights for policy 0, policy_version 27012 (0.0008) -[2023-10-09 01:07:03,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 55312384. Throughput: 0: 1710.2, 1: 1702.0. Samples: 13842964. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:07:03,975][87372] Avg episode reward: [(0, '5.860'), (1, '5.620')] -[2023-10-09 01:07:04,203][88326] Updated weights for policy 0, policy_version 27022 (0.0007) -[2023-10-09 01:07:04,571][88326] Updated weights for policy 0, policy_version 27032 (0.0009) -[2023-10-09 01:07:04,644][88327] Updated weights for policy 1, policy_version 27010 (0.0010) -[2023-10-09 01:07:05,015][88327] Updated weights for policy 1, policy_version 27020 (0.0008) -[2023-10-09 01:07:05,381][88327] Updated weights for policy 1, policy_version 27030 (0.0009) -[2023-10-09 01:07:05,744][88327] Updated weights for policy 1, policy_version 27040 (0.0007) -[2023-10-09 01:07:08,729][88326] Updated weights for policy 0, policy_version 27042 (0.0010) -[2023-10-09 01:07:08,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 55377920. Throughput: 0: 1692.4, 1: 1684.0. Samples: 13852010. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:07:08,974][87372] Avg episode reward: [(0, '6.110'), (1, '6.010')] -[2023-10-09 01:07:09,095][88326] Updated weights for policy 0, policy_version 27052 (0.0010) -[2023-10-09 01:07:09,469][88326] Updated weights for policy 0, policy_version 27062 (0.0009) -[2023-10-09 01:07:09,747][88327] Updated weights for policy 1, policy_version 27050 (0.0009) -[2023-10-09 01:07:09,828][88326] Updated weights for policy 0, policy_version 27072 (0.0009) -[2023-10-09 01:07:10,113][88327] Updated weights for policy 1, policy_version 27060 (0.0008) -[2023-10-09 01:07:10,475][88327] Updated weights for policy 1, policy_version 27070 (0.0008) -[2023-10-09 01:07:13,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 55443456. Throughput: 0: 1708.2, 1: 1702.7. Samples: 13873050. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:07:13,975][87372] Avg episode reward: [(0, '5.760'), (1, '5.750')] -[2023-10-09 01:07:14,018][88326] Updated weights for policy 0, policy_version 27082 (0.0010) -[2023-10-09 01:07:14,394][88326] Updated weights for policy 0, policy_version 27092 (0.0009) -[2023-10-09 01:07:14,484][88327] Updated weights for policy 1, policy_version 27080 (0.0009) -[2023-10-09 01:07:14,769][88326] Updated weights for policy 0, policy_version 27102 (0.0007) -[2023-10-09 01:07:14,854][88327] Updated weights for policy 1, policy_version 27090 (0.0008) -[2023-10-09 01:07:15,224][88327] Updated weights for policy 1, policy_version 27100 (0.0008) -[2023-10-09 01:07:18,775][88326] Updated weights for policy 0, policy_version 27112 (0.0008) -[2023-10-09 01:07:18,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 55508992. Throughput: 0: 1697.4, 1: 1702.3. Samples: 13893606. Policy #0 lag: (min: 15.0, avg: 38.0, max: 40.0) -[2023-10-09 01:07:18,975][87372] Avg episode reward: [(0, '6.130'), (1, '5.590')] -[2023-10-09 01:07:19,147][88326] Updated weights for policy 0, policy_version 27122 (0.0007) -[2023-10-09 01:07:19,198][88327] Updated weights for policy 1, policy_version 27110 (0.0008) -[2023-10-09 01:07:19,506][88326] Updated weights for policy 0, policy_version 27132 (0.0009) -[2023-10-09 01:07:19,556][88327] Updated weights for policy 1, policy_version 27120 (0.0008) -[2023-10-09 01:07:19,925][88327] Updated weights for policy 1, policy_version 27130 (0.0010) -[2023-10-09 01:07:23,657][88326] Updated weights for policy 0, policy_version 27142 (0.0008) -[2023-10-09 01:07:23,962][88327] Updated weights for policy 1, policy_version 27140 (0.0009) -[2023-10-09 01:07:23,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 55574528. Throughput: 0: 1695.8, 1: 1687.0. Samples: 13902726. Policy #0 lag: (min: 15.0, avg: 38.0, max: 40.0) -[2023-10-09 01:07:23,975][87372] Avg episode reward: [(0, '6.430'), (1, '5.700')] -[2023-10-09 01:07:24,022][88326] Updated weights for policy 0, policy_version 27152 (0.0007) -[2023-10-09 01:07:24,323][88327] Updated weights for policy 1, policy_version 27150 (0.0008) -[2023-10-09 01:07:24,391][88326] Updated weights for policy 0, policy_version 27162 (0.0007) -[2023-10-09 01:07:24,695][88327] Updated weights for policy 1, policy_version 27160 (0.0007) -[2023-10-09 01:07:28,370][88326] Updated weights for policy 0, policy_version 27172 (0.0010) -[2023-10-09 01:07:28,685][88327] Updated weights for policy 1, policy_version 27170 (0.0008) -[2023-10-09 01:07:28,741][88326] Updated weights for policy 0, policy_version 27182 (0.0008) -[2023-10-09 01:07:28,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 55640064. Throughput: 0: 1690.9, 1: 1703.5. Samples: 13923756. Policy #0 lag: (min: 15.0, avg: 38.0, max: 40.0) -[2023-10-09 01:07:28,975][87372] Avg episode reward: [(0, '5.980'), (1, '6.160')] -[2023-10-09 01:07:29,057][88327] Updated weights for policy 1, policy_version 27180 (0.0011) -[2023-10-09 01:07:29,117][88326] Updated weights for policy 0, policy_version 27192 (0.0009) -[2023-10-09 01:07:29,416][88327] Updated weights for policy 1, policy_version 27190 (0.0008) -[2023-10-09 01:07:29,777][88327] Updated weights for policy 1, policy_version 27200 (0.0011) -[2023-10-09 01:07:33,258][88326] Updated weights for policy 0, policy_version 27202 (0.0007) -[2023-10-09 01:07:33,622][88326] Updated weights for policy 0, policy_version 27212 (0.0009) -[2023-10-09 01:07:33,873][88327] Updated weights for policy 1, policy_version 27210 (0.0007) -[2023-10-09 01:07:33,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13329.3). Total num frames: 55705600. Throughput: 0: 1689.5, 1: 1700.9. Samples: 13944442. Policy #0 lag: (min: 15.0, avg: 38.0, max: 40.0) -[2023-10-09 01:07:33,975][87372] Avg episode reward: [(0, '5.930'), (1, '5.840')] -[2023-10-09 01:07:33,986][88326] Updated weights for policy 0, policy_version 27222 (0.0007) -[2023-10-09 01:07:34,238][88327] Updated weights for policy 1, policy_version 27220 (0.0009) -[2023-10-09 01:07:34,347][88326] Updated weights for policy 0, policy_version 27232 (0.0007) -[2023-10-09 01:07:34,602][88327] Updated weights for policy 1, policy_version 27230 (0.0007) -[2023-10-09 01:07:38,291][88326] Updated weights for policy 0, policy_version 27242 (0.0008) -[2023-10-09 01:07:38,579][88327] Updated weights for policy 1, policy_version 27240 (0.0008) -[2023-10-09 01:07:38,666][88326] Updated weights for policy 0, policy_version 27252 (0.0008) -[2023-10-09 01:07:38,939][88327] Updated weights for policy 1, policy_version 27250 (0.0008) -[2023-10-09 01:07:38,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.3, 300 sec: 13329.4). Total num frames: 55771136. Throughput: 0: 1690.2, 1: 1700.3. Samples: 13953632. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:07:38,975][87372] Avg episode reward: [(0, '5.860'), (1, '5.900')] -[2023-10-09 01:07:39,037][88326] Updated weights for policy 0, policy_version 27262 (0.0008) -[2023-10-09 01:07:39,305][88327] Updated weights for policy 1, policy_version 27260 (0.0008) -[2023-10-09 01:07:43,199][88326] Updated weights for policy 0, policy_version 27272 (0.0008) -[2023-10-09 01:07:43,390][88327] Updated weights for policy 1, policy_version 27270 (0.0009) -[2023-10-09 01:07:43,563][88326] Updated weights for policy 0, policy_version 27282 (0.0008) -[2023-10-09 01:07:43,770][88327] Updated weights for policy 1, policy_version 27280 (0.0009) -[2023-10-09 01:07:43,933][88326] Updated weights for policy 0, policy_version 27292 (0.0010) -[2023-10-09 01:07:43,974][87372] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 55836672. Throughput: 0: 1680.6, 1: 1701.2. Samples: 13974382. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:07:43,974][87372] Avg episode reward: [(0, '5.890'), (1, '5.680')] -[2023-10-09 01:07:44,130][88327] Updated weights for policy 1, policy_version 27290 (0.0009) -[2023-10-09 01:07:48,081][88326] Updated weights for policy 0, policy_version 27302 (0.0008) -[2023-10-09 01:07:48,171][88327] Updated weights for policy 1, policy_version 27300 (0.0009) -[2023-10-09 01:07:48,455][88326] Updated weights for policy 0, policy_version 27312 (0.0007) -[2023-10-09 01:07:48,543][88327] Updated weights for policy 1, policy_version 27310 (0.0008) -[2023-10-09 01:07:48,831][88326] Updated weights for policy 0, policy_version 27322 (0.0008) -[2023-10-09 01:07:48,907][88327] Updated weights for policy 1, policy_version 27320 (0.0007) -[2023-10-09 01:07:48,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 55902208. Throughput: 0: 1675.2, 1: 1695.3. Samples: 13994638. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:07:48,975][87372] Avg episode reward: [(0, '5.610'), (1, '5.390')] -[2023-10-09 01:07:52,749][88326] Updated weights for policy 0, policy_version 27332 (0.0008) -[2023-10-09 01:07:52,888][88327] Updated weights for policy 1, policy_version 27330 (0.0008) -[2023-10-09 01:07:53,142][88326] Updated weights for policy 0, policy_version 27342 (0.0007) -[2023-10-09 01:07:53,251][88327] Updated weights for policy 1, policy_version 27340 (0.0007) -[2023-10-09 01:07:53,502][88326] Updated weights for policy 0, policy_version 27352 (0.0007) -[2023-10-09 01:07:53,627][88327] Updated weights for policy 1, policy_version 27350 (0.0008) -[2023-10-09 01:07:53,974][87372] Fps is (10 sec: 16383.9, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 56000512. Throughput: 0: 1689.1, 1: 1696.6. Samples: 14004364. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:07:53,975][87372] Avg episode reward: [(0, '5.770'), (1, '5.640')] -[2023-10-09 01:07:53,989][88327] Updated weights for policy 1, policy_version 27360 (0.0008) -[2023-10-09 01:07:57,634][88326] Updated weights for policy 0, policy_version 27362 (0.0008) -[2023-10-09 01:07:58,007][88326] Updated weights for policy 0, policy_version 27372 (0.0007) -[2023-10-09 01:07:58,034][88327] Updated weights for policy 1, policy_version 27370 (0.0010) -[2023-10-09 01:07:58,370][88326] Updated weights for policy 0, policy_version 27382 (0.0008) -[2023-10-09 01:07:58,391][88327] Updated weights for policy 1, policy_version 27380 (0.0009) -[2023-10-09 01:07:58,736][88326] Updated weights for policy 0, policy_version 27392 (0.0008) -[2023-10-09 01:07:58,749][88327] Updated weights for policy 1, policy_version 27390 (0.0008) -[2023-10-09 01:07:58,974][87372] Fps is (10 sec: 19660.8, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 56098816. Throughput: 0: 1682.5, 1: 1696.9. Samples: 14025120. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:07:58,975][87372] Avg episode reward: [(0, '5.540'), (1, '5.770')] -[2023-10-09 01:08:02,793][88326] Updated weights for policy 0, policy_version 27402 (0.0010) -[2023-10-09 01:08:02,939][88327] Updated weights for policy 1, policy_version 27400 (0.0008) -[2023-10-09 01:08:03,158][88326] Updated weights for policy 0, policy_version 27412 (0.0008) -[2023-10-09 01:08:03,304][88327] Updated weights for policy 1, policy_version 27410 (0.0008) -[2023-10-09 01:08:03,538][88326] Updated weights for policy 0, policy_version 27422 (0.0008) -[2023-10-09 01:08:03,664][88327] Updated weights for policy 1, policy_version 27420 (0.0009) -[2023-10-09 01:08:03,974][87372] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 56164352. Throughput: 0: 1664.1, 1: 1686.2. Samples: 14044370. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:08:03,975][87372] Avg episode reward: [(0, '5.440'), (1, '5.910')] -[2023-10-09 01:08:07,512][88326] Updated weights for policy 0, policy_version 27432 (0.0009) -[2023-10-09 01:08:07,649][88327] Updated weights for policy 1, policy_version 27430 (0.0008) -[2023-10-09 01:08:07,879][88326] Updated weights for policy 0, policy_version 27442 (0.0009) -[2023-10-09 01:08:08,012][88327] Updated weights for policy 1, policy_version 27440 (0.0009) -[2023-10-09 01:08:08,236][88326] Updated weights for policy 0, policy_version 27452 (0.0010) -[2023-10-09 01:08:08,386][88327] Updated weights for policy 1, policy_version 27450 (0.0008) -[2023-10-09 01:08:08,974][87372] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 56229888. Throughput: 0: 1686.6, 1: 1696.7. Samples: 14054976. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:08:08,975][87372] Avg episode reward: [(0, '5.810'), (1, '5.620')] -[2023-10-09 01:08:12,376][88326] Updated weights for policy 0, policy_version 27462 (0.0009) -[2023-10-09 01:08:12,492][88327] Updated weights for policy 1, policy_version 27460 (0.0007) -[2023-10-09 01:08:12,743][88326] Updated weights for policy 0, policy_version 27472 (0.0009) -[2023-10-09 01:08:12,861][88327] Updated weights for policy 1, policy_version 27470 (0.0009) -[2023-10-09 01:08:13,106][88326] Updated weights for policy 0, policy_version 27482 (0.0008) -[2023-10-09 01:08:13,229][88327] Updated weights for policy 1, policy_version 27480 (0.0009) -[2023-10-09 01:08:13,974][87372] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 56295424. Throughput: 0: 1681.2, 1: 1694.5. Samples: 14075666. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-10-09 01:08:13,975][87372] Avg episode reward: [(0, '5.800'), (1, '6.150')] -[2023-10-09 01:08:17,028][88326] Updated weights for policy 0, policy_version 27492 (0.0008) -[2023-10-09 01:08:17,124][88327] Updated weights for policy 1, policy_version 27490 (0.0008) -[2023-10-09 01:08:17,395][88326] Updated weights for policy 0, policy_version 27502 (0.0007) -[2023-10-09 01:08:17,483][88327] Updated weights for policy 1, policy_version 27500 (0.0007) -[2023-10-09 01:08:17,765][88326] Updated weights for policy 0, policy_version 27512 (0.0007) -[2023-10-09 01:08:17,850][88327] Updated weights for policy 1, policy_version 27510 (0.0007) -[2023-10-09 01:08:18,217][88327] Updated weights for policy 1, policy_version 27520 (0.0009) -[2023-10-09 01:08:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 56360960. Throughput: 0: 1660.1, 1: 1674.6. Samples: 14094504. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-10-09 01:08:18,975][87372] Avg episode reward: [(0, '5.480'), (1, '5.490')] -[2023-10-09 01:08:21,824][88326] Updated weights for policy 0, policy_version 27522 (0.0009) -[2023-10-09 01:08:22,193][88326] Updated weights for policy 0, policy_version 27532 (0.0008) -[2023-10-09 01:08:22,250][88327] Updated weights for policy 1, policy_version 27530 (0.0008) -[2023-10-09 01:08:22,558][88326] Updated weights for policy 0, policy_version 27542 (0.0007) -[2023-10-09 01:08:22,618][88327] Updated weights for policy 1, policy_version 27540 (0.0007) -[2023-10-09 01:08:22,922][88326] Updated weights for policy 0, policy_version 27552 (0.0007) -[2023-10-09 01:08:22,991][88327] Updated weights for policy 1, policy_version 27550 (0.0007) -[2023-10-09 01:08:23,974][87372] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 56426496. Throughput: 0: 1689.3, 1: 1699.5. Samples: 14106128. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-10-09 01:08:23,975][87372] Avg episode reward: [(0, '5.590'), (1, '5.640')] -[2023-10-09 01:08:26,937][88326] Updated weights for policy 0, policy_version 27562 (0.0008) -[2023-10-09 01:08:27,111][88327] Updated weights for policy 1, policy_version 27560 (0.0007) -[2023-10-09 01:08:27,302][88326] Updated weights for policy 0, policy_version 27572 (0.0008) -[2023-10-09 01:08:27,477][88327] Updated weights for policy 1, policy_version 27570 (0.0011) -[2023-10-09 01:08:27,665][88326] Updated weights for policy 0, policy_version 27582 (0.0008) -[2023-10-09 01:08:27,850][88327] Updated weights for policy 1, policy_version 27580 (0.0010) -[2023-10-09 01:08:28,974][87372] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 56492032. Throughput: 0: 1677.1, 1: 1694.2. Samples: 14126092. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-10-09 01:08:28,975][87372] Avg episode reward: [(0, '5.510'), (1, '6.130')] -[2023-10-09 01:08:31,584][88326] Updated weights for policy 0, policy_version 27592 (0.0007) -[2023-10-09 01:08:31,958][88326] Updated weights for policy 0, policy_version 27602 (0.0009) -[2023-10-09 01:08:31,995][88327] Updated weights for policy 1, policy_version 27590 (0.0010) -[2023-10-09 01:08:32,319][88326] Updated weights for policy 0, policy_version 27612 (0.0008) -[2023-10-09 01:08:32,374][88327] Updated weights for policy 1, policy_version 27600 (0.0008) -[2023-10-09 01:08:32,739][88327] Updated weights for policy 1, policy_version 27610 (0.0008) -[2023-10-09 01:08:33,974][87372] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 56557568. Throughput: 0: 1673.6, 1: 1673.6. Samples: 14145262. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-10-09 01:08:33,975][87372] Avg episode reward: [(0, '6.030'), (1, '5.750')] -[2023-10-09 01:08:33,983][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000027616_28278784.pth... -[2023-10-09 01:08:33,984][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000027616_28278784.pth... -[2023-10-09 01:08:34,015][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000026048_26673152.pth -[2023-10-09 01:08:34,029][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000026016_26640384.pth -[2023-10-09 01:08:36,431][88326] Updated weights for policy 0, policy_version 27622 (0.0009) -[2023-10-09 01:08:36,727][88327] Updated weights for policy 1, policy_version 27620 (0.0007) -[2023-10-09 01:08:36,796][88326] Updated weights for policy 0, policy_version 27632 (0.0009) -[2023-10-09 01:08:37,098][88327] Updated weights for policy 1, policy_version 27630 (0.0008) -[2023-10-09 01:08:37,182][88326] Updated weights for policy 0, policy_version 27642 (0.0008) -[2023-10-09 01:08:37,460][88327] Updated weights for policy 1, policy_version 27640 (0.0007) -[2023-10-09 01:08:38,974][87372] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 56623104. Throughput: 0: 1691.4, 1: 1698.4. Samples: 14156906. Policy #0 lag: (min: 18.0, avg: 18.0, max: 18.0) -[2023-10-09 01:08:38,975][87372] Avg episode reward: [(0, '5.820'), (1, '6.150')] -[2023-10-09 01:08:41,239][88326] Updated weights for policy 0, policy_version 27652 (0.0009) -[2023-10-09 01:08:41,524][88327] Updated weights for policy 1, policy_version 27650 (0.0008) -[2023-10-09 01:08:41,611][88326] Updated weights for policy 0, policy_version 27662 (0.0008) -[2023-10-09 01:08:41,890][88327] Updated weights for policy 1, policy_version 27660 (0.0008) -[2023-10-09 01:08:41,972][88326] Updated weights for policy 0, policy_version 27672 (0.0007) -[2023-10-09 01:08:42,247][88327] Updated weights for policy 1, policy_version 27670 (0.0009) -[2023-10-09 01:08:42,614][88327] Updated weights for policy 1, policy_version 27680 (0.0008) -[2023-10-09 01:08:43,974][87372] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 56688640. Throughput: 0: 1667.4, 1: 1679.3. Samples: 14175722. Policy #0 lag: (min: 18.0, avg: 18.0, max: 18.0) -[2023-10-09 01:08:43,975][87372] Avg episode reward: [(0, '6.060'), (1, '5.960')] -[2023-10-09 01:08:46,262][88326] Updated weights for policy 0, policy_version 27682 (0.0008) -[2023-10-09 01:08:46,669][88327] Updated weights for policy 1, policy_version 27690 (0.0008) -[2023-10-09 01:08:46,672][88326] Updated weights for policy 0, policy_version 27692 (0.0009) -[2023-10-09 01:08:47,033][88326] Updated weights for policy 0, policy_version 27702 (0.0009) -[2023-10-09 01:08:47,034][88327] Updated weights for policy 1, policy_version 27700 (0.0007) -[2023-10-09 01:08:47,399][88327] Updated weights for policy 1, policy_version 27710 (0.0008) -[2023-10-09 01:08:47,402][88326] Updated weights for policy 0, policy_version 27712 (0.0007) -[2023-10-09 01:08:48,974][87372] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 56754176. Throughput: 0: 1683.2, 1: 1678.8. Samples: 14195664. Policy #0 lag: (min: 18.0, avg: 18.0, max: 18.0) -[2023-10-09 01:08:48,975][87372] Avg episode reward: [(0, '5.480'), (1, '5.830')] -[2023-10-09 01:08:51,554][88327] Updated weights for policy 1, policy_version 27720 (0.0007) -[2023-10-09 01:08:51,572][88326] Updated weights for policy 0, policy_version 27722 (0.0007) -[2023-10-09 01:08:51,923][88327] Updated weights for policy 1, policy_version 27730 (0.0008) -[2023-10-09 01:08:51,942][88326] Updated weights for policy 0, policy_version 27732 (0.0008) -[2023-10-09 01:08:52,273][88327] Updated weights for policy 1, policy_version 27740 (0.0007) -[2023-10-09 01:08:52,314][88326] Updated weights for policy 0, policy_version 27742 (0.0009) -[2023-10-09 01:08:53,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 56819712. Throughput: 0: 1687.8, 1: 1695.8. Samples: 14207236. Policy #0 lag: (min: 18.0, avg: 18.0, max: 18.0) -[2023-10-09 01:08:53,975][87372] Avg episode reward: [(0, '5.290'), (1, '5.930')] -[2023-10-09 01:08:56,304][88327] Updated weights for policy 1, policy_version 27750 (0.0007) -[2023-10-09 01:08:56,448][88326] Updated weights for policy 0, policy_version 27752 (0.0009) -[2023-10-09 01:08:56,670][88327] Updated weights for policy 1, policy_version 27760 (0.0007) -[2023-10-09 01:08:56,822][88326] Updated weights for policy 0, policy_version 27762 (0.0009) -[2023-10-09 01:08:57,028][88327] Updated weights for policy 1, policy_version 27770 (0.0007) -[2023-10-09 01:08:57,191][88326] Updated weights for policy 0, policy_version 27772 (0.0009) -[2023-10-09 01:08:58,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 56885248. Throughput: 0: 1665.1, 1: 1671.5. Samples: 14225812. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-09 01:08:58,975][87372] Avg episode reward: [(0, '5.660'), (1, '5.590')] -[2023-10-09 01:09:01,170][88327] Updated weights for policy 1, policy_version 27780 (0.0008) -[2023-10-09 01:09:01,265][88326] Updated weights for policy 0, policy_version 27782 (0.0008) -[2023-10-09 01:09:01,535][88327] Updated weights for policy 1, policy_version 27790 (0.0008) -[2023-10-09 01:09:01,630][88326] Updated weights for policy 0, policy_version 27792 (0.0008) -[2023-10-09 01:09:01,900][88327] Updated weights for policy 1, policy_version 27800 (0.0009) -[2023-10-09 01:09:01,995][88326] Updated weights for policy 0, policy_version 27802 (0.0007) -[2023-10-09 01:09:03,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 56950784. Throughput: 0: 1684.5, 1: 1685.1. Samples: 14246138. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-09 01:09:03,975][87372] Avg episode reward: [(0, '5.300'), (1, '5.400')] -[2023-10-09 01:09:05,967][88326] Updated weights for policy 0, policy_version 27812 (0.0007) -[2023-10-09 01:09:06,050][88327] Updated weights for policy 1, policy_version 27810 (0.0008) -[2023-10-09 01:09:06,336][88326] Updated weights for policy 0, policy_version 27822 (0.0009) -[2023-10-09 01:09:06,416][88327] Updated weights for policy 1, policy_version 27820 (0.0009) -[2023-10-09 01:09:06,703][88326] Updated weights for policy 0, policy_version 27832 (0.0008) -[2023-10-09 01:09:06,785][88327] Updated weights for policy 1, policy_version 27830 (0.0008) -[2023-10-09 01:09:07,154][88327] Updated weights for policy 1, policy_version 27840 (0.0008) -[2023-10-09 01:09:08,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 57016320. Throughput: 0: 1676.6, 1: 1682.3. Samples: 14257276. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-09 01:09:08,975][87372] Avg episode reward: [(0, '5.450'), (1, '6.110')] -[2023-10-09 01:09:10,753][88326] Updated weights for policy 0, policy_version 27842 (0.0009) -[2023-10-09 01:09:11,114][88326] Updated weights for policy 0, policy_version 27852 (0.0009) -[2023-10-09 01:09:11,173][88327] Updated weights for policy 1, policy_version 27850 (0.0008) -[2023-10-09 01:09:11,483][88326] Updated weights for policy 0, policy_version 27862 (0.0008) -[2023-10-09 01:09:11,536][88327] Updated weights for policy 1, policy_version 27860 (0.0007) -[2023-10-09 01:09:11,842][88326] Updated weights for policy 0, policy_version 27872 (0.0007) -[2023-10-09 01:09:11,912][88327] Updated weights for policy 1, policy_version 27870 (0.0008) -[2023-10-09 01:09:13,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 57081856. Throughput: 0: 1674.8, 1: 1660.8. Samples: 14276196. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-09 01:09:13,975][87372] Avg episode reward: [(0, '5.740'), (1, '5.540')] -[2023-10-09 01:09:15,701][88327] Updated weights for policy 1, policy_version 27880 (0.0008) -[2023-10-09 01:09:15,911][88326] Updated weights for policy 0, policy_version 27882 (0.0007) -[2023-10-09 01:09:16,062][88327] Updated weights for policy 1, policy_version 27890 (0.0008) -[2023-10-09 01:09:16,289][88326] Updated weights for policy 0, policy_version 27892 (0.0009) -[2023-10-09 01:09:16,430][88327] Updated weights for policy 1, policy_version 27900 (0.0009) -[2023-10-09 01:09:16,655][88326] Updated weights for policy 0, policy_version 27902 (0.0010) -[2023-10-09 01:09:18,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 57147392. Throughput: 0: 1686.3, 1: 1686.8. Samples: 14297052. Policy #0 lag: (min: 25.0, avg: 26.9, max: 44.0) -[2023-10-09 01:09:18,975][87372] Avg episode reward: [(0, '5.750'), (1, '5.610')] -[2023-10-09 01:09:20,609][88327] Updated weights for policy 1, policy_version 27910 (0.0009) -[2023-10-09 01:09:20,613][88326] Updated weights for policy 0, policy_version 27912 (0.0008) -[2023-10-09 01:09:20,979][88326] Updated weights for policy 0, policy_version 27922 (0.0007) -[2023-10-09 01:09:21,001][88327] Updated weights for policy 1, policy_version 27920 (0.0008) -[2023-10-09 01:09:21,343][88326] Updated weights for policy 0, policy_version 27932 (0.0009) -[2023-10-09 01:09:21,351][88327] Updated weights for policy 1, policy_version 27930 (0.0007) -[2023-10-09 01:09:23,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 57212928. Throughput: 0: 1665.6, 1: 1668.4. Samples: 14306936. Policy #0 lag: (min: 25.0, avg: 26.9, max: 44.0) -[2023-10-09 01:09:23,976][87372] Avg episode reward: [(0, '5.660'), (1, '6.100')] -[2023-10-09 01:09:25,340][88326] Updated weights for policy 0, policy_version 27942 (0.0008) -[2023-10-09 01:09:25,463][88327] Updated weights for policy 1, policy_version 27940 (0.0008) -[2023-10-09 01:09:25,710][88326] Updated weights for policy 0, policy_version 27952 (0.0009) -[2023-10-09 01:09:25,818][88327] Updated weights for policy 1, policy_version 27950 (0.0008) -[2023-10-09 01:09:26,077][88326] Updated weights for policy 0, policy_version 27962 (0.0007) -[2023-10-09 01:09:26,186][88327] Updated weights for policy 1, policy_version 27960 (0.0008) -[2023-10-09 01:09:28,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 57278464. Throughput: 0: 1689.4, 1: 1675.9. Samples: 14327160. Policy #0 lag: (min: 25.0, avg: 26.9, max: 44.0) -[2023-10-09 01:09:28,975][87372] Avg episode reward: [(0, '5.590'), (1, '6.150')] -[2023-10-09 01:09:29,904][88326] Updated weights for policy 0, policy_version 27972 (0.0008) -[2023-10-09 01:09:30,159][88327] Updated weights for policy 1, policy_version 27970 (0.0008) -[2023-10-09 01:09:30,275][88326] Updated weights for policy 0, policy_version 27982 (0.0010) -[2023-10-09 01:09:30,521][88327] Updated weights for policy 1, policy_version 27980 (0.0008) -[2023-10-09 01:09:30,640][88326] Updated weights for policy 0, policy_version 27992 (0.0009) -[2023-10-09 01:09:30,885][88327] Updated weights for policy 1, policy_version 27990 (0.0008) -[2023-10-09 01:09:31,259][88327] Updated weights for policy 1, policy_version 28000 (0.0009) -[2023-10-09 01:09:33,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 57344000. Throughput: 0: 1696.8, 1: 1694.8. Samples: 14348286. Policy #0 lag: (min: 25.0, avg: 26.9, max: 44.0) -[2023-10-09 01:09:33,975][87372] Avg episode reward: [(0, '5.350'), (1, '6.000')] -[2023-10-09 01:09:34,688][88326] Updated weights for policy 0, policy_version 28002 (0.0007) -[2023-10-09 01:09:35,097][88326] Updated weights for policy 0, policy_version 28012 (0.0008) -[2023-10-09 01:09:35,207][88327] Updated weights for policy 1, policy_version 28010 (0.0010) -[2023-10-09 01:09:35,469][88326] Updated weights for policy 0, policy_version 28022 (0.0009) -[2023-10-09 01:09:35,561][88327] Updated weights for policy 1, policy_version 28020 (0.0008) -[2023-10-09 01:09:35,831][88326] Updated weights for policy 0, policy_version 28032 (0.0010) -[2023-10-09 01:09:35,931][88327] Updated weights for policy 1, policy_version 28030 (0.0009) -[2023-10-09 01:09:38,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 57409536. Throughput: 0: 1667.7, 1: 1666.9. Samples: 14357292. Policy #0 lag: (min: 25.0, avg: 26.9, max: 44.0) -[2023-10-09 01:09:38,975][87372] Avg episode reward: [(0, '5.580'), (1, '5.980')] -[2023-10-09 01:09:39,728][88326] Updated weights for policy 0, policy_version 28042 (0.0008) -[2023-10-09 01:09:40,048][88327] Updated weights for policy 1, policy_version 28040 (0.0008) -[2023-10-09 01:09:40,106][88326] Updated weights for policy 0, policy_version 28052 (0.0008) -[2023-10-09 01:09:40,418][88327] Updated weights for policy 1, policy_version 28050 (0.0007) -[2023-10-09 01:09:40,478][88326] Updated weights for policy 0, policy_version 28062 (0.0007) -[2023-10-09 01:09:40,781][88327] Updated weights for policy 1, policy_version 28060 (0.0008) -[2023-10-09 01:09:43,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 57475072. Throughput: 0: 1701.5, 1: 1689.4. Samples: 14378406. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-09 01:09:43,975][87372] Avg episode reward: [(0, '5.310'), (1, '5.660')] -[2023-10-09 01:09:44,360][88326] Updated weights for policy 0, policy_version 28072 (0.0009) -[2023-10-09 01:09:44,729][88326] Updated weights for policy 0, policy_version 28082 (0.0010) -[2023-10-09 01:09:44,789][88327] Updated weights for policy 1, policy_version 28070 (0.0008) -[2023-10-09 01:09:45,098][88326] Updated weights for policy 0, policy_version 28092 (0.0009) -[2023-10-09 01:09:45,156][88327] Updated weights for policy 1, policy_version 28080 (0.0008) -[2023-10-09 01:09:45,521][88327] Updated weights for policy 1, policy_version 28090 (0.0009) -[2023-10-09 01:09:48,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 57540608. Throughput: 0: 1706.6, 1: 1698.8. Samples: 14399384. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-09 01:09:48,975][87372] Avg episode reward: [(0, '5.290'), (1, '5.830')] -[2023-10-09 01:09:49,095][88326] Updated weights for policy 0, policy_version 28102 (0.0008) -[2023-10-09 01:09:49,459][88326] Updated weights for policy 0, policy_version 28112 (0.0009) -[2023-10-09 01:09:49,598][88327] Updated weights for policy 1, policy_version 28100 (0.0009) -[2023-10-09 01:09:49,836][88326] Updated weights for policy 0, policy_version 28122 (0.0009) -[2023-10-09 01:09:49,967][88327] Updated weights for policy 1, policy_version 28110 (0.0007) -[2023-10-09 01:09:50,333][88327] Updated weights for policy 1, policy_version 28120 (0.0008) -[2023-10-09 01:09:53,974][88326] Updated weights for policy 0, policy_version 28132 (0.0009) -[2023-10-09 01:09:53,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 57606144. Throughput: 0: 1683.7, 1: 1675.2. Samples: 14408430. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-09 01:09:53,975][87372] Avg episode reward: [(0, '5.490'), (1, '5.460')] -[2023-10-09 01:09:54,279][88327] Updated weights for policy 1, policy_version 28130 (0.0011) -[2023-10-09 01:09:54,333][88326] Updated weights for policy 0, policy_version 28142 (0.0009) -[2023-10-09 01:09:54,641][88327] Updated weights for policy 1, policy_version 28140 (0.0007) -[2023-10-09 01:09:54,701][88326] Updated weights for policy 0, policy_version 28152 (0.0008) -[2023-10-09 01:09:55,005][88327] Updated weights for policy 1, policy_version 28150 (0.0009) -[2023-10-09 01:09:55,374][88327] Updated weights for policy 1, policy_version 28160 (0.0010) -[2023-10-09 01:09:58,959][88326] Updated weights for policy 0, policy_version 28162 (0.0007) -[2023-10-09 01:09:58,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13440.5). Total num frames: 57671680. Throughput: 0: 1698.9, 1: 1699.9. Samples: 14429140. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-09 01:09:58,975][87372] Avg episode reward: [(0, '5.180'), (1, '5.810')] -[2023-10-09 01:09:59,331][88326] Updated weights for policy 0, policy_version 28172 (0.0008) -[2023-10-09 01:09:59,483][88327] Updated weights for policy 1, policy_version 28170 (0.0007) -[2023-10-09 01:09:59,702][88326] Updated weights for policy 0, policy_version 28182 (0.0008) -[2023-10-09 01:09:59,846][88327] Updated weights for policy 1, policy_version 28180 (0.0008) -[2023-10-09 01:10:00,073][88326] Updated weights for policy 0, policy_version 28192 (0.0008) -[2023-10-09 01:10:00,205][88327] Updated weights for policy 1, policy_version 28190 (0.0008) -[2023-10-09 01:10:03,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 57737216. Throughput: 0: 1702.0, 1: 1699.0. Samples: 14450096. Policy #0 lag: (min: 2.0, avg: 8.2, max: 34.0) -[2023-10-09 01:10:03,975][87372] Avg episode reward: [(0, '5.990'), (1, '5.680')] -[2023-10-09 01:10:04,218][88327] Updated weights for policy 1, policy_version 28200 (0.0010) -[2023-10-09 01:10:04,270][88326] Updated weights for policy 0, policy_version 28202 (0.0009) -[2023-10-09 01:10:04,582][88327] Updated weights for policy 1, policy_version 28210 (0.0007) -[2023-10-09 01:10:04,639][88326] Updated weights for policy 0, policy_version 28212 (0.0008) -[2023-10-09 01:10:04,941][88327] Updated weights for policy 1, policy_version 28220 (0.0009) -[2023-10-09 01:10:05,009][88326] Updated weights for policy 0, policy_version 28222 (0.0010) -[2023-10-09 01:10:08,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 57802752. Throughput: 0: 1690.9, 1: 1688.6. Samples: 14459010. Policy #0 lag: (min: 2.0, avg: 8.2, max: 34.0) -[2023-10-09 01:10:08,975][87372] Avg episode reward: [(0, '5.390'), (1, '5.760')] -[2023-10-09 01:10:08,997][88327] Updated weights for policy 1, policy_version 28230 (0.0008) -[2023-10-09 01:10:09,050][88326] Updated weights for policy 0, policy_version 28232 (0.0009) -[2023-10-09 01:10:09,351][88327] Updated weights for policy 1, policy_version 28240 (0.0007) -[2023-10-09 01:10:09,415][88326] Updated weights for policy 0, policy_version 28242 (0.0007) -[2023-10-09 01:10:09,713][88327] Updated weights for policy 1, policy_version 28250 (0.0008) -[2023-10-09 01:10:09,784][88326] Updated weights for policy 0, policy_version 28252 (0.0008) -[2023-10-09 01:10:13,658][88327] Updated weights for policy 1, policy_version 28260 (0.0008) -[2023-10-09 01:10:13,929][88326] Updated weights for policy 0, policy_version 28262 (0.0007) -[2023-10-09 01:10:13,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 57868288. Throughput: 0: 1689.3, 1: 1701.8. Samples: 14479756. Policy #0 lag: (min: 2.0, avg: 8.2, max: 34.0) -[2023-10-09 01:10:13,974][87372] Avg episode reward: [(0, '5.300'), (1, '5.760')] -[2023-10-09 01:10:14,020][88327] Updated weights for policy 1, policy_version 28270 (0.0008) -[2023-10-09 01:10:14,301][88326] Updated weights for policy 0, policy_version 28272 (0.0007) -[2023-10-09 01:10:14,377][88327] Updated weights for policy 1, policy_version 28280 (0.0007) -[2023-10-09 01:10:14,669][88326] Updated weights for policy 0, policy_version 28282 (0.0008) -[2023-10-09 01:10:18,363][88327] Updated weights for policy 1, policy_version 28290 (0.0007) -[2023-10-09 01:10:18,531][88326] Updated weights for policy 0, policy_version 28292 (0.0008) -[2023-10-09 01:10:18,726][88327] Updated weights for policy 1, policy_version 28300 (0.0007) -[2023-10-09 01:10:18,893][88326] Updated weights for policy 0, policy_version 28302 (0.0007) -[2023-10-09 01:10:18,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.3, 300 sec: 13329.4). Total num frames: 57933824. Throughput: 0: 1693.5, 1: 1703.4. Samples: 14501146. Policy #0 lag: (min: 2.0, avg: 8.2, max: 34.0) -[2023-10-09 01:10:18,974][87372] Avg episode reward: [(0, '5.280'), (1, '6.580')] -[2023-10-09 01:10:19,093][88327] Updated weights for policy 1, policy_version 28310 (0.0009) -[2023-10-09 01:10:19,259][88326] Updated weights for policy 0, policy_version 28312 (0.0007) -[2023-10-09 01:10:19,455][88168] Saving new best policy, reward=6.580! -[2023-10-09 01:10:19,458][88327] Updated weights for policy 1, policy_version 28320 (0.0007) -[2023-10-09 01:10:23,421][88326] Updated weights for policy 0, policy_version 28322 (0.0007) -[2023-10-09 01:10:23,552][88327] Updated weights for policy 1, policy_version 28330 (0.0008) -[2023-10-09 01:10:23,821][88326] Updated weights for policy 0, policy_version 28332 (0.0009) -[2023-10-09 01:10:23,919][88327] Updated weights for policy 1, policy_version 28340 (0.0009) -[2023-10-09 01:10:23,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13329.3). Total num frames: 57999360. Throughput: 0: 1693.4, 1: 1702.0. Samples: 14510084. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-09 01:10:23,975][87372] Avg episode reward: [(0, '5.150'), (1, '6.190')] -[2023-10-09 01:10:24,187][88326] Updated weights for policy 0, policy_version 28342 (0.0010) -[2023-10-09 01:10:24,281][88327] Updated weights for policy 1, policy_version 28350 (0.0009) -[2023-10-09 01:10:24,548][88326] Updated weights for policy 0, policy_version 28352 (0.0009) -[2023-10-09 01:10:28,284][88327] Updated weights for policy 1, policy_version 28360 (0.0008) -[2023-10-09 01:10:28,585][88326] Updated weights for policy 0, policy_version 28362 (0.0009) -[2023-10-09 01:10:28,649][88327] Updated weights for policy 1, policy_version 28370 (0.0008) -[2023-10-09 01:10:28,952][88326] Updated weights for policy 0, policy_version 28372 (0.0009) -[2023-10-09 01:10:28,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 58064896. Throughput: 0: 1682.6, 1: 1701.8. Samples: 14530706. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-09 01:10:28,975][87372] Avg episode reward: [(0, '5.330'), (1, '6.140')] -[2023-10-09 01:10:29,007][88327] Updated weights for policy 1, policy_version 28380 (0.0008) -[2023-10-09 01:10:29,318][88326] Updated weights for policy 0, policy_version 28382 (0.0009) -[2023-10-09 01:10:32,932][88327] Updated weights for policy 1, policy_version 28390 (0.0008) -[2023-10-09 01:10:33,306][88327] Updated weights for policy 1, policy_version 28400 (0.0007) -[2023-10-09 01:10:33,398][88326] Updated weights for policy 0, policy_version 28392 (0.0008) -[2023-10-09 01:10:33,662][88327] Updated weights for policy 1, policy_version 28410 (0.0007) -[2023-10-09 01:10:33,763][88326] Updated weights for policy 0, policy_version 28402 (0.0008) -[2023-10-09 01:10:33,974][87372] Fps is (10 sec: 16384.3, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 58163200. Throughput: 0: 1683.8, 1: 1694.0. Samples: 14551388. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-09 01:10:33,975][87372] Avg episode reward: [(0, '5.610'), (1, '6.290')] -[2023-10-09 01:10:33,985][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000028416_29097984.pth... -[2023-10-09 01:10:34,018][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000026816_27459584.pth -[2023-10-09 01:10:34,133][88326] Updated weights for policy 0, policy_version 28412 (0.0007) -[2023-10-09 01:10:34,278][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000028416_29097984.pth... -[2023-10-09 01:10:34,307][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000026816_27459584.pth -[2023-10-09 01:10:37,823][88327] Updated weights for policy 1, policy_version 28420 (0.0009) -[2023-10-09 01:10:38,177][88326] Updated weights for policy 0, policy_version 28422 (0.0007) -[2023-10-09 01:10:38,187][88327] Updated weights for policy 1, policy_version 28430 (0.0009) -[2023-10-09 01:10:38,545][88326] Updated weights for policy 0, policy_version 28432 (0.0007) -[2023-10-09 01:10:38,548][88327] Updated weights for policy 1, policy_version 28440 (0.0009) -[2023-10-09 01:10:38,913][88326] Updated weights for policy 0, policy_version 28442 (0.0009) -[2023-10-09 01:10:38,974][87372] Fps is (10 sec: 16383.9, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 58228736. Throughput: 0: 1688.9, 1: 1702.9. Samples: 14561062. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-09 01:10:38,975][87372] Avg episode reward: [(0, '5.230'), (1, '5.500')] -[2023-10-09 01:10:42,605][88327] Updated weights for policy 1, policy_version 28450 (0.0008) -[2023-10-09 01:10:42,927][88326] Updated weights for policy 0, policy_version 28452 (0.0009) -[2023-10-09 01:10:42,977][88327] Updated weights for policy 1, policy_version 28460 (0.0008) -[2023-10-09 01:10:43,283][88326] Updated weights for policy 0, policy_version 28462 (0.0007) -[2023-10-09 01:10:43,351][88327] Updated weights for policy 1, policy_version 28470 (0.0007) -[2023-10-09 01:10:43,654][88326] Updated weights for policy 0, policy_version 28472 (0.0007) -[2023-10-09 01:10:43,716][88327] Updated weights for policy 1, policy_version 28480 (0.0007) -[2023-10-09 01:10:43,974][87372] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 58327040. Throughput: 0: 1688.3, 1: 1705.7. Samples: 14581868. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:10:43,975][87372] Avg episode reward: [(0, '5.190'), (1, '5.340')] -[2023-10-09 01:10:47,599][88327] Updated weights for policy 1, policy_version 28490 (0.0010) -[2023-10-09 01:10:47,844][88326] Updated weights for policy 0, policy_version 28482 (0.0008) -[2023-10-09 01:10:47,970][88327] Updated weights for policy 1, policy_version 28500 (0.0008) -[2023-10-09 01:10:48,208][88326] Updated weights for policy 0, policy_version 28492 (0.0007) -[2023-10-09 01:10:48,330][88327] Updated weights for policy 1, policy_version 28510 (0.0010) -[2023-10-09 01:10:48,584][88326] Updated weights for policy 0, policy_version 28502 (0.0007) -[2023-10-09 01:10:48,943][88326] Updated weights for policy 0, policy_version 28512 (0.0008) -[2023-10-09 01:10:48,974][87372] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 58392576. Throughput: 0: 1677.6, 1: 1689.2. Samples: 14601604. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:10:48,975][87372] Avg episode reward: [(0, '5.340'), (1, '5.810')] -[2023-10-09 01:10:52,281][88327] Updated weights for policy 1, policy_version 28520 (0.0009) -[2023-10-09 01:10:52,648][88327] Updated weights for policy 1, policy_version 28530 (0.0009) -[2023-10-09 01:10:52,978][88326] Updated weights for policy 0, policy_version 28522 (0.0009) -[2023-10-09 01:10:53,015][88327] Updated weights for policy 1, policy_version 28540 (0.0007) -[2023-10-09 01:10:53,346][88326] Updated weights for policy 0, policy_version 28532 (0.0008) -[2023-10-09 01:10:53,728][88326] Updated weights for policy 0, policy_version 28542 (0.0009) -[2023-10-09 01:10:53,974][87372] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 58458112. Throughput: 0: 1691.1, 1: 1714.4. Samples: 14612262. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:10:53,975][87372] Avg episode reward: [(0, '5.660'), (1, '6.130')] -[2023-10-09 01:10:57,061][88327] Updated weights for policy 1, policy_version 28550 (0.0007) -[2023-10-09 01:10:57,450][88327] Updated weights for policy 1, policy_version 28560 (0.0008) -[2023-10-09 01:10:57,826][88327] Updated weights for policy 1, policy_version 28570 (0.0009) -[2023-10-09 01:10:57,846][88326] Updated weights for policy 0, policy_version 28552 (0.0007) -[2023-10-09 01:10:58,217][88326] Updated weights for policy 0, policy_version 28562 (0.0009) -[2023-10-09 01:10:58,587][88326] Updated weights for policy 0, policy_version 28572 (0.0007) -[2023-10-09 01:10:58,974][87372] Fps is (10 sec: 13107.5, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 58523648. Throughput: 0: 1695.7, 1: 1703.9. Samples: 14632736. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:10:58,975][87372] Avg episode reward: [(0, '5.350'), (1, '6.050')] -[2023-10-09 01:11:01,716][88327] Updated weights for policy 1, policy_version 28580 (0.0008) -[2023-10-09 01:11:02,089][88327] Updated weights for policy 1, policy_version 28590 (0.0007) -[2023-10-09 01:11:02,451][88327] Updated weights for policy 1, policy_version 28600 (0.0007) -[2023-10-09 01:11:02,578][88326] Updated weights for policy 0, policy_version 28582 (0.0007) -[2023-10-09 01:11:02,942][88326] Updated weights for policy 0, policy_version 28592 (0.0008) -[2023-10-09 01:11:03,315][88326] Updated weights for policy 0, policy_version 28602 (0.0010) -[2023-10-09 01:11:03,974][87372] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 58589184. Throughput: 0: 1670.8, 1: 1679.6. Samples: 14651916. Policy #0 lag: (min: 17.0, avg: 27.9, max: 49.0) -[2023-10-09 01:11:03,975][87372] Avg episode reward: [(0, '5.880'), (1, '5.680')] -[2023-10-09 01:11:06,546][88327] Updated weights for policy 1, policy_version 28610 (0.0007) -[2023-10-09 01:11:06,917][88327] Updated weights for policy 1, policy_version 28620 (0.0010) -[2023-10-09 01:11:07,283][88327] Updated weights for policy 1, policy_version 28630 (0.0010) -[2023-10-09 01:11:07,290][88326] Updated weights for policy 0, policy_version 28612 (0.0009) -[2023-10-09 01:11:07,639][88327] Updated weights for policy 1, policy_version 28640 (0.0009) -[2023-10-09 01:11:07,662][88326] Updated weights for policy 0, policy_version 28622 (0.0009) -[2023-10-09 01:11:08,034][88326] Updated weights for policy 0, policy_version 28632 (0.0007) -[2023-10-09 01:11:08,974][87372] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 58654720. Throughput: 0: 1694.0, 1: 1709.0. Samples: 14663218. Policy #0 lag: (min: 17.0, avg: 27.9, max: 49.0) -[2023-10-09 01:11:08,975][87372] Avg episode reward: [(0, '5.720'), (1, '6.010')] -[2023-10-09 01:11:11,838][88327] Updated weights for policy 1, policy_version 28650 (0.0008) -[2023-10-09 01:11:12,078][88326] Updated weights for policy 0, policy_version 28642 (0.0007) -[2023-10-09 01:11:12,196][88327] Updated weights for policy 1, policy_version 28660 (0.0009) -[2023-10-09 01:11:12,450][88326] Updated weights for policy 0, policy_version 28652 (0.0008) -[2023-10-09 01:11:12,556][88327] Updated weights for policy 1, policy_version 28670 (0.0009) -[2023-10-09 01:11:12,804][88326] Updated weights for policy 0, policy_version 28662 (0.0007) -[2023-10-09 01:11:13,170][88326] Updated weights for policy 0, policy_version 28672 (0.0008) -[2023-10-09 01:11:13,974][87372] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 58720256. Throughput: 0: 1692.8, 1: 1691.5. Samples: 14683002. Policy #0 lag: (min: 17.0, avg: 27.9, max: 49.0) -[2023-10-09 01:11:13,975][87372] Avg episode reward: [(0, '5.440'), (1, '5.760')] -[2023-10-09 01:11:16,773][88327] Updated weights for policy 1, policy_version 28680 (0.0009) -[2023-10-09 01:11:17,129][88327] Updated weights for policy 1, policy_version 28690 (0.0008) -[2023-10-09 01:11:17,201][88326] Updated weights for policy 0, policy_version 28682 (0.0007) -[2023-10-09 01:11:17,503][88327] Updated weights for policy 1, policy_version 28700 (0.0007) -[2023-10-09 01:11:17,563][88326] Updated weights for policy 0, policy_version 28692 (0.0007) -[2023-10-09 01:11:17,943][88326] Updated weights for policy 0, policy_version 28702 (0.0008) -[2023-10-09 01:11:18,974][87372] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 58785792. Throughput: 0: 1672.3, 1: 1682.2. Samples: 14702338. Policy #0 lag: (min: 17.0, avg: 27.9, max: 49.0) -[2023-10-09 01:11:18,974][87372] Avg episode reward: [(0, '5.370'), (1, '5.150')] -[2023-10-09 01:11:21,565][88327] Updated weights for policy 1, policy_version 28710 (0.0009) -[2023-10-09 01:11:21,935][88327] Updated weights for policy 1, policy_version 28720 (0.0008) -[2023-10-09 01:11:21,964][88326] Updated weights for policy 0, policy_version 28712 (0.0009) -[2023-10-09 01:11:22,301][88327] Updated weights for policy 1, policy_version 28730 (0.0008) -[2023-10-09 01:11:22,332][88326] Updated weights for policy 0, policy_version 28722 (0.0007) -[2023-10-09 01:11:22,701][88326] Updated weights for policy 0, policy_version 28732 (0.0008) -[2023-10-09 01:11:23,974][87372] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 58851328. Throughput: 0: 1696.1, 1: 1705.0. Samples: 14714112. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-09 01:11:23,975][87372] Avg episode reward: [(0, '5.470'), (1, '5.690')] -[2023-10-09 01:11:26,232][88327] Updated weights for policy 1, policy_version 28740 (0.0009) -[2023-10-09 01:11:26,590][88327] Updated weights for policy 1, policy_version 28750 (0.0010) -[2023-10-09 01:11:26,775][88326] Updated weights for policy 0, policy_version 28742 (0.0008) -[2023-10-09 01:11:26,948][88327] Updated weights for policy 1, policy_version 28760 (0.0009) -[2023-10-09 01:11:27,139][88326] Updated weights for policy 0, policy_version 28752 (0.0009) -[2023-10-09 01:11:27,504][88326] Updated weights for policy 0, policy_version 28762 (0.0010) -[2023-10-09 01:11:28,974][87372] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 58916864. Throughput: 0: 1685.7, 1: 1679.1. Samples: 14733284. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-09 01:11:28,975][87372] Avg episode reward: [(0, '5.920'), (1, '5.360')] -[2023-10-09 01:11:31,038][88327] Updated weights for policy 1, policy_version 28770 (0.0010) -[2023-10-09 01:11:31,409][88327] Updated weights for policy 1, policy_version 28780 (0.0008) -[2023-10-09 01:11:31,568][88326] Updated weights for policy 0, policy_version 28772 (0.0011) -[2023-10-09 01:11:31,787][88327] Updated weights for policy 1, policy_version 28790 (0.0008) -[2023-10-09 01:11:31,931][88326] Updated weights for policy 0, policy_version 28782 (0.0007) -[2023-10-09 01:11:32,146][88327] Updated weights for policy 1, policy_version 28800 (0.0008) -[2023-10-09 01:11:32,313][88326] Updated weights for policy 0, policy_version 28792 (0.0007) -[2023-10-09 01:11:33,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 58982400. Throughput: 0: 1678.9, 1: 1688.1. Samples: 14753120. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-09 01:11:33,975][87372] Avg episode reward: [(0, '5.570'), (1, '5.410')] -[2023-10-09 01:11:36,185][88327] Updated weights for policy 1, policy_version 28810 (0.0009) -[2023-10-09 01:11:36,408][88326] Updated weights for policy 0, policy_version 28802 (0.0008) -[2023-10-09 01:11:36,554][88327] Updated weights for policy 1, policy_version 28820 (0.0007) -[2023-10-09 01:11:36,777][88326] Updated weights for policy 0, policy_version 28812 (0.0008) -[2023-10-09 01:11:36,910][88327] Updated weights for policy 1, policy_version 28830 (0.0007) -[2023-10-09 01:11:37,157][88326] Updated weights for policy 0, policy_version 28822 (0.0007) -[2023-10-09 01:11:37,518][88326] Updated weights for policy 0, policy_version 28832 (0.0011) -[2023-10-09 01:11:38,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 59047936. Throughput: 0: 1693.6, 1: 1687.0. Samples: 14764392. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-09 01:11:38,975][87372] Avg episode reward: [(0, '5.860'), (1, '5.680')] -[2023-10-09 01:11:40,922][88327] Updated weights for policy 1, policy_version 28840 (0.0011) -[2023-10-09 01:11:41,282][88327] Updated weights for policy 1, policy_version 28850 (0.0009) -[2023-10-09 01:11:41,543][88326] Updated weights for policy 0, policy_version 28842 (0.0008) -[2023-10-09 01:11:41,655][88327] Updated weights for policy 1, policy_version 28860 (0.0009) -[2023-10-09 01:11:41,914][88326] Updated weights for policy 0, policy_version 28852 (0.0009) -[2023-10-09 01:11:42,281][88326] Updated weights for policy 0, policy_version 28862 (0.0009) -[2023-10-09 01:11:43,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 59113472. Throughput: 0: 1671.9, 1: 1677.7. Samples: 14783468. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-09 01:11:43,975][87372] Avg episode reward: [(0, '5.760'), (1, '5.320')] -[2023-10-09 01:11:45,640][88327] Updated weights for policy 1, policy_version 28870 (0.0011) -[2023-10-09 01:11:46,006][88327] Updated weights for policy 1, policy_version 28880 (0.0011) -[2023-10-09 01:11:46,341][88326] Updated weights for policy 0, policy_version 28872 (0.0008) -[2023-10-09 01:11:46,372][88327] Updated weights for policy 1, policy_version 28890 (0.0007) -[2023-10-09 01:11:46,710][88326] Updated weights for policy 0, policy_version 28882 (0.0008) -[2023-10-09 01:11:47,083][88326] Updated weights for policy 0, policy_version 28892 (0.0010) -[2023-10-09 01:11:48,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 59179008. Throughput: 0: 1685.7, 1: 1698.5. Samples: 14804206. Policy #0 lag: (min: 30.0, avg: 33.0, max: 62.0) -[2023-10-09 01:11:48,975][87372] Avg episode reward: [(0, '5.370'), (1, '5.430')] -[2023-10-09 01:11:50,492][88327] Updated weights for policy 1, policy_version 28900 (0.0008) -[2023-10-09 01:11:50,862][88327] Updated weights for policy 1, policy_version 28910 (0.0008) -[2023-10-09 01:11:51,022][88326] Updated weights for policy 0, policy_version 28902 (0.0010) -[2023-10-09 01:11:51,216][88327] Updated weights for policy 1, policy_version 28920 (0.0008) -[2023-10-09 01:11:51,383][88326] Updated weights for policy 0, policy_version 28912 (0.0010) -[2023-10-09 01:11:51,757][88326] Updated weights for policy 0, policy_version 28922 (0.0008) -[2023-10-09 01:11:53,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 59244544. Throughput: 0: 1686.7, 1: 1680.4. Samples: 14814736. Policy #0 lag: (min: 30.0, avg: 33.0, max: 62.0) -[2023-10-09 01:11:53,975][87372] Avg episode reward: [(0, '5.140'), (1, '5.610')] -[2023-10-09 01:11:55,109][88327] Updated weights for policy 1, policy_version 28930 (0.0008) -[2023-10-09 01:11:55,472][88327] Updated weights for policy 1, policy_version 28940 (0.0011) -[2023-10-09 01:11:55,761][88326] Updated weights for policy 0, policy_version 28932 (0.0007) -[2023-10-09 01:11:55,830][88327] Updated weights for policy 1, policy_version 28950 (0.0009) -[2023-10-09 01:11:56,118][88326] Updated weights for policy 0, policy_version 28942 (0.0009) -[2023-10-09 01:11:56,191][88327] Updated weights for policy 1, policy_version 28960 (0.0008) -[2023-10-09 01:11:56,484][88326] Updated weights for policy 0, policy_version 28952 (0.0007) -[2023-10-09 01:11:58,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 59310080. Throughput: 0: 1671.8, 1: 1695.5. Samples: 14834532. Policy #0 lag: (min: 30.0, avg: 33.0, max: 62.0) -[2023-10-09 01:11:58,975][87372] Avg episode reward: [(0, '5.320'), (1, '5.620')] -[2023-10-09 01:12:00,354][88327] Updated weights for policy 1, policy_version 28970 (0.0008) -[2023-10-09 01:12:00,598][88326] Updated weights for policy 0, policy_version 28962 (0.0008) -[2023-10-09 01:12:00,710][88327] Updated weights for policy 1, policy_version 28980 (0.0011) -[2023-10-09 01:12:01,024][88326] Updated weights for policy 0, policy_version 28972 (0.0010) -[2023-10-09 01:12:01,072][88327] Updated weights for policy 1, policy_version 28990 (0.0008) -[2023-10-09 01:12:01,394][88326] Updated weights for policy 0, policy_version 28982 (0.0008) -[2023-10-09 01:12:01,764][88326] Updated weights for policy 0, policy_version 28992 (0.0008) -[2023-10-09 01:12:03,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 59375616. Throughput: 0: 1687.6, 1: 1707.7. Samples: 14855128. Policy #0 lag: (min: 30.0, avg: 33.0, max: 62.0) -[2023-10-09 01:12:03,975][87372] Avg episode reward: [(0, '5.320'), (1, '5.880')] -[2023-10-09 01:12:05,045][88327] Updated weights for policy 1, policy_version 29000 (0.0009) -[2023-10-09 01:12:05,410][88327] Updated weights for policy 1, policy_version 29010 (0.0010) -[2023-10-09 01:12:05,640][88326] Updated weights for policy 0, policy_version 29002 (0.0009) -[2023-10-09 01:12:05,780][88327] Updated weights for policy 1, policy_version 29020 (0.0008) -[2023-10-09 01:12:06,010][88326] Updated weights for policy 0, policy_version 29012 (0.0007) -[2023-10-09 01:12:06,379][88326] Updated weights for policy 0, policy_version 29022 (0.0007) -[2023-10-09 01:12:08,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 59441152. Throughput: 0: 1667.1, 1: 1675.6. Samples: 14864536. Policy #0 lag: (min: 30.0, avg: 33.0, max: 62.0) -[2023-10-09 01:12:08,975][87372] Avg episode reward: [(0, '5.320'), (1, '5.720')] -[2023-10-09 01:12:09,729][88327] Updated weights for policy 1, policy_version 29030 (0.0008) -[2023-10-09 01:12:10,087][88327] Updated weights for policy 1, policy_version 29040 (0.0008) -[2023-10-09 01:12:10,457][88327] Updated weights for policy 1, policy_version 29050 (0.0007) -[2023-10-09 01:12:10,656][88326] Updated weights for policy 0, policy_version 29032 (0.0007) -[2023-10-09 01:12:11,025][88326] Updated weights for policy 0, policy_version 29042 (0.0008) -[2023-10-09 01:12:11,406][88326] Updated weights for policy 0, policy_version 29052 (0.0008) -[2023-10-09 01:12:13,974][87372] Fps is (10 sec: 13107.6, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 59506688. Throughput: 0: 1667.1, 1: 1699.9. Samples: 14884798. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-09 01:12:13,975][87372] Avg episode reward: [(0, '5.280'), (1, '5.720')] -[2023-10-09 01:12:14,393][88327] Updated weights for policy 1, policy_version 29060 (0.0009) -[2023-10-09 01:12:14,767][88327] Updated weights for policy 1, policy_version 29070 (0.0009) -[2023-10-09 01:12:15,136][88327] Updated weights for policy 1, policy_version 29080 (0.0008) -[2023-10-09 01:12:15,443][88326] Updated weights for policy 0, policy_version 29062 (0.0009) -[2023-10-09 01:12:15,810][88326] Updated weights for policy 0, policy_version 29072 (0.0008) -[2023-10-09 01:12:16,181][88326] Updated weights for policy 0, policy_version 29082 (0.0007) -[2023-10-09 01:12:18,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 59572224. Throughput: 0: 1683.3, 1: 1711.7. Samples: 14905896. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-09 01:12:18,975][87372] Avg episode reward: [(0, '5.830'), (1, '6.170')] -[2023-10-09 01:12:19,182][88327] Updated weights for policy 1, policy_version 29090 (0.0008) -[2023-10-09 01:12:19,550][88327] Updated weights for policy 1, policy_version 29100 (0.0009) -[2023-10-09 01:12:19,915][88327] Updated weights for policy 1, policy_version 29110 (0.0008) -[2023-10-09 01:12:20,285][88327] Updated weights for policy 1, policy_version 29120 (0.0008) -[2023-10-09 01:12:20,356][88326] Updated weights for policy 0, policy_version 29092 (0.0007) -[2023-10-09 01:12:20,724][88326] Updated weights for policy 0, policy_version 29102 (0.0009) -[2023-10-09 01:12:21,096][88326] Updated weights for policy 0, policy_version 29112 (0.0010) -[2023-10-09 01:12:23,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 59637760. Throughput: 0: 1662.0, 1: 1689.6. Samples: 14915210. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-09 01:12:23,975][87372] Avg episode reward: [(0, '6.020'), (1, '6.090')] -[2023-10-09 01:12:24,294][88327] Updated weights for policy 1, policy_version 29130 (0.0007) -[2023-10-09 01:12:24,664][88327] Updated weights for policy 1, policy_version 29140 (0.0007) -[2023-10-09 01:12:25,021][88327] Updated weights for policy 1, policy_version 29150 (0.0008) -[2023-10-09 01:12:25,146][88326] Updated weights for policy 0, policy_version 29122 (0.0007) -[2023-10-09 01:12:25,512][88326] Updated weights for policy 0, policy_version 29132 (0.0008) -[2023-10-09 01:12:25,888][88326] Updated weights for policy 0, policy_version 29142 (0.0010) -[2023-10-09 01:12:26,268][88326] Updated weights for policy 0, policy_version 29152 (0.0011) -[2023-10-09 01:12:28,967][88327] Updated weights for policy 1, policy_version 29160 (0.0008) -[2023-10-09 01:12:28,974][87372] Fps is (10 sec: 13106.7, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 59703296. Throughput: 0: 1676.3, 1: 1712.6. Samples: 14935970. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-09 01:12:28,976][87372] Avg episode reward: [(0, '5.710'), (1, '6.190')] -[2023-10-09 01:12:29,337][88327] Updated weights for policy 1, policy_version 29170 (0.0007) -[2023-10-09 01:12:29,703][88327] Updated weights for policy 1, policy_version 29180 (0.0007) -[2023-10-09 01:12:30,313][88326] Updated weights for policy 0, policy_version 29162 (0.0011) -[2023-10-09 01:12:30,692][88326] Updated weights for policy 0, policy_version 29172 (0.0012) -[2023-10-09 01:12:31,050][88326] Updated weights for policy 0, policy_version 29182 (0.0009) -[2023-10-09 01:12:33,871][88327] Updated weights for policy 1, policy_version 29190 (0.0009) -[2023-10-09 01:12:33,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 59768832. Throughput: 0: 1682.6, 1: 1711.6. Samples: 14956946. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-09 01:12:33,975][87372] Avg episode reward: [(0, '5.700'), (1, '6.490')] -[2023-10-09 01:12:33,981][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000029184_29884416.pth... -[2023-10-09 01:12:34,014][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000027616_28278784.pth -[2023-10-09 01:12:34,250][88327] Updated weights for policy 1, policy_version 29200 (0.0010) -[2023-10-09 01:12:34,611][88327] Updated weights for policy 1, policy_version 29210 (0.0011) -[2023-10-09 01:12:34,834][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000029216_29917184.pth... -[2023-10-09 01:12:34,863][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000027616_28278784.pth -[2023-10-09 01:12:35,093][88326] Updated weights for policy 0, policy_version 29192 (0.0008) -[2023-10-09 01:12:35,469][88326] Updated weights for policy 0, policy_version 29202 (0.0008) -[2023-10-09 01:12:35,842][88326] Updated weights for policy 0, policy_version 29212 (0.0007) -[2023-10-09 01:12:38,581][88327] Updated weights for policy 1, policy_version 29220 (0.0008) -[2023-10-09 01:12:38,942][88327] Updated weights for policy 1, policy_version 29230 (0.0008) -[2023-10-09 01:12:38,974][87372] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 59834368. Throughput: 0: 1663.0, 1: 1696.7. Samples: 14965922. Policy #0 lag: (min: 21.0, avg: 28.7, max: 53.0) -[2023-10-09 01:12:38,975][87372] Avg episode reward: [(0, '5.050'), (1, '5.710')] -[2023-10-09 01:12:39,320][88327] Updated weights for policy 1, policy_version 29240 (0.0009) -[2023-10-09 01:12:39,933][88326] Updated weights for policy 0, policy_version 29222 (0.0007) -[2023-10-09 01:12:40,297][88326] Updated weights for policy 0, policy_version 29232 (0.0007) -[2023-10-09 01:12:40,669][88326] Updated weights for policy 0, policy_version 29242 (0.0007) -[2023-10-09 01:12:43,364][88327] Updated weights for policy 1, policy_version 29250 (0.0010) -[2023-10-09 01:12:43,722][88327] Updated weights for policy 1, policy_version 29260 (0.0008) -[2023-10-09 01:12:43,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 59899904. Throughput: 0: 1679.5, 1: 1703.8. Samples: 14986780. Policy #0 lag: (min: 21.0, avg: 28.7, max: 53.0) -[2023-10-09 01:12:43,975][87372] Avg episode reward: [(0, '4.990'), (1, '5.760')] -[2023-10-09 01:12:44,099][88327] Updated weights for policy 1, policy_version 29270 (0.0009) -[2023-10-09 01:12:44,464][88327] Updated weights for policy 1, policy_version 29280 (0.0011) -[2023-10-09 01:12:44,648][88326] Updated weights for policy 0, policy_version 29252 (0.0008) -[2023-10-09 01:12:45,024][88326] Updated weights for policy 0, policy_version 29262 (0.0011) -[2023-10-09 01:12:45,402][88326] Updated weights for policy 0, policy_version 29272 (0.0011) -[2023-10-09 01:12:48,504][88327] Updated weights for policy 1, policy_version 29290 (0.0008) -[2023-10-09 01:12:48,864][88327] Updated weights for policy 1, policy_version 29300 (0.0007) -[2023-10-09 01:12:48,974][87372] Fps is (10 sec: 13106.8, 60 sec: 13107.1, 300 sec: 13440.4). Total num frames: 59965440. Throughput: 0: 1684.7, 1: 1701.9. Samples: 15007526. Policy #0 lag: (min: 21.0, avg: 28.7, max: 53.0) -[2023-10-09 01:12:48,975][87372] Avg episode reward: [(0, '5.940'), (1, '5.570')] -[2023-10-09 01:12:49,230][88327] Updated weights for policy 1, policy_version 29310 (0.0010) -[2023-10-09 01:12:49,428][88326] Updated weights for policy 0, policy_version 29282 (0.0008) -[2023-10-09 01:12:49,817][88326] Updated weights for policy 0, policy_version 29292 (0.0007) -[2023-10-09 01:12:50,192][88326] Updated weights for policy 0, policy_version 29302 (0.0008) -[2023-10-09 01:12:50,571][88326] Updated weights for policy 0, policy_version 29312 (0.0010) -[2023-10-09 01:12:53,247][88327] Updated weights for policy 1, policy_version 29320 (0.0009) -[2023-10-09 01:12:53,610][88327] Updated weights for policy 1, policy_version 29330 (0.0008) -[2023-10-09 01:12:53,974][88327] Updated weights for policy 1, policy_version 29340 (0.0010) -[2023-10-09 01:12:53,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 60030976. Throughput: 0: 1677.9, 1: 1705.3. Samples: 15016778. Policy #0 lag: (min: 21.0, avg: 28.7, max: 53.0) -[2023-10-09 01:12:53,975][87372] Avg episode reward: [(0, '5.890'), (1, '5.410')] -[2023-10-09 01:12:54,363][88326] Updated weights for policy 0, policy_version 29322 (0.0009) -[2023-10-09 01:12:54,726][88326] Updated weights for policy 0, policy_version 29332 (0.0007) -[2023-10-09 01:12:55,093][88326] Updated weights for policy 0, policy_version 29342 (0.0007) -[2023-10-09 01:12:58,093][88327] Updated weights for policy 1, policy_version 29350 (0.0008) -[2023-10-09 01:12:58,457][88327] Updated weights for policy 1, policy_version 29360 (0.0007) -[2023-10-09 01:12:58,819][88327] Updated weights for policy 1, policy_version 29370 (0.0007) -[2023-10-09 01:12:58,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 60096512. Throughput: 0: 1694.7, 1: 1703.7. Samples: 15037726. Policy #0 lag: (min: 21.0, avg: 28.7, max: 53.0) -[2023-10-09 01:12:58,975][87372] Avg episode reward: [(0, '5.350'), (1, '5.420')] -[2023-10-09 01:12:59,178][88326] Updated weights for policy 0, policy_version 29352 (0.0009) -[2023-10-09 01:12:59,541][88326] Updated weights for policy 0, policy_version 29362 (0.0012) -[2023-10-09 01:12:59,914][88326] Updated weights for policy 0, policy_version 29372 (0.0009) -[2023-10-09 01:13:02,764][88327] Updated weights for policy 1, policy_version 29380 (0.0008) -[2023-10-09 01:13:03,136][88327] Updated weights for policy 1, policy_version 29390 (0.0008) -[2023-10-09 01:13:03,504][88327] Updated weights for policy 1, policy_version 29400 (0.0007) -[2023-10-09 01:13:03,878][88326] Updated weights for policy 0, policy_version 29382 (0.0008) -[2023-10-09 01:13:03,974][87372] Fps is (10 sec: 16384.0, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 60194816. Throughput: 0: 1694.3, 1: 1691.0. Samples: 15058232. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-09 01:13:03,974][87372] Avg episode reward: [(0, '5.520'), (1, '5.570')] -[2023-10-09 01:13:04,251][88326] Updated weights for policy 0, policy_version 29392 (0.0007) -[2023-10-09 01:13:04,616][88326] Updated weights for policy 0, policy_version 29402 (0.0010) -[2023-10-09 01:13:07,530][88327] Updated weights for policy 1, policy_version 29410 (0.0007) -[2023-10-09 01:13:07,900][88327] Updated weights for policy 1, policy_version 29420 (0.0009) -[2023-10-09 01:13:08,267][88327] Updated weights for policy 1, policy_version 29430 (0.0011) -[2023-10-09 01:13:08,636][88327] Updated weights for policy 1, policy_version 29440 (0.0010) -[2023-10-09 01:13:08,852][88326] Updated weights for policy 0, policy_version 29412 (0.0008) -[2023-10-09 01:13:08,974][87372] Fps is (10 sec: 16384.2, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 60260352. Throughput: 0: 1690.3, 1: 1708.0. Samples: 15068134. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-09 01:13:08,974][87372] Avg episode reward: [(0, '5.170'), (1, '5.780')] -[2023-10-09 01:13:09,226][88326] Updated weights for policy 0, policy_version 29422 (0.0010) -[2023-10-09 01:13:09,597][88326] Updated weights for policy 0, policy_version 29432 (0.0008) -[2023-10-09 01:13:12,831][88327] Updated weights for policy 1, policy_version 29450 (0.0008) -[2023-10-09 01:13:13,208][88327] Updated weights for policy 1, policy_version 29460 (0.0009) -[2023-10-09 01:13:13,575][88327] Updated weights for policy 1, policy_version 29470 (0.0008) -[2023-10-09 01:13:13,612][88326] Updated weights for policy 0, policy_version 29442 (0.0010) -[2023-10-09 01:13:13,970][88326] Updated weights for policy 0, policy_version 29452 (0.0009) -[2023-10-09 01:13:13,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 60325888. Throughput: 0: 1697.0, 1: 1700.4. Samples: 15088850. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-09 01:13:13,975][87372] Avg episode reward: [(0, '5.320'), (1, '5.510')] -[2023-10-09 01:13:14,347][88326] Updated weights for policy 0, policy_version 29462 (0.0008) -[2023-10-09 01:13:14,723][88326] Updated weights for policy 0, policy_version 29472 (0.0008) -[2023-10-09 01:13:17,554][88327] Updated weights for policy 1, policy_version 29480 (0.0008) -[2023-10-09 01:13:17,921][88327] Updated weights for policy 1, policy_version 29490 (0.0007) -[2023-10-09 01:13:18,287][88327] Updated weights for policy 1, policy_version 29500 (0.0008) -[2023-10-09 01:13:18,731][88326] Updated weights for policy 0, policy_version 29482 (0.0008) -[2023-10-09 01:13:18,974][87372] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 60391424. Throughput: 0: 1700.7, 1: 1680.0. Samples: 15109076. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-09 01:13:18,975][87372] Avg episode reward: [(0, '5.690'), (1, '5.790')] -[2023-10-09 01:13:19,099][88326] Updated weights for policy 0, policy_version 29492 (0.0008) -[2023-10-09 01:13:19,474][88326] Updated weights for policy 0, policy_version 29502 (0.0009) -[2023-10-09 01:13:22,336][88327] Updated weights for policy 1, policy_version 29510 (0.0008) -[2023-10-09 01:13:22,731][88327] Updated weights for policy 1, policy_version 29520 (0.0010) -[2023-10-09 01:13:23,101][88327] Updated weights for policy 1, policy_version 29530 (0.0009) -[2023-10-09 01:13:23,495][88326] Updated weights for policy 0, policy_version 29512 (0.0007) -[2023-10-09 01:13:23,867][88326] Updated weights for policy 0, policy_version 29522 (0.0008) -[2023-10-09 01:13:23,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 60456960. Throughput: 0: 1700.0, 1: 1708.4. Samples: 15119300. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-09 01:13:23,975][87372] Avg episode reward: [(0, '5.720'), (1, '5.390')] -[2023-10-09 01:13:24,241][88326] Updated weights for policy 0, policy_version 29532 (0.0008) -[2023-10-09 01:13:26,952][88327] Updated weights for policy 1, policy_version 29540 (0.0009) -[2023-10-09 01:13:27,320][88327] Updated weights for policy 1, policy_version 29550 (0.0008) -[2023-10-09 01:13:27,696][88327] Updated weights for policy 1, policy_version 29560 (0.0007) -[2023-10-09 01:13:28,456][88326] Updated weights for policy 0, policy_version 29542 (0.0009) -[2023-10-09 01:13:28,816][88326] Updated weights for policy 0, policy_version 29552 (0.0009) -[2023-10-09 01:13:28,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 60522496. Throughput: 0: 1700.7, 1: 1698.3. Samples: 15139736. Policy #0 lag: (min: 13.0, avg: 22.3, max: 45.0) -[2023-10-09 01:13:28,975][87372] Avg episode reward: [(0, '5.840'), (1, '5.610')] -[2023-10-09 01:13:29,196][88326] Updated weights for policy 0, policy_version 29562 (0.0008) -[2023-10-09 01:13:31,713][88327] Updated weights for policy 1, policy_version 29570 (0.0008) -[2023-10-09 01:13:32,068][88327] Updated weights for policy 1, policy_version 29580 (0.0011) -[2023-10-09 01:13:32,435][88327] Updated weights for policy 1, policy_version 29590 (0.0011) -[2023-10-09 01:13:32,795][88327] Updated weights for policy 1, policy_version 29600 (0.0010) -[2023-10-09 01:13:33,039][88326] Updated weights for policy 0, policy_version 29572 (0.0010) -[2023-10-09 01:13:33,407][88326] Updated weights for policy 0, policy_version 29582 (0.0008) -[2023-10-09 01:13:33,789][88326] Updated weights for policy 0, policy_version 29592 (0.0008) -[2023-10-09 01:13:33,975][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 60588032. Throughput: 0: 1692.2, 1: 1682.6. Samples: 15159390. Policy #0 lag: (min: 13.0, avg: 22.3, max: 45.0) -[2023-10-09 01:13:33,976][87372] Avg episode reward: [(0, '5.810'), (1, '5.920')] -[2023-10-09 01:13:36,718][88327] Updated weights for policy 1, policy_version 29610 (0.0007) -[2023-10-09 01:13:37,090][88327] Updated weights for policy 1, policy_version 29620 (0.0008) -[2023-10-09 01:13:37,448][88327] Updated weights for policy 1, policy_version 29630 (0.0010) -[2023-10-09 01:13:37,635][88326] Updated weights for policy 0, policy_version 29602 (0.0008) -[2023-10-09 01:13:38,028][88326] Updated weights for policy 0, policy_version 29612 (0.0009) -[2023-10-09 01:13:38,393][88326] Updated weights for policy 0, policy_version 29622 (0.0010) -[2023-10-09 01:13:38,766][88326] Updated weights for policy 0, policy_version 29632 (0.0008) -[2023-10-09 01:13:38,974][87372] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 60686336. Throughput: 0: 1704.4, 1: 1707.7. Samples: 15170322. Policy #0 lag: (min: 13.0, avg: 22.3, max: 45.0) -[2023-10-09 01:13:38,975][87372] Avg episode reward: [(0, '5.670'), (1, '5.550')] -[2023-10-09 01:13:41,632][88327] Updated weights for policy 1, policy_version 29640 (0.0011) -[2023-10-09 01:13:41,991][88327] Updated weights for policy 1, policy_version 29650 (0.0007) -[2023-10-09 01:13:42,361][88327] Updated weights for policy 1, policy_version 29660 (0.0007) -[2023-10-09 01:13:42,859][88326] Updated weights for policy 0, policy_version 29642 (0.0011) -[2023-10-09 01:13:43,230][88326] Updated weights for policy 0, policy_version 29652 (0.0010) -[2023-10-09 01:13:43,603][88326] Updated weights for policy 0, policy_version 29662 (0.0009) -[2023-10-09 01:13:43,974][87372] Fps is (10 sec: 16384.6, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 60751872. Throughput: 0: 1700.5, 1: 1693.1. Samples: 15190438. Policy #0 lag: (min: 13.0, avg: 22.3, max: 45.0) -[2023-10-09 01:13:43,975][87372] Avg episode reward: [(0, '5.840'), (1, '5.860')] -[2023-10-09 01:13:46,327][88327] Updated weights for policy 1, policy_version 29670 (0.0010) -[2023-10-09 01:13:46,694][88327] Updated weights for policy 1, policy_version 29680 (0.0008) -[2023-10-09 01:13:47,060][88327] Updated weights for policy 1, policy_version 29690 (0.0008) -[2023-10-09 01:13:47,546][88326] Updated weights for policy 0, policy_version 29672 (0.0010) -[2023-10-09 01:13:47,923][88326] Updated weights for policy 0, policy_version 29682 (0.0011) -[2023-10-09 01:13:48,283][88326] Updated weights for policy 0, policy_version 29692 (0.0007) -[2023-10-09 01:13:48,974][87372] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 60817408. Throughput: 0: 1681.3, 1: 1693.2. Samples: 15210084. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-09 01:13:48,975][87372] Avg episode reward: [(0, '5.910'), (1, '5.500')] -[2023-10-09 01:13:50,925][88327] Updated weights for policy 1, policy_version 29700 (0.0008) -[2023-10-09 01:13:51,301][88327] Updated weights for policy 1, policy_version 29710 (0.0009) -[2023-10-09 01:13:51,664][88327] Updated weights for policy 1, policy_version 29720 (0.0010) -[2023-10-09 01:13:52,334][88326] Updated weights for policy 0, policy_version 29702 (0.0007) -[2023-10-09 01:13:52,700][88326] Updated weights for policy 0, policy_version 29712 (0.0007) -[2023-10-09 01:13:53,069][88326] Updated weights for policy 0, policy_version 29722 (0.0008) -[2023-10-09 01:13:53,974][87372] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 60882944. Throughput: 0: 1704.1, 1: 1697.5. Samples: 15221206. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-09 01:13:53,975][87372] Avg episode reward: [(0, '5.830'), (1, '5.760')] -[2023-10-09 01:13:55,699][88327] Updated weights for policy 1, policy_version 29730 (0.0008) -[2023-10-09 01:13:56,072][88327] Updated weights for policy 1, policy_version 29740 (0.0010) -[2023-10-09 01:13:56,430][88327] Updated weights for policy 1, policy_version 29750 (0.0008) -[2023-10-09 01:13:56,798][88327] Updated weights for policy 1, policy_version 29760 (0.0009) -[2023-10-09 01:13:57,141][88326] Updated weights for policy 0, policy_version 29732 (0.0012) -[2023-10-09 01:13:57,514][88326] Updated weights for policy 0, policy_version 29742 (0.0010) -[2023-10-09 01:13:57,891][88326] Updated weights for policy 0, policy_version 29752 (0.0010) -[2023-10-09 01:13:58,974][87372] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 60948480. Throughput: 0: 1699.1, 1: 1681.1. Samples: 15240958. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-09 01:13:58,975][87372] Avg episode reward: [(0, '6.210'), (1, '6.050')] -[2023-10-09 01:14:00,944][88327] Updated weights for policy 1, policy_version 29770 (0.0011) -[2023-10-09 01:14:01,319][88327] Updated weights for policy 1, policy_version 29780 (0.0011) -[2023-10-09 01:14:01,687][88327] Updated weights for policy 1, policy_version 29790 (0.0010) -[2023-10-09 01:14:01,989][88326] Updated weights for policy 0, policy_version 29762 (0.0009) -[2023-10-09 01:14:02,364][88326] Updated weights for policy 0, policy_version 29772 (0.0008) -[2023-10-09 01:14:02,744][88326] Updated weights for policy 0, policy_version 29782 (0.0008) -[2023-10-09 01:14:03,110][88326] Updated weights for policy 0, policy_version 29792 (0.0008) -[2023-10-09 01:14:03,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 61014016. Throughput: 0: 1668.8, 1: 1703.2. Samples: 15260816. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-09 01:14:03,975][87372] Avg episode reward: [(0, '5.670'), (1, '5.450')] -[2023-10-09 01:14:05,754][88327] Updated weights for policy 1, policy_version 29800 (0.0008) -[2023-10-09 01:14:06,130][88327] Updated weights for policy 1, policy_version 29810 (0.0010) -[2023-10-09 01:14:06,495][88327] Updated weights for policy 1, policy_version 29820 (0.0008) -[2023-10-09 01:14:07,077][88326] Updated weights for policy 0, policy_version 29802 (0.0009) -[2023-10-09 01:14:07,443][88326] Updated weights for policy 0, policy_version 29812 (0.0007) -[2023-10-09 01:14:07,825][88326] Updated weights for policy 0, policy_version 29822 (0.0009) -[2023-10-09 01:14:08,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 61079552. Throughput: 0: 1698.1, 1: 1691.8. Samples: 15271844. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-09 01:14:08,975][87372] Avg episode reward: [(0, '5.680'), (1, '5.840')] -[2023-10-09 01:14:10,528][88327] Updated weights for policy 1, policy_version 29830 (0.0009) -[2023-10-09 01:14:10,897][88327] Updated weights for policy 1, policy_version 29840 (0.0010) -[2023-10-09 01:14:11,266][88327] Updated weights for policy 1, policy_version 29850 (0.0008) -[2023-10-09 01:14:11,844][88326] Updated weights for policy 0, policy_version 29832 (0.0008) -[2023-10-09 01:14:12,218][88326] Updated weights for policy 0, policy_version 29842 (0.0008) -[2023-10-09 01:14:12,584][88326] Updated weights for policy 0, policy_version 29852 (0.0007) -[2023-10-09 01:14:13,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 61145088. Throughput: 0: 1683.2, 1: 1683.9. Samples: 15291258. Policy #0 lag: (min: 6.0, avg: 12.3, max: 38.0) -[2023-10-09 01:14:13,975][87372] Avg episode reward: [(0, '5.310'), (1, '5.690')] -[2023-10-09 01:14:15,271][88327] Updated weights for policy 1, policy_version 29860 (0.0008) -[2023-10-09 01:14:15,665][88327] Updated weights for policy 1, policy_version 29870 (0.0009) -[2023-10-09 01:14:16,037][88327] Updated weights for policy 1, policy_version 29880 (0.0007) -[2023-10-09 01:14:16,460][88326] Updated weights for policy 0, policy_version 29862 (0.0008) -[2023-10-09 01:14:16,837][88326] Updated weights for policy 0, policy_version 29872 (0.0009) -[2023-10-09 01:14:17,212][88326] Updated weights for policy 0, policy_version 29882 (0.0007) -[2023-10-09 01:14:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 61210624. Throughput: 0: 1682.1, 1: 1699.9. Samples: 15311576. Policy #0 lag: (min: 6.0, avg: 12.3, max: 38.0) -[2023-10-09 01:14:18,975][87372] Avg episode reward: [(0, '5.230'), (1, '5.180')] -[2023-10-09 01:14:20,055][88327] Updated weights for policy 1, policy_version 29890 (0.0010) -[2023-10-09 01:14:20,422][88327] Updated weights for policy 1, policy_version 29900 (0.0010) -[2023-10-09 01:14:20,793][88327] Updated weights for policy 1, policy_version 29910 (0.0009) -[2023-10-09 01:14:21,158][88327] Updated weights for policy 1, policy_version 29920 (0.0009) -[2023-10-09 01:14:21,161][88326] Updated weights for policy 0, policy_version 29892 (0.0008) -[2023-10-09 01:14:21,530][88326] Updated weights for policy 0, policy_version 29902 (0.0009) -[2023-10-09 01:14:21,903][88326] Updated weights for policy 0, policy_version 29912 (0.0009) -[2023-10-09 01:14:23,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 61276160. Throughput: 0: 1693.2, 1: 1670.4. Samples: 15321688. Policy #0 lag: (min: 6.0, avg: 12.3, max: 38.0) -[2023-10-09 01:14:23,975][87372] Avg episode reward: [(0, '5.480'), (1, '5.220')] -[2023-10-09 01:14:25,139][88327] Updated weights for policy 1, policy_version 29930 (0.0007) -[2023-10-09 01:14:25,504][88327] Updated weights for policy 1, policy_version 29940 (0.0008) -[2023-10-09 01:14:25,867][88327] Updated weights for policy 1, policy_version 29950 (0.0010) -[2023-10-09 01:14:26,021][88326] Updated weights for policy 0, policy_version 29922 (0.0009) -[2023-10-09 01:14:26,430][88326] Updated weights for policy 0, policy_version 29932 (0.0010) -[2023-10-09 01:14:26,804][88326] Updated weights for policy 0, policy_version 29942 (0.0011) -[2023-10-09 01:14:27,178][88326] Updated weights for policy 0, policy_version 29952 (0.0008) -[2023-10-09 01:14:28,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 61341696. Throughput: 0: 1669.4, 1: 1686.0. Samples: 15341428. Policy #0 lag: (min: 6.0, avg: 12.3, max: 38.0) -[2023-10-09 01:14:28,975][87372] Avg episode reward: [(0, '5.330'), (1, '5.220')] -[2023-10-09 01:14:29,985][88327] Updated weights for policy 1, policy_version 29960 (0.0009) -[2023-10-09 01:14:30,348][88327] Updated weights for policy 1, policy_version 29970 (0.0009) -[2023-10-09 01:14:30,721][88327] Updated weights for policy 1, policy_version 29980 (0.0009) -[2023-10-09 01:14:31,403][88326] Updated weights for policy 0, policy_version 29962 (0.0010) -[2023-10-09 01:14:31,764][88326] Updated weights for policy 0, policy_version 29972 (0.0010) -[2023-10-09 01:14:32,136][88326] Updated weights for policy 0, policy_version 29982 (0.0008) -[2023-10-09 01:14:33,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 61407232. Throughput: 0: 1687.1, 1: 1689.6. Samples: 15362034. Policy #0 lag: (min: 6.0, avg: 12.3, max: 38.0) -[2023-10-09 01:14:33,975][87372] Avg episode reward: [(0, '5.700'), (1, '5.370')] -[2023-10-09 01:14:33,985][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000029984_30703616.pth... -[2023-10-09 01:14:33,985][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000029984_30703616.pth... -[2023-10-09 01:14:34,016][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000028416_29097984.pth -[2023-10-09 01:14:34,025][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000028416_29097984.pth -[2023-10-09 01:14:34,908][88327] Updated weights for policy 1, policy_version 29990 (0.0008) -[2023-10-09 01:14:35,260][88327] Updated weights for policy 1, policy_version 30000 (0.0010) -[2023-10-09 01:14:35,627][88327] Updated weights for policy 1, policy_version 30010 (0.0009) -[2023-10-09 01:14:36,001][88326] Updated weights for policy 0, policy_version 29992 (0.0008) -[2023-10-09 01:14:36,380][88326] Updated weights for policy 0, policy_version 30002 (0.0007) -[2023-10-09 01:14:36,749][88326] Updated weights for policy 0, policy_version 30012 (0.0007) -[2023-10-09 01:14:38,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 61472768. Throughput: 0: 1682.4, 1: 1668.4. Samples: 15371988. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-09 01:14:38,974][87372] Avg episode reward: [(0, '5.510'), (1, '5.450')] -[2023-10-09 01:14:39,506][88327] Updated weights for policy 1, policy_version 30020 (0.0008) -[2023-10-09 01:14:39,878][88327] Updated weights for policy 1, policy_version 30030 (0.0009) -[2023-10-09 01:14:40,242][88327] Updated weights for policy 1, policy_version 30040 (0.0009) -[2023-10-09 01:14:40,846][88326] Updated weights for policy 0, policy_version 30022 (0.0009) -[2023-10-09 01:14:41,216][88326] Updated weights for policy 0, policy_version 30032 (0.0010) -[2023-10-09 01:14:41,587][88326] Updated weights for policy 0, policy_version 30042 (0.0008) -[2023-10-09 01:14:43,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 61538304. Throughput: 0: 1675.3, 1: 1693.1. Samples: 15392534. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-09 01:14:43,974][87372] Avg episode reward: [(0, '5.370'), (1, '5.720')] -[2023-10-09 01:14:44,206][88327] Updated weights for policy 1, policy_version 30050 (0.0009) -[2023-10-09 01:14:44,568][88327] Updated weights for policy 1, policy_version 30060 (0.0008) -[2023-10-09 01:14:44,935][88327] Updated weights for policy 1, policy_version 30070 (0.0008) -[2023-10-09 01:14:45,303][88327] Updated weights for policy 1, policy_version 30080 (0.0008) -[2023-10-09 01:14:45,846][88326] Updated weights for policy 0, policy_version 30052 (0.0008) -[2023-10-09 01:14:46,209][88326] Updated weights for policy 0, policy_version 30062 (0.0010) -[2023-10-09 01:14:46,584][88326] Updated weights for policy 0, policy_version 30072 (0.0007) -[2023-10-09 01:14:48,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 61603840. Throughput: 0: 1701.4, 1: 1693.4. Samples: 15413582. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-09 01:14:48,975][87372] Avg episode reward: [(0, '5.810'), (1, '6.030')] -[2023-10-09 01:14:49,171][88327] Updated weights for policy 1, policy_version 30090 (0.0010) -[2023-10-09 01:14:49,532][88327] Updated weights for policy 1, policy_version 30100 (0.0011) -[2023-10-09 01:14:49,903][88327] Updated weights for policy 1, policy_version 30110 (0.0010) -[2023-10-09 01:14:50,519][88326] Updated weights for policy 0, policy_version 30082 (0.0007) -[2023-10-09 01:14:50,886][88326] Updated weights for policy 0, policy_version 30092 (0.0007) -[2023-10-09 01:14:51,252][88326] Updated weights for policy 0, policy_version 30102 (0.0008) -[2023-10-09 01:14:51,613][88326] Updated weights for policy 0, policy_version 30112 (0.0008) -[2023-10-09 01:14:53,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 61669376. Throughput: 0: 1688.9, 1: 1679.8. Samples: 15423434. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-09 01:14:53,975][87372] Avg episode reward: [(0, '5.670'), (1, '5.910')] -[2023-10-09 01:14:54,060][88327] Updated weights for policy 1, policy_version 30120 (0.0008) -[2023-10-09 01:14:54,423][88327] Updated weights for policy 1, policy_version 30130 (0.0007) -[2023-10-09 01:14:54,778][88327] Updated weights for policy 1, policy_version 30140 (0.0007) -[2023-10-09 01:14:55,483][88326] Updated weights for policy 0, policy_version 30122 (0.0009) -[2023-10-09 01:14:55,854][88326] Updated weights for policy 0, policy_version 30132 (0.0009) -[2023-10-09 01:14:56,225][88326] Updated weights for policy 0, policy_version 30142 (0.0008) -[2023-10-09 01:14:58,893][88327] Updated weights for policy 1, policy_version 30150 (0.0008) -[2023-10-09 01:14:58,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 61734912. Throughput: 0: 1697.7, 1: 1701.6. Samples: 15444226. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-09 01:14:58,975][87372] Avg episode reward: [(0, '6.230'), (1, '5.650')] -[2023-10-09 01:14:59,260][88327] Updated weights for policy 1, policy_version 30160 (0.0008) -[2023-10-09 01:14:59,635][88327] Updated weights for policy 1, policy_version 30170 (0.0008) -[2023-10-09 01:15:00,255][88326] Updated weights for policy 0, policy_version 30152 (0.0009) -[2023-10-09 01:15:00,627][88326] Updated weights for policy 0, policy_version 30162 (0.0007) -[2023-10-09 01:15:00,992][88326] Updated weights for policy 0, policy_version 30172 (0.0008) -[2023-10-09 01:15:03,808][88327] Updated weights for policy 1, policy_version 30180 (0.0009) -[2023-10-09 01:15:03,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 61800448. Throughput: 0: 1706.2, 1: 1701.3. Samples: 15464912. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-09 01:15:03,975][87372] Avg episode reward: [(0, '5.810'), (1, '5.640')] -[2023-10-09 01:15:04,206][88327] Updated weights for policy 1, policy_version 30190 (0.0010) -[2023-10-09 01:15:04,576][88327] Updated weights for policy 1, policy_version 30200 (0.0010) -[2023-10-09 01:15:04,992][88326] Updated weights for policy 0, policy_version 30182 (0.0008) -[2023-10-09 01:15:05,358][88326] Updated weights for policy 0, policy_version 30192 (0.0009) -[2023-10-09 01:15:05,729][88326] Updated weights for policy 0, policy_version 30202 (0.0011) -[2023-10-09 01:15:08,553][88327] Updated weights for policy 1, policy_version 30210 (0.0007) -[2023-10-09 01:15:08,921][88327] Updated weights for policy 1, policy_version 30220 (0.0009) -[2023-10-09 01:15:08,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 61865984. Throughput: 0: 1686.4, 1: 1699.0. Samples: 15474030. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-09 01:15:08,975][87372] Avg episode reward: [(0, '5.810'), (1, '5.640')] -[2023-10-09 01:15:09,286][88327] Updated weights for policy 1, policy_version 30230 (0.0009) -[2023-10-09 01:15:09,650][88327] Updated weights for policy 1, policy_version 30240 (0.0008) -[2023-10-09 01:15:09,731][88326] Updated weights for policy 0, policy_version 30212 (0.0007) -[2023-10-09 01:15:10,097][88326] Updated weights for policy 0, policy_version 30222 (0.0007) -[2023-10-09 01:15:10,464][88326] Updated weights for policy 0, policy_version 30232 (0.0007) -[2023-10-09 01:15:13,870][88327] Updated weights for policy 1, policy_version 30250 (0.0011) -[2023-10-09 01:15:13,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 61931520. Throughput: 0: 1712.9, 1: 1698.4. Samples: 15494940. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-09 01:15:13,975][87372] Avg episode reward: [(0, '5.900'), (1, '5.290')] -[2023-10-09 01:15:14,244][88327] Updated weights for policy 1, policy_version 30260 (0.0008) -[2023-10-09 01:15:14,418][88326] Updated weights for policy 0, policy_version 30242 (0.0007) -[2023-10-09 01:15:14,610][88327] Updated weights for policy 1, policy_version 30270 (0.0008) -[2023-10-09 01:15:14,811][88326] Updated weights for policy 0, policy_version 30252 (0.0007) -[2023-10-09 01:15:15,177][88326] Updated weights for policy 0, policy_version 30262 (0.0007) -[2023-10-09 01:15:15,546][88326] Updated weights for policy 0, policy_version 30272 (0.0008) -[2023-10-09 01:15:18,702][88327] Updated weights for policy 1, policy_version 30280 (0.0010) -[2023-10-09 01:15:18,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 61997056. Throughput: 0: 1717.3, 1: 1699.2. Samples: 15515780. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-09 01:15:18,975][87372] Avg episode reward: [(0, '5.730'), (1, '5.640')] -[2023-10-09 01:15:19,073][88327] Updated weights for policy 1, policy_version 30290 (0.0010) -[2023-10-09 01:15:19,433][88327] Updated weights for policy 1, policy_version 30300 (0.0009) -[2023-10-09 01:15:19,450][88326] Updated weights for policy 0, policy_version 30282 (0.0008) -[2023-10-09 01:15:19,820][88326] Updated weights for policy 0, policy_version 30292 (0.0008) -[2023-10-09 01:15:20,184][88326] Updated weights for policy 0, policy_version 30302 (0.0008) -[2023-10-09 01:15:23,350][88327] Updated weights for policy 1, policy_version 30310 (0.0010) -[2023-10-09 01:15:23,718][88327] Updated weights for policy 1, policy_version 30320 (0.0010) -[2023-10-09 01:15:23,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 62062592. Throughput: 0: 1697.6, 1: 1702.5. Samples: 15524996. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-09 01:15:23,975][87372] Avg episode reward: [(0, '5.790'), (1, '6.150')] -[2023-10-09 01:15:24,079][88327] Updated weights for policy 1, policy_version 30330 (0.0007) -[2023-10-09 01:15:24,307][88326] Updated weights for policy 0, policy_version 30312 (0.0008) -[2023-10-09 01:15:24,672][88326] Updated weights for policy 0, policy_version 30322 (0.0008) -[2023-10-09 01:15:25,048][88326] Updated weights for policy 0, policy_version 30332 (0.0008) -[2023-10-09 01:15:28,169][88327] Updated weights for policy 1, policy_version 30340 (0.0008) -[2023-10-09 01:15:28,532][88327] Updated weights for policy 1, policy_version 30350 (0.0010) -[2023-10-09 01:15:28,896][88327] Updated weights for policy 1, policy_version 30360 (0.0010) -[2023-10-09 01:15:28,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 62128128. Throughput: 0: 1708.7, 1: 1697.9. Samples: 15545828. Policy #0 lag: (min: 5.0, avg: 6.2, max: 29.0) -[2023-10-09 01:15:28,974][87372] Avg episode reward: [(0, '5.270'), (1, '5.500')] -[2023-10-09 01:15:29,086][88326] Updated weights for policy 0, policy_version 30342 (0.0009) -[2023-10-09 01:15:29,451][88326] Updated weights for policy 0, policy_version 30352 (0.0007) -[2023-10-09 01:15:29,825][88326] Updated weights for policy 0, policy_version 30362 (0.0007) -[2023-10-09 01:15:32,872][88327] Updated weights for policy 1, policy_version 30370 (0.0009) -[2023-10-09 01:15:33,247][88327] Updated weights for policy 1, policy_version 30380 (0.0009) -[2023-10-09 01:15:33,606][88327] Updated weights for policy 1, policy_version 30390 (0.0009) -[2023-10-09 01:15:33,957][88326] Updated weights for policy 0, policy_version 30372 (0.0008) -[2023-10-09 01:15:33,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 62193664. Throughput: 0: 1704.3, 1: 1685.9. Samples: 15566138. Policy #0 lag: (min: 5.0, avg: 6.2, max: 29.0) -[2023-10-09 01:15:33,975][87372] Avg episode reward: [(0, '5.390'), (1, '5.750')] -[2023-10-09 01:15:33,983][88327] Updated weights for policy 1, policy_version 30400 (0.0008) -[2023-10-09 01:15:34,334][88326] Updated weights for policy 0, policy_version 30382 (0.0010) -[2023-10-09 01:15:34,704][88326] Updated weights for policy 0, policy_version 30392 (0.0009) -[2023-10-09 01:15:37,876][88327] Updated weights for policy 1, policy_version 30410 (0.0009) -[2023-10-09 01:15:38,237][88327] Updated weights for policy 1, policy_version 30420 (0.0009) -[2023-10-09 01:15:38,598][88327] Updated weights for policy 1, policy_version 30430 (0.0008) -[2023-10-09 01:15:38,806][88326] Updated weights for policy 0, policy_version 30402 (0.0008) -[2023-10-09 01:15:38,974][87372] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 62291968. Throughput: 0: 1687.7, 1: 1696.0. Samples: 15575702. Policy #0 lag: (min: 5.0, avg: 6.2, max: 29.0) -[2023-10-09 01:15:38,975][87372] Avg episode reward: [(0, '5.340'), (1, '5.910')] -[2023-10-09 01:15:39,181][88326] Updated weights for policy 0, policy_version 30412 (0.0008) -[2023-10-09 01:15:39,543][88326] Updated weights for policy 0, policy_version 30422 (0.0008) -[2023-10-09 01:15:39,911][88326] Updated weights for policy 0, policy_version 30432 (0.0007) -[2023-10-09 01:15:42,889][88327] Updated weights for policy 1, policy_version 30440 (0.0007) -[2023-10-09 01:15:43,257][88327] Updated weights for policy 1, policy_version 30450 (0.0007) -[2023-10-09 01:15:43,632][88327] Updated weights for policy 1, policy_version 30460 (0.0008) -[2023-10-09 01:15:43,935][88326] Updated weights for policy 0, policy_version 30442 (0.0008) -[2023-10-09 01:15:43,974][87372] Fps is (10 sec: 16384.2, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 62357504. Throughput: 0: 1693.2, 1: 1687.9. Samples: 15596376. Policy #0 lag: (min: 5.0, avg: 6.2, max: 29.0) -[2023-10-09 01:15:43,974][87372] Avg episode reward: [(0, '5.800'), (1, '5.140')] -[2023-10-09 01:15:44,310][88326] Updated weights for policy 0, policy_version 30452 (0.0008) -[2023-10-09 01:15:44,685][88326] Updated weights for policy 0, policy_version 30462 (0.0008) -[2023-10-09 01:15:47,686][88327] Updated weights for policy 1, policy_version 30470 (0.0010) -[2023-10-09 01:15:48,050][88327] Updated weights for policy 1, policy_version 30480 (0.0009) -[2023-10-09 01:15:48,421][88327] Updated weights for policy 1, policy_version 30490 (0.0007) -[2023-10-09 01:15:48,785][88326] Updated weights for policy 0, policy_version 30472 (0.0008) -[2023-10-09 01:15:48,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 62423040. Throughput: 0: 1691.6, 1: 1677.0. Samples: 15616498. Policy #0 lag: (min: 5.0, avg: 6.2, max: 29.0) -[2023-10-09 01:15:48,975][87372] Avg episode reward: [(0, '5.500'), (1, '5.500')] -[2023-10-09 01:15:49,154][88326] Updated weights for policy 0, policy_version 30482 (0.0007) -[2023-10-09 01:15:49,521][88326] Updated weights for policy 0, policy_version 30492 (0.0007) -[2023-10-09 01:15:52,454][88327] Updated weights for policy 1, policy_version 30500 (0.0008) -[2023-10-09 01:15:52,810][88327] Updated weights for policy 1, policy_version 30510 (0.0009) -[2023-10-09 01:15:53,168][88327] Updated weights for policy 1, policy_version 30520 (0.0009) -[2023-10-09 01:15:53,436][88326] Updated weights for policy 0, policy_version 30502 (0.0009) -[2023-10-09 01:15:53,808][88326] Updated weights for policy 0, policy_version 30512 (0.0009) -[2023-10-09 01:15:53,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 62488576. Throughput: 0: 1685.6, 1: 1696.7. Samples: 15626234. Policy #0 lag: (min: 30.0, avg: 38.0, max: 62.0) -[2023-10-09 01:15:53,975][87372] Avg episode reward: [(0, '5.680'), (1, '5.720')] -[2023-10-09 01:15:54,167][88326] Updated weights for policy 0, policy_version 30522 (0.0010) -[2023-10-09 01:15:57,095][88327] Updated weights for policy 1, policy_version 30530 (0.0007) -[2023-10-09 01:15:57,475][88327] Updated weights for policy 1, policy_version 30540 (0.0009) -[2023-10-09 01:15:57,840][88327] Updated weights for policy 1, policy_version 30550 (0.0008) -[2023-10-09 01:15:58,179][88326] Updated weights for policy 0, policy_version 30532 (0.0008) -[2023-10-09 01:15:58,202][88327] Updated weights for policy 1, policy_version 30560 (0.0009) -[2023-10-09 01:15:58,551][88326] Updated weights for policy 0, policy_version 30542 (0.0008) -[2023-10-09 01:15:58,927][88326] Updated weights for policy 0, policy_version 30552 (0.0007) -[2023-10-09 01:15:58,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 62554112. Throughput: 0: 1689.3, 1: 1699.5. Samples: 15647440. Policy #0 lag: (min: 30.0, avg: 38.0, max: 62.0) -[2023-10-09 01:15:58,975][87372] Avg episode reward: [(0, '5.470'), (1, '5.540')] -[2023-10-09 01:16:02,159][88327] Updated weights for policy 1, policy_version 30570 (0.0011) -[2023-10-09 01:16:02,524][88327] Updated weights for policy 1, policy_version 30580 (0.0009) -[2023-10-09 01:16:02,896][88327] Updated weights for policy 1, policy_version 30590 (0.0008) -[2023-10-09 01:16:03,096][88326] Updated weights for policy 0, policy_version 30562 (0.0009) -[2023-10-09 01:16:03,491][88326] Updated weights for policy 0, policy_version 30572 (0.0008) -[2023-10-09 01:16:03,868][88326] Updated weights for policy 0, policy_version 30582 (0.0008) -[2023-10-09 01:16:03,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 62619648. Throughput: 0: 1681.2, 1: 1677.6. Samples: 15666928. Policy #0 lag: (min: 30.0, avg: 38.0, max: 62.0) -[2023-10-09 01:16:03,975][87372] Avg episode reward: [(0, '5.500'), (1, '5.550')] -[2023-10-09 01:16:04,244][88326] Updated weights for policy 0, policy_version 30592 (0.0008) -[2023-10-09 01:16:06,965][88327] Updated weights for policy 1, policy_version 30600 (0.0007) -[2023-10-09 01:16:07,335][88327] Updated weights for policy 1, policy_version 30610 (0.0009) -[2023-10-09 01:16:07,704][88327] Updated weights for policy 1, policy_version 30620 (0.0008) -[2023-10-09 01:16:08,289][88326] Updated weights for policy 0, policy_version 30602 (0.0009) -[2023-10-09 01:16:08,662][88326] Updated weights for policy 0, policy_version 30612 (0.0009) -[2023-10-09 01:16:08,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 62685184. Throughput: 0: 1684.5, 1: 1703.1. Samples: 15677438. Policy #0 lag: (min: 30.0, avg: 38.0, max: 62.0) -[2023-10-09 01:16:08,975][87372] Avg episode reward: [(0, '5.810'), (1, '5.750')] -[2023-10-09 01:16:09,027][88326] Updated weights for policy 0, policy_version 30622 (0.0007) -[2023-10-09 01:16:11,614][88327] Updated weights for policy 1, policy_version 30630 (0.0008) -[2023-10-09 01:16:11,987][88327] Updated weights for policy 1, policy_version 30640 (0.0009) -[2023-10-09 01:16:12,360][88327] Updated weights for policy 1, policy_version 30650 (0.0007) -[2023-10-09 01:16:13,167][88326] Updated weights for policy 0, policy_version 30632 (0.0008) -[2023-10-09 01:16:13,532][88326] Updated weights for policy 0, policy_version 30642 (0.0009) -[2023-10-09 01:16:13,910][88326] Updated weights for policy 0, policy_version 30652 (0.0007) -[2023-10-09 01:16:13,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 62750720. Throughput: 0: 1690.4, 1: 1684.2. Samples: 15697684. Policy #0 lag: (min: 30.0, avg: 38.0, max: 62.0) -[2023-10-09 01:16:13,975][87372] Avg episode reward: [(0, '5.710'), (1, '5.550')] -[2023-10-09 01:16:16,365][88327] Updated weights for policy 1, policy_version 30660 (0.0008) -[2023-10-09 01:16:16,729][88327] Updated weights for policy 1, policy_version 30670 (0.0009) -[2023-10-09 01:16:17,097][88327] Updated weights for policy 1, policy_version 30680 (0.0008) -[2023-10-09 01:16:17,861][88326] Updated weights for policy 0, policy_version 30662 (0.0007) -[2023-10-09 01:16:18,232][88326] Updated weights for policy 0, policy_version 30672 (0.0007) -[2023-10-09 01:16:18,612][88326] Updated weights for policy 0, policy_version 30682 (0.0007) -[2023-10-09 01:16:18,974][87372] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 62849024. Throughput: 0: 1684.5, 1: 1683.6. Samples: 15717702. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:16:18,975][87372] Avg episode reward: [(0, '5.840'), (1, '5.540')] -[2023-10-09 01:16:21,297][88327] Updated weights for policy 1, policy_version 30690 (0.0008) -[2023-10-09 01:16:21,662][88327] Updated weights for policy 1, policy_version 30700 (0.0009) -[2023-10-09 01:16:22,026][88327] Updated weights for policy 1, policy_version 30710 (0.0009) -[2023-10-09 01:16:22,389][88327] Updated weights for policy 1, policy_version 30720 (0.0008) -[2023-10-09 01:16:22,542][88326] Updated weights for policy 0, policy_version 30692 (0.0007) -[2023-10-09 01:16:22,912][88326] Updated weights for policy 0, policy_version 30702 (0.0007) -[2023-10-09 01:16:23,280][88326] Updated weights for policy 0, policy_version 30712 (0.0007) -[2023-10-09 01:16:23,974][87372] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 62914560. Throughput: 0: 1696.8, 1: 1700.6. Samples: 15728584. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:16:23,975][87372] Avg episode reward: [(0, '5.600'), (1, '6.150')] -[2023-10-09 01:16:26,359][88327] Updated weights for policy 1, policy_version 30730 (0.0009) -[2023-10-09 01:16:26,716][88327] Updated weights for policy 1, policy_version 30740 (0.0009) -[2023-10-09 01:16:27,081][88327] Updated weights for policy 1, policy_version 30750 (0.0011) -[2023-10-09 01:16:27,353][88326] Updated weights for policy 0, policy_version 30722 (0.0008) -[2023-10-09 01:16:27,729][88326] Updated weights for policy 0, policy_version 30732 (0.0008) -[2023-10-09 01:16:28,097][88326] Updated weights for policy 0, policy_version 30742 (0.0009) -[2023-10-09 01:16:28,467][88326] Updated weights for policy 0, policy_version 30752 (0.0007) -[2023-10-09 01:16:28,974][87372] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 62980096. Throughput: 0: 1700.0, 1: 1675.0. Samples: 15748250. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:16:28,976][87372] Avg episode reward: [(0, '5.700'), (1, '5.990')] -[2023-10-09 01:16:31,167][88327] Updated weights for policy 1, policy_version 30760 (0.0009) -[2023-10-09 01:16:31,527][88327] Updated weights for policy 1, policy_version 30770 (0.0008) -[2023-10-09 01:16:31,888][88327] Updated weights for policy 1, policy_version 30780 (0.0009) -[2023-10-09 01:16:32,455][88326] Updated weights for policy 0, policy_version 30762 (0.0008) -[2023-10-09 01:16:32,829][88326] Updated weights for policy 0, policy_version 30772 (0.0011) -[2023-10-09 01:16:33,186][88326] Updated weights for policy 0, policy_version 30782 (0.0008) -[2023-10-09 01:16:33,974][87372] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 63045632. Throughput: 0: 1678.9, 1: 1689.4. Samples: 15768070. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:16:33,975][87372] Avg episode reward: [(0, '5.770'), (1, '6.290')] -[2023-10-09 01:16:33,987][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000030784_31522816.pth... -[2023-10-09 01:16:33,987][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000030784_31522816.pth... -[2023-10-09 01:16:34,028][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000029184_29884416.pth -[2023-10-09 01:16:34,030][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000029216_29917184.pth -[2023-10-09 01:16:35,956][88327] Updated weights for policy 1, policy_version 30790 (0.0008) -[2023-10-09 01:16:36,312][88327] Updated weights for policy 1, policy_version 30800 (0.0007) -[2023-10-09 01:16:36,688][88327] Updated weights for policy 1, policy_version 30810 (0.0007) -[2023-10-09 01:16:37,116][88326] Updated weights for policy 0, policy_version 30792 (0.0007) -[2023-10-09 01:16:37,481][88326] Updated weights for policy 0, policy_version 30802 (0.0007) -[2023-10-09 01:16:37,854][88326] Updated weights for policy 0, policy_version 30812 (0.0007) -[2023-10-09 01:16:38,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 63111168. Throughput: 0: 1708.5, 1: 1691.2. Samples: 15779222. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-09 01:16:38,975][87372] Avg episode reward: [(0, '5.730'), (1, '6.230')] -[2023-10-09 01:16:40,686][88327] Updated weights for policy 1, policy_version 30820 (0.0010) -[2023-10-09 01:16:41,053][88327] Updated weights for policy 1, policy_version 30830 (0.0009) -[2023-10-09 01:16:41,423][88327] Updated weights for policy 1, policy_version 30840 (0.0009) -[2023-10-09 01:16:41,764][88326] Updated weights for policy 0, policy_version 30822 (0.0007) -[2023-10-09 01:16:42,129][88326] Updated weights for policy 0, policy_version 30832 (0.0009) -[2023-10-09 01:16:42,498][88326] Updated weights for policy 0, policy_version 30842 (0.0008) -[2023-10-09 01:16:43,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 63176704. Throughput: 0: 1687.9, 1: 1670.0. Samples: 15798546. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-09 01:16:43,975][87372] Avg episode reward: [(0, '5.740'), (1, '6.430')] -[2023-10-09 01:16:45,384][88327] Updated weights for policy 1, policy_version 30850 (0.0009) -[2023-10-09 01:16:45,747][88327] Updated weights for policy 1, policy_version 30860 (0.0008) -[2023-10-09 01:16:46,116][88327] Updated weights for policy 1, policy_version 30870 (0.0008) -[2023-10-09 01:16:46,480][88327] Updated weights for policy 1, policy_version 30880 (0.0009) -[2023-10-09 01:16:46,495][88326] Updated weights for policy 0, policy_version 30852 (0.0007) -[2023-10-09 01:16:46,861][88326] Updated weights for policy 0, policy_version 30862 (0.0007) -[2023-10-09 01:16:47,231][88326] Updated weights for policy 0, policy_version 30872 (0.0008) -[2023-10-09 01:16:48,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 63242240. Throughput: 0: 1680.9, 1: 1700.2. Samples: 15819078. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-09 01:16:48,975][87372] Avg episode reward: [(0, '6.720'), (1, '5.980')] -[2023-10-09 01:16:48,983][88088] Saving new best policy, reward=6.720! -[2023-10-09 01:16:50,460][88327] Updated weights for policy 1, policy_version 30890 (0.0009) -[2023-10-09 01:16:50,828][88327] Updated weights for policy 1, policy_version 30900 (0.0009) -[2023-10-09 01:16:51,195][88327] Updated weights for policy 1, policy_version 30910 (0.0007) -[2023-10-09 01:16:51,463][88326] Updated weights for policy 0, policy_version 30882 (0.0010) -[2023-10-09 01:16:51,881][88326] Updated weights for policy 0, policy_version 30892 (0.0009) -[2023-10-09 01:16:52,249][88326] Updated weights for policy 0, policy_version 30902 (0.0008) -[2023-10-09 01:16:52,612][88326] Updated weights for policy 0, policy_version 30912 (0.0009) -[2023-10-09 01:16:53,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 63307776. Throughput: 0: 1704.4, 1: 1672.8. Samples: 15829416. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-09 01:16:53,975][87372] Avg episode reward: [(0, '5.830'), (1, '5.830')] -[2023-10-09 01:16:55,109][88327] Updated weights for policy 1, policy_version 30920 (0.0009) -[2023-10-09 01:16:55,484][88327] Updated weights for policy 1, policy_version 30930 (0.0008) -[2023-10-09 01:16:55,843][88327] Updated weights for policy 1, policy_version 30940 (0.0008) -[2023-10-09 01:16:56,692][88326] Updated weights for policy 0, policy_version 30922 (0.0010) -[2023-10-09 01:16:57,060][88326] Updated weights for policy 0, policy_version 30932 (0.0010) -[2023-10-09 01:16:57,432][88326] Updated weights for policy 0, policy_version 30942 (0.0008) -[2023-10-09 01:16:58,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 63373312. Throughput: 0: 1675.7, 1: 1692.4. Samples: 15849252. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-09 01:16:58,975][87372] Avg episode reward: [(0, '5.800'), (1, '5.700')] -[2023-10-09 01:17:00,000][88327] Updated weights for policy 1, policy_version 30950 (0.0009) -[2023-10-09 01:17:00,363][88327] Updated weights for policy 1, policy_version 30960 (0.0011) -[2023-10-09 01:17:00,730][88327] Updated weights for policy 1, policy_version 30970 (0.0009) -[2023-10-09 01:17:01,569][88326] Updated weights for policy 0, policy_version 30952 (0.0007) -[2023-10-09 01:17:01,936][88326] Updated weights for policy 0, policy_version 30962 (0.0008) -[2023-10-09 01:17:02,303][88326] Updated weights for policy 0, policy_version 30972 (0.0010) -[2023-10-09 01:17:03,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 63438848. Throughput: 0: 1675.6, 1: 1706.6. Samples: 15869900. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-09 01:17:03,975][87372] Avg episode reward: [(0, '6.150'), (1, '5.700')] -[2023-10-09 01:17:04,630][88327] Updated weights for policy 1, policy_version 30980 (0.0008) -[2023-10-09 01:17:04,997][88327] Updated weights for policy 1, policy_version 30990 (0.0009) -[2023-10-09 01:17:05,361][88327] Updated weights for policy 1, policy_version 31000 (0.0010) -[2023-10-09 01:17:06,278][88326] Updated weights for policy 0, policy_version 30982 (0.0009) -[2023-10-09 01:17:06,653][88326] Updated weights for policy 0, policy_version 30992 (0.0008) -[2023-10-09 01:17:07,021][88326] Updated weights for policy 0, policy_version 31002 (0.0009) -[2023-10-09 01:17:08,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 63504384. Throughput: 0: 1691.8, 1: 1681.2. Samples: 15880368. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-09 01:17:08,974][87372] Avg episode reward: [(0, '5.300'), (1, '5.650')] -[2023-10-09 01:17:09,421][88327] Updated weights for policy 1, policy_version 31010 (0.0010) -[2023-10-09 01:17:09,786][88327] Updated weights for policy 1, policy_version 31020 (0.0009) -[2023-10-09 01:17:10,157][88327] Updated weights for policy 1, policy_version 31030 (0.0009) -[2023-10-09 01:17:10,523][88327] Updated weights for policy 1, policy_version 31040 (0.0009) -[2023-10-09 01:17:10,899][88326] Updated weights for policy 0, policy_version 31012 (0.0009) -[2023-10-09 01:17:11,258][88326] Updated weights for policy 0, policy_version 31022 (0.0010) -[2023-10-09 01:17:11,632][88326] Updated weights for policy 0, policy_version 31032 (0.0008) -[2023-10-09 01:17:13,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 63569920. Throughput: 0: 1669.3, 1: 1711.2. Samples: 15900374. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-09 01:17:13,975][87372] Avg episode reward: [(0, '5.340'), (1, '5.430')] -[2023-10-09 01:17:14,520][88327] Updated weights for policy 1, policy_version 31050 (0.0009) -[2023-10-09 01:17:14,889][88327] Updated weights for policy 1, policy_version 31060 (0.0011) -[2023-10-09 01:17:15,254][88327] Updated weights for policy 1, policy_version 31070 (0.0010) -[2023-10-09 01:17:15,713][88326] Updated weights for policy 0, policy_version 31042 (0.0010) -[2023-10-09 01:17:16,084][88326] Updated weights for policy 0, policy_version 31052 (0.0007) -[2023-10-09 01:17:16,457][88326] Updated weights for policy 0, policy_version 31062 (0.0010) -[2023-10-09 01:17:16,818][88326] Updated weights for policy 0, policy_version 31072 (0.0007) -[2023-10-09 01:17:18,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 63635456. Throughput: 0: 1699.2, 1: 1710.4. Samples: 15921500. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-09 01:17:18,975][87372] Avg episode reward: [(0, '5.980'), (1, '5.410')] -[2023-10-09 01:17:19,354][88327] Updated weights for policy 1, policy_version 31080 (0.0008) -[2023-10-09 01:17:19,714][88327] Updated weights for policy 1, policy_version 31090 (0.0008) -[2023-10-09 01:17:20,084][88327] Updated weights for policy 1, policy_version 31100 (0.0010) -[2023-10-09 01:17:20,757][88326] Updated weights for policy 0, policy_version 31082 (0.0009) -[2023-10-09 01:17:21,122][88326] Updated weights for policy 0, policy_version 31092 (0.0008) -[2023-10-09 01:17:21,504][88326] Updated weights for policy 0, policy_version 31102 (0.0010) -[2023-10-09 01:17:23,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 63700992. Throughput: 0: 1682.7, 1: 1691.5. Samples: 15931058. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-09 01:17:23,974][87372] Avg episode reward: [(0, '5.580'), (1, '5.230')] -[2023-10-09 01:17:24,075][88327] Updated weights for policy 1, policy_version 31110 (0.0010) -[2023-10-09 01:17:24,447][88327] Updated weights for policy 1, policy_version 31120 (0.0008) -[2023-10-09 01:17:24,804][88327] Updated weights for policy 1, policy_version 31130 (0.0008) -[2023-10-09 01:17:25,490][88326] Updated weights for policy 0, policy_version 31112 (0.0011) -[2023-10-09 01:17:25,861][88326] Updated weights for policy 0, policy_version 31122 (0.0011) -[2023-10-09 01:17:26,237][88326] Updated weights for policy 0, policy_version 31132 (0.0007) -[2023-10-09 01:17:28,879][88327] Updated weights for policy 1, policy_version 31140 (0.0009) -[2023-10-09 01:17:28,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 63766528. Throughput: 0: 1692.4, 1: 1711.8. Samples: 15951732. Policy #0 lag: (min: 27.0, avg: 35.0, max: 59.0) -[2023-10-09 01:17:28,975][87372] Avg episode reward: [(0, '5.800'), (1, '5.180')] -[2023-10-09 01:17:29,244][88327] Updated weights for policy 1, policy_version 31150 (0.0009) -[2023-10-09 01:17:29,598][88327] Updated weights for policy 1, policy_version 31160 (0.0009) -[2023-10-09 01:17:30,257][88326] Updated weights for policy 0, policy_version 31142 (0.0008) -[2023-10-09 01:17:30,625][88326] Updated weights for policy 0, policy_version 31152 (0.0007) -[2023-10-09 01:17:30,992][88326] Updated weights for policy 0, policy_version 31162 (0.0010) -[2023-10-09 01:17:33,665][88327] Updated weights for policy 1, policy_version 31170 (0.0008) -[2023-10-09 01:17:33,974][87372] Fps is (10 sec: 13106.8, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 63832064. Throughput: 0: 1710.4, 1: 1704.3. Samples: 15972742. Policy #0 lag: (min: 27.0, avg: 35.0, max: 59.0) -[2023-10-09 01:17:33,975][87372] Avg episode reward: [(0, '6.280'), (1, '4.890')] -[2023-10-09 01:17:34,085][88327] Updated weights for policy 1, policy_version 31180 (0.0008) -[2023-10-09 01:17:34,449][88327] Updated weights for policy 1, policy_version 31190 (0.0009) -[2023-10-09 01:17:34,794][88326] Updated weights for policy 0, policy_version 31172 (0.0008) -[2023-10-09 01:17:34,821][88327] Updated weights for policy 1, policy_version 31200 (0.0009) -[2023-10-09 01:17:35,156][88326] Updated weights for policy 0, policy_version 31182 (0.0011) -[2023-10-09 01:17:35,533][88326] Updated weights for policy 0, policy_version 31192 (0.0008) -[2023-10-09 01:17:38,868][88327] Updated weights for policy 1, policy_version 31210 (0.0010) -[2023-10-09 01:17:38,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 63897600. Throughput: 0: 1685.6, 1: 1697.8. Samples: 15981670. Policy #0 lag: (min: 27.0, avg: 35.0, max: 59.0) -[2023-10-09 01:17:38,975][87372] Avg episode reward: [(0, '5.300'), (1, '4.850')] -[2023-10-09 01:17:39,249][88327] Updated weights for policy 1, policy_version 31220 (0.0009) -[2023-10-09 01:17:39,619][88327] Updated weights for policy 1, policy_version 31230 (0.0009) -[2023-10-09 01:17:39,671][88326] Updated weights for policy 0, policy_version 31202 (0.0007) -[2023-10-09 01:17:40,043][88326] Updated weights for policy 0, policy_version 31212 (0.0008) -[2023-10-09 01:17:40,421][88326] Updated weights for policy 0, policy_version 31222 (0.0007) -[2023-10-09 01:17:40,790][88326] Updated weights for policy 0, policy_version 31232 (0.0007) -[2023-10-09 01:17:43,825][88327] Updated weights for policy 1, policy_version 31240 (0.0008) -[2023-10-09 01:17:43,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 63963136. Throughput: 0: 1704.8, 1: 1691.1. Samples: 16002066. Policy #0 lag: (min: 27.0, avg: 35.0, max: 59.0) -[2023-10-09 01:17:43,975][87372] Avg episode reward: [(0, '5.530'), (1, '5.280')] -[2023-10-09 01:17:44,201][88327] Updated weights for policy 1, policy_version 31250 (0.0009) -[2023-10-09 01:17:44,557][88327] Updated weights for policy 1, policy_version 31260 (0.0010) -[2023-10-09 01:17:44,843][88326] Updated weights for policy 0, policy_version 31242 (0.0007) -[2023-10-09 01:17:45,222][88326] Updated weights for policy 0, policy_version 31252 (0.0009) -[2023-10-09 01:17:45,599][88326] Updated weights for policy 0, policy_version 31262 (0.0008) -[2023-10-09 01:17:48,557][88327] Updated weights for policy 1, policy_version 31270 (0.0007) -[2023-10-09 01:17:48,925][88327] Updated weights for policy 1, policy_version 31280 (0.0007) -[2023-10-09 01:17:48,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 64028672. Throughput: 0: 1717.0, 1: 1686.1. Samples: 16023040. Policy #0 lag: (min: 27.0, avg: 35.0, max: 59.0) -[2023-10-09 01:17:48,975][87372] Avg episode reward: [(0, '6.040'), (1, '5.430')] -[2023-10-09 01:17:49,294][88327] Updated weights for policy 1, policy_version 31290 (0.0009) -[2023-10-09 01:17:49,633][88326] Updated weights for policy 0, policy_version 31272 (0.0009) -[2023-10-09 01:17:50,006][88326] Updated weights for policy 0, policy_version 31282 (0.0009) -[2023-10-09 01:17:50,378][88326] Updated weights for policy 0, policy_version 31292 (0.0008) -[2023-10-09 01:17:53,312][88327] Updated weights for policy 1, policy_version 31300 (0.0009) -[2023-10-09 01:17:53,680][88327] Updated weights for policy 1, policy_version 31310 (0.0009) -[2023-10-09 01:17:53,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 64094208. Throughput: 0: 1690.0, 1: 1684.3. Samples: 16032212. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:17:53,975][87372] Avg episode reward: [(0, '5.790'), (1, '5.640')] -[2023-10-09 01:17:54,049][88327] Updated weights for policy 1, policy_version 31320 (0.0010) -[2023-10-09 01:17:54,282][88326] Updated weights for policy 0, policy_version 31302 (0.0007) -[2023-10-09 01:17:54,656][88326] Updated weights for policy 0, policy_version 31312 (0.0007) -[2023-10-09 01:17:55,033][88326] Updated weights for policy 0, policy_version 31322 (0.0007) -[2023-10-09 01:17:58,101][88327] Updated weights for policy 1, policy_version 31330 (0.0009) -[2023-10-09 01:17:58,469][88327] Updated weights for policy 1, policy_version 31340 (0.0008) -[2023-10-09 01:17:58,836][88327] Updated weights for policy 1, policy_version 31350 (0.0009) -[2023-10-09 01:17:58,969][88326] Updated weights for policy 0, policy_version 31332 (0.0008) -[2023-10-09 01:17:58,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 64159744. Throughput: 0: 1717.6, 1: 1685.0. Samples: 16053492. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:17:58,975][87372] Avg episode reward: [(0, '5.690'), (1, '5.770')] -[2023-10-09 01:17:59,193][88327] Updated weights for policy 1, policy_version 31360 (0.0010) -[2023-10-09 01:17:59,342][88326] Updated weights for policy 0, policy_version 31342 (0.0007) -[2023-10-09 01:17:59,705][88326] Updated weights for policy 0, policy_version 31352 (0.0007) -[2023-10-09 01:18:03,359][88327] Updated weights for policy 1, policy_version 31370 (0.0007) -[2023-10-09 01:18:03,727][88327] Updated weights for policy 1, policy_version 31380 (0.0010) -[2023-10-09 01:18:03,771][88326] Updated weights for policy 0, policy_version 31362 (0.0009) -[2023-10-09 01:18:03,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 64225280. Throughput: 0: 1713.2, 1: 1679.2. Samples: 16074158. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:18:03,975][87372] Avg episode reward: [(0, '5.970'), (1, '5.490')] -[2023-10-09 01:18:04,096][88327] Updated weights for policy 1, policy_version 31390 (0.0010) -[2023-10-09 01:18:04,136][88326] Updated weights for policy 0, policy_version 31372 (0.0007) -[2023-10-09 01:18:04,507][88326] Updated weights for policy 0, policy_version 31382 (0.0009) -[2023-10-09 01:18:04,885][88326] Updated weights for policy 0, policy_version 31392 (0.0009) -[2023-10-09 01:18:08,040][88327] Updated weights for policy 1, policy_version 31400 (0.0008) -[2023-10-09 01:18:08,404][88327] Updated weights for policy 1, policy_version 31410 (0.0009) -[2023-10-09 01:18:08,739][88326] Updated weights for policy 0, policy_version 31402 (0.0007) -[2023-10-09 01:18:08,769][88327] Updated weights for policy 1, policy_version 31420 (0.0008) -[2023-10-09 01:18:08,974][87372] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 64323584. Throughput: 0: 1702.4, 1: 1687.6. Samples: 16083610. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:18:08,975][87372] Avg episode reward: [(0, '5.670'), (1, '5.820')] -[2023-10-09 01:18:09,098][88326] Updated weights for policy 0, policy_version 31412 (0.0009) -[2023-10-09 01:18:09,463][88326] Updated weights for policy 0, policy_version 31422 (0.0010) -[2023-10-09 01:18:12,873][88327] Updated weights for policy 1, policy_version 31430 (0.0009) -[2023-10-09 01:18:13,249][88327] Updated weights for policy 1, policy_version 31440 (0.0007) -[2023-10-09 01:18:13,528][88326] Updated weights for policy 0, policy_version 31432 (0.0008) -[2023-10-09 01:18:13,617][88327] Updated weights for policy 1, policy_version 31450 (0.0009) -[2023-10-09 01:18:13,894][88326] Updated weights for policy 0, policy_version 31442 (0.0007) -[2023-10-09 01:18:13,974][87372] Fps is (10 sec: 16384.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 64389120. Throughput: 0: 1704.3, 1: 1683.8. Samples: 16104194. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:18:13,975][87372] Avg episode reward: [(0, '5.720'), (1, '5.870')] -[2023-10-09 01:18:14,259][88326] Updated weights for policy 0, policy_version 31452 (0.0010) -[2023-10-09 01:18:17,613][88327] Updated weights for policy 1, policy_version 31460 (0.0009) -[2023-10-09 01:18:17,982][88327] Updated weights for policy 1, policy_version 31470 (0.0008) -[2023-10-09 01:18:18,314][88326] Updated weights for policy 0, policy_version 31462 (0.0009) -[2023-10-09 01:18:18,341][88327] Updated weights for policy 1, policy_version 31480 (0.0009) -[2023-10-09 01:18:18,682][88326] Updated weights for policy 0, policy_version 31472 (0.0007) -[2023-10-09 01:18:18,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 64454656. Throughput: 0: 1699.7, 1: 1671.0. Samples: 16124422. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) -[2023-10-09 01:18:18,975][87372] Avg episode reward: [(0, '6.050'), (1, '5.920')] -[2023-10-09 01:18:19,051][88326] Updated weights for policy 0, policy_version 31482 (0.0007) -[2023-10-09 01:18:22,548][88327] Updated weights for policy 1, policy_version 31490 (0.0008) -[2023-10-09 01:18:22,962][88327] Updated weights for policy 1, policy_version 31500 (0.0008) -[2023-10-09 01:18:23,038][88326] Updated weights for policy 0, policy_version 31492 (0.0009) -[2023-10-09 01:18:23,324][88327] Updated weights for policy 1, policy_version 31510 (0.0008) -[2023-10-09 01:18:23,406][88326] Updated weights for policy 0, policy_version 31502 (0.0010) -[2023-10-09 01:18:23,689][88327] Updated weights for policy 1, policy_version 31520 (0.0009) -[2023-10-09 01:18:23,769][88326] Updated weights for policy 0, policy_version 31512 (0.0008) -[2023-10-09 01:18:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 64520192. Throughput: 0: 1702.8, 1: 1689.5. Samples: 16134322. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) -[2023-10-09 01:18:23,974][87372] Avg episode reward: [(0, '6.100'), (1, '5.920')] -[2023-10-09 01:18:27,663][88327] Updated weights for policy 1, policy_version 31530 (0.0008) -[2023-10-09 01:18:27,763][88326] Updated weights for policy 0, policy_version 31522 (0.0010) -[2023-10-09 01:18:28,026][88327] Updated weights for policy 1, policy_version 31540 (0.0007) -[2023-10-09 01:18:28,126][88326] Updated weights for policy 0, policy_version 31532 (0.0008) -[2023-10-09 01:18:28,386][88327] Updated weights for policy 1, policy_version 31550 (0.0010) -[2023-10-09 01:18:28,500][88326] Updated weights for policy 0, policy_version 31542 (0.0007) -[2023-10-09 01:18:28,865][88326] Updated weights for policy 0, policy_version 31552 (0.0007) -[2023-10-09 01:18:28,974][87372] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 64618496. Throughput: 0: 1711.3, 1: 1692.4. Samples: 16155232. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) -[2023-10-09 01:18:28,974][87372] Avg episode reward: [(0, '5.750'), (1, '5.580')] -[2023-10-09 01:18:32,276][88327] Updated weights for policy 1, policy_version 31560 (0.0008) -[2023-10-09 01:18:32,637][88327] Updated weights for policy 1, policy_version 31570 (0.0007) -[2023-10-09 01:18:32,943][88326] Updated weights for policy 0, policy_version 31562 (0.0009) -[2023-10-09 01:18:33,000][88327] Updated weights for policy 1, policy_version 31580 (0.0007) -[2023-10-09 01:18:33,314][88326] Updated weights for policy 0, policy_version 31572 (0.0009) -[2023-10-09 01:18:33,685][88326] Updated weights for policy 0, policy_version 31582 (0.0010) -[2023-10-09 01:18:33,974][87372] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 64684032. Throughput: 0: 1693.7, 1: 1664.0. Samples: 16174136. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) -[2023-10-09 01:18:33,975][87372] Avg episode reward: [(0, '5.440'), (1, '5.260')] -[2023-10-09 01:18:33,982][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000031584_32342016.pth... -[2023-10-09 01:18:33,982][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000031584_32342016.pth... -[2023-10-09 01:18:34,013][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000029984_30703616.pth -[2023-10-09 01:18:34,017][88088] Saving a milestone ./train_atari/atari_battlezone_APPO/checkpoint_p0/milestones/checkpoint_000031584_32342016.pth -[2023-10-09 01:18:34,018][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000029984_30703616.pth -[2023-10-09 01:18:34,024][88168] Saving a milestone ./train_atari/atari_battlezone_APPO/checkpoint_p1/milestones/checkpoint_000031584_32342016.pth -[2023-10-09 01:18:37,001][88327] Updated weights for policy 1, policy_version 31590 (0.0008) -[2023-10-09 01:18:37,371][88327] Updated weights for policy 1, policy_version 31600 (0.0008) -[2023-10-09 01:18:37,741][88327] Updated weights for policy 1, policy_version 31610 (0.0008) -[2023-10-09 01:18:37,902][88326] Updated weights for policy 0, policy_version 31592 (0.0008) -[2023-10-09 01:18:38,263][88326] Updated weights for policy 0, policy_version 31602 (0.0010) -[2023-10-09 01:18:38,634][88326] Updated weights for policy 0, policy_version 31612 (0.0009) -[2023-10-09 01:18:38,974][87372] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 64749568. Throughput: 0: 1703.5, 1: 1696.4. Samples: 16185204. Policy #0 lag: (min: 10.0, avg: 10.0, max: 10.0) -[2023-10-09 01:18:38,975][87372] Avg episode reward: [(0, '5.540'), (1, '5.060')] -[2023-10-09 01:18:41,986][88327] Updated weights for policy 1, policy_version 31620 (0.0009) -[2023-10-09 01:18:42,360][88327] Updated weights for policy 1, policy_version 31630 (0.0008) -[2023-10-09 01:18:42,719][88327] Updated weights for policy 1, policy_version 31640 (0.0007) -[2023-10-09 01:18:42,868][88326] Updated weights for policy 0, policy_version 31622 (0.0007) -[2023-10-09 01:18:43,246][88326] Updated weights for policy 0, policy_version 31632 (0.0007) -[2023-10-09 01:18:43,619][88326] Updated weights for policy 0, policy_version 31642 (0.0008) -[2023-10-09 01:18:43,974][87372] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 64815104. Throughput: 0: 1695.9, 1: 1681.2. Samples: 16205460. Policy #0 lag: (min: 10.0, avg: 10.0, max: 10.0) -[2023-10-09 01:18:43,975][87372] Avg episode reward: [(0, '5.600'), (1, '5.710')] -[2023-10-09 01:18:46,993][88327] Updated weights for policy 1, policy_version 31650 (0.0008) -[2023-10-09 01:18:47,365][88327] Updated weights for policy 1, policy_version 31660 (0.0009) -[2023-10-09 01:18:47,654][88326] Updated weights for policy 0, policy_version 31652 (0.0009) -[2023-10-09 01:18:47,724][88327] Updated weights for policy 1, policy_version 31670 (0.0009) -[2023-10-09 01:18:48,016][88326] Updated weights for policy 0, policy_version 31662 (0.0008) -[2023-10-09 01:18:48,086][88327] Updated weights for policy 1, policy_version 31680 (0.0008) -[2023-10-09 01:18:48,381][88326] Updated weights for policy 0, policy_version 31672 (0.0008) -[2023-10-09 01:18:48,974][87372] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 64880640. Throughput: 0: 1672.8, 1: 1663.6. Samples: 16224298. Policy #0 lag: (min: 10.0, avg: 10.0, max: 10.0) -[2023-10-09 01:18:48,975][87372] Avg episode reward: [(0, '5.500'), (1, '5.470')] -[2023-10-09 01:18:52,194][88327] Updated weights for policy 1, policy_version 31690 (0.0009) -[2023-10-09 01:18:52,398][88326] Updated weights for policy 0, policy_version 31682 (0.0007) -[2023-10-09 01:18:52,572][88327] Updated weights for policy 1, policy_version 31700 (0.0008) -[2023-10-09 01:18:52,755][88326] Updated weights for policy 0, policy_version 31692 (0.0007) -[2023-10-09 01:18:52,938][88327] Updated weights for policy 1, policy_version 31710 (0.0008) -[2023-10-09 01:18:53,128][88326] Updated weights for policy 0, policy_version 31702 (0.0010) -[2023-10-09 01:18:53,491][88326] Updated weights for policy 0, policy_version 31712 (0.0008) -[2023-10-09 01:18:53,974][87372] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 64946176. Throughput: 0: 1688.0, 1: 1685.0. Samples: 16235396. Policy #0 lag: (min: 10.0, avg: 10.0, max: 10.0) -[2023-10-09 01:18:53,975][87372] Avg episode reward: [(0, '5.860'), (1, '5.920')] -[2023-10-09 01:18:56,827][88327] Updated weights for policy 1, policy_version 31720 (0.0011) -[2023-10-09 01:18:57,187][88327] Updated weights for policy 1, policy_version 31730 (0.0009) -[2023-10-09 01:18:57,547][88327] Updated weights for policy 1, policy_version 31740 (0.0008) -[2023-10-09 01:18:57,577][88326] Updated weights for policy 0, policy_version 31722 (0.0008) -[2023-10-09 01:18:57,945][88326] Updated weights for policy 0, policy_version 31732 (0.0008) -[2023-10-09 01:18:58,315][88326] Updated weights for policy 0, policy_version 31742 (0.0008) -[2023-10-09 01:18:58,974][87372] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 65011712. Throughput: 0: 1692.7, 1: 1673.9. Samples: 16255692. Policy #0 lag: (min: 10.0, avg: 10.0, max: 10.0) -[2023-10-09 01:18:58,975][87372] Avg episode reward: [(0, '5.520'), (1, '5.860')] -[2023-10-09 01:19:01,580][88327] Updated weights for policy 1, policy_version 31750 (0.0008) -[2023-10-09 01:19:01,949][88327] Updated weights for policy 1, policy_version 31760 (0.0009) -[2023-10-09 01:19:02,278][88326] Updated weights for policy 0, policy_version 31752 (0.0007) -[2023-10-09 01:19:02,310][88327] Updated weights for policy 1, policy_version 31770 (0.0009) -[2023-10-09 01:19:02,651][88326] Updated weights for policy 0, policy_version 31762 (0.0007) -[2023-10-09 01:19:03,021][88326] Updated weights for policy 0, policy_version 31772 (0.0007) -[2023-10-09 01:19:03,974][87372] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 65077248. Throughput: 0: 1664.2, 1: 1675.8. Samples: 16274720. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-09 01:19:03,975][87372] Avg episode reward: [(0, '5.500'), (1, '5.280')] -[2023-10-09 01:19:06,454][88327] Updated weights for policy 1, policy_version 31780 (0.0008) -[2023-10-09 01:19:06,828][88327] Updated weights for policy 1, policy_version 31790 (0.0007) -[2023-10-09 01:19:06,934][88326] Updated weights for policy 0, policy_version 31782 (0.0009) -[2023-10-09 01:19:07,192][88327] Updated weights for policy 1, policy_version 31800 (0.0008) -[2023-10-09 01:19:07,299][88326] Updated weights for policy 0, policy_version 31792 (0.0008) -[2023-10-09 01:19:07,668][88326] Updated weights for policy 0, policy_version 31802 (0.0009) -[2023-10-09 01:19:08,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 65142784. Throughput: 0: 1691.2, 1: 1688.0. Samples: 16286386. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-09 01:19:08,975][87372] Avg episode reward: [(0, '6.150'), (1, '5.580')] -[2023-10-09 01:19:10,968][88327] Updated weights for policy 1, policy_version 31810 (0.0008) -[2023-10-09 01:19:11,331][88327] Updated weights for policy 1, policy_version 31820 (0.0008) -[2023-10-09 01:19:11,692][88327] Updated weights for policy 1, policy_version 31830 (0.0009) -[2023-10-09 01:19:11,752][88326] Updated weights for policy 0, policy_version 31812 (0.0007) -[2023-10-09 01:19:12,054][88327] Updated weights for policy 1, policy_version 31840 (0.0010) -[2023-10-09 01:19:12,112][88326] Updated weights for policy 0, policy_version 31822 (0.0008) -[2023-10-09 01:19:12,488][88326] Updated weights for policy 0, policy_version 31832 (0.0008) -[2023-10-09 01:19:13,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 65208320. Throughput: 0: 1672.4, 1: 1663.1. Samples: 16305330. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-09 01:19:13,975][87372] Avg episode reward: [(0, '5.680'), (1, '5.350')] -[2023-10-09 01:19:16,285][88327] Updated weights for policy 1, policy_version 31850 (0.0009) -[2023-10-09 01:19:16,442][88326] Updated weights for policy 0, policy_version 31842 (0.0009) -[2023-10-09 01:19:16,659][88327] Updated weights for policy 1, policy_version 31860 (0.0009) -[2023-10-09 01:19:16,803][88326] Updated weights for policy 0, policy_version 31852 (0.0008) -[2023-10-09 01:19:17,025][88327] Updated weights for policy 1, policy_version 31870 (0.0009) -[2023-10-09 01:19:17,169][88326] Updated weights for policy 0, policy_version 31862 (0.0007) -[2023-10-09 01:19:17,533][88326] Updated weights for policy 0, policy_version 31872 (0.0007) -[2023-10-09 01:19:18,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 65273856. Throughput: 0: 1675.9, 1: 1688.1. Samples: 16325516. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-09 01:19:18,975][87372] Avg episode reward: [(0, '5.930'), (1, '5.120')] -[2023-10-09 01:19:21,180][88327] Updated weights for policy 1, policy_version 31880 (0.0011) -[2023-10-09 01:19:21,553][88327] Updated weights for policy 1, policy_version 31890 (0.0009) -[2023-10-09 01:19:21,794][88326] Updated weights for policy 0, policy_version 31882 (0.0007) -[2023-10-09 01:19:21,915][88327] Updated weights for policy 1, policy_version 31900 (0.0010) -[2023-10-09 01:19:22,162][88326] Updated weights for policy 0, policy_version 31892 (0.0008) -[2023-10-09 01:19:22,531][88326] Updated weights for policy 0, policy_version 31902 (0.0008) -[2023-10-09 01:19:23,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 65339392. Throughput: 0: 1690.6, 1: 1677.1. Samples: 16336750. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-09 01:19:23,975][87372] Avg episode reward: [(0, '6.270'), (1, '5.370')] -[2023-10-09 01:19:25,892][88327] Updated weights for policy 1, policy_version 31910 (0.0007) -[2023-10-09 01:19:26,253][88327] Updated weights for policy 1, policy_version 31920 (0.0011) -[2023-10-09 01:19:26,490][88326] Updated weights for policy 0, policy_version 31912 (0.0007) -[2023-10-09 01:19:26,621][88327] Updated weights for policy 1, policy_version 31930 (0.0007) -[2023-10-09 01:19:26,857][88326] Updated weights for policy 0, policy_version 31922 (0.0008) -[2023-10-09 01:19:27,222][88326] Updated weights for policy 0, policy_version 31932 (0.0009) -[2023-10-09 01:19:28,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 65404928. Throughput: 0: 1667.3, 1: 1667.2. Samples: 16355512. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:19:28,975][87372] Avg episode reward: [(0, '5.780'), (1, '5.760')] -[2023-10-09 01:19:30,691][88327] Updated weights for policy 1, policy_version 31940 (0.0007) -[2023-10-09 01:19:31,060][88327] Updated weights for policy 1, policy_version 31950 (0.0009) -[2023-10-09 01:19:31,357][88326] Updated weights for policy 0, policy_version 31942 (0.0008) -[2023-10-09 01:19:31,420][88327] Updated weights for policy 1, policy_version 31960 (0.0009) -[2023-10-09 01:19:31,711][88326] Updated weights for policy 0, policy_version 31952 (0.0007) -[2023-10-09 01:19:32,090][88326] Updated weights for policy 0, policy_version 31962 (0.0009) -[2023-10-09 01:19:33,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 65470464. Throughput: 0: 1682.1, 1: 1689.9. Samples: 16376040. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:19:33,975][87372] Avg episode reward: [(0, '6.130'), (1, '6.250')] -[2023-10-09 01:19:35,744][88327] Updated weights for policy 1, policy_version 31970 (0.0008) -[2023-10-09 01:19:36,113][88327] Updated weights for policy 1, policy_version 31980 (0.0009) -[2023-10-09 01:19:36,274][88326] Updated weights for policy 0, policy_version 31972 (0.0011) -[2023-10-09 01:19:36,483][88327] Updated weights for policy 1, policy_version 31990 (0.0009) -[2023-10-09 01:19:36,643][88326] Updated weights for policy 0, policy_version 31982 (0.0007) -[2023-10-09 01:19:36,849][88327] Updated weights for policy 1, policy_version 32000 (0.0007) -[2023-10-09 01:19:37,014][88326] Updated weights for policy 0, policy_version 31992 (0.0008) -[2023-10-09 01:19:38,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 65536000. Throughput: 0: 1693.5, 1: 1676.9. Samples: 16387062. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:19:38,975][87372] Avg episode reward: [(0, '5.760'), (1, '6.200')] -[2023-10-09 01:19:40,910][88327] Updated weights for policy 1, policy_version 32010 (0.0010) -[2023-10-09 01:19:41,058][88326] Updated weights for policy 0, policy_version 32002 (0.0010) -[2023-10-09 01:19:41,276][88327] Updated weights for policy 1, policy_version 32020 (0.0008) -[2023-10-09 01:19:41,434][88326] Updated weights for policy 0, policy_version 32012 (0.0009) -[2023-10-09 01:19:41,644][88327] Updated weights for policy 1, policy_version 32030 (0.0007) -[2023-10-09 01:19:41,798][88326] Updated weights for policy 0, policy_version 32022 (0.0009) -[2023-10-09 01:19:42,169][88326] Updated weights for policy 0, policy_version 32032 (0.0011) -[2023-10-09 01:19:43,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 65601536. Throughput: 0: 1661.6, 1: 1672.0. Samples: 16405702. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:19:43,974][87372] Avg episode reward: [(0, '5.800'), (1, '6.090')] -[2023-10-09 01:19:45,497][88327] Updated weights for policy 1, policy_version 32040 (0.0010) -[2023-10-09 01:19:45,863][88327] Updated weights for policy 1, policy_version 32050 (0.0009) -[2023-10-09 01:19:46,218][88327] Updated weights for policy 1, policy_version 32060 (0.0007) -[2023-10-09 01:19:46,236][88326] Updated weights for policy 0, policy_version 32042 (0.0008) -[2023-10-09 01:19:46,607][88326] Updated weights for policy 0, policy_version 32052 (0.0007) -[2023-10-09 01:19:46,977][88326] Updated weights for policy 0, policy_version 32062 (0.0007) -[2023-10-09 01:19:48,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 65667072. Throughput: 0: 1688.9, 1: 1687.5. Samples: 16426658. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:19:48,975][87372] Avg episode reward: [(0, '5.810'), (1, '6.110')] -[2023-10-09 01:19:50,145][88327] Updated weights for policy 1, policy_version 32070 (0.0009) -[2023-10-09 01:19:50,515][88327] Updated weights for policy 1, policy_version 32080 (0.0008) -[2023-10-09 01:19:50,886][88327] Updated weights for policy 1, policy_version 32090 (0.0010) -[2023-10-09 01:19:51,102][88326] Updated weights for policy 0, policy_version 32072 (0.0009) -[2023-10-09 01:19:51,467][88326] Updated weights for policy 0, policy_version 32082 (0.0009) -[2023-10-09 01:19:51,853][88326] Updated weights for policy 0, policy_version 32092 (0.0010) -[2023-10-09 01:19:53,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 65732608. Throughput: 0: 1678.6, 1: 1662.0. Samples: 16436710. Policy #0 lag: (min: 9.0, avg: 19.1, max: 41.0) -[2023-10-09 01:19:53,975][87372] Avg episode reward: [(0, '5.850'), (1, '5.340')] -[2023-10-09 01:19:54,978][88327] Updated weights for policy 1, policy_version 32100 (0.0008) -[2023-10-09 01:19:55,353][88327] Updated weights for policy 1, policy_version 32110 (0.0009) -[2023-10-09 01:19:55,714][88327] Updated weights for policy 1, policy_version 32120 (0.0009) -[2023-10-09 01:19:55,843][88326] Updated weights for policy 0, policy_version 32102 (0.0007) -[2023-10-09 01:19:56,211][88326] Updated weights for policy 0, policy_version 32112 (0.0008) -[2023-10-09 01:19:56,582][88326] Updated weights for policy 0, policy_version 32122 (0.0009) -[2023-10-09 01:19:58,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 65798144. Throughput: 0: 1676.4, 1: 1692.5. Samples: 16456930. Policy #0 lag: (min: 9.0, avg: 19.1, max: 41.0) -[2023-10-09 01:19:58,974][87372] Avg episode reward: [(0, '6.310'), (1, '5.800')] -[2023-10-09 01:19:59,841][88327] Updated weights for policy 1, policy_version 32130 (0.0008) -[2023-10-09 01:20:00,207][88327] Updated weights for policy 1, policy_version 32140 (0.0008) -[2023-10-09 01:20:00,461][88326] Updated weights for policy 0, policy_version 32132 (0.0008) -[2023-10-09 01:20:00,560][88327] Updated weights for policy 1, policy_version 32150 (0.0009) -[2023-10-09 01:20:00,837][88326] Updated weights for policy 0, policy_version 32142 (0.0007) -[2023-10-09 01:20:00,927][88327] Updated weights for policy 1, policy_version 32160 (0.0007) -[2023-10-09 01:20:01,210][88326] Updated weights for policy 0, policy_version 32152 (0.0011) -[2023-10-09 01:20:03,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 65863680. Throughput: 0: 1695.2, 1: 1698.0. Samples: 16478212. Policy #0 lag: (min: 9.0, avg: 19.1, max: 41.0) -[2023-10-09 01:20:03,975][87372] Avg episode reward: [(0, '6.070'), (1, '5.340')] -[2023-10-09 01:20:04,825][88327] Updated weights for policy 1, policy_version 32170 (0.0008) -[2023-10-09 01:20:05,185][88326] Updated weights for policy 0, policy_version 32162 (0.0007) -[2023-10-09 01:20:05,194][88327] Updated weights for policy 1, policy_version 32180 (0.0007) -[2023-10-09 01:20:05,555][88326] Updated weights for policy 0, policy_version 32172 (0.0009) -[2023-10-09 01:20:05,559][88327] Updated weights for policy 1, policy_version 32190 (0.0008) -[2023-10-09 01:20:05,917][88326] Updated weights for policy 0, policy_version 32182 (0.0009) -[2023-10-09 01:20:06,290][88326] Updated weights for policy 0, policy_version 32192 (0.0010) -[2023-10-09 01:20:08,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 65929216. Throughput: 0: 1672.4, 1: 1673.8. Samples: 16487332. Policy #0 lag: (min: 9.0, avg: 19.1, max: 41.0) -[2023-10-09 01:20:08,975][87372] Avg episode reward: [(0, '5.290'), (1, '5.340')] -[2023-10-09 01:20:09,554][88327] Updated weights for policy 1, policy_version 32200 (0.0008) -[2023-10-09 01:20:09,929][88327] Updated weights for policy 1, policy_version 32210 (0.0009) -[2023-10-09 01:20:10,280][88327] Updated weights for policy 1, policy_version 32220 (0.0009) -[2023-10-09 01:20:10,313][88326] Updated weights for policy 0, policy_version 32202 (0.0007) -[2023-10-09 01:20:10,673][88326] Updated weights for policy 0, policy_version 32212 (0.0008) -[2023-10-09 01:20:11,049][88326] Updated weights for policy 0, policy_version 32222 (0.0008) -[2023-10-09 01:20:13,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 65994752. Throughput: 0: 1690.9, 1: 1694.4. Samples: 16507850. Policy #0 lag: (min: 9.0, avg: 19.1, max: 41.0) -[2023-10-09 01:20:13,975][87372] Avg episode reward: [(0, '5.590'), (1, '5.470')] -[2023-10-09 01:20:14,440][88327] Updated weights for policy 1, policy_version 32230 (0.0008) -[2023-10-09 01:20:14,807][88327] Updated weights for policy 1, policy_version 32240 (0.0008) -[2023-10-09 01:20:15,161][88327] Updated weights for policy 1, policy_version 32250 (0.0007) -[2023-10-09 01:20:15,276][88326] Updated weights for policy 0, policy_version 32232 (0.0008) -[2023-10-09 01:20:15,650][88326] Updated weights for policy 0, policy_version 32242 (0.0008) -[2023-10-09 01:20:16,019][88326] Updated weights for policy 0, policy_version 32252 (0.0010) -[2023-10-09 01:20:18,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 66060288. Throughput: 0: 1694.7, 1: 1699.2. Samples: 16528764. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-09 01:20:18,975][87372] Avg episode reward: [(0, '5.770'), (1, '5.540')] -[2023-10-09 01:20:19,289][88327] Updated weights for policy 1, policy_version 32260 (0.0008) -[2023-10-09 01:20:19,648][88327] Updated weights for policy 1, policy_version 32270 (0.0007) -[2023-10-09 01:20:20,015][88327] Updated weights for policy 1, policy_version 32280 (0.0007) -[2023-10-09 01:20:20,063][88326] Updated weights for policy 0, policy_version 32262 (0.0009) -[2023-10-09 01:20:20,428][88326] Updated weights for policy 0, policy_version 32272 (0.0008) -[2023-10-09 01:20:20,794][88326] Updated weights for policy 0, policy_version 32282 (0.0008) -[2023-10-09 01:20:23,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 66125824. Throughput: 0: 1665.4, 1: 1684.8. Samples: 16537820. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-09 01:20:23,974][87372] Avg episode reward: [(0, '5.170'), (1, '5.770')] -[2023-10-09 01:20:24,040][88327] Updated weights for policy 1, policy_version 32290 (0.0007) -[2023-10-09 01:20:24,411][88327] Updated weights for policy 1, policy_version 32300 (0.0009) -[2023-10-09 01:20:24,667][88326] Updated weights for policy 0, policy_version 32292 (0.0008) -[2023-10-09 01:20:24,777][88327] Updated weights for policy 1, policy_version 32310 (0.0008) -[2023-10-09 01:20:25,031][88326] Updated weights for policy 0, policy_version 32302 (0.0008) -[2023-10-09 01:20:25,141][88327] Updated weights for policy 1, policy_version 32320 (0.0009) -[2023-10-09 01:20:25,397][88326] Updated weights for policy 0, policy_version 32312 (0.0010) -[2023-10-09 01:20:28,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 66191360. Throughput: 0: 1698.9, 1: 1701.9. Samples: 16558736. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-09 01:20:28,975][87372] Avg episode reward: [(0, '5.620'), (1, '5.660')] -[2023-10-09 01:20:29,205][88327] Updated weights for policy 1, policy_version 32330 (0.0007) -[2023-10-09 01:20:29,459][88326] Updated weights for policy 0, policy_version 32322 (0.0007) -[2023-10-09 01:20:29,570][88327] Updated weights for policy 1, policy_version 32340 (0.0008) -[2023-10-09 01:20:29,839][88326] Updated weights for policy 0, policy_version 32332 (0.0008) -[2023-10-09 01:20:29,939][88327] Updated weights for policy 1, policy_version 32350 (0.0008) -[2023-10-09 01:20:30,205][88326] Updated weights for policy 0, policy_version 32342 (0.0009) -[2023-10-09 01:20:30,573][88326] Updated weights for policy 0, policy_version 32352 (0.0008) -[2023-10-09 01:20:33,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 66256896. Throughput: 0: 1697.9, 1: 1700.0. Samples: 16579564. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-09 01:20:33,975][87372] Avg episode reward: [(0, '5.650'), (1, '5.300')] -[2023-10-09 01:20:33,983][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000032352_33128448.pth... -[2023-10-09 01:20:34,020][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000030784_31522816.pth -[2023-10-09 01:20:34,029][88327] Updated weights for policy 1, policy_version 32360 (0.0008) -[2023-10-09 01:20:34,388][88327] Updated weights for policy 1, policy_version 32370 (0.0009) -[2023-10-09 01:20:34,594][88326] Updated weights for policy 0, policy_version 32362 (0.0007) -[2023-10-09 01:20:34,739][88327] Updated weights for policy 1, policy_version 32380 (0.0007) -[2023-10-09 01:20:34,884][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000032384_33161216.pth... -[2023-10-09 01:20:34,913][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000030784_31522816.pth -[2023-10-09 01:20:34,969][88326] Updated weights for policy 0, policy_version 32372 (0.0007) -[2023-10-09 01:20:35,351][88326] Updated weights for policy 0, policy_version 32382 (0.0008) -[2023-10-09 01:20:38,733][88327] Updated weights for policy 1, policy_version 32390 (0.0007) -[2023-10-09 01:20:38,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 66322432. Throughput: 0: 1676.9, 1: 1701.8. Samples: 16588750. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-09 01:20:38,974][87372] Avg episode reward: [(0, '5.420'), (1, '5.490')] -[2023-10-09 01:20:39,101][88327] Updated weights for policy 1, policy_version 32400 (0.0009) -[2023-10-09 01:20:39,436][88326] Updated weights for policy 0, policy_version 32392 (0.0008) -[2023-10-09 01:20:39,466][88327] Updated weights for policy 1, policy_version 32410 (0.0009) -[2023-10-09 01:20:39,801][88326] Updated weights for policy 0, policy_version 32402 (0.0008) -[2023-10-09 01:20:40,177][88326] Updated weights for policy 0, policy_version 32412 (0.0011) -[2023-10-09 01:20:43,482][88327] Updated weights for policy 1, policy_version 32420 (0.0007) -[2023-10-09 01:20:43,848][88327] Updated weights for policy 1, policy_version 32430 (0.0008) -[2023-10-09 01:20:43,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 66387968. Throughput: 0: 1689.3, 1: 1698.3. Samples: 16609372. Policy #0 lag: (min: 29.0, avg: 35.3, max: 61.0) -[2023-10-09 01:20:43,974][87372] Avg episode reward: [(0, '5.820'), (1, '5.440')] -[2023-10-09 01:20:44,222][88327] Updated weights for policy 1, policy_version 32440 (0.0008) -[2023-10-09 01:20:44,372][88326] Updated weights for policy 0, policy_version 32422 (0.0009) -[2023-10-09 01:20:44,740][88326] Updated weights for policy 0, policy_version 32432 (0.0010) -[2023-10-09 01:20:45,108][88326] Updated weights for policy 0, policy_version 32442 (0.0007) -[2023-10-09 01:20:48,227][88327] Updated weights for policy 1, policy_version 32450 (0.0008) -[2023-10-09 01:20:48,586][88327] Updated weights for policy 1, policy_version 32460 (0.0007) -[2023-10-09 01:20:48,955][88327] Updated weights for policy 1, policy_version 32470 (0.0008) -[2023-10-09 01:20:48,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 66453504. Throughput: 0: 1686.4, 1: 1696.1. Samples: 16630426. Policy #0 lag: (min: 29.0, avg: 35.3, max: 61.0) -[2023-10-09 01:20:48,975][87372] Avg episode reward: [(0, '6.110'), (1, '6.000')] -[2023-10-09 01:20:49,114][88326] Updated weights for policy 0, policy_version 32452 (0.0008) -[2023-10-09 01:20:49,322][88327] Updated weights for policy 1, policy_version 32480 (0.0008) -[2023-10-09 01:20:49,477][88326] Updated weights for policy 0, policy_version 32462 (0.0009) -[2023-10-09 01:20:49,852][88326] Updated weights for policy 0, policy_version 32472 (0.0010) -[2023-10-09 01:20:53,443][88327] Updated weights for policy 1, policy_version 32490 (0.0009) -[2023-10-09 01:20:53,806][88327] Updated weights for policy 1, policy_version 32500 (0.0007) -[2023-10-09 01:20:53,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 66519040. Throughput: 0: 1679.7, 1: 1702.0. Samples: 16639510. Policy #0 lag: (min: 29.0, avg: 35.3, max: 61.0) -[2023-10-09 01:20:53,975][87372] Avg episode reward: [(0, '6.210'), (1, '6.380')] -[2023-10-09 01:20:53,985][88326] Updated weights for policy 0, policy_version 32482 (0.0007) -[2023-10-09 01:20:54,171][88327] Updated weights for policy 1, policy_version 32510 (0.0009) -[2023-10-09 01:20:54,355][88326] Updated weights for policy 0, policy_version 32492 (0.0008) -[2023-10-09 01:20:54,735][88326] Updated weights for policy 0, policy_version 32502 (0.0008) -[2023-10-09 01:20:55,110][88326] Updated weights for policy 0, policy_version 32512 (0.0010) -[2023-10-09 01:20:58,204][88327] Updated weights for policy 1, policy_version 32520 (0.0008) -[2023-10-09 01:20:58,574][88327] Updated weights for policy 1, policy_version 32530 (0.0007) -[2023-10-09 01:20:58,938][88327] Updated weights for policy 1, policy_version 32540 (0.0008) -[2023-10-09 01:20:58,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 66584576. Throughput: 0: 1687.4, 1: 1699.2. Samples: 16660246. Policy #0 lag: (min: 29.0, avg: 35.3, max: 61.0) -[2023-10-09 01:20:58,975][87372] Avg episode reward: [(0, '5.950'), (1, '6.070')] -[2023-10-09 01:20:59,098][88326] Updated weights for policy 0, policy_version 32522 (0.0008) -[2023-10-09 01:20:59,469][88326] Updated weights for policy 0, policy_version 32532 (0.0008) -[2023-10-09 01:20:59,840][88326] Updated weights for policy 0, policy_version 32542 (0.0007) -[2023-10-09 01:21:02,810][88327] Updated weights for policy 1, policy_version 32550 (0.0007) -[2023-10-09 01:21:03,177][88327] Updated weights for policy 1, policy_version 32560 (0.0008) -[2023-10-09 01:21:03,536][88327] Updated weights for policy 1, policy_version 32570 (0.0009) -[2023-10-09 01:21:03,817][88326] Updated weights for policy 0, policy_version 32552 (0.0009) -[2023-10-09 01:21:03,974][87372] Fps is (10 sec: 16383.7, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 66682880. Throughput: 0: 1690.8, 1: 1689.3. Samples: 16680866. Policy #0 lag: (min: 29.0, avg: 35.3, max: 61.0) -[2023-10-09 01:21:03,975][87372] Avg episode reward: [(0, '6.150'), (1, '6.390')] -[2023-10-09 01:21:04,186][88326] Updated weights for policy 0, policy_version 32562 (0.0010) -[2023-10-09 01:21:04,559][88326] Updated weights for policy 0, policy_version 32572 (0.0007) -[2023-10-09 01:21:07,552][88327] Updated weights for policy 1, policy_version 32580 (0.0008) -[2023-10-09 01:21:07,920][88327] Updated weights for policy 1, policy_version 32590 (0.0010) -[2023-10-09 01:21:08,273][88327] Updated weights for policy 1, policy_version 32600 (0.0009) -[2023-10-09 01:21:08,509][88326] Updated weights for policy 0, policy_version 32582 (0.0007) -[2023-10-09 01:21:08,880][88326] Updated weights for policy 0, policy_version 32592 (0.0009) -[2023-10-09 01:21:08,974][87372] Fps is (10 sec: 16384.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 66748416. Throughput: 0: 1690.6, 1: 1705.3. Samples: 16690634. Policy #0 lag: (min: 1.0, avg: 10.8, max: 33.0) -[2023-10-09 01:21:08,974][87372] Avg episode reward: [(0, '6.000'), (1, '5.560')] -[2023-10-09 01:21:09,253][88326] Updated weights for policy 0, policy_version 32602 (0.0009) -[2023-10-09 01:21:12,220][88327] Updated weights for policy 1, policy_version 32610 (0.0010) -[2023-10-09 01:21:12,595][88327] Updated weights for policy 1, policy_version 32620 (0.0009) -[2023-10-09 01:21:12,967][88327] Updated weights for policy 1, policy_version 32630 (0.0010) -[2023-10-09 01:21:13,339][88327] Updated weights for policy 1, policy_version 32640 (0.0008) -[2023-10-09 01:21:13,402][88326] Updated weights for policy 0, policy_version 32612 (0.0009) -[2023-10-09 01:21:13,770][88326] Updated weights for policy 0, policy_version 32622 (0.0008) -[2023-10-09 01:21:13,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 66813952. Throughput: 0: 1687.9, 1: 1710.4. Samples: 16711660. Policy #0 lag: (min: 1.0, avg: 10.8, max: 33.0) -[2023-10-09 01:21:13,975][87372] Avg episode reward: [(0, '5.800'), (1, '5.630')] -[2023-10-09 01:21:14,146][88326] Updated weights for policy 0, policy_version 32632 (0.0007) -[2023-10-09 01:21:17,319][88327] Updated weights for policy 1, policy_version 32650 (0.0009) -[2023-10-09 01:21:17,684][88327] Updated weights for policy 1, policy_version 32660 (0.0009) -[2023-10-09 01:21:18,062][88327] Updated weights for policy 1, policy_version 32670 (0.0010) -[2023-10-09 01:21:18,240][88326] Updated weights for policy 0, policy_version 32642 (0.0007) -[2023-10-09 01:21:18,620][88326] Updated weights for policy 0, policy_version 32652 (0.0009) -[2023-10-09 01:21:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 66879488. Throughput: 0: 1688.3, 1: 1685.3. Samples: 16731378. Policy #0 lag: (min: 1.0, avg: 10.8, max: 33.0) -[2023-10-09 01:21:18,974][87372] Avg episode reward: [(0, '5.630'), (1, '5.480')] -[2023-10-09 01:21:18,984][88326] Updated weights for policy 0, policy_version 32662 (0.0008) -[2023-10-09 01:21:19,355][88326] Updated weights for policy 0, policy_version 32672 (0.0007) -[2023-10-09 01:21:22,164][88327] Updated weights for policy 1, policy_version 32680 (0.0008) -[2023-10-09 01:21:22,527][88327] Updated weights for policy 1, policy_version 32690 (0.0008) -[2023-10-09 01:21:22,888][88327] Updated weights for policy 1, policy_version 32700 (0.0009) -[2023-10-09 01:21:23,310][88326] Updated weights for policy 0, policy_version 32682 (0.0007) -[2023-10-09 01:21:23,679][88326] Updated weights for policy 0, policy_version 32692 (0.0008) -[2023-10-09 01:21:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 66945024. Throughput: 0: 1692.5, 1: 1711.3. Samples: 16741922. Policy #0 lag: (min: 1.0, avg: 10.8, max: 33.0) -[2023-10-09 01:21:23,974][87372] Avg episode reward: [(0, '5.710'), (1, '5.230')] -[2023-10-09 01:21:24,042][88326] Updated weights for policy 0, policy_version 32702 (0.0007) -[2023-10-09 01:21:26,808][88327] Updated weights for policy 1, policy_version 32710 (0.0008) -[2023-10-09 01:21:27,169][88327] Updated weights for policy 1, policy_version 32720 (0.0008) -[2023-10-09 01:21:27,536][88327] Updated weights for policy 1, policy_version 32730 (0.0009) -[2023-10-09 01:21:28,070][88326] Updated weights for policy 0, policy_version 32712 (0.0008) -[2023-10-09 01:21:28,444][88326] Updated weights for policy 0, policy_version 32722 (0.0008) -[2023-10-09 01:21:28,819][88326] Updated weights for policy 0, policy_version 32732 (0.0007) -[2023-10-09 01:21:28,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 67010560. Throughput: 0: 1705.5, 1: 1700.0. Samples: 16762620. Policy #0 lag: (min: 1.0, avg: 10.8, max: 33.0) -[2023-10-09 01:21:28,975][87372] Avg episode reward: [(0, '5.760'), (1, '5.740')] -[2023-10-09 01:21:31,682][88327] Updated weights for policy 1, policy_version 32740 (0.0010) -[2023-10-09 01:21:32,047][88327] Updated weights for policy 1, policy_version 32750 (0.0010) -[2023-10-09 01:21:32,410][88327] Updated weights for policy 1, policy_version 32760 (0.0010) -[2023-10-09 01:21:32,882][88326] Updated weights for policy 0, policy_version 32742 (0.0008) -[2023-10-09 01:21:33,254][88326] Updated weights for policy 0, policy_version 32752 (0.0007) -[2023-10-09 01:21:33,627][88326] Updated weights for policy 0, policy_version 32762 (0.0007) -[2023-10-09 01:21:33,974][87372] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 67108864. Throughput: 0: 1686.9, 1: 1680.0. Samples: 16781938. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:21:33,975][87372] Avg episode reward: [(0, '5.720'), (1, '5.740')] -[2023-10-09 01:21:36,449][88327] Updated weights for policy 1, policy_version 32770 (0.0007) -[2023-10-09 01:21:36,805][88327] Updated weights for policy 1, policy_version 32780 (0.0007) -[2023-10-09 01:21:37,171][88327] Updated weights for policy 1, policy_version 32790 (0.0010) -[2023-10-09 01:21:37,478][88326] Updated weights for policy 0, policy_version 32772 (0.0007) -[2023-10-09 01:21:37,537][88327] Updated weights for policy 1, policy_version 32800 (0.0008) -[2023-10-09 01:21:37,845][88326] Updated weights for policy 0, policy_version 32782 (0.0008) -[2023-10-09 01:21:38,218][88326] Updated weights for policy 0, policy_version 32792 (0.0009) -[2023-10-09 01:21:38,974][87372] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 67174400. Throughput: 0: 1705.7, 1: 1708.8. Samples: 16793164. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:21:38,975][87372] Avg episode reward: [(0, '5.780'), (1, '5.770')] -[2023-10-09 01:21:41,604][88327] Updated weights for policy 1, policy_version 32810 (0.0007) -[2023-10-09 01:21:41,966][88327] Updated weights for policy 1, policy_version 32820 (0.0009) -[2023-10-09 01:21:42,286][88326] Updated weights for policy 0, policy_version 32802 (0.0011) -[2023-10-09 01:21:42,332][88327] Updated weights for policy 1, policy_version 32830 (0.0010) -[2023-10-09 01:21:42,665][88326] Updated weights for policy 0, policy_version 32812 (0.0011) -[2023-10-09 01:21:43,023][88326] Updated weights for policy 0, policy_version 32822 (0.0010) -[2023-10-09 01:21:43,400][88326] Updated weights for policy 0, policy_version 32832 (0.0009) -[2023-10-09 01:21:43,974][87372] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 67239936. Throughput: 0: 1705.5, 1: 1692.2. Samples: 16813144. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:21:43,975][87372] Avg episode reward: [(0, '5.570'), (1, '5.600')] -[2023-10-09 01:21:46,413][88327] Updated weights for policy 1, policy_version 32840 (0.0009) -[2023-10-09 01:21:46,783][88327] Updated weights for policy 1, policy_version 32850 (0.0009) -[2023-10-09 01:21:47,145][88327] Updated weights for policy 1, policy_version 32860 (0.0007) -[2023-10-09 01:21:47,416][88326] Updated weights for policy 0, policy_version 32842 (0.0011) -[2023-10-09 01:21:47,787][88326] Updated weights for policy 0, policy_version 32852 (0.0007) -[2023-10-09 01:21:48,166][88326] Updated weights for policy 0, policy_version 32862 (0.0008) -[2023-10-09 01:21:48,974][87372] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 67305472. Throughput: 0: 1679.2, 1: 1690.0. Samples: 16832478. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:21:48,975][87372] Avg episode reward: [(0, '5.570'), (1, '5.440')] -[2023-10-09 01:21:51,171][88327] Updated weights for policy 1, policy_version 32870 (0.0009) -[2023-10-09 01:21:51,551][88327] Updated weights for policy 1, policy_version 32880 (0.0010) -[2023-10-09 01:21:51,919][88327] Updated weights for policy 1, policy_version 32890 (0.0007) -[2023-10-09 01:21:52,054][88326] Updated weights for policy 0, policy_version 32872 (0.0008) -[2023-10-09 01:21:52,428][88326] Updated weights for policy 0, policy_version 32882 (0.0009) -[2023-10-09 01:21:52,808][88326] Updated weights for policy 0, policy_version 32892 (0.0007) -[2023-10-09 01:21:53,974][87372] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 67371008. Throughput: 0: 1709.1, 1: 1698.3. Samples: 16843970. Policy #0 lag: (min: 17.0, avg: 35.8, max: 49.0) -[2023-10-09 01:21:53,975][87372] Avg episode reward: [(0, '5.570'), (1, '5.560')] -[2023-10-09 01:21:55,904][88327] Updated weights for policy 1, policy_version 32900 (0.0009) -[2023-10-09 01:21:56,270][88327] Updated weights for policy 1, policy_version 32910 (0.0009) -[2023-10-09 01:21:56,628][88327] Updated weights for policy 1, policy_version 32920 (0.0008) -[2023-10-09 01:21:56,861][88326] Updated weights for policy 0, policy_version 32902 (0.0007) -[2023-10-09 01:21:57,235][88326] Updated weights for policy 0, policy_version 32912 (0.0009) -[2023-10-09 01:21:57,592][88326] Updated weights for policy 0, policy_version 32922 (0.0008) -[2023-10-09 01:21:58,974][87372] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 67436544. Throughput: 0: 1692.0, 1: 1673.4. Samples: 16863104. Policy #0 lag: (min: 17.0, avg: 35.8, max: 49.0) -[2023-10-09 01:21:58,975][87372] Avg episode reward: [(0, '5.490'), (1, '5.820')] -[2023-10-09 01:22:00,663][88327] Updated weights for policy 1, policy_version 32930 (0.0007) -[2023-10-09 01:22:01,033][88327] Updated weights for policy 1, policy_version 32940 (0.0009) -[2023-10-09 01:22:01,399][88327] Updated weights for policy 1, policy_version 32950 (0.0010) -[2023-10-09 01:22:01,751][88327] Updated weights for policy 1, policy_version 32960 (0.0008) -[2023-10-09 01:22:01,782][88326] Updated weights for policy 0, policy_version 32932 (0.0007) -[2023-10-09 01:22:02,156][88326] Updated weights for policy 0, policy_version 32942 (0.0007) -[2023-10-09 01:22:02,525][88326] Updated weights for policy 0, policy_version 32952 (0.0007) -[2023-10-09 01:22:03,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 67502080. Throughput: 0: 1676.3, 1: 1700.7. Samples: 16883346. Policy #0 lag: (min: 17.0, avg: 35.8, max: 49.0) -[2023-10-09 01:22:03,975][87372] Avg episode reward: [(0, '5.780'), (1, '5.950')] -[2023-10-09 01:22:05,848][88327] Updated weights for policy 1, policy_version 32970 (0.0009) -[2023-10-09 01:22:06,202][88327] Updated weights for policy 1, policy_version 32980 (0.0007) -[2023-10-09 01:22:06,568][88327] Updated weights for policy 1, policy_version 32990 (0.0007) -[2023-10-09 01:22:06,686][88326] Updated weights for policy 0, policy_version 32962 (0.0009) -[2023-10-09 01:22:07,067][88326] Updated weights for policy 0, policy_version 32972 (0.0009) -[2023-10-09 01:22:07,430][88326] Updated weights for policy 0, policy_version 32982 (0.0008) -[2023-10-09 01:22:07,801][88326] Updated weights for policy 0, policy_version 32992 (0.0009) -[2023-10-09 01:22:08,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 67567616. Throughput: 0: 1698.3, 1: 1681.4. Samples: 16894006. Policy #0 lag: (min: 17.0, avg: 35.8, max: 49.0) -[2023-10-09 01:22:08,974][87372] Avg episode reward: [(0, '5.580'), (1, '5.830')] -[2023-10-09 01:22:10,654][88327] Updated weights for policy 1, policy_version 33000 (0.0007) -[2023-10-09 01:22:11,020][88327] Updated weights for policy 1, policy_version 33010 (0.0009) -[2023-10-09 01:22:11,392][88327] Updated weights for policy 1, policy_version 33020 (0.0009) -[2023-10-09 01:22:11,792][88326] Updated weights for policy 0, policy_version 33002 (0.0008) -[2023-10-09 01:22:12,164][88326] Updated weights for policy 0, policy_version 33012 (0.0008) -[2023-10-09 01:22:12,541][88326] Updated weights for policy 0, policy_version 33022 (0.0009) -[2023-10-09 01:22:13,974][87372] Fps is (10 sec: 13107.6, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 67633152. Throughput: 0: 1671.5, 1: 1679.7. Samples: 16913424. Policy #0 lag: (min: 17.0, avg: 35.8, max: 49.0) -[2023-10-09 01:22:13,975][87372] Avg episode reward: [(0, '6.250'), (1, '5.270')] -[2023-10-09 01:22:15,310][88327] Updated weights for policy 1, policy_version 33030 (0.0009) -[2023-10-09 01:22:15,674][88327] Updated weights for policy 1, policy_version 33040 (0.0008) -[2023-10-09 01:22:16,030][88327] Updated weights for policy 1, policy_version 33050 (0.0010) -[2023-10-09 01:22:16,565][88326] Updated weights for policy 0, policy_version 33032 (0.0010) -[2023-10-09 01:22:16,933][88326] Updated weights for policy 0, policy_version 33042 (0.0007) -[2023-10-09 01:22:17,302][88326] Updated weights for policy 0, policy_version 33052 (0.0008) -[2023-10-09 01:22:18,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 67698688. Throughput: 0: 1677.0, 1: 1699.1. Samples: 16933860. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:22:18,975][87372] Avg episode reward: [(0, '6.220'), (1, '5.100')] -[2023-10-09 01:22:20,040][88327] Updated weights for policy 1, policy_version 33060 (0.0008) -[2023-10-09 01:22:20,407][88327] Updated weights for policy 1, policy_version 33070 (0.0008) -[2023-10-09 01:22:20,768][88327] Updated weights for policy 1, policy_version 33080 (0.0009) -[2023-10-09 01:22:21,312][88326] Updated weights for policy 0, policy_version 33062 (0.0008) -[2023-10-09 01:22:21,684][88326] Updated weights for policy 0, policy_version 33072 (0.0009) -[2023-10-09 01:22:22,063][88326] Updated weights for policy 0, policy_version 33082 (0.0008) -[2023-10-09 01:22:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 67764224. Throughput: 0: 1687.1, 1: 1669.4. Samples: 16944206. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:22:23,975][87372] Avg episode reward: [(0, '6.130'), (1, '5.340')] -[2023-10-09 01:22:24,781][88327] Updated weights for policy 1, policy_version 33090 (0.0008) -[2023-10-09 01:22:25,155][88327] Updated weights for policy 1, policy_version 33100 (0.0009) -[2023-10-09 01:22:25,512][88327] Updated weights for policy 1, policy_version 33110 (0.0009) -[2023-10-09 01:22:25,873][88327] Updated weights for policy 1, policy_version 33120 (0.0008) -[2023-10-09 01:22:25,959][88326] Updated weights for policy 0, policy_version 33092 (0.0008) -[2023-10-09 01:22:26,328][88326] Updated weights for policy 0, policy_version 33102 (0.0010) -[2023-10-09 01:22:26,700][88326] Updated weights for policy 0, policy_version 33112 (0.0009) -[2023-10-09 01:22:28,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 67829760. Throughput: 0: 1660.7, 1: 1695.2. Samples: 16964164. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:22:28,975][87372] Avg episode reward: [(0, '6.750'), (1, '5.590')] -[2023-10-09 01:22:28,977][88088] Saving new best policy, reward=6.750! -[2023-10-09 01:22:29,837][88327] Updated weights for policy 1, policy_version 33130 (0.0008) -[2023-10-09 01:22:30,220][88327] Updated weights for policy 1, policy_version 33140 (0.0009) -[2023-10-09 01:22:30,583][88327] Updated weights for policy 1, policy_version 33150 (0.0008) -[2023-10-09 01:22:30,800][88326] Updated weights for policy 0, policy_version 33122 (0.0008) -[2023-10-09 01:22:31,175][88326] Updated weights for policy 0, policy_version 33132 (0.0008) -[2023-10-09 01:22:31,554][88326] Updated weights for policy 0, policy_version 33142 (0.0007) -[2023-10-09 01:22:31,923][88326] Updated weights for policy 0, policy_version 33152 (0.0009) -[2023-10-09 01:22:33,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 67895296. Throughput: 0: 1684.2, 1: 1703.0. Samples: 16984902. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:22:33,975][87372] Avg episode reward: [(0, '6.120'), (1, '5.400')] -[2023-10-09 01:22:33,983][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000033152_33947648.pth... -[2023-10-09 01:22:33,983][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000033152_33947648.pth... -[2023-10-09 01:22:34,023][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000031584_32342016.pth -[2023-10-09 01:22:34,024][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000031584_32342016.pth -[2023-10-09 01:22:34,655][88327] Updated weights for policy 1, policy_version 33160 (0.0008) -[2023-10-09 01:22:35,026][88327] Updated weights for policy 1, policy_version 33170 (0.0009) -[2023-10-09 01:22:35,382][88327] Updated weights for policy 1, policy_version 33180 (0.0008) -[2023-10-09 01:22:35,952][88326] Updated weights for policy 0, policy_version 33162 (0.0010) -[2023-10-09 01:22:36,328][88326] Updated weights for policy 0, policy_version 33172 (0.0009) -[2023-10-09 01:22:36,697][88326] Updated weights for policy 0, policy_version 33182 (0.0010) -[2023-10-09 01:22:38,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 67960832. Throughput: 0: 1672.9, 1: 1674.9. Samples: 16994620. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:22:38,975][87372] Avg episode reward: [(0, '6.100'), (1, '5.540')] -[2023-10-09 01:22:39,568][88327] Updated weights for policy 1, policy_version 33190 (0.0009) -[2023-10-09 01:22:39,935][88327] Updated weights for policy 1, policy_version 33200 (0.0010) -[2023-10-09 01:22:40,294][88327] Updated weights for policy 1, policy_version 33210 (0.0007) -[2023-10-09 01:22:40,675][88326] Updated weights for policy 0, policy_version 33192 (0.0010) -[2023-10-09 01:22:41,043][88326] Updated weights for policy 0, policy_version 33202 (0.0009) -[2023-10-09 01:22:41,416][88326] Updated weights for policy 0, policy_version 33212 (0.0011) -[2023-10-09 01:22:43,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 68026368. Throughput: 0: 1675.8, 1: 1695.5. Samples: 17014810. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-10-09 01:22:43,975][87372] Avg episode reward: [(0, '6.270'), (1, '5.640')] -[2023-10-09 01:22:44,472][88327] Updated weights for policy 1, policy_version 33220 (0.0007) -[2023-10-09 01:22:44,844][88327] Updated weights for policy 1, policy_version 33230 (0.0007) -[2023-10-09 01:22:45,212][88327] Updated weights for policy 1, policy_version 33240 (0.0007) -[2023-10-09 01:22:45,617][88326] Updated weights for policy 0, policy_version 33222 (0.0008) -[2023-10-09 01:22:45,993][88326] Updated weights for policy 0, policy_version 33232 (0.0009) -[2023-10-09 01:22:46,362][88326] Updated weights for policy 0, policy_version 33242 (0.0010) -[2023-10-09 01:22:48,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 68091904. Throughput: 0: 1690.7, 1: 1693.5. Samples: 17035636. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-10-09 01:22:48,975][87372] Avg episode reward: [(0, '5.770'), (1, '5.450')] -[2023-10-09 01:22:49,142][88327] Updated weights for policy 1, policy_version 33250 (0.0009) -[2023-10-09 01:22:49,505][88327] Updated weights for policy 1, policy_version 33260 (0.0009) -[2023-10-09 01:22:49,858][88327] Updated weights for policy 1, policy_version 33270 (0.0010) -[2023-10-09 01:22:50,219][88327] Updated weights for policy 1, policy_version 33280 (0.0011) -[2023-10-09 01:22:50,371][88326] Updated weights for policy 0, policy_version 33252 (0.0008) -[2023-10-09 01:22:50,748][88326] Updated weights for policy 0, policy_version 33262 (0.0008) -[2023-10-09 01:22:51,104][88326] Updated weights for policy 0, policy_version 33272 (0.0011) -[2023-10-09 01:22:53,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 68157440. Throughput: 0: 1671.3, 1: 1682.4. Samples: 17044922. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-10-09 01:22:53,975][87372] Avg episode reward: [(0, '6.010'), (1, '5.380')] -[2023-10-09 01:22:54,413][88327] Updated weights for policy 1, policy_version 33290 (0.0009) -[2023-10-09 01:22:54,794][88327] Updated weights for policy 1, policy_version 33300 (0.0008) -[2023-10-09 01:22:55,069][88326] Updated weights for policy 0, policy_version 33282 (0.0010) -[2023-10-09 01:22:55,151][88327] Updated weights for policy 1, policy_version 33310 (0.0009) -[2023-10-09 01:22:55,443][88326] Updated weights for policy 0, policy_version 33292 (0.0008) -[2023-10-09 01:22:55,808][88326] Updated weights for policy 0, policy_version 33302 (0.0008) -[2023-10-09 01:22:56,175][88326] Updated weights for policy 0, policy_version 33312 (0.0008) -[2023-10-09 01:22:58,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 68222976. Throughput: 0: 1689.8, 1: 1695.0. Samples: 17065742. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-10-09 01:22:58,976][87372] Avg episode reward: [(0, '6.140'), (1, '5.630')] -[2023-10-09 01:22:59,219][88327] Updated weights for policy 1, policy_version 33320 (0.0009) -[2023-10-09 01:22:59,587][88327] Updated weights for policy 1, policy_version 33330 (0.0010) -[2023-10-09 01:22:59,953][88327] Updated weights for policy 1, policy_version 33340 (0.0008) -[2023-10-09 01:23:00,025][88326] Updated weights for policy 0, policy_version 33322 (0.0009) -[2023-10-09 01:23:00,386][88326] Updated weights for policy 0, policy_version 33332 (0.0008) -[2023-10-09 01:23:00,762][88326] Updated weights for policy 0, policy_version 33342 (0.0008) -[2023-10-09 01:23:03,863][88327] Updated weights for policy 1, policy_version 33350 (0.0008) -[2023-10-09 01:23:03,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 68288512. Throughput: 0: 1700.0, 1: 1696.0. Samples: 17086680. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-10-09 01:23:03,975][87372] Avg episode reward: [(0, '5.750'), (1, '4.820')] -[2023-10-09 01:23:04,222][88327] Updated weights for policy 1, policy_version 33360 (0.0009) -[2023-10-09 01:23:04,583][88327] Updated weights for policy 1, policy_version 33370 (0.0008) -[2023-10-09 01:23:04,831][88326] Updated weights for policy 0, policy_version 33352 (0.0010) -[2023-10-09 01:23:05,195][88326] Updated weights for policy 0, policy_version 33362 (0.0011) -[2023-10-09 01:23:05,565][88326] Updated weights for policy 0, policy_version 33372 (0.0009) -[2023-10-09 01:23:08,668][88327] Updated weights for policy 1, policy_version 33380 (0.0009) -[2023-10-09 01:23:08,974][87372] Fps is (10 sec: 13107.7, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 68354048. Throughput: 0: 1675.6, 1: 1696.0. Samples: 17095928. Policy #0 lag: (min: 27.0, avg: 32.4, max: 59.0) -[2023-10-09 01:23:08,974][87372] Avg episode reward: [(0, '5.740'), (1, '5.120')] -[2023-10-09 01:23:09,026][88327] Updated weights for policy 1, policy_version 33390 (0.0009) -[2023-10-09 01:23:09,394][88327] Updated weights for policy 1, policy_version 33400 (0.0009) -[2023-10-09 01:23:09,681][88326] Updated weights for policy 0, policy_version 33382 (0.0008) -[2023-10-09 01:23:10,058][88326] Updated weights for policy 0, policy_version 33392 (0.0008) -[2023-10-09 01:23:10,423][88326] Updated weights for policy 0, policy_version 33402 (0.0009) -[2023-10-09 01:23:13,439][88327] Updated weights for policy 1, policy_version 33410 (0.0009) -[2023-10-09 01:23:13,811][88327] Updated weights for policy 1, policy_version 33420 (0.0008) -[2023-10-09 01:23:13,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 68419584. Throughput: 0: 1700.4, 1: 1691.1. Samples: 17116780. Policy #0 lag: (min: 27.0, avg: 32.4, max: 59.0) -[2023-10-09 01:23:13,975][87372] Avg episode reward: [(0, '5.840'), (1, '6.110')] -[2023-10-09 01:23:14,176][88327] Updated weights for policy 1, policy_version 33430 (0.0008) -[2023-10-09 01:23:14,432][88326] Updated weights for policy 0, policy_version 33412 (0.0009) -[2023-10-09 01:23:14,542][88327] Updated weights for policy 1, policy_version 33440 (0.0008) -[2023-10-09 01:23:14,799][88326] Updated weights for policy 0, policy_version 33422 (0.0009) -[2023-10-09 01:23:15,164][88326] Updated weights for policy 0, policy_version 33432 (0.0010) -[2023-10-09 01:23:18,482][88327] Updated weights for policy 1, policy_version 33450 (0.0007) -[2023-10-09 01:23:18,853][88327] Updated weights for policy 1, policy_version 33460 (0.0007) -[2023-10-09 01:23:18,974][87372] Fps is (10 sec: 13106.8, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 68485120. Throughput: 0: 1707.4, 1: 1692.6. Samples: 17137902. Policy #0 lag: (min: 27.0, avg: 32.4, max: 59.0) -[2023-10-09 01:23:18,975][87372] Avg episode reward: [(0, '5.270'), (1, '5.060')] -[2023-10-09 01:23:19,208][88327] Updated weights for policy 1, policy_version 33470 (0.0010) -[2023-10-09 01:23:19,246][88326] Updated weights for policy 0, policy_version 33442 (0.0009) -[2023-10-09 01:23:19,606][88326] Updated weights for policy 0, policy_version 33452 (0.0009) -[2023-10-09 01:23:19,985][88326] Updated weights for policy 0, policy_version 33462 (0.0008) -[2023-10-09 01:23:20,355][88326] Updated weights for policy 0, policy_version 33472 (0.0008) -[2023-10-09 01:23:23,405][88327] Updated weights for policy 1, policy_version 33480 (0.0009) -[2023-10-09 01:23:23,771][88327] Updated weights for policy 1, policy_version 33490 (0.0008) -[2023-10-09 01:23:23,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 68550656. Throughput: 0: 1692.6, 1: 1698.1. Samples: 17147204. Policy #0 lag: (min: 27.0, avg: 32.4, max: 59.0) -[2023-10-09 01:23:23,975][87372] Avg episode reward: [(0, '5.580'), (1, '5.290')] -[2023-10-09 01:23:24,142][88327] Updated weights for policy 1, policy_version 33500 (0.0009) -[2023-10-09 01:23:24,223][88326] Updated weights for policy 0, policy_version 33482 (0.0008) -[2023-10-09 01:23:24,593][88326] Updated weights for policy 0, policy_version 33492 (0.0008) -[2023-10-09 01:23:24,960][88326] Updated weights for policy 0, policy_version 33502 (0.0007) -[2023-10-09 01:23:28,027][88327] Updated weights for policy 1, policy_version 33510 (0.0010) -[2023-10-09 01:23:28,398][88327] Updated weights for policy 1, policy_version 33520 (0.0011) -[2023-10-09 01:23:28,763][88327] Updated weights for policy 1, policy_version 33530 (0.0008) -[2023-10-09 01:23:28,891][88326] Updated weights for policy 0, policy_version 33512 (0.0008) -[2023-10-09 01:23:28,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13329.3). Total num frames: 68616192. Throughput: 0: 1708.7, 1: 1703.6. Samples: 17168360. Policy #0 lag: (min: 27.0, avg: 32.4, max: 59.0) -[2023-10-09 01:23:28,976][87372] Avg episode reward: [(0, '5.640'), (1, '5.580')] -[2023-10-09 01:23:29,261][88326] Updated weights for policy 0, policy_version 33522 (0.0008) -[2023-10-09 01:23:29,622][88326] Updated weights for policy 0, policy_version 33532 (0.0008) -[2023-10-09 01:23:32,866][88327] Updated weights for policy 1, policy_version 33540 (0.0009) -[2023-10-09 01:23:33,234][88327] Updated weights for policy 1, policy_version 33550 (0.0007) -[2023-10-09 01:23:33,599][88327] Updated weights for policy 1, policy_version 33560 (0.0009) -[2023-10-09 01:23:33,806][88326] Updated weights for policy 0, policy_version 33542 (0.0008) -[2023-10-09 01:23:33,974][87372] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 68714496. Throughput: 0: 1709.9, 1: 1690.8. Samples: 17188666. Policy #0 lag: (min: 1.0, avg: 5.5, max: 33.0) -[2023-10-09 01:23:33,975][87372] Avg episode reward: [(0, '5.580'), (1, '5.080')] -[2023-10-09 01:23:34,182][88326] Updated weights for policy 0, policy_version 33552 (0.0007) -[2023-10-09 01:23:34,556][88326] Updated weights for policy 0, policy_version 33562 (0.0008) -[2023-10-09 01:23:37,513][88327] Updated weights for policy 1, policy_version 33570 (0.0008) -[2023-10-09 01:23:37,877][88327] Updated weights for policy 1, policy_version 33580 (0.0007) -[2023-10-09 01:23:38,247][88327] Updated weights for policy 1, policy_version 33590 (0.0009) -[2023-10-09 01:23:38,580][88326] Updated weights for policy 0, policy_version 33572 (0.0008) -[2023-10-09 01:23:38,617][88327] Updated weights for policy 1, policy_version 33600 (0.0008) -[2023-10-09 01:23:38,951][88326] Updated weights for policy 0, policy_version 33582 (0.0007) -[2023-10-09 01:23:38,974][87372] Fps is (10 sec: 16384.2, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 68780032. Throughput: 0: 1701.5, 1: 1707.6. Samples: 17198334. Policy #0 lag: (min: 1.0, avg: 5.5, max: 33.0) -[2023-10-09 01:23:38,975][87372] Avg episode reward: [(0, '5.910'), (1, '5.460')] -[2023-10-09 01:23:39,327][88326] Updated weights for policy 0, policy_version 33592 (0.0009) -[2023-10-09 01:23:42,726][88327] Updated weights for policy 1, policy_version 33610 (0.0008) -[2023-10-09 01:23:43,095][88327] Updated weights for policy 1, policy_version 33620 (0.0010) -[2023-10-09 01:23:43,448][88326] Updated weights for policy 0, policy_version 33602 (0.0009) -[2023-10-09 01:23:43,465][88327] Updated weights for policy 1, policy_version 33630 (0.0009) -[2023-10-09 01:23:43,817][88326] Updated weights for policy 0, policy_version 33612 (0.0007) -[2023-10-09 01:23:43,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 68845568. Throughput: 0: 1695.7, 1: 1709.8. Samples: 17218992. Policy #0 lag: (min: 1.0, avg: 5.5, max: 33.0) -[2023-10-09 01:23:43,975][87372] Avg episode reward: [(0, '5.700'), (1, '5.890')] -[2023-10-09 01:23:44,191][88326] Updated weights for policy 0, policy_version 33622 (0.0009) -[2023-10-09 01:23:44,563][88326] Updated weights for policy 0, policy_version 33632 (0.0009) -[2023-10-09 01:23:47,487][88327] Updated weights for policy 1, policy_version 33640 (0.0008) -[2023-10-09 01:23:47,857][88327] Updated weights for policy 1, policy_version 33650 (0.0007) -[2023-10-09 01:23:48,224][88327] Updated weights for policy 1, policy_version 33660 (0.0010) -[2023-10-09 01:23:48,825][88326] Updated weights for policy 0, policy_version 33642 (0.0007) -[2023-10-09 01:23:48,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 68911104. Throughput: 0: 1693.9, 1: 1685.2. Samples: 17238736. Policy #0 lag: (min: 1.0, avg: 5.5, max: 33.0) -[2023-10-09 01:23:48,975][87372] Avg episode reward: [(0, '5.290'), (1, '5.590')] -[2023-10-09 01:23:49,196][88326] Updated weights for policy 0, policy_version 33652 (0.0007) -[2023-10-09 01:23:49,561][88326] Updated weights for policy 0, policy_version 33662 (0.0007) -[2023-10-09 01:23:52,350][88327] Updated weights for policy 1, policy_version 33670 (0.0008) -[2023-10-09 01:23:52,720][88327] Updated weights for policy 1, policy_version 33680 (0.0007) -[2023-10-09 01:23:53,084][88327] Updated weights for policy 1, policy_version 33690 (0.0010) -[2023-10-09 01:23:53,611][88326] Updated weights for policy 0, policy_version 33672 (0.0007) -[2023-10-09 01:23:53,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 68976640. Throughput: 0: 1693.4, 1: 1703.1. Samples: 17248770. Policy #0 lag: (min: 1.0, avg: 5.5, max: 33.0) -[2023-10-09 01:23:53,975][87372] Avg episode reward: [(0, '5.740'), (1, '5.380')] -[2023-10-09 01:23:53,983][88326] Updated weights for policy 0, policy_version 33682 (0.0007) -[2023-10-09 01:23:54,351][88326] Updated weights for policy 0, policy_version 33692 (0.0009) -[2023-10-09 01:23:56,961][88327] Updated weights for policy 1, policy_version 33700 (0.0009) -[2023-10-09 01:23:57,325][88327] Updated weights for policy 1, policy_version 33710 (0.0009) -[2023-10-09 01:23:57,692][88327] Updated weights for policy 1, policy_version 33720 (0.0008) -[2023-10-09 01:23:58,294][88326] Updated weights for policy 0, policy_version 33702 (0.0007) -[2023-10-09 01:23:58,665][88326] Updated weights for policy 0, policy_version 33712 (0.0007) -[2023-10-09 01:23:58,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 69042176. Throughput: 0: 1699.6, 1: 1697.0. Samples: 17269626. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:23:58,975][87372] Avg episode reward: [(0, '5.870'), (1, '5.650')] -[2023-10-09 01:23:59,023][88326] Updated weights for policy 0, policy_version 33722 (0.0010) -[2023-10-09 01:24:01,924][88327] Updated weights for policy 1, policy_version 33730 (0.0009) -[2023-10-09 01:24:02,296][88327] Updated weights for policy 1, policy_version 33740 (0.0007) -[2023-10-09 01:24:02,671][88327] Updated weights for policy 1, policy_version 33750 (0.0007) -[2023-10-09 01:24:03,038][88327] Updated weights for policy 1, policy_version 33760 (0.0007) -[2023-10-09 01:24:03,120][88326] Updated weights for policy 0, policy_version 33732 (0.0010) -[2023-10-09 01:24:03,481][88326] Updated weights for policy 0, policy_version 33742 (0.0010) -[2023-10-09 01:24:03,847][88326] Updated weights for policy 0, policy_version 33752 (0.0008) -[2023-10-09 01:24:03,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 69107712. Throughput: 0: 1690.5, 1: 1669.9. Samples: 17289118. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:24:03,975][87372] Avg episode reward: [(0, '5.860'), (1, '5.430')] -[2023-10-09 01:24:07,046][88327] Updated weights for policy 1, policy_version 33770 (0.0008) -[2023-10-09 01:24:07,409][88327] Updated weights for policy 1, policy_version 33780 (0.0009) -[2023-10-09 01:24:07,728][88326] Updated weights for policy 0, policy_version 33762 (0.0008) -[2023-10-09 01:24:07,781][88327] Updated weights for policy 1, policy_version 33790 (0.0008) -[2023-10-09 01:24:08,091][88326] Updated weights for policy 0, policy_version 33772 (0.0008) -[2023-10-09 01:24:08,461][88326] Updated weights for policy 0, policy_version 33782 (0.0008) -[2023-10-09 01:24:08,828][88326] Updated weights for policy 0, policy_version 33792 (0.0007) -[2023-10-09 01:24:08,974][87372] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 69206016. Throughput: 0: 1697.3, 1: 1695.2. Samples: 17299866. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:24:08,975][87372] Avg episode reward: [(0, '5.900'), (1, '5.720')] -[2023-10-09 01:24:12,147][88327] Updated weights for policy 1, policy_version 33800 (0.0010) -[2023-10-09 01:24:12,519][88327] Updated weights for policy 1, policy_version 33810 (0.0008) -[2023-10-09 01:24:12,790][88326] Updated weights for policy 0, policy_version 33802 (0.0007) -[2023-10-09 01:24:12,877][88327] Updated weights for policy 1, policy_version 33820 (0.0009) -[2023-10-09 01:24:13,157][88326] Updated weights for policy 0, policy_version 33812 (0.0009) -[2023-10-09 01:24:13,526][88326] Updated weights for policy 0, policy_version 33822 (0.0007) -[2023-10-09 01:24:13,974][87372] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 69271552. Throughput: 0: 1701.1, 1: 1673.2. Samples: 17320202. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:24:13,975][87372] Avg episode reward: [(0, '5.540'), (1, '6.140')] -[2023-10-09 01:24:16,882][88327] Updated weights for policy 1, policy_version 33830 (0.0007) -[2023-10-09 01:24:17,249][88327] Updated weights for policy 1, policy_version 33840 (0.0007) -[2023-10-09 01:24:17,546][88326] Updated weights for policy 0, policy_version 33832 (0.0008) -[2023-10-09 01:24:17,610][88327] Updated weights for policy 1, policy_version 33850 (0.0008) -[2023-10-09 01:24:17,912][88326] Updated weights for policy 0, policy_version 33842 (0.0009) -[2023-10-09 01:24:18,281][88326] Updated weights for policy 0, policy_version 33852 (0.0009) -[2023-10-09 01:24:18,974][87372] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 69337088. Throughput: 0: 1676.0, 1: 1663.2. Samples: 17338928. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:24:18,974][87372] Avg episode reward: [(0, '5.850'), (1, '5.720')] -[2023-10-09 01:24:21,663][88327] Updated weights for policy 1, policy_version 33860 (0.0009) -[2023-10-09 01:24:22,025][88327] Updated weights for policy 1, policy_version 33870 (0.0010) -[2023-10-09 01:24:22,390][88327] Updated weights for policy 1, policy_version 33880 (0.0008) -[2023-10-09 01:24:22,434][88326] Updated weights for policy 0, policy_version 33862 (0.0009) -[2023-10-09 01:24:22,815][88326] Updated weights for policy 0, policy_version 33872 (0.0009) -[2023-10-09 01:24:23,189][88326] Updated weights for policy 0, policy_version 33882 (0.0007) -[2023-10-09 01:24:23,974][87372] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 69402624. Throughput: 0: 1700.8, 1: 1678.1. Samples: 17350386. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:24:23,975][87372] Avg episode reward: [(0, '5.320'), (1, '5.910')] -[2023-10-09 01:24:26,502][88327] Updated weights for policy 1, policy_version 33890 (0.0008) -[2023-10-09 01:24:26,878][88327] Updated weights for policy 1, policy_version 33900 (0.0008) -[2023-10-09 01:24:27,251][88327] Updated weights for policy 1, policy_version 33910 (0.0009) -[2023-10-09 01:24:27,284][88326] Updated weights for policy 0, policy_version 33892 (0.0007) -[2023-10-09 01:24:27,615][88327] Updated weights for policy 1, policy_version 33920 (0.0007) -[2023-10-09 01:24:27,645][88326] Updated weights for policy 0, policy_version 33902 (0.0008) -[2023-10-09 01:24:28,019][88326] Updated weights for policy 0, policy_version 33912 (0.0007) -[2023-10-09 01:24:28,974][87372] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 69468160. Throughput: 0: 1701.8, 1: 1656.0. Samples: 17370092. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:24:28,975][87372] Avg episode reward: [(0, '5.610'), (1, '5.780')] -[2023-10-09 01:24:31,578][88327] Updated weights for policy 1, policy_version 33930 (0.0008) -[2023-10-09 01:24:31,942][88327] Updated weights for policy 1, policy_version 33940 (0.0007) -[2023-10-09 01:24:31,970][88326] Updated weights for policy 0, policy_version 33922 (0.0008) -[2023-10-09 01:24:32,299][88327] Updated weights for policy 1, policy_version 33950 (0.0007) -[2023-10-09 01:24:32,344][88326] Updated weights for policy 0, policy_version 33932 (0.0009) -[2023-10-09 01:24:32,716][88326] Updated weights for policy 0, policy_version 33942 (0.0007) -[2023-10-09 01:24:33,084][88326] Updated weights for policy 0, policy_version 33952 (0.0007) -[2023-10-09 01:24:33,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 69533696. Throughput: 0: 1671.7, 1: 1673.2. Samples: 17389258. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:24:33,975][87372] Avg episode reward: [(0, '5.870'), (1, '5.390')] -[2023-10-09 01:24:33,987][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000033952_34766848.pth... -[2023-10-09 01:24:33,988][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000033952_34766848.pth... -[2023-10-09 01:24:34,025][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000032384_33161216.pth -[2023-10-09 01:24:34,027][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000032352_33128448.pth -[2023-10-09 01:24:36,334][88327] Updated weights for policy 1, policy_version 33960 (0.0010) -[2023-10-09 01:24:36,699][88327] Updated weights for policy 1, policy_version 33970 (0.0010) -[2023-10-09 01:24:37,068][88327] Updated weights for policy 1, policy_version 33980 (0.0009) -[2023-10-09 01:24:37,175][88326] Updated weights for policy 0, policy_version 33962 (0.0007) -[2023-10-09 01:24:37,551][88326] Updated weights for policy 0, policy_version 33972 (0.0007) -[2023-10-09 01:24:37,920][88326] Updated weights for policy 0, policy_version 33982 (0.0007) -[2023-10-09 01:24:38,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 69599232. Throughput: 0: 1703.6, 1: 1675.8. Samples: 17400840. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:24:38,975][87372] Avg episode reward: [(0, '6.080'), (1, '5.610')] -[2023-10-09 01:24:41,070][88327] Updated weights for policy 1, policy_version 33990 (0.0008) -[2023-10-09 01:24:41,436][88327] Updated weights for policy 1, policy_version 34000 (0.0009) -[2023-10-09 01:24:41,801][88327] Updated weights for policy 1, policy_version 34010 (0.0010) -[2023-10-09 01:24:42,019][88326] Updated weights for policy 0, policy_version 33992 (0.0009) -[2023-10-09 01:24:42,381][88326] Updated weights for policy 0, policy_version 34002 (0.0007) -[2023-10-09 01:24:42,750][88326] Updated weights for policy 0, policy_version 34012 (0.0009) -[2023-10-09 01:24:43,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 69664768. Throughput: 0: 1685.5, 1: 1655.1. Samples: 17419952. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:24:43,975][87372] Avg episode reward: [(0, '6.240'), (1, '6.110')] -[2023-10-09 01:24:45,949][88327] Updated weights for policy 1, policy_version 34020 (0.0008) -[2023-10-09 01:24:46,313][88327] Updated weights for policy 1, policy_version 34030 (0.0008) -[2023-10-09 01:24:46,681][88327] Updated weights for policy 1, policy_version 34040 (0.0007) -[2023-10-09 01:24:46,764][88326] Updated weights for policy 0, policy_version 34022 (0.0008) -[2023-10-09 01:24:47,124][88326] Updated weights for policy 0, policy_version 34032 (0.0010) -[2023-10-09 01:24:47,500][88326] Updated weights for policy 0, policy_version 34042 (0.0008) -[2023-10-09 01:24:48,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 69730304. Throughput: 0: 1673.6, 1: 1680.1. Samples: 17440038. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:24:48,975][87372] Avg episode reward: [(0, '6.340'), (1, '5.730')] -[2023-10-09 01:24:50,792][88327] Updated weights for policy 1, policy_version 34050 (0.0008) -[2023-10-09 01:24:51,162][88327] Updated weights for policy 1, policy_version 34060 (0.0007) -[2023-10-09 01:24:51,536][88327] Updated weights for policy 1, policy_version 34070 (0.0007) -[2023-10-09 01:24:51,607][88326] Updated weights for policy 0, policy_version 34052 (0.0008) -[2023-10-09 01:24:51,891][88327] Updated weights for policy 1, policy_version 34080 (0.0008) -[2023-10-09 01:24:51,981][88326] Updated weights for policy 0, policy_version 34062 (0.0007) -[2023-10-09 01:24:52,345][88326] Updated weights for policy 0, policy_version 34072 (0.0007) -[2023-10-09 01:24:53,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 69795840. Throughput: 0: 1696.5, 1: 1668.7. Samples: 17451298. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:24:53,975][87372] Avg episode reward: [(0, '5.700'), (1, '6.180')] -[2023-10-09 01:24:55,880][88327] Updated weights for policy 1, policy_version 34090 (0.0009) -[2023-10-09 01:24:56,193][88326] Updated weights for policy 0, policy_version 34082 (0.0008) -[2023-10-09 01:24:56,241][88327] Updated weights for policy 1, policy_version 34100 (0.0009) -[2023-10-09 01:24:56,565][88326] Updated weights for policy 0, policy_version 34092 (0.0008) -[2023-10-09 01:24:56,605][88327] Updated weights for policy 1, policy_version 34110 (0.0009) -[2023-10-09 01:24:56,929][88326] Updated weights for policy 0, policy_version 34102 (0.0007) -[2023-10-09 01:24:57,308][88326] Updated weights for policy 0, policy_version 34112 (0.0007) -[2023-10-09 01:24:58,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 69861376. Throughput: 0: 1665.6, 1: 1670.1. Samples: 17470306. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:24:58,975][87372] Avg episode reward: [(0, '5.480'), (1, '6.090')] -[2023-10-09 01:25:00,782][88327] Updated weights for policy 1, policy_version 34120 (0.0008) -[2023-10-09 01:25:01,144][88327] Updated weights for policy 1, policy_version 34130 (0.0008) -[2023-10-09 01:25:01,486][88326] Updated weights for policy 0, policy_version 34122 (0.0008) -[2023-10-09 01:25:01,519][88327] Updated weights for policy 1, policy_version 34140 (0.0008) -[2023-10-09 01:25:01,858][88326] Updated weights for policy 0, policy_version 34132 (0.0009) -[2023-10-09 01:25:02,219][88326] Updated weights for policy 0, policy_version 34142 (0.0009) -[2023-10-09 01:25:03,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 69926912. Throughput: 0: 1686.2, 1: 1694.5. Samples: 17491060. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:25:03,975][87372] Avg episode reward: [(0, '5.950'), (1, '6.180')] -[2023-10-09 01:25:05,306][88327] Updated weights for policy 1, policy_version 34150 (0.0009) -[2023-10-09 01:25:05,668][88327] Updated weights for policy 1, policy_version 34160 (0.0009) -[2023-10-09 01:25:06,038][88327] Updated weights for policy 1, policy_version 34170 (0.0008) -[2023-10-09 01:25:06,190][88326] Updated weights for policy 0, policy_version 34152 (0.0008) -[2023-10-09 01:25:06,558][88326] Updated weights for policy 0, policy_version 34162 (0.0009) -[2023-10-09 01:25:06,927][88326] Updated weights for policy 0, policy_version 34172 (0.0008) -[2023-10-09 01:25:08,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 69992448. Throughput: 0: 1683.2, 1: 1670.8. Samples: 17501316. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-09 01:25:08,975][87372] Avg episode reward: [(0, '5.440'), (1, '6.160')] -[2023-10-09 01:25:10,009][88327] Updated weights for policy 1, policy_version 34180 (0.0008) -[2023-10-09 01:25:10,375][88327] Updated weights for policy 1, policy_version 34190 (0.0010) -[2023-10-09 01:25:10,745][88327] Updated weights for policy 1, policy_version 34200 (0.0011) -[2023-10-09 01:25:11,002][88326] Updated weights for policy 0, policy_version 34182 (0.0008) -[2023-10-09 01:25:11,379][88326] Updated weights for policy 0, policy_version 34192 (0.0011) -[2023-10-09 01:25:11,739][88326] Updated weights for policy 0, policy_version 34202 (0.0010) -[2023-10-09 01:25:13,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 70057984. Throughput: 0: 1665.7, 1: 1689.0. Samples: 17521052. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-09 01:25:13,975][87372] Avg episode reward: [(0, '5.950'), (1, '6.050')] -[2023-10-09 01:25:14,718][88327] Updated weights for policy 1, policy_version 34210 (0.0007) -[2023-10-09 01:25:15,083][88327] Updated weights for policy 1, policy_version 34220 (0.0007) -[2023-10-09 01:25:15,453][88327] Updated weights for policy 1, policy_version 34230 (0.0008) -[2023-10-09 01:25:15,722][88326] Updated weights for policy 0, policy_version 34212 (0.0008) -[2023-10-09 01:25:15,818][88327] Updated weights for policy 1, policy_version 34240 (0.0009) -[2023-10-09 01:25:16,098][88326] Updated weights for policy 0, policy_version 34222 (0.0008) -[2023-10-09 01:25:16,469][88326] Updated weights for policy 0, policy_version 34232 (0.0009) -[2023-10-09 01:25:18,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 70123520. Throughput: 0: 1695.7, 1: 1695.2. Samples: 17541848. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-09 01:25:18,975][87372] Avg episode reward: [(0, '5.230'), (1, '6.220')] -[2023-10-09 01:25:19,997][88327] Updated weights for policy 1, policy_version 34250 (0.0007) -[2023-10-09 01:25:20,361][88327] Updated weights for policy 1, policy_version 34260 (0.0008) -[2023-10-09 01:25:20,588][88326] Updated weights for policy 0, policy_version 34242 (0.0008) -[2023-10-09 01:25:20,732][88327] Updated weights for policy 1, policy_version 34270 (0.0009) -[2023-10-09 01:25:20,968][88326] Updated weights for policy 0, policy_version 34252 (0.0009) -[2023-10-09 01:25:21,333][88326] Updated weights for policy 0, policy_version 34262 (0.0010) -[2023-10-09 01:25:21,697][88326] Updated weights for policy 0, policy_version 34272 (0.0008) -[2023-10-09 01:25:23,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 70189056. Throughput: 0: 1672.3, 1: 1674.3. Samples: 17551436. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-09 01:25:23,975][87372] Avg episode reward: [(0, '5.400'), (1, '5.750')] -[2023-10-09 01:25:24,720][88327] Updated weights for policy 1, policy_version 34280 (0.0007) -[2023-10-09 01:25:25,083][88327] Updated weights for policy 1, policy_version 34290 (0.0007) -[2023-10-09 01:25:25,443][88327] Updated weights for policy 1, policy_version 34300 (0.0009) -[2023-10-09 01:25:25,687][88326] Updated weights for policy 0, policy_version 34282 (0.0008) -[2023-10-09 01:25:26,056][88326] Updated weights for policy 0, policy_version 34292 (0.0010) -[2023-10-09 01:25:26,424][88326] Updated weights for policy 0, policy_version 34302 (0.0008) -[2023-10-09 01:25:28,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 70254592. Throughput: 0: 1671.3, 1: 1703.9. Samples: 17571838. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-09 01:25:28,975][87372] Avg episode reward: [(0, '5.990'), (1, '5.730')] -[2023-10-09 01:25:29,565][88327] Updated weights for policy 1, policy_version 34310 (0.0008) -[2023-10-09 01:25:29,935][88327] Updated weights for policy 1, policy_version 34320 (0.0007) -[2023-10-09 01:25:30,295][88327] Updated weights for policy 1, policy_version 34330 (0.0008) -[2023-10-09 01:25:30,650][88326] Updated weights for policy 0, policy_version 34312 (0.0007) -[2023-10-09 01:25:31,017][88326] Updated weights for policy 0, policy_version 34322 (0.0009) -[2023-10-09 01:25:31,383][88326] Updated weights for policy 0, policy_version 34332 (0.0007) -[2023-10-09 01:25:33,974][87372] Fps is (10 sec: 13106.8, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 70320128. Throughput: 0: 1688.8, 1: 1706.3. Samples: 17592820. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:25:33,975][87372] Avg episode reward: [(0, '5.980'), (1, '5.740')] -[2023-10-09 01:25:34,394][88327] Updated weights for policy 1, policy_version 34340 (0.0008) -[2023-10-09 01:25:34,763][88327] Updated weights for policy 1, policy_version 34350 (0.0007) -[2023-10-09 01:25:35,124][88327] Updated weights for policy 1, policy_version 34360 (0.0008) -[2023-10-09 01:25:35,411][88326] Updated weights for policy 0, policy_version 34342 (0.0007) -[2023-10-09 01:25:35,786][88326] Updated weights for policy 0, policy_version 34352 (0.0009) -[2023-10-09 01:25:36,154][88326] Updated weights for policy 0, policy_version 34362 (0.0007) -[2023-10-09 01:25:38,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 70385664. Throughput: 0: 1662.4, 1: 1689.0. Samples: 17602110. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:25:38,975][87372] Avg episode reward: [(0, '6.090'), (1, '5.590')] -[2023-10-09 01:25:39,283][88327] Updated weights for policy 1, policy_version 34370 (0.0007) -[2023-10-09 01:25:39,655][88327] Updated weights for policy 1, policy_version 34380 (0.0008) -[2023-10-09 01:25:40,020][88327] Updated weights for policy 1, policy_version 34390 (0.0007) -[2023-10-09 01:25:40,187][88326] Updated weights for policy 0, policy_version 34372 (0.0008) -[2023-10-09 01:25:40,382][88327] Updated weights for policy 1, policy_version 34400 (0.0007) -[2023-10-09 01:25:40,553][88326] Updated weights for policy 0, policy_version 34382 (0.0008) -[2023-10-09 01:25:40,922][88326] Updated weights for policy 0, policy_version 34392 (0.0009) -[2023-10-09 01:25:43,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 70451200. Throughput: 0: 1683.7, 1: 1701.4. Samples: 17622638. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:25:43,975][87372] Avg episode reward: [(0, '6.110'), (1, '5.130')] -[2023-10-09 01:25:44,333][88327] Updated weights for policy 1, policy_version 34410 (0.0009) -[2023-10-09 01:25:44,692][88327] Updated weights for policy 1, policy_version 34420 (0.0010) -[2023-10-09 01:25:44,747][88326] Updated weights for policy 0, policy_version 34402 (0.0008) -[2023-10-09 01:25:45,068][88327] Updated weights for policy 1, policy_version 34430 (0.0008) -[2023-10-09 01:25:45,118][88326] Updated weights for policy 0, policy_version 34412 (0.0007) -[2023-10-09 01:25:45,481][88326] Updated weights for policy 0, policy_version 34422 (0.0007) -[2023-10-09 01:25:45,853][88326] Updated weights for policy 0, policy_version 34432 (0.0010) -[2023-10-09 01:25:48,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 70516736. Throughput: 0: 1690.7, 1: 1699.8. Samples: 17643632. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:25:48,975][87372] Avg episode reward: [(0, '6.320'), (1, '5.540')] -[2023-10-09 01:25:49,121][88327] Updated weights for policy 1, policy_version 34440 (0.0008) -[2023-10-09 01:25:49,508][88327] Updated weights for policy 1, policy_version 34450 (0.0008) -[2023-10-09 01:25:49,873][88327] Updated weights for policy 1, policy_version 34460 (0.0008) -[2023-10-09 01:25:49,916][88326] Updated weights for policy 0, policy_version 34442 (0.0007) -[2023-10-09 01:25:50,295][88326] Updated weights for policy 0, policy_version 34452 (0.0008) -[2023-10-09 01:25:50,658][88326] Updated weights for policy 0, policy_version 34462 (0.0011) -[2023-10-09 01:25:53,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 70582272. Throughput: 0: 1668.3, 1: 1688.6. Samples: 17652378. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:25:53,975][87372] Avg episode reward: [(0, '5.910'), (1, '5.540')] -[2023-10-09 01:25:53,982][88327] Updated weights for policy 1, policy_version 34470 (0.0008) -[2023-10-09 01:25:54,356][88327] Updated weights for policy 1, policy_version 34480 (0.0009) -[2023-10-09 01:25:54,661][88326] Updated weights for policy 0, policy_version 34472 (0.0008) -[2023-10-09 01:25:54,722][88327] Updated weights for policy 1, policy_version 34490 (0.0007) -[2023-10-09 01:25:55,019][88326] Updated weights for policy 0, policy_version 34482 (0.0009) -[2023-10-09 01:25:55,398][88326] Updated weights for policy 0, policy_version 34492 (0.0008) -[2023-10-09 01:25:58,873][88327] Updated weights for policy 1, policy_version 34500 (0.0008) -[2023-10-09 01:25:58,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 70647808. Throughput: 0: 1697.0, 1: 1690.6. Samples: 17673492. Policy #0 lag: (min: 31.0, avg: 31.4, max: 46.0) -[2023-10-09 01:25:58,974][87372] Avg episode reward: [(0, '6.070'), (1, '5.510')] -[2023-10-09 01:25:59,247][88327] Updated weights for policy 1, policy_version 34510 (0.0008) -[2023-10-09 01:25:59,505][88326] Updated weights for policy 0, policy_version 34502 (0.0008) -[2023-10-09 01:25:59,609][88327] Updated weights for policy 1, policy_version 34520 (0.0010) -[2023-10-09 01:25:59,873][88326] Updated weights for policy 0, policy_version 34512 (0.0008) -[2023-10-09 01:26:00,244][88326] Updated weights for policy 0, policy_version 34522 (0.0008) -[2023-10-09 01:26:03,368][88327] Updated weights for policy 1, policy_version 34530 (0.0008) -[2023-10-09 01:26:03,739][88327] Updated weights for policy 1, policy_version 34540 (0.0008) -[2023-10-09 01:26:03,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 70713344. Throughput: 0: 1698.1, 1: 1699.5. Samples: 17694738. Policy #0 lag: (min: 31.0, avg: 31.4, max: 46.0) -[2023-10-09 01:26:03,975][87372] Avg episode reward: [(0, '5.700'), (1, '6.400')] -[2023-10-09 01:26:04,097][88327] Updated weights for policy 1, policy_version 34550 (0.0008) -[2023-10-09 01:26:04,466][88327] Updated weights for policy 1, policy_version 34560 (0.0010) -[2023-10-09 01:26:04,589][88326] Updated weights for policy 0, policy_version 34532 (0.0009) -[2023-10-09 01:26:04,984][88326] Updated weights for policy 0, policy_version 34542 (0.0008) -[2023-10-09 01:26:05,347][88326] Updated weights for policy 0, policy_version 34552 (0.0008) -[2023-10-09 01:26:08,458][88327] Updated weights for policy 1, policy_version 34570 (0.0009) -[2023-10-09 01:26:08,825][88327] Updated weights for policy 1, policy_version 34580 (0.0008) -[2023-10-09 01:26:08,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 70778880. Throughput: 0: 1685.2, 1: 1699.6. Samples: 17703752. Policy #0 lag: (min: 31.0, avg: 31.4, max: 46.0) -[2023-10-09 01:26:08,974][87372] Avg episode reward: [(0, '5.490'), (1, '5.780')] -[2023-10-09 01:26:09,198][88327] Updated weights for policy 1, policy_version 34590 (0.0010) -[2023-10-09 01:26:09,307][88326] Updated weights for policy 0, policy_version 34562 (0.0009) -[2023-10-09 01:26:09,674][88326] Updated weights for policy 0, policy_version 34572 (0.0008) -[2023-10-09 01:26:10,051][88326] Updated weights for policy 0, policy_version 34582 (0.0008) -[2023-10-09 01:26:10,414][88326] Updated weights for policy 0, policy_version 34592 (0.0010) -[2023-10-09 01:26:13,213][88327] Updated weights for policy 1, policy_version 34600 (0.0009) -[2023-10-09 01:26:13,583][88327] Updated weights for policy 1, policy_version 34610 (0.0010) -[2023-10-09 01:26:13,949][88327] Updated weights for policy 1, policy_version 34620 (0.0008) -[2023-10-09 01:26:13,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 70844416. Throughput: 0: 1700.2, 1: 1694.7. Samples: 17724608. Policy #0 lag: (min: 31.0, avg: 31.4, max: 46.0) -[2023-10-09 01:26:13,975][87372] Avg episode reward: [(0, '5.780'), (1, '5.570')] -[2023-10-09 01:26:14,323][88326] Updated weights for policy 0, policy_version 34602 (0.0008) -[2023-10-09 01:26:14,693][88326] Updated weights for policy 0, policy_version 34612 (0.0010) -[2023-10-09 01:26:15,072][88326] Updated weights for policy 0, policy_version 34622 (0.0010) -[2023-10-09 01:26:17,814][88327] Updated weights for policy 1, policy_version 34630 (0.0007) -[2023-10-09 01:26:18,177][88327] Updated weights for policy 1, policy_version 34640 (0.0008) -[2023-10-09 01:26:18,533][88327] Updated weights for policy 1, policy_version 34650 (0.0007) -[2023-10-09 01:26:18,974][87372] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 70942720. Throughput: 0: 1698.3, 1: 1689.0. Samples: 17745250. Policy #0 lag: (min: 31.0, avg: 31.4, max: 46.0) -[2023-10-09 01:26:18,975][87372] Avg episode reward: [(0, '5.550'), (1, '5.910')] -[2023-10-09 01:26:19,064][88326] Updated weights for policy 0, policy_version 34632 (0.0009) -[2023-10-09 01:26:19,425][88326] Updated weights for policy 0, policy_version 34642 (0.0009) -[2023-10-09 01:26:19,801][88326] Updated weights for policy 0, policy_version 34652 (0.0007) -[2023-10-09 01:26:22,630][88327] Updated weights for policy 1, policy_version 34660 (0.0008) -[2023-10-09 01:26:22,988][88327] Updated weights for policy 1, policy_version 34670 (0.0008) -[2023-10-09 01:26:23,348][88327] Updated weights for policy 1, policy_version 34680 (0.0007) -[2023-10-09 01:26:23,854][88326] Updated weights for policy 0, policy_version 34662 (0.0009) -[2023-10-09 01:26:23,974][87372] Fps is (10 sec: 16383.8, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 71008256. Throughput: 0: 1692.7, 1: 1703.6. Samples: 17754940. Policy #0 lag: (min: 31.0, avg: 31.5, max: 46.0) -[2023-10-09 01:26:23,975][87372] Avg episode reward: [(0, '5.320'), (1, '5.610')] -[2023-10-09 01:26:24,231][88326] Updated weights for policy 0, policy_version 34672 (0.0012) -[2023-10-09 01:26:24,608][88326] Updated weights for policy 0, policy_version 34682 (0.0010) -[2023-10-09 01:26:27,371][88327] Updated weights for policy 1, policy_version 34690 (0.0009) -[2023-10-09 01:26:27,743][88327] Updated weights for policy 1, policy_version 34700 (0.0009) -[2023-10-09 01:26:28,101][88327] Updated weights for policy 1, policy_version 34710 (0.0009) -[2023-10-09 01:26:28,465][88327] Updated weights for policy 1, policy_version 34720 (0.0010) -[2023-10-09 01:26:28,653][88326] Updated weights for policy 0, policy_version 34692 (0.0009) -[2023-10-09 01:26:28,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 71073792. Throughput: 0: 1695.8, 1: 1711.5. Samples: 17775968. Policy #0 lag: (min: 31.0, avg: 31.5, max: 46.0) -[2023-10-09 01:26:28,975][87372] Avg episode reward: [(0, '5.340'), (1, '5.700')] -[2023-10-09 01:26:29,029][88326] Updated weights for policy 0, policy_version 34702 (0.0007) -[2023-10-09 01:26:29,395][88326] Updated weights for policy 0, policy_version 34712 (0.0007) -[2023-10-09 01:26:32,465][88327] Updated weights for policy 1, policy_version 34730 (0.0007) -[2023-10-09 01:26:32,837][88327] Updated weights for policy 1, policy_version 34740 (0.0008) -[2023-10-09 01:26:33,204][88327] Updated weights for policy 1, policy_version 34750 (0.0007) -[2023-10-09 01:26:33,466][88326] Updated weights for policy 0, policy_version 34722 (0.0008) -[2023-10-09 01:26:33,844][88326] Updated weights for policy 0, policy_version 34732 (0.0008) -[2023-10-09 01:26:33,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 71139328. Throughput: 0: 1693.8, 1: 1689.6. Samples: 17795886. Policy #0 lag: (min: 31.0, avg: 31.5, max: 46.0) -[2023-10-09 01:26:33,975][87372] Avg episode reward: [(0, '5.030'), (1, '5.890')] -[2023-10-09 01:26:33,983][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000034752_35586048.pth... -[2023-10-09 01:26:34,026][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000033152_33947648.pth -[2023-10-09 01:26:34,206][88326] Updated weights for policy 0, policy_version 34742 (0.0011) -[2023-10-09 01:26:34,567][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000034752_35586048.pth... -[2023-10-09 01:26:34,571][88326] Updated weights for policy 0, policy_version 34752 (0.0007) -[2023-10-09 01:26:34,605][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000033152_33947648.pth -[2023-10-09 01:26:37,309][88327] Updated weights for policy 1, policy_version 34760 (0.0008) -[2023-10-09 01:26:37,691][88327] Updated weights for policy 1, policy_version 34770 (0.0007) -[2023-10-09 01:26:38,059][88327] Updated weights for policy 1, policy_version 34780 (0.0009) -[2023-10-09 01:26:38,549][88326] Updated weights for policy 0, policy_version 34762 (0.0011) -[2023-10-09 01:26:38,915][88326] Updated weights for policy 0, policy_version 34772 (0.0009) -[2023-10-09 01:26:38,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 71204864. Throughput: 0: 1698.9, 1: 1718.2. Samples: 17806150. Policy #0 lag: (min: 31.0, avg: 31.5, max: 46.0) -[2023-10-09 01:26:38,975][87372] Avg episode reward: [(0, '5.500'), (1, '5.450')] -[2023-10-09 01:26:39,280][88326] Updated weights for policy 0, policy_version 34782 (0.0011) -[2023-10-09 01:26:41,945][88327] Updated weights for policy 1, policy_version 34790 (0.0009) -[2023-10-09 01:26:42,306][88327] Updated weights for policy 1, policy_version 34800 (0.0011) -[2023-10-09 01:26:42,670][88327] Updated weights for policy 1, policy_version 34810 (0.0008) -[2023-10-09 01:26:43,328][88326] Updated weights for policy 0, policy_version 34792 (0.0008) -[2023-10-09 01:26:43,692][88326] Updated weights for policy 0, policy_version 34802 (0.0010) -[2023-10-09 01:26:43,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 71270400. Throughput: 0: 1696.1, 1: 1707.5. Samples: 17826654. Policy #0 lag: (min: 31.0, avg: 31.5, max: 46.0) -[2023-10-09 01:26:43,975][87372] Avg episode reward: [(0, '6.080'), (1, '5.450')] -[2023-10-09 01:26:44,070][88326] Updated weights for policy 0, policy_version 34812 (0.0009) -[2023-10-09 01:26:46,616][88327] Updated weights for policy 1, policy_version 34820 (0.0009) -[2023-10-09 01:26:46,989][88327] Updated weights for policy 1, policy_version 34830 (0.0008) -[2023-10-09 01:26:47,345][88327] Updated weights for policy 1, policy_version 34840 (0.0009) -[2023-10-09 01:26:48,148][88326] Updated weights for policy 0, policy_version 34822 (0.0008) -[2023-10-09 01:26:48,508][88326] Updated weights for policy 0, policy_version 34832 (0.0007) -[2023-10-09 01:26:48,875][88326] Updated weights for policy 0, policy_version 34842 (0.0007) -[2023-10-09 01:26:48,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 71335936. Throughput: 0: 1690.8, 1: 1682.3. Samples: 17846528. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 01:26:48,975][87372] Avg episode reward: [(0, '5.610'), (1, '5.660')] -[2023-10-09 01:26:51,344][88327] Updated weights for policy 1, policy_version 34850 (0.0010) -[2023-10-09 01:26:51,712][88327] Updated weights for policy 1, policy_version 34860 (0.0009) -[2023-10-09 01:26:52,080][88327] Updated weights for policy 1, policy_version 34870 (0.0007) -[2023-10-09 01:26:52,438][88327] Updated weights for policy 1, policy_version 34880 (0.0007) -[2023-10-09 01:26:52,982][88326] Updated weights for policy 0, policy_version 34852 (0.0008) -[2023-10-09 01:26:53,370][88326] Updated weights for policy 0, policy_version 34862 (0.0008) -[2023-10-09 01:26:53,742][88326] Updated weights for policy 0, policy_version 34872 (0.0008) -[2023-10-09 01:26:53,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 71401472. Throughput: 0: 1699.2, 1: 1710.2. Samples: 17857172. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 01:26:53,975][87372] Avg episode reward: [(0, '5.780'), (1, '6.010')] -[2023-10-09 01:26:56,609][88327] Updated weights for policy 1, policy_version 34890 (0.0008) -[2023-10-09 01:26:56,966][88327] Updated weights for policy 1, policy_version 34900 (0.0007) -[2023-10-09 01:26:57,330][88327] Updated weights for policy 1, policy_version 34910 (0.0008) -[2023-10-09 01:26:57,651][88326] Updated weights for policy 0, policy_version 34882 (0.0007) -[2023-10-09 01:26:58,026][88326] Updated weights for policy 0, policy_version 34892 (0.0008) -[2023-10-09 01:26:58,389][88326] Updated weights for policy 0, policy_version 34902 (0.0010) -[2023-10-09 01:26:58,758][88326] Updated weights for policy 0, policy_version 34912 (0.0008) -[2023-10-09 01:26:58,974][87372] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 71499776. Throughput: 0: 1702.7, 1: 1688.9. Samples: 17877228. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 01:26:58,974][87372] Avg episode reward: [(0, '5.370'), (1, '6.050')] -[2023-10-09 01:27:01,436][88327] Updated weights for policy 1, policy_version 34920 (0.0007) -[2023-10-09 01:27:01,801][88327] Updated weights for policy 1, policy_version 34930 (0.0007) -[2023-10-09 01:27:02,176][88327] Updated weights for policy 1, policy_version 34940 (0.0007) -[2023-10-09 01:27:02,783][88326] Updated weights for policy 0, policy_version 34922 (0.0008) -[2023-10-09 01:27:03,157][88326] Updated weights for policy 0, policy_version 34932 (0.0009) -[2023-10-09 01:27:03,528][88326] Updated weights for policy 0, policy_version 34942 (0.0007) -[2023-10-09 01:27:03,974][87372] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 71565312. Throughput: 0: 1686.8, 1: 1682.8. Samples: 17896886. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 01:27:03,975][87372] Avg episode reward: [(0, '5.290'), (1, '5.960')] -[2023-10-09 01:27:06,152][88327] Updated weights for policy 1, policy_version 34950 (0.0008) -[2023-10-09 01:27:06,516][88327] Updated weights for policy 1, policy_version 34960 (0.0010) -[2023-10-09 01:27:06,877][88327] Updated weights for policy 1, policy_version 34970 (0.0010) -[2023-10-09 01:27:07,489][88326] Updated weights for policy 0, policy_version 34952 (0.0008) -[2023-10-09 01:27:07,860][88326] Updated weights for policy 0, policy_version 34962 (0.0009) -[2023-10-09 01:27:08,220][88326] Updated weights for policy 0, policy_version 34972 (0.0009) -[2023-10-09 01:27:08,974][87372] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 71630848. Throughput: 0: 1707.0, 1: 1696.4. Samples: 17908090. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-09 01:27:08,975][87372] Avg episode reward: [(0, '6.200'), (1, '5.990')] -[2023-10-09 01:27:11,061][88327] Updated weights for policy 1, policy_version 34980 (0.0011) -[2023-10-09 01:27:11,429][88327] Updated weights for policy 1, policy_version 34990 (0.0011) -[2023-10-09 01:27:11,798][88327] Updated weights for policy 1, policy_version 35000 (0.0008) -[2023-10-09 01:27:12,359][88326] Updated weights for policy 0, policy_version 34982 (0.0009) -[2023-10-09 01:27:12,721][88326] Updated weights for policy 0, policy_version 34992 (0.0007) -[2023-10-09 01:27:13,093][88326] Updated weights for policy 0, policy_version 35002 (0.0007) -[2023-10-09 01:27:13,974][87372] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 71696384. Throughput: 0: 1704.3, 1: 1670.3. Samples: 17927824. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-09 01:27:13,975][87372] Avg episode reward: [(0, '5.590'), (1, '5.440')] -[2023-10-09 01:27:15,670][88327] Updated weights for policy 1, policy_version 35010 (0.0011) -[2023-10-09 01:27:16,034][88327] Updated weights for policy 1, policy_version 35020 (0.0009) -[2023-10-09 01:27:16,405][88327] Updated weights for policy 1, policy_version 35030 (0.0008) -[2023-10-09 01:27:16,765][88327] Updated weights for policy 1, policy_version 35040 (0.0010) -[2023-10-09 01:27:17,099][88326] Updated weights for policy 0, policy_version 35012 (0.0007) -[2023-10-09 01:27:17,469][88326] Updated weights for policy 0, policy_version 35022 (0.0008) -[2023-10-09 01:27:17,841][88326] Updated weights for policy 0, policy_version 35032 (0.0007) -[2023-10-09 01:27:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 71761920. Throughput: 0: 1676.5, 1: 1695.1. Samples: 17947610. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-09 01:27:18,975][87372] Avg episode reward: [(0, '5.310'), (1, '5.570')] -[2023-10-09 01:27:20,751][88327] Updated weights for policy 1, policy_version 35050 (0.0007) -[2023-10-09 01:27:21,119][88327] Updated weights for policy 1, policy_version 35060 (0.0009) -[2023-10-09 01:27:21,495][88327] Updated weights for policy 1, policy_version 35070 (0.0011) -[2023-10-09 01:27:21,748][88326] Updated weights for policy 0, policy_version 35042 (0.0010) -[2023-10-09 01:27:22,122][88326] Updated weights for policy 0, policy_version 35052 (0.0009) -[2023-10-09 01:27:22,502][88326] Updated weights for policy 0, policy_version 35062 (0.0009) -[2023-10-09 01:27:22,874][88326] Updated weights for policy 0, policy_version 35072 (0.0009) -[2023-10-09 01:27:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 71827456. Throughput: 0: 1705.7, 1: 1685.4. Samples: 17958752. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-09 01:27:23,975][87372] Avg episode reward: [(0, '5.740'), (1, '6.100')] -[2023-10-09 01:27:25,559][88327] Updated weights for policy 1, policy_version 35080 (0.0009) -[2023-10-09 01:27:25,915][88327] Updated weights for policy 1, policy_version 35090 (0.0009) -[2023-10-09 01:27:26,292][88327] Updated weights for policy 1, policy_version 35100 (0.0009) -[2023-10-09 01:27:26,897][88326] Updated weights for policy 0, policy_version 35082 (0.0010) -[2023-10-09 01:27:27,258][88326] Updated weights for policy 0, policy_version 35092 (0.0010) -[2023-10-09 01:27:27,633][88326] Updated weights for policy 0, policy_version 35102 (0.0008) -[2023-10-09 01:27:28,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 71892992. Throughput: 0: 1685.9, 1: 1684.9. Samples: 17978342. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-09 01:27:28,975][87372] Avg episode reward: [(0, '5.610'), (1, '6.100')] -[2023-10-09 01:27:30,450][88327] Updated weights for policy 1, policy_version 35110 (0.0007) -[2023-10-09 01:27:30,814][88327] Updated weights for policy 1, policy_version 35120 (0.0009) -[2023-10-09 01:27:31,174][88327] Updated weights for policy 1, policy_version 35130 (0.0010) -[2023-10-09 01:27:31,461][88326] Updated weights for policy 0, policy_version 35112 (0.0007) -[2023-10-09 01:27:31,828][88326] Updated weights for policy 0, policy_version 35122 (0.0008) -[2023-10-09 01:27:32,195][88326] Updated weights for policy 0, policy_version 35132 (0.0008) -[2023-10-09 01:27:33,974][87372] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 71958528. Throughput: 0: 1683.0, 1: 1702.2. Samples: 17998862. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-09 01:27:33,976][87372] Avg episode reward: [(0, '5.550'), (1, '6.210')] -[2023-10-09 01:27:35,144][88327] Updated weights for policy 1, policy_version 35140 (0.0008) -[2023-10-09 01:27:35,505][88327] Updated weights for policy 1, policy_version 35150 (0.0009) -[2023-10-09 01:27:35,877][88327] Updated weights for policy 1, policy_version 35160 (0.0008) -[2023-10-09 01:27:36,243][88326] Updated weights for policy 0, policy_version 35142 (0.0008) -[2023-10-09 01:27:36,611][88326] Updated weights for policy 0, policy_version 35152 (0.0007) -[2023-10-09 01:27:36,965][88326] Updated weights for policy 0, policy_version 35162 (0.0009) -[2023-10-09 01:27:38,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 72024064. Throughput: 0: 1702.8, 1: 1678.6. Samples: 18009336. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-09 01:27:38,975][87372] Avg episode reward: [(0, '5.940'), (1, '6.800')] -[2023-10-09 01:27:38,975][88168] Saving new best policy, reward=6.800! -[2023-10-09 01:27:39,754][88327] Updated weights for policy 1, policy_version 35170 (0.0007) -[2023-10-09 01:27:40,122][88327] Updated weights for policy 1, policy_version 35180 (0.0008) -[2023-10-09 01:27:40,477][88327] Updated weights for policy 1, policy_version 35190 (0.0010) -[2023-10-09 01:27:40,844][88327] Updated weights for policy 1, policy_version 35200 (0.0008) -[2023-10-09 01:27:41,127][88326] Updated weights for policy 0, policy_version 35172 (0.0008) -[2023-10-09 01:27:41,501][88326] Updated weights for policy 0, policy_version 35182 (0.0007) -[2023-10-09 01:27:41,863][88326] Updated weights for policy 0, policy_version 35192 (0.0009) -[2023-10-09 01:27:43,974][87372] Fps is (10 sec: 13107.6, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 72089600. Throughput: 0: 1671.8, 1: 1699.1. Samples: 18028916. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-09 01:27:43,975][87372] Avg episode reward: [(0, '6.310'), (1, '6.290')] -[2023-10-09 01:27:44,921][88327] Updated weights for policy 1, policy_version 35210 (0.0009) -[2023-10-09 01:27:45,289][88327] Updated weights for policy 1, policy_version 35220 (0.0007) -[2023-10-09 01:27:45,651][88327] Updated weights for policy 1, policy_version 35230 (0.0008) -[2023-10-09 01:27:46,044][88326] Updated weights for policy 0, policy_version 35202 (0.0010) -[2023-10-09 01:27:46,436][88326] Updated weights for policy 0, policy_version 35212 (0.0008) -[2023-10-09 01:27:46,793][88326] Updated weights for policy 0, policy_version 35222 (0.0007) -[2023-10-09 01:27:47,165][88326] Updated weights for policy 0, policy_version 35232 (0.0007) -[2023-10-09 01:27:48,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 72155136. Throughput: 0: 1685.2, 1: 1708.8. Samples: 18049616. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-09 01:27:48,975][87372] Avg episode reward: [(0, '5.740'), (1, '6.450')] -[2023-10-09 01:27:49,821][88327] Updated weights for policy 1, policy_version 35240 (0.0008) -[2023-10-09 01:27:50,189][88327] Updated weights for policy 1, policy_version 35250 (0.0007) -[2023-10-09 01:27:50,545][88327] Updated weights for policy 1, policy_version 35260 (0.0009) -[2023-10-09 01:27:51,041][88326] Updated weights for policy 0, policy_version 35242 (0.0011) -[2023-10-09 01:27:51,417][88326] Updated weights for policy 0, policy_version 35252 (0.0009) -[2023-10-09 01:27:51,791][88326] Updated weights for policy 0, policy_version 35262 (0.0008) -[2023-10-09 01:27:53,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 72220672. Throughput: 0: 1685.2, 1: 1678.2. Samples: 18059444. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-09 01:27:53,975][87372] Avg episode reward: [(0, '5.880'), (1, '6.040')] -[2023-10-09 01:27:54,707][88327] Updated weights for policy 1, policy_version 35270 (0.0010) -[2023-10-09 01:27:55,074][88327] Updated weights for policy 1, policy_version 35280 (0.0011) -[2023-10-09 01:27:55,442][88327] Updated weights for policy 1, policy_version 35290 (0.0009) -[2023-10-09 01:27:55,635][88326] Updated weights for policy 0, policy_version 35272 (0.0007) -[2023-10-09 01:27:56,008][88326] Updated weights for policy 0, policy_version 35282 (0.0010) -[2023-10-09 01:27:56,365][88326] Updated weights for policy 0, policy_version 35292 (0.0011) -[2023-10-09 01:27:58,974][87372] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 72286208. Throughput: 0: 1674.6, 1: 1702.1. Samples: 18079776. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-09 01:27:58,975][87372] Avg episode reward: [(0, '6.410'), (1, '6.850')] -[2023-10-09 01:27:58,975][88168] Saving new best policy, reward=6.850! -[2023-10-09 01:27:59,559][88327] Updated weights for policy 1, policy_version 35300 (0.0008) -[2023-10-09 01:27:59,931][88327] Updated weights for policy 1, policy_version 35310 (0.0010) -[2023-10-09 01:28:00,296][88327] Updated weights for policy 1, policy_version 35320 (0.0010) -[2023-10-09 01:28:00,547][88326] Updated weights for policy 0, policy_version 35302 (0.0008) -[2023-10-09 01:28:00,920][88326] Updated weights for policy 0, policy_version 35312 (0.0009) -[2023-10-09 01:28:01,296][88326] Updated weights for policy 0, policy_version 35322 (0.0009) -[2023-10-09 01:28:03,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 72351744. Throughput: 0: 1704.0, 1: 1697.7. Samples: 18100690. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-09 01:28:03,974][87372] Avg episode reward: [(0, '5.630'), (1, '6.360')] -[2023-10-09 01:28:04,251][88327] Updated weights for policy 1, policy_version 35330 (0.0007) -[2023-10-09 01:28:04,620][88327] Updated weights for policy 1, policy_version 35340 (0.0007) -[2023-10-09 01:28:04,982][88327] Updated weights for policy 1, policy_version 35350 (0.0007) -[2023-10-09 01:28:05,316][88326] Updated weights for policy 0, policy_version 35332 (0.0009) -[2023-10-09 01:28:05,354][88327] Updated weights for policy 1, policy_version 35360 (0.0009) -[2023-10-09 01:28:05,688][88326] Updated weights for policy 0, policy_version 35342 (0.0008) -[2023-10-09 01:28:06,061][88326] Updated weights for policy 0, policy_version 35352 (0.0008) -[2023-10-09 01:28:08,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 72417280. Throughput: 0: 1679.0, 1: 1685.3. Samples: 18110146. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-09 01:28:08,975][87372] Avg episode reward: [(0, '6.230'), (1, '5.930')] -[2023-10-09 01:28:09,431][88327] Updated weights for policy 1, policy_version 35370 (0.0008) -[2023-10-09 01:28:09,801][88327] Updated weights for policy 1, policy_version 35380 (0.0007) -[2023-10-09 01:28:09,937][88326] Updated weights for policy 0, policy_version 35362 (0.0010) -[2023-10-09 01:28:10,166][88327] Updated weights for policy 1, policy_version 35390 (0.0008) -[2023-10-09 01:28:10,296][88326] Updated weights for policy 0, policy_version 35372 (0.0008) -[2023-10-09 01:28:10,662][88326] Updated weights for policy 0, policy_version 35382 (0.0010) -[2023-10-09 01:28:11,027][88326] Updated weights for policy 0, policy_version 35392 (0.0010) -[2023-10-09 01:28:13,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 72482816. Throughput: 0: 1693.9, 1: 1700.8. Samples: 18131100. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-09 01:28:13,975][87372] Avg episode reward: [(0, '5.980'), (1, '5.970')] -[2023-10-09 01:28:14,093][88327] Updated weights for policy 1, policy_version 35400 (0.0007) -[2023-10-09 01:28:14,470][88327] Updated weights for policy 1, policy_version 35410 (0.0008) -[2023-10-09 01:28:14,830][88327] Updated weights for policy 1, policy_version 35420 (0.0007) -[2023-10-09 01:28:15,014][88326] Updated weights for policy 0, policy_version 35402 (0.0008) -[2023-10-09 01:28:15,388][88326] Updated weights for policy 0, policy_version 35412 (0.0009) -[2023-10-09 01:28:15,752][88326] Updated weights for policy 0, policy_version 35422 (0.0010) -[2023-10-09 01:28:18,853][88327] Updated weights for policy 1, policy_version 35430 (0.0008) -[2023-10-09 01:28:18,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 72548352. Throughput: 0: 1702.7, 1: 1702.9. Samples: 18152112. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-09 01:28:18,975][87372] Avg episode reward: [(0, '5.970'), (1, '5.920')] -[2023-10-09 01:28:19,217][88327] Updated weights for policy 1, policy_version 35440 (0.0008) -[2023-10-09 01:28:19,589][88327] Updated weights for policy 1, policy_version 35450 (0.0008) -[2023-10-09 01:28:19,892][88326] Updated weights for policy 0, policy_version 35432 (0.0009) -[2023-10-09 01:28:20,259][88326] Updated weights for policy 0, policy_version 35442 (0.0010) -[2023-10-09 01:28:20,641][88326] Updated weights for policy 0, policy_version 35452 (0.0009) -[2023-10-09 01:28:23,660][88327] Updated weights for policy 1, policy_version 35460 (0.0010) -[2023-10-09 01:28:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 72613888. Throughput: 0: 1676.5, 1: 1698.0. Samples: 18161190. Policy #0 lag: (min: 4.0, avg: 6.7, max: 36.0) -[2023-10-09 01:28:23,975][87372] Avg episode reward: [(0, '6.130'), (1, '5.310')] -[2023-10-09 01:28:24,025][88327] Updated weights for policy 1, policy_version 35470 (0.0007) -[2023-10-09 01:28:24,398][88327] Updated weights for policy 1, policy_version 35480 (0.0007) -[2023-10-09 01:28:24,843][88326] Updated weights for policy 0, policy_version 35462 (0.0009) -[2023-10-09 01:28:25,216][88326] Updated weights for policy 0, policy_version 35472 (0.0007) -[2023-10-09 01:28:25,588][88326] Updated weights for policy 0, policy_version 35482 (0.0009) -[2023-10-09 01:28:28,299][88327] Updated weights for policy 1, policy_version 35490 (0.0008) -[2023-10-09 01:28:28,660][88327] Updated weights for policy 1, policy_version 35500 (0.0007) -[2023-10-09 01:28:28,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 72679424. Throughput: 0: 1706.2, 1: 1697.8. Samples: 18182096. Policy #0 lag: (min: 4.0, avg: 6.7, max: 36.0) -[2023-10-09 01:28:28,975][87372] Avg episode reward: [(0, '5.560'), (1, '5.630')] -[2023-10-09 01:28:29,025][88327] Updated weights for policy 1, policy_version 35510 (0.0007) -[2023-10-09 01:28:29,391][88327] Updated weights for policy 1, policy_version 35520 (0.0007) -[2023-10-09 01:28:29,403][88326] Updated weights for policy 0, policy_version 35492 (0.0007) -[2023-10-09 01:28:29,766][88326] Updated weights for policy 0, policy_version 35502 (0.0009) -[2023-10-09 01:28:30,137][88326] Updated weights for policy 0, policy_version 35512 (0.0007) -[2023-10-09 01:28:33,257][88327] Updated weights for policy 1, policy_version 35530 (0.0007) -[2023-10-09 01:28:33,619][88327] Updated weights for policy 1, policy_version 35540 (0.0008) -[2023-10-09 01:28:33,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.3, 300 sec: 13440.4). Total num frames: 72744960. Throughput: 0: 1710.0, 1: 1699.8. Samples: 18203056. Policy #0 lag: (min: 4.0, avg: 6.7, max: 36.0) -[2023-10-09 01:28:33,975][87372] Avg episode reward: [(0, '5.800'), (1, '6.100')] -[2023-10-09 01:28:33,983][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000035520_36372480.pth... -[2023-10-09 01:28:33,983][88327] Updated weights for policy 1, policy_version 35550 (0.0009) -[2023-10-09 01:28:34,017][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000033952_34766848.pth -[2023-10-09 01:28:34,054][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000035552_36405248.pth... -[2023-10-09 01:28:34,084][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000033952_34766848.pth -[2023-10-09 01:28:34,299][88326] Updated weights for policy 0, policy_version 35522 (0.0009) -[2023-10-09 01:28:34,701][88326] Updated weights for policy 0, policy_version 35532 (0.0009) -[2023-10-09 01:28:35,079][88326] Updated weights for policy 0, policy_version 35542 (0.0007) -[2023-10-09 01:28:35,439][88326] Updated weights for policy 0, policy_version 35552 (0.0007) -[2023-10-09 01:28:38,030][88327] Updated weights for policy 1, policy_version 35560 (0.0007) -[2023-10-09 01:28:38,402][88327] Updated weights for policy 1, policy_version 35570 (0.0007) -[2023-10-09 01:28:38,773][88327] Updated weights for policy 1, policy_version 35580 (0.0007) -[2023-10-09 01:28:38,974][87372] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 72843264. Throughput: 0: 1690.3, 1: 1710.8. Samples: 18212494. Policy #0 lag: (min: 4.0, avg: 6.7, max: 36.0) -[2023-10-09 01:28:38,975][87372] Avg episode reward: [(0, '5.270'), (1, '6.160')] -[2023-10-09 01:28:39,361][88326] Updated weights for policy 0, policy_version 35562 (0.0009) -[2023-10-09 01:28:39,724][88326] Updated weights for policy 0, policy_version 35572 (0.0011) -[2023-10-09 01:28:40,098][88326] Updated weights for policy 0, policy_version 35582 (0.0008) -[2023-10-09 01:28:42,726][88327] Updated weights for policy 1, policy_version 35590 (0.0009) -[2023-10-09 01:28:43,093][88327] Updated weights for policy 1, policy_version 35600 (0.0009) -[2023-10-09 01:28:43,451][88327] Updated weights for policy 1, policy_version 35610 (0.0008) -[2023-10-09 01:28:43,974][87372] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 72908800. Throughput: 0: 1705.3, 1: 1708.5. Samples: 18233398. Policy #0 lag: (min: 4.0, avg: 6.7, max: 36.0) -[2023-10-09 01:28:43,975][87372] Avg episode reward: [(0, '5.240'), (1, '6.190')] -[2023-10-09 01:28:44,136][88326] Updated weights for policy 0, policy_version 35592 (0.0011) -[2023-10-09 01:28:44,505][88326] Updated weights for policy 0, policy_version 35602 (0.0009) -[2023-10-09 01:28:44,885][88326] Updated weights for policy 0, policy_version 35612 (0.0010) -[2023-10-09 01:28:47,599][88327] Updated weights for policy 1, policy_version 35620 (0.0008) -[2023-10-09 01:28:47,974][88327] Updated weights for policy 1, policy_version 35630 (0.0010) -[2023-10-09 01:28:48,338][88327] Updated weights for policy 1, policy_version 35640 (0.0007) -[2023-10-09 01:28:48,808][88326] Updated weights for policy 0, policy_version 35622 (0.0009) -[2023-10-09 01:28:48,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 72974336. Throughput: 0: 1709.4, 1: 1691.6. Samples: 18253736. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:28:48,975][87372] Avg episode reward: [(0, '6.390'), (1, '6.070')] -[2023-10-09 01:28:49,180][88326] Updated weights for policy 0, policy_version 35632 (0.0008) -[2023-10-09 01:28:49,545][88326] Updated weights for policy 0, policy_version 35642 (0.0009) -[2023-10-09 01:28:52,329][88327] Updated weights for policy 1, policy_version 35650 (0.0009) -[2023-10-09 01:28:52,685][88327] Updated weights for policy 1, policy_version 35660 (0.0008) -[2023-10-09 01:28:53,044][88327] Updated weights for policy 1, policy_version 35670 (0.0007) -[2023-10-09 01:28:53,404][88327] Updated weights for policy 1, policy_version 35680 (0.0008) -[2023-10-09 01:28:53,640][88326] Updated weights for policy 0, policy_version 35652 (0.0008) -[2023-10-09 01:28:53,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 73039872. Throughput: 0: 1701.5, 1: 1707.5. Samples: 18263550. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:28:53,975][87372] Avg episode reward: [(0, '5.850'), (1, '5.740')] -[2023-10-09 01:28:54,013][88326] Updated weights for policy 0, policy_version 35662 (0.0008) -[2023-10-09 01:28:54,371][88326] Updated weights for policy 0, policy_version 35672 (0.0007) -[2023-10-09 01:28:57,539][88327] Updated weights for policy 1, policy_version 35690 (0.0008) -[2023-10-09 01:28:57,911][88327] Updated weights for policy 1, policy_version 35700 (0.0007) -[2023-10-09 01:28:58,277][88327] Updated weights for policy 1, policy_version 35710 (0.0009) -[2023-10-09 01:28:58,474][88326] Updated weights for policy 0, policy_version 35682 (0.0009) -[2023-10-09 01:28:58,848][88326] Updated weights for policy 0, policy_version 35692 (0.0007) -[2023-10-09 01:28:58,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 73105408. Throughput: 0: 1703.0, 1: 1706.3. Samples: 18284520. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:28:58,974][87372] Avg episode reward: [(0, '5.860'), (1, '6.210')] -[2023-10-09 01:28:59,215][88326] Updated weights for policy 0, policy_version 35702 (0.0008) -[2023-10-09 01:28:59,592][88326] Updated weights for policy 0, policy_version 35712 (0.0009) -[2023-10-09 01:29:02,371][88327] Updated weights for policy 1, policy_version 35720 (0.0009) -[2023-10-09 01:29:02,740][88327] Updated weights for policy 1, policy_version 35730 (0.0010) -[2023-10-09 01:29:03,102][88327] Updated weights for policy 1, policy_version 35740 (0.0012) -[2023-10-09 01:29:03,547][88326] Updated weights for policy 0, policy_version 35722 (0.0009) -[2023-10-09 01:29:03,915][88326] Updated weights for policy 0, policy_version 35732 (0.0008) -[2023-10-09 01:29:03,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 73170944. Throughput: 0: 1706.1, 1: 1673.0. Samples: 18304170. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:29:03,975][87372] Avg episode reward: [(0, '5.640'), (1, '6.300')] -[2023-10-09 01:29:04,295][88326] Updated weights for policy 0, policy_version 35742 (0.0009) -[2023-10-09 01:29:07,089][88327] Updated weights for policy 1, policy_version 35750 (0.0009) -[2023-10-09 01:29:07,460][88327] Updated weights for policy 1, policy_version 35760 (0.0010) -[2023-10-09 01:29:07,825][88327] Updated weights for policy 1, policy_version 35770 (0.0009) -[2023-10-09 01:29:08,103][88326] Updated weights for policy 0, policy_version 35752 (0.0009) -[2023-10-09 01:29:08,470][88326] Updated weights for policy 0, policy_version 35762 (0.0009) -[2023-10-09 01:29:08,835][88326] Updated weights for policy 0, policy_version 35772 (0.0010) -[2023-10-09 01:29:08,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 73236480. Throughput: 0: 1710.8, 1: 1697.6. Samples: 18314566. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:29:08,975][87372] Avg episode reward: [(0, '5.690'), (1, '6.090')] -[2023-10-09 01:29:11,922][88327] Updated weights for policy 1, policy_version 35780 (0.0007) -[2023-10-09 01:29:12,297][88327] Updated weights for policy 1, policy_version 35790 (0.0008) -[2023-10-09 01:29:12,656][88327] Updated weights for policy 1, policy_version 35800 (0.0007) -[2023-10-09 01:29:12,915][88326] Updated weights for policy 0, policy_version 35782 (0.0008) -[2023-10-09 01:29:13,287][88326] Updated weights for policy 0, policy_version 35792 (0.0010) -[2023-10-09 01:29:13,662][88326] Updated weights for policy 0, policy_version 35802 (0.0008) -[2023-10-09 01:29:13,974][87372] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 73334784. Throughput: 0: 1709.1, 1: 1693.4. Samples: 18335208. Policy #0 lag: (min: 19.0, avg: 26.9, max: 51.0) -[2023-10-09 01:29:13,975][87372] Avg episode reward: [(0, '5.680'), (1, '6.130')] -[2023-10-09 01:29:16,617][88327] Updated weights for policy 1, policy_version 35810 (0.0007) -[2023-10-09 01:29:16,983][88327] Updated weights for policy 1, policy_version 35820 (0.0007) -[2023-10-09 01:29:17,351][88327] Updated weights for policy 1, policy_version 35830 (0.0010) -[2023-10-09 01:29:17,622][88326] Updated weights for policy 0, policy_version 35812 (0.0008) -[2023-10-09 01:29:17,713][88327] Updated weights for policy 1, policy_version 35840 (0.0008) -[2023-10-09 01:29:17,992][88326] Updated weights for policy 0, policy_version 35822 (0.0009) -[2023-10-09 01:29:18,362][88326] Updated weights for policy 0, policy_version 35832 (0.0007) -[2023-10-09 01:29:18,974][87372] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 73400320. Throughput: 0: 1695.0, 1: 1675.6. Samples: 18354732. Policy #0 lag: (min: 19.0, avg: 26.9, max: 51.0) -[2023-10-09 01:29:18,975][87372] Avg episode reward: [(0, '5.920'), (1, '5.640')] -[2023-10-09 01:29:21,888][88327] Updated weights for policy 1, policy_version 35850 (0.0008) -[2023-10-09 01:29:22,242][88326] Updated weights for policy 0, policy_version 35842 (0.0007) -[2023-10-09 01:29:22,253][88327] Updated weights for policy 1, policy_version 35860 (0.0010) -[2023-10-09 01:29:22,613][88327] Updated weights for policy 1, policy_version 35870 (0.0008) -[2023-10-09 01:29:22,639][88326] Updated weights for policy 0, policy_version 35852 (0.0009) -[2023-10-09 01:29:23,004][88326] Updated weights for policy 0, policy_version 35862 (0.0007) -[2023-10-09 01:29:23,365][88326] Updated weights for policy 0, policy_version 35872 (0.0008) -[2023-10-09 01:29:23,974][87372] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 73465856. Throughput: 0: 1716.1, 1: 1695.4. Samples: 18366014. Policy #0 lag: (min: 19.0, avg: 26.9, max: 51.0) -[2023-10-09 01:29:23,975][87372] Avg episode reward: [(0, '5.990'), (1, '5.450')] -[2023-10-09 01:29:26,391][88327] Updated weights for policy 1, policy_version 35880 (0.0009) -[2023-10-09 01:29:26,757][88327] Updated weights for policy 1, policy_version 35890 (0.0010) -[2023-10-09 01:29:27,119][88327] Updated weights for policy 1, policy_version 35900 (0.0009) -[2023-10-09 01:29:27,524][88326] Updated weights for policy 0, policy_version 35882 (0.0009) -[2023-10-09 01:29:27,897][88326] Updated weights for policy 0, policy_version 35892 (0.0007) -[2023-10-09 01:29:28,270][88326] Updated weights for policy 0, policy_version 35902 (0.0010) -[2023-10-09 01:29:28,974][87372] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 73531392. Throughput: 0: 1712.4, 1: 1678.7. Samples: 18385996. Policy #0 lag: (min: 19.0, avg: 26.9, max: 51.0) -[2023-10-09 01:29:28,975][87372] Avg episode reward: [(0, '5.670'), (1, '5.970')] -[2023-10-09 01:29:31,176][88327] Updated weights for policy 1, policy_version 35910 (0.0009) -[2023-10-09 01:29:31,541][88327] Updated weights for policy 1, policy_version 35920 (0.0011) -[2023-10-09 01:29:31,908][88327] Updated weights for policy 1, policy_version 35930 (0.0010) -[2023-10-09 01:29:32,230][88326] Updated weights for policy 0, policy_version 35912 (0.0008) -[2023-10-09 01:29:32,602][88326] Updated weights for policy 0, policy_version 35922 (0.0007) -[2023-10-09 01:29:32,977][88326] Updated weights for policy 0, policy_version 35932 (0.0008) -[2023-10-09 01:29:33,974][87372] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 73596928. Throughput: 0: 1679.0, 1: 1691.2. Samples: 18405392. Policy #0 lag: (min: 8.0, avg: 35.9, max: 40.0) -[2023-10-09 01:29:33,975][87372] Avg episode reward: [(0, '5.500'), (1, '5.710')] -[2023-10-09 01:29:36,040][88327] Updated weights for policy 1, policy_version 35940 (0.0009) -[2023-10-09 01:29:36,404][88327] Updated weights for policy 1, policy_version 35950 (0.0007) -[2023-10-09 01:29:36,773][88327] Updated weights for policy 1, policy_version 35960 (0.0007) -[2023-10-09 01:29:37,034][88326] Updated weights for policy 0, policy_version 35942 (0.0007) -[2023-10-09 01:29:37,408][88326] Updated weights for policy 0, policy_version 35952 (0.0008) -[2023-10-09 01:29:37,776][88326] Updated weights for policy 0, policy_version 35962 (0.0007) -[2023-10-09 01:29:38,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 73662464. Throughput: 0: 1710.7, 1: 1696.0. Samples: 18416854. Policy #0 lag: (min: 8.0, avg: 35.9, max: 40.0) -[2023-10-09 01:29:38,974][87372] Avg episode reward: [(0, '5.720'), (1, '5.590')] -[2023-10-09 01:29:40,789][88327] Updated weights for policy 1, policy_version 35970 (0.0008) -[2023-10-09 01:29:41,158][88327] Updated weights for policy 1, policy_version 35980 (0.0007) -[2023-10-09 01:29:41,518][88327] Updated weights for policy 1, policy_version 35990 (0.0007) -[2023-10-09 01:29:41,762][88326] Updated weights for policy 0, policy_version 35972 (0.0010) -[2023-10-09 01:29:41,884][88327] Updated weights for policy 1, policy_version 36000 (0.0007) -[2023-10-09 01:29:42,129][88326] Updated weights for policy 0, policy_version 35982 (0.0009) -[2023-10-09 01:29:42,506][88326] Updated weights for policy 0, policy_version 35992 (0.0008) -[2023-10-09 01:29:43,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 73728000. Throughput: 0: 1697.9, 1: 1670.8. Samples: 18436112. Policy #0 lag: (min: 8.0, avg: 35.9, max: 40.0) -[2023-10-09 01:29:43,975][87372] Avg episode reward: [(0, '5.540'), (1, '6.130')] -[2023-10-09 01:29:45,894][88327] Updated weights for policy 1, policy_version 36010 (0.0008) -[2023-10-09 01:29:46,260][88327] Updated weights for policy 1, policy_version 36020 (0.0009) -[2023-10-09 01:29:46,509][88326] Updated weights for policy 0, policy_version 36002 (0.0008) -[2023-10-09 01:29:46,621][88327] Updated weights for policy 1, policy_version 36030 (0.0009) -[2023-10-09 01:29:46,880][88326] Updated weights for policy 0, policy_version 36012 (0.0008) -[2023-10-09 01:29:47,247][88326] Updated weights for policy 0, policy_version 36022 (0.0007) -[2023-10-09 01:29:47,601][88326] Updated weights for policy 0, policy_version 36032 (0.0010) -[2023-10-09 01:29:48,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 73793536. Throughput: 0: 1677.9, 1: 1703.5. Samples: 18456338. Policy #0 lag: (min: 8.0, avg: 35.9, max: 40.0) -[2023-10-09 01:29:48,975][87372] Avg episode reward: [(0, '5.610'), (1, '5.950')] -[2023-10-09 01:29:50,925][88327] Updated weights for policy 1, policy_version 36040 (0.0008) -[2023-10-09 01:29:51,296][88327] Updated weights for policy 1, policy_version 36050 (0.0008) -[2023-10-09 01:29:51,658][88327] Updated weights for policy 1, policy_version 36060 (0.0007) -[2023-10-09 01:29:51,721][88326] Updated weights for policy 0, policy_version 36042 (0.0009) -[2023-10-09 01:29:52,081][88326] Updated weights for policy 0, policy_version 36052 (0.0010) -[2023-10-09 01:29:52,462][88326] Updated weights for policy 0, policy_version 36062 (0.0008) -[2023-10-09 01:29:53,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 73859072. Throughput: 0: 1706.3, 1: 1692.6. Samples: 18467516. Policy #0 lag: (min: 8.0, avg: 35.9, max: 40.0) -[2023-10-09 01:29:53,975][87372] Avg episode reward: [(0, '6.290'), (1, '6.330')] -[2023-10-09 01:29:55,524][88327] Updated weights for policy 1, policy_version 36070 (0.0009) -[2023-10-09 01:29:55,904][88327] Updated weights for policy 1, policy_version 36080 (0.0008) -[2023-10-09 01:29:56,265][88327] Updated weights for policy 1, policy_version 36090 (0.0008) -[2023-10-09 01:29:56,586][88326] Updated weights for policy 0, policy_version 36072 (0.0008) -[2023-10-09 01:29:56,964][88326] Updated weights for policy 0, policy_version 36082 (0.0008) -[2023-10-09 01:29:57,331][88326] Updated weights for policy 0, policy_version 36092 (0.0007) -[2023-10-09 01:29:58,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 73924608. Throughput: 0: 1682.3, 1: 1687.9. Samples: 18486868. Policy #0 lag: (min: 17.0, avg: 29.8, max: 49.0) -[2023-10-09 01:29:58,975][87372] Avg episode reward: [(0, '6.310'), (1, '6.110')] -[2023-10-09 01:30:00,386][88327] Updated weights for policy 1, policy_version 36100 (0.0011) -[2023-10-09 01:30:00,759][88327] Updated weights for policy 1, policy_version 36110 (0.0010) -[2023-10-09 01:30:01,112][88327] Updated weights for policy 1, policy_version 36120 (0.0010) -[2023-10-09 01:30:01,359][88326] Updated weights for policy 0, policy_version 36102 (0.0008) -[2023-10-09 01:30:01,737][88326] Updated weights for policy 0, policy_version 36112 (0.0007) -[2023-10-09 01:30:02,094][88326] Updated weights for policy 0, policy_version 36122 (0.0010) -[2023-10-09 01:30:03,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 73990144. Throughput: 0: 1687.6, 1: 1698.7. Samples: 18507118. Policy #0 lag: (min: 17.0, avg: 29.8, max: 49.0) -[2023-10-09 01:30:03,975][87372] Avg episode reward: [(0, '6.390'), (1, '5.570')] -[2023-10-09 01:30:05,260][88327] Updated weights for policy 1, policy_version 36130 (0.0008) -[2023-10-09 01:30:05,625][88327] Updated weights for policy 1, policy_version 36140 (0.0011) -[2023-10-09 01:30:05,988][88327] Updated weights for policy 1, policy_version 36150 (0.0008) -[2023-10-09 01:30:05,991][88326] Updated weights for policy 0, policy_version 36132 (0.0009) -[2023-10-09 01:30:06,355][88326] Updated weights for policy 0, policy_version 36142 (0.0010) -[2023-10-09 01:30:06,356][88327] Updated weights for policy 1, policy_version 36160 (0.0009) -[2023-10-09 01:30:06,727][88326] Updated weights for policy 0, policy_version 36152 (0.0008) -[2023-10-09 01:30:08,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 74055680. Throughput: 0: 1688.4, 1: 1673.7. Samples: 18517310. Policy #0 lag: (min: 17.0, avg: 29.8, max: 49.0) -[2023-10-09 01:30:08,975][87372] Avg episode reward: [(0, '6.490'), (1, '5.800')] -[2023-10-09 01:30:10,440][88327] Updated weights for policy 1, policy_version 36170 (0.0010) -[2023-10-09 01:30:10,798][88327] Updated weights for policy 1, policy_version 36180 (0.0008) -[2023-10-09 01:30:10,849][88326] Updated weights for policy 0, policy_version 36162 (0.0011) -[2023-10-09 01:30:11,155][88327] Updated weights for policy 1, policy_version 36190 (0.0007) -[2023-10-09 01:30:11,215][88326] Updated weights for policy 0, policy_version 36172 (0.0008) -[2023-10-09 01:30:11,585][88326] Updated weights for policy 0, policy_version 36182 (0.0009) -[2023-10-09 01:30:11,954][88326] Updated weights for policy 0, policy_version 36192 (0.0010) -[2023-10-09 01:30:13,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 74121216. Throughput: 0: 1666.5, 1: 1686.6. Samples: 18536884. Policy #0 lag: (min: 17.0, avg: 29.8, max: 49.0) -[2023-10-09 01:30:13,975][87372] Avg episode reward: [(0, '6.100'), (1, '6.370')] -[2023-10-09 01:30:15,101][88327] Updated weights for policy 1, policy_version 36200 (0.0007) -[2023-10-09 01:30:15,457][88327] Updated weights for policy 1, policy_version 36210 (0.0008) -[2023-10-09 01:30:15,813][88327] Updated weights for policy 1, policy_version 36220 (0.0008) -[2023-10-09 01:30:16,125][88326] Updated weights for policy 0, policy_version 36202 (0.0007) -[2023-10-09 01:30:16,493][88326] Updated weights for policy 0, policy_version 36212 (0.0009) -[2023-10-09 01:30:16,871][88326] Updated weights for policy 0, policy_version 36222 (0.0009) -[2023-10-09 01:30:18,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 74186752. Throughput: 0: 1692.4, 1: 1695.0. Samples: 18557826. Policy #0 lag: (min: 17.0, avg: 29.8, max: 49.0) -[2023-10-09 01:30:18,974][87372] Avg episode reward: [(0, '5.920'), (1, '5.790')] -[2023-10-09 01:30:19,880][88327] Updated weights for policy 1, policy_version 36230 (0.0008) -[2023-10-09 01:30:20,245][88327] Updated weights for policy 1, policy_version 36240 (0.0008) -[2023-10-09 01:30:20,609][88327] Updated weights for policy 1, policy_version 36250 (0.0009) -[2023-10-09 01:30:20,771][88326] Updated weights for policy 0, policy_version 36232 (0.0009) -[2023-10-09 01:30:21,146][88326] Updated weights for policy 0, policy_version 36242 (0.0009) -[2023-10-09 01:30:21,516][88326] Updated weights for policy 0, policy_version 36252 (0.0011) -[2023-10-09 01:30:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 74252288. Throughput: 0: 1675.1, 1: 1673.9. Samples: 18567560. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-09 01:30:23,975][87372] Avg episode reward: [(0, '6.060'), (1, '5.620')] -[2023-10-09 01:30:24,659][88327] Updated weights for policy 1, policy_version 36260 (0.0008) -[2023-10-09 01:30:25,027][88327] Updated weights for policy 1, policy_version 36270 (0.0007) -[2023-10-09 01:30:25,389][88327] Updated weights for policy 1, policy_version 36280 (0.0009) -[2023-10-09 01:30:25,480][88326] Updated weights for policy 0, policy_version 36262 (0.0008) -[2023-10-09 01:30:25,852][88326] Updated weights for policy 0, policy_version 36272 (0.0008) -[2023-10-09 01:30:26,217][88326] Updated weights for policy 0, policy_version 36282 (0.0008) -[2023-10-09 01:30:28,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 74317824. Throughput: 0: 1678.9, 1: 1697.2. Samples: 18588038. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-09 01:30:28,974][87372] Avg episode reward: [(0, '5.550'), (1, '6.070')] -[2023-10-09 01:30:29,248][88327] Updated weights for policy 1, policy_version 36290 (0.0008) -[2023-10-09 01:30:29,614][88327] Updated weights for policy 1, policy_version 36300 (0.0009) -[2023-10-09 01:30:29,982][88327] Updated weights for policy 1, policy_version 36310 (0.0008) -[2023-10-09 01:30:30,198][88326] Updated weights for policy 0, policy_version 36292 (0.0007) -[2023-10-09 01:30:30,346][88327] Updated weights for policy 1, policy_version 36320 (0.0008) -[2023-10-09 01:30:30,567][88326] Updated weights for policy 0, policy_version 36302 (0.0007) -[2023-10-09 01:30:30,932][88326] Updated weights for policy 0, policy_version 36312 (0.0009) -[2023-10-09 01:30:33,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 74383360. Throughput: 0: 1698.3, 1: 1697.3. Samples: 18609138. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-09 01:30:33,975][87372] Avg episode reward: [(0, '5.740'), (1, '6.340')] -[2023-10-09 01:30:33,984][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000036320_37191680.pth... -[2023-10-09 01:30:34,021][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000034752_35586048.pth -[2023-10-09 01:30:34,378][88327] Updated weights for policy 1, policy_version 36330 (0.0008) -[2023-10-09 01:30:34,741][88327] Updated weights for policy 1, policy_version 36340 (0.0010) -[2023-10-09 01:30:35,014][88326] Updated weights for policy 0, policy_version 36322 (0.0007) -[2023-10-09 01:30:35,110][88327] Updated weights for policy 1, policy_version 36350 (0.0009) -[2023-10-09 01:30:35,174][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000036352_37224448.pth... -[2023-10-09 01:30:35,206][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000034752_35586048.pth -[2023-10-09 01:30:35,381][88326] Updated weights for policy 0, policy_version 36332 (0.0008) -[2023-10-09 01:30:35,746][88326] Updated weights for policy 0, policy_version 36342 (0.0010) -[2023-10-09 01:30:36,107][88326] Updated weights for policy 0, policy_version 36352 (0.0008) -[2023-10-09 01:30:38,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 74448896. Throughput: 0: 1667.8, 1: 1681.5. Samples: 18618232. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-09 01:30:38,975][87372] Avg episode reward: [(0, '6.210'), (1, '6.110')] -[2023-10-09 01:30:39,214][88327] Updated weights for policy 1, policy_version 36360 (0.0009) -[2023-10-09 01:30:39,580][88327] Updated weights for policy 1, policy_version 36370 (0.0009) -[2023-10-09 01:30:39,947][88327] Updated weights for policy 1, policy_version 36380 (0.0010) -[2023-10-09 01:30:40,090][88326] Updated weights for policy 0, policy_version 36362 (0.0009) -[2023-10-09 01:30:40,457][88326] Updated weights for policy 0, policy_version 36372 (0.0009) -[2023-10-09 01:30:40,822][88326] Updated weights for policy 0, policy_version 36382 (0.0009) -[2023-10-09 01:30:43,962][88327] Updated weights for policy 1, policy_version 36390 (0.0009) -[2023-10-09 01:30:43,974][87372] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 74514432. Throughput: 0: 1689.2, 1: 1696.8. Samples: 18639236. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-09 01:30:43,975][87372] Avg episode reward: [(0, '5.930'), (1, '6.270')] -[2023-10-09 01:30:44,322][88327] Updated weights for policy 1, policy_version 36400 (0.0009) -[2023-10-09 01:30:44,690][88327] Updated weights for policy 1, policy_version 36410 (0.0010) -[2023-10-09 01:30:44,858][88326] Updated weights for policy 0, policy_version 36392 (0.0008) -[2023-10-09 01:30:45,230][88326] Updated weights for policy 0, policy_version 36402 (0.0008) -[2023-10-09 01:30:45,600][88326] Updated weights for policy 0, policy_version 36412 (0.0010) -[2023-10-09 01:30:48,752][88327] Updated weights for policy 1, policy_version 36420 (0.0009) -[2023-10-09 01:30:48,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 74579968. Throughput: 0: 1694.5, 1: 1702.6. Samples: 18659990. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-09 01:30:48,975][87372] Avg episode reward: [(0, '5.960'), (1, '6.100')] -[2023-10-09 01:30:49,126][88327] Updated weights for policy 1, policy_version 36430 (0.0008) -[2023-10-09 01:30:49,489][88327] Updated weights for policy 1, policy_version 36440 (0.0007) -[2023-10-09 01:30:49,592][88326] Updated weights for policy 0, policy_version 36422 (0.0010) -[2023-10-09 01:30:49,969][88326] Updated weights for policy 0, policy_version 36432 (0.0008) -[2023-10-09 01:30:50,326][88326] Updated weights for policy 0, policy_version 36442 (0.0008) -[2023-10-09 01:30:53,437][88327] Updated weights for policy 1, policy_version 36450 (0.0007) -[2023-10-09 01:30:53,795][88327] Updated weights for policy 1, policy_version 36460 (0.0008) -[2023-10-09 01:30:53,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 74645504. Throughput: 0: 1675.1, 1: 1698.4. Samples: 18669116. Policy #0 lag: (min: 11.0, avg: 19.0, max: 43.0) -[2023-10-09 01:30:53,975][87372] Avg episode reward: [(0, '6.510'), (1, '5.790')] -[2023-10-09 01:30:54,163][88327] Updated weights for policy 1, policy_version 36470 (0.0008) -[2023-10-09 01:30:54,345][88326] Updated weights for policy 0, policy_version 36452 (0.0009) -[2023-10-09 01:30:54,521][88327] Updated weights for policy 1, policy_version 36480 (0.0008) -[2023-10-09 01:30:54,709][88326] Updated weights for policy 0, policy_version 36462 (0.0010) -[2023-10-09 01:30:55,088][88326] Updated weights for policy 0, policy_version 36472 (0.0010) -[2023-10-09 01:30:58,671][88327] Updated weights for policy 1, policy_version 36490 (0.0012) -[2023-10-09 01:30:58,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 74711040. Throughput: 0: 1694.6, 1: 1704.0. Samples: 18689820. Policy #0 lag: (min: 11.0, avg: 19.0, max: 43.0) -[2023-10-09 01:30:58,975][87372] Avg episode reward: [(0, '6.210'), (1, '5.980')] -[2023-10-09 01:30:59,037][88327] Updated weights for policy 1, policy_version 36500 (0.0009) -[2023-10-09 01:30:59,221][88326] Updated weights for policy 0, policy_version 36482 (0.0007) -[2023-10-09 01:30:59,401][88327] Updated weights for policy 1, policy_version 36510 (0.0007) -[2023-10-09 01:30:59,586][88326] Updated weights for policy 0, policy_version 36492 (0.0007) -[2023-10-09 01:30:59,955][88326] Updated weights for policy 0, policy_version 36502 (0.0008) -[2023-10-09 01:31:00,321][88326] Updated weights for policy 0, policy_version 36512 (0.0011) -[2023-10-09 01:31:03,458][88327] Updated weights for policy 1, policy_version 36520 (0.0007) -[2023-10-09 01:31:03,827][88327] Updated weights for policy 1, policy_version 36530 (0.0008) -[2023-10-09 01:31:03,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 74776576. Throughput: 0: 1695.5, 1: 1700.7. Samples: 18710656. Policy #0 lag: (min: 11.0, avg: 19.0, max: 43.0) -[2023-10-09 01:31:03,975][87372] Avg episode reward: [(0, '6.140'), (1, '6.160')] -[2023-10-09 01:31:04,194][88327] Updated weights for policy 1, policy_version 36540 (0.0009) -[2023-10-09 01:31:04,497][88326] Updated weights for policy 0, policy_version 36522 (0.0008) -[2023-10-09 01:31:04,865][88326] Updated weights for policy 0, policy_version 36532 (0.0008) -[2023-10-09 01:31:05,244][88326] Updated weights for policy 0, policy_version 36542 (0.0008) -[2023-10-09 01:31:08,269][88327] Updated weights for policy 1, policy_version 36550 (0.0008) -[2023-10-09 01:31:08,634][88327] Updated weights for policy 1, policy_version 36560 (0.0009) -[2023-10-09 01:31:08,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 74842112. Throughput: 0: 1682.8, 1: 1701.9. Samples: 18719868. Policy #0 lag: (min: 11.0, avg: 19.0, max: 43.0) -[2023-10-09 01:31:08,975][87372] Avg episode reward: [(0, '5.790'), (1, '6.290')] -[2023-10-09 01:31:08,998][88327] Updated weights for policy 1, policy_version 36570 (0.0008) -[2023-10-09 01:31:09,397][88326] Updated weights for policy 0, policy_version 36552 (0.0009) -[2023-10-09 01:31:09,771][88326] Updated weights for policy 0, policy_version 36562 (0.0007) -[2023-10-09 01:31:10,131][88326] Updated weights for policy 0, policy_version 36572 (0.0007) -[2023-10-09 01:31:12,947][88327] Updated weights for policy 1, policy_version 36580 (0.0008) -[2023-10-09 01:31:13,308][88327] Updated weights for policy 1, policy_version 36590 (0.0008) -[2023-10-09 01:31:13,678][88327] Updated weights for policy 1, policy_version 36600 (0.0010) -[2023-10-09 01:31:13,974][87372] Fps is (10 sec: 16384.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 74940416. Throughput: 0: 1690.3, 1: 1700.6. Samples: 18740630. Policy #0 lag: (min: 11.0, avg: 19.0, max: 43.0) -[2023-10-09 01:31:13,974][87372] Avg episode reward: [(0, '5.590'), (1, '6.040')] -[2023-10-09 01:31:14,262][88326] Updated weights for policy 0, policy_version 36582 (0.0008) -[2023-10-09 01:31:14,629][88326] Updated weights for policy 0, policy_version 36592 (0.0007) -[2023-10-09 01:31:14,990][88326] Updated weights for policy 0, policy_version 36602 (0.0008) -[2023-10-09 01:31:17,703][88327] Updated weights for policy 1, policy_version 36610 (0.0009) -[2023-10-09 01:31:18,067][88327] Updated weights for policy 1, policy_version 36620 (0.0008) -[2023-10-09 01:31:18,438][88327] Updated weights for policy 1, policy_version 36630 (0.0007) -[2023-10-09 01:31:18,807][88327] Updated weights for policy 1, policy_version 36640 (0.0007) -[2023-10-09 01:31:18,974][87372] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 75005952. Throughput: 0: 1684.7, 1: 1691.0. Samples: 18761044. Policy #0 lag: (min: 1.0, avg: 9.1, max: 33.0) -[2023-10-09 01:31:18,975][87372] Avg episode reward: [(0, '5.770'), (1, '6.090')] -[2023-10-09 01:31:19,217][88326] Updated weights for policy 0, policy_version 36612 (0.0009) -[2023-10-09 01:31:19,587][88326] Updated weights for policy 0, policy_version 36622 (0.0007) -[2023-10-09 01:31:19,960][88326] Updated weights for policy 0, policy_version 36632 (0.0007) -[2023-10-09 01:31:22,782][88327] Updated weights for policy 1, policy_version 36650 (0.0007) -[2023-10-09 01:31:23,147][88327] Updated weights for policy 1, policy_version 36660 (0.0007) -[2023-10-09 01:31:23,519][88327] Updated weights for policy 1, policy_version 36670 (0.0009) -[2023-10-09 01:31:23,897][88326] Updated weights for policy 0, policy_version 36642 (0.0007) -[2023-10-09 01:31:23,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 75071488. Throughput: 0: 1685.3, 1: 1707.2. Samples: 18770896. Policy #0 lag: (min: 1.0, avg: 9.1, max: 33.0) -[2023-10-09 01:31:23,974][87372] Avg episode reward: [(0, '5.940'), (1, '6.200')] -[2023-10-09 01:31:24,272][88326] Updated weights for policy 0, policy_version 36652 (0.0008) -[2023-10-09 01:31:24,636][88326] Updated weights for policy 0, policy_version 36662 (0.0008) -[2023-10-09 01:31:25,010][88326] Updated weights for policy 0, policy_version 36672 (0.0010) -[2023-10-09 01:31:27,530][88327] Updated weights for policy 1, policy_version 36680 (0.0009) -[2023-10-09 01:31:27,898][88327] Updated weights for policy 1, policy_version 36690 (0.0009) -[2023-10-09 01:31:28,270][88327] Updated weights for policy 1, policy_version 36700 (0.0008) -[2023-10-09 01:31:28,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 75137024. Throughput: 0: 1685.6, 1: 1707.2. Samples: 18791910. Policy #0 lag: (min: 1.0, avg: 9.1, max: 33.0) -[2023-10-09 01:31:28,975][87372] Avg episode reward: [(0, '5.910'), (1, '5.840')] -[2023-10-09 01:31:29,113][88326] Updated weights for policy 0, policy_version 36682 (0.0008) -[2023-10-09 01:31:29,478][88326] Updated weights for policy 0, policy_version 36692 (0.0010) -[2023-10-09 01:31:29,846][88326] Updated weights for policy 0, policy_version 36702 (0.0008) -[2023-10-09 01:31:32,315][88327] Updated weights for policy 1, policy_version 36710 (0.0010) -[2023-10-09 01:31:32,673][88327] Updated weights for policy 1, policy_version 36720 (0.0008) -[2023-10-09 01:31:33,047][88327] Updated weights for policy 1, policy_version 36730 (0.0009) -[2023-10-09 01:31:33,746][88326] Updated weights for policy 0, policy_version 36712 (0.0008) -[2023-10-09 01:31:33,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 75202560. Throughput: 0: 1690.2, 1: 1682.3. Samples: 18811754. Policy #0 lag: (min: 1.0, avg: 9.1, max: 33.0) -[2023-10-09 01:31:33,975][87372] Avg episode reward: [(0, '6.150'), (1, '5.710')] -[2023-10-09 01:31:34,119][88326] Updated weights for policy 0, policy_version 36722 (0.0008) -[2023-10-09 01:31:34,485][88326] Updated weights for policy 0, policy_version 36732 (0.0007) -[2023-10-09 01:31:36,936][88327] Updated weights for policy 1, policy_version 36740 (0.0008) -[2023-10-09 01:31:37,304][88327] Updated weights for policy 1, policy_version 36750 (0.0007) -[2023-10-09 01:31:37,666][88327] Updated weights for policy 1, policy_version 36760 (0.0009) -[2023-10-09 01:31:38,290][88326] Updated weights for policy 0, policy_version 36742 (0.0008) -[2023-10-09 01:31:38,664][88326] Updated weights for policy 0, policy_version 36752 (0.0009) -[2023-10-09 01:31:38,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 75268096. Throughput: 0: 1688.6, 1: 1713.1. Samples: 18822192. Policy #0 lag: (min: 1.0, avg: 9.1, max: 33.0) -[2023-10-09 01:31:38,974][87372] Avg episode reward: [(0, '5.860'), (1, '6.500')] -[2023-10-09 01:31:39,033][88326] Updated weights for policy 0, policy_version 36762 (0.0007) -[2023-10-09 01:31:41,770][88327] Updated weights for policy 1, policy_version 36770 (0.0007) -[2023-10-09 01:31:42,136][88327] Updated weights for policy 1, policy_version 36780 (0.0009) -[2023-10-09 01:31:42,506][88327] Updated weights for policy 1, policy_version 36790 (0.0008) -[2023-10-09 01:31:42,877][88327] Updated weights for policy 1, policy_version 36800 (0.0008) -[2023-10-09 01:31:43,102][88326] Updated weights for policy 0, policy_version 36772 (0.0009) -[2023-10-09 01:31:43,486][88326] Updated weights for policy 0, policy_version 36782 (0.0009) -[2023-10-09 01:31:43,866][88326] Updated weights for policy 0, policy_version 36792 (0.0009) -[2023-10-09 01:31:43,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 75333632. Throughput: 0: 1699.9, 1: 1702.0. Samples: 18842904. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-09 01:31:43,975][87372] Avg episode reward: [(0, '6.220'), (1, '6.210')] -[2023-10-09 01:31:46,886][88327] Updated weights for policy 1, policy_version 36810 (0.0008) -[2023-10-09 01:31:47,263][88327] Updated weights for policy 1, policy_version 36820 (0.0008) -[2023-10-09 01:31:47,629][88327] Updated weights for policy 1, policy_version 36830 (0.0011) -[2023-10-09 01:31:47,803][88326] Updated weights for policy 0, policy_version 36802 (0.0008) -[2023-10-09 01:31:48,165][88326] Updated weights for policy 0, policy_version 36812 (0.0010) -[2023-10-09 01:31:48,546][88326] Updated weights for policy 0, policy_version 36822 (0.0010) -[2023-10-09 01:31:48,910][88326] Updated weights for policy 0, policy_version 36832 (0.0008) -[2023-10-09 01:31:48,974][87372] Fps is (10 sec: 16383.5, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 75431936. Throughput: 0: 1691.6, 1: 1680.5. Samples: 18862402. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-09 01:31:48,975][87372] Avg episode reward: [(0, '6.530'), (1, '6.510')] -[2023-10-09 01:31:51,695][88327] Updated weights for policy 1, policy_version 36840 (0.0008) -[2023-10-09 01:31:52,058][88327] Updated weights for policy 1, policy_version 36850 (0.0007) -[2023-10-09 01:31:52,435][88327] Updated weights for policy 1, policy_version 36860 (0.0009) -[2023-10-09 01:31:52,992][88326] Updated weights for policy 0, policy_version 36842 (0.0010) -[2023-10-09 01:31:53,369][88326] Updated weights for policy 0, policy_version 36852 (0.0008) -[2023-10-09 01:31:53,735][88326] Updated weights for policy 0, policy_version 36862 (0.0007) -[2023-10-09 01:31:53,974][87372] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 75497472. Throughput: 0: 1700.7, 1: 1709.4. Samples: 18873322. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-09 01:31:53,975][87372] Avg episode reward: [(0, '5.890'), (1, '6.400')] -[2023-10-09 01:31:56,436][88327] Updated weights for policy 1, policy_version 36870 (0.0008) -[2023-10-09 01:31:56,802][88327] Updated weights for policy 1, policy_version 36880 (0.0009) -[2023-10-09 01:31:57,165][88327] Updated weights for policy 1, policy_version 36890 (0.0008) -[2023-10-09 01:31:57,644][88326] Updated weights for policy 0, policy_version 36872 (0.0008) -[2023-10-09 01:31:58,009][88326] Updated weights for policy 0, policy_version 36882 (0.0009) -[2023-10-09 01:31:58,373][88326] Updated weights for policy 0, policy_version 36892 (0.0011) -[2023-10-09 01:31:58,974][87372] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 75563008. Throughput: 0: 1704.7, 1: 1689.0. Samples: 18893344. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-09 01:31:58,975][87372] Avg episode reward: [(0, '6.370'), (1, '5.770')] -[2023-10-09 01:32:01,139][88327] Updated weights for policy 1, policy_version 36900 (0.0008) -[2023-10-09 01:32:01,505][88327] Updated weights for policy 1, policy_version 36910 (0.0011) -[2023-10-09 01:32:01,864][88327] Updated weights for policy 1, policy_version 36920 (0.0011) -[2023-10-09 01:32:02,413][88326] Updated weights for policy 0, policy_version 36902 (0.0009) -[2023-10-09 01:32:02,786][88326] Updated weights for policy 0, policy_version 36912 (0.0008) -[2023-10-09 01:32:03,153][88326] Updated weights for policy 0, policy_version 36922 (0.0009) -[2023-10-09 01:32:03,974][87372] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 75628544. Throughput: 0: 1681.3, 1: 1692.5. Samples: 18912864. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) -[2023-10-09 01:32:03,975][87372] Avg episode reward: [(0, '6.200'), (1, '6.280')] -[2023-10-09 01:32:05,805][88327] Updated weights for policy 1, policy_version 36930 (0.0009) -[2023-10-09 01:32:06,174][88327] Updated weights for policy 1, policy_version 36940 (0.0009) -[2023-10-09 01:32:06,534][88327] Updated weights for policy 1, policy_version 36950 (0.0009) -[2023-10-09 01:32:06,897][88327] Updated weights for policy 1, policy_version 36960 (0.0009) -[2023-10-09 01:32:07,287][88326] Updated weights for policy 0, policy_version 36932 (0.0007) -[2023-10-09 01:32:07,661][88326] Updated weights for policy 0, policy_version 36942 (0.0008) -[2023-10-09 01:32:08,033][88326] Updated weights for policy 0, policy_version 36952 (0.0008) -[2023-10-09 01:32:08,974][87372] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 75694080. Throughput: 0: 1703.4, 1: 1699.9. Samples: 18924044. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) -[2023-10-09 01:32:08,975][87372] Avg episode reward: [(0, '5.900'), (1, '5.570')] -[2023-10-09 01:32:10,860][88327] Updated weights for policy 1, policy_version 36970 (0.0009) -[2023-10-09 01:32:11,224][88327] Updated weights for policy 1, policy_version 36980 (0.0010) -[2023-10-09 01:32:11,587][88327] Updated weights for policy 1, policy_version 36990 (0.0009) -[2023-10-09 01:32:12,138][88326] Updated weights for policy 0, policy_version 36962 (0.0008) -[2023-10-09 01:32:12,505][88326] Updated weights for policy 0, policy_version 36972 (0.0007) -[2023-10-09 01:32:12,879][88326] Updated weights for policy 0, policy_version 36982 (0.0008) -[2023-10-09 01:32:13,241][88326] Updated weights for policy 0, policy_version 36992 (0.0011) -[2023-10-09 01:32:13,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 75759616. Throughput: 0: 1701.6, 1: 1675.8. Samples: 18943894. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) -[2023-10-09 01:32:13,975][87372] Avg episode reward: [(0, '6.470'), (1, '5.910')] -[2023-10-09 01:32:15,863][88327] Updated weights for policy 1, policy_version 37000 (0.0008) -[2023-10-09 01:32:16,253][88327] Updated weights for policy 1, policy_version 37010 (0.0009) -[2023-10-09 01:32:16,625][88327] Updated weights for policy 1, policy_version 37020 (0.0007) -[2023-10-09 01:32:17,186][88326] Updated weights for policy 0, policy_version 37002 (0.0008) -[2023-10-09 01:32:17,558][88326] Updated weights for policy 0, policy_version 37012 (0.0008) -[2023-10-09 01:32:17,921][88326] Updated weights for policy 0, policy_version 37022 (0.0007) -[2023-10-09 01:32:18,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 75825152. Throughput: 0: 1677.7, 1: 1696.8. Samples: 18963606. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) -[2023-10-09 01:32:18,975][87372] Avg episode reward: [(0, '5.950'), (1, '6.020')] -[2023-10-09 01:32:20,519][88327] Updated weights for policy 1, policy_version 37030 (0.0010) -[2023-10-09 01:32:20,884][88327] Updated weights for policy 1, policy_version 37040 (0.0009) -[2023-10-09 01:32:21,254][88327] Updated weights for policy 1, policy_version 37050 (0.0008) -[2023-10-09 01:32:21,769][88326] Updated weights for policy 0, policy_version 37032 (0.0008) -[2023-10-09 01:32:22,137][88326] Updated weights for policy 0, policy_version 37042 (0.0007) -[2023-10-09 01:32:22,507][88326] Updated weights for policy 0, policy_version 37052 (0.0008) -[2023-10-09 01:32:23,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 75890688. Throughput: 0: 1709.1, 1: 1674.8. Samples: 18974466. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) -[2023-10-09 01:32:23,975][87372] Avg episode reward: [(0, '6.060'), (1, '6.200')] -[2023-10-09 01:32:25,360][88327] Updated weights for policy 1, policy_version 37060 (0.0008) -[2023-10-09 01:32:25,731][88327] Updated weights for policy 1, policy_version 37070 (0.0007) -[2023-10-09 01:32:26,089][88327] Updated weights for policy 1, policy_version 37080 (0.0009) -[2023-10-09 01:32:26,671][88326] Updated weights for policy 0, policy_version 37062 (0.0010) -[2023-10-09 01:32:27,043][88326] Updated weights for policy 0, policy_version 37072 (0.0009) -[2023-10-09 01:32:27,413][88326] Updated weights for policy 0, policy_version 37082 (0.0010) -[2023-10-09 01:32:28,974][87372] Fps is (10 sec: 13107.6, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 75956224. Throughput: 0: 1686.4, 1: 1673.7. Samples: 18994110. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) -[2023-10-09 01:32:28,974][87372] Avg episode reward: [(0, '6.480'), (1, '6.080')] -[2023-10-09 01:32:30,109][88327] Updated weights for policy 1, policy_version 37090 (0.0008) -[2023-10-09 01:32:30,479][88327] Updated weights for policy 1, policy_version 37100 (0.0009) -[2023-10-09 01:32:30,842][88327] Updated weights for policy 1, policy_version 37110 (0.0009) -[2023-10-09 01:32:31,210][88327] Updated weights for policy 1, policy_version 37120 (0.0008) -[2023-10-09 01:32:31,430][88326] Updated weights for policy 0, policy_version 37092 (0.0009) -[2023-10-09 01:32:31,798][88326] Updated weights for policy 0, policy_version 37102 (0.0009) -[2023-10-09 01:32:32,169][88326] Updated weights for policy 0, policy_version 37112 (0.0007) -[2023-10-09 01:32:33,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 76021760. Throughput: 0: 1684.0, 1: 1696.6. Samples: 19014528. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:32:33,975][87372] Avg episode reward: [(0, '5.880'), (1, '5.810')] -[2023-10-09 01:32:33,982][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000037120_38010880.pth... -[2023-10-09 01:32:33,982][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000037120_38010880.pth... -[2023-10-09 01:32:34,012][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000035520_36372480.pth -[2023-10-09 01:32:34,015][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000035552_36405248.pth -[2023-10-09 01:32:35,260][88327] Updated weights for policy 1, policy_version 37130 (0.0009) -[2023-10-09 01:32:35,616][88327] Updated weights for policy 1, policy_version 37140 (0.0009) -[2023-10-09 01:32:35,973][88327] Updated weights for policy 1, policy_version 37150 (0.0007) -[2023-10-09 01:32:36,086][88326] Updated weights for policy 0, policy_version 37122 (0.0010) -[2023-10-09 01:32:36,461][88326] Updated weights for policy 0, policy_version 37132 (0.0008) -[2023-10-09 01:32:36,834][88326] Updated weights for policy 0, policy_version 37142 (0.0008) -[2023-10-09 01:32:37,204][88326] Updated weights for policy 0, policy_version 37152 (0.0008) -[2023-10-09 01:32:38,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 76087296. Throughput: 0: 1699.5, 1: 1665.7. Samples: 19024756. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:32:38,975][87372] Avg episode reward: [(0, '6.220'), (1, '5.890')] -[2023-10-09 01:32:40,124][88327] Updated weights for policy 1, policy_version 37160 (0.0010) -[2023-10-09 01:32:40,484][88327] Updated weights for policy 1, policy_version 37170 (0.0009) -[2023-10-09 01:32:40,851][88327] Updated weights for policy 1, policy_version 37180 (0.0010) -[2023-10-09 01:32:41,250][88326] Updated weights for policy 0, policy_version 37162 (0.0007) -[2023-10-09 01:32:41,619][88326] Updated weights for policy 0, policy_version 37172 (0.0007) -[2023-10-09 01:32:41,984][88326] Updated weights for policy 0, policy_version 37182 (0.0008) -[2023-10-09 01:32:43,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 76152832. Throughput: 0: 1672.7, 1: 1684.2. Samples: 19044404. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:32:43,975][87372] Avg episode reward: [(0, '6.650'), (1, '5.570')] -[2023-10-09 01:32:45,047][88327] Updated weights for policy 1, policy_version 37190 (0.0008) -[2023-10-09 01:32:45,407][88327] Updated weights for policy 1, policy_version 37200 (0.0008) -[2023-10-09 01:32:45,768][88327] Updated weights for policy 1, policy_version 37210 (0.0008) -[2023-10-09 01:32:46,033][88326] Updated weights for policy 0, policy_version 37192 (0.0007) -[2023-10-09 01:32:46,403][88326] Updated weights for policy 0, policy_version 37202 (0.0007) -[2023-10-09 01:32:46,768][88326] Updated weights for policy 0, policy_version 37212 (0.0008) -[2023-10-09 01:32:48,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 76218368. Throughput: 0: 1698.3, 1: 1686.4. Samples: 19065172. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:32:48,975][87372] Avg episode reward: [(0, '5.770'), (1, '5.750')] -[2023-10-09 01:32:49,872][88327] Updated weights for policy 1, policy_version 37220 (0.0008) -[2023-10-09 01:32:50,230][88327] Updated weights for policy 1, policy_version 37230 (0.0010) -[2023-10-09 01:32:50,590][88327] Updated weights for policy 1, policy_version 37240 (0.0009) -[2023-10-09 01:32:50,733][88326] Updated weights for policy 0, policy_version 37222 (0.0009) -[2023-10-09 01:32:51,091][88326] Updated weights for policy 0, policy_version 37232 (0.0009) -[2023-10-09 01:32:51,466][88326] Updated weights for policy 0, policy_version 37242 (0.0008) -[2023-10-09 01:32:53,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 76283904. Throughput: 0: 1688.3, 1: 1662.4. Samples: 19074828. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:32:53,975][87372] Avg episode reward: [(0, '6.300'), (1, '5.880')] -[2023-10-09 01:32:54,718][88327] Updated weights for policy 1, policy_version 37250 (0.0009) -[2023-10-09 01:32:55,081][88327] Updated weights for policy 1, policy_version 37260 (0.0009) -[2023-10-09 01:32:55,447][88327] Updated weights for policy 1, policy_version 37270 (0.0010) -[2023-10-09 01:32:55,632][88326] Updated weights for policy 0, policy_version 37252 (0.0008) -[2023-10-09 01:32:55,807][88327] Updated weights for policy 1, policy_version 37280 (0.0008) -[2023-10-09 01:32:56,003][88326] Updated weights for policy 0, policy_version 37262 (0.0009) -[2023-10-09 01:32:56,374][88326] Updated weights for policy 0, policy_version 37272 (0.0008) -[2023-10-09 01:32:58,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 76349440. Throughput: 0: 1681.2, 1: 1688.7. Samples: 19095536. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:32:58,975][87372] Avg episode reward: [(0, '7.030'), (1, '5.860')] -[2023-10-09 01:32:58,976][88088] Saving new best policy, reward=7.030! -[2023-10-09 01:32:59,811][88327] Updated weights for policy 1, policy_version 37290 (0.0010) -[2023-10-09 01:33:00,187][88327] Updated weights for policy 1, policy_version 37300 (0.0009) -[2023-10-09 01:33:00,333][88326] Updated weights for policy 0, policy_version 37282 (0.0007) -[2023-10-09 01:33:00,547][88327] Updated weights for policy 1, policy_version 37310 (0.0008) -[2023-10-09 01:33:00,684][88326] Updated weights for policy 0, policy_version 37292 (0.0008) -[2023-10-09 01:33:01,057][88326] Updated weights for policy 0, policy_version 37302 (0.0010) -[2023-10-09 01:33:01,422][88326] Updated weights for policy 0, policy_version 37312 (0.0007) -[2023-10-09 01:33:03,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 76414976. Throughput: 0: 1703.8, 1: 1686.2. Samples: 19116156. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-09 01:33:03,975][87372] Avg episode reward: [(0, '6.010'), (1, '6.120')] -[2023-10-09 01:33:04,659][88327] Updated weights for policy 1, policy_version 37320 (0.0007) -[2023-10-09 01:33:05,026][88327] Updated weights for policy 1, policy_version 37330 (0.0007) -[2023-10-09 01:33:05,387][88327] Updated weights for policy 1, policy_version 37340 (0.0008) -[2023-10-09 01:33:05,404][88326] Updated weights for policy 0, policy_version 37322 (0.0008) -[2023-10-09 01:33:05,779][88326] Updated weights for policy 0, policy_version 37332 (0.0008) -[2023-10-09 01:33:06,146][88326] Updated weights for policy 0, policy_version 37342 (0.0009) -[2023-10-09 01:33:08,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 76480512. Throughput: 0: 1675.4, 1: 1680.7. Samples: 19125488. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-09 01:33:08,974][87372] Avg episode reward: [(0, '6.130'), (1, '6.050')] -[2023-10-09 01:33:09,365][88327] Updated weights for policy 1, policy_version 37350 (0.0008) -[2023-10-09 01:33:09,729][88327] Updated weights for policy 1, policy_version 37360 (0.0009) -[2023-10-09 01:33:10,093][88327] Updated weights for policy 1, policy_version 37370 (0.0010) -[2023-10-09 01:33:10,134][88326] Updated weights for policy 0, policy_version 37352 (0.0008) -[2023-10-09 01:33:10,504][88326] Updated weights for policy 0, policy_version 37362 (0.0009) -[2023-10-09 01:33:10,877][88326] Updated weights for policy 0, policy_version 37372 (0.0011) -[2023-10-09 01:33:13,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 76546048. Throughput: 0: 1694.7, 1: 1690.3. Samples: 19146432. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-09 01:33:13,974][87372] Avg episode reward: [(0, '6.690'), (1, '6.460')] -[2023-10-09 01:33:14,108][88327] Updated weights for policy 1, policy_version 37380 (0.0009) -[2023-10-09 01:33:14,474][88327] Updated weights for policy 1, policy_version 37390 (0.0009) -[2023-10-09 01:33:14,829][88326] Updated weights for policy 0, policy_version 37382 (0.0009) -[2023-10-09 01:33:14,844][88327] Updated weights for policy 1, policy_version 37400 (0.0007) -[2023-10-09 01:33:15,195][88326] Updated weights for policy 0, policy_version 37392 (0.0010) -[2023-10-09 01:33:15,557][88326] Updated weights for policy 0, policy_version 37402 (0.0010) -[2023-10-09 01:33:18,974][87372] Fps is (10 sec: 13106.6, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 76611584. Throughput: 0: 1704.0, 1: 1693.5. Samples: 19167416. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-09 01:33:18,975][87372] Avg episode reward: [(0, '6.480'), (1, '6.470')] -[2023-10-09 01:33:18,989][88327] Updated weights for policy 1, policy_version 37410 (0.0008) -[2023-10-09 01:33:19,358][88327] Updated weights for policy 1, policy_version 37420 (0.0008) -[2023-10-09 01:33:19,631][88326] Updated weights for policy 0, policy_version 37412 (0.0007) -[2023-10-09 01:33:19,727][88327] Updated weights for policy 1, policy_version 37430 (0.0007) -[2023-10-09 01:33:20,000][88326] Updated weights for policy 0, policy_version 37422 (0.0009) -[2023-10-09 01:33:20,095][88327] Updated weights for policy 1, policy_version 37440 (0.0008) -[2023-10-09 01:33:20,368][88326] Updated weights for policy 0, policy_version 37432 (0.0009) -[2023-10-09 01:33:23,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 76677120. Throughput: 0: 1679.4, 1: 1692.5. Samples: 19176490. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-09 01:33:23,975][87372] Avg episode reward: [(0, '6.270'), (1, '6.190')] -[2023-10-09 01:33:23,975][88327] Updated weights for policy 1, policy_version 37450 (0.0011) -[2023-10-09 01:33:24,340][88327] Updated weights for policy 1, policy_version 37460 (0.0009) -[2023-10-09 01:33:24,355][88326] Updated weights for policy 0, policy_version 37442 (0.0008) -[2023-10-09 01:33:24,707][88327] Updated weights for policy 1, policy_version 37470 (0.0008) -[2023-10-09 01:33:24,717][88326] Updated weights for policy 0, policy_version 37452 (0.0008) -[2023-10-09 01:33:25,083][88326] Updated weights for policy 0, policy_version 37462 (0.0010) -[2023-10-09 01:33:25,458][88326] Updated weights for policy 0, policy_version 37472 (0.0010) -[2023-10-09 01:33:28,750][88327] Updated weights for policy 1, policy_version 37480 (0.0010) -[2023-10-09 01:33:28,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 76742656. Throughput: 0: 1705.5, 1: 1696.6. Samples: 19197498. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-09 01:33:28,975][87372] Avg episode reward: [(0, '6.250'), (1, '6.670')] -[2023-10-09 01:33:29,114][88327] Updated weights for policy 1, policy_version 37490 (0.0009) -[2023-10-09 01:33:29,482][88327] Updated weights for policy 1, policy_version 37500 (0.0010) -[2023-10-09 01:33:29,553][88326] Updated weights for policy 0, policy_version 37482 (0.0008) -[2023-10-09 01:33:29,923][88326] Updated weights for policy 0, policy_version 37492 (0.0007) -[2023-10-09 01:33:30,282][88326] Updated weights for policy 0, policy_version 37502 (0.0009) -[2023-10-09 01:33:33,621][88327] Updated weights for policy 1, policy_version 37510 (0.0008) -[2023-10-09 01:33:33,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 76808192. Throughput: 0: 1711.4, 1: 1694.2. Samples: 19218426. Policy #0 lag: (min: 8.0, avg: 28.3, max: 40.0) -[2023-10-09 01:33:33,975][87372] Avg episode reward: [(0, '6.180'), (1, '5.710')] -[2023-10-09 01:33:33,983][88327] Updated weights for policy 1, policy_version 37520 (0.0009) -[2023-10-09 01:33:34,353][88327] Updated weights for policy 1, policy_version 37530 (0.0008) -[2023-10-09 01:33:34,420][88326] Updated weights for policy 0, policy_version 37512 (0.0007) -[2023-10-09 01:33:34,789][88326] Updated weights for policy 0, policy_version 37522 (0.0007) -[2023-10-09 01:33:35,163][88326] Updated weights for policy 0, policy_version 37532 (0.0007) -[2023-10-09 01:33:38,486][88327] Updated weights for policy 1, policy_version 37540 (0.0007) -[2023-10-09 01:33:38,864][88327] Updated weights for policy 1, policy_version 37550 (0.0007) -[2023-10-09 01:33:38,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 76873728. Throughput: 0: 1691.4, 1: 1697.6. Samples: 19227334. Policy #0 lag: (min: 8.0, avg: 28.3, max: 40.0) -[2023-10-09 01:33:38,975][87372] Avg episode reward: [(0, '6.120'), (1, '5.600')] -[2023-10-09 01:33:39,224][88327] Updated weights for policy 1, policy_version 37560 (0.0008) -[2023-10-09 01:33:39,323][88326] Updated weights for policy 0, policy_version 37542 (0.0008) -[2023-10-09 01:33:39,690][88326] Updated weights for policy 0, policy_version 37552 (0.0008) -[2023-10-09 01:33:40,072][88326] Updated weights for policy 0, policy_version 37562 (0.0008) -[2023-10-09 01:33:43,232][88327] Updated weights for policy 1, policy_version 37570 (0.0007) -[2023-10-09 01:33:43,596][88327] Updated weights for policy 1, policy_version 37580 (0.0009) -[2023-10-09 01:33:43,957][88327] Updated weights for policy 1, policy_version 37590 (0.0009) -[2023-10-09 01:33:43,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 76939264. Throughput: 0: 1699.4, 1: 1688.5. Samples: 19247990. Policy #0 lag: (min: 8.0, avg: 28.3, max: 40.0) -[2023-10-09 01:33:43,975][87372] Avg episode reward: [(0, '6.030'), (1, '6.130')] -[2023-10-09 01:33:43,984][88326] Updated weights for policy 0, policy_version 37572 (0.0010) -[2023-10-09 01:33:44,331][88327] Updated weights for policy 1, policy_version 37600 (0.0008) -[2023-10-09 01:33:44,347][88326] Updated weights for policy 0, policy_version 37582 (0.0009) -[2023-10-09 01:33:44,723][88326] Updated weights for policy 0, policy_version 37592 (0.0009) -[2023-10-09 01:33:48,367][88327] Updated weights for policy 1, policy_version 37610 (0.0009) -[2023-10-09 01:33:48,733][88327] Updated weights for policy 1, policy_version 37620 (0.0009) -[2023-10-09 01:33:48,854][88326] Updated weights for policy 0, policy_version 37602 (0.0010) -[2023-10-09 01:33:48,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 77004800. Throughput: 0: 1701.1, 1: 1691.9. Samples: 19268840. Policy #0 lag: (min: 8.0, avg: 28.3, max: 40.0) -[2023-10-09 01:33:48,975][87372] Avg episode reward: [(0, '6.390'), (1, '5.550')] -[2023-10-09 01:33:49,094][88327] Updated weights for policy 1, policy_version 37630 (0.0007) -[2023-10-09 01:33:49,221][88326] Updated weights for policy 0, policy_version 37612 (0.0007) -[2023-10-09 01:33:49,580][88326] Updated weights for policy 0, policy_version 37622 (0.0007) -[2023-10-09 01:33:49,956][88326] Updated weights for policy 0, policy_version 37632 (0.0007) -[2023-10-09 01:33:53,154][88327] Updated weights for policy 1, policy_version 37640 (0.0008) -[2023-10-09 01:33:53,517][88327] Updated weights for policy 1, policy_version 37650 (0.0008) -[2023-10-09 01:33:53,874][88327] Updated weights for policy 1, policy_version 37660 (0.0007) -[2023-10-09 01:33:53,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 77070336. Throughput: 0: 1699.5, 1: 1696.1. Samples: 19278290. Policy #0 lag: (min: 8.0, avg: 28.3, max: 40.0) -[2023-10-09 01:33:53,975][87372] Avg episode reward: [(0, '5.790'), (1, '5.880')] -[2023-10-09 01:33:54,001][88326] Updated weights for policy 0, policy_version 37642 (0.0009) -[2023-10-09 01:33:54,378][88326] Updated weights for policy 0, policy_version 37652 (0.0009) -[2023-10-09 01:33:54,748][88326] Updated weights for policy 0, policy_version 37662 (0.0009) -[2023-10-09 01:33:57,943][88327] Updated weights for policy 1, policy_version 37670 (0.0009) -[2023-10-09 01:33:58,311][88327] Updated weights for policy 1, policy_version 37680 (0.0009) -[2023-10-09 01:33:58,679][88327] Updated weights for policy 1, policy_version 37690 (0.0007) -[2023-10-09 01:33:58,800][88326] Updated weights for policy 0, policy_version 37672 (0.0007) -[2023-10-09 01:33:58,974][87372] Fps is (10 sec: 16384.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 77168640. Throughput: 0: 1698.9, 1: 1697.2. Samples: 19299256. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:33:58,975][87372] Avg episode reward: [(0, '5.710'), (1, '5.960')] -[2023-10-09 01:33:59,158][88326] Updated weights for policy 0, policy_version 37682 (0.0009) -[2023-10-09 01:33:59,530][88326] Updated weights for policy 0, policy_version 37692 (0.0010) -[2023-10-09 01:34:02,705][88327] Updated weights for policy 1, policy_version 37700 (0.0008) -[2023-10-09 01:34:03,073][88327] Updated weights for policy 1, policy_version 37710 (0.0009) -[2023-10-09 01:34:03,434][88327] Updated weights for policy 1, policy_version 37720 (0.0009) -[2023-10-09 01:34:03,594][88326] Updated weights for policy 0, policy_version 37702 (0.0010) -[2023-10-09 01:34:03,966][88326] Updated weights for policy 0, policy_version 37712 (0.0008) -[2023-10-09 01:34:03,974][87372] Fps is (10 sec: 16384.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 77234176. Throughput: 0: 1696.2, 1: 1680.4. Samples: 19319360. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:34:03,975][87372] Avg episode reward: [(0, '6.270'), (1, '6.160')] -[2023-10-09 01:34:04,334][88326] Updated weights for policy 0, policy_version 37722 (0.0008) -[2023-10-09 01:34:07,402][88327] Updated weights for policy 1, policy_version 37730 (0.0009) -[2023-10-09 01:34:07,770][88327] Updated weights for policy 1, policy_version 37740 (0.0011) -[2023-10-09 01:34:08,131][88327] Updated weights for policy 1, policy_version 37750 (0.0008) -[2023-10-09 01:34:08,325][88326] Updated weights for policy 0, policy_version 37732 (0.0007) -[2023-10-09 01:34:08,489][88327] Updated weights for policy 1, policy_version 37760 (0.0007) -[2023-10-09 01:34:08,688][88326] Updated weights for policy 0, policy_version 37742 (0.0008) -[2023-10-09 01:34:08,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 77299712. Throughput: 0: 1694.4, 1: 1695.6. Samples: 19329040. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:34:08,975][87372] Avg episode reward: [(0, '5.630'), (1, '5.710')] -[2023-10-09 01:34:09,056][88326] Updated weights for policy 0, policy_version 37752 (0.0009) -[2023-10-09 01:34:12,534][88327] Updated weights for policy 1, policy_version 37770 (0.0007) -[2023-10-09 01:34:12,905][88327] Updated weights for policy 1, policy_version 37780 (0.0007) -[2023-10-09 01:34:13,103][88326] Updated weights for policy 0, policy_version 37762 (0.0008) -[2023-10-09 01:34:13,272][88327] Updated weights for policy 1, policy_version 37790 (0.0008) -[2023-10-09 01:34:13,473][88326] Updated weights for policy 0, policy_version 37772 (0.0009) -[2023-10-09 01:34:13,833][88326] Updated weights for policy 0, policy_version 37782 (0.0010) -[2023-10-09 01:34:13,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 77365248. Throughput: 0: 1696.3, 1: 1693.8. Samples: 19350052. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:34:13,975][87372] Avg episode reward: [(0, '5.840'), (1, '5.510')] -[2023-10-09 01:34:14,202][88326] Updated weights for policy 0, policy_version 37792 (0.0008) -[2023-10-09 01:34:17,253][88327] Updated weights for policy 1, policy_version 37800 (0.0009) -[2023-10-09 01:34:17,622][88327] Updated weights for policy 1, policy_version 37810 (0.0008) -[2023-10-09 01:34:17,987][88327] Updated weights for policy 1, policy_version 37820 (0.0009) -[2023-10-09 01:34:18,258][88326] Updated weights for policy 0, policy_version 37802 (0.0007) -[2023-10-09 01:34:18,627][88326] Updated weights for policy 0, policy_version 37812 (0.0007) -[2023-10-09 01:34:18,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 77430784. Throughput: 0: 1685.5, 1: 1671.2. Samples: 19369476. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:34:18,975][87372] Avg episode reward: [(0, '6.480'), (1, '5.640')] -[2023-10-09 01:34:18,996][88326] Updated weights for policy 0, policy_version 37822 (0.0008) -[2023-10-09 01:34:22,125][88327] Updated weights for policy 1, policy_version 37830 (0.0007) -[2023-10-09 01:34:22,480][88327] Updated weights for policy 1, policy_version 37840 (0.0010) -[2023-10-09 01:34:22,840][88327] Updated weights for policy 1, policy_version 37850 (0.0009) -[2023-10-09 01:34:22,999][88326] Updated weights for policy 0, policy_version 37832 (0.0007) -[2023-10-09 01:34:23,362][88326] Updated weights for policy 0, policy_version 37842 (0.0007) -[2023-10-09 01:34:23,734][88326] Updated weights for policy 0, policy_version 37852 (0.0007) -[2023-10-09 01:34:23,974][87372] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 77529088. Throughput: 0: 1700.0, 1: 1697.1. Samples: 19380204. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:34:23,975][87372] Avg episode reward: [(0, '6.370'), (1, '5.530')] -[2023-10-09 01:34:26,997][88327] Updated weights for policy 1, policy_version 37860 (0.0010) -[2023-10-09 01:34:27,360][88327] Updated weights for policy 1, policy_version 37870 (0.0009) -[2023-10-09 01:34:27,727][88326] Updated weights for policy 0, policy_version 37862 (0.0009) -[2023-10-09 01:34:27,731][88327] Updated weights for policy 1, policy_version 37880 (0.0008) -[2023-10-09 01:34:28,092][88326] Updated weights for policy 0, policy_version 37872 (0.0008) -[2023-10-09 01:34:28,463][88326] Updated weights for policy 0, policy_version 37882 (0.0009) -[2023-10-09 01:34:28,974][87372] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 77594624. Throughput: 0: 1703.6, 1: 1689.4. Samples: 19400674. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:34:28,975][87372] Avg episode reward: [(0, '6.180'), (1, '5.710')] -[2023-10-09 01:34:31,785][88327] Updated weights for policy 1, policy_version 37890 (0.0007) -[2023-10-09 01:34:32,156][88327] Updated weights for policy 1, policy_version 37900 (0.0007) -[2023-10-09 01:34:32,523][88327] Updated weights for policy 1, policy_version 37910 (0.0009) -[2023-10-09 01:34:32,577][88326] Updated weights for policy 0, policy_version 37892 (0.0007) -[2023-10-09 01:34:32,885][88327] Updated weights for policy 1, policy_version 37920 (0.0009) -[2023-10-09 01:34:32,940][88326] Updated weights for policy 0, policy_version 37902 (0.0008) -[2023-10-09 01:34:33,313][88326] Updated weights for policy 0, policy_version 37912 (0.0009) -[2023-10-09 01:34:33,974][87372] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 77660160. Throughput: 0: 1677.5, 1: 1666.7. Samples: 19419330. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:34:33,975][87372] Avg episode reward: [(0, '6.110'), (1, '5.770')] -[2023-10-09 01:34:33,986][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000037920_38830080.pth... -[2023-10-09 01:34:33,986][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000037920_38830080.pth... -[2023-10-09 01:34:34,022][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000036352_37224448.pth -[2023-10-09 01:34:34,026][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000036320_37191680.pth -[2023-10-09 01:34:36,927][88327] Updated weights for policy 1, policy_version 37930 (0.0010) -[2023-10-09 01:34:37,293][88327] Updated weights for policy 1, policy_version 37940 (0.0010) -[2023-10-09 01:34:37,421][88326] Updated weights for policy 0, policy_version 37922 (0.0008) -[2023-10-09 01:34:37,663][88327] Updated weights for policy 1, policy_version 37950 (0.0007) -[2023-10-09 01:34:37,790][88326] Updated weights for policy 0, policy_version 37932 (0.0009) -[2023-10-09 01:34:38,168][88326] Updated weights for policy 0, policy_version 37942 (0.0010) -[2023-10-09 01:34:38,535][88326] Updated weights for policy 0, policy_version 37952 (0.0008) -[2023-10-09 01:34:38,974][87372] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 77725696. Throughput: 0: 1691.7, 1: 1690.6. Samples: 19430494. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:34:38,975][87372] Avg episode reward: [(0, '5.770'), (1, '5.820')] -[2023-10-09 01:34:41,696][88327] Updated weights for policy 1, policy_version 37960 (0.0009) -[2023-10-09 01:34:42,059][88327] Updated weights for policy 1, policy_version 37970 (0.0009) -[2023-10-09 01:34:42,429][88327] Updated weights for policy 1, policy_version 37980 (0.0008) -[2023-10-09 01:34:42,582][88326] Updated weights for policy 0, policy_version 37962 (0.0008) -[2023-10-09 01:34:42,944][88326] Updated weights for policy 0, policy_version 37972 (0.0010) -[2023-10-09 01:34:43,318][88326] Updated weights for policy 0, policy_version 37982 (0.0008) -[2023-10-09 01:34:43,974][87372] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 77791232. Throughput: 0: 1689.2, 1: 1673.0. Samples: 19450554. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:34:43,975][87372] Avg episode reward: [(0, '6.000'), (1, '5.700')] -[2023-10-09 01:34:46,444][88327] Updated weights for policy 1, policy_version 37990 (0.0010) -[2023-10-09 01:34:46,806][88327] Updated weights for policy 1, policy_version 38000 (0.0008) -[2023-10-09 01:34:47,173][88327] Updated weights for policy 1, policy_version 38010 (0.0007) -[2023-10-09 01:34:47,390][88326] Updated weights for policy 0, policy_version 37992 (0.0007) -[2023-10-09 01:34:47,757][88326] Updated weights for policy 0, policy_version 38002 (0.0010) -[2023-10-09 01:34:48,130][88326] Updated weights for policy 0, policy_version 38012 (0.0009) -[2023-10-09 01:34:48,974][87372] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 77856768. Throughput: 0: 1668.0, 1: 1677.6. Samples: 19469912. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:34:48,975][87372] Avg episode reward: [(0, '6.120'), (1, '5.620')] -[2023-10-09 01:34:51,284][88327] Updated weights for policy 1, policy_version 38020 (0.0007) -[2023-10-09 01:34:51,651][88327] Updated weights for policy 1, policy_version 38030 (0.0007) -[2023-10-09 01:34:52,018][88327] Updated weights for policy 1, policy_version 38040 (0.0008) -[2023-10-09 01:34:52,115][88326] Updated weights for policy 0, policy_version 38022 (0.0008) -[2023-10-09 01:34:52,482][88326] Updated weights for policy 0, policy_version 38032 (0.0007) -[2023-10-09 01:34:52,847][88326] Updated weights for policy 0, policy_version 38042 (0.0008) -[2023-10-09 01:34:53,974][87372] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 77922304. Throughput: 0: 1697.0, 1: 1692.4. Samples: 19481562. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-10-09 01:34:53,975][87372] Avg episode reward: [(0, '6.020'), (1, '5.750')] -[2023-10-09 01:34:55,826][88327] Updated weights for policy 1, policy_version 38050 (0.0009) -[2023-10-09 01:34:56,191][88327] Updated weights for policy 1, policy_version 38060 (0.0008) -[2023-10-09 01:34:56,556][88327] Updated weights for policy 1, policy_version 38070 (0.0008) -[2023-10-09 01:34:56,898][88326] Updated weights for policy 0, policy_version 38052 (0.0008) -[2023-10-09 01:34:56,918][88327] Updated weights for policy 1, policy_version 38080 (0.0008) -[2023-10-09 01:34:57,268][88326] Updated weights for policy 0, policy_version 38062 (0.0007) -[2023-10-09 01:34:57,630][88326] Updated weights for policy 0, policy_version 38072 (0.0007) -[2023-10-09 01:34:58,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 77987840. Throughput: 0: 1682.8, 1: 1668.7. Samples: 19500872. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-10-09 01:34:58,975][87372] Avg episode reward: [(0, '6.120'), (1, '6.040')] -[2023-10-09 01:35:00,985][88327] Updated weights for policy 1, policy_version 38090 (0.0008) -[2023-10-09 01:35:01,339][88327] Updated weights for policy 1, policy_version 38100 (0.0010) -[2023-10-09 01:35:01,610][88326] Updated weights for policy 0, policy_version 38082 (0.0008) -[2023-10-09 01:35:01,705][88327] Updated weights for policy 1, policy_version 38110 (0.0010) -[2023-10-09 01:35:01,972][88326] Updated weights for policy 0, policy_version 38092 (0.0009) -[2023-10-09 01:35:02,339][88326] Updated weights for policy 0, policy_version 38102 (0.0007) -[2023-10-09 01:35:02,710][88326] Updated weights for policy 0, policy_version 38112 (0.0009) -[2023-10-09 01:35:03,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 78053376. Throughput: 0: 1670.5, 1: 1695.8. Samples: 19520962. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-10-09 01:35:03,975][87372] Avg episode reward: [(0, '6.210'), (1, '5.700')] -[2023-10-09 01:35:05,863][88327] Updated weights for policy 1, policy_version 38120 (0.0010) -[2023-10-09 01:35:06,219][88327] Updated weights for policy 1, policy_version 38130 (0.0009) -[2023-10-09 01:35:06,581][88327] Updated weights for policy 1, policy_version 38140 (0.0008) -[2023-10-09 01:35:06,701][88326] Updated weights for policy 0, policy_version 38122 (0.0009) -[2023-10-09 01:35:07,074][88326] Updated weights for policy 0, policy_version 38132 (0.0008) -[2023-10-09 01:35:07,441][88326] Updated weights for policy 0, policy_version 38142 (0.0007) -[2023-10-09 01:35:08,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 78118912. Throughput: 0: 1695.5, 1: 1683.8. Samples: 19532270. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-10-09 01:35:08,975][87372] Avg episode reward: [(0, '6.280'), (1, '5.790')] -[2023-10-09 01:35:10,615][88327] Updated weights for policy 1, policy_version 38150 (0.0009) -[2023-10-09 01:35:10,978][88327] Updated weights for policy 1, policy_version 38160 (0.0008) -[2023-10-09 01:35:11,344][88327] Updated weights for policy 1, policy_version 38170 (0.0008) -[2023-10-09 01:35:11,474][88326] Updated weights for policy 0, policy_version 38152 (0.0008) -[2023-10-09 01:35:11,831][88326] Updated weights for policy 0, policy_version 38162 (0.0009) -[2023-10-09 01:35:12,205][88326] Updated weights for policy 0, policy_version 38172 (0.0007) -[2023-10-09 01:35:13,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 78184448. Throughput: 0: 1666.8, 1: 1682.4. Samples: 19551390. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-10-09 01:35:13,975][87372] Avg episode reward: [(0, '6.330'), (1, '5.900')] -[2023-10-09 01:35:15,289][88327] Updated weights for policy 1, policy_version 38180 (0.0007) -[2023-10-09 01:35:15,663][88327] Updated weights for policy 1, policy_version 38190 (0.0009) -[2023-10-09 01:35:16,030][88327] Updated weights for policy 1, policy_version 38200 (0.0007) -[2023-10-09 01:35:16,372][88326] Updated weights for policy 0, policy_version 38182 (0.0008) -[2023-10-09 01:35:16,732][88326] Updated weights for policy 0, policy_version 38192 (0.0007) -[2023-10-09 01:35:17,102][88326] Updated weights for policy 0, policy_version 38202 (0.0007) -[2023-10-09 01:35:18,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 78249984. Throughput: 0: 1688.1, 1: 1710.9. Samples: 19572286. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-10-09 01:35:18,975][87372] Avg episode reward: [(0, '6.500'), (1, '5.650')] -[2023-10-09 01:35:20,137][88327] Updated weights for policy 1, policy_version 38210 (0.0008) -[2023-10-09 01:35:20,501][88327] Updated weights for policy 1, policy_version 38220 (0.0008) -[2023-10-09 01:35:20,873][88327] Updated weights for policy 1, policy_version 38230 (0.0008) -[2023-10-09 01:35:21,215][88326] Updated weights for policy 0, policy_version 38212 (0.0007) -[2023-10-09 01:35:21,231][88327] Updated weights for policy 1, policy_version 38240 (0.0007) -[2023-10-09 01:35:21,579][88326] Updated weights for policy 0, policy_version 38222 (0.0007) -[2023-10-09 01:35:21,948][88326] Updated weights for policy 0, policy_version 38232 (0.0010) -[2023-10-09 01:35:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 78315520. Throughput: 0: 1697.9, 1: 1686.4. Samples: 19582788. Policy #0 lag: (min: 26.0, avg: 26.1, max: 34.0) -[2023-10-09 01:35:23,975][87372] Avg episode reward: [(0, '6.050'), (1, '5.700')] -[2023-10-09 01:35:25,306][88327] Updated weights for policy 1, policy_version 38250 (0.0009) -[2023-10-09 01:35:25,674][88327] Updated weights for policy 1, policy_version 38260 (0.0010) -[2023-10-09 01:35:26,006][88326] Updated weights for policy 0, policy_version 38242 (0.0007) -[2023-10-09 01:35:26,034][88327] Updated weights for policy 1, policy_version 38270 (0.0009) -[2023-10-09 01:35:26,375][88326] Updated weights for policy 0, policy_version 38252 (0.0011) -[2023-10-09 01:35:26,751][88326] Updated weights for policy 0, policy_version 38262 (0.0011) -[2023-10-09 01:35:27,115][88326] Updated weights for policy 0, policy_version 38272 (0.0010) -[2023-10-09 01:35:28,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 78381056. Throughput: 0: 1666.4, 1: 1701.2. Samples: 19602100. Policy #0 lag: (min: 26.0, avg: 26.1, max: 34.0) -[2023-10-09 01:35:28,975][87372] Avg episode reward: [(0, '5.940'), (1, '5.960')] -[2023-10-09 01:35:30,056][88327] Updated weights for policy 1, policy_version 38280 (0.0008) -[2023-10-09 01:35:30,426][88327] Updated weights for policy 1, policy_version 38290 (0.0008) -[2023-10-09 01:35:30,789][88327] Updated weights for policy 1, policy_version 38300 (0.0008) -[2023-10-09 01:35:31,105][88326] Updated weights for policy 0, policy_version 38282 (0.0008) -[2023-10-09 01:35:31,475][88326] Updated weights for policy 0, policy_version 38292 (0.0010) -[2023-10-09 01:35:31,849][88326] Updated weights for policy 0, policy_version 38302 (0.0011) -[2023-10-09 01:35:33,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 78446592. Throughput: 0: 1689.5, 1: 1712.6. Samples: 19623006. Policy #0 lag: (min: 26.0, avg: 26.1, max: 34.0) -[2023-10-09 01:35:33,975][87372] Avg episode reward: [(0, '6.220'), (1, '5.500')] -[2023-10-09 01:35:34,630][88327] Updated weights for policy 1, policy_version 38310 (0.0009) -[2023-10-09 01:35:34,998][88327] Updated weights for policy 1, policy_version 38320 (0.0009) -[2023-10-09 01:35:35,358][88327] Updated weights for policy 1, policy_version 38330 (0.0008) -[2023-10-09 01:35:36,067][88326] Updated weights for policy 0, policy_version 38312 (0.0009) -[2023-10-09 01:35:36,449][88326] Updated weights for policy 0, policy_version 38322 (0.0010) -[2023-10-09 01:35:36,815][88326] Updated weights for policy 0, policy_version 38332 (0.0010) -[2023-10-09 01:35:38,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 78512128. Throughput: 0: 1679.6, 1: 1684.1. Samples: 19632930. Policy #0 lag: (min: 26.0, avg: 26.1, max: 34.0) -[2023-10-09 01:35:38,975][87372] Avg episode reward: [(0, '6.550'), (1, '5.840')] -[2023-10-09 01:35:39,377][88327] Updated weights for policy 1, policy_version 38340 (0.0007) -[2023-10-09 01:35:39,750][88327] Updated weights for policy 1, policy_version 38350 (0.0007) -[2023-10-09 01:35:40,118][88327] Updated weights for policy 1, policy_version 38360 (0.0009) -[2023-10-09 01:35:40,770][88326] Updated weights for policy 0, policy_version 38342 (0.0009) -[2023-10-09 01:35:41,144][88326] Updated weights for policy 0, policy_version 38352 (0.0008) -[2023-10-09 01:35:41,520][88326] Updated weights for policy 0, policy_version 38362 (0.0008) -[2023-10-09 01:35:43,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 78577664. Throughput: 0: 1674.3, 1: 1707.9. Samples: 19653068. Policy #0 lag: (min: 26.0, avg: 26.1, max: 34.0) -[2023-10-09 01:35:43,975][87372] Avg episode reward: [(0, '6.070'), (1, '6.290')] -[2023-10-09 01:35:44,256][88327] Updated weights for policy 1, policy_version 38370 (0.0008) -[2023-10-09 01:35:44,623][88327] Updated weights for policy 1, policy_version 38380 (0.0008) -[2023-10-09 01:35:44,988][88327] Updated weights for policy 1, policy_version 38390 (0.0007) -[2023-10-09 01:35:45,351][88327] Updated weights for policy 1, policy_version 38400 (0.0008) -[2023-10-09 01:35:45,527][88326] Updated weights for policy 0, policy_version 38372 (0.0008) -[2023-10-09 01:35:45,886][88326] Updated weights for policy 0, policy_version 38382 (0.0010) -[2023-10-09 01:35:46,255][88326] Updated weights for policy 0, policy_version 38392 (0.0008) -[2023-10-09 01:35:48,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 78643200. Throughput: 0: 1698.1, 1: 1706.1. Samples: 19674146. Policy #0 lag: (min: 26.0, avg: 26.1, max: 34.0) -[2023-10-09 01:35:48,975][87372] Avg episode reward: [(0, '6.190'), (1, '6.300')] -[2023-10-09 01:35:49,276][88327] Updated weights for policy 1, policy_version 38410 (0.0008) -[2023-10-09 01:35:49,637][88327] Updated weights for policy 1, policy_version 38420 (0.0008) -[2023-10-09 01:35:50,011][88327] Updated weights for policy 1, policy_version 38430 (0.0008) -[2023-10-09 01:35:50,187][88326] Updated weights for policy 0, policy_version 38402 (0.0007) -[2023-10-09 01:35:50,557][88326] Updated weights for policy 0, policy_version 38412 (0.0009) -[2023-10-09 01:35:50,926][88326] Updated weights for policy 0, policy_version 38422 (0.0009) -[2023-10-09 01:35:51,293][88326] Updated weights for policy 0, policy_version 38432 (0.0008) -[2023-10-09 01:35:53,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 78708736. Throughput: 0: 1668.5, 1: 1692.4. Samples: 19683512. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-09 01:35:53,975][87372] Avg episode reward: [(0, '6.510'), (1, '6.140')] -[2023-10-09 01:35:54,065][88327] Updated weights for policy 1, policy_version 38440 (0.0009) -[2023-10-09 01:35:54,424][88327] Updated weights for policy 1, policy_version 38450 (0.0012) -[2023-10-09 01:35:54,802][88327] Updated weights for policy 1, policy_version 38460 (0.0008) -[2023-10-09 01:35:55,301][88326] Updated weights for policy 0, policy_version 38442 (0.0007) -[2023-10-09 01:35:55,661][88326] Updated weights for policy 0, policy_version 38452 (0.0008) -[2023-10-09 01:35:56,030][88326] Updated weights for policy 0, policy_version 38462 (0.0007) -[2023-10-09 01:35:58,837][88327] Updated weights for policy 1, policy_version 38470 (0.0010) -[2023-10-09 01:35:58,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 78774272. Throughput: 0: 1695.0, 1: 1701.6. Samples: 19704238. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-09 01:35:58,975][87372] Avg episode reward: [(0, '5.810'), (1, '6.630')] -[2023-10-09 01:35:59,205][88327] Updated weights for policy 1, policy_version 38480 (0.0010) -[2023-10-09 01:35:59,574][88327] Updated weights for policy 1, policy_version 38490 (0.0007) -[2023-10-09 01:36:00,000][88326] Updated weights for policy 0, policy_version 38472 (0.0008) -[2023-10-09 01:36:00,365][88326] Updated weights for policy 0, policy_version 38482 (0.0009) -[2023-10-09 01:36:00,745][88326] Updated weights for policy 0, policy_version 38492 (0.0009) -[2023-10-09 01:36:03,432][88327] Updated weights for policy 1, policy_version 38500 (0.0007) -[2023-10-09 01:36:03,794][88327] Updated weights for policy 1, policy_version 38510 (0.0008) -[2023-10-09 01:36:03,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 78839808. Throughput: 0: 1697.5, 1: 1705.4. Samples: 19725418. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-09 01:36:03,975][87372] Avg episode reward: [(0, '6.370'), (1, '5.910')] -[2023-10-09 01:36:04,164][88327] Updated weights for policy 1, policy_version 38520 (0.0010) -[2023-10-09 01:36:04,786][88326] Updated weights for policy 0, policy_version 38502 (0.0009) -[2023-10-09 01:36:05,163][88326] Updated weights for policy 0, policy_version 38512 (0.0008) -[2023-10-09 01:36:05,534][88326] Updated weights for policy 0, policy_version 38522 (0.0009) -[2023-10-09 01:36:08,169][88327] Updated weights for policy 1, policy_version 38530 (0.0008) -[2023-10-09 01:36:08,531][88327] Updated weights for policy 1, policy_version 38540 (0.0008) -[2023-10-09 01:36:08,904][88327] Updated weights for policy 1, policy_version 38550 (0.0008) -[2023-10-09 01:36:08,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 78905344. Throughput: 0: 1667.7, 1: 1700.6. Samples: 19734362. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-09 01:36:08,975][87372] Avg episode reward: [(0, '6.310'), (1, '5.830')] -[2023-10-09 01:36:09,257][88327] Updated weights for policy 1, policy_version 38560 (0.0009) -[2023-10-09 01:36:09,471][88326] Updated weights for policy 0, policy_version 38532 (0.0008) -[2023-10-09 01:36:09,831][88326] Updated weights for policy 0, policy_version 38542 (0.0007) -[2023-10-09 01:36:10,206][88326] Updated weights for policy 0, policy_version 38552 (0.0009) -[2023-10-09 01:36:13,367][88327] Updated weights for policy 1, policy_version 38570 (0.0007) -[2023-10-09 01:36:13,735][88327] Updated weights for policy 1, policy_version 38580 (0.0008) -[2023-10-09 01:36:13,974][87372] Fps is (10 sec: 13106.8, 60 sec: 13107.1, 300 sec: 13440.4). Total num frames: 78970880. Throughput: 0: 1706.3, 1: 1706.8. Samples: 19755688. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-09 01:36:13,976][87372] Avg episode reward: [(0, '6.000'), (1, '6.120')] -[2023-10-09 01:36:14,092][88327] Updated weights for policy 1, policy_version 38590 (0.0009) -[2023-10-09 01:36:14,187][88326] Updated weights for policy 0, policy_version 38562 (0.0009) -[2023-10-09 01:36:14,558][88326] Updated weights for policy 0, policy_version 38572 (0.0007) -[2023-10-09 01:36:14,937][88326] Updated weights for policy 0, policy_version 38582 (0.0008) -[2023-10-09 01:36:15,302][88326] Updated weights for policy 0, policy_version 38592 (0.0008) -[2023-10-09 01:36:18,103][88327] Updated weights for policy 1, policy_version 38600 (0.0009) -[2023-10-09 01:36:18,475][88327] Updated weights for policy 1, policy_version 38610 (0.0007) -[2023-10-09 01:36:18,845][88327] Updated weights for policy 1, policy_version 38620 (0.0010) -[2023-10-09 01:36:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.3, 300 sec: 13440.4). Total num frames: 79036416. Throughput: 0: 1709.6, 1: 1696.9. Samples: 19776298. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-09 01:36:18,974][87372] Avg episode reward: [(0, '6.180'), (1, '5.620')] -[2023-10-09 01:36:19,302][88326] Updated weights for policy 0, policy_version 38602 (0.0009) -[2023-10-09 01:36:19,663][88326] Updated weights for policy 0, policy_version 38612 (0.0008) -[2023-10-09 01:36:20,037][88326] Updated weights for policy 0, policy_version 38622 (0.0010) -[2023-10-09 01:36:22,896][88327] Updated weights for policy 1, policy_version 38630 (0.0009) -[2023-10-09 01:36:23,273][88327] Updated weights for policy 1, policy_version 38640 (0.0007) -[2023-10-09 01:36:23,637][88327] Updated weights for policy 1, policy_version 38650 (0.0007) -[2023-10-09 01:36:23,974][87372] Fps is (10 sec: 16384.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 79134720. Throughput: 0: 1692.6, 1: 1704.4. Samples: 19785798. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-09 01:36:23,975][87372] Avg episode reward: [(0, '6.250'), (1, '5.510')] -[2023-10-09 01:36:24,118][88326] Updated weights for policy 0, policy_version 38632 (0.0007) -[2023-10-09 01:36:24,482][88326] Updated weights for policy 0, policy_version 38642 (0.0008) -[2023-10-09 01:36:24,835][88326] Updated weights for policy 0, policy_version 38652 (0.0009) -[2023-10-09 01:36:27,625][88327] Updated weights for policy 1, policy_version 38660 (0.0008) -[2023-10-09 01:36:27,993][88327] Updated weights for policy 1, policy_version 38670 (0.0010) -[2023-10-09 01:36:28,347][88327] Updated weights for policy 1, policy_version 38680 (0.0010) -[2023-10-09 01:36:28,907][88326] Updated weights for policy 0, policy_version 38662 (0.0009) -[2023-10-09 01:36:28,974][87372] Fps is (10 sec: 16383.7, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 79200256. Throughput: 0: 1708.9, 1: 1708.6. Samples: 19806856. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-09 01:36:28,975][87372] Avg episode reward: [(0, '6.380'), (1, '6.100')] -[2023-10-09 01:36:29,277][88326] Updated weights for policy 0, policy_version 38672 (0.0009) -[2023-10-09 01:36:29,647][88326] Updated weights for policy 0, policy_version 38682 (0.0011) -[2023-10-09 01:36:32,292][88327] Updated weights for policy 1, policy_version 38690 (0.0009) -[2023-10-09 01:36:32,668][88327] Updated weights for policy 1, policy_version 38700 (0.0009) -[2023-10-09 01:36:33,031][88327] Updated weights for policy 1, policy_version 38710 (0.0008) -[2023-10-09 01:36:33,389][88327] Updated weights for policy 1, policy_version 38720 (0.0008) -[2023-10-09 01:36:33,657][88326] Updated weights for policy 0, policy_version 38692 (0.0010) -[2023-10-09 01:36:33,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 79265792. Throughput: 0: 1704.5, 1: 1688.6. Samples: 19826836. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-09 01:36:33,975][87372] Avg episode reward: [(0, '5.880'), (1, '5.970')] -[2023-10-09 01:36:33,983][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000038720_39649280.pth... -[2023-10-09 01:36:34,011][88326] Updated weights for policy 0, policy_version 38702 (0.0009) -[2023-10-09 01:36:34,020][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000037120_38010880.pth -[2023-10-09 01:36:34,384][88326] Updated weights for policy 0, policy_version 38712 (0.0010) -[2023-10-09 01:36:34,680][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000038720_39649280.pth... -[2023-10-09 01:36:34,713][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000037120_38010880.pth -[2023-10-09 01:36:37,306][88327] Updated weights for policy 1, policy_version 38730 (0.0007) -[2023-10-09 01:36:37,673][88327] Updated weights for policy 1, policy_version 38740 (0.0007) -[2023-10-09 01:36:38,036][88327] Updated weights for policy 1, policy_version 38750 (0.0009) -[2023-10-09 01:36:38,244][88326] Updated weights for policy 0, policy_version 38722 (0.0011) -[2023-10-09 01:36:38,613][88326] Updated weights for policy 0, policy_version 38732 (0.0010) -[2023-10-09 01:36:38,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 79331328. Throughput: 0: 1702.3, 1: 1711.6. Samples: 19837136. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-09 01:36:38,975][87372] Avg episode reward: [(0, '6.480'), (1, '6.420')] -[2023-10-09 01:36:38,989][88326] Updated weights for policy 0, policy_version 38742 (0.0011) -[2023-10-09 01:36:39,352][88326] Updated weights for policy 0, policy_version 38752 (0.0009) -[2023-10-09 01:36:42,052][88327] Updated weights for policy 1, policy_version 38760 (0.0008) -[2023-10-09 01:36:42,419][88327] Updated weights for policy 1, policy_version 38770 (0.0007) -[2023-10-09 01:36:42,787][88327] Updated weights for policy 1, policy_version 38780 (0.0009) -[2023-10-09 01:36:43,367][88326] Updated weights for policy 0, policy_version 38762 (0.0007) -[2023-10-09 01:36:43,735][88326] Updated weights for policy 0, policy_version 38772 (0.0007) -[2023-10-09 01:36:43,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 79396864. Throughput: 0: 1703.9, 1: 1707.1. Samples: 19857730. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-09 01:36:43,975][87372] Avg episode reward: [(0, '6.640'), (1, '6.600')] -[2023-10-09 01:36:44,100][88326] Updated weights for policy 0, policy_version 38782 (0.0010) -[2023-10-09 01:36:46,835][88327] Updated weights for policy 1, policy_version 38790 (0.0008) -[2023-10-09 01:36:47,193][88327] Updated weights for policy 1, policy_version 38800 (0.0009) -[2023-10-09 01:36:47,556][88327] Updated weights for policy 1, policy_version 38810 (0.0008) -[2023-10-09 01:36:48,350][88326] Updated weights for policy 0, policy_version 38792 (0.0009) -[2023-10-09 01:36:48,721][88326] Updated weights for policy 0, policy_version 38802 (0.0009) -[2023-10-09 01:36:48,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 79462400. Throughput: 0: 1699.6, 1: 1683.8. Samples: 19877670. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-09 01:36:48,975][87372] Avg episode reward: [(0, '5.950'), (1, '6.470')] -[2023-10-09 01:36:49,094][88326] Updated weights for policy 0, policy_version 38812 (0.0010) -[2023-10-09 01:36:51,515][88327] Updated weights for policy 1, policy_version 38820 (0.0008) -[2023-10-09 01:36:51,881][88327] Updated weights for policy 1, policy_version 38830 (0.0008) -[2023-10-09 01:36:52,253][88327] Updated weights for policy 1, policy_version 38840 (0.0010) -[2023-10-09 01:36:53,152][88326] Updated weights for policy 0, policy_version 38822 (0.0009) -[2023-10-09 01:36:53,546][88326] Updated weights for policy 0, policy_version 38832 (0.0008) -[2023-10-09 01:36:53,916][88326] Updated weights for policy 0, policy_version 38842 (0.0009) -[2023-10-09 01:36:53,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 79527936. Throughput: 0: 1706.4, 1: 1714.4. Samples: 19888298. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-09 01:36:53,975][87372] Avg episode reward: [(0, '6.300'), (1, '6.360')] -[2023-10-09 01:36:56,265][88327] Updated weights for policy 1, policy_version 38850 (0.0008) -[2023-10-09 01:36:56,633][88327] Updated weights for policy 1, policy_version 38860 (0.0009) -[2023-10-09 01:36:56,988][88327] Updated weights for policy 1, policy_version 38870 (0.0008) -[2023-10-09 01:36:57,353][88327] Updated weights for policy 1, policy_version 38880 (0.0007) -[2023-10-09 01:36:57,965][88326] Updated weights for policy 0, policy_version 38852 (0.0009) -[2023-10-09 01:36:58,335][88326] Updated weights for policy 0, policy_version 38862 (0.0007) -[2023-10-09 01:36:58,698][88326] Updated weights for policy 0, policy_version 38872 (0.0007) -[2023-10-09 01:36:58,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 79593472. Throughput: 0: 1701.5, 1: 1695.0. Samples: 19908530. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-09 01:36:58,975][87372] Avg episode reward: [(0, '5.970'), (1, '5.970')] -[2023-10-09 01:37:01,465][88327] Updated weights for policy 1, policy_version 38890 (0.0007) -[2023-10-09 01:37:01,834][88327] Updated weights for policy 1, policy_version 38900 (0.0007) -[2023-10-09 01:37:02,202][88327] Updated weights for policy 1, policy_version 38910 (0.0009) -[2023-10-09 01:37:02,757][88326] Updated weights for policy 0, policy_version 38882 (0.0008) -[2023-10-09 01:37:03,133][88326] Updated weights for policy 0, policy_version 38892 (0.0007) -[2023-10-09 01:37:03,490][88326] Updated weights for policy 0, policy_version 38902 (0.0008) -[2023-10-09 01:37:03,853][88326] Updated weights for policy 0, policy_version 38912 (0.0009) -[2023-10-09 01:37:03,974][87372] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 79691776. Throughput: 0: 1690.9, 1: 1693.4. Samples: 19928592. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-09 01:37:03,975][87372] Avg episode reward: [(0, '5.700'), (1, '6.200')] -[2023-10-09 01:37:06,139][88327] Updated weights for policy 1, policy_version 38920 (0.0008) -[2023-10-09 01:37:06,507][88327] Updated weights for policy 1, policy_version 38930 (0.0009) -[2023-10-09 01:37:06,877][88327] Updated weights for policy 1, policy_version 38940 (0.0009) -[2023-10-09 01:37:07,813][88326] Updated weights for policy 0, policy_version 38922 (0.0008) -[2023-10-09 01:37:08,190][88326] Updated weights for policy 0, policy_version 38932 (0.0008) -[2023-10-09 01:37:08,553][88326] Updated weights for policy 0, policy_version 38942 (0.0007) -[2023-10-09 01:37:08,974][87372] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 79757312. Throughput: 0: 1701.3, 1: 1708.1. Samples: 19939218. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-09 01:37:08,974][87372] Avg episode reward: [(0, '6.360'), (1, '6.250')] -[2023-10-09 01:37:10,919][88327] Updated weights for policy 1, policy_version 38950 (0.0008) -[2023-10-09 01:37:11,287][88327] Updated weights for policy 1, policy_version 38960 (0.0007) -[2023-10-09 01:37:11,653][88327] Updated weights for policy 1, policy_version 38970 (0.0007) -[2023-10-09 01:37:12,519][88326] Updated weights for policy 0, policy_version 38952 (0.0008) -[2023-10-09 01:37:12,876][88326] Updated weights for policy 0, policy_version 38962 (0.0008) -[2023-10-09 01:37:13,250][88326] Updated weights for policy 0, policy_version 38972 (0.0008) -[2023-10-09 01:37:13,974][87372] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 79822848. Throughput: 0: 1703.7, 1: 1682.7. Samples: 19959244. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-09 01:37:13,975][87372] Avg episode reward: [(0, '5.930'), (1, '6.120')] -[2023-10-09 01:37:15,580][88327] Updated weights for policy 1, policy_version 38980 (0.0009) -[2023-10-09 01:37:15,947][88327] Updated weights for policy 1, policy_version 38990 (0.0008) -[2023-10-09 01:37:16,303][88327] Updated weights for policy 1, policy_version 39000 (0.0007) -[2023-10-09 01:37:17,201][88326] Updated weights for policy 0, policy_version 38982 (0.0007) -[2023-10-09 01:37:17,562][88326] Updated weights for policy 0, policy_version 38992 (0.0009) -[2023-10-09 01:37:17,926][88326] Updated weights for policy 0, policy_version 39002 (0.0008) -[2023-10-09 01:37:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 79888384. Throughput: 0: 1677.5, 1: 1709.2. Samples: 19979238. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:37:18,975][87372] Avg episode reward: [(0, '5.350'), (1, '6.410')] -[2023-10-09 01:37:20,308][88327] Updated weights for policy 1, policy_version 39010 (0.0008) -[2023-10-09 01:37:20,666][88327] Updated weights for policy 1, policy_version 39020 (0.0008) -[2023-10-09 01:37:21,036][88327] Updated weights for policy 1, policy_version 39030 (0.0007) -[2023-10-09 01:37:21,390][88327] Updated weights for policy 1, policy_version 39040 (0.0008) -[2023-10-09 01:37:21,726][88326] Updated weights for policy 0, policy_version 39012 (0.0008) -[2023-10-09 01:37:22,104][88326] Updated weights for policy 0, policy_version 39022 (0.0007) -[2023-10-09 01:37:22,479][88326] Updated weights for policy 0, policy_version 39032 (0.0008) -[2023-10-09 01:37:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 79953920. Throughput: 0: 1706.2, 1: 1693.5. Samples: 19990124. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:37:23,975][87372] Avg episode reward: [(0, '6.110'), (1, '6.040')] -[2023-10-09 01:37:25,506][88327] Updated weights for policy 1, policy_version 39050 (0.0009) -[2023-10-09 01:37:25,872][88327] Updated weights for policy 1, policy_version 39060 (0.0009) -[2023-10-09 01:37:26,249][88327] Updated weights for policy 1, policy_version 39070 (0.0009) -[2023-10-09 01:37:26,378][88326] Updated weights for policy 0, policy_version 39042 (0.0010) -[2023-10-09 01:37:26,756][88326] Updated weights for policy 0, policy_version 39052 (0.0009) -[2023-10-09 01:37:27,116][88326] Updated weights for policy 0, policy_version 39062 (0.0008) -[2023-10-09 01:37:27,479][88326] Updated weights for policy 0, policy_version 39072 (0.0008) -[2023-10-09 01:37:28,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 80019456. Throughput: 0: 1689.7, 1: 1693.5. Samples: 20009972. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:37:28,975][87372] Avg episode reward: [(0, '6.180'), (1, '6.090')] -[2023-10-09 01:37:30,263][88327] Updated weights for policy 1, policy_version 39080 (0.0009) -[2023-10-09 01:37:30,627][88327] Updated weights for policy 1, policy_version 39090 (0.0007) -[2023-10-09 01:37:30,991][88327] Updated weights for policy 1, policy_version 39100 (0.0010) -[2023-10-09 01:37:31,590][88326] Updated weights for policy 0, policy_version 39082 (0.0009) -[2023-10-09 01:37:31,958][88326] Updated weights for policy 0, policy_version 39092 (0.0007) -[2023-10-09 01:37:32,319][88326] Updated weights for policy 0, policy_version 39102 (0.0008) -[2023-10-09 01:37:33,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 80084992. Throughput: 0: 1688.6, 1: 1708.9. Samples: 20030556. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:37:33,975][87372] Avg episode reward: [(0, '5.720'), (1, '5.730')] -[2023-10-09 01:37:34,981][88327] Updated weights for policy 1, policy_version 39110 (0.0008) -[2023-10-09 01:37:35,350][88327] Updated weights for policy 1, policy_version 39120 (0.0010) -[2023-10-09 01:37:35,715][88327] Updated weights for policy 1, policy_version 39130 (0.0008) -[2023-10-09 01:37:36,549][88326] Updated weights for policy 0, policy_version 39112 (0.0007) -[2023-10-09 01:37:36,924][88326] Updated weights for policy 0, policy_version 39122 (0.0007) -[2023-10-09 01:37:37,288][88326] Updated weights for policy 0, policy_version 39132 (0.0010) -[2023-10-09 01:37:38,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 80150528. Throughput: 0: 1711.7, 1: 1679.9. Samples: 20040920. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:37:38,975][87372] Avg episode reward: [(0, '6.050'), (1, '6.300')] -[2023-10-09 01:37:39,743][88327] Updated weights for policy 1, policy_version 39140 (0.0010) -[2023-10-09 01:37:40,115][88327] Updated weights for policy 1, policy_version 39150 (0.0008) -[2023-10-09 01:37:40,474][88327] Updated weights for policy 1, policy_version 39160 (0.0009) -[2023-10-09 01:37:41,318][88326] Updated weights for policy 0, policy_version 39142 (0.0007) -[2023-10-09 01:37:41,686][88326] Updated weights for policy 0, policy_version 39152 (0.0009) -[2023-10-09 01:37:42,055][88326] Updated weights for policy 0, policy_version 39162 (0.0010) -[2023-10-09 01:37:43,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 80216064. Throughput: 0: 1686.8, 1: 1700.9. Samples: 20060980. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:37:43,975][87372] Avg episode reward: [(0, '5.800'), (1, '5.790')] -[2023-10-09 01:37:44,587][88327] Updated weights for policy 1, policy_version 39170 (0.0011) -[2023-10-09 01:37:44,949][88327] Updated weights for policy 1, policy_version 39180 (0.0008) -[2023-10-09 01:37:45,317][88327] Updated weights for policy 1, policy_version 39190 (0.0007) -[2023-10-09 01:37:45,677][88327] Updated weights for policy 1, policy_version 39200 (0.0009) -[2023-10-09 01:37:46,054][88326] Updated weights for policy 0, policy_version 39172 (0.0008) -[2023-10-09 01:37:46,434][88326] Updated weights for policy 0, policy_version 39182 (0.0009) -[2023-10-09 01:37:46,808][88326] Updated weights for policy 0, policy_version 39192 (0.0010) -[2023-10-09 01:37:48,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 80281600. Throughput: 0: 1692.2, 1: 1708.9. Samples: 20081642. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:37:48,974][87372] Avg episode reward: [(0, '5.550'), (1, '5.910')] -[2023-10-09 01:37:49,942][88327] Updated weights for policy 1, policy_version 39210 (0.0010) -[2023-10-09 01:37:50,310][88327] Updated weights for policy 1, policy_version 39220 (0.0010) -[2023-10-09 01:37:50,507][88326] Updated weights for policy 0, policy_version 39202 (0.0007) -[2023-10-09 01:37:50,671][88327] Updated weights for policy 1, policy_version 39230 (0.0008) -[2023-10-09 01:37:50,881][88326] Updated weights for policy 0, policy_version 39212 (0.0008) -[2023-10-09 01:37:51,240][88326] Updated weights for policy 0, policy_version 39222 (0.0008) -[2023-10-09 01:37:51,611][88326] Updated weights for policy 0, policy_version 39232 (0.0007) -[2023-10-09 01:37:53,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 80347136. Throughput: 0: 1694.3, 1: 1681.6. Samples: 20091134. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:37:53,974][87372] Avg episode reward: [(0, '5.860'), (1, '6.140')] -[2023-10-09 01:37:54,492][88327] Updated weights for policy 1, policy_version 39240 (0.0009) -[2023-10-09 01:37:54,862][88327] Updated weights for policy 1, policy_version 39250 (0.0007) -[2023-10-09 01:37:55,218][88327] Updated weights for policy 1, policy_version 39260 (0.0010) -[2023-10-09 01:37:55,683][88326] Updated weights for policy 0, policy_version 39242 (0.0010) -[2023-10-09 01:37:56,057][88326] Updated weights for policy 0, policy_version 39252 (0.0009) -[2023-10-09 01:37:56,415][88326] Updated weights for policy 0, policy_version 39262 (0.0007) -[2023-10-09 01:37:58,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 80412672. Throughput: 0: 1683.2, 1: 1709.0. Samples: 20111892. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:37:58,974][87372] Avg episode reward: [(0, '6.210'), (1, '5.790')] -[2023-10-09 01:37:59,244][88327] Updated weights for policy 1, policy_version 39270 (0.0010) -[2023-10-09 01:37:59,602][88327] Updated weights for policy 1, policy_version 39280 (0.0009) -[2023-10-09 01:37:59,963][88327] Updated weights for policy 1, policy_version 39290 (0.0010) -[2023-10-09 01:38:00,339][88326] Updated weights for policy 0, policy_version 39272 (0.0010) -[2023-10-09 01:38:00,715][88326] Updated weights for policy 0, policy_version 39282 (0.0008) -[2023-10-09 01:38:01,087][88326] Updated weights for policy 0, policy_version 39292 (0.0010) -[2023-10-09 01:38:03,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 80478208. Throughput: 0: 1711.8, 1: 1701.9. Samples: 20132854. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:38:03,975][87372] Avg episode reward: [(0, '5.490'), (1, '5.950')] -[2023-10-09 01:38:04,149][88327] Updated weights for policy 1, policy_version 39300 (0.0009) -[2023-10-09 01:38:04,512][88327] Updated weights for policy 1, policy_version 39310 (0.0008) -[2023-10-09 01:38:04,875][88327] Updated weights for policy 1, policy_version 39320 (0.0008) -[2023-10-09 01:38:05,125][88326] Updated weights for policy 0, policy_version 39302 (0.0008) -[2023-10-09 01:38:05,488][88326] Updated weights for policy 0, policy_version 39312 (0.0009) -[2023-10-09 01:38:05,863][88326] Updated weights for policy 0, policy_version 39322 (0.0008) -[2023-10-09 01:38:08,957][88327] Updated weights for policy 1, policy_version 39330 (0.0008) -[2023-10-09 01:38:08,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 80543744. Throughput: 0: 1681.7, 1: 1695.0. Samples: 20142074. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:38:08,975][87372] Avg episode reward: [(0, '5.980'), (1, '5.900')] -[2023-10-09 01:38:09,325][88327] Updated weights for policy 1, policy_version 39340 (0.0008) -[2023-10-09 01:38:09,694][88327] Updated weights for policy 1, policy_version 39350 (0.0007) -[2023-10-09 01:38:09,944][88326] Updated weights for policy 0, policy_version 39332 (0.0007) -[2023-10-09 01:38:10,059][88327] Updated weights for policy 1, policy_version 39360 (0.0007) -[2023-10-09 01:38:10,311][88326] Updated weights for policy 0, policy_version 39342 (0.0008) -[2023-10-09 01:38:10,676][88326] Updated weights for policy 0, policy_version 39352 (0.0007) -[2023-10-09 01:38:13,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 80609280. Throughput: 0: 1693.6, 1: 1696.4. Samples: 20162522. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:38:13,975][87372] Avg episode reward: [(0, '6.290'), (1, '5.920')] -[2023-10-09 01:38:14,179][88327] Updated weights for policy 1, policy_version 39370 (0.0007) -[2023-10-09 01:38:14,538][88327] Updated weights for policy 1, policy_version 39380 (0.0009) -[2023-10-09 01:38:14,616][88326] Updated weights for policy 0, policy_version 39362 (0.0009) -[2023-10-09 01:38:14,902][88327] Updated weights for policy 1, policy_version 39390 (0.0009) -[2023-10-09 01:38:14,990][88326] Updated weights for policy 0, policy_version 39372 (0.0007) -[2023-10-09 01:38:15,365][88326] Updated weights for policy 0, policy_version 39382 (0.0009) -[2023-10-09 01:38:15,725][88326] Updated weights for policy 0, policy_version 39392 (0.0008) -[2023-10-09 01:38:18,915][88327] Updated weights for policy 1, policy_version 39400 (0.0007) -[2023-10-09 01:38:18,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 80674816. Throughput: 0: 1701.3, 1: 1700.3. Samples: 20183628. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-09 01:38:18,975][87372] Avg episode reward: [(0, '5.830'), (1, '5.760')] -[2023-10-09 01:38:19,278][88327] Updated weights for policy 1, policy_version 39410 (0.0008) -[2023-10-09 01:38:19,648][88327] Updated weights for policy 1, policy_version 39420 (0.0009) -[2023-10-09 01:38:19,754][88326] Updated weights for policy 0, policy_version 39402 (0.0008) -[2023-10-09 01:38:20,131][88326] Updated weights for policy 0, policy_version 39412 (0.0007) -[2023-10-09 01:38:20,500][88326] Updated weights for policy 0, policy_version 39422 (0.0010) -[2023-10-09 01:38:23,750][88327] Updated weights for policy 1, policy_version 39430 (0.0008) -[2023-10-09 01:38:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 80740352. Throughput: 0: 1675.7, 1: 1696.0. Samples: 20192646. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-09 01:38:23,975][87372] Avg episode reward: [(0, '6.130'), (1, '5.940')] -[2023-10-09 01:38:24,113][88327] Updated weights for policy 1, policy_version 39440 (0.0011) -[2023-10-09 01:38:24,478][88327] Updated weights for policy 1, policy_version 39450 (0.0008) -[2023-10-09 01:38:24,604][88326] Updated weights for policy 0, policy_version 39432 (0.0008) -[2023-10-09 01:38:24,974][88326] Updated weights for policy 0, policy_version 39442 (0.0009) -[2023-10-09 01:38:25,343][88326] Updated weights for policy 0, policy_version 39452 (0.0011) -[2023-10-09 01:38:28,518][88327] Updated weights for policy 1, policy_version 39460 (0.0007) -[2023-10-09 01:38:28,871][88327] Updated weights for policy 1, policy_version 39470 (0.0008) -[2023-10-09 01:38:28,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 80805888. Throughput: 0: 1697.8, 1: 1688.5. Samples: 20213362. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-09 01:38:28,975][87372] Avg episode reward: [(0, '6.190'), (1, '6.400')] -[2023-10-09 01:38:29,235][88327] Updated weights for policy 1, policy_version 39480 (0.0010) -[2023-10-09 01:38:29,404][88326] Updated weights for policy 0, policy_version 39462 (0.0009) -[2023-10-09 01:38:29,768][88326] Updated weights for policy 0, policy_version 39472 (0.0007) -[2023-10-09 01:38:30,148][88326] Updated weights for policy 0, policy_version 39482 (0.0007) -[2023-10-09 01:38:33,345][88327] Updated weights for policy 1, policy_version 39490 (0.0009) -[2023-10-09 01:38:33,715][88327] Updated weights for policy 1, policy_version 39500 (0.0011) -[2023-10-09 01:38:33,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 80871424. Throughput: 0: 1701.6, 1: 1687.5. Samples: 20234154. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-09 01:38:33,975][87372] Avg episode reward: [(0, '5.870'), (1, '5.970')] -[2023-10-09 01:38:33,983][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000039488_40435712.pth... -[2023-10-09 01:38:34,016][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000037920_38830080.pth -[2023-10-09 01:38:34,021][88088] Saving a milestone ./train_atari/atari_battlezone_APPO/checkpoint_p0/milestones/checkpoint_000039488_40435712.pth -[2023-10-09 01:38:34,074][88327] Updated weights for policy 1, policy_version 39510 (0.0009) -[2023-10-09 01:38:34,379][88326] Updated weights for policy 0, policy_version 39492 (0.0008) -[2023-10-09 01:38:34,430][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000039520_40468480.pth... -[2023-10-09 01:38:34,431][88327] Updated weights for policy 1, policy_version 39520 (0.0008) -[2023-10-09 01:38:34,459][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000037920_38830080.pth -[2023-10-09 01:38:34,463][88168] Saving a milestone ./train_atari/atari_battlezone_APPO/checkpoint_p1/milestones/checkpoint_000039520_40468480.pth -[2023-10-09 01:38:34,771][88326] Updated weights for policy 0, policy_version 39502 (0.0009) -[2023-10-09 01:38:35,147][88326] Updated weights for policy 0, policy_version 39512 (0.0007) -[2023-10-09 01:38:38,673][88327] Updated weights for policy 1, policy_version 39530 (0.0009) -[2023-10-09 01:38:38,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 80936960. Throughput: 0: 1686.8, 1: 1693.1. Samples: 20243228. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-09 01:38:38,975][87372] Avg episode reward: [(0, '5.940'), (1, '6.230')] -[2023-10-09 01:38:39,046][88327] Updated weights for policy 1, policy_version 39540 (0.0008) -[2023-10-09 01:38:39,106][88326] Updated weights for policy 0, policy_version 39522 (0.0007) -[2023-10-09 01:38:39,413][88327] Updated weights for policy 1, policy_version 39550 (0.0007) -[2023-10-09 01:38:39,462][88326] Updated weights for policy 0, policy_version 39532 (0.0008) -[2023-10-09 01:38:39,831][88326] Updated weights for policy 0, policy_version 39542 (0.0007) -[2023-10-09 01:38:40,206][88326] Updated weights for policy 0, policy_version 39552 (0.0007) -[2023-10-09 01:38:43,184][88327] Updated weights for policy 1, policy_version 39560 (0.0007) -[2023-10-09 01:38:43,555][88327] Updated weights for policy 1, policy_version 39570 (0.0007) -[2023-10-09 01:38:43,917][88327] Updated weights for policy 1, policy_version 39580 (0.0010) -[2023-10-09 01:38:43,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 81002496. Throughput: 0: 1694.4, 1: 1688.0. Samples: 20264098. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-09 01:38:43,975][87372] Avg episode reward: [(0, '6.030'), (1, '6.220')] -[2023-10-09 01:38:44,448][88326] Updated weights for policy 0, policy_version 39562 (0.0009) -[2023-10-09 01:38:44,817][88326] Updated weights for policy 0, policy_version 39572 (0.0008) -[2023-10-09 01:38:45,188][88326] Updated weights for policy 0, policy_version 39582 (0.0009) -[2023-10-09 01:38:47,899][88327] Updated weights for policy 1, policy_version 39590 (0.0009) -[2023-10-09 01:38:48,270][88327] Updated weights for policy 1, policy_version 39600 (0.0009) -[2023-10-09 01:38:48,646][88327] Updated weights for policy 1, policy_version 39610 (0.0010) -[2023-10-09 01:38:48,974][87372] Fps is (10 sec: 16384.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 81100800. Throughput: 0: 1683.6, 1: 1683.4. Samples: 20284366. Policy #0 lag: (min: 31.0, avg: 34.2, max: 63.0) -[2023-10-09 01:38:48,974][87372] Avg episode reward: [(0, '5.750'), (1, '5.910')] -[2023-10-09 01:38:49,302][88326] Updated weights for policy 0, policy_version 39592 (0.0008) -[2023-10-09 01:38:49,683][88326] Updated weights for policy 0, policy_version 39602 (0.0009) -[2023-10-09 01:38:50,052][88326] Updated weights for policy 0, policy_version 39612 (0.0009) -[2023-10-09 01:38:52,607][88327] Updated weights for policy 1, policy_version 39620 (0.0007) -[2023-10-09 01:38:52,967][88327] Updated weights for policy 1, policy_version 39630 (0.0007) -[2023-10-09 01:38:53,337][88327] Updated weights for policy 1, policy_version 39640 (0.0007) -[2023-10-09 01:38:53,974][87372] Fps is (10 sec: 16384.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 81166336. Throughput: 0: 1684.4, 1: 1691.5. Samples: 20293990. Policy #0 lag: (min: 31.0, avg: 34.2, max: 63.0) -[2023-10-09 01:38:53,975][87372] Avg episode reward: [(0, '5.950'), (1, '5.840')] -[2023-10-09 01:38:53,987][88326] Updated weights for policy 0, policy_version 39622 (0.0010) -[2023-10-09 01:38:54,357][88326] Updated weights for policy 0, policy_version 39632 (0.0007) -[2023-10-09 01:38:54,734][88326] Updated weights for policy 0, policy_version 39642 (0.0010) -[2023-10-09 01:38:57,336][88327] Updated weights for policy 1, policy_version 39650 (0.0008) -[2023-10-09 01:38:57,712][88327] Updated weights for policy 1, policy_version 39660 (0.0009) -[2023-10-09 01:38:58,090][88327] Updated weights for policy 1, policy_version 39670 (0.0008) -[2023-10-09 01:38:58,455][88327] Updated weights for policy 1, policy_version 39680 (0.0011) -[2023-10-09 01:38:58,841][88326] Updated weights for policy 0, policy_version 39652 (0.0007) -[2023-10-09 01:38:58,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 81231872. Throughput: 0: 1691.7, 1: 1696.8. Samples: 20315008. Policy #0 lag: (min: 31.0, avg: 34.2, max: 63.0) -[2023-10-09 01:38:58,975][87372] Avg episode reward: [(0, '6.090'), (1, '6.190')] -[2023-10-09 01:38:59,211][88326] Updated weights for policy 0, policy_version 39662 (0.0008) -[2023-10-09 01:38:59,584][88326] Updated weights for policy 0, policy_version 39672 (0.0010) -[2023-10-09 01:39:02,546][88327] Updated weights for policy 1, policy_version 39690 (0.0008) -[2023-10-09 01:39:02,916][88327] Updated weights for policy 1, policy_version 39700 (0.0009) -[2023-10-09 01:39:03,288][88327] Updated weights for policy 1, policy_version 39710 (0.0008) -[2023-10-09 01:39:03,753][88326] Updated weights for policy 0, policy_version 39682 (0.0010) -[2023-10-09 01:39:03,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 81297408. Throughput: 0: 1689.6, 1: 1670.1. Samples: 20334818. Policy #0 lag: (min: 31.0, avg: 34.2, max: 63.0) -[2023-10-09 01:39:03,975][87372] Avg episode reward: [(0, '6.220'), (1, '5.720')] -[2023-10-09 01:39:04,129][88326] Updated weights for policy 0, policy_version 39692 (0.0009) -[2023-10-09 01:39:04,496][88326] Updated weights for policy 0, policy_version 39702 (0.0007) -[2023-10-09 01:39:04,862][88326] Updated weights for policy 0, policy_version 39712 (0.0011) -[2023-10-09 01:39:07,415][88327] Updated weights for policy 1, policy_version 39720 (0.0009) -[2023-10-09 01:39:07,784][88327] Updated weights for policy 1, policy_version 39730 (0.0007) -[2023-10-09 01:39:08,145][88327] Updated weights for policy 1, policy_version 39740 (0.0009) -[2023-10-09 01:39:08,915][88326] Updated weights for policy 0, policy_version 39722 (0.0007) -[2023-10-09 01:39:08,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 81362944. Throughput: 0: 1689.0, 1: 1694.2. Samples: 20344892. Policy #0 lag: (min: 31.0, avg: 34.2, max: 63.0) -[2023-10-09 01:39:08,975][87372] Avg episode reward: [(0, '6.510'), (1, '5.900')] -[2023-10-09 01:39:09,283][88326] Updated weights for policy 0, policy_version 39732 (0.0009) -[2023-10-09 01:39:09,662][88326] Updated weights for policy 0, policy_version 39742 (0.0009) -[2023-10-09 01:39:12,253][88327] Updated weights for policy 1, policy_version 39750 (0.0008) -[2023-10-09 01:39:12,612][88327] Updated weights for policy 1, policy_version 39760 (0.0008) -[2023-10-09 01:39:12,983][88327] Updated weights for policy 1, policy_version 39770 (0.0008) -[2023-10-09 01:39:13,570][88326] Updated weights for policy 0, policy_version 39752 (0.0009) -[2023-10-09 01:39:13,933][88326] Updated weights for policy 0, policy_version 39762 (0.0009) -[2023-10-09 01:39:13,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 81428480. Throughput: 0: 1694.1, 1: 1693.6. Samples: 20365808. Policy #0 lag: (min: 31.0, avg: 34.2, max: 63.0) -[2023-10-09 01:39:13,974][87372] Avg episode reward: [(0, '5.990'), (1, '6.130')] -[2023-10-09 01:39:14,306][88326] Updated weights for policy 0, policy_version 39772 (0.0009) -[2023-10-09 01:39:16,874][88327] Updated weights for policy 1, policy_version 39780 (0.0009) -[2023-10-09 01:39:17,233][88327] Updated weights for policy 1, policy_version 39790 (0.0007) -[2023-10-09 01:39:17,603][88327] Updated weights for policy 1, policy_version 39800 (0.0008) -[2023-10-09 01:39:18,461][88326] Updated weights for policy 0, policy_version 39782 (0.0007) -[2023-10-09 01:39:18,832][88326] Updated weights for policy 0, policy_version 39792 (0.0009) -[2023-10-09 01:39:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 81494016. Throughput: 0: 1693.9, 1: 1671.1. Samples: 20385580. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:39:18,975][87372] Avg episode reward: [(0, '6.350'), (1, '5.620')] -[2023-10-09 01:39:19,199][88326] Updated weights for policy 0, policy_version 39802 (0.0011) -[2023-10-09 01:39:21,553][88327] Updated weights for policy 1, policy_version 39810 (0.0009) -[2023-10-09 01:39:21,912][88327] Updated weights for policy 1, policy_version 39820 (0.0011) -[2023-10-09 01:39:22,281][88327] Updated weights for policy 1, policy_version 39830 (0.0011) -[2023-10-09 01:39:22,649][88327] Updated weights for policy 1, policy_version 39840 (0.0010) -[2023-10-09 01:39:23,084][88326] Updated weights for policy 0, policy_version 39812 (0.0009) -[2023-10-09 01:39:23,455][88326] Updated weights for policy 0, policy_version 39822 (0.0007) -[2023-10-09 01:39:23,829][88326] Updated weights for policy 0, policy_version 39832 (0.0009) -[2023-10-09 01:39:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 81559552. Throughput: 0: 1697.9, 1: 1705.5. Samples: 20396378. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:39:23,974][87372] Avg episode reward: [(0, '6.370'), (1, '5.550')] -[2023-10-09 01:39:26,707][88327] Updated weights for policy 1, policy_version 39850 (0.0008) -[2023-10-09 01:39:27,084][88327] Updated weights for policy 1, policy_version 39860 (0.0009) -[2023-10-09 01:39:27,445][88327] Updated weights for policy 1, policy_version 39870 (0.0008) -[2023-10-09 01:39:27,704][88326] Updated weights for policy 0, policy_version 39842 (0.0008) -[2023-10-09 01:39:28,072][88326] Updated weights for policy 0, policy_version 39852 (0.0010) -[2023-10-09 01:39:28,447][88326] Updated weights for policy 0, policy_version 39862 (0.0008) -[2023-10-09 01:39:28,807][88326] Updated weights for policy 0, policy_version 39872 (0.0009) -[2023-10-09 01:39:28,974][87372] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 81657856. Throughput: 0: 1703.0, 1: 1682.3. Samples: 20416438. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:39:28,975][87372] Avg episode reward: [(0, '6.010'), (1, '5.940')] -[2023-10-09 01:39:31,544][88327] Updated weights for policy 1, policy_version 39880 (0.0009) -[2023-10-09 01:39:31,914][88327] Updated weights for policy 1, policy_version 39890 (0.0010) -[2023-10-09 01:39:32,276][88327] Updated weights for policy 1, policy_version 39900 (0.0011) -[2023-10-09 01:39:32,841][88326] Updated weights for policy 0, policy_version 39882 (0.0008) -[2023-10-09 01:39:33,208][88326] Updated weights for policy 0, policy_version 39892 (0.0007) -[2023-10-09 01:39:33,582][88326] Updated weights for policy 0, policy_version 39902 (0.0008) -[2023-10-09 01:39:33,974][87372] Fps is (10 sec: 16383.5, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 81723392. Throughput: 0: 1693.7, 1: 1674.4. Samples: 20435932. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:39:33,975][87372] Avg episode reward: [(0, '6.210'), (1, '5.990')] -[2023-10-09 01:39:36,214][88327] Updated weights for policy 1, policy_version 39910 (0.0007) -[2023-10-09 01:39:36,570][88327] Updated weights for policy 1, policy_version 39920 (0.0008) -[2023-10-09 01:39:36,942][88327] Updated weights for policy 1, policy_version 39930 (0.0010) -[2023-10-09 01:39:37,699][88326] Updated weights for policy 0, policy_version 39912 (0.0009) -[2023-10-09 01:39:38,062][88326] Updated weights for policy 0, policy_version 39922 (0.0008) -[2023-10-09 01:39:38,442][88326] Updated weights for policy 0, policy_version 39932 (0.0008) -[2023-10-09 01:39:38,974][87372] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 81788928. Throughput: 0: 1708.5, 1: 1687.4. Samples: 20446806. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:39:38,975][87372] Avg episode reward: [(0, '6.530'), (1, '5.920')] -[2023-10-09 01:39:41,091][88327] Updated weights for policy 1, policy_version 39940 (0.0010) -[2023-10-09 01:39:41,449][88327] Updated weights for policy 1, policy_version 39950 (0.0008) -[2023-10-09 01:39:41,816][88327] Updated weights for policy 1, policy_version 39960 (0.0008) -[2023-10-09 01:39:42,550][88326] Updated weights for policy 0, policy_version 39942 (0.0010) -[2023-10-09 01:39:42,922][88326] Updated weights for policy 0, policy_version 39952 (0.0010) -[2023-10-09 01:39:43,282][88326] Updated weights for policy 0, policy_version 39962 (0.0009) -[2023-10-09 01:39:43,974][87372] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 81854464. Throughput: 0: 1700.9, 1: 1664.4. Samples: 20466446. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-09 01:39:43,975][87372] Avg episode reward: [(0, '6.100'), (1, '5.890')] -[2023-10-09 01:39:45,852][88327] Updated weights for policy 1, policy_version 39970 (0.0008) -[2023-10-09 01:39:46,223][88327] Updated weights for policy 1, policy_version 39980 (0.0010) -[2023-10-09 01:39:46,592][88327] Updated weights for policy 1, policy_version 39990 (0.0008) -[2023-10-09 01:39:46,951][88327] Updated weights for policy 1, policy_version 40000 (0.0007) -[2023-10-09 01:39:47,239][88326] Updated weights for policy 0, policy_version 39972 (0.0007) -[2023-10-09 01:39:47,608][88326] Updated weights for policy 0, policy_version 39982 (0.0007) -[2023-10-09 01:39:47,968][88326] Updated weights for policy 0, policy_version 39992 (0.0009) -[2023-10-09 01:39:48,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 81920000. Throughput: 0: 1672.7, 1: 1689.6. Samples: 20486122. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-09 01:39:48,975][87372] Avg episode reward: [(0, '6.310'), (1, '5.990')] -[2023-10-09 01:39:51,006][88327] Updated weights for policy 1, policy_version 40010 (0.0010) -[2023-10-09 01:39:51,366][88327] Updated weights for policy 1, policy_version 40020 (0.0009) -[2023-10-09 01:39:51,731][88327] Updated weights for policy 1, policy_version 40030 (0.0010) -[2023-10-09 01:39:51,976][88326] Updated weights for policy 0, policy_version 40002 (0.0008) -[2023-10-09 01:39:52,351][88326] Updated weights for policy 0, policy_version 40012 (0.0009) -[2023-10-09 01:39:52,720][88326] Updated weights for policy 0, policy_version 40022 (0.0007) -[2023-10-09 01:39:53,081][88326] Updated weights for policy 0, policy_version 40032 (0.0007) -[2023-10-09 01:39:53,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 81985536. Throughput: 0: 1701.2, 1: 1686.3. Samples: 20497334. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-09 01:39:53,975][87372] Avg episode reward: [(0, '6.150'), (1, '5.990')] -[2023-10-09 01:39:55,845][88327] Updated weights for policy 1, policy_version 40040 (0.0007) -[2023-10-09 01:39:56,225][88327] Updated weights for policy 1, policy_version 40050 (0.0007) -[2023-10-09 01:39:56,588][88327] Updated weights for policy 1, policy_version 40060 (0.0009) -[2023-10-09 01:39:57,166][88326] Updated weights for policy 0, policy_version 40042 (0.0009) -[2023-10-09 01:39:57,533][88326] Updated weights for policy 0, policy_version 40052 (0.0007) -[2023-10-09 01:39:57,898][88326] Updated weights for policy 0, policy_version 40062 (0.0008) -[2023-10-09 01:39:58,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 82051072. Throughput: 0: 1690.4, 1: 1675.1. Samples: 20517254. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-09 01:39:58,975][87372] Avg episode reward: [(0, '6.070'), (1, '5.960')] -[2023-10-09 01:40:00,577][88327] Updated weights for policy 1, policy_version 40070 (0.0008) -[2023-10-09 01:40:00,936][88327] Updated weights for policy 1, policy_version 40080 (0.0007) -[2023-10-09 01:40:01,307][88327] Updated weights for policy 1, policy_version 40090 (0.0008) -[2023-10-09 01:40:02,017][88326] Updated weights for policy 0, policy_version 40072 (0.0009) -[2023-10-09 01:40:02,380][88326] Updated weights for policy 0, policy_version 40082 (0.0008) -[2023-10-09 01:40:02,751][88326] Updated weights for policy 0, policy_version 40092 (0.0008) -[2023-10-09 01:40:03,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 82116608. Throughput: 0: 1669.7, 1: 1700.8. Samples: 20537250. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-09 01:40:03,975][87372] Avg episode reward: [(0, '6.360'), (1, '6.140')] -[2023-10-09 01:40:05,313][88327] Updated weights for policy 1, policy_version 40100 (0.0008) -[2023-10-09 01:40:05,679][88327] Updated weights for policy 1, policy_version 40110 (0.0008) -[2023-10-09 01:40:06,048][88327] Updated weights for policy 1, policy_version 40120 (0.0007) -[2023-10-09 01:40:06,768][88326] Updated weights for policy 0, policy_version 40102 (0.0009) -[2023-10-09 01:40:07,132][88326] Updated weights for policy 0, policy_version 40112 (0.0008) -[2023-10-09 01:40:07,495][88326] Updated weights for policy 0, policy_version 40122 (0.0009) -[2023-10-09 01:40:08,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 82182144. Throughput: 0: 1698.0, 1: 1671.2. Samples: 20547994. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-09 01:40:08,975][87372] Avg episode reward: [(0, '6.460'), (1, '5.660')] -[2023-10-09 01:40:10,199][88327] Updated weights for policy 1, policy_version 40130 (0.0008) -[2023-10-09 01:40:10,562][88327] Updated weights for policy 1, policy_version 40140 (0.0008) -[2023-10-09 01:40:10,931][88327] Updated weights for policy 1, policy_version 40150 (0.0007) -[2023-10-09 01:40:11,308][88327] Updated weights for policy 1, policy_version 40160 (0.0010) -[2023-10-09 01:40:11,500][88326] Updated weights for policy 0, policy_version 40132 (0.0008) -[2023-10-09 01:40:11,875][88326] Updated weights for policy 0, policy_version 40142 (0.0009) -[2023-10-09 01:40:12,251][88326] Updated weights for policy 0, policy_version 40152 (0.0008) -[2023-10-09 01:40:13,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 82247680. Throughput: 0: 1673.2, 1: 1681.3. Samples: 20567392. Policy #0 lag: (min: 20.0, avg: 35.3, max: 52.0) -[2023-10-09 01:40:13,975][87372] Avg episode reward: [(0, '6.300'), (1, '5.790')] -[2023-10-09 01:40:15,486][88327] Updated weights for policy 1, policy_version 40170 (0.0009) -[2023-10-09 01:40:15,864][88327] Updated weights for policy 1, policy_version 40180 (0.0007) -[2023-10-09 01:40:16,171][88326] Updated weights for policy 0, policy_version 40162 (0.0007) -[2023-10-09 01:40:16,225][88327] Updated weights for policy 1, policy_version 40190 (0.0008) -[2023-10-09 01:40:16,569][88326] Updated weights for policy 0, policy_version 40172 (0.0007) -[2023-10-09 01:40:16,933][88326] Updated weights for policy 0, policy_version 40182 (0.0008) -[2023-10-09 01:40:17,307][88326] Updated weights for policy 0, policy_version 40192 (0.0007) -[2023-10-09 01:40:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 82313216. Throughput: 0: 1683.3, 1: 1693.8. Samples: 20587900. Policy #0 lag: (min: 20.0, avg: 35.3, max: 52.0) -[2023-10-09 01:40:18,975][87372] Avg episode reward: [(0, '6.360'), (1, '5.670')] -[2023-10-09 01:40:20,163][88327] Updated weights for policy 1, policy_version 40200 (0.0009) -[2023-10-09 01:40:20,529][88327] Updated weights for policy 1, policy_version 40210 (0.0008) -[2023-10-09 01:40:20,898][88327] Updated weights for policy 1, policy_version 40220 (0.0008) -[2023-10-09 01:40:21,458][88326] Updated weights for policy 0, policy_version 40202 (0.0009) -[2023-10-09 01:40:21,818][88326] Updated weights for policy 0, policy_version 40212 (0.0009) -[2023-10-09 01:40:22,192][88326] Updated weights for policy 0, policy_version 40222 (0.0007) -[2023-10-09 01:40:23,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 82378752. Throughput: 0: 1688.9, 1: 1672.5. Samples: 20598070. Policy #0 lag: (min: 20.0, avg: 35.3, max: 52.0) -[2023-10-09 01:40:23,975][87372] Avg episode reward: [(0, '6.560'), (1, '6.090')] -[2023-10-09 01:40:24,830][88327] Updated weights for policy 1, policy_version 40230 (0.0009) -[2023-10-09 01:40:25,206][88327] Updated weights for policy 1, policy_version 40240 (0.0009) -[2023-10-09 01:40:25,566][88327] Updated weights for policy 1, policy_version 40250 (0.0011) -[2023-10-09 01:40:26,144][88326] Updated weights for policy 0, policy_version 40232 (0.0008) -[2023-10-09 01:40:26,522][88326] Updated weights for policy 0, policy_version 40242 (0.0010) -[2023-10-09 01:40:26,899][88326] Updated weights for policy 0, policy_version 40252 (0.0010) -[2023-10-09 01:40:28,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 82444288. Throughput: 0: 1668.6, 1: 1698.6. Samples: 20617970. Policy #0 lag: (min: 20.0, avg: 35.3, max: 52.0) -[2023-10-09 01:40:28,975][87372] Avg episode reward: [(0, '6.430'), (1, '6.470')] -[2023-10-09 01:40:29,763][88327] Updated weights for policy 1, policy_version 40260 (0.0009) -[2023-10-09 01:40:30,135][88327] Updated weights for policy 1, policy_version 40270 (0.0007) -[2023-10-09 01:40:30,498][88327] Updated weights for policy 1, policy_version 40280 (0.0007) -[2023-10-09 01:40:31,055][88326] Updated weights for policy 0, policy_version 40262 (0.0010) -[2023-10-09 01:40:31,414][88326] Updated weights for policy 0, policy_version 40272 (0.0010) -[2023-10-09 01:40:31,791][88326] Updated weights for policy 0, policy_version 40282 (0.0010) -[2023-10-09 01:40:33,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 82509824. Throughput: 0: 1695.6, 1: 1699.7. Samples: 20638912. Policy #0 lag: (min: 20.0, avg: 35.3, max: 52.0) -[2023-10-09 01:40:33,975][87372] Avg episode reward: [(0, '6.490'), (1, '6.370')] -[2023-10-09 01:40:33,986][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000040288_41254912.pth... -[2023-10-09 01:40:33,986][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000040288_41254912.pth... -[2023-10-09 01:40:34,022][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000038720_39649280.pth -[2023-10-09 01:40:34,024][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000038720_39649280.pth -[2023-10-09 01:40:34,450][88327] Updated weights for policy 1, policy_version 40290 (0.0008) -[2023-10-09 01:40:34,818][88327] Updated weights for policy 1, policy_version 40300 (0.0009) -[2023-10-09 01:40:35,194][88327] Updated weights for policy 1, policy_version 40310 (0.0009) -[2023-10-09 01:40:35,560][88327] Updated weights for policy 1, policy_version 40320 (0.0009) -[2023-10-09 01:40:35,878][88326] Updated weights for policy 0, policy_version 40292 (0.0009) -[2023-10-09 01:40:36,240][88326] Updated weights for policy 0, policy_version 40302 (0.0007) -[2023-10-09 01:40:36,618][88326] Updated weights for policy 0, policy_version 40312 (0.0008) -[2023-10-09 01:40:38,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 82575360. Throughput: 0: 1685.4, 1: 1679.4. Samples: 20648752. Policy #0 lag: (min: 20.0, avg: 35.3, max: 52.0) -[2023-10-09 01:40:38,974][87372] Avg episode reward: [(0, '6.340'), (1, '6.510')] -[2023-10-09 01:40:39,407][88327] Updated weights for policy 1, policy_version 40330 (0.0010) -[2023-10-09 01:40:39,767][88327] Updated weights for policy 1, policy_version 40340 (0.0009) -[2023-10-09 01:40:40,132][88327] Updated weights for policy 1, policy_version 40350 (0.0009) -[2023-10-09 01:40:40,628][88326] Updated weights for policy 0, policy_version 40322 (0.0008) -[2023-10-09 01:40:40,995][88326] Updated weights for policy 0, policy_version 40332 (0.0009) -[2023-10-09 01:40:41,358][88326] Updated weights for policy 0, policy_version 40342 (0.0007) -[2023-10-09 01:40:41,725][88326] Updated weights for policy 0, policy_version 40352 (0.0007) -[2023-10-09 01:40:43,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 82640896. Throughput: 0: 1675.3, 1: 1696.0. Samples: 20668962. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:40:43,975][87372] Avg episode reward: [(0, '6.080'), (1, '6.310')] -[2023-10-09 01:40:44,249][88327] Updated weights for policy 1, policy_version 40360 (0.0008) -[2023-10-09 01:40:44,624][88327] Updated weights for policy 1, policy_version 40370 (0.0008) -[2023-10-09 01:40:44,987][88327] Updated weights for policy 1, policy_version 40380 (0.0010) -[2023-10-09 01:40:45,723][88326] Updated weights for policy 0, policy_version 40362 (0.0009) -[2023-10-09 01:40:46,086][88326] Updated weights for policy 0, policy_version 40372 (0.0010) -[2023-10-09 01:40:46,461][88326] Updated weights for policy 0, policy_version 40382 (0.0008) -[2023-10-09 01:40:48,973][88327] Updated weights for policy 1, policy_version 40390 (0.0009) -[2023-10-09 01:40:48,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 82706432. Throughput: 0: 1701.7, 1: 1695.7. Samples: 20690134. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:40:48,975][87372] Avg episode reward: [(0, '5.960'), (1, '6.000')] -[2023-10-09 01:40:49,345][88327] Updated weights for policy 1, policy_version 40400 (0.0009) -[2023-10-09 01:40:49,710][88327] Updated weights for policy 1, policy_version 40410 (0.0009) -[2023-10-09 01:40:50,375][88326] Updated weights for policy 0, policy_version 40392 (0.0011) -[2023-10-09 01:40:50,740][88326] Updated weights for policy 0, policy_version 40402 (0.0010) -[2023-10-09 01:40:51,120][88326] Updated weights for policy 0, policy_version 40412 (0.0010) -[2023-10-09 01:40:53,746][88327] Updated weights for policy 1, policy_version 40420 (0.0009) -[2023-10-09 01:40:53,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 82771968. Throughput: 0: 1671.2, 1: 1692.4. Samples: 20699352. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:40:53,975][87372] Avg episode reward: [(0, '5.740'), (1, '6.050')] -[2023-10-09 01:40:54,098][88327] Updated weights for policy 1, policy_version 40430 (0.0009) -[2023-10-09 01:40:54,473][88327] Updated weights for policy 1, policy_version 40440 (0.0010) -[2023-10-09 01:40:55,234][88326] Updated weights for policy 0, policy_version 40422 (0.0010) -[2023-10-09 01:40:55,597][88326] Updated weights for policy 0, policy_version 40432 (0.0009) -[2023-10-09 01:40:55,966][88326] Updated weights for policy 0, policy_version 40442 (0.0009) -[2023-10-09 01:40:58,431][88327] Updated weights for policy 1, policy_version 40450 (0.0010) -[2023-10-09 01:40:58,802][88327] Updated weights for policy 1, policy_version 40460 (0.0007) -[2023-10-09 01:40:58,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 82837504. Throughput: 0: 1691.1, 1: 1701.0. Samples: 20720034. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:40:58,975][87372] Avg episode reward: [(0, '6.550'), (1, '6.260')] -[2023-10-09 01:40:59,167][88327] Updated weights for policy 1, policy_version 40470 (0.0008) -[2023-10-09 01:40:59,527][88327] Updated weights for policy 1, policy_version 40480 (0.0009) -[2023-10-09 01:41:00,026][88326] Updated weights for policy 0, policy_version 40452 (0.0008) -[2023-10-09 01:41:00,391][88326] Updated weights for policy 0, policy_version 40462 (0.0010) -[2023-10-09 01:41:00,765][88326] Updated weights for policy 0, policy_version 40472 (0.0007) -[2023-10-09 01:41:03,576][88327] Updated weights for policy 1, policy_version 40490 (0.0009) -[2023-10-09 01:41:03,942][88327] Updated weights for policy 1, policy_version 40500 (0.0009) -[2023-10-09 01:41:03,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 82903040. Throughput: 0: 1700.3, 1: 1708.3. Samples: 20741286. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:41:03,975][87372] Avg episode reward: [(0, '6.430'), (1, '6.060')] -[2023-10-09 01:41:04,299][88327] Updated weights for policy 1, policy_version 40510 (0.0011) -[2023-10-09 01:41:04,794][88326] Updated weights for policy 0, policy_version 40482 (0.0008) -[2023-10-09 01:41:05,221][88326] Updated weights for policy 0, policy_version 40492 (0.0009) -[2023-10-09 01:41:05,586][88326] Updated weights for policy 0, policy_version 40502 (0.0008) -[2023-10-09 01:41:05,957][88326] Updated weights for policy 0, policy_version 40512 (0.0008) -[2023-10-09 01:41:08,311][88327] Updated weights for policy 1, policy_version 40520 (0.0010) -[2023-10-09 01:41:08,677][88327] Updated weights for policy 1, policy_version 40530 (0.0008) -[2023-10-09 01:41:08,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 82968576. Throughput: 0: 1675.6, 1: 1708.0. Samples: 20750332. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:41:08,975][87372] Avg episode reward: [(0, '6.940'), (1, '5.730')] -[2023-10-09 01:41:09,041][88327] Updated weights for policy 1, policy_version 40540 (0.0007) -[2023-10-09 01:41:10,007][88326] Updated weights for policy 0, policy_version 40522 (0.0008) -[2023-10-09 01:41:10,376][88326] Updated weights for policy 0, policy_version 40532 (0.0008) -[2023-10-09 01:41:10,742][88326] Updated weights for policy 0, policy_version 40542 (0.0008) -[2023-10-09 01:41:13,249][88327] Updated weights for policy 1, policy_version 40550 (0.0009) -[2023-10-09 01:41:13,611][88327] Updated weights for policy 1, policy_version 40560 (0.0008) -[2023-10-09 01:41:13,970][88327] Updated weights for policy 1, policy_version 40570 (0.0011) -[2023-10-09 01:41:13,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 83034112. Throughput: 0: 1699.2, 1: 1705.3. Samples: 20771172. Policy #0 lag: (min: 31.0, avg: 32.8, max: 59.0) -[2023-10-09 01:41:13,975][87372] Avg episode reward: [(0, '6.810'), (1, '6.110')] -[2023-10-09 01:41:14,850][88326] Updated weights for policy 0, policy_version 40552 (0.0010) -[2023-10-09 01:41:15,223][88326] Updated weights for policy 0, policy_version 40562 (0.0008) -[2023-10-09 01:41:15,593][88326] Updated weights for policy 0, policy_version 40572 (0.0008) -[2023-10-09 01:41:18,126][88327] Updated weights for policy 1, policy_version 40580 (0.0010) -[2023-10-09 01:41:18,489][88327] Updated weights for policy 1, policy_version 40590 (0.0007) -[2023-10-09 01:41:18,855][88327] Updated weights for policy 1, policy_version 40600 (0.0007) -[2023-10-09 01:41:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 83099648. Throughput: 0: 1700.8, 1: 1695.9. Samples: 20791762. Policy #0 lag: (min: 31.0, avg: 32.8, max: 59.0) -[2023-10-09 01:41:18,975][87372] Avg episode reward: [(0, '6.680'), (1, '5.500')] -[2023-10-09 01:41:19,462][88326] Updated weights for policy 0, policy_version 40582 (0.0008) -[2023-10-09 01:41:19,831][88326] Updated weights for policy 0, policy_version 40592 (0.0009) -[2023-10-09 01:41:20,194][88326] Updated weights for policy 0, policy_version 40602 (0.0011) -[2023-10-09 01:41:22,822][88327] Updated weights for policy 1, policy_version 40610 (0.0009) -[2023-10-09 01:41:23,184][88327] Updated weights for policy 1, policy_version 40620 (0.0008) -[2023-10-09 01:41:23,540][88327] Updated weights for policy 1, policy_version 40630 (0.0008) -[2023-10-09 01:41:23,900][88327] Updated weights for policy 1, policy_version 40640 (0.0009) -[2023-10-09 01:41:23,974][87372] Fps is (10 sec: 16383.8, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 83197952. Throughput: 0: 1683.4, 1: 1705.3. Samples: 20801244. Policy #0 lag: (min: 31.0, avg: 32.8, max: 59.0) -[2023-10-09 01:41:23,975][87372] Avg episode reward: [(0, '6.250'), (1, '5.570')] -[2023-10-09 01:41:24,261][88326] Updated weights for policy 0, policy_version 40612 (0.0009) -[2023-10-09 01:41:24,635][88326] Updated weights for policy 0, policy_version 40622 (0.0008) -[2023-10-09 01:41:25,012][88326] Updated weights for policy 0, policy_version 40632 (0.0007) -[2023-10-09 01:41:27,907][88327] Updated weights for policy 1, policy_version 40650 (0.0007) -[2023-10-09 01:41:28,274][88327] Updated weights for policy 1, policy_version 40660 (0.0010) -[2023-10-09 01:41:28,643][88327] Updated weights for policy 1, policy_version 40670 (0.0009) -[2023-10-09 01:41:28,917][88326] Updated weights for policy 0, policy_version 40642 (0.0007) -[2023-10-09 01:41:28,974][87372] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 83263488. Throughput: 0: 1704.9, 1: 1702.3. Samples: 20822288. Policy #0 lag: (min: 31.0, avg: 32.8, max: 59.0) -[2023-10-09 01:41:28,975][87372] Avg episode reward: [(0, '5.830'), (1, '6.020')] -[2023-10-09 01:41:29,287][88326] Updated weights for policy 0, policy_version 40652 (0.0007) -[2023-10-09 01:41:29,656][88326] Updated weights for policy 0, policy_version 40662 (0.0008) -[2023-10-09 01:41:30,020][88326] Updated weights for policy 0, policy_version 40672 (0.0007) -[2023-10-09 01:41:32,749][88327] Updated weights for policy 1, policy_version 40680 (0.0010) -[2023-10-09 01:41:33,106][88327] Updated weights for policy 1, policy_version 40690 (0.0008) -[2023-10-09 01:41:33,479][88327] Updated weights for policy 1, policy_version 40700 (0.0008) -[2023-10-09 01:41:33,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 83329024. Throughput: 0: 1703.6, 1: 1681.9. Samples: 20842480. Policy #0 lag: (min: 31.0, avg: 32.8, max: 59.0) -[2023-10-09 01:41:33,974][87372] Avg episode reward: [(0, '5.750'), (1, '5.520')] -[2023-10-09 01:41:33,982][88326] Updated weights for policy 0, policy_version 40682 (0.0009) -[2023-10-09 01:41:34,355][88326] Updated weights for policy 0, policy_version 40692 (0.0008) -[2023-10-09 01:41:34,719][88326] Updated weights for policy 0, policy_version 40702 (0.0008) -[2023-10-09 01:41:37,394][88327] Updated weights for policy 1, policy_version 40710 (0.0009) -[2023-10-09 01:41:37,767][88327] Updated weights for policy 1, policy_version 40720 (0.0009) -[2023-10-09 01:41:38,123][88327] Updated weights for policy 1, policy_version 40730 (0.0009) -[2023-10-09 01:41:38,695][88326] Updated weights for policy 0, policy_version 40712 (0.0010) -[2023-10-09 01:41:38,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 83394560. Throughput: 0: 1704.0, 1: 1696.4. Samples: 20852368. Policy #0 lag: (min: 31.0, avg: 32.8, max: 59.0) -[2023-10-09 01:41:38,974][87372] Avg episode reward: [(0, '7.180'), (1, '5.600')] -[2023-10-09 01:41:39,061][88326] Updated weights for policy 0, policy_version 40722 (0.0007) -[2023-10-09 01:41:39,429][88326] Updated weights for policy 0, policy_version 40732 (0.0007) -[2023-10-09 01:41:39,582][88088] Saving new best policy, reward=7.180! -[2023-10-09 01:41:42,249][88327] Updated weights for policy 1, policy_version 40740 (0.0009) -[2023-10-09 01:41:42,612][88327] Updated weights for policy 1, policy_version 40750 (0.0008) -[2023-10-09 01:41:42,977][88327] Updated weights for policy 1, policy_version 40760 (0.0010) -[2023-10-09 01:41:43,495][88326] Updated weights for policy 0, policy_version 40742 (0.0007) -[2023-10-09 01:41:43,866][88326] Updated weights for policy 0, policy_version 40752 (0.0008) -[2023-10-09 01:41:43,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 83460096. Throughput: 0: 1704.7, 1: 1692.1. Samples: 20872890. Policy #0 lag: (min: 31.0, avg: 31.1, max: 39.0) -[2023-10-09 01:41:43,975][87372] Avg episode reward: [(0, '6.590'), (1, '5.940')] -[2023-10-09 01:41:44,231][88326] Updated weights for policy 0, policy_version 40762 (0.0008) -[2023-10-09 01:41:47,042][88327] Updated weights for policy 1, policy_version 40770 (0.0008) -[2023-10-09 01:41:47,410][88327] Updated weights for policy 1, policy_version 40780 (0.0009) -[2023-10-09 01:41:47,780][88327] Updated weights for policy 1, policy_version 40790 (0.0010) -[2023-10-09 01:41:48,153][88327] Updated weights for policy 1, policy_version 40800 (0.0008) -[2023-10-09 01:41:48,318][88326] Updated weights for policy 0, policy_version 40772 (0.0009) -[2023-10-09 01:41:48,681][88326] Updated weights for policy 0, policy_version 40782 (0.0010) -[2023-10-09 01:41:48,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 83525632. Throughput: 0: 1699.9, 1: 1661.7. Samples: 20892560. Policy #0 lag: (min: 31.0, avg: 31.1, max: 39.0) -[2023-10-09 01:41:48,975][87372] Avg episode reward: [(0, '6.480'), (1, '6.180')] -[2023-10-09 01:41:49,056][88326] Updated weights for policy 0, policy_version 40792 (0.0008) -[2023-10-09 01:41:52,413][88327] Updated weights for policy 1, policy_version 40810 (0.0008) -[2023-10-09 01:41:52,789][88327] Updated weights for policy 1, policy_version 40820 (0.0009) -[2023-10-09 01:41:52,976][88326] Updated weights for policy 0, policy_version 40802 (0.0009) -[2023-10-09 01:41:53,145][88327] Updated weights for policy 1, policy_version 40830 (0.0007) -[2023-10-09 01:41:53,400][88326] Updated weights for policy 0, policy_version 40812 (0.0009) -[2023-10-09 01:41:53,771][88326] Updated weights for policy 0, policy_version 40822 (0.0008) -[2023-10-09 01:41:53,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 83591168. Throughput: 0: 1706.5, 1: 1689.7. Samples: 20903162. Policy #0 lag: (min: 31.0, avg: 31.1, max: 39.0) -[2023-10-09 01:41:53,975][87372] Avg episode reward: [(0, '6.850'), (1, '5.970')] -[2023-10-09 01:41:54,139][88326] Updated weights for policy 0, policy_version 40832 (0.0010) -[2023-10-09 01:41:57,062][88327] Updated weights for policy 1, policy_version 40840 (0.0009) -[2023-10-09 01:41:57,426][88327] Updated weights for policy 1, policy_version 40850 (0.0007) -[2023-10-09 01:41:57,791][88327] Updated weights for policy 1, policy_version 40860 (0.0008) -[2023-10-09 01:41:58,200][88326] Updated weights for policy 0, policy_version 40842 (0.0009) -[2023-10-09 01:41:58,579][88326] Updated weights for policy 0, policy_version 40852 (0.0009) -[2023-10-09 01:41:58,947][88326] Updated weights for policy 0, policy_version 40862 (0.0010) -[2023-10-09 01:41:58,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 83656704. Throughput: 0: 1704.8, 1: 1680.8. Samples: 20923526. Policy #0 lag: (min: 31.0, avg: 31.1, max: 39.0) -[2023-10-09 01:41:58,975][87372] Avg episode reward: [(0, '5.660'), (1, '5.740')] -[2023-10-09 01:42:01,857][88327] Updated weights for policy 1, policy_version 40870 (0.0010) -[2023-10-09 01:42:02,226][88327] Updated weights for policy 1, policy_version 40880 (0.0010) -[2023-10-09 01:42:02,589][88327] Updated weights for policy 1, policy_version 40890 (0.0007) -[2023-10-09 01:42:02,768][88326] Updated weights for policy 0, policy_version 40872 (0.0008) -[2023-10-09 01:42:03,136][88326] Updated weights for policy 0, policy_version 40882 (0.0009) -[2023-10-09 01:42:03,514][88326] Updated weights for policy 0, policy_version 40892 (0.0010) -[2023-10-09 01:42:03,974][87372] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 83755008. Throughput: 0: 1691.8, 1: 1666.4. Samples: 20942884. Policy #0 lag: (min: 31.0, avg: 31.1, max: 39.0) -[2023-10-09 01:42:03,975][87372] Avg episode reward: [(0, '6.310'), (1, '5.590')] -[2023-10-09 01:42:06,578][88327] Updated weights for policy 1, policy_version 40900 (0.0008) -[2023-10-09 01:42:06,939][88327] Updated weights for policy 1, policy_version 40910 (0.0008) -[2023-10-09 01:42:07,306][88327] Updated weights for policy 1, policy_version 40920 (0.0009) -[2023-10-09 01:42:07,596][88326] Updated weights for policy 0, policy_version 40902 (0.0008) -[2023-10-09 01:42:07,962][88326] Updated weights for policy 0, policy_version 40912 (0.0010) -[2023-10-09 01:42:08,331][88326] Updated weights for policy 0, policy_version 40922 (0.0010) -[2023-10-09 01:42:08,974][87372] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 83820544. Throughput: 0: 1706.8, 1: 1687.5. Samples: 20953986. Policy #0 lag: (min: 11.0, avg: 18.5, max: 43.0) -[2023-10-09 01:42:08,975][87372] Avg episode reward: [(0, '6.240'), (1, '5.620')] -[2023-10-09 01:42:11,351][88327] Updated weights for policy 1, policy_version 40930 (0.0007) -[2023-10-09 01:42:11,717][88327] Updated weights for policy 1, policy_version 40940 (0.0009) -[2023-10-09 01:42:12,095][88327] Updated weights for policy 1, policy_version 40950 (0.0009) -[2023-10-09 01:42:12,303][88326] Updated weights for policy 0, policy_version 40932 (0.0009) -[2023-10-09 01:42:12,460][88327] Updated weights for policy 1, policy_version 40960 (0.0009) -[2023-10-09 01:42:12,674][88326] Updated weights for policy 0, policy_version 40942 (0.0007) -[2023-10-09 01:42:13,034][88326] Updated weights for policy 0, policy_version 40952 (0.0007) -[2023-10-09 01:42:13,974][87372] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 83886080. Throughput: 0: 1701.0, 1: 1668.3. Samples: 20973908. Policy #0 lag: (min: 11.0, avg: 18.5, max: 43.0) -[2023-10-09 01:42:13,975][87372] Avg episode reward: [(0, '5.920'), (1, '5.630')] -[2023-10-09 01:42:16,430][88327] Updated weights for policy 1, policy_version 40970 (0.0009) -[2023-10-09 01:42:16,797][88327] Updated weights for policy 1, policy_version 40980 (0.0008) -[2023-10-09 01:42:17,138][88326] Updated weights for policy 0, policy_version 40962 (0.0007) -[2023-10-09 01:42:17,155][88327] Updated weights for policy 1, policy_version 40990 (0.0008) -[2023-10-09 01:42:17,501][88326] Updated weights for policy 0, policy_version 40972 (0.0008) -[2023-10-09 01:42:17,870][88326] Updated weights for policy 0, policy_version 40982 (0.0009) -[2023-10-09 01:42:18,243][88326] Updated weights for policy 0, policy_version 40992 (0.0007) -[2023-10-09 01:42:18,974][87372] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 83951616. Throughput: 0: 1671.7, 1: 1676.2. Samples: 20993138. Policy #0 lag: (min: 11.0, avg: 18.5, max: 43.0) -[2023-10-09 01:42:18,975][87372] Avg episode reward: [(0, '6.590'), (1, '6.240')] -[2023-10-09 01:42:21,344][88327] Updated weights for policy 1, policy_version 41000 (0.0009) -[2023-10-09 01:42:21,707][88327] Updated weights for policy 1, policy_version 41010 (0.0008) -[2023-10-09 01:42:22,062][88327] Updated weights for policy 1, policy_version 41020 (0.0009) -[2023-10-09 01:42:22,279][88326] Updated weights for policy 0, policy_version 41002 (0.0008) -[2023-10-09 01:42:22,660][88326] Updated weights for policy 0, policy_version 41012 (0.0008) -[2023-10-09 01:42:23,023][88326] Updated weights for policy 0, policy_version 41022 (0.0008) -[2023-10-09 01:42:23,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 84017152. Throughput: 0: 1700.4, 1: 1687.7. Samples: 21004834. Policy #0 lag: (min: 11.0, avg: 18.5, max: 43.0) -[2023-10-09 01:42:23,974][87372] Avg episode reward: [(0, '6.100'), (1, '6.110')] -[2023-10-09 01:42:26,165][88327] Updated weights for policy 1, policy_version 41030 (0.0008) -[2023-10-09 01:42:26,537][88327] Updated weights for policy 1, policy_version 41040 (0.0009) -[2023-10-09 01:42:26,909][88327] Updated weights for policy 1, policy_version 41050 (0.0007) -[2023-10-09 01:42:27,100][88326] Updated weights for policy 0, policy_version 41032 (0.0008) -[2023-10-09 01:42:27,476][88326] Updated weights for policy 0, policy_version 41042 (0.0010) -[2023-10-09 01:42:27,843][88326] Updated weights for policy 0, policy_version 41052 (0.0011) -[2023-10-09 01:42:28,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 84082688. Throughput: 0: 1692.5, 1: 1670.1. Samples: 21024208. Policy #0 lag: (min: 11.0, avg: 18.5, max: 43.0) -[2023-10-09 01:42:28,974][87372] Avg episode reward: [(0, '5.860'), (1, '5.900')] -[2023-10-09 01:42:30,957][88327] Updated weights for policy 1, policy_version 41060 (0.0008) -[2023-10-09 01:42:31,330][88327] Updated weights for policy 1, policy_version 41070 (0.0007) -[2023-10-09 01:42:31,691][88327] Updated weights for policy 1, policy_version 41080 (0.0007) -[2023-10-09 01:42:31,928][88326] Updated weights for policy 0, policy_version 41062 (0.0009) -[2023-10-09 01:42:32,290][88326] Updated weights for policy 0, policy_version 41072 (0.0009) -[2023-10-09 01:42:32,663][88326] Updated weights for policy 0, policy_version 41082 (0.0007) -[2023-10-09 01:42:33,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 84148224. Throughput: 0: 1673.9, 1: 1693.2. Samples: 21044082. Policy #0 lag: (min: 11.0, avg: 18.5, max: 43.0) -[2023-10-09 01:42:33,975][87372] Avg episode reward: [(0, '6.190'), (1, '6.570')] -[2023-10-09 01:42:33,985][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000041088_42074112.pth... -[2023-10-09 01:42:33,985][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000041088_42074112.pth... -[2023-10-09 01:42:34,035][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000039520_40468480.pth -[2023-10-09 01:42:34,035][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000039488_40435712.pth -[2023-10-09 01:42:35,645][88327] Updated weights for policy 1, policy_version 41090 (0.0007) -[2023-10-09 01:42:36,005][88327] Updated weights for policy 1, policy_version 41100 (0.0008) -[2023-10-09 01:42:36,372][88327] Updated weights for policy 1, policy_version 41110 (0.0009) -[2023-10-09 01:42:36,647][88326] Updated weights for policy 0, policy_version 41092 (0.0007) -[2023-10-09 01:42:36,731][88327] Updated weights for policy 1, policy_version 41120 (0.0008) -[2023-10-09 01:42:37,019][88326] Updated weights for policy 0, policy_version 41102 (0.0008) -[2023-10-09 01:42:37,388][88326] Updated weights for policy 0, policy_version 41112 (0.0008) -[2023-10-09 01:42:38,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 84213760. Throughput: 0: 1704.1, 1: 1679.2. Samples: 21055414. Policy #0 lag: (min: 16.0, avg: 36.5, max: 48.0) -[2023-10-09 01:42:38,975][87372] Avg episode reward: [(0, '6.360'), (1, '6.910')] -[2023-10-09 01:42:38,977][88168] Saving new best policy, reward=6.910! -[2023-10-09 01:42:40,842][88327] Updated weights for policy 1, policy_version 41130 (0.0011) -[2023-10-09 01:42:41,200][88327] Updated weights for policy 1, policy_version 41140 (0.0008) -[2023-10-09 01:42:41,273][88326] Updated weights for policy 0, policy_version 41122 (0.0008) -[2023-10-09 01:42:41,551][88327] Updated weights for policy 1, policy_version 41150 (0.0008) -[2023-10-09 01:42:41,629][88326] Updated weights for policy 0, policy_version 41132 (0.0009) -[2023-10-09 01:42:42,001][88326] Updated weights for policy 0, policy_version 41142 (0.0009) -[2023-10-09 01:42:42,378][88326] Updated weights for policy 0, policy_version 41152 (0.0007) -[2023-10-09 01:42:43,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 84279296. Throughput: 0: 1686.0, 1: 1670.2. Samples: 21074556. Policy #0 lag: (min: 16.0, avg: 36.5, max: 48.0) -[2023-10-09 01:42:43,975][87372] Avg episode reward: [(0, '6.300'), (1, '6.680')] -[2023-10-09 01:42:45,805][88327] Updated weights for policy 1, policy_version 41160 (0.0010) -[2023-10-09 01:42:46,168][88327] Updated weights for policy 1, policy_version 41170 (0.0009) -[2023-10-09 01:42:46,448][88326] Updated weights for policy 0, policy_version 41162 (0.0008) -[2023-10-09 01:42:46,526][88327] Updated weights for policy 1, policy_version 41180 (0.0008) -[2023-10-09 01:42:46,808][88326] Updated weights for policy 0, policy_version 41172 (0.0008) -[2023-10-09 01:42:47,178][88326] Updated weights for policy 0, policy_version 41182 (0.0008) -[2023-10-09 01:42:48,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 84344832. Throughput: 0: 1693.5, 1: 1690.5. Samples: 21095164. Policy #0 lag: (min: 16.0, avg: 36.5, max: 48.0) -[2023-10-09 01:42:48,975][87372] Avg episode reward: [(0, '6.400'), (1, '6.640')] -[2023-10-09 01:42:50,701][88327] Updated weights for policy 1, policy_version 41190 (0.0010) -[2023-10-09 01:42:51,067][88327] Updated weights for policy 1, policy_version 41200 (0.0008) -[2023-10-09 01:42:51,177][88326] Updated weights for policy 0, policy_version 41192 (0.0007) -[2023-10-09 01:42:51,436][88327] Updated weights for policy 1, policy_version 41210 (0.0009) -[2023-10-09 01:42:51,558][88326] Updated weights for policy 0, policy_version 41202 (0.0009) -[2023-10-09 01:42:51,920][88326] Updated weights for policy 0, policy_version 41212 (0.0008) -[2023-10-09 01:42:53,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 84410368. Throughput: 0: 1698.5, 1: 1678.6. Samples: 21105954. Policy #0 lag: (min: 16.0, avg: 36.5, max: 48.0) -[2023-10-09 01:42:53,975][87372] Avg episode reward: [(0, '6.600'), (1, '6.560')] -[2023-10-09 01:42:55,585][88327] Updated weights for policy 1, policy_version 41220 (0.0008) -[2023-10-09 01:42:55,783][88326] Updated weights for policy 0, policy_version 41222 (0.0007) -[2023-10-09 01:42:55,953][88327] Updated weights for policy 1, policy_version 41230 (0.0008) -[2023-10-09 01:42:56,154][88326] Updated weights for policy 0, policy_version 41232 (0.0007) -[2023-10-09 01:42:56,315][88327] Updated weights for policy 1, policy_version 41240 (0.0007) -[2023-10-09 01:42:56,513][88326] Updated weights for policy 0, policy_version 41242 (0.0008) -[2023-10-09 01:42:58,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 84475904. Throughput: 0: 1678.0, 1: 1687.5. Samples: 21125356. Policy #0 lag: (min: 16.0, avg: 36.5, max: 48.0) -[2023-10-09 01:42:58,975][87372] Avg episode reward: [(0, '6.800'), (1, '6.180')] -[2023-10-09 01:43:00,152][88327] Updated weights for policy 1, policy_version 41250 (0.0008) -[2023-10-09 01:43:00,512][88327] Updated weights for policy 1, policy_version 41260 (0.0009) -[2023-10-09 01:43:00,642][88326] Updated weights for policy 0, policy_version 41252 (0.0007) -[2023-10-09 01:43:00,878][88327] Updated weights for policy 1, policy_version 41270 (0.0007) -[2023-10-09 01:43:01,009][88326] Updated weights for policy 0, policy_version 41262 (0.0009) -[2023-10-09 01:43:01,241][88327] Updated weights for policy 1, policy_version 41280 (0.0007) -[2023-10-09 01:43:01,374][88326] Updated weights for policy 0, policy_version 41272 (0.0007) -[2023-10-09 01:43:03,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 84541440. Throughput: 0: 1710.0, 1: 1700.2. Samples: 21146596. Policy #0 lag: (min: 16.0, avg: 36.5, max: 48.0) -[2023-10-09 01:43:03,975][87372] Avg episode reward: [(0, '6.460'), (1, '5.800')] -[2023-10-09 01:43:05,146][88327] Updated weights for policy 1, policy_version 41290 (0.0011) -[2023-10-09 01:43:05,436][88326] Updated weights for policy 0, policy_version 41282 (0.0007) -[2023-10-09 01:43:05,511][88327] Updated weights for policy 1, policy_version 41300 (0.0009) -[2023-10-09 01:43:05,798][88326] Updated weights for policy 0, policy_version 41292 (0.0008) -[2023-10-09 01:43:05,871][88327] Updated weights for policy 1, policy_version 41310 (0.0008) -[2023-10-09 01:43:06,174][88326] Updated weights for policy 0, policy_version 41302 (0.0009) -[2023-10-09 01:43:06,541][88326] Updated weights for policy 0, policy_version 41312 (0.0009) -[2023-10-09 01:43:08,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 84606976. Throughput: 0: 1691.3, 1: 1671.4. Samples: 21156156. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-09 01:43:08,975][87372] Avg episode reward: [(0, '6.350'), (1, '6.150')] -[2023-10-09 01:43:09,932][88327] Updated weights for policy 1, policy_version 41320 (0.0010) -[2023-10-09 01:43:10,300][88327] Updated weights for policy 1, policy_version 41330 (0.0008) -[2023-10-09 01:43:10,613][88326] Updated weights for policy 0, policy_version 41322 (0.0008) -[2023-10-09 01:43:10,670][88327] Updated weights for policy 1, policy_version 41340 (0.0007) -[2023-10-09 01:43:10,978][88326] Updated weights for policy 0, policy_version 41332 (0.0009) -[2023-10-09 01:43:11,354][88326] Updated weights for policy 0, policy_version 41342 (0.0007) -[2023-10-09 01:43:13,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 84672512. Throughput: 0: 1693.5, 1: 1697.2. Samples: 21176790. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-09 01:43:13,975][87372] Avg episode reward: [(0, '6.720'), (1, '6.140')] -[2023-10-09 01:43:14,758][88327] Updated weights for policy 1, policy_version 41350 (0.0008) -[2023-10-09 01:43:15,113][88327] Updated weights for policy 1, policy_version 41360 (0.0011) -[2023-10-09 01:43:15,407][88326] Updated weights for policy 0, policy_version 41352 (0.0009) -[2023-10-09 01:43:15,475][88327] Updated weights for policy 1, policy_version 41370 (0.0009) -[2023-10-09 01:43:15,772][88326] Updated weights for policy 0, policy_version 41362 (0.0007) -[2023-10-09 01:43:16,141][88326] Updated weights for policy 0, policy_version 41372 (0.0010) -[2023-10-09 01:43:18,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 84738048. Throughput: 0: 1714.3, 1: 1699.0. Samples: 21197682. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-09 01:43:18,975][87372] Avg episode reward: [(0, '5.990'), (1, '5.950')] -[2023-10-09 01:43:19,470][88327] Updated weights for policy 1, policy_version 41380 (0.0008) -[2023-10-09 01:43:19,826][88327] Updated weights for policy 1, policy_version 41390 (0.0008) -[2023-10-09 01:43:20,128][88326] Updated weights for policy 0, policy_version 41382 (0.0008) -[2023-10-09 01:43:20,189][88327] Updated weights for policy 1, policy_version 41400 (0.0009) -[2023-10-09 01:43:20,496][88326] Updated weights for policy 0, policy_version 41392 (0.0008) -[2023-10-09 01:43:20,865][88326] Updated weights for policy 0, policy_version 41402 (0.0007) -[2023-10-09 01:43:23,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 84803584. Throughput: 0: 1680.9, 1: 1684.0. Samples: 21206836. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-09 01:43:23,975][87372] Avg episode reward: [(0, '5.930'), (1, '6.090')] -[2023-10-09 01:43:24,106][88327] Updated weights for policy 1, policy_version 41410 (0.0008) -[2023-10-09 01:43:24,477][88327] Updated weights for policy 1, policy_version 41420 (0.0007) -[2023-10-09 01:43:24,845][88327] Updated weights for policy 1, policy_version 41430 (0.0009) -[2023-10-09 01:43:24,861][88326] Updated weights for policy 0, policy_version 41412 (0.0008) -[2023-10-09 01:43:25,205][88327] Updated weights for policy 1, policy_version 41440 (0.0008) -[2023-10-09 01:43:25,226][88326] Updated weights for policy 0, policy_version 41422 (0.0007) -[2023-10-09 01:43:25,593][88326] Updated weights for policy 0, policy_version 41432 (0.0010) -[2023-10-09 01:43:28,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 84869120. Throughput: 0: 1700.0, 1: 1707.9. Samples: 21227912. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-09 01:43:28,975][87372] Avg episode reward: [(0, '5.900'), (1, '5.940')] -[2023-10-09 01:43:29,220][88327] Updated weights for policy 1, policy_version 41450 (0.0009) -[2023-10-09 01:43:29,597][88327] Updated weights for policy 1, policy_version 41460 (0.0010) -[2023-10-09 01:43:29,620][88326] Updated weights for policy 0, policy_version 41442 (0.0008) -[2023-10-09 01:43:29,962][88327] Updated weights for policy 1, policy_version 41470 (0.0008) -[2023-10-09 01:43:29,991][88326] Updated weights for policy 0, policy_version 41452 (0.0007) -[2023-10-09 01:43:30,364][88326] Updated weights for policy 0, policy_version 41462 (0.0007) -[2023-10-09 01:43:30,736][88326] Updated weights for policy 0, policy_version 41472 (0.0008) -[2023-10-09 01:43:33,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 84934656. Throughput: 0: 1703.5, 1: 1707.3. Samples: 21248648. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-09 01:43:33,975][87372] Avg episode reward: [(0, '5.500'), (1, '6.250')] -[2023-10-09 01:43:34,038][88327] Updated weights for policy 1, policy_version 41480 (0.0010) -[2023-10-09 01:43:34,403][88327] Updated weights for policy 1, policy_version 41490 (0.0010) -[2023-10-09 01:43:34,775][88327] Updated weights for policy 1, policy_version 41500 (0.0007) -[2023-10-09 01:43:34,881][88326] Updated weights for policy 0, policy_version 41482 (0.0007) -[2023-10-09 01:43:35,247][88326] Updated weights for policy 0, policy_version 41492 (0.0008) -[2023-10-09 01:43:35,612][88326] Updated weights for policy 0, policy_version 41502 (0.0010) -[2023-10-09 01:43:38,693][88327] Updated weights for policy 1, policy_version 41510 (0.0009) -[2023-10-09 01:43:38,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 85000192. Throughput: 0: 1680.5, 1: 1690.9. Samples: 21257668. Policy #0 lag: (min: 31.0, avg: 32.2, max: 54.0) -[2023-10-09 01:43:38,975][87372] Avg episode reward: [(0, '5.300'), (1, '6.040')] -[2023-10-09 01:43:39,055][88327] Updated weights for policy 1, policy_version 41520 (0.0011) -[2023-10-09 01:43:39,419][88327] Updated weights for policy 1, policy_version 41530 (0.0009) -[2023-10-09 01:43:39,580][88326] Updated weights for policy 0, policy_version 41512 (0.0009) -[2023-10-09 01:43:39,949][88326] Updated weights for policy 0, policy_version 41522 (0.0010) -[2023-10-09 01:43:40,329][88326] Updated weights for policy 0, policy_version 41532 (0.0009) -[2023-10-09 01:43:43,478][88327] Updated weights for policy 1, policy_version 41540 (0.0009) -[2023-10-09 01:43:43,832][88327] Updated weights for policy 1, policy_version 41550 (0.0009) -[2023-10-09 01:43:43,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 85065728. Throughput: 0: 1698.9, 1: 1706.0. Samples: 21278578. Policy #0 lag: (min: 31.0, avg: 32.2, max: 54.0) -[2023-10-09 01:43:43,975][87372] Avg episode reward: [(0, '5.380'), (1, '6.100')] -[2023-10-09 01:43:44,201][88327] Updated weights for policy 1, policy_version 41560 (0.0010) -[2023-10-09 01:43:44,310][88326] Updated weights for policy 0, policy_version 41542 (0.0009) -[2023-10-09 01:43:44,667][88326] Updated weights for policy 0, policy_version 41552 (0.0009) -[2023-10-09 01:43:45,040][88326] Updated weights for policy 0, policy_version 41562 (0.0008) -[2023-10-09 01:43:48,501][88327] Updated weights for policy 1, policy_version 41570 (0.0008) -[2023-10-09 01:43:48,865][88327] Updated weights for policy 1, policy_version 41580 (0.0011) -[2023-10-09 01:43:48,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.3, 300 sec: 13440.4). Total num frames: 85131264. Throughput: 0: 1694.6, 1: 1704.0. Samples: 21299534. Policy #0 lag: (min: 31.0, avg: 32.2, max: 54.0) -[2023-10-09 01:43:48,975][87372] Avg episode reward: [(0, '6.120'), (1, '6.490')] -[2023-10-09 01:43:49,037][88326] Updated weights for policy 0, policy_version 41572 (0.0008) -[2023-10-09 01:43:49,225][88327] Updated weights for policy 1, policy_version 41590 (0.0007) -[2023-10-09 01:43:49,406][88326] Updated weights for policy 0, policy_version 41582 (0.0008) -[2023-10-09 01:43:49,587][88327] Updated weights for policy 1, policy_version 41600 (0.0008) -[2023-10-09 01:43:49,773][88326] Updated weights for policy 0, policy_version 41592 (0.0009) -[2023-10-09 01:43:53,551][88327] Updated weights for policy 1, policy_version 41610 (0.0011) -[2023-10-09 01:43:53,891][88326] Updated weights for policy 0, policy_version 41602 (0.0008) -[2023-10-09 01:43:53,912][88327] Updated weights for policy 1, policy_version 41620 (0.0009) -[2023-10-09 01:43:53,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 85196800. Throughput: 0: 1685.7, 1: 1705.2. Samples: 21308748. Policy #0 lag: (min: 31.0, avg: 32.2, max: 54.0) -[2023-10-09 01:43:53,974][87372] Avg episode reward: [(0, '6.030'), (1, '6.060')] -[2023-10-09 01:43:54,257][88326] Updated weights for policy 0, policy_version 41612 (0.0007) -[2023-10-09 01:43:54,282][88327] Updated weights for policy 1, policy_version 41630 (0.0007) -[2023-10-09 01:43:54,627][88326] Updated weights for policy 0, policy_version 41622 (0.0008) -[2023-10-09 01:43:54,994][88326] Updated weights for policy 0, policy_version 41632 (0.0009) -[2023-10-09 01:43:58,065][88327] Updated weights for policy 1, policy_version 41640 (0.0009) -[2023-10-09 01:43:58,423][88327] Updated weights for policy 1, policy_version 41650 (0.0010) -[2023-10-09 01:43:58,785][88327] Updated weights for policy 1, policy_version 41660 (0.0010) -[2023-10-09 01:43:58,974][87372] Fps is (10 sec: 16384.0, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 85295104. Throughput: 0: 1692.9, 1: 1708.4. Samples: 21329852. Policy #0 lag: (min: 31.0, avg: 32.2, max: 54.0) -[2023-10-09 01:43:58,975][87372] Avg episode reward: [(0, '6.130'), (1, '5.980')] -[2023-10-09 01:43:59,069][88326] Updated weights for policy 0, policy_version 41642 (0.0009) -[2023-10-09 01:43:59,438][88326] Updated weights for policy 0, policy_version 41652 (0.0011) -[2023-10-09 01:43:59,802][88326] Updated weights for policy 0, policy_version 41662 (0.0010) -[2023-10-09 01:44:02,745][88327] Updated weights for policy 1, policy_version 41670 (0.0009) -[2023-10-09 01:44:03,108][88327] Updated weights for policy 1, policy_version 41680 (0.0009) -[2023-10-09 01:44:03,467][88327] Updated weights for policy 1, policy_version 41690 (0.0009) -[2023-10-09 01:44:03,888][88326] Updated weights for policy 0, policy_version 41672 (0.0008) -[2023-10-09 01:44:03,974][87372] Fps is (10 sec: 16383.6, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 85360640. Throughput: 0: 1690.9, 1: 1693.0. Samples: 21349960. Policy #0 lag: (min: 31.0, avg: 32.2, max: 54.0) -[2023-10-09 01:44:03,975][87372] Avg episode reward: [(0, '6.240'), (1, '6.690')] -[2023-10-09 01:44:04,256][88326] Updated weights for policy 0, policy_version 41682 (0.0010) -[2023-10-09 01:44:04,623][88326] Updated weights for policy 0, policy_version 41692 (0.0009) -[2023-10-09 01:44:07,514][88327] Updated weights for policy 1, policy_version 41700 (0.0009) -[2023-10-09 01:44:07,893][88327] Updated weights for policy 1, policy_version 41710 (0.0011) -[2023-10-09 01:44:08,252][88327] Updated weights for policy 1, policy_version 41720 (0.0010) -[2023-10-09 01:44:08,500][88326] Updated weights for policy 0, policy_version 41702 (0.0008) -[2023-10-09 01:44:08,870][88326] Updated weights for policy 0, policy_version 41712 (0.0009) -[2023-10-09 01:44:08,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 85426176. Throughput: 0: 1692.8, 1: 1709.4. Samples: 21359938. Policy #0 lag: (min: 31.0, avg: 31.8, max: 50.0) -[2023-10-09 01:44:08,975][87372] Avg episode reward: [(0, '6.220'), (1, '6.620')] -[2023-10-09 01:44:09,234][88326] Updated weights for policy 0, policy_version 41722 (0.0009) -[2023-10-09 01:44:12,343][88327] Updated weights for policy 1, policy_version 41730 (0.0009) -[2023-10-09 01:44:12,704][88327] Updated weights for policy 1, policy_version 41740 (0.0009) -[2023-10-09 01:44:13,071][88327] Updated weights for policy 1, policy_version 41750 (0.0008) -[2023-10-09 01:44:13,175][88326] Updated weights for policy 0, policy_version 41732 (0.0008) -[2023-10-09 01:44:13,439][88327] Updated weights for policy 1, policy_version 41760 (0.0009) -[2023-10-09 01:44:13,538][88326] Updated weights for policy 0, policy_version 41742 (0.0007) -[2023-10-09 01:44:13,914][88326] Updated weights for policy 0, policy_version 41752 (0.0009) -[2023-10-09 01:44:13,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 85491712. Throughput: 0: 1696.2, 1: 1705.2. Samples: 21380972. Policy #0 lag: (min: 31.0, avg: 31.8, max: 50.0) -[2023-10-09 01:44:13,974][87372] Avg episode reward: [(0, '5.980'), (1, '6.830')] -[2023-10-09 01:44:17,559][88327] Updated weights for policy 1, policy_version 41770 (0.0009) -[2023-10-09 01:44:17,940][88327] Updated weights for policy 1, policy_version 41780 (0.0008) -[2023-10-09 01:44:18,110][88326] Updated weights for policy 0, policy_version 41762 (0.0008) -[2023-10-09 01:44:18,303][88327] Updated weights for policy 1, policy_version 41790 (0.0009) -[2023-10-09 01:44:18,478][88326] Updated weights for policy 0, policy_version 41772 (0.0008) -[2023-10-09 01:44:18,849][88326] Updated weights for policy 0, policy_version 41782 (0.0009) -[2023-10-09 01:44:18,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 85557248. Throughput: 0: 1692.4, 1: 1685.5. Samples: 21400656. Policy #0 lag: (min: 31.0, avg: 31.8, max: 50.0) -[2023-10-09 01:44:18,976][87372] Avg episode reward: [(0, '6.260'), (1, '6.630')] -[2023-10-09 01:44:19,228][88326] Updated weights for policy 0, policy_version 41792 (0.0011) -[2023-10-09 01:44:22,199][88327] Updated weights for policy 1, policy_version 41800 (0.0008) -[2023-10-09 01:44:22,562][88327] Updated weights for policy 1, policy_version 41810 (0.0008) -[2023-10-09 01:44:22,930][88327] Updated weights for policy 1, policy_version 41820 (0.0007) -[2023-10-09 01:44:23,217][88326] Updated weights for policy 0, policy_version 41802 (0.0008) -[2023-10-09 01:44:23,593][88326] Updated weights for policy 0, policy_version 41812 (0.0010) -[2023-10-09 01:44:23,963][88326] Updated weights for policy 0, policy_version 41822 (0.0010) -[2023-10-09 01:44:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 85622784. Throughput: 0: 1697.5, 1: 1708.3. Samples: 21410930. Policy #0 lag: (min: 31.0, avg: 31.8, max: 50.0) -[2023-10-09 01:44:23,974][87372] Avg episode reward: [(0, '6.280'), (1, '6.630')] -[2023-10-09 01:44:27,155][88327] Updated weights for policy 1, policy_version 41830 (0.0008) -[2023-10-09 01:44:27,509][88327] Updated weights for policy 1, policy_version 41840 (0.0009) -[2023-10-09 01:44:27,880][88327] Updated weights for policy 1, policy_version 41850 (0.0007) -[2023-10-09 01:44:27,883][88326] Updated weights for policy 0, policy_version 41832 (0.0007) -[2023-10-09 01:44:28,243][88326] Updated weights for policy 0, policy_version 41842 (0.0010) -[2023-10-09 01:44:28,616][88326] Updated weights for policy 0, policy_version 41852 (0.0008) -[2023-10-09 01:44:28,974][87372] Fps is (10 sec: 16384.7, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 85721088. Throughput: 0: 1706.3, 1: 1697.7. Samples: 21431758. Policy #0 lag: (min: 31.0, avg: 31.8, max: 50.0) -[2023-10-09 01:44:28,975][87372] Avg episode reward: [(0, '5.970'), (1, '6.090')] -[2023-10-09 01:44:31,938][88327] Updated weights for policy 1, policy_version 41860 (0.0009) -[2023-10-09 01:44:32,295][88327] Updated weights for policy 1, policy_version 41870 (0.0008) -[2023-10-09 01:44:32,590][88326] Updated weights for policy 0, policy_version 41862 (0.0007) -[2023-10-09 01:44:32,661][88327] Updated weights for policy 1, policy_version 41880 (0.0007) -[2023-10-09 01:44:32,955][88326] Updated weights for policy 0, policy_version 41872 (0.0008) -[2023-10-09 01:44:33,336][88326] Updated weights for policy 0, policy_version 41882 (0.0008) -[2023-10-09 01:44:33,974][87372] Fps is (10 sec: 16383.5, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 85786624. Throughput: 0: 1685.9, 1: 1675.0. Samples: 21450776. Policy #0 lag: (min: 31.0, avg: 33.1, max: 62.0) -[2023-10-09 01:44:33,975][87372] Avg episode reward: [(0, '6.200'), (1, '6.370')] -[2023-10-09 01:44:33,989][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000041888_42893312.pth... -[2023-10-09 01:44:33,989][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000041888_42893312.pth... -[2023-10-09 01:44:34,025][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000040288_41254912.pth -[2023-10-09 01:44:34,029][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000040288_41254912.pth -[2023-10-09 01:44:36,655][88327] Updated weights for policy 1, policy_version 41890 (0.0009) -[2023-10-09 01:44:37,010][88327] Updated weights for policy 1, policy_version 41900 (0.0008) -[2023-10-09 01:44:37,290][88326] Updated weights for policy 0, policy_version 41892 (0.0008) -[2023-10-09 01:44:37,377][88327] Updated weights for policy 1, policy_version 41910 (0.0008) -[2023-10-09 01:44:37,665][88326] Updated weights for policy 0, policy_version 41902 (0.0009) -[2023-10-09 01:44:37,738][88327] Updated weights for policy 1, policy_version 41920 (0.0008) -[2023-10-09 01:44:38,031][88326] Updated weights for policy 0, policy_version 41912 (0.0009) -[2023-10-09 01:44:38,974][87372] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 85852160. Throughput: 0: 1703.8, 1: 1702.2. Samples: 21462016. Policy #0 lag: (min: 31.0, avg: 33.1, max: 62.0) -[2023-10-09 01:44:38,975][87372] Avg episode reward: [(0, '6.010'), (1, '6.470')] -[2023-10-09 01:44:41,835][88327] Updated weights for policy 1, policy_version 41930 (0.0008) -[2023-10-09 01:44:42,196][88327] Updated weights for policy 1, policy_version 41940 (0.0008) -[2023-10-09 01:44:42,238][88326] Updated weights for policy 0, policy_version 41922 (0.0008) -[2023-10-09 01:44:42,564][88327] Updated weights for policy 1, policy_version 41950 (0.0008) -[2023-10-09 01:44:42,615][88326] Updated weights for policy 0, policy_version 41932 (0.0008) -[2023-10-09 01:44:42,989][88326] Updated weights for policy 0, policy_version 41942 (0.0010) -[2023-10-09 01:44:43,356][88326] Updated weights for policy 0, policy_version 41952 (0.0011) -[2023-10-09 01:44:43,974][87372] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 85917696. Throughput: 0: 1698.6, 1: 1681.1. Samples: 21481936. Policy #0 lag: (min: 31.0, avg: 33.1, max: 62.0) -[2023-10-09 01:44:43,975][87372] Avg episode reward: [(0, '6.120'), (1, '6.230')] -[2023-10-09 01:44:46,545][88327] Updated weights for policy 1, policy_version 41960 (0.0008) -[2023-10-09 01:44:46,908][88327] Updated weights for policy 1, policy_version 41970 (0.0008) -[2023-10-09 01:44:47,269][88327] Updated weights for policy 1, policy_version 41980 (0.0007) -[2023-10-09 01:44:47,416][88326] Updated weights for policy 0, policy_version 41962 (0.0008) -[2023-10-09 01:44:47,774][88326] Updated weights for policy 0, policy_version 41972 (0.0011) -[2023-10-09 01:44:48,151][88326] Updated weights for policy 0, policy_version 41982 (0.0010) -[2023-10-09 01:44:48,974][87372] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 85983232. Throughput: 0: 1670.6, 1: 1684.0. Samples: 21500914. Policy #0 lag: (min: 31.0, avg: 33.1, max: 62.0) -[2023-10-09 01:44:48,975][87372] Avg episode reward: [(0, '6.160'), (1, '6.070')] -[2023-10-09 01:44:51,561][88327] Updated weights for policy 1, policy_version 41990 (0.0008) -[2023-10-09 01:44:51,922][88327] Updated weights for policy 1, policy_version 42000 (0.0008) -[2023-10-09 01:44:52,287][88327] Updated weights for policy 1, policy_version 42010 (0.0008) -[2023-10-09 01:44:52,322][88326] Updated weights for policy 0, policy_version 41992 (0.0008) -[2023-10-09 01:44:52,692][88326] Updated weights for policy 0, policy_version 42002 (0.0009) -[2023-10-09 01:44:53,062][88326] Updated weights for policy 0, policy_version 42012 (0.0007) -[2023-10-09 01:44:53,974][87372] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 86048768. Throughput: 0: 1694.4, 1: 1692.7. Samples: 21512356. Policy #0 lag: (min: 31.0, avg: 33.1, max: 62.0) -[2023-10-09 01:44:53,975][87372] Avg episode reward: [(0, '6.280'), (1, '5.790')] -[2023-10-09 01:44:56,387][88327] Updated weights for policy 1, policy_version 42020 (0.0008) -[2023-10-09 01:44:56,767][88327] Updated weights for policy 1, policy_version 42030 (0.0007) -[2023-10-09 01:44:57,131][88327] Updated weights for policy 1, policy_version 42040 (0.0010) -[2023-10-09 01:44:57,218][88326] Updated weights for policy 0, policy_version 42022 (0.0007) -[2023-10-09 01:44:57,591][88326] Updated weights for policy 0, policy_version 42032 (0.0008) -[2023-10-09 01:44:57,961][88326] Updated weights for policy 0, policy_version 42042 (0.0009) -[2023-10-09 01:44:58,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 86114304. Throughput: 0: 1684.8, 1: 1672.3. Samples: 21532042. Policy #0 lag: (min: 31.0, avg: 33.1, max: 62.0) -[2023-10-09 01:44:58,975][87372] Avg episode reward: [(0, '6.400'), (1, '5.770')] -[2023-10-09 01:45:00,969][88327] Updated weights for policy 1, policy_version 42050 (0.0007) -[2023-10-09 01:45:01,340][88327] Updated weights for policy 1, policy_version 42060 (0.0009) -[2023-10-09 01:45:01,708][88327] Updated weights for policy 1, policy_version 42070 (0.0009) -[2023-10-09 01:45:01,890][88326] Updated weights for policy 0, policy_version 42052 (0.0008) -[2023-10-09 01:45:02,066][88327] Updated weights for policy 1, policy_version 42080 (0.0009) -[2023-10-09 01:45:02,258][88326] Updated weights for policy 0, policy_version 42062 (0.0008) -[2023-10-09 01:45:02,623][88326] Updated weights for policy 0, policy_version 42072 (0.0009) -[2023-10-09 01:45:03,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 86179840. Throughput: 0: 1664.1, 1: 1690.3. Samples: 21551604. Policy #0 lag: (min: 31.0, avg: 43.0, max: 63.0) -[2023-10-09 01:45:03,975][87372] Avg episode reward: [(0, '6.790'), (1, '5.870')] -[2023-10-09 01:45:06,280][88327] Updated weights for policy 1, policy_version 42090 (0.0009) -[2023-10-09 01:45:06,648][88327] Updated weights for policy 1, policy_version 42100 (0.0009) -[2023-10-09 01:45:06,735][88326] Updated weights for policy 0, policy_version 42082 (0.0010) -[2023-10-09 01:45:07,021][88327] Updated weights for policy 1, policy_version 42110 (0.0008) -[2023-10-09 01:45:07,103][88326] Updated weights for policy 0, policy_version 42092 (0.0008) -[2023-10-09 01:45:07,465][88326] Updated weights for policy 0, policy_version 42102 (0.0008) -[2023-10-09 01:45:07,832][88326] Updated weights for policy 0, policy_version 42112 (0.0008) -[2023-10-09 01:45:08,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 86245376. Throughput: 0: 1693.2, 1: 1686.7. Samples: 21563024. Policy #0 lag: (min: 31.0, avg: 43.0, max: 63.0) -[2023-10-09 01:45:08,975][87372] Avg episode reward: [(0, '6.170'), (1, '6.200')] -[2023-10-09 01:45:11,173][88327] Updated weights for policy 1, policy_version 42120 (0.0010) -[2023-10-09 01:45:11,543][88327] Updated weights for policy 1, policy_version 42130 (0.0010) -[2023-10-09 01:45:11,908][88327] Updated weights for policy 1, policy_version 42140 (0.0008) -[2023-10-09 01:45:12,022][88326] Updated weights for policy 0, policy_version 42122 (0.0010) -[2023-10-09 01:45:12,390][88326] Updated weights for policy 0, policy_version 42132 (0.0007) -[2023-10-09 01:45:12,764][88326] Updated weights for policy 0, policy_version 42142 (0.0008) -[2023-10-09 01:45:13,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 86310912. Throughput: 0: 1666.5, 1: 1666.8. Samples: 21581758. Policy #0 lag: (min: 31.0, avg: 43.0, max: 63.0) -[2023-10-09 01:45:13,975][87372] Avg episode reward: [(0, '6.590'), (1, '6.240')] -[2023-10-09 01:45:15,883][88327] Updated weights for policy 1, policy_version 42150 (0.0007) -[2023-10-09 01:45:16,247][88327] Updated weights for policy 1, policy_version 42160 (0.0007) -[2023-10-09 01:45:16,602][88327] Updated weights for policy 1, policy_version 42170 (0.0008) -[2023-10-09 01:45:16,724][88326] Updated weights for policy 0, policy_version 42152 (0.0008) -[2023-10-09 01:45:17,090][88326] Updated weights for policy 0, policy_version 42162 (0.0010) -[2023-10-09 01:45:17,449][88326] Updated weights for policy 0, policy_version 42172 (0.0011) -[2023-10-09 01:45:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 86376448. Throughput: 0: 1669.0, 1: 1692.6. Samples: 21602048. Policy #0 lag: (min: 31.0, avg: 43.0, max: 63.0) -[2023-10-09 01:45:18,975][87372] Avg episode reward: [(0, '6.040'), (1, '6.190')] -[2023-10-09 01:45:20,719][88327] Updated weights for policy 1, policy_version 42180 (0.0009) -[2023-10-09 01:45:21,084][88327] Updated weights for policy 1, policy_version 42190 (0.0008) -[2023-10-09 01:45:21,379][88326] Updated weights for policy 0, policy_version 42182 (0.0008) -[2023-10-09 01:45:21,444][88327] Updated weights for policy 1, policy_version 42200 (0.0007) -[2023-10-09 01:45:21,748][88326] Updated weights for policy 0, policy_version 42192 (0.0008) -[2023-10-09 01:45:22,121][88326] Updated weights for policy 0, policy_version 42202 (0.0010) -[2023-10-09 01:45:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 86441984. Throughput: 0: 1682.0, 1: 1678.9. Samples: 21613256. Policy #0 lag: (min: 31.0, avg: 43.0, max: 63.0) -[2023-10-09 01:45:23,975][87372] Avg episode reward: [(0, '5.770'), (1, '6.100')] -[2023-10-09 01:45:25,384][88327] Updated weights for policy 1, policy_version 42210 (0.0007) -[2023-10-09 01:45:25,750][88327] Updated weights for policy 1, policy_version 42220 (0.0008) -[2023-10-09 01:45:26,111][88327] Updated weights for policy 1, policy_version 42230 (0.0008) -[2023-10-09 01:45:26,193][88326] Updated weights for policy 0, policy_version 42212 (0.0008) -[2023-10-09 01:45:26,471][88327] Updated weights for policy 1, policy_version 42240 (0.0008) -[2023-10-09 01:45:26,556][88326] Updated weights for policy 0, policy_version 42222 (0.0009) -[2023-10-09 01:45:26,921][88326] Updated weights for policy 0, policy_version 42232 (0.0008) -[2023-10-09 01:45:28,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 86507520. Throughput: 0: 1659.8, 1: 1682.6. Samples: 21632344. Policy #0 lag: (min: 31.0, avg: 43.0, max: 63.0) -[2023-10-09 01:45:28,975][87372] Avg episode reward: [(0, '6.950'), (1, '6.300')] -[2023-10-09 01:45:30,607][88327] Updated weights for policy 1, policy_version 42250 (0.0010) -[2023-10-09 01:45:30,836][88326] Updated weights for policy 0, policy_version 42242 (0.0011) -[2023-10-09 01:45:30,968][88327] Updated weights for policy 1, policy_version 42260 (0.0008) -[2023-10-09 01:45:31,208][88326] Updated weights for policy 0, policy_version 42252 (0.0009) -[2023-10-09 01:45:31,329][88327] Updated weights for policy 1, policy_version 42270 (0.0008) -[2023-10-09 01:45:31,564][88326] Updated weights for policy 0, policy_version 42262 (0.0009) -[2023-10-09 01:45:31,940][88326] Updated weights for policy 0, policy_version 42272 (0.0009) -[2023-10-09 01:45:33,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 86573056. Throughput: 0: 1688.8, 1: 1697.1. Samples: 21653280. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:45:33,975][87372] Avg episode reward: [(0, '6.190'), (1, '6.180')] -[2023-10-09 01:45:35,240][88327] Updated weights for policy 1, policy_version 42280 (0.0007) -[2023-10-09 01:45:35,594][88327] Updated weights for policy 1, policy_version 42290 (0.0009) -[2023-10-09 01:45:35,963][88327] Updated weights for policy 1, policy_version 42300 (0.0007) -[2023-10-09 01:45:36,071][88326] Updated weights for policy 0, policy_version 42282 (0.0008) -[2023-10-09 01:45:36,435][88326] Updated weights for policy 0, policy_version 42292 (0.0009) -[2023-10-09 01:45:36,808][88326] Updated weights for policy 0, policy_version 42302 (0.0008) -[2023-10-09 01:45:38,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 86638592. Throughput: 0: 1682.1, 1: 1673.5. Samples: 21663356. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:45:38,974][87372] Avg episode reward: [(0, '6.420'), (1, '6.180')] -[2023-10-09 01:45:39,998][88327] Updated weights for policy 1, policy_version 42310 (0.0009) -[2023-10-09 01:45:40,359][88327] Updated weights for policy 1, policy_version 42320 (0.0010) -[2023-10-09 01:45:40,725][88327] Updated weights for policy 1, policy_version 42330 (0.0008) -[2023-10-09 01:45:40,834][88326] Updated weights for policy 0, policy_version 42312 (0.0009) -[2023-10-09 01:45:41,197][88326] Updated weights for policy 0, policy_version 42322 (0.0009) -[2023-10-09 01:45:41,567][88326] Updated weights for policy 0, policy_version 42332 (0.0009) -[2023-10-09 01:45:43,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 86704128. Throughput: 0: 1673.8, 1: 1693.7. Samples: 21683580. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:45:43,976][87372] Avg episode reward: [(0, '6.710'), (1, '6.930')] -[2023-10-09 01:45:43,978][88168] Saving new best policy, reward=6.930! -[2023-10-09 01:45:44,667][88327] Updated weights for policy 1, policy_version 42340 (0.0008) -[2023-10-09 01:45:45,033][88327] Updated weights for policy 1, policy_version 42350 (0.0008) -[2023-10-09 01:45:45,397][88327] Updated weights for policy 1, policy_version 42360 (0.0009) -[2023-10-09 01:45:45,803][88326] Updated weights for policy 0, policy_version 42342 (0.0011) -[2023-10-09 01:45:46,166][88326] Updated weights for policy 0, policy_version 42352 (0.0008) -[2023-10-09 01:45:46,542][88326] Updated weights for policy 0, policy_version 42362 (0.0007) -[2023-10-09 01:45:48,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 86769664. Throughput: 0: 1698.5, 1: 1700.6. Samples: 21704564. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:45:48,975][87372] Avg episode reward: [(0, '6.160'), (1, '6.120')] -[2023-10-09 01:45:49,356][88327] Updated weights for policy 1, policy_version 42370 (0.0009) -[2023-10-09 01:45:49,719][88327] Updated weights for policy 1, policy_version 42380 (0.0008) -[2023-10-09 01:45:50,074][88327] Updated weights for policy 1, policy_version 42390 (0.0007) -[2023-10-09 01:45:50,435][88327] Updated weights for policy 1, policy_version 42400 (0.0008) -[2023-10-09 01:45:50,519][88326] Updated weights for policy 0, policy_version 42372 (0.0009) -[2023-10-09 01:45:50,882][88326] Updated weights for policy 0, policy_version 42382 (0.0009) -[2023-10-09 01:45:51,257][88326] Updated weights for policy 0, policy_version 42392 (0.0009) -[2023-10-09 01:45:53,974][87372] Fps is (10 sec: 13107.7, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 86835200. Throughput: 0: 1675.6, 1: 1683.5. Samples: 21714180. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:45:53,974][87372] Avg episode reward: [(0, '6.570'), (1, '5.880')] -[2023-10-09 01:45:54,652][88327] Updated weights for policy 1, policy_version 42410 (0.0010) -[2023-10-09 01:45:55,029][88327] Updated weights for policy 1, policy_version 42420 (0.0009) -[2023-10-09 01:45:55,378][88326] Updated weights for policy 0, policy_version 42402 (0.0008) -[2023-10-09 01:45:55,398][88327] Updated weights for policy 1, policy_version 42430 (0.0007) -[2023-10-09 01:45:55,750][88326] Updated weights for policy 0, policy_version 42412 (0.0008) -[2023-10-09 01:45:56,121][88326] Updated weights for policy 0, policy_version 42422 (0.0008) -[2023-10-09 01:45:56,492][88326] Updated weights for policy 0, policy_version 42432 (0.0008) -[2023-10-09 01:45:58,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 86900736. Throughput: 0: 1691.3, 1: 1704.1. Samples: 21734552. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:45:58,975][87372] Avg episode reward: [(0, '6.130'), (1, '6.550')] -[2023-10-09 01:45:59,390][88327] Updated weights for policy 1, policy_version 42440 (0.0007) -[2023-10-09 01:45:59,748][88327] Updated weights for policy 1, policy_version 42450 (0.0008) -[2023-10-09 01:46:00,109][88327] Updated weights for policy 1, policy_version 42460 (0.0007) -[2023-10-09 01:46:00,335][88326] Updated weights for policy 0, policy_version 42442 (0.0011) -[2023-10-09 01:46:00,701][88326] Updated weights for policy 0, policy_version 42452 (0.0011) -[2023-10-09 01:46:01,074][88326] Updated weights for policy 0, policy_version 42462 (0.0008) -[2023-10-09 01:46:03,974][87372] Fps is (10 sec: 13106.7, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 86966272. Throughput: 0: 1705.1, 1: 1704.0. Samples: 21755458. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:46:03,975][87372] Avg episode reward: [(0, '5.820'), (1, '5.710')] -[2023-10-09 01:46:04,123][88327] Updated weights for policy 1, policy_version 42470 (0.0007) -[2023-10-09 01:46:04,487][88327] Updated weights for policy 1, policy_version 42480 (0.0010) -[2023-10-09 01:46:04,852][88327] Updated weights for policy 1, policy_version 42490 (0.0011) -[2023-10-09 01:46:05,118][88326] Updated weights for policy 0, policy_version 42472 (0.0008) -[2023-10-09 01:46:05,489][88326] Updated weights for policy 0, policy_version 42482 (0.0007) -[2023-10-09 01:46:05,865][88326] Updated weights for policy 0, policy_version 42492 (0.0010) -[2023-10-09 01:46:08,880][88327] Updated weights for policy 1, policy_version 42500 (0.0008) -[2023-10-09 01:46:08,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 87031808. Throughput: 0: 1672.1, 1: 1688.6. Samples: 21764490. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:46:08,975][87372] Avg episode reward: [(0, '6.300'), (1, '5.830')] -[2023-10-09 01:46:09,255][88327] Updated weights for policy 1, policy_version 42510 (0.0009) -[2023-10-09 01:46:09,624][88327] Updated weights for policy 1, policy_version 42520 (0.0008) -[2023-10-09 01:46:09,882][88326] Updated weights for policy 0, policy_version 42502 (0.0009) -[2023-10-09 01:46:10,256][88326] Updated weights for policy 0, policy_version 42512 (0.0011) -[2023-10-09 01:46:10,622][88326] Updated weights for policy 0, policy_version 42522 (0.0008) -[2023-10-09 01:46:13,611][88327] Updated weights for policy 1, policy_version 42530 (0.0007) -[2023-10-09 01:46:13,974][87372] Fps is (10 sec: 13107.7, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 87097344. Throughput: 0: 1696.8, 1: 1703.4. Samples: 21785354. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:46:13,974][87372] Avg episode reward: [(0, '6.240'), (1, '6.130')] -[2023-10-09 01:46:13,976][88327] Updated weights for policy 1, policy_version 42540 (0.0009) -[2023-10-09 01:46:14,349][88327] Updated weights for policy 1, policy_version 42550 (0.0009) -[2023-10-09 01:46:14,717][88327] Updated weights for policy 1, policy_version 42560 (0.0008) -[2023-10-09 01:46:14,799][88326] Updated weights for policy 0, policy_version 42532 (0.0009) -[2023-10-09 01:46:15,164][88326] Updated weights for policy 0, policy_version 42542 (0.0007) -[2023-10-09 01:46:15,530][88326] Updated weights for policy 0, policy_version 42552 (0.0008) -[2023-10-09 01:46:18,893][88327] Updated weights for policy 1, policy_version 42570 (0.0009) -[2023-10-09 01:46:18,975][87372] Fps is (10 sec: 13106.8, 60 sec: 13107.1, 300 sec: 13440.4). Total num frames: 87162880. Throughput: 0: 1700.4, 1: 1700.2. Samples: 21806308. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:46:18,976][87372] Avg episode reward: [(0, '6.190'), (1, '6.110')] -[2023-10-09 01:46:19,261][88327] Updated weights for policy 1, policy_version 42580 (0.0010) -[2023-10-09 01:46:19,579][88326] Updated weights for policy 0, policy_version 42562 (0.0008) -[2023-10-09 01:46:19,626][88327] Updated weights for policy 1, policy_version 42590 (0.0008) -[2023-10-09 01:46:19,945][88326] Updated weights for policy 0, policy_version 42572 (0.0009) -[2023-10-09 01:46:20,322][88326] Updated weights for policy 0, policy_version 42582 (0.0008) -[2023-10-09 01:46:20,682][88326] Updated weights for policy 0, policy_version 42592 (0.0008) -[2023-10-09 01:46:23,668][88327] Updated weights for policy 1, policy_version 42600 (0.0009) -[2023-10-09 01:46:23,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 87228416. Throughput: 0: 1682.7, 1: 1697.2. Samples: 21815454. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:46:23,975][87372] Avg episode reward: [(0, '6.270'), (1, '6.200')] -[2023-10-09 01:46:24,037][88327] Updated weights for policy 1, policy_version 42610 (0.0008) -[2023-10-09 01:46:24,405][88327] Updated weights for policy 1, policy_version 42620 (0.0009) -[2023-10-09 01:46:24,569][88326] Updated weights for policy 0, policy_version 42602 (0.0007) -[2023-10-09 01:46:24,937][88326] Updated weights for policy 0, policy_version 42612 (0.0008) -[2023-10-09 01:46:25,318][88326] Updated weights for policy 0, policy_version 42622 (0.0008) -[2023-10-09 01:46:28,630][88327] Updated weights for policy 1, policy_version 42630 (0.0008) -[2023-10-09 01:46:28,974][87372] Fps is (10 sec: 13107.8, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 87293952. Throughput: 0: 1702.7, 1: 1695.8. Samples: 21836514. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:46:28,975][87372] Avg episode reward: [(0, '5.990'), (1, '5.820')] -[2023-10-09 01:46:28,994][88327] Updated weights for policy 1, policy_version 42640 (0.0009) -[2023-10-09 01:46:29,291][88326] Updated weights for policy 0, policy_version 42632 (0.0008) -[2023-10-09 01:46:29,355][88327] Updated weights for policy 1, policy_version 42650 (0.0007) -[2023-10-09 01:46:29,657][88326] Updated weights for policy 0, policy_version 42642 (0.0010) -[2023-10-09 01:46:30,036][88326] Updated weights for policy 0, policy_version 42652 (0.0008) -[2023-10-09 01:46:33,298][88327] Updated weights for policy 1, policy_version 42660 (0.0009) -[2023-10-09 01:46:33,662][88327] Updated weights for policy 1, policy_version 42670 (0.0010) -[2023-10-09 01:46:33,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 87359488. Throughput: 0: 1702.0, 1: 1689.9. Samples: 21857200. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:46:33,975][87372] Avg episode reward: [(0, '6.130'), (1, '6.430')] -[2023-10-09 01:46:34,023][88327] Updated weights for policy 1, policy_version 42680 (0.0010) -[2023-10-09 01:46:34,068][88326] Updated weights for policy 0, policy_version 42662 (0.0007) -[2023-10-09 01:46:34,316][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000042688_43712512.pth... -[2023-10-09 01:46:34,349][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000041088_42074112.pth -[2023-10-09 01:46:34,432][88326] Updated weights for policy 0, policy_version 42672 (0.0009) -[2023-10-09 01:46:34,794][88326] Updated weights for policy 0, policy_version 42682 (0.0008) -[2023-10-09 01:46:35,014][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000042688_43712512.pth... -[2023-10-09 01:46:35,055][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000041088_42074112.pth -[2023-10-09 01:46:37,995][88327] Updated weights for policy 1, policy_version 42690 (0.0009) -[2023-10-09 01:46:38,356][88327] Updated weights for policy 1, policy_version 42700 (0.0009) -[2023-10-09 01:46:38,726][88327] Updated weights for policy 1, policy_version 42710 (0.0007) -[2023-10-09 01:46:38,785][88326] Updated weights for policy 0, policy_version 42692 (0.0007) -[2023-10-09 01:46:38,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 87425024. Throughput: 0: 1690.9, 1: 1690.8. Samples: 21866358. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:46:38,974][87372] Avg episode reward: [(0, '6.570'), (1, '5.860')] -[2023-10-09 01:46:39,083][88327] Updated weights for policy 1, policy_version 42720 (0.0009) -[2023-10-09 01:46:39,163][88326] Updated weights for policy 0, policy_version 42702 (0.0010) -[2023-10-09 01:46:39,520][88326] Updated weights for policy 0, policy_version 42712 (0.0008) -[2023-10-09 01:46:42,992][88327] Updated weights for policy 1, policy_version 42730 (0.0007) -[2023-10-09 01:46:43,352][88327] Updated weights for policy 1, policy_version 42740 (0.0007) -[2023-10-09 01:46:43,543][88326] Updated weights for policy 0, policy_version 42722 (0.0007) -[2023-10-09 01:46:43,725][88327] Updated weights for policy 1, policy_version 42750 (0.0007) -[2023-10-09 01:46:43,910][88326] Updated weights for policy 0, policy_version 42732 (0.0007) -[2023-10-09 01:46:43,974][87372] Fps is (10 sec: 16383.9, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 87523328. Throughput: 0: 1697.0, 1: 1702.5. Samples: 21887526. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:46:43,975][87372] Avg episode reward: [(0, '6.330'), (1, '6.070')] -[2023-10-09 01:46:44,276][88326] Updated weights for policy 0, policy_version 42742 (0.0007) -[2023-10-09 01:46:44,645][88326] Updated weights for policy 0, policy_version 42752 (0.0007) -[2023-10-09 01:46:47,861][88327] Updated weights for policy 1, policy_version 42760 (0.0010) -[2023-10-09 01:46:48,238][88327] Updated weights for policy 1, policy_version 42770 (0.0007) -[2023-10-09 01:46:48,603][88327] Updated weights for policy 1, policy_version 42780 (0.0007) -[2023-10-09 01:46:48,885][88326] Updated weights for policy 0, policy_version 42762 (0.0008) -[2023-10-09 01:46:48,974][87372] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 87588864. Throughput: 0: 1698.8, 1: 1682.1. Samples: 21907594. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:46:48,974][87372] Avg episode reward: [(0, '6.070'), (1, '6.160')] -[2023-10-09 01:46:49,255][88326] Updated weights for policy 0, policy_version 42772 (0.0010) -[2023-10-09 01:46:49,620][88326] Updated weights for policy 0, policy_version 42782 (0.0010) -[2023-10-09 01:46:52,697][88327] Updated weights for policy 1, policy_version 42790 (0.0009) -[2023-10-09 01:46:53,065][88327] Updated weights for policy 1, policy_version 42800 (0.0008) -[2023-10-09 01:46:53,432][88327] Updated weights for policy 1, policy_version 42810 (0.0010) -[2023-10-09 01:46:53,776][88326] Updated weights for policy 0, policy_version 42792 (0.0008) -[2023-10-09 01:46:53,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 87654400. Throughput: 0: 1691.2, 1: 1697.6. Samples: 21916986. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:46:53,975][87372] Avg episode reward: [(0, '6.070'), (1, '5.520')] -[2023-10-09 01:46:54,145][88326] Updated weights for policy 0, policy_version 42802 (0.0008) -[2023-10-09 01:46:54,514][88326] Updated weights for policy 0, policy_version 42812 (0.0009) -[2023-10-09 01:46:57,103][88327] Updated weights for policy 1, policy_version 42820 (0.0009) -[2023-10-09 01:46:57,458][88327] Updated weights for policy 1, policy_version 42830 (0.0007) -[2023-10-09 01:46:57,825][88327] Updated weights for policy 1, policy_version 42840 (0.0011) -[2023-10-09 01:46:58,582][88326] Updated weights for policy 0, policy_version 42822 (0.0008) -[2023-10-09 01:46:58,961][88326] Updated weights for policy 0, policy_version 42832 (0.0007) -[2023-10-09 01:46:58,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 87719936. Throughput: 0: 1694.2, 1: 1698.9. Samples: 21938044. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:46:58,975][87372] Avg episode reward: [(0, '6.610'), (1, '5.970')] -[2023-10-09 01:46:59,336][88326] Updated weights for policy 0, policy_version 42842 (0.0009) -[2023-10-09 01:47:01,917][88327] Updated weights for policy 1, policy_version 42850 (0.0010) -[2023-10-09 01:47:02,274][88327] Updated weights for policy 1, policy_version 42860 (0.0010) -[2023-10-09 01:47:02,633][88327] Updated weights for policy 1, policy_version 42870 (0.0012) -[2023-10-09 01:47:02,999][88327] Updated weights for policy 1, policy_version 42880 (0.0010) -[2023-10-09 01:47:03,333][88326] Updated weights for policy 0, policy_version 42852 (0.0009) -[2023-10-09 01:47:03,714][88326] Updated weights for policy 0, policy_version 42862 (0.0009) -[2023-10-09 01:47:03,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 87785472. Throughput: 0: 1688.7, 1: 1677.4. Samples: 21957782. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-09 01:47:03,974][87372] Avg episode reward: [(0, '6.690'), (1, '5.610')] -[2023-10-09 01:47:04,088][88326] Updated weights for policy 0, policy_version 42872 (0.0010) -[2023-10-09 01:47:07,071][88327] Updated weights for policy 1, policy_version 42890 (0.0011) -[2023-10-09 01:47:07,436][88327] Updated weights for policy 1, policy_version 42900 (0.0012) -[2023-10-09 01:47:07,805][88327] Updated weights for policy 1, policy_version 42910 (0.0009) -[2023-10-09 01:47:08,017][88326] Updated weights for policy 0, policy_version 42882 (0.0009) -[2023-10-09 01:47:08,377][88326] Updated weights for policy 0, policy_version 42892 (0.0008) -[2023-10-09 01:47:08,747][88326] Updated weights for policy 0, policy_version 42902 (0.0008) -[2023-10-09 01:47:08,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 87851008. Throughput: 0: 1687.8, 1: 1709.8. Samples: 21968344. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-09 01:47:08,975][87372] Avg episode reward: [(0, '6.480'), (1, '5.660')] -[2023-10-09 01:47:09,107][88326] Updated weights for policy 0, policy_version 42912 (0.0009) -[2023-10-09 01:47:11,914][88327] Updated weights for policy 1, policy_version 42920 (0.0008) -[2023-10-09 01:47:12,285][88327] Updated weights for policy 1, policy_version 42930 (0.0007) -[2023-10-09 01:47:12,662][88327] Updated weights for policy 1, policy_version 42940 (0.0008) -[2023-10-09 01:47:13,295][88326] Updated weights for policy 0, policy_version 42922 (0.0008) -[2023-10-09 01:47:13,671][88326] Updated weights for policy 0, policy_version 42932 (0.0007) -[2023-10-09 01:47:13,974][87372] Fps is (10 sec: 13106.7, 60 sec: 13653.2, 300 sec: 13440.4). Total num frames: 87916544. Throughput: 0: 1684.8, 1: 1695.9. Samples: 21988648. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-09 01:47:13,976][87372] Avg episode reward: [(0, '6.760'), (1, '5.420')] -[2023-10-09 01:47:14,043][88326] Updated weights for policy 0, policy_version 42942 (0.0008) -[2023-10-09 01:47:16,651][88327] Updated weights for policy 1, policy_version 42950 (0.0008) -[2023-10-09 01:47:17,005][88327] Updated weights for policy 1, policy_version 42960 (0.0010) -[2023-10-09 01:47:17,371][88327] Updated weights for policy 1, policy_version 42970 (0.0010) -[2023-10-09 01:47:17,951][88326] Updated weights for policy 0, policy_version 42952 (0.0009) -[2023-10-09 01:47:18,319][88326] Updated weights for policy 0, policy_version 42962 (0.0008) -[2023-10-09 01:47:18,679][88326] Updated weights for policy 0, policy_version 42972 (0.0008) -[2023-10-09 01:47:18,974][87372] Fps is (10 sec: 16384.2, 60 sec: 14199.6, 300 sec: 13551.5). Total num frames: 88014848. Throughput: 0: 1676.8, 1: 1682.8. Samples: 22008382. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-09 01:47:18,975][87372] Avg episode reward: [(0, '5.920'), (1, '5.490')] -[2023-10-09 01:47:21,524][88327] Updated weights for policy 1, policy_version 42980 (0.0007) -[2023-10-09 01:47:21,885][88327] Updated weights for policy 1, policy_version 42990 (0.0007) -[2023-10-09 01:47:22,239][88327] Updated weights for policy 1, policy_version 43000 (0.0007) -[2023-10-09 01:47:22,853][88326] Updated weights for policy 0, policy_version 42982 (0.0009) -[2023-10-09 01:47:23,223][88326] Updated weights for policy 0, policy_version 42992 (0.0008) -[2023-10-09 01:47:23,601][88326] Updated weights for policy 0, policy_version 43002 (0.0008) -[2023-10-09 01:47:23,974][87372] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 88080384. Throughput: 0: 1692.2, 1: 1706.3. Samples: 22019290. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-09 01:47:23,975][87372] Avg episode reward: [(0, '5.630'), (1, '5.880')] -[2023-10-09 01:47:26,156][88327] Updated weights for policy 1, policy_version 43010 (0.0007) -[2023-10-09 01:47:26,523][88327] Updated weights for policy 1, policy_version 43020 (0.0009) -[2023-10-09 01:47:26,883][88327] Updated weights for policy 1, policy_version 43030 (0.0010) -[2023-10-09 01:47:27,244][88327] Updated weights for policy 1, policy_version 43040 (0.0011) -[2023-10-09 01:47:27,600][88326] Updated weights for policy 0, policy_version 43012 (0.0010) -[2023-10-09 01:47:27,967][88326] Updated weights for policy 0, policy_version 43022 (0.0010) -[2023-10-09 01:47:28,334][88326] Updated weights for policy 0, policy_version 43032 (0.0007) -[2023-10-09 01:47:28,974][87372] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 88145920. Throughput: 0: 1692.2, 1: 1678.4. Samples: 22039206. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-09 01:47:28,975][87372] Avg episode reward: [(0, '6.280'), (1, '5.460')] -[2023-10-09 01:47:31,410][88327] Updated weights for policy 1, policy_version 43050 (0.0009) -[2023-10-09 01:47:31,777][88327] Updated weights for policy 1, policy_version 43060 (0.0010) -[2023-10-09 01:47:32,147][88327] Updated weights for policy 1, policy_version 43070 (0.0008) -[2023-10-09 01:47:32,282][88326] Updated weights for policy 0, policy_version 43042 (0.0009) -[2023-10-09 01:47:32,660][88326] Updated weights for policy 0, policy_version 43052 (0.0010) -[2023-10-09 01:47:33,033][88326] Updated weights for policy 0, policy_version 43062 (0.0008) -[2023-10-09 01:47:33,395][88326] Updated weights for policy 0, policy_version 43072 (0.0009) -[2023-10-09 01:47:33,974][87372] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 88211456. Throughput: 0: 1673.1, 1: 1691.9. Samples: 22059020. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-09 01:47:33,975][87372] Avg episode reward: [(0, '5.960'), (1, '5.680')] -[2023-10-09 01:47:35,898][88327] Updated weights for policy 1, policy_version 43080 (0.0008) -[2023-10-09 01:47:36,271][88327] Updated weights for policy 1, policy_version 43090 (0.0009) -[2023-10-09 01:47:36,646][88327] Updated weights for policy 1, policy_version 43100 (0.0008) -[2023-10-09 01:47:37,560][88326] Updated weights for policy 0, policy_version 43082 (0.0008) -[2023-10-09 01:47:37,925][88326] Updated weights for policy 0, policy_version 43092 (0.0008) -[2023-10-09 01:47:38,298][88326] Updated weights for policy 0, policy_version 43102 (0.0010) -[2023-10-09 01:47:38,974][87372] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 88276992. Throughput: 0: 1702.1, 1: 1695.9. Samples: 22069896. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-09 01:47:38,975][87372] Avg episode reward: [(0, '5.830'), (1, '5.920')] -[2023-10-09 01:47:40,775][88327] Updated weights for policy 1, policy_version 43110 (0.0007) -[2023-10-09 01:47:41,132][88327] Updated weights for policy 1, policy_version 43120 (0.0010) -[2023-10-09 01:47:41,511][88327] Updated weights for policy 1, policy_version 43130 (0.0009) -[2023-10-09 01:47:42,383][88326] Updated weights for policy 0, policy_version 43112 (0.0011) -[2023-10-09 01:47:42,741][88326] Updated weights for policy 0, policy_version 43122 (0.0010) -[2023-10-09 01:47:43,107][88326] Updated weights for policy 0, policy_version 43132 (0.0010) -[2023-10-09 01:47:43,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 88342528. Throughput: 0: 1690.7, 1: 1672.6. Samples: 22089392. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-09 01:47:43,975][87372] Avg episode reward: [(0, '6.400'), (1, '6.270')] -[2023-10-09 01:47:45,490][88327] Updated weights for policy 1, policy_version 43140 (0.0010) -[2023-10-09 01:47:45,842][88327] Updated weights for policy 1, policy_version 43150 (0.0011) -[2023-10-09 01:47:46,206][88327] Updated weights for policy 1, policy_version 43160 (0.0010) -[2023-10-09 01:47:47,285][88326] Updated weights for policy 0, policy_version 43142 (0.0011) -[2023-10-09 01:47:47,657][88326] Updated weights for policy 0, policy_version 43152 (0.0010) -[2023-10-09 01:47:48,020][88326] Updated weights for policy 0, policy_version 43162 (0.0009) -[2023-10-09 01:47:48,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 88408064. Throughput: 0: 1666.4, 1: 1698.8. Samples: 22109220. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-09 01:47:48,975][87372] Avg episode reward: [(0, '6.360'), (1, '6.350')] -[2023-10-09 01:47:50,295][88327] Updated weights for policy 1, policy_version 43170 (0.0009) -[2023-10-09 01:47:50,666][88327] Updated weights for policy 1, policy_version 43180 (0.0011) -[2023-10-09 01:47:51,040][88327] Updated weights for policy 1, policy_version 43190 (0.0008) -[2023-10-09 01:47:51,399][88327] Updated weights for policy 1, policy_version 43200 (0.0008) -[2023-10-09 01:47:52,079][88326] Updated weights for policy 0, policy_version 43172 (0.0008) -[2023-10-09 01:47:52,456][88326] Updated weights for policy 0, policy_version 43182 (0.0009) -[2023-10-09 01:47:52,821][88326] Updated weights for policy 0, policy_version 43192 (0.0009) -[2023-10-09 01:47:53,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 88473600. Throughput: 0: 1690.3, 1: 1676.9. Samples: 22119868. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-09 01:47:53,975][87372] Avg episode reward: [(0, '6.280'), (1, '6.290')] -[2023-10-09 01:47:55,314][88327] Updated weights for policy 1, policy_version 43210 (0.0009) -[2023-10-09 01:47:55,689][88327] Updated weights for policy 1, policy_version 43220 (0.0009) -[2023-10-09 01:47:56,048][88327] Updated weights for policy 1, policy_version 43230 (0.0009) -[2023-10-09 01:47:56,862][88326] Updated weights for policy 0, policy_version 43202 (0.0008) -[2023-10-09 01:47:57,241][88326] Updated weights for policy 0, policy_version 43212 (0.0007) -[2023-10-09 01:47:57,603][88326] Updated weights for policy 0, policy_version 43222 (0.0009) -[2023-10-09 01:47:57,975][88326] Updated weights for policy 0, policy_version 43232 (0.0008) -[2023-10-09 01:47:58,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 88539136. Throughput: 0: 1678.8, 1: 1688.1. Samples: 22140158. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-09 01:47:58,975][87372] Avg episode reward: [(0, '6.400'), (1, '5.760')] -[2023-10-09 01:47:59,951][88327] Updated weights for policy 1, policy_version 43240 (0.0009) -[2023-10-09 01:48:00,313][88327] Updated weights for policy 1, policy_version 43250 (0.0008) -[2023-10-09 01:48:00,670][88327] Updated weights for policy 1, policy_version 43260 (0.0008) -[2023-10-09 01:48:01,963][88326] Updated weights for policy 0, policy_version 43242 (0.0007) -[2023-10-09 01:48:02,338][88326] Updated weights for policy 0, policy_version 43252 (0.0007) -[2023-10-09 01:48:02,716][88326] Updated weights for policy 0, policy_version 43262 (0.0010) -[2023-10-09 01:48:03,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 88604672. Throughput: 0: 1671.4, 1: 1710.4. Samples: 22160560. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-09 01:48:03,974][87372] Avg episode reward: [(0, '6.590'), (1, '5.870')] -[2023-10-09 01:48:04,602][88327] Updated weights for policy 1, policy_version 43270 (0.0009) -[2023-10-09 01:48:04,960][88327] Updated weights for policy 1, policy_version 43280 (0.0007) -[2023-10-09 01:48:05,327][88327] Updated weights for policy 1, policy_version 43290 (0.0007) -[2023-10-09 01:48:06,712][88326] Updated weights for policy 0, policy_version 43272 (0.0007) -[2023-10-09 01:48:07,070][88326] Updated weights for policy 0, policy_version 43282 (0.0008) -[2023-10-09 01:48:07,440][88326] Updated weights for policy 0, policy_version 43292 (0.0011) -[2023-10-09 01:48:08,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 88670208. Throughput: 0: 1688.9, 1: 1683.9. Samples: 22171064. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-09 01:48:08,975][87372] Avg episode reward: [(0, '6.170'), (1, '6.390')] -[2023-10-09 01:48:09,424][88327] Updated weights for policy 1, policy_version 43300 (0.0010) -[2023-10-09 01:48:09,795][88327] Updated weights for policy 1, policy_version 43310 (0.0009) -[2023-10-09 01:48:10,161][88327] Updated weights for policy 1, policy_version 43320 (0.0009) -[2023-10-09 01:48:11,472][88326] Updated weights for policy 0, policy_version 43302 (0.0010) -[2023-10-09 01:48:11,843][88326] Updated weights for policy 0, policy_version 43312 (0.0009) -[2023-10-09 01:48:12,208][88326] Updated weights for policy 0, policy_version 43322 (0.0007) -[2023-10-09 01:48:13,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 88735744. Throughput: 0: 1662.8, 1: 1708.4. Samples: 22190906. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-09 01:48:13,975][87372] Avg episode reward: [(0, '6.130'), (1, '5.880')] -[2023-10-09 01:48:14,095][88327] Updated weights for policy 1, policy_version 43330 (0.0011) -[2023-10-09 01:48:14,466][88327] Updated weights for policy 1, policy_version 43340 (0.0009) -[2023-10-09 01:48:14,828][88327] Updated weights for policy 1, policy_version 43350 (0.0009) -[2023-10-09 01:48:15,190][88327] Updated weights for policy 1, policy_version 43360 (0.0007) -[2023-10-09 01:48:16,092][88326] Updated weights for policy 0, policy_version 43332 (0.0009) -[2023-10-09 01:48:16,456][88326] Updated weights for policy 0, policy_version 43342 (0.0011) -[2023-10-09 01:48:16,818][88326] Updated weights for policy 0, policy_version 43352 (0.0010) -[2023-10-09 01:48:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 88801280. Throughput: 0: 1673.8, 1: 1714.9. Samples: 22211514. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-09 01:48:18,975][87372] Avg episode reward: [(0, '6.500'), (1, '6.270')] -[2023-10-09 01:48:19,278][88327] Updated weights for policy 1, policy_version 43370 (0.0007) -[2023-10-09 01:48:19,651][88327] Updated weights for policy 1, policy_version 43380 (0.0007) -[2023-10-09 01:48:20,013][88327] Updated weights for policy 1, policy_version 43390 (0.0008) -[2023-10-09 01:48:21,081][88326] Updated weights for policy 0, policy_version 43362 (0.0008) -[2023-10-09 01:48:21,446][88326] Updated weights for policy 0, policy_version 43372 (0.0007) -[2023-10-09 01:48:21,814][88326] Updated weights for policy 0, policy_version 43382 (0.0008) -[2023-10-09 01:48:22,189][88326] Updated weights for policy 0, policy_version 43392 (0.0009) -[2023-10-09 01:48:23,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 88866816. Throughput: 0: 1674.9, 1: 1690.4. Samples: 22221338. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-09 01:48:23,975][87372] Avg episode reward: [(0, '6.680'), (1, '5.960')] -[2023-10-09 01:48:24,154][88327] Updated weights for policy 1, policy_version 43400 (0.0009) -[2023-10-09 01:48:24,525][88327] Updated weights for policy 1, policy_version 43410 (0.0009) -[2023-10-09 01:48:24,892][88327] Updated weights for policy 1, policy_version 43420 (0.0009) -[2023-10-09 01:48:26,300][88326] Updated weights for policy 0, policy_version 43402 (0.0011) -[2023-10-09 01:48:26,660][88326] Updated weights for policy 0, policy_version 43412 (0.0008) -[2023-10-09 01:48:27,034][88326] Updated weights for policy 0, policy_version 43422 (0.0007) -[2023-10-09 01:48:28,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 88932352. Throughput: 0: 1660.9, 1: 1712.5. Samples: 22241196. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-09 01:48:28,975][87372] Avg episode reward: [(0, '6.280'), (1, '5.990')] -[2023-10-09 01:48:29,104][88327] Updated weights for policy 1, policy_version 43430 (0.0009) -[2023-10-09 01:48:29,473][88327] Updated weights for policy 1, policy_version 43440 (0.0011) -[2023-10-09 01:48:29,849][88327] Updated weights for policy 1, policy_version 43450 (0.0009) -[2023-10-09 01:48:31,015][88326] Updated weights for policy 0, policy_version 43432 (0.0009) -[2023-10-09 01:48:31,388][88326] Updated weights for policy 0, policy_version 43442 (0.0009) -[2023-10-09 01:48:31,756][88326] Updated weights for policy 0, policy_version 43452 (0.0007) -[2023-10-09 01:48:33,892][88327] Updated weights for policy 1, policy_version 43460 (0.0011) -[2023-10-09 01:48:33,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 88997888. Throughput: 0: 1690.0, 1: 1711.2. Samples: 22262276. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-09 01:48:33,975][87372] Avg episode reward: [(0, '6.340'), (1, '6.570')] -[2023-10-09 01:48:33,983][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000043456_44498944.pth... -[2023-10-09 01:48:34,016][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000041888_42893312.pth -[2023-10-09 01:48:34,255][88327] Updated weights for policy 1, policy_version 43470 (0.0011) -[2023-10-09 01:48:34,630][88327] Updated weights for policy 1, policy_version 43480 (0.0010) -[2023-10-09 01:48:34,911][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000043488_44531712.pth... -[2023-10-09 01:48:34,941][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000041888_42893312.pth -[2023-10-09 01:48:35,821][88326] Updated weights for policy 0, policy_version 43462 (0.0009) -[2023-10-09 01:48:36,189][88326] Updated weights for policy 0, policy_version 43472 (0.0008) -[2023-10-09 01:48:36,548][88326] Updated weights for policy 0, policy_version 43482 (0.0007) -[2023-10-09 01:48:38,490][88327] Updated weights for policy 1, policy_version 43490 (0.0008) -[2023-10-09 01:48:38,853][88327] Updated weights for policy 1, policy_version 43500 (0.0008) -[2023-10-09 01:48:38,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 89063424. Throughput: 0: 1681.0, 1: 1701.5. Samples: 22272078. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-09 01:48:38,976][87372] Avg episode reward: [(0, '6.540'), (1, '6.380')] -[2023-10-09 01:48:39,230][88327] Updated weights for policy 1, policy_version 43510 (0.0009) -[2023-10-09 01:48:39,596][88327] Updated weights for policy 1, policy_version 43520 (0.0008) -[2023-10-09 01:48:40,590][88326] Updated weights for policy 0, policy_version 43492 (0.0008) -[2023-10-09 01:48:40,955][88326] Updated weights for policy 0, policy_version 43502 (0.0009) -[2023-10-09 01:48:41,323][88326] Updated weights for policy 0, policy_version 43512 (0.0008) -[2023-10-09 01:48:43,643][88327] Updated weights for policy 1, policy_version 43530 (0.0008) -[2023-10-09 01:48:43,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 89128960. Throughput: 0: 1680.3, 1: 1711.5. Samples: 22292790. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-09 01:48:43,976][87372] Avg episode reward: [(0, '6.170'), (1, '6.310')] -[2023-10-09 01:48:44,013][88327] Updated weights for policy 1, policy_version 43540 (0.0011) -[2023-10-09 01:48:44,383][88327] Updated weights for policy 1, policy_version 43550 (0.0008) -[2023-10-09 01:48:45,266][88326] Updated weights for policy 0, policy_version 43522 (0.0009) -[2023-10-09 01:48:45,627][88326] Updated weights for policy 0, policy_version 43532 (0.0011) -[2023-10-09 01:48:46,004][88326] Updated weights for policy 0, policy_version 43542 (0.0011) -[2023-10-09 01:48:46,363][88326] Updated weights for policy 0, policy_version 43552 (0.0009) -[2023-10-09 01:48:48,202][88327] Updated weights for policy 1, policy_version 43560 (0.0007) -[2023-10-09 01:48:48,581][88327] Updated weights for policy 1, policy_version 43570 (0.0009) -[2023-10-09 01:48:48,947][88327] Updated weights for policy 1, policy_version 43580 (0.0007) -[2023-10-09 01:48:48,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 89194496. Throughput: 0: 1703.6, 1: 1704.7. Samples: 22313936. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-09 01:48:48,975][87372] Avg episode reward: [(0, '6.200'), (1, '6.170')] -[2023-10-09 01:48:50,380][88326] Updated weights for policy 0, policy_version 43562 (0.0008) -[2023-10-09 01:48:50,744][88326] Updated weights for policy 0, policy_version 43572 (0.0009) -[2023-10-09 01:48:51,104][88326] Updated weights for policy 0, policy_version 43582 (0.0009) -[2023-10-09 01:48:52,834][88327] Updated weights for policy 1, policy_version 43590 (0.0008) -[2023-10-09 01:48:53,195][88327] Updated weights for policy 1, policy_version 43600 (0.0008) -[2023-10-09 01:48:53,574][88327] Updated weights for policy 1, policy_version 43610 (0.0009) -[2023-10-09 01:48:53,974][87372] Fps is (10 sec: 16384.6, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 89292800. Throughput: 0: 1676.9, 1: 1710.2. Samples: 22323480. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-09 01:48:53,974][87372] Avg episode reward: [(0, '6.340'), (1, '6.270')] -[2023-10-09 01:48:55,204][88326] Updated weights for policy 0, policy_version 43592 (0.0009) -[2023-10-09 01:48:55,566][88326] Updated weights for policy 0, policy_version 43602 (0.0008) -[2023-10-09 01:48:55,940][88326] Updated weights for policy 0, policy_version 43612 (0.0008) -[2023-10-09 01:48:57,594][88327] Updated weights for policy 1, policy_version 43620 (0.0010) -[2023-10-09 01:48:57,965][88327] Updated weights for policy 1, policy_version 43630 (0.0008) -[2023-10-09 01:48:58,319][88327] Updated weights for policy 1, policy_version 43640 (0.0007) -[2023-10-09 01:48:58,974][87372] Fps is (10 sec: 16384.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 89358336. Throughput: 0: 1698.4, 1: 1712.5. Samples: 22344394. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-09 01:48:58,975][87372] Avg episode reward: [(0, '6.610'), (1, '6.320')] -[2023-10-09 01:48:59,842][88326] Updated weights for policy 0, policy_version 43622 (0.0007) -[2023-10-09 01:49:00,215][88326] Updated weights for policy 0, policy_version 43632 (0.0009) -[2023-10-09 01:49:00,583][88326] Updated weights for policy 0, policy_version 43642 (0.0009) -[2023-10-09 01:49:02,453][88327] Updated weights for policy 1, policy_version 43650 (0.0008) -[2023-10-09 01:49:02,819][88327] Updated weights for policy 1, policy_version 43660 (0.0007) -[2023-10-09 01:49:03,195][88327] Updated weights for policy 1, policy_version 43670 (0.0007) -[2023-10-09 01:49:03,552][88327] Updated weights for policy 1, policy_version 43680 (0.0007) -[2023-10-09 01:49:03,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 89423872. Throughput: 0: 1708.3, 1: 1690.2. Samples: 22364446. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-09 01:49:03,975][87372] Avg episode reward: [(0, '6.410'), (1, '6.760')] -[2023-10-09 01:49:04,616][88326] Updated weights for policy 0, policy_version 43652 (0.0008) -[2023-10-09 01:49:04,982][88326] Updated weights for policy 0, policy_version 43662 (0.0009) -[2023-10-09 01:49:05,349][88326] Updated weights for policy 0, policy_version 43672 (0.0011) -[2023-10-09 01:49:07,600][88327] Updated weights for policy 1, policy_version 43690 (0.0008) -[2023-10-09 01:49:07,972][88327] Updated weights for policy 1, policy_version 43700 (0.0009) -[2023-10-09 01:49:08,337][88327] Updated weights for policy 1, policy_version 43710 (0.0008) -[2023-10-09 01:49:08,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 89489408. Throughput: 0: 1684.8, 1: 1716.1. Samples: 22374380. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-09 01:49:08,975][87372] Avg episode reward: [(0, '6.390'), (1, '6.240')] -[2023-10-09 01:49:09,341][88326] Updated weights for policy 0, policy_version 43682 (0.0010) -[2023-10-09 01:49:09,713][88326] Updated weights for policy 0, policy_version 43692 (0.0007) -[2023-10-09 01:49:10,083][88326] Updated weights for policy 0, policy_version 43702 (0.0007) -[2023-10-09 01:49:10,450][88326] Updated weights for policy 0, policy_version 43712 (0.0009) -[2023-10-09 01:49:12,550][88327] Updated weights for policy 1, policy_version 43720 (0.0007) -[2023-10-09 01:49:12,924][88327] Updated weights for policy 1, policy_version 43730 (0.0009) -[2023-10-09 01:49:13,285][88327] Updated weights for policy 1, policy_version 43740 (0.0009) -[2023-10-09 01:49:13,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 89554944. Throughput: 0: 1709.0, 1: 1710.0. Samples: 22395052. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-09 01:49:13,975][87372] Avg episode reward: [(0, '6.370'), (1, '6.120')] -[2023-10-09 01:49:14,665][88326] Updated weights for policy 0, policy_version 43722 (0.0007) -[2023-10-09 01:49:15,029][88326] Updated weights for policy 0, policy_version 43732 (0.0010) -[2023-10-09 01:49:15,397][88326] Updated weights for policy 0, policy_version 43742 (0.0010) -[2023-10-09 01:49:17,361][88327] Updated weights for policy 1, policy_version 43750 (0.0010) -[2023-10-09 01:49:17,725][88327] Updated weights for policy 1, policy_version 43760 (0.0008) -[2023-10-09 01:49:18,096][88327] Updated weights for policy 1, policy_version 43770 (0.0009) -[2023-10-09 01:49:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 89620480. Throughput: 0: 1704.1, 1: 1679.8. Samples: 22414552. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-09 01:49:18,975][87372] Avg episode reward: [(0, '6.930'), (1, '6.240')] -[2023-10-09 01:49:19,377][88326] Updated weights for policy 0, policy_version 43752 (0.0009) -[2023-10-09 01:49:19,737][88326] Updated weights for policy 0, policy_version 43762 (0.0008) -[2023-10-09 01:49:20,115][88326] Updated weights for policy 0, policy_version 43772 (0.0009) -[2023-10-09 01:49:22,116][88327] Updated weights for policy 1, policy_version 43780 (0.0008) -[2023-10-09 01:49:22,480][88327] Updated weights for policy 1, policy_version 43790 (0.0007) -[2023-10-09 01:49:22,835][88327] Updated weights for policy 1, policy_version 43800 (0.0008) -[2023-10-09 01:49:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 89686016. Throughput: 0: 1687.5, 1: 1706.0. Samples: 22424784. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-09 01:49:23,975][87372] Avg episode reward: [(0, '6.470'), (1, '6.240')] -[2023-10-09 01:49:24,334][88326] Updated weights for policy 0, policy_version 43782 (0.0009) -[2023-10-09 01:49:24,698][88326] Updated weights for policy 0, policy_version 43792 (0.0007) -[2023-10-09 01:49:25,078][88326] Updated weights for policy 0, policy_version 43802 (0.0008) -[2023-10-09 01:49:26,989][88327] Updated weights for policy 1, policy_version 43810 (0.0008) -[2023-10-09 01:49:27,350][88327] Updated weights for policy 1, policy_version 43820 (0.0009) -[2023-10-09 01:49:27,729][88327] Updated weights for policy 1, policy_version 43830 (0.0010) -[2023-10-09 01:49:28,093][88327] Updated weights for policy 1, policy_version 43840 (0.0010) -[2023-10-09 01:49:28,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 89751552. Throughput: 0: 1697.3, 1: 1688.6. Samples: 22445154. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-09 01:49:28,975][87372] Avg episode reward: [(0, '6.450'), (1, '6.230')] -[2023-10-09 01:49:29,122][88326] Updated weights for policy 0, policy_version 43812 (0.0010) -[2023-10-09 01:49:29,495][88326] Updated weights for policy 0, policy_version 43822 (0.0007) -[2023-10-09 01:49:29,853][88326] Updated weights for policy 0, policy_version 43832 (0.0007) -[2023-10-09 01:49:32,149][88327] Updated weights for policy 1, policy_version 43850 (0.0011) -[2023-10-09 01:49:32,518][88327] Updated weights for policy 1, policy_version 43860 (0.0010) -[2023-10-09 01:49:32,875][88327] Updated weights for policy 1, policy_version 43870 (0.0009) -[2023-10-09 01:49:33,864][88326] Updated weights for policy 0, policy_version 43842 (0.0007) -[2023-10-09 01:49:33,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 89817088. Throughput: 0: 1690.1, 1: 1665.8. Samples: 22464952. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-09 01:49:33,975][87372] Avg episode reward: [(0, '7.040'), (1, '6.380')] -[2023-10-09 01:49:34,224][88326] Updated weights for policy 0, policy_version 43852 (0.0008) -[2023-10-09 01:49:34,580][88326] Updated weights for policy 0, policy_version 43862 (0.0008) -[2023-10-09 01:49:34,945][88326] Updated weights for policy 0, policy_version 43872 (0.0007) -[2023-10-09 01:49:36,902][88327] Updated weights for policy 1, policy_version 43880 (0.0009) -[2023-10-09 01:49:37,271][88327] Updated weights for policy 1, policy_version 43890 (0.0007) -[2023-10-09 01:49:37,640][88327] Updated weights for policy 1, policy_version 43900 (0.0009) -[2023-10-09 01:49:38,915][88326] Updated weights for policy 0, policy_version 43882 (0.0007) -[2023-10-09 01:49:38,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 89882624. Throughput: 0: 1685.0, 1: 1688.4. Samples: 22475282. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-09 01:49:38,975][87372] Avg episode reward: [(0, '6.660'), (1, '6.630')] -[2023-10-09 01:49:39,281][88326] Updated weights for policy 0, policy_version 43892 (0.0007) -[2023-10-09 01:49:39,652][88326] Updated weights for policy 0, policy_version 43902 (0.0007) -[2023-10-09 01:49:41,687][88327] Updated weights for policy 1, policy_version 43910 (0.0007) -[2023-10-09 01:49:42,056][88327] Updated weights for policy 1, policy_version 43920 (0.0009) -[2023-10-09 01:49:42,418][88327] Updated weights for policy 1, policy_version 43930 (0.0008) -[2023-10-09 01:49:43,663][88326] Updated weights for policy 0, policy_version 43912 (0.0008) -[2023-10-09 01:49:43,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 89948160. Throughput: 0: 1691.9, 1: 1668.5. Samples: 22495612. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-09 01:49:43,975][87372] Avg episode reward: [(0, '6.100'), (1, '6.390')] -[2023-10-09 01:49:44,025][88326] Updated weights for policy 0, policy_version 43922 (0.0010) -[2023-10-09 01:49:44,407][88326] Updated weights for policy 0, policy_version 43932 (0.0010) -[2023-10-09 01:49:46,604][88327] Updated weights for policy 1, policy_version 43940 (0.0010) -[2023-10-09 01:49:46,978][88327] Updated weights for policy 1, policy_version 43950 (0.0009) -[2023-10-09 01:49:47,338][88327] Updated weights for policy 1, policy_version 43960 (0.0009) -[2023-10-09 01:49:48,432][88326] Updated weights for policy 0, policy_version 43942 (0.0009) -[2023-10-09 01:49:48,805][88326] Updated weights for policy 0, policy_version 43952 (0.0010) -[2023-10-09 01:49:48,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 90013696. Throughput: 0: 1689.0, 1: 1674.5. Samples: 22515804. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-09 01:49:48,975][87372] Avg episode reward: [(0, '6.410'), (1, '6.520')] -[2023-10-09 01:49:49,180][88326] Updated weights for policy 0, policy_version 43962 (0.0007) -[2023-10-09 01:49:51,341][88327] Updated weights for policy 1, policy_version 43970 (0.0009) -[2023-10-09 01:49:51,713][88327] Updated weights for policy 1, policy_version 43980 (0.0009) -[2023-10-09 01:49:52,076][88327] Updated weights for policy 1, policy_version 43990 (0.0007) -[2023-10-09 01:49:52,442][88327] Updated weights for policy 1, policy_version 44000 (0.0007) -[2023-10-09 01:49:53,311][88326] Updated weights for policy 0, policy_version 43972 (0.0008) -[2023-10-09 01:49:53,687][88326] Updated weights for policy 0, policy_version 43982 (0.0008) -[2023-10-09 01:49:53,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.1, 300 sec: 13440.4). Total num frames: 90079232. Throughput: 0: 1687.1, 1: 1683.8. Samples: 22526074. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-09 01:49:53,976][87372] Avg episode reward: [(0, '6.200'), (1, '6.040')] -[2023-10-09 01:49:54,049][88326] Updated weights for policy 0, policy_version 43992 (0.0010) -[2023-10-09 01:49:56,542][88327] Updated weights for policy 1, policy_version 44010 (0.0010) -[2023-10-09 01:49:56,918][88327] Updated weights for policy 1, policy_version 44020 (0.0009) -[2023-10-09 01:49:57,288][88327] Updated weights for policy 1, policy_version 44030 (0.0008) -[2023-10-09 01:49:57,914][88326] Updated weights for policy 0, policy_version 44002 (0.0008) -[2023-10-09 01:49:58,274][88326] Updated weights for policy 0, policy_version 44012 (0.0008) -[2023-10-09 01:49:58,649][88326] Updated weights for policy 0, policy_version 44022 (0.0008) -[2023-10-09 01:49:58,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 90144768. Throughput: 0: 1688.8, 1: 1662.9. Samples: 22545874. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:49:58,975][87372] Avg episode reward: [(0, '6.310'), (1, '6.360')] -[2023-10-09 01:49:59,007][88326] Updated weights for policy 0, policy_version 44032 (0.0007) -[2023-10-09 01:50:01,192][88327] Updated weights for policy 1, policy_version 44040 (0.0009) -[2023-10-09 01:50:01,561][88327] Updated weights for policy 1, policy_version 44050 (0.0008) -[2023-10-09 01:50:01,932][88327] Updated weights for policy 1, policy_version 44060 (0.0008) -[2023-10-09 01:50:03,065][88326] Updated weights for policy 0, policy_version 44042 (0.0007) -[2023-10-09 01:50:03,431][88326] Updated weights for policy 0, policy_version 44052 (0.0009) -[2023-10-09 01:50:03,800][88326] Updated weights for policy 0, policy_version 44062 (0.0008) -[2023-10-09 01:50:03,974][87372] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 90243072. Throughput: 0: 1681.2, 1: 1686.3. Samples: 22566092. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:50:03,975][87372] Avg episode reward: [(0, '6.130'), (1, '6.510')] -[2023-10-09 01:50:05,971][88327] Updated weights for policy 1, policy_version 44070 (0.0007) -[2023-10-09 01:50:06,335][88327] Updated weights for policy 1, policy_version 44080 (0.0009) -[2023-10-09 01:50:06,695][88327] Updated weights for policy 1, policy_version 44090 (0.0008) -[2023-10-09 01:50:07,865][88326] Updated weights for policy 0, policy_version 44072 (0.0007) -[2023-10-09 01:50:08,223][88326] Updated weights for policy 0, policy_version 44082 (0.0011) -[2023-10-09 01:50:08,588][88326] Updated weights for policy 0, policy_version 44092 (0.0009) -[2023-10-09 01:50:08,974][87372] Fps is (10 sec: 16384.0, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 90308608. Throughput: 0: 1696.3, 1: 1678.1. Samples: 22576634. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:50:08,974][87372] Avg episode reward: [(0, '5.680'), (1, '6.120')] -[2023-10-09 01:50:10,594][88327] Updated weights for policy 1, policy_version 44100 (0.0007) -[2023-10-09 01:50:10,952][88327] Updated weights for policy 1, policy_version 44110 (0.0008) -[2023-10-09 01:50:11,322][88327] Updated weights for policy 1, policy_version 44120 (0.0009) -[2023-10-09 01:50:12,769][88326] Updated weights for policy 0, policy_version 44102 (0.0007) -[2023-10-09 01:50:13,146][88326] Updated weights for policy 0, policy_version 44112 (0.0007) -[2023-10-09 01:50:13,523][88326] Updated weights for policy 0, policy_version 44122 (0.0007) -[2023-10-09 01:50:13,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 90374144. Throughput: 0: 1697.2, 1: 1670.6. Samples: 22596702. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:50:13,975][87372] Avg episode reward: [(0, '5.960'), (1, '6.640')] -[2023-10-09 01:50:15,561][88327] Updated weights for policy 1, policy_version 44130 (0.0009) -[2023-10-09 01:50:15,924][88327] Updated weights for policy 1, policy_version 44140 (0.0011) -[2023-10-09 01:50:16,295][88327] Updated weights for policy 1, policy_version 44150 (0.0008) -[2023-10-09 01:50:16,654][88327] Updated weights for policy 1, policy_version 44160 (0.0009) -[2023-10-09 01:50:17,509][88326] Updated weights for policy 0, policy_version 44132 (0.0007) -[2023-10-09 01:50:17,876][88326] Updated weights for policy 0, policy_version 44142 (0.0008) -[2023-10-09 01:50:18,246][88326] Updated weights for policy 0, policy_version 44152 (0.0008) -[2023-10-09 01:50:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 90439680. Throughput: 0: 1677.2, 1: 1692.0. Samples: 22616570. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:50:18,974][87372] Avg episode reward: [(0, '6.010'), (1, '6.710')] -[2023-10-09 01:50:20,729][88327] Updated weights for policy 1, policy_version 44170 (0.0008) -[2023-10-09 01:50:21,093][88327] Updated weights for policy 1, policy_version 44180 (0.0008) -[2023-10-09 01:50:21,456][88327] Updated weights for policy 1, policy_version 44190 (0.0008) -[2023-10-09 01:50:22,188][88326] Updated weights for policy 0, policy_version 44162 (0.0009) -[2023-10-09 01:50:22,551][88326] Updated weights for policy 0, policy_version 44172 (0.0009) -[2023-10-09 01:50:22,919][88326] Updated weights for policy 0, policy_version 44182 (0.0007) -[2023-10-09 01:50:23,291][88326] Updated weights for policy 0, policy_version 44192 (0.0009) -[2023-10-09 01:50:23,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 90505216. Throughput: 0: 1699.9, 1: 1675.4. Samples: 22627170. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-09 01:50:23,975][87372] Avg episode reward: [(0, '6.280'), (1, '6.560')] -[2023-10-09 01:50:25,473][88327] Updated weights for policy 1, policy_version 44200 (0.0010) -[2023-10-09 01:50:25,849][88327] Updated weights for policy 1, policy_version 44210 (0.0009) -[2023-10-09 01:50:26,205][88327] Updated weights for policy 1, policy_version 44220 (0.0011) -[2023-10-09 01:50:27,348][88326] Updated weights for policy 0, policy_version 44202 (0.0007) -[2023-10-09 01:50:27,717][88326] Updated weights for policy 0, policy_version 44212 (0.0010) -[2023-10-09 01:50:28,087][88326] Updated weights for policy 0, policy_version 44222 (0.0009) -[2023-10-09 01:50:28,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 90570752. Throughput: 0: 1692.8, 1: 1680.9. Samples: 22647428. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-09 01:50:28,975][87372] Avg episode reward: [(0, '5.910'), (1, '6.430')] -[2023-10-09 01:50:30,304][88327] Updated weights for policy 1, policy_version 44230 (0.0009) -[2023-10-09 01:50:30,673][88327] Updated weights for policy 1, policy_version 44240 (0.0007) -[2023-10-09 01:50:31,029][88327] Updated weights for policy 1, policy_version 44250 (0.0007) -[2023-10-09 01:50:32,028][88326] Updated weights for policy 0, policy_version 44232 (0.0011) -[2023-10-09 01:50:32,396][88326] Updated weights for policy 0, policy_version 44242 (0.0008) -[2023-10-09 01:50:32,771][88326] Updated weights for policy 0, policy_version 44252 (0.0007) -[2023-10-09 01:50:33,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 90636288. Throughput: 0: 1671.1, 1: 1696.5. Samples: 22667346. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-09 01:50:33,975][87372] Avg episode reward: [(0, '6.150'), (1, '6.890')] -[2023-10-09 01:50:33,982][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000044256_45318144.pth... -[2023-10-09 01:50:33,983][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000044256_45318144.pth... -[2023-10-09 01:50:34,022][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000042688_43712512.pth -[2023-10-09 01:50:34,024][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000042688_43712512.pth -[2023-10-09 01:50:35,032][88327] Updated weights for policy 1, policy_version 44260 (0.0009) -[2023-10-09 01:50:35,405][88327] Updated weights for policy 1, policy_version 44270 (0.0010) -[2023-10-09 01:50:35,763][88327] Updated weights for policy 1, policy_version 44280 (0.0009) -[2023-10-09 01:50:36,842][88326] Updated weights for policy 0, policy_version 44262 (0.0008) -[2023-10-09 01:50:37,196][88326] Updated weights for policy 0, policy_version 44272 (0.0008) -[2023-10-09 01:50:37,577][88326] Updated weights for policy 0, policy_version 44282 (0.0010) -[2023-10-09 01:50:38,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 90701824. Throughput: 0: 1704.3, 1: 1668.1. Samples: 22677832. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-09 01:50:38,975][87372] Avg episode reward: [(0, '6.110'), (1, '6.410')] -[2023-10-09 01:50:39,648][88327] Updated weights for policy 1, policy_version 44290 (0.0008) -[2023-10-09 01:50:40,015][88327] Updated weights for policy 1, policy_version 44300 (0.0008) -[2023-10-09 01:50:40,371][88327] Updated weights for policy 1, policy_version 44310 (0.0008) -[2023-10-09 01:50:40,739][88327] Updated weights for policy 1, policy_version 44320 (0.0009) -[2023-10-09 01:50:41,779][88326] Updated weights for policy 0, policy_version 44292 (0.0009) -[2023-10-09 01:50:42,157][88326] Updated weights for policy 0, policy_version 44302 (0.0009) -[2023-10-09 01:50:42,523][88326] Updated weights for policy 0, policy_version 44312 (0.0009) -[2023-10-09 01:50:43,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 90767360. Throughput: 0: 1688.6, 1: 1697.4. Samples: 22698244. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-09 01:50:43,975][87372] Avg episode reward: [(0, '6.140'), (1, '6.270')] -[2023-10-09 01:50:44,751][88327] Updated weights for policy 1, policy_version 44330 (0.0009) -[2023-10-09 01:50:45,125][88327] Updated weights for policy 1, policy_version 44340 (0.0008) -[2023-10-09 01:50:45,490][88327] Updated weights for policy 1, policy_version 44350 (0.0009) -[2023-10-09 01:50:46,595][88326] Updated weights for policy 0, policy_version 44322 (0.0011) -[2023-10-09 01:50:46,952][88326] Updated weights for policy 0, policy_version 44332 (0.0009) -[2023-10-09 01:50:47,320][88326] Updated weights for policy 0, policy_version 44342 (0.0008) -[2023-10-09 01:50:47,685][88326] Updated weights for policy 0, policy_version 44352 (0.0008) -[2023-10-09 01:50:48,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 90832896. Throughput: 0: 1681.9, 1: 1704.7. Samples: 22718488. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-09 01:50:48,974][87372] Avg episode reward: [(0, '6.330'), (1, '6.400')] -[2023-10-09 01:50:49,466][88327] Updated weights for policy 1, policy_version 44360 (0.0008) -[2023-10-09 01:50:49,837][88327] Updated weights for policy 1, policy_version 44370 (0.0007) -[2023-10-09 01:50:50,208][88327] Updated weights for policy 1, policy_version 44380 (0.0007) -[2023-10-09 01:50:51,784][88326] Updated weights for policy 0, policy_version 44362 (0.0009) -[2023-10-09 01:50:52,165][88326] Updated weights for policy 0, policy_version 44372 (0.0011) -[2023-10-09 01:50:52,542][88326] Updated weights for policy 0, policy_version 44382 (0.0008) -[2023-10-09 01:50:53,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 90898432. Throughput: 0: 1698.4, 1: 1688.4. Samples: 22729044. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:50:53,975][87372] Avg episode reward: [(0, '6.550'), (1, '6.050')] -[2023-10-09 01:50:54,144][88327] Updated weights for policy 1, policy_version 44390 (0.0008) -[2023-10-09 01:50:54,517][88327] Updated weights for policy 1, policy_version 44400 (0.0011) -[2023-10-09 01:50:54,885][88327] Updated weights for policy 1, policy_version 44410 (0.0011) -[2023-10-09 01:50:56,420][88326] Updated weights for policy 0, policy_version 44392 (0.0007) -[2023-10-09 01:50:56,790][88326] Updated weights for policy 0, policy_version 44402 (0.0008) -[2023-10-09 01:50:57,154][88326] Updated weights for policy 0, policy_version 44412 (0.0010) -[2023-10-09 01:50:58,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 90963968. Throughput: 0: 1676.8, 1: 1707.0. Samples: 22748972. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:50:58,975][87372] Avg episode reward: [(0, '6.580'), (1, '6.480')] -[2023-10-09 01:50:59,016][88327] Updated weights for policy 1, policy_version 44420 (0.0008) -[2023-10-09 01:50:59,376][88327] Updated weights for policy 1, policy_version 44430 (0.0007) -[2023-10-09 01:50:59,748][88327] Updated weights for policy 1, policy_version 44440 (0.0008) -[2023-10-09 01:51:01,037][88326] Updated weights for policy 0, policy_version 44422 (0.0011) -[2023-10-09 01:51:01,404][88326] Updated weights for policy 0, policy_version 44432 (0.0008) -[2023-10-09 01:51:01,774][88326] Updated weights for policy 0, policy_version 44442 (0.0009) -[2023-10-09 01:51:03,751][88327] Updated weights for policy 1, policy_version 44450 (0.0009) -[2023-10-09 01:51:03,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 91029504. Throughput: 0: 1700.2, 1: 1710.3. Samples: 22770046. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:51:03,975][87372] Avg episode reward: [(0, '6.050'), (1, '6.280')] -[2023-10-09 01:51:04,126][88327] Updated weights for policy 1, policy_version 44460 (0.0009) -[2023-10-09 01:51:04,493][88327] Updated weights for policy 1, policy_version 44470 (0.0007) -[2023-10-09 01:51:04,854][88327] Updated weights for policy 1, policy_version 44480 (0.0009) -[2023-10-09 01:51:05,639][88326] Updated weights for policy 0, policy_version 44452 (0.0007) -[2023-10-09 01:51:06,023][88326] Updated weights for policy 0, policy_version 44462 (0.0007) -[2023-10-09 01:51:06,392][88326] Updated weights for policy 0, policy_version 44472 (0.0009) -[2023-10-09 01:51:08,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 91095040. Throughput: 0: 1693.8, 1: 1696.7. Samples: 22779740. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:51:08,975][87372] Avg episode reward: [(0, '6.560'), (1, '6.280')] -[2023-10-09 01:51:09,025][88327] Updated weights for policy 1, policy_version 44490 (0.0008) -[2023-10-09 01:51:09,394][88327] Updated weights for policy 1, policy_version 44500 (0.0009) -[2023-10-09 01:51:09,757][88327] Updated weights for policy 1, policy_version 44510 (0.0008) -[2023-10-09 01:51:10,410][88326] Updated weights for policy 0, policy_version 44482 (0.0008) -[2023-10-09 01:51:10,775][88326] Updated weights for policy 0, policy_version 44492 (0.0007) -[2023-10-09 01:51:11,147][88326] Updated weights for policy 0, policy_version 44502 (0.0010) -[2023-10-09 01:51:11,519][88326] Updated weights for policy 0, policy_version 44512 (0.0009) -[2023-10-09 01:51:13,865][88327] Updated weights for policy 1, policy_version 44520 (0.0009) -[2023-10-09 01:51:13,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 91160576. Throughput: 0: 1684.9, 1: 1708.2. Samples: 22800118. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:51:13,975][87372] Avg episode reward: [(0, '6.290'), (1, '6.610')] -[2023-10-09 01:51:14,228][88327] Updated weights for policy 1, policy_version 44530 (0.0008) -[2023-10-09 01:51:14,591][88327] Updated weights for policy 1, policy_version 44540 (0.0008) -[2023-10-09 01:51:15,458][88326] Updated weights for policy 0, policy_version 44522 (0.0008) -[2023-10-09 01:51:15,834][88326] Updated weights for policy 0, policy_version 44532 (0.0008) -[2023-10-09 01:51:16,192][88326] Updated weights for policy 0, policy_version 44542 (0.0007) -[2023-10-09 01:51:18,626][88327] Updated weights for policy 1, policy_version 44550 (0.0009) -[2023-10-09 01:51:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 91226112. Throughput: 0: 1712.8, 1: 1706.5. Samples: 22821214. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:51:18,975][87372] Avg episode reward: [(0, '6.560'), (1, '5.940')] -[2023-10-09 01:51:18,989][88327] Updated weights for policy 1, policy_version 44560 (0.0008) -[2023-10-09 01:51:19,350][88327] Updated weights for policy 1, policy_version 44570 (0.0007) -[2023-10-09 01:51:20,231][88326] Updated weights for policy 0, policy_version 44552 (0.0008) -[2023-10-09 01:51:20,600][88326] Updated weights for policy 0, policy_version 44562 (0.0007) -[2023-10-09 01:51:20,975][88326] Updated weights for policy 0, policy_version 44572 (0.0008) -[2023-10-09 01:51:23,365][88327] Updated weights for policy 1, policy_version 44580 (0.0007) -[2023-10-09 01:51:23,737][88327] Updated weights for policy 1, policy_version 44590 (0.0008) -[2023-10-09 01:51:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 91291648. Throughput: 0: 1683.9, 1: 1708.5. Samples: 22830490. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:51:23,975][87372] Avg episode reward: [(0, '6.450'), (1, '5.930')] -[2023-10-09 01:51:24,089][88327] Updated weights for policy 1, policy_version 44600 (0.0008) -[2023-10-09 01:51:25,077][88326] Updated weights for policy 0, policy_version 44582 (0.0008) -[2023-10-09 01:51:25,438][88326] Updated weights for policy 0, policy_version 44592 (0.0008) -[2023-10-09 01:51:25,818][88326] Updated weights for policy 0, policy_version 44602 (0.0009) -[2023-10-09 01:51:28,069][88327] Updated weights for policy 1, policy_version 44610 (0.0010) -[2023-10-09 01:51:28,433][88327] Updated weights for policy 1, policy_version 44620 (0.0009) -[2023-10-09 01:51:28,798][88327] Updated weights for policy 1, policy_version 44630 (0.0007) -[2023-10-09 01:51:28,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 91357184. Throughput: 0: 1700.5, 1: 1705.6. Samples: 22851516. Policy #0 lag: (min: 6.0, avg: 6.6, max: 22.0) -[2023-10-09 01:51:28,975][87372] Avg episode reward: [(0, '6.630'), (1, '6.160')] -[2023-10-09 01:51:29,169][88327] Updated weights for policy 1, policy_version 44640 (0.0007) -[2023-10-09 01:51:29,717][88326] Updated weights for policy 0, policy_version 44612 (0.0008) -[2023-10-09 01:51:30,090][88326] Updated weights for policy 0, policy_version 44622 (0.0007) -[2023-10-09 01:51:30,464][88326] Updated weights for policy 0, policy_version 44632 (0.0009) -[2023-10-09 01:51:33,379][88327] Updated weights for policy 1, policy_version 44650 (0.0010) -[2023-10-09 01:51:33,747][88327] Updated weights for policy 1, policy_version 44660 (0.0008) -[2023-10-09 01:51:33,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 91422720. Throughput: 0: 1720.6, 1: 1700.1. Samples: 22872420. Policy #0 lag: (min: 6.0, avg: 6.6, max: 22.0) -[2023-10-09 01:51:33,975][87372] Avg episode reward: [(0, '6.500'), (1, '5.810')] -[2023-10-09 01:51:34,117][88327] Updated weights for policy 1, policy_version 44670 (0.0009) -[2023-10-09 01:51:34,450][88326] Updated weights for policy 0, policy_version 44642 (0.0010) -[2023-10-09 01:51:34,813][88326] Updated weights for policy 0, policy_version 44652 (0.0007) -[2023-10-09 01:51:35,184][88326] Updated weights for policy 0, policy_version 44662 (0.0010) -[2023-10-09 01:51:35,543][88326] Updated weights for policy 0, policy_version 44672 (0.0009) -[2023-10-09 01:51:38,047][88327] Updated weights for policy 1, policy_version 44680 (0.0008) -[2023-10-09 01:51:38,417][88327] Updated weights for policy 1, policy_version 44690 (0.0007) -[2023-10-09 01:51:38,774][88327] Updated weights for policy 1, policy_version 44700 (0.0009) -[2023-10-09 01:51:38,974][87372] Fps is (10 sec: 16384.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 91521024. Throughput: 0: 1691.3, 1: 1702.9. Samples: 22881784. Policy #0 lag: (min: 6.0, avg: 6.6, max: 22.0) -[2023-10-09 01:51:38,975][87372] Avg episode reward: [(0, '6.050'), (1, '5.540')] -[2023-10-09 01:51:39,668][88326] Updated weights for policy 0, policy_version 44682 (0.0007) -[2023-10-09 01:51:40,038][88326] Updated weights for policy 0, policy_version 44692 (0.0007) -[2023-10-09 01:51:40,406][88326] Updated weights for policy 0, policy_version 44702 (0.0007) -[2023-10-09 01:51:42,749][88327] Updated weights for policy 1, policy_version 44710 (0.0011) -[2023-10-09 01:51:43,108][88327] Updated weights for policy 1, policy_version 44720 (0.0008) -[2023-10-09 01:51:43,479][88327] Updated weights for policy 1, policy_version 44730 (0.0010) -[2023-10-09 01:51:43,974][87372] Fps is (10 sec: 16384.5, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 91586560. Throughput: 0: 1712.8, 1: 1705.9. Samples: 22902816. Policy #0 lag: (min: 6.0, avg: 6.6, max: 22.0) -[2023-10-09 01:51:43,975][87372] Avg episode reward: [(0, '6.350'), (1, '5.890')] -[2023-10-09 01:51:44,191][88326] Updated weights for policy 0, policy_version 44712 (0.0008) -[2023-10-09 01:51:44,565][88326] Updated weights for policy 0, policy_version 44722 (0.0009) -[2023-10-09 01:51:44,943][88326] Updated weights for policy 0, policy_version 44732 (0.0008) -[2023-10-09 01:51:47,546][88327] Updated weights for policy 1, policy_version 44740 (0.0008) -[2023-10-09 01:51:47,911][88327] Updated weights for policy 1, policy_version 44750 (0.0008) -[2023-10-09 01:51:48,273][88327] Updated weights for policy 1, policy_version 44760 (0.0010) -[2023-10-09 01:51:48,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 91652096. Throughput: 0: 1709.6, 1: 1682.7. Samples: 22922698. Policy #0 lag: (min: 6.0, avg: 6.6, max: 22.0) -[2023-10-09 01:51:48,975][87372] Avg episode reward: [(0, '5.950'), (1, '6.660')] -[2023-10-09 01:51:49,080][88326] Updated weights for policy 0, policy_version 44742 (0.0009) -[2023-10-09 01:51:49,443][88326] Updated weights for policy 0, policy_version 44752 (0.0008) -[2023-10-09 01:51:49,819][88326] Updated weights for policy 0, policy_version 44762 (0.0009) -[2023-10-09 01:51:52,413][88327] Updated weights for policy 1, policy_version 44770 (0.0009) -[2023-10-09 01:51:52,777][88327] Updated weights for policy 1, policy_version 44780 (0.0007) -[2023-10-09 01:51:53,150][88327] Updated weights for policy 1, policy_version 44790 (0.0008) -[2023-10-09 01:51:53,507][88327] Updated weights for policy 1, policy_version 44800 (0.0009) -[2023-10-09 01:51:53,927][88326] Updated weights for policy 0, policy_version 44772 (0.0010) -[2023-10-09 01:51:53,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 91717632. Throughput: 0: 1695.7, 1: 1705.6. Samples: 22932798. Policy #0 lag: (min: 6.0, avg: 6.6, max: 22.0) -[2023-10-09 01:51:53,975][87372] Avg episode reward: [(0, '5.660'), (1, '6.250')] -[2023-10-09 01:51:54,297][88326] Updated weights for policy 0, policy_version 44782 (0.0011) -[2023-10-09 01:51:54,674][88326] Updated weights for policy 0, policy_version 44792 (0.0009) -[2023-10-09 01:51:57,312][88327] Updated weights for policy 1, policy_version 44810 (0.0008) -[2023-10-09 01:51:57,670][88327] Updated weights for policy 1, policy_version 44820 (0.0009) -[2023-10-09 01:51:58,031][88327] Updated weights for policy 1, policy_version 44830 (0.0010) -[2023-10-09 01:51:58,616][88326] Updated weights for policy 0, policy_version 44802 (0.0009) -[2023-10-09 01:51:58,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 91783168. Throughput: 0: 1711.2, 1: 1699.6. Samples: 22953604. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-10-09 01:51:58,975][87372] Avg episode reward: [(0, '6.470'), (1, '6.440')] -[2023-10-09 01:51:58,994][88326] Updated weights for policy 0, policy_version 44812 (0.0009) -[2023-10-09 01:51:59,363][88326] Updated weights for policy 0, policy_version 44822 (0.0009) -[2023-10-09 01:51:59,729][88326] Updated weights for policy 0, policy_version 44832 (0.0009) -[2023-10-09 01:52:01,936][88327] Updated weights for policy 1, policy_version 44840 (0.0010) -[2023-10-09 01:52:02,303][88327] Updated weights for policy 1, policy_version 44850 (0.0010) -[2023-10-09 01:52:02,664][88327] Updated weights for policy 1, policy_version 44860 (0.0010) -[2023-10-09 01:52:03,696][88326] Updated weights for policy 0, policy_version 44842 (0.0009) -[2023-10-09 01:52:03,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 91848704. Throughput: 0: 1710.2, 1: 1676.2. Samples: 22973604. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-10-09 01:52:03,975][87372] Avg episode reward: [(0, '6.420'), (1, '5.870')] -[2023-10-09 01:52:04,055][88326] Updated weights for policy 0, policy_version 44852 (0.0008) -[2023-10-09 01:52:04,434][88326] Updated weights for policy 0, policy_version 44862 (0.0009) -[2023-10-09 01:52:06,691][88327] Updated weights for policy 1, policy_version 44870 (0.0007) -[2023-10-09 01:52:07,065][88327] Updated weights for policy 1, policy_version 44880 (0.0010) -[2023-10-09 01:52:07,424][88327] Updated weights for policy 1, policy_version 44890 (0.0008) -[2023-10-09 01:52:08,414][88326] Updated weights for policy 0, policy_version 44872 (0.0010) -[2023-10-09 01:52:08,786][88326] Updated weights for policy 0, policy_version 44882 (0.0009) -[2023-10-09 01:52:08,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 91914240. Throughput: 0: 1708.2, 1: 1704.5. Samples: 22984062. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-10-09 01:52:08,975][87372] Avg episode reward: [(0, '6.580'), (1, '5.660')] -[2023-10-09 01:52:09,148][88326] Updated weights for policy 0, policy_version 44892 (0.0011) -[2023-10-09 01:52:11,512][88327] Updated weights for policy 1, policy_version 44900 (0.0008) -[2023-10-09 01:52:11,875][88327] Updated weights for policy 1, policy_version 44910 (0.0007) -[2023-10-09 01:52:12,238][88327] Updated weights for policy 1, policy_version 44920 (0.0008) -[2023-10-09 01:52:13,108][88326] Updated weights for policy 0, policy_version 44902 (0.0008) -[2023-10-09 01:52:13,474][88326] Updated weights for policy 0, policy_version 44912 (0.0008) -[2023-10-09 01:52:13,840][88326] Updated weights for policy 0, policy_version 44922 (0.0008) -[2023-10-09 01:52:13,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 91979776. Throughput: 0: 1708.4, 1: 1685.5. Samples: 23004242. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-10-09 01:52:13,975][87372] Avg episode reward: [(0, '6.830'), (1, '5.700')] -[2023-10-09 01:52:16,404][88327] Updated weights for policy 1, policy_version 44930 (0.0007) -[2023-10-09 01:52:16,773][88327] Updated weights for policy 1, policy_version 44940 (0.0008) -[2023-10-09 01:52:17,128][88327] Updated weights for policy 1, policy_version 44950 (0.0007) -[2023-10-09 01:52:17,505][88327] Updated weights for policy 1, policy_version 44960 (0.0007) -[2023-10-09 01:52:17,880][88326] Updated weights for policy 0, policy_version 44932 (0.0008) -[2023-10-09 01:52:18,241][88326] Updated weights for policy 0, policy_version 44942 (0.0009) -[2023-10-09 01:52:18,609][88326] Updated weights for policy 0, policy_version 44952 (0.0009) -[2023-10-09 01:52:18,974][87372] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 92078080. Throughput: 0: 1699.9, 1: 1680.6. Samples: 23024542. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-10-09 01:52:18,975][87372] Avg episode reward: [(0, '6.830'), (1, '5.960')] -[2023-10-09 01:52:21,596][88327] Updated weights for policy 1, policy_version 44970 (0.0009) -[2023-10-09 01:52:21,977][88327] Updated weights for policy 1, policy_version 44980 (0.0009) -[2023-10-09 01:52:22,341][88327] Updated weights for policy 1, policy_version 44990 (0.0010) -[2023-10-09 01:52:22,578][88326] Updated weights for policy 0, policy_version 44962 (0.0007) -[2023-10-09 01:52:22,956][88326] Updated weights for policy 0, policy_version 44972 (0.0008) -[2023-10-09 01:52:23,325][88326] Updated weights for policy 0, policy_version 44982 (0.0008) -[2023-10-09 01:52:23,693][88326] Updated weights for policy 0, policy_version 44992 (0.0009) -[2023-10-09 01:52:23,974][87372] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 92143616. Throughput: 0: 1711.1, 1: 1706.7. Samples: 23035584. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-10-09 01:52:23,975][87372] Avg episode reward: [(0, '6.200'), (1, '6.130')] -[2023-10-09 01:52:26,226][88327] Updated weights for policy 1, policy_version 45000 (0.0009) -[2023-10-09 01:52:26,592][88327] Updated weights for policy 1, policy_version 45010 (0.0009) -[2023-10-09 01:52:26,958][88327] Updated weights for policy 1, policy_version 45020 (0.0008) -[2023-10-09 01:52:27,736][88326] Updated weights for policy 0, policy_version 45002 (0.0007) -[2023-10-09 01:52:28,105][88326] Updated weights for policy 0, policy_version 45012 (0.0008) -[2023-10-09 01:52:28,472][88326] Updated weights for policy 0, policy_version 45022 (0.0008) -[2023-10-09 01:52:28,974][87372] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 92209152. Throughput: 0: 1718.4, 1: 1671.8. Samples: 23055376. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) -[2023-10-09 01:52:28,975][87372] Avg episode reward: [(0, '6.120'), (1, '5.970')] -[2023-10-09 01:52:30,906][88327] Updated weights for policy 1, policy_version 45030 (0.0008) -[2023-10-09 01:52:31,269][88327] Updated weights for policy 1, policy_version 45040 (0.0011) -[2023-10-09 01:52:31,637][88327] Updated weights for policy 1, policy_version 45050 (0.0008) -[2023-10-09 01:52:32,510][88326] Updated weights for policy 0, policy_version 45032 (0.0009) -[2023-10-09 01:52:32,872][88326] Updated weights for policy 0, policy_version 45042 (0.0011) -[2023-10-09 01:52:33,250][88326] Updated weights for policy 0, policy_version 45052 (0.0008) -[2023-10-09 01:52:33,974][87372] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 92274688. Throughput: 0: 1691.2, 1: 1696.5. Samples: 23075146. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) -[2023-10-09 01:52:33,975][87372] Avg episode reward: [(0, '6.680'), (1, '6.110')] -[2023-10-09 01:52:33,987][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000045056_46137344.pth... -[2023-10-09 01:52:33,987][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000045056_46137344.pth... -[2023-10-09 01:52:34,028][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000043488_44531712.pth -[2023-10-09 01:52:34,028][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000043456_44498944.pth -[2023-10-09 01:52:35,580][88327] Updated weights for policy 1, policy_version 45060 (0.0009) -[2023-10-09 01:52:35,941][88327] Updated weights for policy 1, policy_version 45070 (0.0009) -[2023-10-09 01:52:36,302][88327] Updated weights for policy 1, policy_version 45080 (0.0009) -[2023-10-09 01:52:37,259][88326] Updated weights for policy 0, policy_version 45062 (0.0007) -[2023-10-09 01:52:37,628][88326] Updated weights for policy 0, policy_version 45072 (0.0008) -[2023-10-09 01:52:37,988][88326] Updated weights for policy 0, policy_version 45082 (0.0008) -[2023-10-09 01:52:38,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 92340224. Throughput: 0: 1716.7, 1: 1686.8. Samples: 23085954. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) -[2023-10-09 01:52:38,975][87372] Avg episode reward: [(0, '6.720'), (1, '7.260')] -[2023-10-09 01:52:38,977][88168] Saving new best policy, reward=7.260! -[2023-10-09 01:52:40,293][88327] Updated weights for policy 1, policy_version 45090 (0.0009) -[2023-10-09 01:52:40,663][88327] Updated weights for policy 1, policy_version 45100 (0.0008) -[2023-10-09 01:52:41,035][88327] Updated weights for policy 1, policy_version 45110 (0.0009) -[2023-10-09 01:52:41,401][88327] Updated weights for policy 1, policy_version 45120 (0.0008) -[2023-10-09 01:52:41,978][88326] Updated weights for policy 0, policy_version 45092 (0.0008) -[2023-10-09 01:52:42,355][88326] Updated weights for policy 0, policy_version 45102 (0.0008) -[2023-10-09 01:52:42,717][88326] Updated weights for policy 0, policy_version 45112 (0.0007) -[2023-10-09 01:52:43,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 92405760. Throughput: 0: 1707.5, 1: 1681.5. Samples: 23106110. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) -[2023-10-09 01:52:43,975][87372] Avg episode reward: [(0, '6.660'), (1, '6.630')] -[2023-10-09 01:52:45,371][88327] Updated weights for policy 1, policy_version 45130 (0.0009) -[2023-10-09 01:52:45,733][88327] Updated weights for policy 1, policy_version 45140 (0.0009) -[2023-10-09 01:52:46,107][88327] Updated weights for policy 1, policy_version 45150 (0.0007) -[2023-10-09 01:52:46,802][88326] Updated weights for policy 0, policy_version 45122 (0.0008) -[2023-10-09 01:52:47,185][88326] Updated weights for policy 0, policy_version 45132 (0.0009) -[2023-10-09 01:52:47,555][88326] Updated weights for policy 0, policy_version 45142 (0.0010) -[2023-10-09 01:52:47,926][88326] Updated weights for policy 0, policy_version 45152 (0.0007) -[2023-10-09 01:52:48,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 92471296. Throughput: 0: 1684.2, 1: 1709.5. Samples: 23126320. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) -[2023-10-09 01:52:48,975][87372] Avg episode reward: [(0, '6.600'), (1, '6.290')] -[2023-10-09 01:52:50,206][88327] Updated weights for policy 1, policy_version 45160 (0.0009) -[2023-10-09 01:52:50,569][88327] Updated weights for policy 1, policy_version 45170 (0.0009) -[2023-10-09 01:52:50,938][88327] Updated weights for policy 1, policy_version 45180 (0.0011) -[2023-10-09 01:52:51,852][88326] Updated weights for policy 0, policy_version 45162 (0.0009) -[2023-10-09 01:52:52,227][88326] Updated weights for policy 0, policy_version 45172 (0.0007) -[2023-10-09 01:52:52,598][88326] Updated weights for policy 0, policy_version 45182 (0.0010) -[2023-10-09 01:52:53,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 92536832. Throughput: 0: 1711.6, 1: 1679.5. Samples: 23136660. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) -[2023-10-09 01:52:53,975][87372] Avg episode reward: [(0, '6.130'), (1, '6.520')] -[2023-10-09 01:52:55,143][88327] Updated weights for policy 1, policy_version 45190 (0.0009) -[2023-10-09 01:52:55,501][88327] Updated weights for policy 1, policy_version 45200 (0.0010) -[2023-10-09 01:52:55,865][88327] Updated weights for policy 1, policy_version 45210 (0.0010) -[2023-10-09 01:52:56,682][88326] Updated weights for policy 0, policy_version 45192 (0.0009) -[2023-10-09 01:52:57,056][88326] Updated weights for policy 0, policy_version 45202 (0.0009) -[2023-10-09 01:52:57,427][88326] Updated weights for policy 0, policy_version 45212 (0.0010) -[2023-10-09 01:52:58,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 92602368. Throughput: 0: 1691.8, 1: 1697.6. Samples: 23156762. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) -[2023-10-09 01:52:58,975][87372] Avg episode reward: [(0, '6.060'), (1, '5.810')] -[2023-10-09 01:52:59,865][88327] Updated weights for policy 1, policy_version 45220 (0.0009) -[2023-10-09 01:53:00,222][88327] Updated weights for policy 1, policy_version 45230 (0.0009) -[2023-10-09 01:53:00,592][88327] Updated weights for policy 1, policy_version 45240 (0.0007) -[2023-10-09 01:53:01,534][88326] Updated weights for policy 0, policy_version 45222 (0.0007) -[2023-10-09 01:53:01,900][88326] Updated weights for policy 0, policy_version 45232 (0.0007) -[2023-10-09 01:53:02,268][88326] Updated weights for policy 0, policy_version 45242 (0.0007) -[2023-10-09 01:53:03,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 92667904. Throughput: 0: 1687.3, 1: 1705.2. Samples: 23177200. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:53:03,974][87372] Avg episode reward: [(0, '5.720'), (1, '5.880')] -[2023-10-09 01:53:04,556][88327] Updated weights for policy 1, policy_version 45250 (0.0009) -[2023-10-09 01:53:04,920][88327] Updated weights for policy 1, policy_version 45260 (0.0010) -[2023-10-09 01:53:05,286][88327] Updated weights for policy 1, policy_version 45270 (0.0009) -[2023-10-09 01:53:05,650][88327] Updated weights for policy 1, policy_version 45280 (0.0009) -[2023-10-09 01:53:06,225][88326] Updated weights for policy 0, policy_version 45252 (0.0008) -[2023-10-09 01:53:06,601][88326] Updated weights for policy 0, policy_version 45262 (0.0008) -[2023-10-09 01:53:06,969][88326] Updated weights for policy 0, policy_version 45272 (0.0008) -[2023-10-09 01:53:08,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 92733440. Throughput: 0: 1701.0, 1: 1674.6. Samples: 23187484. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:53:08,975][87372] Avg episode reward: [(0, '6.010'), (1, '6.380')] -[2023-10-09 01:53:09,775][88327] Updated weights for policy 1, policy_version 45290 (0.0007) -[2023-10-09 01:53:10,153][88327] Updated weights for policy 1, policy_version 45300 (0.0008) -[2023-10-09 01:53:10,524][88327] Updated weights for policy 1, policy_version 45310 (0.0010) -[2023-10-09 01:53:10,993][88326] Updated weights for policy 0, policy_version 45282 (0.0007) -[2023-10-09 01:53:11,359][88326] Updated weights for policy 0, policy_version 45292 (0.0008) -[2023-10-09 01:53:11,723][88326] Updated weights for policy 0, policy_version 45302 (0.0010) -[2023-10-09 01:53:12,099][88326] Updated weights for policy 0, policy_version 45312 (0.0010) -[2023-10-09 01:53:13,974][87372] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 92798976. Throughput: 0: 1666.9, 1: 1706.3. Samples: 23207172. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:53:13,975][87372] Avg episode reward: [(0, '6.570'), (1, '6.410')] -[2023-10-09 01:53:14,562][88327] Updated weights for policy 1, policy_version 45320 (0.0009) -[2023-10-09 01:53:14,924][88327] Updated weights for policy 1, policy_version 45330 (0.0009) -[2023-10-09 01:53:15,299][88327] Updated weights for policy 1, policy_version 45340 (0.0009) -[2023-10-09 01:53:16,116][88326] Updated weights for policy 0, policy_version 45322 (0.0009) -[2023-10-09 01:53:16,481][88326] Updated weights for policy 0, policy_version 45332 (0.0008) -[2023-10-09 01:53:16,860][88326] Updated weights for policy 0, policy_version 45342 (0.0008) -[2023-10-09 01:53:18,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 92864512. Throughput: 0: 1695.4, 1: 1706.5. Samples: 23228232. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:53:18,975][87372] Avg episode reward: [(0, '6.580'), (1, '5.500')] -[2023-10-09 01:53:19,219][88327] Updated weights for policy 1, policy_version 45350 (0.0009) -[2023-10-09 01:53:19,588][88327] Updated weights for policy 1, policy_version 45360 (0.0007) -[2023-10-09 01:53:19,951][88327] Updated weights for policy 1, policy_version 45370 (0.0007) -[2023-10-09 01:53:20,776][88326] Updated weights for policy 0, policy_version 45352 (0.0010) -[2023-10-09 01:53:21,149][88326] Updated weights for policy 0, policy_version 45362 (0.0010) -[2023-10-09 01:53:21,519][88326] Updated weights for policy 0, policy_version 45372 (0.0009) -[2023-10-09 01:53:23,863][88327] Updated weights for policy 1, policy_version 45380 (0.0007) -[2023-10-09 01:53:23,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 92930048. Throughput: 0: 1683.3, 1: 1695.4. Samples: 23237992. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:53:23,975][87372] Avg episode reward: [(0, '6.480'), (1, '6.220')] -[2023-10-09 01:53:24,227][88327] Updated weights for policy 1, policy_version 45390 (0.0008) -[2023-10-09 01:53:24,601][88327] Updated weights for policy 1, policy_version 45400 (0.0009) -[2023-10-09 01:53:25,573][88326] Updated weights for policy 0, policy_version 45382 (0.0008) -[2023-10-09 01:53:25,940][88326] Updated weights for policy 0, policy_version 45392 (0.0007) -[2023-10-09 01:53:26,310][88326] Updated weights for policy 0, policy_version 45402 (0.0008) -[2023-10-09 01:53:28,572][88327] Updated weights for policy 1, policy_version 45410 (0.0009) -[2023-10-09 01:53:28,958][88327] Updated weights for policy 1, policy_version 45420 (0.0008) -[2023-10-09 01:53:28,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 92995584. Throughput: 0: 1678.0, 1: 1709.1. Samples: 23258528. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:53:28,975][87372] Avg episode reward: [(0, '6.760'), (1, '5.920')] -[2023-10-09 01:53:29,311][88327] Updated weights for policy 1, policy_version 45430 (0.0009) -[2023-10-09 01:53:29,683][88327] Updated weights for policy 1, policy_version 45440 (0.0008) -[2023-10-09 01:53:30,297][88326] Updated weights for policy 0, policy_version 45412 (0.0010) -[2023-10-09 01:53:30,668][88326] Updated weights for policy 0, policy_version 45422 (0.0010) -[2023-10-09 01:53:31,029][88326] Updated weights for policy 0, policy_version 45432 (0.0010) -[2023-10-09 01:53:33,804][88327] Updated weights for policy 1, policy_version 45450 (0.0010) -[2023-10-09 01:53:33,974][87372] Fps is (10 sec: 13106.8, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 93061120. Throughput: 0: 1702.0, 1: 1702.3. Samples: 23279512. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:53:33,975][87372] Avg episode reward: [(0, '7.350'), (1, '5.760')] -[2023-10-09 01:53:33,986][88088] Saving new best policy, reward=7.350! -[2023-10-09 01:53:34,163][88327] Updated weights for policy 1, policy_version 45460 (0.0010) -[2023-10-09 01:53:34,538][88327] Updated weights for policy 1, policy_version 45470 (0.0010) -[2023-10-09 01:53:34,985][88326] Updated weights for policy 0, policy_version 45442 (0.0008) -[2023-10-09 01:53:35,366][88326] Updated weights for policy 0, policy_version 45452 (0.0008) -[2023-10-09 01:53:35,723][88326] Updated weights for policy 0, policy_version 45462 (0.0009) -[2023-10-09 01:53:36,100][88326] Updated weights for policy 0, policy_version 45472 (0.0010) -[2023-10-09 01:53:38,569][88327] Updated weights for policy 1, policy_version 45480 (0.0009) -[2023-10-09 01:53:38,939][88327] Updated weights for policy 1, policy_version 45490 (0.0010) -[2023-10-09 01:53:38,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 93126656. Throughput: 0: 1677.1, 1: 1703.9. Samples: 23288802. Policy #0 lag: (min: 8.0, avg: 30.7, max: 40.0) -[2023-10-09 01:53:38,975][87372] Avg episode reward: [(0, '6.830'), (1, '6.330')] -[2023-10-09 01:53:39,309][88327] Updated weights for policy 1, policy_version 45500 (0.0009) -[2023-10-09 01:53:40,088][88326] Updated weights for policy 0, policy_version 45482 (0.0009) -[2023-10-09 01:53:40,462][88326] Updated weights for policy 0, policy_version 45492 (0.0011) -[2023-10-09 01:53:40,827][88326] Updated weights for policy 0, policy_version 45502 (0.0009) -[2023-10-09 01:53:43,344][88327] Updated weights for policy 1, policy_version 45510 (0.0008) -[2023-10-09 01:53:43,714][88327] Updated weights for policy 1, policy_version 45520 (0.0008) -[2023-10-09 01:53:43,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 93192192. Throughput: 0: 1695.7, 1: 1702.2. Samples: 23309668. Policy #0 lag: (min: 8.0, avg: 30.7, max: 40.0) -[2023-10-09 01:53:43,975][87372] Avg episode reward: [(0, '6.620'), (1, '6.170')] -[2023-10-09 01:53:44,084][88327] Updated weights for policy 1, policy_version 45530 (0.0009) -[2023-10-09 01:53:45,036][88326] Updated weights for policy 0, policy_version 45512 (0.0008) -[2023-10-09 01:53:45,402][88326] Updated weights for policy 0, policy_version 45522 (0.0007) -[2023-10-09 01:53:45,772][88326] Updated weights for policy 0, policy_version 45532 (0.0007) -[2023-10-09 01:53:48,083][88327] Updated weights for policy 1, policy_version 45540 (0.0008) -[2023-10-09 01:53:48,442][88327] Updated weights for policy 1, policy_version 45550 (0.0007) -[2023-10-09 01:53:48,805][88327] Updated weights for policy 1, policy_version 45560 (0.0007) -[2023-10-09 01:53:48,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 93257728. Throughput: 0: 1704.2, 1: 1698.0. Samples: 23330298. Policy #0 lag: (min: 8.0, avg: 30.7, max: 40.0) -[2023-10-09 01:53:48,975][87372] Avg episode reward: [(0, '6.300'), (1, '6.430')] -[2023-10-09 01:53:49,745][88326] Updated weights for policy 0, policy_version 45542 (0.0008) -[2023-10-09 01:53:50,114][88326] Updated weights for policy 0, policy_version 45552 (0.0007) -[2023-10-09 01:53:50,484][88326] Updated weights for policy 0, policy_version 45562 (0.0009) -[2023-10-09 01:53:52,995][88327] Updated weights for policy 1, policy_version 45570 (0.0008) -[2023-10-09 01:53:53,365][88327] Updated weights for policy 1, policy_version 45580 (0.0009) -[2023-10-09 01:53:53,733][88327] Updated weights for policy 1, policy_version 45590 (0.0011) -[2023-10-09 01:53:53,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 93323264. Throughput: 0: 1679.3, 1: 1704.0. Samples: 23339736. Policy #0 lag: (min: 8.0, avg: 30.7, max: 40.0) -[2023-10-09 01:53:53,975][87372] Avg episode reward: [(0, '5.970'), (1, '6.640')] -[2023-10-09 01:53:54,092][88327] Updated weights for policy 1, policy_version 45600 (0.0008) -[2023-10-09 01:53:54,514][88326] Updated weights for policy 0, policy_version 45572 (0.0007) -[2023-10-09 01:53:54,877][88326] Updated weights for policy 0, policy_version 45582 (0.0008) -[2023-10-09 01:53:55,252][88326] Updated weights for policy 0, policy_version 45592 (0.0008) -[2023-10-09 01:53:58,041][88327] Updated weights for policy 1, policy_version 45610 (0.0008) -[2023-10-09 01:53:58,403][88327] Updated weights for policy 1, policy_version 45620 (0.0010) -[2023-10-09 01:53:58,771][88327] Updated weights for policy 1, policy_version 45630 (0.0008) -[2023-10-09 01:53:58,974][87372] Fps is (10 sec: 16383.8, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 93421568. Throughput: 0: 1704.0, 1: 1708.6. Samples: 23360740. Policy #0 lag: (min: 8.0, avg: 30.7, max: 40.0) -[2023-10-09 01:53:58,975][87372] Avg episode reward: [(0, '6.040'), (1, '6.090')] -[2023-10-09 01:53:59,283][88326] Updated weights for policy 0, policy_version 45602 (0.0010) -[2023-10-09 01:53:59,656][88326] Updated weights for policy 0, policy_version 45612 (0.0009) -[2023-10-09 01:54:00,028][88326] Updated weights for policy 0, policy_version 45622 (0.0010) -[2023-10-09 01:54:00,394][88326] Updated weights for policy 0, policy_version 45632 (0.0008) -[2023-10-09 01:54:03,012][88327] Updated weights for policy 1, policy_version 45640 (0.0010) -[2023-10-09 01:54:03,383][88327] Updated weights for policy 1, policy_version 45650 (0.0011) -[2023-10-09 01:54:03,746][88327] Updated weights for policy 1, policy_version 45660 (0.0012) -[2023-10-09 01:54:03,974][87372] Fps is (10 sec: 16384.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 93487104. Throughput: 0: 1702.4, 1: 1690.9. Samples: 23380930. Policy #0 lag: (min: 8.0, avg: 30.7, max: 40.0) -[2023-10-09 01:54:03,975][87372] Avg episode reward: [(0, '5.860'), (1, '6.640')] -[2023-10-09 01:54:04,438][88326] Updated weights for policy 0, policy_version 45642 (0.0010) -[2023-10-09 01:54:04,807][88326] Updated weights for policy 0, policy_version 45652 (0.0010) -[2023-10-09 01:54:05,175][88326] Updated weights for policy 0, policy_version 45662 (0.0009) -[2023-10-09 01:54:07,773][88327] Updated weights for policy 1, policy_version 45670 (0.0009) -[2023-10-09 01:54:08,135][88327] Updated weights for policy 1, policy_version 45680 (0.0010) -[2023-10-09 01:54:08,495][88327] Updated weights for policy 1, policy_version 45690 (0.0008) -[2023-10-09 01:54:08,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 93552640. Throughput: 0: 1687.0, 1: 1699.4. Samples: 23390378. Policy #0 lag: (min: 23.0, avg: 26.7, max: 55.0) -[2023-10-09 01:54:08,974][87372] Avg episode reward: [(0, '6.240'), (1, '6.740')] -[2023-10-09 01:54:09,190][88326] Updated weights for policy 0, policy_version 45672 (0.0007) -[2023-10-09 01:54:09,569][88326] Updated weights for policy 0, policy_version 45682 (0.0007) -[2023-10-09 01:54:09,929][88326] Updated weights for policy 0, policy_version 45692 (0.0008) -[2023-10-09 01:54:12,453][88327] Updated weights for policy 1, policy_version 45700 (0.0007) -[2023-10-09 01:54:12,815][88327] Updated weights for policy 1, policy_version 45710 (0.0007) -[2023-10-09 01:54:13,180][88327] Updated weights for policy 1, policy_version 45720 (0.0008) -[2023-10-09 01:54:13,818][88326] Updated weights for policy 0, policy_version 45702 (0.0009) -[2023-10-09 01:54:13,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 93618176. Throughput: 0: 1707.2, 1: 1690.4. Samples: 23411422. Policy #0 lag: (min: 23.0, avg: 26.7, max: 55.0) -[2023-10-09 01:54:13,975][87372] Avg episode reward: [(0, '6.460'), (1, '6.270')] -[2023-10-09 01:54:14,192][88326] Updated weights for policy 0, policy_version 45712 (0.0008) -[2023-10-09 01:54:14,559][88326] Updated weights for policy 0, policy_version 45722 (0.0008) -[2023-10-09 01:54:17,245][88327] Updated weights for policy 1, policy_version 45730 (0.0008) -[2023-10-09 01:54:17,610][88327] Updated weights for policy 1, policy_version 45740 (0.0010) -[2023-10-09 01:54:17,981][88327] Updated weights for policy 1, policy_version 45750 (0.0009) -[2023-10-09 01:54:18,347][88327] Updated weights for policy 1, policy_version 45760 (0.0009) -[2023-10-09 01:54:18,473][88326] Updated weights for policy 0, policy_version 45732 (0.0009) -[2023-10-09 01:54:18,838][88326] Updated weights for policy 0, policy_version 45742 (0.0010) -[2023-10-09 01:54:18,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 93683712. Throughput: 0: 1706.6, 1: 1669.7. Samples: 23431446. Policy #0 lag: (min: 23.0, avg: 26.7, max: 55.0) -[2023-10-09 01:54:18,975][87372] Avg episode reward: [(0, '6.420'), (1, '6.060')] -[2023-10-09 01:54:19,204][88326] Updated weights for policy 0, policy_version 45752 (0.0011) -[2023-10-09 01:54:22,457][88327] Updated weights for policy 1, policy_version 45770 (0.0011) -[2023-10-09 01:54:22,824][88327] Updated weights for policy 1, policy_version 45780 (0.0010) -[2023-10-09 01:54:23,195][88327] Updated weights for policy 1, policy_version 45790 (0.0009) -[2023-10-09 01:54:23,341][88326] Updated weights for policy 0, policy_version 45762 (0.0009) -[2023-10-09 01:54:23,718][88326] Updated weights for policy 0, policy_version 45772 (0.0008) -[2023-10-09 01:54:23,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 93749248. Throughput: 0: 1706.9, 1: 1691.4. Samples: 23441726. Policy #0 lag: (min: 23.0, avg: 26.7, max: 55.0) -[2023-10-09 01:54:23,974][87372] Avg episode reward: [(0, '6.960'), (1, '6.330')] -[2023-10-09 01:54:24,083][88326] Updated weights for policy 0, policy_version 45782 (0.0009) -[2023-10-09 01:54:24,449][88326] Updated weights for policy 0, policy_version 45792 (0.0009) -[2023-10-09 01:54:27,217][88327] Updated weights for policy 1, policy_version 45800 (0.0007) -[2023-10-09 01:54:27,585][88327] Updated weights for policy 1, policy_version 45810 (0.0007) -[2023-10-09 01:54:27,955][88327] Updated weights for policy 1, policy_version 45820 (0.0008) -[2023-10-09 01:54:28,378][88326] Updated weights for policy 0, policy_version 45802 (0.0007) -[2023-10-09 01:54:28,756][88326] Updated weights for policy 0, policy_version 45812 (0.0010) -[2023-10-09 01:54:28,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 93814784. Throughput: 0: 1708.7, 1: 1687.4. Samples: 23462490. Policy #0 lag: (min: 23.0, avg: 26.7, max: 55.0) -[2023-10-09 01:54:28,975][87372] Avg episode reward: [(0, '6.900'), (1, '6.020')] -[2023-10-09 01:54:29,125][88326] Updated weights for policy 0, policy_version 45822 (0.0008) -[2023-10-09 01:54:31,952][88327] Updated weights for policy 1, policy_version 45830 (0.0010) -[2023-10-09 01:54:32,313][88327] Updated weights for policy 1, policy_version 45840 (0.0008) -[2023-10-09 01:54:32,690][88327] Updated weights for policy 1, policy_version 45850 (0.0007) -[2023-10-09 01:54:33,128][88326] Updated weights for policy 0, policy_version 45832 (0.0007) -[2023-10-09 01:54:33,499][88326] Updated weights for policy 0, policy_version 45842 (0.0007) -[2023-10-09 01:54:33,882][88326] Updated weights for policy 0, policy_version 45852 (0.0009) -[2023-10-09 01:54:33,974][87372] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 93880320. Throughput: 0: 1700.0, 1: 1667.4. Samples: 23481830. Policy #0 lag: (min: 23.0, avg: 26.7, max: 55.0) -[2023-10-09 01:54:33,975][87372] Avg episode reward: [(0, '6.200'), (1, '6.220')] -[2023-10-09 01:54:33,987][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000045856_46956544.pth... -[2023-10-09 01:54:34,018][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000044256_45318144.pth -[2023-10-09 01:54:34,021][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000045856_46956544.pth... -[2023-10-09 01:54:34,060][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000044256_45318144.pth -[2023-10-09 01:54:36,604][88327] Updated weights for policy 1, policy_version 45860 (0.0007) -[2023-10-09 01:54:36,956][88327] Updated weights for policy 1, policy_version 45870 (0.0009) -[2023-10-09 01:54:37,330][88327] Updated weights for policy 1, policy_version 45880 (0.0008) -[2023-10-09 01:54:37,919][88326] Updated weights for policy 0, policy_version 45862 (0.0008) -[2023-10-09 01:54:38,290][88326] Updated weights for policy 0, policy_version 45872 (0.0008) -[2023-10-09 01:54:38,671][88326] Updated weights for policy 0, policy_version 45882 (0.0008) -[2023-10-09 01:54:38,974][87372] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 93978624. Throughput: 0: 1705.3, 1: 1695.9. Samples: 23492790. Policy #0 lag: (min: 2.0, avg: 8.9, max: 34.0) -[2023-10-09 01:54:38,975][87372] Avg episode reward: [(0, '6.650'), (1, '6.110')] -[2023-10-09 01:54:41,429][88327] Updated weights for policy 1, policy_version 45890 (0.0011) -[2023-10-09 01:54:41,786][88327] Updated weights for policy 1, policy_version 45900 (0.0009) -[2023-10-09 01:54:42,160][88327] Updated weights for policy 1, policy_version 45910 (0.0009) -[2023-10-09 01:54:42,529][88327] Updated weights for policy 1, policy_version 45920 (0.0009) -[2023-10-09 01:54:42,881][88326] Updated weights for policy 0, policy_version 45892 (0.0007) -[2023-10-09 01:54:43,243][88326] Updated weights for policy 0, policy_version 45902 (0.0009) -[2023-10-09 01:54:43,599][88326] Updated weights for policy 0, policy_version 45912 (0.0010) -[2023-10-09 01:54:43,974][87372] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 94044160. Throughput: 0: 1704.1, 1: 1670.4. Samples: 23512594. Policy #0 lag: (min: 2.0, avg: 8.9, max: 34.0) -[2023-10-09 01:54:43,975][87372] Avg episode reward: [(0, '6.610'), (1, '6.390')] -[2023-10-09 01:54:46,628][88327] Updated weights for policy 1, policy_version 45930 (0.0009) -[2023-10-09 01:54:46,990][88327] Updated weights for policy 1, policy_version 45940 (0.0007) -[2023-10-09 01:54:47,359][88327] Updated weights for policy 1, policy_version 45950 (0.0007) -[2023-10-09 01:54:47,732][88326] Updated weights for policy 0, policy_version 45922 (0.0009) -[2023-10-09 01:54:48,095][88326] Updated weights for policy 0, policy_version 45932 (0.0008) -[2023-10-09 01:54:48,468][88326] Updated weights for policy 0, policy_version 45942 (0.0010) -[2023-10-09 01:54:48,839][88326] Updated weights for policy 0, policy_version 45952 (0.0009) -[2023-10-09 01:54:48,974][87372] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 94109696. Throughput: 0: 1690.6, 1: 1674.6. Samples: 23532364. Policy #0 lag: (min: 2.0, avg: 8.9, max: 34.0) -[2023-10-09 01:54:48,975][87372] Avg episode reward: [(0, '6.630'), (1, '6.380')] -[2023-10-09 01:54:51,412][88327] Updated weights for policy 1, policy_version 45960 (0.0010) -[2023-10-09 01:54:51,778][88327] Updated weights for policy 1, policy_version 45970 (0.0010) -[2023-10-09 01:54:52,147][88327] Updated weights for policy 1, policy_version 45980 (0.0009) -[2023-10-09 01:54:53,074][88326] Updated weights for policy 0, policy_version 45962 (0.0008) -[2023-10-09 01:54:53,438][88326] Updated weights for policy 0, policy_version 45972 (0.0009) -[2023-10-09 01:54:53,805][88326] Updated weights for policy 0, policy_version 45982 (0.0009) -[2023-10-09 01:54:53,974][87372] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 94175232. Throughput: 0: 1704.4, 1: 1693.8. Samples: 23543296. Policy #0 lag: (min: 2.0, avg: 8.9, max: 34.0) -[2023-10-09 01:54:53,975][87372] Avg episode reward: [(0, '6.280'), (1, '6.280')] -[2023-10-09 01:54:56,187][88327] Updated weights for policy 1, policy_version 45990 (0.0008) -[2023-10-09 01:54:56,569][88327] Updated weights for policy 1, policy_version 46000 (0.0011) -[2023-10-09 01:54:56,927][88327] Updated weights for policy 1, policy_version 46010 (0.0009) -[2023-10-09 01:54:57,706][88326] Updated weights for policy 0, policy_version 45992 (0.0007) -[2023-10-09 01:54:58,072][88326] Updated weights for policy 0, policy_version 46002 (0.0009) -[2023-10-09 01:54:58,446][88326] Updated weights for policy 0, policy_version 46012 (0.0008) -[2023-10-09 01:54:58,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 94240768. Throughput: 0: 1695.0, 1: 1670.9. Samples: 23562886. Policy #0 lag: (min: 2.0, avg: 8.9, max: 34.0) -[2023-10-09 01:54:58,975][87372] Avg episode reward: [(0, '6.140'), (1, '5.970')] -[2023-10-09 01:55:01,052][88327] Updated weights for policy 1, policy_version 46020 (0.0008) -[2023-10-09 01:55:01,417][88327] Updated weights for policy 1, policy_version 46030 (0.0008) -[2023-10-09 01:55:01,774][88327] Updated weights for policy 1, policy_version 46040 (0.0009) -[2023-10-09 01:55:02,333][88326] Updated weights for policy 0, policy_version 46022 (0.0007) -[2023-10-09 01:55:02,706][88326] Updated weights for policy 0, policy_version 46032 (0.0007) -[2023-10-09 01:55:03,066][88326] Updated weights for policy 0, policy_version 46042 (0.0009) -[2023-10-09 01:55:03,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 94306304. Throughput: 0: 1667.1, 1: 1691.3. Samples: 23582574. Policy #0 lag: (min: 2.0, avg: 8.9, max: 34.0) -[2023-10-09 01:55:03,974][87372] Avg episode reward: [(0, '6.640'), (1, '5.830')] -[2023-10-09 01:55:05,879][88327] Updated weights for policy 1, policy_version 46050 (0.0009) -[2023-10-09 01:55:06,254][88327] Updated weights for policy 1, policy_version 46060 (0.0009) -[2023-10-09 01:55:06,620][88327] Updated weights for policy 1, policy_version 46070 (0.0007) -[2023-10-09 01:55:06,981][88327] Updated weights for policy 1, policy_version 46080 (0.0007) -[2023-10-09 01:55:07,181][88326] Updated weights for policy 0, policy_version 46052 (0.0009) -[2023-10-09 01:55:07,547][88326] Updated weights for policy 0, policy_version 46062 (0.0007) -[2023-10-09 01:55:07,926][88326] Updated weights for policy 0, policy_version 46072 (0.0010) -[2023-10-09 01:55:08,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 94371840. Throughput: 0: 1690.8, 1: 1686.7. Samples: 23593712. Policy #0 lag: (min: 31.0, avg: 40.7, max: 63.0) -[2023-10-09 01:55:08,975][87372] Avg episode reward: [(0, '6.440'), (1, '6.320')] -[2023-10-09 01:55:11,009][88327] Updated weights for policy 1, policy_version 46090 (0.0010) -[2023-10-09 01:55:11,368][88327] Updated weights for policy 1, policy_version 46100 (0.0009) -[2023-10-09 01:55:11,734][88327] Updated weights for policy 1, policy_version 46110 (0.0009) -[2023-10-09 01:55:11,809][88326] Updated weights for policy 0, policy_version 46082 (0.0009) -[2023-10-09 01:55:12,173][88326] Updated weights for policy 0, policy_version 46092 (0.0011) -[2023-10-09 01:55:12,534][88326] Updated weights for policy 0, policy_version 46102 (0.0010) -[2023-10-09 01:55:12,908][88326] Updated weights for policy 0, policy_version 46112 (0.0011) -[2023-10-09 01:55:13,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 94437376. Throughput: 0: 1677.3, 1: 1668.8. Samples: 23613066. Policy #0 lag: (min: 31.0, avg: 40.7, max: 63.0) -[2023-10-09 01:55:13,975][87372] Avg episode reward: [(0, '6.330'), (1, '6.690')] -[2023-10-09 01:55:15,856][88327] Updated weights for policy 1, policy_version 46120 (0.0008) -[2023-10-09 01:55:16,236][88327] Updated weights for policy 1, policy_version 46130 (0.0009) -[2023-10-09 01:55:16,598][88327] Updated weights for policy 1, policy_version 46140 (0.0010) -[2023-10-09 01:55:16,937][88326] Updated weights for policy 0, policy_version 46122 (0.0007) -[2023-10-09 01:55:17,302][88326] Updated weights for policy 0, policy_version 46132 (0.0010) -[2023-10-09 01:55:17,676][88326] Updated weights for policy 0, policy_version 46142 (0.0009) -[2023-10-09 01:55:18,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 94502912. Throughput: 0: 1670.1, 1: 1691.1. Samples: 23633084. Policy #0 lag: (min: 31.0, avg: 40.7, max: 63.0) -[2023-10-09 01:55:18,974][87372] Avg episode reward: [(0, '6.590'), (1, '6.550')] -[2023-10-09 01:55:20,591][88327] Updated weights for policy 1, policy_version 46150 (0.0008) -[2023-10-09 01:55:20,956][88327] Updated weights for policy 1, policy_version 46160 (0.0010) -[2023-10-09 01:55:21,316][88327] Updated weights for policy 1, policy_version 46170 (0.0007) -[2023-10-09 01:55:21,889][88326] Updated weights for policy 0, policy_version 46152 (0.0009) -[2023-10-09 01:55:22,255][88326] Updated weights for policy 0, policy_version 46162 (0.0010) -[2023-10-09 01:55:22,619][88326] Updated weights for policy 0, policy_version 46172 (0.0010) -[2023-10-09 01:55:23,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 94568448. Throughput: 0: 1687.8, 1: 1668.5. Samples: 23643826. Policy #0 lag: (min: 31.0, avg: 40.7, max: 63.0) -[2023-10-09 01:55:23,975][87372] Avg episode reward: [(0, '6.260'), (1, '6.450')] -[2023-10-09 01:55:25,320][88327] Updated weights for policy 1, policy_version 46180 (0.0007) -[2023-10-09 01:55:25,679][88327] Updated weights for policy 1, policy_version 46190 (0.0011) -[2023-10-09 01:55:26,047][88327] Updated weights for policy 1, policy_version 46200 (0.0008) -[2023-10-09 01:55:26,504][88326] Updated weights for policy 0, policy_version 46182 (0.0008) -[2023-10-09 01:55:26,869][88326] Updated weights for policy 0, policy_version 46192 (0.0007) -[2023-10-09 01:55:27,247][88326] Updated weights for policy 0, policy_version 46202 (0.0007) -[2023-10-09 01:55:28,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 94633984. Throughput: 0: 1677.4, 1: 1678.1. Samples: 23663592. Policy #0 lag: (min: 31.0, avg: 40.7, max: 63.0) -[2023-10-09 01:55:28,975][87372] Avg episode reward: [(0, '6.030'), (1, '6.090')] -[2023-10-09 01:55:30,111][88327] Updated weights for policy 1, policy_version 46210 (0.0008) -[2023-10-09 01:55:30,471][88327] Updated weights for policy 1, policy_version 46220 (0.0010) -[2023-10-09 01:55:30,839][88327] Updated weights for policy 1, policy_version 46230 (0.0010) -[2023-10-09 01:55:31,205][88327] Updated weights for policy 1, policy_version 46240 (0.0009) -[2023-10-09 01:55:31,380][88326] Updated weights for policy 0, policy_version 46212 (0.0009) -[2023-10-09 01:55:31,755][88326] Updated weights for policy 0, policy_version 46222 (0.0010) -[2023-10-09 01:55:32,128][88326] Updated weights for policy 0, policy_version 46232 (0.0009) -[2023-10-09 01:55:33,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 94699520. Throughput: 0: 1680.9, 1: 1690.8. Samples: 23684088. Policy #0 lag: (min: 31.0, avg: 40.7, max: 63.0) -[2023-10-09 01:55:33,975][87372] Avg episode reward: [(0, '6.370'), (1, '6.110')] -[2023-10-09 01:55:35,295][88327] Updated weights for policy 1, policy_version 46250 (0.0010) -[2023-10-09 01:55:35,666][88327] Updated weights for policy 1, policy_version 46260 (0.0009) -[2023-10-09 01:55:36,025][88327] Updated weights for policy 1, policy_version 46270 (0.0007) -[2023-10-09 01:55:36,093][88326] Updated weights for policy 0, policy_version 46242 (0.0008) -[2023-10-09 01:55:36,463][88326] Updated weights for policy 0, policy_version 46252 (0.0007) -[2023-10-09 01:55:36,827][88326] Updated weights for policy 0, policy_version 46262 (0.0009) -[2023-10-09 01:55:37,196][88326] Updated weights for policy 0, policy_version 46272 (0.0008) -[2023-10-09 01:55:38,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 94765056. Throughput: 0: 1695.9, 1: 1662.8. Samples: 23694436. Policy #0 lag: (min: 31.0, avg: 40.7, max: 63.0) -[2023-10-09 01:55:38,975][87372] Avg episode reward: [(0, '6.760'), (1, '6.380')] -[2023-10-09 01:55:39,809][88327] Updated weights for policy 1, policy_version 46280 (0.0010) -[2023-10-09 01:55:40,180][88327] Updated weights for policy 1, policy_version 46290 (0.0009) -[2023-10-09 01:55:40,529][88327] Updated weights for policy 1, policy_version 46300 (0.0010) -[2023-10-09 01:55:41,372][88326] Updated weights for policy 0, policy_version 46282 (0.0007) -[2023-10-09 01:55:41,732][88326] Updated weights for policy 0, policy_version 46292 (0.0008) -[2023-10-09 01:55:42,110][88326] Updated weights for policy 0, policy_version 46302 (0.0009) -[2023-10-09 01:55:43,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 94830592. Throughput: 0: 1669.9, 1: 1695.4. Samples: 23714324. Policy #0 lag: (min: 8.0, avg: 31.4, max: 40.0) -[2023-10-09 01:55:43,975][87372] Avg episode reward: [(0, '6.380'), (1, '6.180')] -[2023-10-09 01:55:44,568][88327] Updated weights for policy 1, policy_version 46310 (0.0009) -[2023-10-09 01:55:44,929][88327] Updated weights for policy 1, policy_version 46320 (0.0008) -[2023-10-09 01:55:45,310][88327] Updated weights for policy 1, policy_version 46330 (0.0009) -[2023-10-09 01:55:46,238][88326] Updated weights for policy 0, policy_version 46312 (0.0007) -[2023-10-09 01:55:46,603][88326] Updated weights for policy 0, policy_version 46322 (0.0007) -[2023-10-09 01:55:46,985][88326] Updated weights for policy 0, policy_version 46332 (0.0008) -[2023-10-09 01:55:48,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 94896128. Throughput: 0: 1691.7, 1: 1697.4. Samples: 23735086. Policy #0 lag: (min: 8.0, avg: 31.4, max: 40.0) -[2023-10-09 01:55:48,975][87372] Avg episode reward: [(0, '6.560'), (1, '6.370')] -[2023-10-09 01:55:49,399][88327] Updated weights for policy 1, policy_version 46340 (0.0008) -[2023-10-09 01:55:49,757][88327] Updated weights for policy 1, policy_version 46350 (0.0007) -[2023-10-09 01:55:50,130][88327] Updated weights for policy 1, policy_version 46360 (0.0009) -[2023-10-09 01:55:51,123][88326] Updated weights for policy 0, policy_version 46342 (0.0008) -[2023-10-09 01:55:51,487][88326] Updated weights for policy 0, policy_version 46352 (0.0008) -[2023-10-09 01:55:51,857][88326] Updated weights for policy 0, policy_version 46362 (0.0010) -[2023-10-09 01:55:53,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 94961664. Throughput: 0: 1686.1, 1: 1676.1. Samples: 23745012. Policy #0 lag: (min: 8.0, avg: 31.4, max: 40.0) -[2023-10-09 01:55:53,975][87372] Avg episode reward: [(0, '6.410'), (1, '6.070')] -[2023-10-09 01:55:54,226][88327] Updated weights for policy 1, policy_version 46370 (0.0008) -[2023-10-09 01:55:54,597][88327] Updated weights for policy 1, policy_version 46380 (0.0011) -[2023-10-09 01:55:54,961][88327] Updated weights for policy 1, policy_version 46390 (0.0009) -[2023-10-09 01:55:55,329][88327] Updated weights for policy 1, policy_version 46400 (0.0009) -[2023-10-09 01:55:55,817][88326] Updated weights for policy 0, policy_version 46372 (0.0008) -[2023-10-09 01:55:56,184][88326] Updated weights for policy 0, policy_version 46382 (0.0008) -[2023-10-09 01:55:56,552][88326] Updated weights for policy 0, policy_version 46392 (0.0008) -[2023-10-09 01:55:58,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 95027200. Throughput: 0: 1680.3, 1: 1703.2. Samples: 23765320. Policy #0 lag: (min: 8.0, avg: 31.4, max: 40.0) -[2023-10-09 01:55:58,975][87372] Avg episode reward: [(0, '6.760'), (1, '5.890')] -[2023-10-09 01:55:59,356][88327] Updated weights for policy 1, policy_version 46410 (0.0009) -[2023-10-09 01:55:59,710][88327] Updated weights for policy 1, policy_version 46420 (0.0009) -[2023-10-09 01:56:00,079][88327] Updated weights for policy 1, policy_version 46430 (0.0008) -[2023-10-09 01:56:00,315][88326] Updated weights for policy 0, policy_version 46402 (0.0007) -[2023-10-09 01:56:00,691][88326] Updated weights for policy 0, policy_version 46412 (0.0007) -[2023-10-09 01:56:01,058][88326] Updated weights for policy 0, policy_version 46422 (0.0007) -[2023-10-09 01:56:01,430][88326] Updated weights for policy 0, policy_version 46432 (0.0008) -[2023-10-09 01:56:03,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 95092736. Throughput: 0: 1709.3, 1: 1704.9. Samples: 23786724. Policy #0 lag: (min: 8.0, avg: 31.4, max: 40.0) -[2023-10-09 01:56:03,974][87372] Avg episode reward: [(0, '6.500'), (1, '5.960')] -[2023-10-09 01:56:04,141][88327] Updated weights for policy 1, policy_version 46440 (0.0007) -[2023-10-09 01:56:04,497][88327] Updated weights for policy 1, policy_version 46450 (0.0007) -[2023-10-09 01:56:04,860][88327] Updated weights for policy 1, policy_version 46460 (0.0009) -[2023-10-09 01:56:05,412][88326] Updated weights for policy 0, policy_version 46442 (0.0009) -[2023-10-09 01:56:05,784][88326] Updated weights for policy 0, policy_version 46452 (0.0007) -[2023-10-09 01:56:06,147][88326] Updated weights for policy 0, policy_version 46462 (0.0007) -[2023-10-09 01:56:08,960][88327] Updated weights for policy 1, policy_version 46470 (0.0008) -[2023-10-09 01:56:08,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 95158272. Throughput: 0: 1687.4, 1: 1693.3. Samples: 23795956. Policy #0 lag: (min: 8.0, avg: 31.4, max: 40.0) -[2023-10-09 01:56:08,974][87372] Avg episode reward: [(0, '7.340'), (1, '6.600')] -[2023-10-09 01:56:09,316][88327] Updated weights for policy 1, policy_version 46480 (0.0007) -[2023-10-09 01:56:09,681][88327] Updated weights for policy 1, policy_version 46490 (0.0007) -[2023-10-09 01:56:10,296][88326] Updated weights for policy 0, policy_version 46472 (0.0008) -[2023-10-09 01:56:10,669][88326] Updated weights for policy 0, policy_version 46482 (0.0008) -[2023-10-09 01:56:11,033][88326] Updated weights for policy 0, policy_version 46492 (0.0010) -[2023-10-09 01:56:13,686][88327] Updated weights for policy 1, policy_version 46500 (0.0007) -[2023-10-09 01:56:13,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 95223808. Throughput: 0: 1696.1, 1: 1703.3. Samples: 23816564. Policy #0 lag: (min: 8.0, avg: 31.4, max: 40.0) -[2023-10-09 01:56:13,975][87372] Avg episode reward: [(0, '6.850'), (1, '6.140')] -[2023-10-09 01:56:14,057][88327] Updated weights for policy 1, policy_version 46510 (0.0009) -[2023-10-09 01:56:14,434][88327] Updated weights for policy 1, policy_version 46520 (0.0007) -[2023-10-09 01:56:14,897][88326] Updated weights for policy 0, policy_version 46502 (0.0009) -[2023-10-09 01:56:15,267][88326] Updated weights for policy 0, policy_version 46512 (0.0011) -[2023-10-09 01:56:15,648][88326] Updated weights for policy 0, policy_version 46522 (0.0009) -[2023-10-09 01:56:18,276][88327] Updated weights for policy 1, policy_version 46530 (0.0008) -[2023-10-09 01:56:18,644][88327] Updated weights for policy 1, policy_version 46540 (0.0010) -[2023-10-09 01:56:18,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 95289344. Throughput: 0: 1707.0, 1: 1709.1. Samples: 23837812. Policy #0 lag: (min: 19.0, avg: 23.0, max: 51.0) -[2023-10-09 01:56:18,975][87372] Avg episode reward: [(0, '6.670'), (1, '6.520')] -[2023-10-09 01:56:19,009][88327] Updated weights for policy 1, policy_version 46550 (0.0008) -[2023-10-09 01:56:19,368][88327] Updated weights for policy 1, policy_version 46560 (0.0008) -[2023-10-09 01:56:19,672][88326] Updated weights for policy 0, policy_version 46532 (0.0007) -[2023-10-09 01:56:20,040][88326] Updated weights for policy 0, policy_version 46542 (0.0007) -[2023-10-09 01:56:20,412][88326] Updated weights for policy 0, policy_version 46552 (0.0009) -[2023-10-09 01:56:23,544][88327] Updated weights for policy 1, policy_version 46570 (0.0008) -[2023-10-09 01:56:23,903][88327] Updated weights for policy 1, policy_version 46580 (0.0011) -[2023-10-09 01:56:23,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 95354880. Throughput: 0: 1681.7, 1: 1708.7. Samples: 23847002. Policy #0 lag: (min: 19.0, avg: 23.0, max: 51.0) -[2023-10-09 01:56:23,975][87372] Avg episode reward: [(0, '6.840'), (1, '6.380')] -[2023-10-09 01:56:24,265][88327] Updated weights for policy 1, policy_version 46590 (0.0008) -[2023-10-09 01:56:24,419][88326] Updated weights for policy 0, policy_version 46562 (0.0008) -[2023-10-09 01:56:24,796][88326] Updated weights for policy 0, policy_version 46572 (0.0009) -[2023-10-09 01:56:25,156][88326] Updated weights for policy 0, policy_version 46582 (0.0010) -[2023-10-09 01:56:25,523][88326] Updated weights for policy 0, policy_version 46592 (0.0010) -[2023-10-09 01:56:28,344][88327] Updated weights for policy 1, policy_version 46600 (0.0007) -[2023-10-09 01:56:28,718][88327] Updated weights for policy 1, policy_version 46610 (0.0009) -[2023-10-09 01:56:28,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 95420416. Throughput: 0: 1707.9, 1: 1700.2. Samples: 23867688. Policy #0 lag: (min: 19.0, avg: 23.0, max: 51.0) -[2023-10-09 01:56:28,975][87372] Avg episode reward: [(0, '6.320'), (1, '5.730')] -[2023-10-09 01:56:29,072][88327] Updated weights for policy 1, policy_version 46620 (0.0011) -[2023-10-09 01:56:29,502][88326] Updated weights for policy 0, policy_version 46602 (0.0010) -[2023-10-09 01:56:29,876][88326] Updated weights for policy 0, policy_version 46612 (0.0008) -[2023-10-09 01:56:30,233][88326] Updated weights for policy 0, policy_version 46622 (0.0011) -[2023-10-09 01:56:33,075][88327] Updated weights for policy 1, policy_version 46630 (0.0010) -[2023-10-09 01:56:33,438][88327] Updated weights for policy 1, policy_version 46640 (0.0008) -[2023-10-09 01:56:33,803][88327] Updated weights for policy 1, policy_version 46650 (0.0007) -[2023-10-09 01:56:33,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 95485952. Throughput: 0: 1710.7, 1: 1694.3. Samples: 23888310. Policy #0 lag: (min: 19.0, avg: 23.0, max: 51.0) -[2023-10-09 01:56:33,975][87372] Avg episode reward: [(0, '6.430'), (1, '6.250')] -[2023-10-09 01:56:34,014][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000046656_47775744.pth... -[2023-10-09 01:56:34,049][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000045056_46137344.pth -[2023-10-09 01:56:34,381][88326] Updated weights for policy 0, policy_version 46632 (0.0009) -[2023-10-09 01:56:34,761][88326] Updated weights for policy 0, policy_version 46642 (0.0008) -[2023-10-09 01:56:35,123][88326] Updated weights for policy 0, policy_version 46652 (0.0008) -[2023-10-09 01:56:35,271][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000046656_47775744.pth... -[2023-10-09 01:56:35,304][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000045056_46137344.pth -[2023-10-09 01:56:37,969][88327] Updated weights for policy 1, policy_version 46660 (0.0008) -[2023-10-09 01:56:38,328][88327] Updated weights for policy 1, policy_version 46670 (0.0010) -[2023-10-09 01:56:38,694][88327] Updated weights for policy 1, policy_version 46680 (0.0008) -[2023-10-09 01:56:38,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 95551488. Throughput: 0: 1685.8, 1: 1703.5. Samples: 23897530. Policy #0 lag: (min: 19.0, avg: 23.0, max: 51.0) -[2023-10-09 01:56:38,975][87372] Avg episode reward: [(0, '7.000'), (1, '6.110')] -[2023-10-09 01:56:39,148][88326] Updated weights for policy 0, policy_version 46662 (0.0010) -[2023-10-09 01:56:39,512][88326] Updated weights for policy 0, policy_version 46672 (0.0009) -[2023-10-09 01:56:39,879][88326] Updated weights for policy 0, policy_version 46682 (0.0008) -[2023-10-09 01:56:42,729][88327] Updated weights for policy 1, policy_version 46690 (0.0009) -[2023-10-09 01:56:43,093][88327] Updated weights for policy 1, policy_version 46700 (0.0008) -[2023-10-09 01:56:43,461][88327] Updated weights for policy 1, policy_version 46710 (0.0007) -[2023-10-09 01:56:43,825][88327] Updated weights for policy 1, policy_version 46720 (0.0007) -[2023-10-09 01:56:43,944][88326] Updated weights for policy 0, policy_version 46692 (0.0008) -[2023-10-09 01:56:43,974][87372] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 95649792. Throughput: 0: 1702.0, 1: 1698.1. Samples: 23918322. Policy #0 lag: (min: 19.0, avg: 23.0, max: 51.0) -[2023-10-09 01:56:43,975][87372] Avg episode reward: [(0, '6.680'), (1, '5.740')] -[2023-10-09 01:56:44,312][88326] Updated weights for policy 0, policy_version 46702 (0.0007) -[2023-10-09 01:56:44,676][88326] Updated weights for policy 0, policy_version 46712 (0.0007) -[2023-10-09 01:56:47,898][88327] Updated weights for policy 1, policy_version 46730 (0.0008) -[2023-10-09 01:56:48,262][88327] Updated weights for policy 1, policy_version 46740 (0.0009) -[2023-10-09 01:56:48,627][88327] Updated weights for policy 1, policy_version 46750 (0.0009) -[2023-10-09 01:56:48,732][88326] Updated weights for policy 0, policy_version 46722 (0.0008) -[2023-10-09 01:56:48,974][87372] Fps is (10 sec: 16384.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 95715328. Throughput: 0: 1688.8, 1: 1682.8. Samples: 23938448. Policy #0 lag: (min: 19.0, avg: 23.0, max: 51.0) -[2023-10-09 01:56:48,974][87372] Avg episode reward: [(0, '6.480'), (1, '6.230')] -[2023-10-09 01:56:49,103][88326] Updated weights for policy 0, policy_version 46732 (0.0009) -[2023-10-09 01:56:49,465][88326] Updated weights for policy 0, policy_version 46742 (0.0007) -[2023-10-09 01:56:49,839][88326] Updated weights for policy 0, policy_version 46752 (0.0007) -[2023-10-09 01:56:52,671][88327] Updated weights for policy 1, policy_version 46760 (0.0008) -[2023-10-09 01:56:53,043][88327] Updated weights for policy 1, policy_version 46770 (0.0009) -[2023-10-09 01:56:53,409][88327] Updated weights for policy 1, policy_version 46780 (0.0007) -[2023-10-09 01:56:53,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 95780864. Throughput: 0: 1684.4, 1: 1699.6. Samples: 23948232. Policy #0 lag: (min: 3.0, avg: 13.7, max: 35.0) -[2023-10-09 01:56:53,974][87372] Avg episode reward: [(0, '6.660'), (1, '6.070')] -[2023-10-09 01:56:53,994][88326] Updated weights for policy 0, policy_version 46762 (0.0008) -[2023-10-09 01:56:54,365][88326] Updated weights for policy 0, policy_version 46772 (0.0008) -[2023-10-09 01:56:54,744][88326] Updated weights for policy 0, policy_version 46782 (0.0008) -[2023-10-09 01:56:57,376][88327] Updated weights for policy 1, policy_version 46790 (0.0008) -[2023-10-09 01:56:57,741][88327] Updated weights for policy 1, policy_version 46800 (0.0008) -[2023-10-09 01:56:58,111][88327] Updated weights for policy 1, policy_version 46810 (0.0007) -[2023-10-09 01:56:58,806][88326] Updated weights for policy 0, policy_version 46792 (0.0007) -[2023-10-09 01:56:58,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 95846400. Throughput: 0: 1684.9, 1: 1702.0. Samples: 23968978. Policy #0 lag: (min: 3.0, avg: 13.7, max: 35.0) -[2023-10-09 01:56:58,975][87372] Avg episode reward: [(0, '6.890'), (1, '6.140')] -[2023-10-09 01:56:59,169][88326] Updated weights for policy 0, policy_version 46802 (0.0008) -[2023-10-09 01:56:59,533][88326] Updated weights for policy 0, policy_version 46812 (0.0007) -[2023-10-09 01:57:02,094][88327] Updated weights for policy 1, policy_version 46820 (0.0008) -[2023-10-09 01:57:02,465][88327] Updated weights for policy 1, policy_version 46830 (0.0007) -[2023-10-09 01:57:02,825][88327] Updated weights for policy 1, policy_version 46840 (0.0007) -[2023-10-09 01:57:03,451][88326] Updated weights for policy 0, policy_version 46822 (0.0007) -[2023-10-09 01:57:03,816][88326] Updated weights for policy 0, policy_version 46832 (0.0009) -[2023-10-09 01:57:03,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 95911936. Throughput: 0: 1689.1, 1: 1668.1. Samples: 23988886. Policy #0 lag: (min: 3.0, avg: 13.7, max: 35.0) -[2023-10-09 01:57:03,974][87372] Avg episode reward: [(0, '6.690'), (1, '6.550')] -[2023-10-09 01:57:04,182][88326] Updated weights for policy 0, policy_version 46842 (0.0011) -[2023-10-09 01:57:06,681][88327] Updated weights for policy 1, policy_version 46850 (0.0007) -[2023-10-09 01:57:07,041][88327] Updated weights for policy 1, policy_version 46860 (0.0010) -[2023-10-09 01:57:07,403][88327] Updated weights for policy 1, policy_version 46870 (0.0007) -[2023-10-09 01:57:07,763][88327] Updated weights for policy 1, policy_version 46880 (0.0007) -[2023-10-09 01:57:08,363][88326] Updated weights for policy 0, policy_version 46852 (0.0009) -[2023-10-09 01:57:08,723][88326] Updated weights for policy 0, policy_version 46862 (0.0008) -[2023-10-09 01:57:08,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 95977472. Throughput: 0: 1685.4, 1: 1701.8. Samples: 23999426. Policy #0 lag: (min: 3.0, avg: 13.7, max: 35.0) -[2023-10-09 01:57:08,975][87372] Avg episode reward: [(0, '6.600'), (1, '6.780')] -[2023-10-09 01:57:09,089][88326] Updated weights for policy 0, policy_version 46872 (0.0008) -[2023-10-09 01:57:11,863][88327] Updated weights for policy 1, policy_version 46890 (0.0007) -[2023-10-09 01:57:12,238][88327] Updated weights for policy 1, policy_version 46900 (0.0007) -[2023-10-09 01:57:12,605][88327] Updated weights for policy 1, policy_version 46910 (0.0007) -[2023-10-09 01:57:13,021][88326] Updated weights for policy 0, policy_version 46882 (0.0009) -[2023-10-09 01:57:13,394][88326] Updated weights for policy 0, policy_version 46892 (0.0007) -[2023-10-09 01:57:13,760][88326] Updated weights for policy 0, policy_version 46902 (0.0008) -[2023-10-09 01:57:13,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 96043008. Throughput: 0: 1690.3, 1: 1690.3. Samples: 24019812. Policy #0 lag: (min: 3.0, avg: 13.7, max: 35.0) -[2023-10-09 01:57:13,975][87372] Avg episode reward: [(0, '6.830'), (1, '6.250')] -[2023-10-09 01:57:14,132][88326] Updated weights for policy 0, policy_version 46912 (0.0010) -[2023-10-09 01:57:16,554][88327] Updated weights for policy 1, policy_version 46920 (0.0007) -[2023-10-09 01:57:16,918][88327] Updated weights for policy 1, policy_version 46930 (0.0008) -[2023-10-09 01:57:17,289][88327] Updated weights for policy 1, policy_version 46940 (0.0008) -[2023-10-09 01:57:18,301][88326] Updated weights for policy 0, policy_version 46922 (0.0011) -[2023-10-09 01:57:18,665][88326] Updated weights for policy 0, policy_version 46932 (0.0008) -[2023-10-09 01:57:18,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 96108544. Throughput: 0: 1680.7, 1: 1686.8. Samples: 24039848. Policy #0 lag: (min: 3.0, avg: 13.7, max: 35.0) -[2023-10-09 01:57:18,975][87372] Avg episode reward: [(0, '6.850'), (1, '6.210')] -[2023-10-09 01:57:19,030][88326] Updated weights for policy 0, policy_version 46942 (0.0009) -[2023-10-09 01:57:21,414][88327] Updated weights for policy 1, policy_version 46950 (0.0009) -[2023-10-09 01:57:21,775][88327] Updated weights for policy 1, policy_version 46960 (0.0009) -[2023-10-09 01:57:22,149][88327] Updated weights for policy 1, policy_version 46970 (0.0009) -[2023-10-09 01:57:23,136][88326] Updated weights for policy 0, policy_version 46952 (0.0009) -[2023-10-09 01:57:23,514][88326] Updated weights for policy 0, policy_version 46962 (0.0010) -[2023-10-09 01:57:23,889][88326] Updated weights for policy 0, policy_version 46972 (0.0008) -[2023-10-09 01:57:23,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 96174080. Throughput: 0: 1691.1, 1: 1707.2. Samples: 24050452. Policy #0 lag: (min: 3.0, avg: 13.7, max: 35.0) -[2023-10-09 01:57:23,975][87372] Avg episode reward: [(0, '7.050'), (1, '6.740')] -[2023-10-09 01:57:26,151][88327] Updated weights for policy 1, policy_version 46980 (0.0009) -[2023-10-09 01:57:26,526][88327] Updated weights for policy 1, policy_version 46990 (0.0008) -[2023-10-09 01:57:26,896][88327] Updated weights for policy 1, policy_version 47000 (0.0008) -[2023-10-09 01:57:27,742][88326] Updated weights for policy 0, policy_version 46982 (0.0008) -[2023-10-09 01:57:28,106][88326] Updated weights for policy 0, policy_version 46992 (0.0008) -[2023-10-09 01:57:28,473][88326] Updated weights for policy 0, policy_version 47002 (0.0011) -[2023-10-09 01:57:28,974][87372] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 96272384. Throughput: 0: 1696.0, 1: 1686.4. Samples: 24070528. Policy #0 lag: (min: 31.0, avg: 31.9, max: 52.0) -[2023-10-09 01:57:28,975][87372] Avg episode reward: [(0, '6.800'), (1, '6.300')] -[2023-10-09 01:57:31,114][88327] Updated weights for policy 1, policy_version 47010 (0.0008) -[2023-10-09 01:57:31,482][88327] Updated weights for policy 1, policy_version 47020 (0.0008) -[2023-10-09 01:57:31,843][88327] Updated weights for policy 1, policy_version 47030 (0.0008) -[2023-10-09 01:57:32,210][88327] Updated weights for policy 1, policy_version 47040 (0.0010) -[2023-10-09 01:57:32,660][88326] Updated weights for policy 0, policy_version 47012 (0.0009) -[2023-10-09 01:57:33,024][88326] Updated weights for policy 0, policy_version 47022 (0.0009) -[2023-10-09 01:57:33,393][88326] Updated weights for policy 0, policy_version 47032 (0.0008) -[2023-10-09 01:57:33,974][87372] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 96337920. Throughput: 0: 1676.0, 1: 1699.8. Samples: 24090362. Policy #0 lag: (min: 31.0, avg: 31.9, max: 52.0) -[2023-10-09 01:57:33,974][87372] Avg episode reward: [(0, '7.230'), (1, '6.490')] -[2023-10-09 01:57:36,037][88327] Updated weights for policy 1, policy_version 47050 (0.0010) -[2023-10-09 01:57:36,397][88327] Updated weights for policy 1, policy_version 47060 (0.0009) -[2023-10-09 01:57:36,758][88327] Updated weights for policy 1, policy_version 47070 (0.0008) -[2023-10-09 01:57:37,558][88326] Updated weights for policy 0, policy_version 47042 (0.0009) -[2023-10-09 01:57:37,929][88326] Updated weights for policy 0, policy_version 47052 (0.0009) -[2023-10-09 01:57:38,299][88326] Updated weights for policy 0, policy_version 47062 (0.0008) -[2023-10-09 01:57:38,671][88326] Updated weights for policy 0, policy_version 47072 (0.0008) -[2023-10-09 01:57:38,974][87372] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 96403456. Throughput: 0: 1693.6, 1: 1701.5. Samples: 24101012. Policy #0 lag: (min: 31.0, avg: 31.9, max: 52.0) -[2023-10-09 01:57:38,975][87372] Avg episode reward: [(0, '6.560'), (1, '6.850')] -[2023-10-09 01:57:40,904][88327] Updated weights for policy 1, policy_version 47080 (0.0008) -[2023-10-09 01:57:41,277][88327] Updated weights for policy 1, policy_version 47090 (0.0008) -[2023-10-09 01:57:41,637][88327] Updated weights for policy 1, policy_version 47100 (0.0008) -[2023-10-09 01:57:42,729][88326] Updated weights for policy 0, policy_version 47082 (0.0007) -[2023-10-09 01:57:43,101][88326] Updated weights for policy 0, policy_version 47092 (0.0007) -[2023-10-09 01:57:43,469][88326] Updated weights for policy 0, policy_version 47102 (0.0009) -[2023-10-09 01:57:43,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 96468992. Throughput: 0: 1701.3, 1: 1680.7. Samples: 24121168. Policy #0 lag: (min: 31.0, avg: 31.9, max: 52.0) -[2023-10-09 01:57:43,975][87372] Avg episode reward: [(0, '6.880'), (1, '6.580')] -[2023-10-09 01:57:45,648][88327] Updated weights for policy 1, policy_version 47110 (0.0009) -[2023-10-09 01:57:46,021][88327] Updated weights for policy 1, policy_version 47120 (0.0011) -[2023-10-09 01:57:46,387][88327] Updated weights for policy 1, policy_version 47130 (0.0009) -[2023-10-09 01:57:47,458][88326] Updated weights for policy 0, policy_version 47112 (0.0010) -[2023-10-09 01:57:47,829][88326] Updated weights for policy 0, policy_version 47122 (0.0009) -[2023-10-09 01:57:48,206][88326] Updated weights for policy 0, policy_version 47132 (0.0008) -[2023-10-09 01:57:48,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 96534528. Throughput: 0: 1672.4, 1: 1707.7. Samples: 24140988. Policy #0 lag: (min: 31.0, avg: 31.9, max: 52.0) -[2023-10-09 01:57:48,975][87372] Avg episode reward: [(0, '6.860'), (1, '6.300')] -[2023-10-09 01:57:50,351][88327] Updated weights for policy 1, policy_version 47140 (0.0008) -[2023-10-09 01:57:50,713][88327] Updated weights for policy 1, policy_version 47150 (0.0008) -[2023-10-09 01:57:51,081][88327] Updated weights for policy 1, policy_version 47160 (0.0008) -[2023-10-09 01:57:52,328][88326] Updated weights for policy 0, policy_version 47142 (0.0009) -[2023-10-09 01:57:52,688][88326] Updated weights for policy 0, policy_version 47152 (0.0010) -[2023-10-09 01:57:53,061][88326] Updated weights for policy 0, policy_version 47162 (0.0010) -[2023-10-09 01:57:53,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 96600064. Throughput: 0: 1695.6, 1: 1681.5. Samples: 24151398. Policy #0 lag: (min: 31.0, avg: 31.9, max: 52.0) -[2023-10-09 01:57:53,975][87372] Avg episode reward: [(0, '6.720'), (1, '6.650')] -[2023-10-09 01:57:55,087][88327] Updated weights for policy 1, policy_version 47170 (0.0007) -[2023-10-09 01:57:55,463][88327] Updated weights for policy 1, policy_version 47180 (0.0009) -[2023-10-09 01:57:55,825][88327] Updated weights for policy 1, policy_version 47190 (0.0010) -[2023-10-09 01:57:56,193][88327] Updated weights for policy 1, policy_version 47200 (0.0009) -[2023-10-09 01:57:57,173][88326] Updated weights for policy 0, policy_version 47172 (0.0009) -[2023-10-09 01:57:57,554][88326] Updated weights for policy 0, policy_version 47182 (0.0010) -[2023-10-09 01:57:57,924][88326] Updated weights for policy 0, policy_version 47192 (0.0009) -[2023-10-09 01:57:58,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 96665600. Throughput: 0: 1686.7, 1: 1689.5. Samples: 24171740. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) -[2023-10-09 01:57:58,975][87372] Avg episode reward: [(0, '6.640'), (1, '6.390')] -[2023-10-09 01:58:00,407][88327] Updated weights for policy 1, policy_version 47210 (0.0010) -[2023-10-09 01:58:00,777][88327] Updated weights for policy 1, policy_version 47220 (0.0009) -[2023-10-09 01:58:01,141][88327] Updated weights for policy 1, policy_version 47230 (0.0010) -[2023-10-09 01:58:02,016][88326] Updated weights for policy 0, policy_version 47202 (0.0007) -[2023-10-09 01:58:02,391][88326] Updated weights for policy 0, policy_version 47212 (0.0008) -[2023-10-09 01:58:02,763][88326] Updated weights for policy 0, policy_version 47222 (0.0007) -[2023-10-09 01:58:03,124][88326] Updated weights for policy 0, policy_version 47232 (0.0010) -[2023-10-09 01:58:03,974][87372] Fps is (10 sec: 13106.7, 60 sec: 13653.2, 300 sec: 13551.5). Total num frames: 96731136. Throughput: 0: 1669.2, 1: 1696.9. Samples: 24191324. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) -[2023-10-09 01:58:03,976][87372] Avg episode reward: [(0, '6.200'), (1, '6.540')] -[2023-10-09 01:58:05,152][88327] Updated weights for policy 1, policy_version 47240 (0.0010) -[2023-10-09 01:58:05,518][88327] Updated weights for policy 1, policy_version 47250 (0.0009) -[2023-10-09 01:58:05,885][88327] Updated weights for policy 1, policy_version 47260 (0.0010) -[2023-10-09 01:58:07,199][88326] Updated weights for policy 0, policy_version 47242 (0.0008) -[2023-10-09 01:58:07,563][88326] Updated weights for policy 0, policy_version 47252 (0.0010) -[2023-10-09 01:58:07,933][88326] Updated weights for policy 0, policy_version 47262 (0.0009) -[2023-10-09 01:58:08,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 96796672. Throughput: 0: 1691.8, 1: 1669.8. Samples: 24201724. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) -[2023-10-09 01:58:08,975][87372] Avg episode reward: [(0, '6.000'), (1, '6.560')] -[2023-10-09 01:58:09,801][88327] Updated weights for policy 1, policy_version 47270 (0.0007) -[2023-10-09 01:58:10,164][88327] Updated weights for policy 1, policy_version 47280 (0.0007) -[2023-10-09 01:58:10,527][88327] Updated weights for policy 1, policy_version 47290 (0.0007) -[2023-10-09 01:58:12,034][88326] Updated weights for policy 0, policy_version 47272 (0.0008) -[2023-10-09 01:58:12,396][88326] Updated weights for policy 0, policy_version 47282 (0.0007) -[2023-10-09 01:58:12,775][88326] Updated weights for policy 0, policy_version 47292 (0.0007) -[2023-10-09 01:58:13,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 96862208. Throughput: 0: 1672.9, 1: 1697.6. Samples: 24222202. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) -[2023-10-09 01:58:13,975][87372] Avg episode reward: [(0, '5.970'), (1, '6.570')] -[2023-10-09 01:58:14,519][88327] Updated weights for policy 1, policy_version 47300 (0.0008) -[2023-10-09 01:58:14,885][88327] Updated weights for policy 1, policy_version 47310 (0.0008) -[2023-10-09 01:58:15,253][88327] Updated weights for policy 1, policy_version 47320 (0.0009) -[2023-10-09 01:58:16,675][88326] Updated weights for policy 0, policy_version 47302 (0.0010) -[2023-10-09 01:58:17,042][88326] Updated weights for policy 0, policy_version 47312 (0.0009) -[2023-10-09 01:58:17,404][88326] Updated weights for policy 0, policy_version 47322 (0.0007) -[2023-10-09 01:58:18,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 96927744. Throughput: 0: 1678.6, 1: 1704.0. Samples: 24242580. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) -[2023-10-09 01:58:18,975][87372] Avg episode reward: [(0, '5.990'), (1, '6.590')] -[2023-10-09 01:58:19,130][88327] Updated weights for policy 1, policy_version 47330 (0.0011) -[2023-10-09 01:58:19,501][88327] Updated weights for policy 1, policy_version 47340 (0.0009) -[2023-10-09 01:58:19,863][88327] Updated weights for policy 1, policy_version 47350 (0.0007) -[2023-10-09 01:58:20,231][88327] Updated weights for policy 1, policy_version 47360 (0.0009) -[2023-10-09 01:58:21,407][88326] Updated weights for policy 0, policy_version 47332 (0.0008) -[2023-10-09 01:58:21,769][88326] Updated weights for policy 0, policy_version 47342 (0.0009) -[2023-10-09 01:58:22,139][88326] Updated weights for policy 0, policy_version 47352 (0.0009) -[2023-10-09 01:58:23,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 96993280. Throughput: 0: 1690.6, 1: 1687.0. Samples: 24253004. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) -[2023-10-09 01:58:23,975][87372] Avg episode reward: [(0, '6.640'), (1, '6.370')] -[2023-10-09 01:58:24,159][88327] Updated weights for policy 1, policy_version 47370 (0.0011) -[2023-10-09 01:58:24,520][88327] Updated weights for policy 1, policy_version 47380 (0.0011) -[2023-10-09 01:58:24,885][88327] Updated weights for policy 1, policy_version 47390 (0.0009) -[2023-10-09 01:58:26,108][88326] Updated weights for policy 0, policy_version 47362 (0.0008) -[2023-10-09 01:58:26,475][88326] Updated weights for policy 0, policy_version 47372 (0.0009) -[2023-10-09 01:58:26,850][88326] Updated weights for policy 0, policy_version 47382 (0.0007) -[2023-10-09 01:58:27,220][88326] Updated weights for policy 0, policy_version 47392 (0.0009) -[2023-10-09 01:58:28,852][88327] Updated weights for policy 1, policy_version 47400 (0.0008) -[2023-10-09 01:58:28,974][87372] Fps is (10 sec: 13106.8, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 97058816. Throughput: 0: 1658.9, 1: 1713.8. Samples: 24272942. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) -[2023-10-09 01:58:28,976][87372] Avg episode reward: [(0, '6.140'), (1, '6.300')] -[2023-10-09 01:58:29,223][88327] Updated weights for policy 1, policy_version 47410 (0.0008) -[2023-10-09 01:58:29,578][88327] Updated weights for policy 1, policy_version 47420 (0.0009) -[2023-10-09 01:58:31,228][88326] Updated weights for policy 0, policy_version 47402 (0.0010) -[2023-10-09 01:58:31,591][88326] Updated weights for policy 0, policy_version 47412 (0.0008) -[2023-10-09 01:58:31,964][88326] Updated weights for policy 0, policy_version 47422 (0.0009) -[2023-10-09 01:58:33,593][88327] Updated weights for policy 1, policy_version 47430 (0.0008) -[2023-10-09 01:58:33,962][88327] Updated weights for policy 1, policy_version 47440 (0.0009) -[2023-10-09 01:58:33,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 97124352. Throughput: 0: 1682.8, 1: 1712.3. Samples: 24293768. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:58:33,975][87372] Avg episode reward: [(0, '6.270'), (1, '6.330')] -[2023-10-09 01:58:33,985][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000047424_48562176.pth... -[2023-10-09 01:58:34,014][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000045856_46956544.pth -[2023-10-09 01:58:34,018][88088] Saving a milestone ./train_atari/atari_battlezone_APPO/checkpoint_p0/milestones/checkpoint_000047424_48562176.pth -[2023-10-09 01:58:34,339][88327] Updated weights for policy 1, policy_version 47450 (0.0012) -[2023-10-09 01:58:34,555][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000047456_48594944.pth... -[2023-10-09 01:58:34,584][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000045856_46956544.pth -[2023-10-09 01:58:34,588][88168] Saving a milestone ./train_atari/atari_battlezone_APPO/checkpoint_p1/milestones/checkpoint_000047456_48594944.pth -[2023-10-09 01:58:36,118][88326] Updated weights for policy 0, policy_version 47432 (0.0008) -[2023-10-09 01:58:36,484][88326] Updated weights for policy 0, policy_version 47442 (0.0007) -[2023-10-09 01:58:36,849][88326] Updated weights for policy 0, policy_version 47452 (0.0009) -[2023-10-09 01:58:38,551][88327] Updated weights for policy 1, policy_version 47460 (0.0010) -[2023-10-09 01:58:38,910][88327] Updated weights for policy 1, policy_version 47470 (0.0007) -[2023-10-09 01:58:38,974][87372] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 97189888. Throughput: 0: 1679.4, 1: 1701.8. Samples: 24303550. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:58:38,975][87372] Avg episode reward: [(0, '6.600'), (1, '6.430')] -[2023-10-09 01:58:39,272][88327] Updated weights for policy 1, policy_version 47480 (0.0008) -[2023-10-09 01:58:41,005][88326] Updated weights for policy 0, policy_version 47462 (0.0009) -[2023-10-09 01:58:41,380][88326] Updated weights for policy 0, policy_version 47472 (0.0007) -[2023-10-09 01:58:41,753][88326] Updated weights for policy 0, policy_version 47482 (0.0008) -[2023-10-09 01:58:43,418][88327] Updated weights for policy 1, policy_version 47490 (0.0008) -[2023-10-09 01:58:43,787][88327] Updated weights for policy 1, policy_version 47500 (0.0011) -[2023-10-09 01:58:43,974][87372] Fps is (10 sec: 13107.7, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 97255424. Throughput: 0: 1658.2, 1: 1708.0. Samples: 24323216. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:58:43,975][87372] Avg episode reward: [(0, '6.090'), (1, '6.670')] -[2023-10-09 01:58:44,146][88327] Updated weights for policy 1, policy_version 47510 (0.0007) -[2023-10-09 01:58:44,520][88327] Updated weights for policy 1, policy_version 47520 (0.0008) -[2023-10-09 01:58:45,655][88326] Updated weights for policy 0, policy_version 47492 (0.0011) -[2023-10-09 01:58:46,018][88326] Updated weights for policy 0, policy_version 47502 (0.0008) -[2023-10-09 01:58:46,383][88326] Updated weights for policy 0, policy_version 47512 (0.0009) -[2023-10-09 01:58:48,610][88327] Updated weights for policy 1, policy_version 47530 (0.0008) -[2023-10-09 01:58:48,969][88327] Updated weights for policy 1, policy_version 47540 (0.0008) -[2023-10-09 01:58:48,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 97320960. Throughput: 0: 1690.1, 1: 1710.6. Samples: 24344354. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:58:48,975][87372] Avg episode reward: [(0, '6.430'), (1, '6.990')] -[2023-10-09 01:58:49,327][88327] Updated weights for policy 1, policy_version 47550 (0.0010) -[2023-10-09 01:58:50,492][88326] Updated weights for policy 0, policy_version 47522 (0.0008) -[2023-10-09 01:58:50,866][88326] Updated weights for policy 0, policy_version 47532 (0.0010) -[2023-10-09 01:58:51,241][88326] Updated weights for policy 0, policy_version 47542 (0.0011) -[2023-10-09 01:58:51,611][88326] Updated weights for policy 0, policy_version 47552 (0.0011) -[2023-10-09 01:58:53,361][88327] Updated weights for policy 1, policy_version 47560 (0.0008) -[2023-10-09 01:58:53,727][88327] Updated weights for policy 1, policy_version 47570 (0.0009) -[2023-10-09 01:58:53,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 97386496. Throughput: 0: 1673.2, 1: 1706.0. Samples: 24353786. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:58:53,975][87372] Avg episode reward: [(0, '7.440'), (1, '6.680')] -[2023-10-09 01:58:53,976][88088] Saving new best policy, reward=7.440! -[2023-10-09 01:58:54,091][88327] Updated weights for policy 1, policy_version 47580 (0.0009) -[2023-10-09 01:58:55,549][88326] Updated weights for policy 0, policy_version 47562 (0.0007) -[2023-10-09 01:58:55,919][88326] Updated weights for policy 0, policy_version 47572 (0.0007) -[2023-10-09 01:58:56,285][88326] Updated weights for policy 0, policy_version 47582 (0.0007) -[2023-10-09 01:58:58,187][88327] Updated weights for policy 1, policy_version 47590 (0.0009) -[2023-10-09 01:58:58,545][88327] Updated weights for policy 1, policy_version 47600 (0.0009) -[2023-10-09 01:58:58,917][88327] Updated weights for policy 1, policy_version 47610 (0.0008) -[2023-10-09 01:58:58,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 97452032. Throughput: 0: 1679.2, 1: 1704.9. Samples: 24374484. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:58:58,975][87372] Avg episode reward: [(0, '7.150'), (1, '6.630')] -[2023-10-09 01:59:00,282][88326] Updated weights for policy 0, policy_version 47592 (0.0008) -[2023-10-09 01:59:00,653][88326] Updated weights for policy 0, policy_version 47602 (0.0007) -[2023-10-09 01:59:01,020][88326] Updated weights for policy 0, policy_version 47612 (0.0007) -[2023-10-09 01:59:02,945][88327] Updated weights for policy 1, policy_version 47620 (0.0010) -[2023-10-09 01:59:03,300][88327] Updated weights for policy 1, policy_version 47630 (0.0009) -[2023-10-09 01:59:03,669][88327] Updated weights for policy 1, policy_version 47640 (0.0008) -[2023-10-09 01:59:03,974][87372] Fps is (10 sec: 16384.0, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 97550336. Throughput: 0: 1696.4, 1: 1693.1. Samples: 24395108. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 01:59:03,975][87372] Avg episode reward: [(0, '7.080'), (1, '6.640')] -[2023-10-09 01:59:05,176][88326] Updated weights for policy 0, policy_version 47622 (0.0008) -[2023-10-09 01:59:05,536][88326] Updated weights for policy 0, policy_version 47632 (0.0008) -[2023-10-09 01:59:05,900][88326] Updated weights for policy 0, policy_version 47642 (0.0011) -[2023-10-09 01:59:07,755][88327] Updated weights for policy 1, policy_version 47650 (0.0009) -[2023-10-09 01:59:08,126][88327] Updated weights for policy 1, policy_version 47660 (0.0009) -[2023-10-09 01:59:08,487][88327] Updated weights for policy 1, policy_version 47670 (0.0008) -[2023-10-09 01:59:08,863][88327] Updated weights for policy 1, policy_version 47680 (0.0009) -[2023-10-09 01:59:08,974][87372] Fps is (10 sec: 16383.8, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 97615872. Throughput: 0: 1667.4, 1: 1698.4. Samples: 24404462. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-10-09 01:59:08,975][87372] Avg episode reward: [(0, '6.610'), (1, '6.490')] -[2023-10-09 01:59:10,099][88326] Updated weights for policy 0, policy_version 47652 (0.0010) -[2023-10-09 01:59:10,472][88326] Updated weights for policy 0, policy_version 47662 (0.0010) -[2023-10-09 01:59:10,836][88326] Updated weights for policy 0, policy_version 47672 (0.0010) -[2023-10-09 01:59:12,925][88327] Updated weights for policy 1, policy_version 47690 (0.0008) -[2023-10-09 01:59:13,295][88327] Updated weights for policy 1, policy_version 47700 (0.0007) -[2023-10-09 01:59:13,665][88327] Updated weights for policy 1, policy_version 47710 (0.0007) -[2023-10-09 01:59:13,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 97681408. Throughput: 0: 1688.1, 1: 1690.2. Samples: 24424968. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-10-09 01:59:13,975][87372] Avg episode reward: [(0, '6.600'), (1, '6.160')] -[2023-10-09 01:59:14,883][88326] Updated weights for policy 0, policy_version 47682 (0.0011) -[2023-10-09 01:59:15,251][88326] Updated weights for policy 0, policy_version 47692 (0.0007) -[2023-10-09 01:59:15,610][88326] Updated weights for policy 0, policy_version 47702 (0.0010) -[2023-10-09 01:59:15,979][88326] Updated weights for policy 0, policy_version 47712 (0.0010) -[2023-10-09 01:59:17,577][88327] Updated weights for policy 1, policy_version 47720 (0.0009) -[2023-10-09 01:59:17,952][88327] Updated weights for policy 1, policy_version 47730 (0.0009) -[2023-10-09 01:59:18,316][88327] Updated weights for policy 1, policy_version 47740 (0.0009) -[2023-10-09 01:59:18,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 97746944. Throughput: 0: 1691.4, 1: 1675.7. Samples: 24445286. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-10-09 01:59:18,975][87372] Avg episode reward: [(0, '6.710'), (1, '6.500')] -[2023-10-09 01:59:19,816][88326] Updated weights for policy 0, policy_version 47722 (0.0008) -[2023-10-09 01:59:20,191][88326] Updated weights for policy 0, policy_version 47732 (0.0009) -[2023-10-09 01:59:20,549][88326] Updated weights for policy 0, policy_version 47742 (0.0007) -[2023-10-09 01:59:22,372][88327] Updated weights for policy 1, policy_version 47750 (0.0007) -[2023-10-09 01:59:22,728][88327] Updated weights for policy 1, policy_version 47760 (0.0009) -[2023-10-09 01:59:23,094][88327] Updated weights for policy 1, policy_version 47770 (0.0009) -[2023-10-09 01:59:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 97812480. Throughput: 0: 1671.4, 1: 1697.8. Samples: 24455164. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-10-09 01:59:23,975][87372] Avg episode reward: [(0, '6.130'), (1, '6.260')] -[2023-10-09 01:59:24,533][88326] Updated weights for policy 0, policy_version 47752 (0.0007) -[2023-10-09 01:59:24,890][88326] Updated weights for policy 0, policy_version 47762 (0.0007) -[2023-10-09 01:59:25,256][88326] Updated weights for policy 0, policy_version 47772 (0.0008) -[2023-10-09 01:59:27,136][88327] Updated weights for policy 1, policy_version 47780 (0.0010) -[2023-10-09 01:59:27,509][88327] Updated weights for policy 1, policy_version 47790 (0.0012) -[2023-10-09 01:59:27,867][88327] Updated weights for policy 1, policy_version 47800 (0.0011) -[2023-10-09 01:59:28,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 97878016. Throughput: 0: 1703.2, 1: 1691.6. Samples: 24475980. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-10-09 01:59:28,974][87372] Avg episode reward: [(0, '6.560'), (1, '6.030')] -[2023-10-09 01:59:29,349][88326] Updated weights for policy 0, policy_version 47782 (0.0007) -[2023-10-09 01:59:29,720][88326] Updated weights for policy 0, policy_version 47792 (0.0008) -[2023-10-09 01:59:30,094][88326] Updated weights for policy 0, policy_version 47802 (0.0008) -[2023-10-09 01:59:31,855][88327] Updated weights for policy 1, policy_version 47810 (0.0011) -[2023-10-09 01:59:32,219][88327] Updated weights for policy 1, policy_version 47820 (0.0010) -[2023-10-09 01:59:32,586][88327] Updated weights for policy 1, policy_version 47830 (0.0008) -[2023-10-09 01:59:32,953][88327] Updated weights for policy 1, policy_version 47840 (0.0009) -[2023-10-09 01:59:33,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 97943552. Throughput: 0: 1702.0, 1: 1667.8. Samples: 24495994. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-10-09 01:59:33,975][87372] Avg episode reward: [(0, '6.740'), (1, '6.330')] -[2023-10-09 01:59:34,121][88326] Updated weights for policy 0, policy_version 47812 (0.0007) -[2023-10-09 01:59:34,478][88326] Updated weights for policy 0, policy_version 47822 (0.0008) -[2023-10-09 01:59:34,852][88326] Updated weights for policy 0, policy_version 47832 (0.0011) -[2023-10-09 01:59:36,989][88327] Updated weights for policy 1, policy_version 47850 (0.0011) -[2023-10-09 01:59:37,348][88327] Updated weights for policy 1, policy_version 47860 (0.0010) -[2023-10-09 01:59:37,706][88327] Updated weights for policy 1, policy_version 47870 (0.0009) -[2023-10-09 01:59:38,823][88326] Updated weights for policy 0, policy_version 47842 (0.0009) -[2023-10-09 01:59:38,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 98009088. Throughput: 0: 1692.0, 1: 1707.0. Samples: 24506740. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-10-09 01:59:38,975][87372] Avg episode reward: [(0, '6.200'), (1, '6.240')] -[2023-10-09 01:59:39,184][88326] Updated weights for policy 0, policy_version 47852 (0.0008) -[2023-10-09 01:59:39,555][88326] Updated weights for policy 0, policy_version 47862 (0.0007) -[2023-10-09 01:59:39,922][88326] Updated weights for policy 0, policy_version 47872 (0.0009) -[2023-10-09 01:59:41,923][88327] Updated weights for policy 1, policy_version 47880 (0.0010) -[2023-10-09 01:59:42,284][88327] Updated weights for policy 1, policy_version 47890 (0.0008) -[2023-10-09 01:59:42,660][88327] Updated weights for policy 1, policy_version 47900 (0.0009) -[2023-10-09 01:59:43,842][88326] Updated weights for policy 0, policy_version 47882 (0.0007) -[2023-10-09 01:59:43,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 98074624. Throughput: 0: 1706.4, 1: 1681.5. Samples: 24526938. Policy #0 lag: (min: 31.0, avg: 31.2, max: 40.0) -[2023-10-09 01:59:43,974][87372] Avg episode reward: [(0, '6.300'), (1, '6.180')] -[2023-10-09 01:59:44,207][88326] Updated weights for policy 0, policy_version 47892 (0.0010) -[2023-10-09 01:59:44,587][88326] Updated weights for policy 0, policy_version 47902 (0.0008) -[2023-10-09 01:59:46,681][88327] Updated weights for policy 1, policy_version 47910 (0.0009) -[2023-10-09 01:59:47,044][88327] Updated weights for policy 1, policy_version 47920 (0.0009) -[2023-10-09 01:59:47,407][88327] Updated weights for policy 1, policy_version 47930 (0.0009) -[2023-10-09 01:59:48,790][88326] Updated weights for policy 0, policy_version 47912 (0.0009) -[2023-10-09 01:59:48,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 98140160. Throughput: 0: 1705.6, 1: 1672.8. Samples: 24547134. Policy #0 lag: (min: 31.0, avg: 31.2, max: 40.0) -[2023-10-09 01:59:48,975][87372] Avg episode reward: [(0, '6.150'), (1, '6.170')] -[2023-10-09 01:59:49,173][88326] Updated weights for policy 0, policy_version 47922 (0.0009) -[2023-10-09 01:59:49,542][88326] Updated weights for policy 0, policy_version 47932 (0.0008) -[2023-10-09 01:59:51,287][88327] Updated weights for policy 1, policy_version 47940 (0.0010) -[2023-10-09 01:59:51,653][88327] Updated weights for policy 1, policy_version 47950 (0.0008) -[2023-10-09 01:59:52,015][88327] Updated weights for policy 1, policy_version 47960 (0.0008) -[2023-10-09 01:59:53,401][88326] Updated weights for policy 0, policy_version 47942 (0.0008) -[2023-10-09 01:59:53,777][88326] Updated weights for policy 0, policy_version 47952 (0.0008) -[2023-10-09 01:59:53,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 98205696. Throughput: 0: 1704.4, 1: 1695.5. Samples: 24557454. Policy #0 lag: (min: 31.0, avg: 31.2, max: 40.0) -[2023-10-09 01:59:53,975][87372] Avg episode reward: [(0, '6.120'), (1, '6.010')] -[2023-10-09 01:59:54,141][88326] Updated weights for policy 0, policy_version 47962 (0.0008) -[2023-10-09 01:59:55,908][88327] Updated weights for policy 1, policy_version 47970 (0.0007) -[2023-10-09 01:59:56,278][88327] Updated weights for policy 1, policy_version 47980 (0.0010) -[2023-10-09 01:59:56,650][88327] Updated weights for policy 1, policy_version 47990 (0.0010) -[2023-10-09 01:59:57,015][88327] Updated weights for policy 1, policy_version 48000 (0.0010) -[2023-10-09 01:59:58,130][88326] Updated weights for policy 0, policy_version 47972 (0.0008) -[2023-10-09 01:59:58,498][88326] Updated weights for policy 0, policy_version 47982 (0.0009) -[2023-10-09 01:59:58,868][88326] Updated weights for policy 0, policy_version 47992 (0.0011) -[2023-10-09 01:59:58,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 98271232. Throughput: 0: 1717.0, 1: 1670.7. Samples: 24577414. Policy #0 lag: (min: 31.0, avg: 31.2, max: 40.0) -[2023-10-09 01:59:58,975][87372] Avg episode reward: [(0, '6.060'), (1, '5.860')] -[2023-10-09 02:00:01,193][88327] Updated weights for policy 1, policy_version 48010 (0.0010) -[2023-10-09 02:00:01,556][88327] Updated weights for policy 1, policy_version 48020 (0.0009) -[2023-10-09 02:00:01,920][88327] Updated weights for policy 1, policy_version 48030 (0.0009) -[2023-10-09 02:00:02,910][88326] Updated weights for policy 0, policy_version 48002 (0.0008) -[2023-10-09 02:00:03,287][88326] Updated weights for policy 0, policy_version 48012 (0.0010) -[2023-10-09 02:00:03,658][88326] Updated weights for policy 0, policy_version 48022 (0.0009) -[2023-10-09 02:00:03,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 98336768. Throughput: 0: 1706.0, 1: 1689.7. Samples: 24598094. Policy #0 lag: (min: 31.0, avg: 31.2, max: 40.0) -[2023-10-09 02:00:03,975][87372] Avg episode reward: [(0, '6.300'), (1, '5.620')] -[2023-10-09 02:00:04,023][88326] Updated weights for policy 0, policy_version 48032 (0.0011) -[2023-10-09 02:00:05,939][88327] Updated weights for policy 1, policy_version 48040 (0.0010) -[2023-10-09 02:00:06,310][88327] Updated weights for policy 1, policy_version 48050 (0.0009) -[2023-10-09 02:00:06,676][88327] Updated weights for policy 1, policy_version 48060 (0.0009) -[2023-10-09 02:00:07,927][88326] Updated weights for policy 0, policy_version 48042 (0.0008) -[2023-10-09 02:00:08,295][88326] Updated weights for policy 0, policy_version 48052 (0.0009) -[2023-10-09 02:00:08,671][88326] Updated weights for policy 0, policy_version 48062 (0.0008) -[2023-10-09 02:00:08,974][87372] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 98435072. Throughput: 0: 1717.8, 1: 1687.6. Samples: 24608408. Policy #0 lag: (min: 31.0, avg: 31.2, max: 40.0) -[2023-10-09 02:00:08,975][87372] Avg episode reward: [(0, '6.480'), (1, '5.670')] -[2023-10-09 02:00:10,701][88327] Updated weights for policy 1, policy_version 48070 (0.0010) -[2023-10-09 02:00:11,062][88327] Updated weights for policy 1, policy_version 48080 (0.0010) -[2023-10-09 02:00:11,428][88327] Updated weights for policy 1, policy_version 48090 (0.0010) -[2023-10-09 02:00:12,829][88326] Updated weights for policy 0, policy_version 48072 (0.0007) -[2023-10-09 02:00:13,203][88326] Updated weights for policy 0, policy_version 48082 (0.0007) -[2023-10-09 02:00:13,581][88326] Updated weights for policy 0, policy_version 48092 (0.0009) -[2023-10-09 02:00:13,974][87372] Fps is (10 sec: 16383.8, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 98500608. Throughput: 0: 1709.5, 1: 1677.9. Samples: 24628414. Policy #0 lag: (min: 19.0, avg: 22.5, max: 51.0) -[2023-10-09 02:00:13,975][87372] Avg episode reward: [(0, '6.260'), (1, '6.260')] -[2023-10-09 02:00:15,479][88327] Updated weights for policy 1, policy_version 48100 (0.0010) -[2023-10-09 02:00:15,852][88327] Updated weights for policy 1, policy_version 48110 (0.0009) -[2023-10-09 02:00:16,218][88327] Updated weights for policy 1, policy_version 48120 (0.0009) -[2023-10-09 02:00:17,581][88326] Updated weights for policy 0, policy_version 48102 (0.0010) -[2023-10-09 02:00:17,952][88326] Updated weights for policy 0, policy_version 48112 (0.0008) -[2023-10-09 02:00:18,330][88326] Updated weights for policy 0, policy_version 48122 (0.0010) -[2023-10-09 02:00:18,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 98566144. Throughput: 0: 1684.0, 1: 1704.5. Samples: 24648474. Policy #0 lag: (min: 19.0, avg: 22.5, max: 51.0) -[2023-10-09 02:00:18,974][87372] Avg episode reward: [(0, '6.380'), (1, '6.760')] -[2023-10-09 02:00:20,227][88327] Updated weights for policy 1, policy_version 48130 (0.0009) -[2023-10-09 02:00:20,590][88327] Updated weights for policy 1, policy_version 48140 (0.0011) -[2023-10-09 02:00:20,955][88327] Updated weights for policy 1, policy_version 48150 (0.0007) -[2023-10-09 02:00:21,313][88327] Updated weights for policy 1, policy_version 48160 (0.0007) -[2023-10-09 02:00:22,280][88326] Updated weights for policy 0, policy_version 48132 (0.0008) -[2023-10-09 02:00:22,648][88326] Updated weights for policy 0, policy_version 48142 (0.0007) -[2023-10-09 02:00:23,007][88326] Updated weights for policy 0, policy_version 48152 (0.0007) -[2023-10-09 02:00:23,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 98631680. Throughput: 0: 1703.0, 1: 1677.1. Samples: 24658844. Policy #0 lag: (min: 19.0, avg: 22.5, max: 51.0) -[2023-10-09 02:00:23,975][87372] Avg episode reward: [(0, '6.170'), (1, '6.740')] -[2023-10-09 02:00:25,414][88327] Updated weights for policy 1, policy_version 48170 (0.0011) -[2023-10-09 02:00:25,782][88327] Updated weights for policy 1, policy_version 48180 (0.0008) -[2023-10-09 02:00:26,146][88327] Updated weights for policy 1, policy_version 48190 (0.0008) -[2023-10-09 02:00:27,079][88326] Updated weights for policy 0, policy_version 48162 (0.0007) -[2023-10-09 02:00:27,449][88326] Updated weights for policy 0, policy_version 48172 (0.0008) -[2023-10-09 02:00:27,815][88326] Updated weights for policy 0, policy_version 48182 (0.0010) -[2023-10-09 02:00:28,189][88326] Updated weights for policy 0, policy_version 48192 (0.0009) -[2023-10-09 02:00:28,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 98697216. Throughput: 0: 1691.1, 1: 1695.9. Samples: 24679352. Policy #0 lag: (min: 19.0, avg: 22.5, max: 51.0) -[2023-10-09 02:00:28,975][87372] Avg episode reward: [(0, '6.430'), (1, '6.730')] -[2023-10-09 02:00:30,017][88327] Updated weights for policy 1, policy_version 48200 (0.0009) -[2023-10-09 02:00:30,378][88327] Updated weights for policy 1, policy_version 48210 (0.0011) -[2023-10-09 02:00:30,738][88327] Updated weights for policy 1, policy_version 48220 (0.0010) -[2023-10-09 02:00:32,022][88326] Updated weights for policy 0, policy_version 48202 (0.0007) -[2023-10-09 02:00:32,386][88326] Updated weights for policy 0, policy_version 48212 (0.0007) -[2023-10-09 02:00:32,758][88326] Updated weights for policy 0, policy_version 48222 (0.0007) -[2023-10-09 02:00:33,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 98762752. Throughput: 0: 1671.5, 1: 1709.4. Samples: 24699276. Policy #0 lag: (min: 19.0, avg: 22.5, max: 51.0) -[2023-10-09 02:00:33,975][87372] Avg episode reward: [(0, '6.320'), (1, '6.330')] -[2023-10-09 02:00:33,986][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000048224_49381376.pth... -[2023-10-09 02:00:33,985][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000048224_49381376.pth... -[2023-10-09 02:00:34,039][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000046656_47775744.pth -[2023-10-09 02:00:34,040][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000046656_47775744.pth -[2023-10-09 02:00:34,871][88327] Updated weights for policy 1, policy_version 48230 (0.0009) -[2023-10-09 02:00:35,233][88327] Updated weights for policy 1, policy_version 48240 (0.0008) -[2023-10-09 02:00:35,589][88327] Updated weights for policy 1, policy_version 48250 (0.0008) -[2023-10-09 02:00:36,982][88326] Updated weights for policy 0, policy_version 48232 (0.0007) -[2023-10-09 02:00:37,366][88326] Updated weights for policy 0, policy_version 48242 (0.0009) -[2023-10-09 02:00:37,729][88326] Updated weights for policy 0, policy_version 48252 (0.0009) -[2023-10-09 02:00:38,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 98828288. Throughput: 0: 1703.5, 1: 1681.1. Samples: 24709760. Policy #0 lag: (min: 19.0, avg: 22.5, max: 51.0) -[2023-10-09 02:00:38,975][87372] Avg episode reward: [(0, '6.570'), (1, '5.980')] -[2023-10-09 02:00:39,561][88327] Updated weights for policy 1, policy_version 48260 (0.0009) -[2023-10-09 02:00:39,929][88327] Updated weights for policy 1, policy_version 48270 (0.0007) -[2023-10-09 02:00:40,292][88327] Updated weights for policy 1, policy_version 48280 (0.0009) -[2023-10-09 02:00:41,726][88326] Updated weights for policy 0, policy_version 48262 (0.0008) -[2023-10-09 02:00:42,095][88326] Updated weights for policy 0, policy_version 48272 (0.0009) -[2023-10-09 02:00:42,469][88326] Updated weights for policy 0, policy_version 48282 (0.0008) -[2023-10-09 02:00:43,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 98893824. Throughput: 0: 1676.6, 1: 1706.5. Samples: 24729654. Policy #0 lag: (min: 19.0, avg: 22.5, max: 51.0) -[2023-10-09 02:00:43,975][87372] Avg episode reward: [(0, '7.230'), (1, '6.820')] -[2023-10-09 02:00:44,386][88327] Updated weights for policy 1, policy_version 48290 (0.0009) -[2023-10-09 02:00:44,748][88327] Updated weights for policy 1, policy_version 48300 (0.0007) -[2023-10-09 02:00:45,108][88327] Updated weights for policy 1, policy_version 48310 (0.0007) -[2023-10-09 02:00:45,473][88327] Updated weights for policy 1, policy_version 48320 (0.0009) -[2023-10-09 02:00:46,624][88326] Updated weights for policy 0, policy_version 48292 (0.0008) -[2023-10-09 02:00:46,991][88326] Updated weights for policy 0, policy_version 48302 (0.0008) -[2023-10-09 02:00:47,359][88326] Updated weights for policy 0, policy_version 48312 (0.0010) -[2023-10-09 02:00:48,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 98959360. Throughput: 0: 1671.2, 1: 1705.7. Samples: 24750058. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-10-09 02:00:48,975][87372] Avg episode reward: [(0, '6.930'), (1, '6.330')] -[2023-10-09 02:00:49,426][88327] Updated weights for policy 1, policy_version 48330 (0.0008) -[2023-10-09 02:00:49,799][88327] Updated weights for policy 1, policy_version 48340 (0.0008) -[2023-10-09 02:00:50,156][88327] Updated weights for policy 1, policy_version 48350 (0.0008) -[2023-10-09 02:00:51,558][88326] Updated weights for policy 0, policy_version 48322 (0.0008) -[2023-10-09 02:00:51,933][88326] Updated weights for policy 0, policy_version 48332 (0.0010) -[2023-10-09 02:00:52,303][88326] Updated weights for policy 0, policy_version 48342 (0.0008) -[2023-10-09 02:00:52,671][88326] Updated weights for policy 0, policy_version 48352 (0.0009) -[2023-10-09 02:00:53,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 99024896. Throughput: 0: 1690.5, 1: 1688.0. Samples: 24760440. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-10-09 02:00:53,975][87372] Avg episode reward: [(0, '6.950'), (1, '5.820')] -[2023-10-09 02:00:54,155][88327] Updated weights for policy 1, policy_version 48360 (0.0010) -[2023-10-09 02:00:54,535][88327] Updated weights for policy 1, policy_version 48370 (0.0009) -[2023-10-09 02:00:54,893][88327] Updated weights for policy 1, policy_version 48380 (0.0010) -[2023-10-09 02:00:56,753][88326] Updated weights for policy 0, policy_version 48362 (0.0010) -[2023-10-09 02:00:57,129][88326] Updated weights for policy 0, policy_version 48372 (0.0007) -[2023-10-09 02:00:57,493][88326] Updated weights for policy 0, policy_version 48382 (0.0009) -[2023-10-09 02:00:58,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 99090432. Throughput: 0: 1670.9, 1: 1703.5. Samples: 24780262. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-10-09 02:00:58,974][87372] Avg episode reward: [(0, '6.850'), (1, '6.670')] -[2023-10-09 02:00:59,094][88327] Updated weights for policy 1, policy_version 48390 (0.0010) -[2023-10-09 02:00:59,467][88327] Updated weights for policy 1, policy_version 48400 (0.0010) -[2023-10-09 02:00:59,834][88327] Updated weights for policy 1, policy_version 48410 (0.0007) -[2023-10-09 02:01:01,647][88326] Updated weights for policy 0, policy_version 48392 (0.0008) -[2023-10-09 02:01:02,026][88326] Updated weights for policy 0, policy_version 48402 (0.0009) -[2023-10-09 02:01:02,392][88326] Updated weights for policy 0, policy_version 48412 (0.0008) -[2023-10-09 02:01:03,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 99155968. Throughput: 0: 1678.1, 1: 1698.0. Samples: 24800396. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-10-09 02:01:03,975][87372] Avg episode reward: [(0, '6.900'), (1, '5.820')] -[2023-10-09 02:01:04,094][88327] Updated weights for policy 1, policy_version 48420 (0.0008) -[2023-10-09 02:01:04,465][88327] Updated weights for policy 1, policy_version 48430 (0.0010) -[2023-10-09 02:01:04,824][88327] Updated weights for policy 1, policy_version 48440 (0.0008) -[2023-10-09 02:01:06,392][88326] Updated weights for policy 0, policy_version 48422 (0.0007) -[2023-10-09 02:01:06,758][88326] Updated weights for policy 0, policy_version 48432 (0.0007) -[2023-10-09 02:01:07,143][88326] Updated weights for policy 0, policy_version 48442 (0.0008) -[2023-10-09 02:01:08,788][88327] Updated weights for policy 1, policy_version 48450 (0.0008) -[2023-10-09 02:01:08,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 99221504. Throughput: 0: 1686.8, 1: 1690.0. Samples: 24810802. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-10-09 02:01:08,975][87372] Avg episode reward: [(0, '6.770'), (1, '6.160')] -[2023-10-09 02:01:09,160][88327] Updated weights for policy 1, policy_version 48460 (0.0008) -[2023-10-09 02:01:09,529][88327] Updated weights for policy 1, policy_version 48470 (0.0008) -[2023-10-09 02:01:09,904][88327] Updated weights for policy 1, policy_version 48480 (0.0010) -[2023-10-09 02:01:11,162][88326] Updated weights for policy 0, policy_version 48452 (0.0008) -[2023-10-09 02:01:11,532][88326] Updated weights for policy 0, policy_version 48462 (0.0007) -[2023-10-09 02:01:11,898][88326] Updated weights for policy 0, policy_version 48472 (0.0009) -[2023-10-09 02:01:13,789][88327] Updated weights for policy 1, policy_version 48490 (0.0009) -[2023-10-09 02:01:13,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 99287040. Throughput: 0: 1663.6, 1: 1696.2. Samples: 24830540. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-10-09 02:01:13,975][87372] Avg episode reward: [(0, '6.520'), (1, '6.760')] -[2023-10-09 02:01:14,160][88327] Updated weights for policy 1, policy_version 48500 (0.0008) -[2023-10-09 02:01:14,530][88327] Updated weights for policy 1, policy_version 48510 (0.0008) -[2023-10-09 02:01:15,892][88326] Updated weights for policy 0, policy_version 48482 (0.0009) -[2023-10-09 02:01:16,255][88326] Updated weights for policy 0, policy_version 48492 (0.0007) -[2023-10-09 02:01:16,618][88326] Updated weights for policy 0, policy_version 48502 (0.0008) -[2023-10-09 02:01:16,986][88326] Updated weights for policy 0, policy_version 48512 (0.0008) -[2023-10-09 02:01:18,477][88327] Updated weights for policy 1, policy_version 48520 (0.0008) -[2023-10-09 02:01:18,845][88327] Updated weights for policy 1, policy_version 48530 (0.0008) -[2023-10-09 02:01:18,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 99352576. Throughput: 0: 1685.5, 1: 1695.5. Samples: 24851422. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-10-09 02:01:18,975][87372] Avg episode reward: [(0, '6.890'), (1, '6.170')] -[2023-10-09 02:01:19,212][88327] Updated weights for policy 1, policy_version 48540 (0.0009) -[2023-10-09 02:01:21,060][88326] Updated weights for policy 0, policy_version 48522 (0.0010) -[2023-10-09 02:01:21,436][88326] Updated weights for policy 0, policy_version 48532 (0.0010) -[2023-10-09 02:01:21,794][88326] Updated weights for policy 0, policy_version 48542 (0.0010) -[2023-10-09 02:01:23,268][88327] Updated weights for policy 1, policy_version 48550 (0.0009) -[2023-10-09 02:01:23,634][88327] Updated weights for policy 1, policy_version 48560 (0.0010) -[2023-10-09 02:01:23,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 99418112. Throughput: 0: 1676.9, 1: 1692.4. Samples: 24861382. Policy #0 lag: (min: 31.0, avg: 32.6, max: 57.0) -[2023-10-09 02:01:23,974][87372] Avg episode reward: [(0, '6.390'), (1, '6.560')] -[2023-10-09 02:01:23,999][88327] Updated weights for policy 1, policy_version 48570 (0.0009) -[2023-10-09 02:01:26,028][88326] Updated weights for policy 0, policy_version 48552 (0.0009) -[2023-10-09 02:01:26,408][88326] Updated weights for policy 0, policy_version 48562 (0.0009) -[2023-10-09 02:01:26,768][88326] Updated weights for policy 0, policy_version 48572 (0.0008) -[2023-10-09 02:01:27,977][88327] Updated weights for policy 1, policy_version 48580 (0.0008) -[2023-10-09 02:01:28,347][88327] Updated weights for policy 1, policy_version 48590 (0.0010) -[2023-10-09 02:01:28,705][88327] Updated weights for policy 1, policy_version 48600 (0.0009) -[2023-10-09 02:01:28,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 99483648. Throughput: 0: 1676.6, 1: 1693.9. Samples: 24881328. Policy #0 lag: (min: 31.0, avg: 32.6, max: 57.0) -[2023-10-09 02:01:28,975][87372] Avg episode reward: [(0, '6.130'), (1, '6.520')] -[2023-10-09 02:01:30,607][88326] Updated weights for policy 0, policy_version 48582 (0.0007) -[2023-10-09 02:01:30,971][88326] Updated weights for policy 0, policy_version 48592 (0.0007) -[2023-10-09 02:01:31,338][88326] Updated weights for policy 0, policy_version 48602 (0.0007) -[2023-10-09 02:01:33,043][88327] Updated weights for policy 1, policy_version 48610 (0.0010) -[2023-10-09 02:01:33,407][88327] Updated weights for policy 1, policy_version 48620 (0.0007) -[2023-10-09 02:01:33,770][88327] Updated weights for policy 1, policy_version 48630 (0.0008) -[2023-10-09 02:01:33,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 99549184. Throughput: 0: 1691.0, 1: 1680.5. Samples: 24901778. Policy #0 lag: (min: 31.0, avg: 32.6, max: 57.0) -[2023-10-09 02:01:33,974][87372] Avg episode reward: [(0, '5.780'), (1, '6.130')] -[2023-10-09 02:01:34,133][88327] Updated weights for policy 1, policy_version 48640 (0.0009) -[2023-10-09 02:01:35,411][88326] Updated weights for policy 0, policy_version 48612 (0.0009) -[2023-10-09 02:01:35,783][88326] Updated weights for policy 0, policy_version 48622 (0.0010) -[2023-10-09 02:01:36,153][88326] Updated weights for policy 0, policy_version 48632 (0.0009) -[2023-10-09 02:01:38,191][88327] Updated weights for policy 1, policy_version 48650 (0.0008) -[2023-10-09 02:01:38,565][88327] Updated weights for policy 1, policy_version 48660 (0.0009) -[2023-10-09 02:01:38,931][88327] Updated weights for policy 1, policy_version 48670 (0.0009) -[2023-10-09 02:01:38,974][87372] Fps is (10 sec: 13106.7, 60 sec: 13107.1, 300 sec: 13440.4). Total num frames: 99614720. Throughput: 0: 1669.6, 1: 1687.4. Samples: 24911508. Policy #0 lag: (min: 31.0, avg: 32.6, max: 57.0) -[2023-10-09 02:01:38,976][87372] Avg episode reward: [(0, '6.170'), (1, '6.630')] -[2023-10-09 02:01:40,156][88326] Updated weights for policy 0, policy_version 48642 (0.0008) -[2023-10-09 02:01:40,527][88326] Updated weights for policy 0, policy_version 48652 (0.0008) -[2023-10-09 02:01:40,889][88326] Updated weights for policy 0, policy_version 48662 (0.0009) -[2023-10-09 02:01:41,270][88326] Updated weights for policy 0, policy_version 48672 (0.0008) -[2023-10-09 02:01:42,845][88327] Updated weights for policy 1, policy_version 48680 (0.0007) -[2023-10-09 02:01:43,214][88327] Updated weights for policy 1, policy_version 48690 (0.0009) -[2023-10-09 02:01:43,585][88327] Updated weights for policy 1, policy_version 48700 (0.0008) -[2023-10-09 02:01:43,974][87372] Fps is (10 sec: 16383.9, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 99713024. Throughput: 0: 1684.8, 1: 1690.8. Samples: 24932164. Policy #0 lag: (min: 31.0, avg: 32.6, max: 57.0) -[2023-10-09 02:01:43,975][87372] Avg episode reward: [(0, '5.940'), (1, '6.790')] -[2023-10-09 02:01:45,355][88326] Updated weights for policy 0, policy_version 48682 (0.0010) -[2023-10-09 02:01:45,719][88326] Updated weights for policy 0, policy_version 48692 (0.0009) -[2023-10-09 02:01:46,093][88326] Updated weights for policy 0, policy_version 48702 (0.0008) -[2023-10-09 02:01:47,595][88327] Updated weights for policy 1, policy_version 48710 (0.0011) -[2023-10-09 02:01:47,965][88327] Updated weights for policy 1, policy_version 48720 (0.0010) -[2023-10-09 02:01:48,335][88327] Updated weights for policy 1, policy_version 48730 (0.0010) -[2023-10-09 02:01:48,974][87372] Fps is (10 sec: 16384.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 99778560. Throughput: 0: 1696.8, 1: 1679.9. Samples: 24952350. Policy #0 lag: (min: 31.0, avg: 32.6, max: 57.0) -[2023-10-09 02:01:48,975][87372] Avg episode reward: [(0, '6.360'), (1, '5.980')] -[2023-10-09 02:01:50,130][88326] Updated weights for policy 0, policy_version 48712 (0.0009) -[2023-10-09 02:01:50,489][88326] Updated weights for policy 0, policy_version 48722 (0.0009) -[2023-10-09 02:01:50,849][88326] Updated weights for policy 0, policy_version 48732 (0.0010) -[2023-10-09 02:01:52,476][88327] Updated weights for policy 1, policy_version 48740 (0.0011) -[2023-10-09 02:01:52,840][88327] Updated weights for policy 1, policy_version 48750 (0.0007) -[2023-10-09 02:01:53,205][88327] Updated weights for policy 1, policy_version 48760 (0.0007) -[2023-10-09 02:01:53,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 99844096. Throughput: 0: 1670.8, 1: 1695.7. Samples: 24962296. Policy #0 lag: (min: 31.0, avg: 32.6, max: 57.0) -[2023-10-09 02:01:53,974][87372] Avg episode reward: [(0, '6.960'), (1, '6.160')] -[2023-10-09 02:01:54,875][88326] Updated weights for policy 0, policy_version 48742 (0.0008) -[2023-10-09 02:01:55,243][88326] Updated weights for policy 0, policy_version 48752 (0.0008) -[2023-10-09 02:01:55,619][88326] Updated weights for policy 0, policy_version 48762 (0.0009) -[2023-10-09 02:01:57,315][88327] Updated weights for policy 1, policy_version 48770 (0.0010) -[2023-10-09 02:01:57,675][88327] Updated weights for policy 1, policy_version 48780 (0.0010) -[2023-10-09 02:01:58,044][88327] Updated weights for policy 1, policy_version 48790 (0.0009) -[2023-10-09 02:01:58,403][88327] Updated weights for policy 1, policy_version 48800 (0.0011) -[2023-10-09 02:01:58,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 99909632. Throughput: 0: 1698.4, 1: 1691.3. Samples: 24983076. Policy #0 lag: (min: 29.0, avg: 36.8, max: 61.0) -[2023-10-09 02:01:58,975][87372] Avg episode reward: [(0, '6.410'), (1, '5.660')] -[2023-10-09 02:01:59,608][88326] Updated weights for policy 0, policy_version 48772 (0.0008) -[2023-10-09 02:01:59,985][88326] Updated weights for policy 0, policy_version 48782 (0.0009) -[2023-10-09 02:02:00,345][88326] Updated weights for policy 0, policy_version 48792 (0.0011) -[2023-10-09 02:02:02,439][88327] Updated weights for policy 1, policy_version 48810 (0.0007) -[2023-10-09 02:02:02,819][88327] Updated weights for policy 1, policy_version 48820 (0.0007) -[2023-10-09 02:02:03,186][88327] Updated weights for policy 1, policy_version 48830 (0.0008) -[2023-10-09 02:02:03,974][87372] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 99975168. Throughput: 0: 1698.4, 1: 1665.0. Samples: 25002774. Policy #0 lag: (min: 29.0, avg: 36.8, max: 61.0) -[2023-10-09 02:02:03,975][87372] Avg episode reward: [(0, '6.780'), (1, '5.810')] -[2023-10-09 02:02:04,451][88326] Updated weights for policy 0, policy_version 48802 (0.0009) -[2023-10-09 02:02:04,818][88326] Updated weights for policy 0, policy_version 48812 (0.0007) -[2023-10-09 02:02:05,197][88326] Updated weights for policy 0, policy_version 48822 (0.0008) -[2023-10-09 02:02:05,556][88326] Updated weights for policy 0, policy_version 48832 (0.0009) -[2023-10-09 02:02:07,139][88327] Updated weights for policy 1, policy_version 48840 (0.0010) -[2023-10-09 02:02:07,499][88327] Updated weights for policy 1, policy_version 48850 (0.0008) -[2023-10-09 02:02:07,862][88327] Updated weights for policy 1, policy_version 48860 (0.0007) -[2023-10-09 02:02:08,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 100040704. Throughput: 0: 1675.5, 1: 1695.1. Samples: 25013060. Policy #0 lag: (min: 29.0, avg: 36.8, max: 61.0) -[2023-10-09 02:02:08,975][87372] Avg episode reward: [(0, '6.760'), (1, '6.090')] -[2023-10-09 02:02:09,662][88326] Updated weights for policy 0, policy_version 48842 (0.0008) -[2023-10-09 02:02:10,035][88326] Updated weights for policy 0, policy_version 48852 (0.0007) -[2023-10-09 02:02:10,415][88326] Updated weights for policy 0, policy_version 48862 (0.0007) -[2023-10-09 02:02:11,878][88327] Updated weights for policy 1, policy_version 48870 (0.0010) -[2023-10-09 02:02:12,238][88327] Updated weights for policy 1, policy_version 48880 (0.0010) -[2023-10-09 02:02:12,612][88327] Updated weights for policy 1, policy_version 48890 (0.0011) -[2023-10-09 02:02:13,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 100106240. Throughput: 0: 1698.4, 1: 1687.6. Samples: 25033696. Policy #0 lag: (min: 29.0, avg: 36.8, max: 61.0) -[2023-10-09 02:02:13,975][87372] Avg episode reward: [(0, '6.600'), (1, '5.600')] -[2023-10-09 02:02:14,346][88326] Updated weights for policy 0, policy_version 48872 (0.0008) -[2023-10-09 02:02:14,712][88326] Updated weights for policy 0, policy_version 48882 (0.0007) -[2023-10-09 02:02:15,084][88326] Updated weights for policy 0, policy_version 48892 (0.0007) -[2023-10-09 02:02:16,710][88327] Updated weights for policy 1, policy_version 48900 (0.0008) -[2023-10-09 02:02:17,085][88327] Updated weights for policy 1, policy_version 48910 (0.0007) -[2023-10-09 02:02:17,458][88327] Updated weights for policy 1, policy_version 48920 (0.0007) -[2023-10-09 02:02:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 100171776. Throughput: 0: 1698.3, 1: 1680.1. Samples: 25053806. Policy #0 lag: (min: 29.0, avg: 36.8, max: 61.0) -[2023-10-09 02:02:18,975][87372] Avg episode reward: [(0, '6.520'), (1, '5.960')] -[2023-10-09 02:02:18,997][88326] Updated weights for policy 0, policy_version 48902 (0.0007) -[2023-10-09 02:02:19,362][88326] Updated weights for policy 0, policy_version 48912 (0.0007) -[2023-10-09 02:02:19,746][88326] Updated weights for policy 0, policy_version 48922 (0.0007) -[2023-10-09 02:02:21,473][88327] Updated weights for policy 1, policy_version 48930 (0.0008) -[2023-10-09 02:02:21,838][88327] Updated weights for policy 1, policy_version 48940 (0.0008) -[2023-10-09 02:02:22,198][88327] Updated weights for policy 1, policy_version 48950 (0.0008) -[2023-10-09 02:02:22,554][88327] Updated weights for policy 1, policy_version 48960 (0.0010) -[2023-10-09 02:02:23,788][88326] Updated weights for policy 0, policy_version 48932 (0.0008) -[2023-10-09 02:02:23,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 100237312. Throughput: 0: 1691.2, 1: 1704.4. Samples: 25064308. Policy #0 lag: (min: 29.0, avg: 36.8, max: 61.0) -[2023-10-09 02:02:23,975][87372] Avg episode reward: [(0, '6.030'), (1, '5.750')] -[2023-10-09 02:02:24,156][88326] Updated weights for policy 0, policy_version 48942 (0.0009) -[2023-10-09 02:02:24,523][88326] Updated weights for policy 0, policy_version 48952 (0.0009) -[2023-10-09 02:02:26,654][88327] Updated weights for policy 1, policy_version 48970 (0.0009) -[2023-10-09 02:02:27,018][88327] Updated weights for policy 1, policy_version 48980 (0.0007) -[2023-10-09 02:02:27,384][88327] Updated weights for policy 1, policy_version 48990 (0.0007) -[2023-10-09 02:02:28,522][88326] Updated weights for policy 0, policy_version 48962 (0.0008) -[2023-10-09 02:02:28,894][88326] Updated weights for policy 0, policy_version 48972 (0.0008) -[2023-10-09 02:02:28,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 100302848. Throughput: 0: 1699.5, 1: 1683.8. Samples: 25084412. Policy #0 lag: (min: 29.0, avg: 36.8, max: 61.0) -[2023-10-09 02:02:28,974][87372] Avg episode reward: [(0, '6.190'), (1, '6.160')] -[2023-10-09 02:02:29,266][88326] Updated weights for policy 0, policy_version 48982 (0.0009) -[2023-10-09 02:02:29,633][88326] Updated weights for policy 0, policy_version 48992 (0.0007) -[2023-10-09 02:02:31,242][88327] Updated weights for policy 1, policy_version 49000 (0.0008) -[2023-10-09 02:02:31,607][88327] Updated weights for policy 1, policy_version 49010 (0.0007) -[2023-10-09 02:02:31,975][88327] Updated weights for policy 1, policy_version 49020 (0.0007) -[2023-10-09 02:02:33,540][88326] Updated weights for policy 0, policy_version 49002 (0.0008) -[2023-10-09 02:02:33,912][88326] Updated weights for policy 0, policy_version 49012 (0.0008) -[2023-10-09 02:02:33,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 100368384. Throughput: 0: 1701.4, 1: 1690.8. Samples: 25104996. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:02:33,975][87372] Avg episode reward: [(0, '5.730'), (1, '6.430')] -[2023-10-09 02:02:33,985][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000049024_50200576.pth... -[2023-10-09 02:02:34,028][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000047456_48594944.pth -[2023-10-09 02:02:34,277][88326] Updated weights for policy 0, policy_version 49022 (0.0009) -[2023-10-09 02:02:34,351][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000049024_50200576.pth... -[2023-10-09 02:02:34,381][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000047424_48562176.pth -[2023-10-09 02:02:36,017][88327] Updated weights for policy 1, policy_version 49030 (0.0007) -[2023-10-09 02:02:36,386][88327] Updated weights for policy 1, policy_version 49040 (0.0007) -[2023-10-09 02:02:36,759][88327] Updated weights for policy 1, policy_version 49050 (0.0007) -[2023-10-09 02:02:38,281][88326] Updated weights for policy 0, policy_version 49032 (0.0009) -[2023-10-09 02:02:38,647][88326] Updated weights for policy 0, policy_version 49042 (0.0009) -[2023-10-09 02:02:38,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 100433920. Throughput: 0: 1700.3, 1: 1696.8. Samples: 25115168. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:02:38,975][87372] Avg episode reward: [(0, '6.100'), (1, '6.390')] -[2023-10-09 02:02:39,021][88326] Updated weights for policy 0, policy_version 49052 (0.0008) -[2023-10-09 02:02:40,974][88327] Updated weights for policy 1, policy_version 49060 (0.0008) -[2023-10-09 02:02:41,344][88327] Updated weights for policy 1, policy_version 49070 (0.0007) -[2023-10-09 02:02:41,701][88327] Updated weights for policy 1, policy_version 49080 (0.0009) -[2023-10-09 02:02:43,266][88326] Updated weights for policy 0, policy_version 49062 (0.0009) -[2023-10-09 02:02:43,630][88326] Updated weights for policy 0, policy_version 49072 (0.0008) -[2023-10-09 02:02:43,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 100499456. Throughput: 0: 1701.7, 1: 1674.0. Samples: 25134982. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:02:43,975][87372] Avg episode reward: [(0, '6.610'), (1, '6.020')] -[2023-10-09 02:02:44,007][88326] Updated weights for policy 0, policy_version 49082 (0.0009) -[2023-10-09 02:02:45,748][88327] Updated weights for policy 1, policy_version 49090 (0.0009) -[2023-10-09 02:02:46,112][88327] Updated weights for policy 1, policy_version 49100 (0.0011) -[2023-10-09 02:02:46,478][88327] Updated weights for policy 1, policy_version 49110 (0.0010) -[2023-10-09 02:02:46,851][88327] Updated weights for policy 1, policy_version 49120 (0.0008) -[2023-10-09 02:02:48,006][88326] Updated weights for policy 0, policy_version 49092 (0.0009) -[2023-10-09 02:02:48,370][88326] Updated weights for policy 0, policy_version 49102 (0.0010) -[2023-10-09 02:02:48,748][88326] Updated weights for policy 0, policy_version 49112 (0.0010) -[2023-10-09 02:02:48,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 100564992. Throughput: 0: 1687.7, 1: 1706.4. Samples: 25155506. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:02:48,975][87372] Avg episode reward: [(0, '6.100'), (1, '6.830')] -[2023-10-09 02:02:51,053][88327] Updated weights for policy 1, policy_version 49130 (0.0009) -[2023-10-09 02:02:51,421][88327] Updated weights for policy 1, policy_version 49140 (0.0007) -[2023-10-09 02:02:51,783][88327] Updated weights for policy 1, policy_version 49150 (0.0009) -[2023-10-09 02:02:52,862][88326] Updated weights for policy 0, policy_version 49122 (0.0009) -[2023-10-09 02:02:53,225][88326] Updated weights for policy 0, policy_version 49132 (0.0009) -[2023-10-09 02:02:53,599][88326] Updated weights for policy 0, policy_version 49142 (0.0008) -[2023-10-09 02:02:53,968][88326] Updated weights for policy 0, policy_version 49152 (0.0007) -[2023-10-09 02:02:53,974][87372] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 100663296. Throughput: 0: 1700.7, 1: 1692.8. Samples: 25165768. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:02:53,975][87372] Avg episode reward: [(0, '6.270'), (1, '6.950')] -[2023-10-09 02:02:55,870][88327] Updated weights for policy 1, policy_version 49160 (0.0010) -[2023-10-09 02:02:56,231][88327] Updated weights for policy 1, policy_version 49170 (0.0010) -[2023-10-09 02:02:56,600][88327] Updated weights for policy 1, policy_version 49180 (0.0010) -[2023-10-09 02:02:58,008][88326] Updated weights for policy 0, policy_version 49162 (0.0009) -[2023-10-09 02:02:58,380][88326] Updated weights for policy 0, policy_version 49172 (0.0010) -[2023-10-09 02:02:58,742][88326] Updated weights for policy 0, policy_version 49182 (0.0009) -[2023-10-09 02:02:58,974][87372] Fps is (10 sec: 16383.7, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 100728832. Throughput: 0: 1704.4, 1: 1676.5. Samples: 25185838. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:02:58,975][87372] Avg episode reward: [(0, '6.210'), (1, '6.970')] -[2023-10-09 02:03:00,517][88327] Updated weights for policy 1, policy_version 49190 (0.0010) -[2023-10-09 02:03:00,880][88327] Updated weights for policy 1, policy_version 49200 (0.0011) -[2023-10-09 02:03:01,249][88327] Updated weights for policy 1, policy_version 49210 (0.0008) -[2023-10-09 02:03:02,886][88326] Updated weights for policy 0, policy_version 49192 (0.0008) -[2023-10-09 02:03:03,267][88326] Updated weights for policy 0, policy_version 49202 (0.0008) -[2023-10-09 02:03:03,638][88326] Updated weights for policy 0, policy_version 49212 (0.0009) -[2023-10-09 02:03:03,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 100794368. Throughput: 0: 1682.8, 1: 1695.5. Samples: 25205832. Policy #0 lag: (min: 31.0, avg: 46.4, max: 63.0) -[2023-10-09 02:03:03,975][87372] Avg episode reward: [(0, '5.960'), (1, '6.870')] -[2023-10-09 02:03:05,146][88327] Updated weights for policy 1, policy_version 49220 (0.0008) -[2023-10-09 02:03:05,514][88327] Updated weights for policy 1, policy_version 49230 (0.0009) -[2023-10-09 02:03:05,871][88327] Updated weights for policy 1, policy_version 49240 (0.0008) -[2023-10-09 02:03:07,565][88326] Updated weights for policy 0, policy_version 49222 (0.0008) -[2023-10-09 02:03:07,929][88326] Updated weights for policy 0, policy_version 49232 (0.0009) -[2023-10-09 02:03:08,305][88326] Updated weights for policy 0, policy_version 49242 (0.0007) -[2023-10-09 02:03:08,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 100859904. Throughput: 0: 1697.5, 1: 1668.4. Samples: 25215770. Policy #0 lag: (min: 31.0, avg: 46.4, max: 63.0) -[2023-10-09 02:03:08,975][87372] Avg episode reward: [(0, '6.020'), (1, '6.210')] -[2023-10-09 02:03:09,777][88327] Updated weights for policy 1, policy_version 49250 (0.0008) -[2023-10-09 02:03:10,148][88327] Updated weights for policy 1, policy_version 49260 (0.0007) -[2023-10-09 02:03:10,518][88327] Updated weights for policy 1, policy_version 49270 (0.0008) -[2023-10-09 02:03:10,881][88327] Updated weights for policy 1, policy_version 49280 (0.0008) -[2023-10-09 02:03:12,247][88326] Updated weights for policy 0, policy_version 49252 (0.0007) -[2023-10-09 02:03:12,613][88326] Updated weights for policy 0, policy_version 49262 (0.0008) -[2023-10-09 02:03:12,981][88326] Updated weights for policy 0, policy_version 49272 (0.0007) -[2023-10-09 02:03:13,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 100925440. Throughput: 0: 1698.1, 1: 1685.6. Samples: 25236682. Policy #0 lag: (min: 31.0, avg: 46.4, max: 63.0) -[2023-10-09 02:03:13,975][87372] Avg episode reward: [(0, '6.310'), (1, '6.640')] -[2023-10-09 02:03:15,022][88327] Updated weights for policy 1, policy_version 49290 (0.0008) -[2023-10-09 02:03:15,385][88327] Updated weights for policy 1, policy_version 49300 (0.0010) -[2023-10-09 02:03:15,751][88327] Updated weights for policy 1, policy_version 49310 (0.0011) -[2023-10-09 02:03:17,073][88326] Updated weights for policy 0, policy_version 49282 (0.0007) -[2023-10-09 02:03:17,445][88326] Updated weights for policy 0, policy_version 49292 (0.0008) -[2023-10-09 02:03:17,818][88326] Updated weights for policy 0, policy_version 49302 (0.0008) -[2023-10-09 02:03:18,186][88326] Updated weights for policy 0, policy_version 49312 (0.0009) -[2023-10-09 02:03:18,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 100990976. Throughput: 0: 1671.9, 1: 1696.8. Samples: 25256586. Policy #0 lag: (min: 31.0, avg: 46.4, max: 63.0) -[2023-10-09 02:03:18,975][87372] Avg episode reward: [(0, '6.590'), (1, '5.890')] -[2023-10-09 02:03:19,839][88327] Updated weights for policy 1, policy_version 49320 (0.0009) -[2023-10-09 02:03:20,196][88327] Updated weights for policy 1, policy_version 49330 (0.0009) -[2023-10-09 02:03:20,554][88327] Updated weights for policy 1, policy_version 49340 (0.0010) -[2023-10-09 02:03:22,091][88326] Updated weights for policy 0, policy_version 49322 (0.0008) -[2023-10-09 02:03:22,458][88326] Updated weights for policy 0, policy_version 49332 (0.0008) -[2023-10-09 02:03:22,822][88326] Updated weights for policy 0, policy_version 49342 (0.0008) -[2023-10-09 02:03:23,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 101056512. Throughput: 0: 1700.3, 1: 1673.4. Samples: 25266984. Policy #0 lag: (min: 31.0, avg: 46.4, max: 63.0) -[2023-10-09 02:03:23,975][87372] Avg episode reward: [(0, '6.390'), (1, '6.130')] -[2023-10-09 02:03:24,612][88327] Updated weights for policy 1, policy_version 49350 (0.0008) -[2023-10-09 02:03:24,981][88327] Updated weights for policy 1, policy_version 49360 (0.0008) -[2023-10-09 02:03:25,341][88327] Updated weights for policy 1, policy_version 49370 (0.0009) -[2023-10-09 02:03:26,839][88326] Updated weights for policy 0, policy_version 49352 (0.0009) -[2023-10-09 02:03:27,212][88326] Updated weights for policy 0, policy_version 49362 (0.0008) -[2023-10-09 02:03:27,582][88326] Updated weights for policy 0, policy_version 49372 (0.0009) -[2023-10-09 02:03:28,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 101122048. Throughput: 0: 1689.3, 1: 1696.9. Samples: 25287362. Policy #0 lag: (min: 31.0, avg: 46.4, max: 63.0) -[2023-10-09 02:03:28,975][87372] Avg episode reward: [(0, '6.980'), (1, '6.460')] -[2023-10-09 02:03:29,319][88327] Updated weights for policy 1, policy_version 49380 (0.0009) -[2023-10-09 02:03:29,678][88327] Updated weights for policy 1, policy_version 49390 (0.0009) -[2023-10-09 02:03:30,040][88327] Updated weights for policy 1, policy_version 49400 (0.0011) -[2023-10-09 02:03:31,633][88326] Updated weights for policy 0, policy_version 49382 (0.0007) -[2023-10-09 02:03:32,004][88326] Updated weights for policy 0, policy_version 49392 (0.0008) -[2023-10-09 02:03:32,374][88326] Updated weights for policy 0, policy_version 49402 (0.0008) -[2023-10-09 02:03:33,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 101187584. Throughput: 0: 1689.1, 1: 1692.1. Samples: 25307660. Policy #0 lag: (min: 31.0, avg: 46.4, max: 63.0) -[2023-10-09 02:03:33,975][87372] Avg episode reward: [(0, '6.810'), (1, '6.280')] -[2023-10-09 02:03:34,142][88327] Updated weights for policy 1, policy_version 49410 (0.0011) -[2023-10-09 02:03:34,514][88327] Updated weights for policy 1, policy_version 49420 (0.0009) -[2023-10-09 02:03:34,879][88327] Updated weights for policy 1, policy_version 49430 (0.0009) -[2023-10-09 02:03:35,255][88327] Updated weights for policy 1, policy_version 49440 (0.0008) -[2023-10-09 02:03:36,166][88326] Updated weights for policy 0, policy_version 49412 (0.0007) -[2023-10-09 02:03:36,537][88326] Updated weights for policy 0, policy_version 49422 (0.0007) -[2023-10-09 02:03:36,906][88326] Updated weights for policy 0, policy_version 49432 (0.0009) -[2023-10-09 02:03:38,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 101253120. Throughput: 0: 1704.4, 1: 1674.1. Samples: 25317798. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:03:38,975][87372] Avg episode reward: [(0, '5.900'), (1, '6.120')] -[2023-10-09 02:03:39,351][88327] Updated weights for policy 1, policy_version 49450 (0.0009) -[2023-10-09 02:03:39,722][88327] Updated weights for policy 1, policy_version 49460 (0.0010) -[2023-10-09 02:03:40,083][88327] Updated weights for policy 1, policy_version 49470 (0.0008) -[2023-10-09 02:03:40,873][88326] Updated weights for policy 0, policy_version 49442 (0.0009) -[2023-10-09 02:03:41,239][88326] Updated weights for policy 0, policy_version 49452 (0.0007) -[2023-10-09 02:03:41,616][88326] Updated weights for policy 0, policy_version 49462 (0.0007) -[2023-10-09 02:03:41,982][88326] Updated weights for policy 0, policy_version 49472 (0.0008) -[2023-10-09 02:03:43,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 101318656. Throughput: 0: 1679.9, 1: 1691.5. Samples: 25337552. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:03:43,974][87372] Avg episode reward: [(0, '6.060'), (1, '6.280')] -[2023-10-09 02:03:44,182][88327] Updated weights for policy 1, policy_version 49480 (0.0011) -[2023-10-09 02:03:44,550][88327] Updated weights for policy 1, policy_version 49490 (0.0010) -[2023-10-09 02:03:44,913][88327] Updated weights for policy 1, policy_version 49500 (0.0011) -[2023-10-09 02:03:46,041][88326] Updated weights for policy 0, policy_version 49482 (0.0009) -[2023-10-09 02:03:46,402][88326] Updated weights for policy 0, policy_version 49492 (0.0008) -[2023-10-09 02:03:46,778][88326] Updated weights for policy 0, policy_version 49502 (0.0007) -[2023-10-09 02:03:48,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 101384192. Throughput: 0: 1700.2, 1: 1692.6. Samples: 25358508. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:03:48,975][87372] Avg episode reward: [(0, '6.250'), (1, '6.170')] -[2023-10-09 02:03:49,017][88327] Updated weights for policy 1, policy_version 49510 (0.0009) -[2023-10-09 02:03:49,382][88327] Updated weights for policy 1, policy_version 49520 (0.0008) -[2023-10-09 02:03:49,752][88327] Updated weights for policy 1, policy_version 49530 (0.0007) -[2023-10-09 02:03:50,970][88326] Updated weights for policy 0, policy_version 49512 (0.0008) -[2023-10-09 02:03:51,349][88326] Updated weights for policy 0, policy_version 49522 (0.0010) -[2023-10-09 02:03:51,719][88326] Updated weights for policy 0, policy_version 49532 (0.0009) -[2023-10-09 02:03:53,850][88327] Updated weights for policy 1, policy_version 49540 (0.0008) -[2023-10-09 02:03:53,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 101449728. Throughput: 0: 1698.5, 1: 1690.5. Samples: 25368276. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:03:53,975][87372] Avg episode reward: [(0, '6.190'), (1, '5.690')] -[2023-10-09 02:03:54,215][88327] Updated weights for policy 1, policy_version 49550 (0.0012) -[2023-10-09 02:03:54,586][88327] Updated weights for policy 1, policy_version 49560 (0.0009) -[2023-10-09 02:03:55,711][88326] Updated weights for policy 0, policy_version 49542 (0.0009) -[2023-10-09 02:03:56,065][88326] Updated weights for policy 0, policy_version 49552 (0.0009) -[2023-10-09 02:03:56,437][88326] Updated weights for policy 0, policy_version 49562 (0.0008) -[2023-10-09 02:03:58,584][88327] Updated weights for policy 1, policy_version 49570 (0.0008) -[2023-10-09 02:03:58,954][88327] Updated weights for policy 1, policy_version 49580 (0.0008) -[2023-10-09 02:03:58,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 101515264. Throughput: 0: 1685.6, 1: 1689.1. Samples: 25388544. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:03:58,975][87372] Avg episode reward: [(0, '6.450'), (1, '6.140')] -[2023-10-09 02:03:59,319][88327] Updated weights for policy 1, policy_version 49590 (0.0007) -[2023-10-09 02:03:59,675][88327] Updated weights for policy 1, policy_version 49600 (0.0008) -[2023-10-09 02:04:00,437][88326] Updated weights for policy 0, policy_version 49572 (0.0007) -[2023-10-09 02:04:00,808][88326] Updated weights for policy 0, policy_version 49582 (0.0007) -[2023-10-09 02:04:01,184][88326] Updated weights for policy 0, policy_version 49592 (0.0007) -[2023-10-09 02:04:03,694][88327] Updated weights for policy 1, policy_version 49610 (0.0007) -[2023-10-09 02:04:03,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 101580800. Throughput: 0: 1713.6, 1: 1687.2. Samples: 25409622. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:04:03,975][87372] Avg episode reward: [(0, '6.200'), (1, '5.920')] -[2023-10-09 02:04:04,059][88327] Updated weights for policy 1, policy_version 49620 (0.0011) -[2023-10-09 02:04:04,422][88327] Updated weights for policy 1, policy_version 49630 (0.0009) -[2023-10-09 02:04:05,040][88326] Updated weights for policy 0, policy_version 49602 (0.0007) -[2023-10-09 02:04:05,407][88326] Updated weights for policy 0, policy_version 49612 (0.0008) -[2023-10-09 02:04:05,781][88326] Updated weights for policy 0, policy_version 49622 (0.0007) -[2023-10-09 02:04:06,143][88326] Updated weights for policy 0, policy_version 49632 (0.0007) -[2023-10-09 02:04:08,574][88327] Updated weights for policy 1, policy_version 49640 (0.0007) -[2023-10-09 02:04:08,934][88327] Updated weights for policy 1, policy_version 49650 (0.0008) -[2023-10-09 02:04:08,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 101646336. Throughput: 0: 1686.6, 1: 1689.8. Samples: 25418922. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:04:08,975][87372] Avg episode reward: [(0, '5.750'), (1, '5.740')] -[2023-10-09 02:04:09,305][88327] Updated weights for policy 1, policy_version 49660 (0.0010) -[2023-10-09 02:04:10,066][88326] Updated weights for policy 0, policy_version 49642 (0.0009) -[2023-10-09 02:04:10,445][88326] Updated weights for policy 0, policy_version 49652 (0.0008) -[2023-10-09 02:04:10,812][88326] Updated weights for policy 0, policy_version 49662 (0.0009) -[2023-10-09 02:04:13,576][88327] Updated weights for policy 1, policy_version 49670 (0.0009) -[2023-10-09 02:04:13,939][88327] Updated weights for policy 1, policy_version 49680 (0.0009) -[2023-10-09 02:04:13,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 101711872. Throughput: 0: 1698.8, 1: 1686.8. Samples: 25439710. Policy #0 lag: (min: 31.0, avg: 46.3, max: 63.0) -[2023-10-09 02:04:13,975][87372] Avg episode reward: [(0, '5.990'), (1, '6.160')] -[2023-10-09 02:04:14,304][88327] Updated weights for policy 1, policy_version 49690 (0.0009) -[2023-10-09 02:04:14,963][88326] Updated weights for policy 0, policy_version 49672 (0.0009) -[2023-10-09 02:04:15,340][88326] Updated weights for policy 0, policy_version 49682 (0.0008) -[2023-10-09 02:04:15,707][88326] Updated weights for policy 0, policy_version 49692 (0.0008) -[2023-10-09 02:04:18,429][88327] Updated weights for policy 1, policy_version 49700 (0.0010) -[2023-10-09 02:04:18,803][88327] Updated weights for policy 1, policy_version 49710 (0.0007) -[2023-10-09 02:04:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 101777408. Throughput: 0: 1707.6, 1: 1683.9. Samples: 25460280. Policy #0 lag: (min: 31.0, avg: 46.3, max: 63.0) -[2023-10-09 02:04:18,975][87372] Avg episode reward: [(0, '6.270'), (1, '6.300')] -[2023-10-09 02:04:19,166][88327] Updated weights for policy 1, policy_version 49720 (0.0011) -[2023-10-09 02:04:19,889][88326] Updated weights for policy 0, policy_version 49702 (0.0007) -[2023-10-09 02:04:20,262][88326] Updated weights for policy 0, policy_version 49712 (0.0007) -[2023-10-09 02:04:20,626][88326] Updated weights for policy 0, policy_version 49722 (0.0008) -[2023-10-09 02:04:23,091][88327] Updated weights for policy 1, policy_version 49730 (0.0008) -[2023-10-09 02:04:23,459][88327] Updated weights for policy 1, policy_version 49740 (0.0010) -[2023-10-09 02:04:23,814][88327] Updated weights for policy 1, policy_version 49750 (0.0011) -[2023-10-09 02:04:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 101842944. Throughput: 0: 1683.3, 1: 1687.3. Samples: 25469474. Policy #0 lag: (min: 31.0, avg: 46.3, max: 63.0) -[2023-10-09 02:04:23,975][87372] Avg episode reward: [(0, '6.060'), (1, '6.370')] -[2023-10-09 02:04:24,178][88327] Updated weights for policy 1, policy_version 49760 (0.0009) -[2023-10-09 02:04:24,647][88326] Updated weights for policy 0, policy_version 49732 (0.0009) -[2023-10-09 02:04:25,001][88326] Updated weights for policy 0, policy_version 49742 (0.0009) -[2023-10-09 02:04:25,371][88326] Updated weights for policy 0, policy_version 49752 (0.0010) -[2023-10-09 02:04:28,255][88327] Updated weights for policy 1, policy_version 49770 (0.0008) -[2023-10-09 02:04:28,626][88327] Updated weights for policy 1, policy_version 49780 (0.0010) -[2023-10-09 02:04:28,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 101908480. Throughput: 0: 1710.8, 1: 1690.4. Samples: 25490602. Policy #0 lag: (min: 31.0, avg: 46.3, max: 63.0) -[2023-10-09 02:04:28,975][87372] Avg episode reward: [(0, '6.540'), (1, '6.490')] -[2023-10-09 02:04:28,993][88327] Updated weights for policy 1, policy_version 49790 (0.0009) -[2023-10-09 02:04:29,330][88326] Updated weights for policy 0, policy_version 49762 (0.0009) -[2023-10-09 02:04:29,697][88326] Updated weights for policy 0, policy_version 49772 (0.0007) -[2023-10-09 02:04:30,071][88326] Updated weights for policy 0, policy_version 49782 (0.0008) -[2023-10-09 02:04:30,430][88326] Updated weights for policy 0, policy_version 49792 (0.0009) -[2023-10-09 02:04:33,042][88327] Updated weights for policy 1, policy_version 49800 (0.0008) -[2023-10-09 02:04:33,404][88327] Updated weights for policy 1, policy_version 49810 (0.0009) -[2023-10-09 02:04:33,768][88327] Updated weights for policy 1, policy_version 49820 (0.0008) -[2023-10-09 02:04:33,974][87372] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 102006784. Throughput: 0: 1713.6, 1: 1671.8. Samples: 25510850. Policy #0 lag: (min: 31.0, avg: 46.3, max: 63.0) -[2023-10-09 02:04:33,975][87372] Avg episode reward: [(0, '6.410'), (1, '6.100')] -[2023-10-09 02:04:33,984][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000049824_51019776.pth... -[2023-10-09 02:04:34,013][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000048224_49381376.pth -[2023-10-09 02:04:34,435][88326] Updated weights for policy 0, policy_version 49802 (0.0009) -[2023-10-09 02:04:34,801][88326] Updated weights for policy 0, policy_version 49812 (0.0009) -[2023-10-09 02:04:35,176][88326] Updated weights for policy 0, policy_version 49822 (0.0011) -[2023-10-09 02:04:35,246][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000049824_51019776.pth... -[2023-10-09 02:04:35,276][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000048224_49381376.pth -[2023-10-09 02:04:37,949][88327] Updated weights for policy 1, policy_version 49830 (0.0010) -[2023-10-09 02:04:38,309][88327] Updated weights for policy 1, policy_version 49840 (0.0009) -[2023-10-09 02:04:38,679][88327] Updated weights for policy 1, policy_version 49850 (0.0009) -[2023-10-09 02:04:38,974][87372] Fps is (10 sec: 16383.8, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 102072320. Throughput: 0: 1699.8, 1: 1681.9. Samples: 25520454. Policy #0 lag: (min: 31.0, avg: 46.3, max: 63.0) -[2023-10-09 02:04:38,975][87372] Avg episode reward: [(0, '6.140'), (1, '6.110')] -[2023-10-09 02:04:39,357][88326] Updated weights for policy 0, policy_version 49832 (0.0009) -[2023-10-09 02:04:39,719][88326] Updated weights for policy 0, policy_version 49842 (0.0008) -[2023-10-09 02:04:40,089][88326] Updated weights for policy 0, policy_version 49852 (0.0008) -[2023-10-09 02:04:42,660][88327] Updated weights for policy 1, policy_version 49860 (0.0009) -[2023-10-09 02:04:43,022][88327] Updated weights for policy 1, policy_version 49870 (0.0010) -[2023-10-09 02:04:43,378][88327] Updated weights for policy 1, policy_version 49880 (0.0011) -[2023-10-09 02:04:43,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 102137856. Throughput: 0: 1707.1, 1: 1685.0. Samples: 25541190. Policy #0 lag: (min: 31.0, avg: 46.3, max: 63.0) -[2023-10-09 02:04:43,974][87372] Avg episode reward: [(0, '6.580'), (1, '6.190')] -[2023-10-09 02:04:44,007][88326] Updated weights for policy 0, policy_version 49862 (0.0009) -[2023-10-09 02:04:44,372][88326] Updated weights for policy 0, policy_version 49872 (0.0009) -[2023-10-09 02:04:44,735][88326] Updated weights for policy 0, policy_version 49882 (0.0009) -[2023-10-09 02:04:47,567][88327] Updated weights for policy 1, policy_version 49890 (0.0011) -[2023-10-09 02:04:47,937][88327] Updated weights for policy 1, policy_version 49900 (0.0009) -[2023-10-09 02:04:48,302][88327] Updated weights for policy 1, policy_version 49910 (0.0008) -[2023-10-09 02:04:48,667][88327] Updated weights for policy 1, policy_version 49920 (0.0008) -[2023-10-09 02:04:48,705][88326] Updated weights for policy 0, policy_version 49892 (0.0010) -[2023-10-09 02:04:48,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 102203392. Throughput: 0: 1709.2, 1: 1667.2. Samples: 25561564. Policy #0 lag: (min: 45.0, avg: 55.7, max: 56.0) -[2023-10-09 02:04:48,975][87372] Avg episode reward: [(0, '6.610'), (1, '5.840')] -[2023-10-09 02:04:49,075][88326] Updated weights for policy 0, policy_version 49902 (0.0009) -[2023-10-09 02:04:49,438][88326] Updated weights for policy 0, policy_version 49912 (0.0011) -[2023-10-09 02:04:52,690][88327] Updated weights for policy 1, policy_version 49930 (0.0010) -[2023-10-09 02:04:53,067][88327] Updated weights for policy 1, policy_version 49940 (0.0009) -[2023-10-09 02:04:53,438][88327] Updated weights for policy 1, policy_version 49950 (0.0011) -[2023-10-09 02:04:53,500][88326] Updated weights for policy 0, policy_version 49922 (0.0008) -[2023-10-09 02:04:53,869][88326] Updated weights for policy 0, policy_version 49932 (0.0007) -[2023-10-09 02:04:53,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 102268928. Throughput: 0: 1704.7, 1: 1682.0. Samples: 25571326. Policy #0 lag: (min: 45.0, avg: 55.7, max: 56.0) -[2023-10-09 02:04:53,975][87372] Avg episode reward: [(0, '6.600'), (1, '6.730')] -[2023-10-09 02:04:54,236][88326] Updated weights for policy 0, policy_version 49942 (0.0009) -[2023-10-09 02:04:54,595][88326] Updated weights for policy 0, policy_version 49952 (0.0009) -[2023-10-09 02:04:57,247][88327] Updated weights for policy 1, policy_version 49960 (0.0010) -[2023-10-09 02:04:57,615][88327] Updated weights for policy 1, policy_version 49970 (0.0010) -[2023-10-09 02:04:57,975][88327] Updated weights for policy 1, policy_version 49980 (0.0009) -[2023-10-09 02:04:58,453][88326] Updated weights for policy 0, policy_version 49962 (0.0010) -[2023-10-09 02:04:58,819][88326] Updated weights for policy 0, policy_version 49972 (0.0010) -[2023-10-09 02:04:58,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 102334464. Throughput: 0: 1709.6, 1: 1686.2. Samples: 25592520. Policy #0 lag: (min: 45.0, avg: 55.7, max: 56.0) -[2023-10-09 02:04:58,975][87372] Avg episode reward: [(0, '6.450'), (1, '6.290')] -[2023-10-09 02:04:59,186][88326] Updated weights for policy 0, policy_version 49982 (0.0009) -[2023-10-09 02:05:01,977][88327] Updated weights for policy 1, policy_version 49990 (0.0008) -[2023-10-09 02:05:02,346][88327] Updated weights for policy 1, policy_version 50000 (0.0008) -[2023-10-09 02:05:02,706][88327] Updated weights for policy 1, policy_version 50010 (0.0009) -[2023-10-09 02:05:03,193][88326] Updated weights for policy 0, policy_version 49992 (0.0007) -[2023-10-09 02:05:03,552][88326] Updated weights for policy 0, policy_version 50002 (0.0009) -[2023-10-09 02:05:03,931][88326] Updated weights for policy 0, policy_version 50012 (0.0009) -[2023-10-09 02:05:03,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 102400000. Throughput: 0: 1708.3, 1: 1666.2. Samples: 25612134. Policy #0 lag: (min: 45.0, avg: 55.7, max: 56.0) -[2023-10-09 02:05:03,975][87372] Avg episode reward: [(0, '6.780'), (1, '6.550')] -[2023-10-09 02:05:06,718][88327] Updated weights for policy 1, policy_version 50020 (0.0008) -[2023-10-09 02:05:07,078][88327] Updated weights for policy 1, policy_version 50030 (0.0007) -[2023-10-09 02:05:07,452][88327] Updated weights for policy 1, policy_version 50040 (0.0008) -[2023-10-09 02:05:07,918][88326] Updated weights for policy 0, policy_version 50022 (0.0008) -[2023-10-09 02:05:08,281][88326] Updated weights for policy 0, policy_version 50032 (0.0007) -[2023-10-09 02:05:08,656][88326] Updated weights for policy 0, policy_version 50042 (0.0010) -[2023-10-09 02:05:08,974][87372] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 102498304. Throughput: 0: 1714.4, 1: 1698.9. Samples: 25623074. Policy #0 lag: (min: 45.0, avg: 55.7, max: 56.0) -[2023-10-09 02:05:08,974][87372] Avg episode reward: [(0, '6.570'), (1, '6.810')] -[2023-10-09 02:05:11,565][88327] Updated weights for policy 1, policy_version 50050 (0.0008) -[2023-10-09 02:05:11,916][88327] Updated weights for policy 1, policy_version 50060 (0.0011) -[2023-10-09 02:05:12,281][88327] Updated weights for policy 1, policy_version 50070 (0.0008) -[2023-10-09 02:05:12,644][88327] Updated weights for policy 1, policy_version 50080 (0.0007) -[2023-10-09 02:05:12,721][88326] Updated weights for policy 0, policy_version 50052 (0.0007) -[2023-10-09 02:05:13,103][88326] Updated weights for policy 0, policy_version 50062 (0.0007) -[2023-10-09 02:05:13,467][88326] Updated weights for policy 0, policy_version 50072 (0.0007) -[2023-10-09 02:05:13,974][87372] Fps is (10 sec: 16384.1, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 102563840. Throughput: 0: 1706.7, 1: 1682.9. Samples: 25643136. Policy #0 lag: (min: 45.0, avg: 55.7, max: 56.0) -[2023-10-09 02:05:13,975][87372] Avg episode reward: [(0, '6.800'), (1, '6.610')] -[2023-10-09 02:05:16,830][88327] Updated weights for policy 1, policy_version 50090 (0.0007) -[2023-10-09 02:05:17,207][88327] Updated weights for policy 1, policy_version 50100 (0.0008) -[2023-10-09 02:05:17,346][88326] Updated weights for policy 0, policy_version 50082 (0.0009) -[2023-10-09 02:05:17,568][88327] Updated weights for policy 1, policy_version 50110 (0.0008) -[2023-10-09 02:05:17,712][88326] Updated weights for policy 0, policy_version 50092 (0.0007) -[2023-10-09 02:05:18,081][88326] Updated weights for policy 0, policy_version 50102 (0.0009) -[2023-10-09 02:05:18,451][88326] Updated weights for policy 0, policy_version 50112 (0.0010) -[2023-10-09 02:05:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 102629376. Throughput: 0: 1684.8, 1: 1681.4. Samples: 25662326. Policy #0 lag: (min: 31.0, avg: 33.3, max: 63.0) -[2023-10-09 02:05:18,974][87372] Avg episode reward: [(0, '6.700'), (1, '6.720')] -[2023-10-09 02:05:21,499][88327] Updated weights for policy 1, policy_version 50120 (0.0010) -[2023-10-09 02:05:21,868][88327] Updated weights for policy 1, policy_version 50130 (0.0010) -[2023-10-09 02:05:22,232][88327] Updated weights for policy 1, policy_version 50140 (0.0009) -[2023-10-09 02:05:22,518][88326] Updated weights for policy 0, policy_version 50122 (0.0009) -[2023-10-09 02:05:22,879][88326] Updated weights for policy 0, policy_version 50132 (0.0008) -[2023-10-09 02:05:23,248][88326] Updated weights for policy 0, policy_version 50142 (0.0007) -[2023-10-09 02:05:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 102694912. Throughput: 0: 1706.4, 1: 1699.2. Samples: 25673710. Policy #0 lag: (min: 31.0, avg: 33.3, max: 63.0) -[2023-10-09 02:05:23,975][87372] Avg episode reward: [(0, '7.120'), (1, '6.270')] -[2023-10-09 02:05:26,164][88327] Updated weights for policy 1, policy_version 50150 (0.0009) -[2023-10-09 02:05:26,544][88327] Updated weights for policy 1, policy_version 50160 (0.0011) -[2023-10-09 02:05:26,918][88327] Updated weights for policy 1, policy_version 50170 (0.0008) -[2023-10-09 02:05:27,349][88326] Updated weights for policy 0, policy_version 50152 (0.0008) -[2023-10-09 02:05:27,723][88326] Updated weights for policy 0, policy_version 50162 (0.0007) -[2023-10-09 02:05:28,099][88326] Updated weights for policy 0, policy_version 50172 (0.0008) -[2023-10-09 02:05:28,974][87372] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 102760448. Throughput: 0: 1704.4, 1: 1672.1. Samples: 25693132. Policy #0 lag: (min: 31.0, avg: 33.3, max: 63.0) -[2023-10-09 02:05:28,975][87372] Avg episode reward: [(0, '6.440'), (1, '5.960')] -[2023-10-09 02:05:30,816][88327] Updated weights for policy 1, policy_version 50180 (0.0008) -[2023-10-09 02:05:31,178][88327] Updated weights for policy 1, policy_version 50190 (0.0010) -[2023-10-09 02:05:31,547][88327] Updated weights for policy 1, policy_version 50200 (0.0007) -[2023-10-09 02:05:32,079][88326] Updated weights for policy 0, policy_version 50182 (0.0010) -[2023-10-09 02:05:32,453][88326] Updated weights for policy 0, policy_version 50192 (0.0008) -[2023-10-09 02:05:32,818][88326] Updated weights for policy 0, policy_version 50202 (0.0008) -[2023-10-09 02:05:33,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 102825984. Throughput: 0: 1674.8, 1: 1692.1. Samples: 25713076. Policy #0 lag: (min: 31.0, avg: 33.3, max: 63.0) -[2023-10-09 02:05:33,975][87372] Avg episode reward: [(0, '6.960'), (1, '6.140')] -[2023-10-09 02:05:35,593][88327] Updated weights for policy 1, policy_version 50210 (0.0009) -[2023-10-09 02:05:35,971][88327] Updated weights for policy 1, policy_version 50220 (0.0007) -[2023-10-09 02:05:36,340][88327] Updated weights for policy 1, policy_version 50230 (0.0007) -[2023-10-09 02:05:36,708][88327] Updated weights for policy 1, policy_version 50240 (0.0009) -[2023-10-09 02:05:36,743][88326] Updated weights for policy 0, policy_version 50212 (0.0008) -[2023-10-09 02:05:37,114][88326] Updated weights for policy 0, policy_version 50222 (0.0009) -[2023-10-09 02:05:37,498][88326] Updated weights for policy 0, policy_version 50232 (0.0007) -[2023-10-09 02:05:38,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 102891520. Throughput: 0: 1707.5, 1: 1689.4. Samples: 25724188. Policy #0 lag: (min: 31.0, avg: 33.3, max: 63.0) -[2023-10-09 02:05:38,975][87372] Avg episode reward: [(0, '7.270'), (1, '6.120')] -[2023-10-09 02:05:40,767][88327] Updated weights for policy 1, policy_version 50250 (0.0009) -[2023-10-09 02:05:41,134][88327] Updated weights for policy 1, policy_version 50260 (0.0009) -[2023-10-09 02:05:41,505][88327] Updated weights for policy 1, policy_version 50270 (0.0010) -[2023-10-09 02:05:41,620][88326] Updated weights for policy 0, policy_version 50242 (0.0009) -[2023-10-09 02:05:41,983][88326] Updated weights for policy 0, policy_version 50252 (0.0009) -[2023-10-09 02:05:42,356][88326] Updated weights for policy 0, policy_version 50262 (0.0007) -[2023-10-09 02:05:42,729][88326] Updated weights for policy 0, policy_version 50272 (0.0010) -[2023-10-09 02:05:43,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 102957056. Throughput: 0: 1684.5, 1: 1673.5. Samples: 25743630. Policy #0 lag: (min: 31.0, avg: 33.3, max: 63.0) -[2023-10-09 02:05:43,975][87372] Avg episode reward: [(0, '6.280'), (1, '6.130')] -[2023-10-09 02:05:45,609][88327] Updated weights for policy 1, policy_version 50280 (0.0009) -[2023-10-09 02:05:45,976][88327] Updated weights for policy 1, policy_version 50290 (0.0009) -[2023-10-09 02:05:46,341][88327] Updated weights for policy 1, policy_version 50300 (0.0007) -[2023-10-09 02:05:46,698][88326] Updated weights for policy 0, policy_version 50282 (0.0007) -[2023-10-09 02:05:47,061][88326] Updated weights for policy 0, policy_version 50292 (0.0008) -[2023-10-09 02:05:47,428][88326] Updated weights for policy 0, policy_version 50302 (0.0007) -[2023-10-09 02:05:48,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 103022592. Throughput: 0: 1676.7, 1: 1700.3. Samples: 25764100. Policy #0 lag: (min: 31.0, avg: 33.3, max: 63.0) -[2023-10-09 02:05:48,975][87372] Avg episode reward: [(0, '6.420'), (1, '6.700')] -[2023-10-09 02:05:50,325][88327] Updated weights for policy 1, policy_version 50310 (0.0009) -[2023-10-09 02:05:50,693][88327] Updated weights for policy 1, policy_version 50320 (0.0009) -[2023-10-09 02:05:51,059][88327] Updated weights for policy 1, policy_version 50330 (0.0008) -[2023-10-09 02:05:51,462][88326] Updated weights for policy 0, policy_version 50312 (0.0007) -[2023-10-09 02:05:51,825][88326] Updated weights for policy 0, policy_version 50322 (0.0010) -[2023-10-09 02:05:52,196][88326] Updated weights for policy 0, policy_version 50332 (0.0008) -[2023-10-09 02:05:53,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 103088128. Throughput: 0: 1697.5, 1: 1671.1. Samples: 25774666. Policy #0 lag: (min: 18.0, avg: 24.5, max: 50.0) -[2023-10-09 02:05:53,975][87372] Avg episode reward: [(0, '6.170'), (1, '6.240')] -[2023-10-09 02:05:55,008][88327] Updated weights for policy 1, policy_version 50340 (0.0009) -[2023-10-09 02:05:55,364][88327] Updated weights for policy 1, policy_version 50350 (0.0007) -[2023-10-09 02:05:55,730][88327] Updated weights for policy 1, policy_version 50360 (0.0008) -[2023-10-09 02:05:56,236][88326] Updated weights for policy 0, policy_version 50342 (0.0010) -[2023-10-09 02:05:56,606][88326] Updated weights for policy 0, policy_version 50352 (0.0007) -[2023-10-09 02:05:56,975][88326] Updated weights for policy 0, policy_version 50362 (0.0009) -[2023-10-09 02:05:58,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 103153664. Throughput: 0: 1673.2, 1: 1690.3. Samples: 25794496. Policy #0 lag: (min: 18.0, avg: 24.5, max: 50.0) -[2023-10-09 02:05:58,975][87372] Avg episode reward: [(0, '5.750'), (1, '6.520')] -[2023-10-09 02:05:59,828][88327] Updated weights for policy 1, policy_version 50370 (0.0008) -[2023-10-09 02:06:00,198][88327] Updated weights for policy 1, policy_version 50380 (0.0008) -[2023-10-09 02:06:00,562][88327] Updated weights for policy 1, policy_version 50390 (0.0008) -[2023-10-09 02:06:00,926][88327] Updated weights for policy 1, policy_version 50400 (0.0011) -[2023-10-09 02:06:01,188][88326] Updated weights for policy 0, policy_version 50372 (0.0010) -[2023-10-09 02:06:01,558][88326] Updated weights for policy 0, policy_version 50382 (0.0007) -[2023-10-09 02:06:01,930][88326] Updated weights for policy 0, policy_version 50392 (0.0007) -[2023-10-09 02:06:03,974][87372] Fps is (10 sec: 13107.6, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 103219200. Throughput: 0: 1692.6, 1: 1706.5. Samples: 25815286. Policy #0 lag: (min: 18.0, avg: 24.5, max: 50.0) -[2023-10-09 02:06:03,974][87372] Avg episode reward: [(0, '6.320'), (1, '6.570')] -[2023-10-09 02:06:05,121][88327] Updated weights for policy 1, policy_version 50410 (0.0010) -[2023-10-09 02:06:05,476][88327] Updated weights for policy 1, policy_version 50420 (0.0008) -[2023-10-09 02:06:05,848][88327] Updated weights for policy 1, policy_version 50430 (0.0008) -[2023-10-09 02:06:05,912][88326] Updated weights for policy 0, policy_version 50402 (0.0007) -[2023-10-09 02:06:06,285][88326] Updated weights for policy 0, policy_version 50412 (0.0008) -[2023-10-09 02:06:06,657][88326] Updated weights for policy 0, policy_version 50422 (0.0009) -[2023-10-09 02:06:07,024][88326] Updated weights for policy 0, policy_version 50432 (0.0009) -[2023-10-09 02:06:08,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 103284736. Throughput: 0: 1692.3, 1: 1674.9. Samples: 25825232. Policy #0 lag: (min: 18.0, avg: 24.5, max: 50.0) -[2023-10-09 02:06:08,975][87372] Avg episode reward: [(0, '6.360'), (1, '6.320')] -[2023-10-09 02:06:10,008][88327] Updated weights for policy 1, policy_version 50440 (0.0008) -[2023-10-09 02:06:10,372][88327] Updated weights for policy 1, policy_version 50450 (0.0010) -[2023-10-09 02:06:10,735][88327] Updated weights for policy 1, policy_version 50460 (0.0010) -[2023-10-09 02:06:10,968][88326] Updated weights for policy 0, policy_version 50442 (0.0010) -[2023-10-09 02:06:11,337][88326] Updated weights for policy 0, policy_version 50452 (0.0009) -[2023-10-09 02:06:11,709][88326] Updated weights for policy 0, policy_version 50462 (0.0008) -[2023-10-09 02:06:13,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 103350272. Throughput: 0: 1675.9, 1: 1699.3. Samples: 25845014. Policy #0 lag: (min: 18.0, avg: 24.5, max: 50.0) -[2023-10-09 02:06:13,975][87372] Avg episode reward: [(0, '6.060'), (1, '5.710')] -[2023-10-09 02:06:14,825][88327] Updated weights for policy 1, policy_version 50470 (0.0008) -[2023-10-09 02:06:15,181][88327] Updated weights for policy 1, policy_version 50480 (0.0009) -[2023-10-09 02:06:15,543][88327] Updated weights for policy 1, policy_version 50490 (0.0010) -[2023-10-09 02:06:15,904][88326] Updated weights for policy 0, policy_version 50472 (0.0009) -[2023-10-09 02:06:16,275][88326] Updated weights for policy 0, policy_version 50482 (0.0009) -[2023-10-09 02:06:16,644][88326] Updated weights for policy 0, policy_version 50492 (0.0011) -[2023-10-09 02:06:18,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 103415808. Throughput: 0: 1696.2, 1: 1703.5. Samples: 25866062. Policy #0 lag: (min: 18.0, avg: 24.5, max: 50.0) -[2023-10-09 02:06:18,975][87372] Avg episode reward: [(0, '6.510'), (1, '6.630')] -[2023-10-09 02:06:19,413][88327] Updated weights for policy 1, policy_version 50500 (0.0008) -[2023-10-09 02:06:19,774][88327] Updated weights for policy 1, policy_version 50510 (0.0008) -[2023-10-09 02:06:20,150][88327] Updated weights for policy 1, policy_version 50520 (0.0010) -[2023-10-09 02:06:20,681][88326] Updated weights for policy 0, policy_version 50502 (0.0009) -[2023-10-09 02:06:21,051][88326] Updated weights for policy 0, policy_version 50512 (0.0007) -[2023-10-09 02:06:21,422][88326] Updated weights for policy 0, policy_version 50522 (0.0008) -[2023-10-09 02:06:23,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 103481344. Throughput: 0: 1678.3, 1: 1692.9. Samples: 25875890. Policy #0 lag: (min: 18.0, avg: 24.5, max: 50.0) -[2023-10-09 02:06:23,975][87372] Avg episode reward: [(0, '6.350'), (1, '6.490')] -[2023-10-09 02:06:24,212][88327] Updated weights for policy 1, policy_version 50530 (0.0009) -[2023-10-09 02:06:24,580][88327] Updated weights for policy 1, policy_version 50540 (0.0007) -[2023-10-09 02:06:24,943][88327] Updated weights for policy 1, policy_version 50550 (0.0007) -[2023-10-09 02:06:25,306][88327] Updated weights for policy 1, policy_version 50560 (0.0007) -[2023-10-09 02:06:25,446][88326] Updated weights for policy 0, policy_version 50532 (0.0009) -[2023-10-09 02:06:25,819][88326] Updated weights for policy 0, policy_version 50542 (0.0009) -[2023-10-09 02:06:26,190][88326] Updated weights for policy 0, policy_version 50552 (0.0011) -[2023-10-09 02:06:28,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 103546880. Throughput: 0: 1686.5, 1: 1711.0. Samples: 25896516. Policy #0 lag: (min: 10.0, avg: 18.1, max: 42.0) -[2023-10-09 02:06:28,974][87372] Avg episode reward: [(0, '6.240'), (1, '6.140')] -[2023-10-09 02:06:29,218][88327] Updated weights for policy 1, policy_version 50570 (0.0008) -[2023-10-09 02:06:29,594][88327] Updated weights for policy 1, policy_version 50580 (0.0008) -[2023-10-09 02:06:29,954][88327] Updated weights for policy 1, policy_version 50590 (0.0009) -[2023-10-09 02:06:30,058][88326] Updated weights for policy 0, policy_version 50562 (0.0008) -[2023-10-09 02:06:30,424][88326] Updated weights for policy 0, policy_version 50572 (0.0008) -[2023-10-09 02:06:30,800][88326] Updated weights for policy 0, policy_version 50582 (0.0007) -[2023-10-09 02:06:31,159][88326] Updated weights for policy 0, policy_version 50592 (0.0008) -[2023-10-09 02:06:33,802][88327] Updated weights for policy 1, policy_version 50600 (0.0009) -[2023-10-09 02:06:33,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 103612416. Throughput: 0: 1700.6, 1: 1711.0. Samples: 25917624. Policy #0 lag: (min: 10.0, avg: 18.1, max: 42.0) -[2023-10-09 02:06:33,975][87372] Avg episode reward: [(0, '6.330'), (1, '6.640')] -[2023-10-09 02:06:33,982][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000050592_51806208.pth... -[2023-10-09 02:06:34,014][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000049024_50200576.pth -[2023-10-09 02:06:34,173][88327] Updated weights for policy 1, policy_version 50610 (0.0010) -[2023-10-09 02:06:34,535][88327] Updated weights for policy 1, policy_version 50620 (0.0007) -[2023-10-09 02:06:34,678][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000050624_51838976.pth... -[2023-10-09 02:06:34,707][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000049024_50200576.pth -[2023-10-09 02:06:35,233][88326] Updated weights for policy 0, policy_version 50602 (0.0008) -[2023-10-09 02:06:35,604][88326] Updated weights for policy 0, policy_version 50612 (0.0008) -[2023-10-09 02:06:35,970][88326] Updated weights for policy 0, policy_version 50622 (0.0007) -[2023-10-09 02:06:38,432][88327] Updated weights for policy 1, policy_version 50630 (0.0008) -[2023-10-09 02:06:38,802][88327] Updated weights for policy 1, policy_version 50640 (0.0008) -[2023-10-09 02:06:38,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 103677952. Throughput: 0: 1672.4, 1: 1709.4. Samples: 25926844. Policy #0 lag: (min: 10.0, avg: 18.1, max: 42.0) -[2023-10-09 02:06:38,975][87372] Avg episode reward: [(0, '6.690'), (1, '6.320')] -[2023-10-09 02:06:39,167][88327] Updated weights for policy 1, policy_version 50650 (0.0007) -[2023-10-09 02:06:39,912][88326] Updated weights for policy 0, policy_version 50632 (0.0010) -[2023-10-09 02:06:40,289][88326] Updated weights for policy 0, policy_version 50642 (0.0010) -[2023-10-09 02:06:40,651][88326] Updated weights for policy 0, policy_version 50652 (0.0007) -[2023-10-09 02:06:43,067][88327] Updated weights for policy 1, policy_version 50660 (0.0009) -[2023-10-09 02:06:43,429][88327] Updated weights for policy 1, policy_version 50670 (0.0009) -[2023-10-09 02:06:43,802][88327] Updated weights for policy 1, policy_version 50680 (0.0007) -[2023-10-09 02:06:43,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 103743488. Throughput: 0: 1698.4, 1: 1714.7. Samples: 25948082. Policy #0 lag: (min: 10.0, avg: 18.1, max: 42.0) -[2023-10-09 02:06:43,975][87372] Avg episode reward: [(0, '6.420'), (1, '6.500')] -[2023-10-09 02:06:44,645][88326] Updated weights for policy 0, policy_version 50662 (0.0008) -[2023-10-09 02:06:45,017][88326] Updated weights for policy 0, policy_version 50672 (0.0008) -[2023-10-09 02:06:45,379][88326] Updated weights for policy 0, policy_version 50682 (0.0011) -[2023-10-09 02:06:47,957][88327] Updated weights for policy 1, policy_version 50690 (0.0010) -[2023-10-09 02:06:48,329][88327] Updated weights for policy 1, policy_version 50700 (0.0008) -[2023-10-09 02:06:48,693][88327] Updated weights for policy 1, policy_version 50710 (0.0008) -[2023-10-09 02:06:48,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 103809024. Throughput: 0: 1698.2, 1: 1709.4. Samples: 25968628. Policy #0 lag: (min: 10.0, avg: 18.1, max: 42.0) -[2023-10-09 02:06:48,975][87372] Avg episode reward: [(0, '6.170'), (1, '6.290')] -[2023-10-09 02:06:49,046][88327] Updated weights for policy 1, policy_version 50720 (0.0011) -[2023-10-09 02:06:49,452][88326] Updated weights for policy 0, policy_version 50692 (0.0007) -[2023-10-09 02:06:49,821][88326] Updated weights for policy 0, policy_version 50702 (0.0008) -[2023-10-09 02:06:50,184][88326] Updated weights for policy 0, policy_version 50712 (0.0008) -[2023-10-09 02:06:53,298][88327] Updated weights for policy 1, policy_version 50730 (0.0009) -[2023-10-09 02:06:53,664][88327] Updated weights for policy 1, policy_version 50740 (0.0009) -[2023-10-09 02:06:53,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.3, 300 sec: 13440.4). Total num frames: 103874560. Throughput: 0: 1677.4, 1: 1718.2. Samples: 25978032. Policy #0 lag: (min: 10.0, avg: 18.1, max: 42.0) -[2023-10-09 02:06:53,974][87372] Avg episode reward: [(0, '6.110'), (1, '6.680')] -[2023-10-09 02:06:54,030][88327] Updated weights for policy 1, policy_version 50750 (0.0008) -[2023-10-09 02:06:54,302][88326] Updated weights for policy 0, policy_version 50722 (0.0009) -[2023-10-09 02:06:54,672][88326] Updated weights for policy 0, policy_version 50732 (0.0010) -[2023-10-09 02:06:55,042][88326] Updated weights for policy 0, policy_version 50742 (0.0007) -[2023-10-09 02:06:55,414][88326] Updated weights for policy 0, policy_version 50752 (0.0008) -[2023-10-09 02:06:58,127][88327] Updated weights for policy 1, policy_version 50760 (0.0007) -[2023-10-09 02:06:58,493][88327] Updated weights for policy 1, policy_version 50770 (0.0007) -[2023-10-09 02:06:58,860][88327] Updated weights for policy 1, policy_version 50780 (0.0007) -[2023-10-09 02:06:58,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 103940096. Throughput: 0: 1697.7, 1: 1718.2. Samples: 25998732. Policy #0 lag: (min: 10.0, avg: 18.1, max: 42.0) -[2023-10-09 02:06:58,974][87372] Avg episode reward: [(0, '5.840'), (1, '6.620')] -[2023-10-09 02:06:59,610][88326] Updated weights for policy 0, policy_version 50762 (0.0009) -[2023-10-09 02:06:59,985][88326] Updated weights for policy 0, policy_version 50772 (0.0008) -[2023-10-09 02:07:00,353][88326] Updated weights for policy 0, policy_version 50782 (0.0007) -[2023-10-09 02:07:02,828][88327] Updated weights for policy 1, policy_version 50790 (0.0008) -[2023-10-09 02:07:03,188][88327] Updated weights for policy 1, policy_version 50800 (0.0008) -[2023-10-09 02:07:03,560][88327] Updated weights for policy 1, policy_version 50810 (0.0007) -[2023-10-09 02:07:03,974][87372] Fps is (10 sec: 16383.7, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 104038400. Throughput: 0: 1702.3, 1: 1696.9. Samples: 26019028. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:07:03,975][87372] Avg episode reward: [(0, '5.590'), (1, '6.900')] -[2023-10-09 02:07:04,372][88326] Updated weights for policy 0, policy_version 50792 (0.0008) -[2023-10-09 02:07:04,758][88326] Updated weights for policy 0, policy_version 50802 (0.0008) -[2023-10-09 02:07:05,116][88326] Updated weights for policy 0, policy_version 50812 (0.0008) -[2023-10-09 02:07:07,792][88327] Updated weights for policy 1, policy_version 50820 (0.0008) -[2023-10-09 02:07:08,153][88327] Updated weights for policy 1, policy_version 50830 (0.0008) -[2023-10-09 02:07:08,514][88327] Updated weights for policy 1, policy_version 50840 (0.0007) -[2023-10-09 02:07:08,974][87372] Fps is (10 sec: 16383.9, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 104103936. Throughput: 0: 1688.4, 1: 1706.0. Samples: 26028636. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:07:08,975][87372] Avg episode reward: [(0, '6.130'), (1, '6.660')] -[2023-10-09 02:07:09,174][88326] Updated weights for policy 0, policy_version 50822 (0.0008) -[2023-10-09 02:07:09,536][88326] Updated weights for policy 0, policy_version 50832 (0.0007) -[2023-10-09 02:07:09,914][88326] Updated weights for policy 0, policy_version 50842 (0.0008) -[2023-10-09 02:07:12,331][88327] Updated weights for policy 1, policy_version 50850 (0.0010) -[2023-10-09 02:07:12,697][88327] Updated weights for policy 1, policy_version 50860 (0.0011) -[2023-10-09 02:07:13,065][88327] Updated weights for policy 1, policy_version 50870 (0.0011) -[2023-10-09 02:07:13,424][88327] Updated weights for policy 1, policy_version 50880 (0.0010) -[2023-10-09 02:07:13,899][88326] Updated weights for policy 0, policy_version 50852 (0.0007) -[2023-10-09 02:07:13,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 104169472. Throughput: 0: 1695.4, 1: 1705.5. Samples: 26049556. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:07:13,975][87372] Avg episode reward: [(0, '6.020'), (1, '6.580')] -[2023-10-09 02:07:14,275][88326] Updated weights for policy 0, policy_version 50862 (0.0009) -[2023-10-09 02:07:14,648][88326] Updated weights for policy 0, policy_version 50872 (0.0008) -[2023-10-09 02:07:17,559][88327] Updated weights for policy 1, policy_version 50890 (0.0009) -[2023-10-09 02:07:17,925][88327] Updated weights for policy 1, policy_version 50900 (0.0009) -[2023-10-09 02:07:18,284][88327] Updated weights for policy 1, policy_version 50910 (0.0008) -[2023-10-09 02:07:18,699][88326] Updated weights for policy 0, policy_version 50882 (0.0010) -[2023-10-09 02:07:18,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 104235008. Throughput: 0: 1695.1, 1: 1677.6. Samples: 26069398. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:07:18,975][87372] Avg episode reward: [(0, '6.360'), (1, '5.830')] -[2023-10-09 02:07:19,070][88326] Updated weights for policy 0, policy_version 50892 (0.0011) -[2023-10-09 02:07:19,453][88326] Updated weights for policy 0, policy_version 50902 (0.0008) -[2023-10-09 02:07:19,828][88326] Updated weights for policy 0, policy_version 50912 (0.0008) -[2023-10-09 02:07:22,352][88327] Updated weights for policy 1, policy_version 50920 (0.0009) -[2023-10-09 02:07:22,711][88327] Updated weights for policy 1, policy_version 50930 (0.0009) -[2023-10-09 02:07:23,081][88327] Updated weights for policy 1, policy_version 50940 (0.0007) -[2023-10-09 02:07:23,952][88326] Updated weights for policy 0, policy_version 50922 (0.0010) -[2023-10-09 02:07:23,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 104300544. Throughput: 0: 1692.1, 1: 1698.7. Samples: 26079430. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:07:23,975][87372] Avg episode reward: [(0, '6.390'), (1, '5.720')] -[2023-10-09 02:07:24,311][88326] Updated weights for policy 0, policy_version 50932 (0.0009) -[2023-10-09 02:07:24,685][88326] Updated weights for policy 0, policy_version 50942 (0.0009) -[2023-10-09 02:07:27,150][88327] Updated weights for policy 1, policy_version 50950 (0.0007) -[2023-10-09 02:07:27,503][88327] Updated weights for policy 1, policy_version 50960 (0.0009) -[2023-10-09 02:07:27,865][88327] Updated weights for policy 1, policy_version 50970 (0.0008) -[2023-10-09 02:07:28,758][88326] Updated weights for policy 0, policy_version 50952 (0.0007) -[2023-10-09 02:07:28,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 104366080. Throughput: 0: 1691.4, 1: 1685.3. Samples: 26100034. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:07:28,975][87372] Avg episode reward: [(0, '6.430'), (1, '6.140')] -[2023-10-09 02:07:29,126][88326] Updated weights for policy 0, policy_version 50962 (0.0008) -[2023-10-09 02:07:29,494][88326] Updated weights for policy 0, policy_version 50972 (0.0009) -[2023-10-09 02:07:32,025][88327] Updated weights for policy 1, policy_version 50980 (0.0008) -[2023-10-09 02:07:32,395][88327] Updated weights for policy 1, policy_version 50990 (0.0009) -[2023-10-09 02:07:32,759][88327] Updated weights for policy 1, policy_version 51000 (0.0007) -[2023-10-09 02:07:33,543][88326] Updated weights for policy 0, policy_version 50982 (0.0008) -[2023-10-09 02:07:33,914][88326] Updated weights for policy 0, policy_version 50992 (0.0007) -[2023-10-09 02:07:33,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 104431616. Throughput: 0: 1693.9, 1: 1665.8. Samples: 26119814. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:07:33,975][87372] Avg episode reward: [(0, '6.720'), (1, '6.040')] -[2023-10-09 02:07:34,281][88326] Updated weights for policy 0, policy_version 51002 (0.0007) -[2023-10-09 02:07:36,805][88327] Updated weights for policy 1, policy_version 51010 (0.0008) -[2023-10-09 02:07:37,169][88327] Updated weights for policy 1, policy_version 51020 (0.0010) -[2023-10-09 02:07:37,530][88327] Updated weights for policy 1, policy_version 51030 (0.0007) -[2023-10-09 02:07:37,894][88327] Updated weights for policy 1, policy_version 51040 (0.0009) -[2023-10-09 02:07:38,226][88326] Updated weights for policy 0, policy_version 51012 (0.0007) -[2023-10-09 02:07:38,593][88326] Updated weights for policy 0, policy_version 51022 (0.0007) -[2023-10-09 02:07:38,955][88326] Updated weights for policy 0, policy_version 51032 (0.0011) -[2023-10-09 02:07:38,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 104497152. Throughput: 0: 1691.1, 1: 1690.3. Samples: 26130194. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-09 02:07:38,975][87372] Avg episode reward: [(0, '6.490'), (1, '5.820')] -[2023-10-09 02:07:42,030][88327] Updated weights for policy 1, policy_version 51050 (0.0007) -[2023-10-09 02:07:42,396][88327] Updated weights for policy 1, policy_version 51060 (0.0007) -[2023-10-09 02:07:42,770][88327] Updated weights for policy 1, policy_version 51070 (0.0007) -[2023-10-09 02:07:42,987][88326] Updated weights for policy 0, policy_version 51042 (0.0011) -[2023-10-09 02:07:43,354][88326] Updated weights for policy 0, policy_version 51052 (0.0007) -[2023-10-09 02:07:43,727][88326] Updated weights for policy 0, policy_version 51062 (0.0009) -[2023-10-09 02:07:43,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 104562688. Throughput: 0: 1690.6, 1: 1678.5. Samples: 26150340. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-09 02:07:43,975][87372] Avg episode reward: [(0, '6.550'), (1, '6.420')] -[2023-10-09 02:07:44,089][88326] Updated weights for policy 0, policy_version 51072 (0.0010) -[2023-10-09 02:07:46,672][88327] Updated weights for policy 1, policy_version 51080 (0.0010) -[2023-10-09 02:07:47,043][88327] Updated weights for policy 1, policy_version 51090 (0.0008) -[2023-10-09 02:07:47,405][88327] Updated weights for policy 1, policy_version 51100 (0.0007) -[2023-10-09 02:07:48,167][88326] Updated weights for policy 0, policy_version 51082 (0.0008) -[2023-10-09 02:07:48,534][88326] Updated weights for policy 0, policy_version 51092 (0.0009) -[2023-10-09 02:07:48,909][88326] Updated weights for policy 0, policy_version 51102 (0.0012) -[2023-10-09 02:07:48,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 104628224. Throughput: 0: 1678.2, 1: 1675.7. Samples: 26169954. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-09 02:07:48,975][87372] Avg episode reward: [(0, '6.660'), (1, '6.440')] -[2023-10-09 02:07:51,462][88327] Updated weights for policy 1, policy_version 51110 (0.0008) -[2023-10-09 02:07:51,819][88327] Updated weights for policy 1, policy_version 51120 (0.0009) -[2023-10-09 02:07:52,184][88327] Updated weights for policy 1, policy_version 51130 (0.0010) -[2023-10-09 02:07:52,870][88326] Updated weights for policy 0, policy_version 51112 (0.0008) -[2023-10-09 02:07:53,240][88326] Updated weights for policy 0, policy_version 51122 (0.0007) -[2023-10-09 02:07:53,618][88326] Updated weights for policy 0, policy_version 51132 (0.0008) -[2023-10-09 02:07:53,974][87372] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 104726528. Throughput: 0: 1690.1, 1: 1693.5. Samples: 26180898. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-09 02:07:53,975][87372] Avg episode reward: [(0, '6.300'), (1, '6.560')] -[2023-10-09 02:07:56,185][88327] Updated weights for policy 1, policy_version 51140 (0.0008) -[2023-10-09 02:07:56,553][88327] Updated weights for policy 1, policy_version 51150 (0.0007) -[2023-10-09 02:07:56,914][88327] Updated weights for policy 1, policy_version 51160 (0.0007) -[2023-10-09 02:07:57,567][88326] Updated weights for policy 0, policy_version 51142 (0.0009) -[2023-10-09 02:07:57,938][88326] Updated weights for policy 0, policy_version 51152 (0.0008) -[2023-10-09 02:07:58,321][88326] Updated weights for policy 0, policy_version 51162 (0.0007) -[2023-10-09 02:07:58,974][87372] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 104792064. Throughput: 0: 1697.6, 1: 1665.9. Samples: 26200912. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-09 02:07:58,975][87372] Avg episode reward: [(0, '6.290'), (1, '6.620')] -[2023-10-09 02:08:00,858][88327] Updated weights for policy 1, policy_version 51170 (0.0010) -[2023-10-09 02:08:01,223][88327] Updated weights for policy 1, policy_version 51180 (0.0008) -[2023-10-09 02:08:01,585][88327] Updated weights for policy 1, policy_version 51190 (0.0007) -[2023-10-09 02:08:01,947][88327] Updated weights for policy 1, policy_version 51200 (0.0007) -[2023-10-09 02:08:02,279][88326] Updated weights for policy 0, policy_version 51172 (0.0008) -[2023-10-09 02:08:02,652][88326] Updated weights for policy 0, policy_version 51182 (0.0007) -[2023-10-09 02:08:03,028][88326] Updated weights for policy 0, policy_version 51192 (0.0008) -[2023-10-09 02:08:03,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 104857600. Throughput: 0: 1670.6, 1: 1689.1. Samples: 26220584. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-09 02:08:03,975][87372] Avg episode reward: [(0, '6.330'), (1, '6.950')] -[2023-10-09 02:08:05,879][88327] Updated weights for policy 1, policy_version 51210 (0.0009) -[2023-10-09 02:08:06,251][88327] Updated weights for policy 1, policy_version 51220 (0.0007) -[2023-10-09 02:08:06,614][88327] Updated weights for policy 1, policy_version 51230 (0.0007) -[2023-10-09 02:08:07,223][88326] Updated weights for policy 0, policy_version 51202 (0.0008) -[2023-10-09 02:08:07,585][88326] Updated weights for policy 0, policy_version 51212 (0.0007) -[2023-10-09 02:08:07,953][88326] Updated weights for policy 0, policy_version 51222 (0.0007) -[2023-10-09 02:08:08,322][88326] Updated weights for policy 0, policy_version 51232 (0.0008) -[2023-10-09 02:08:08,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 104923136. Throughput: 0: 1699.4, 1: 1680.1. Samples: 26231508. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-09 02:08:08,974][87372] Avg episode reward: [(0, '5.620'), (1, '6.580')] -[2023-10-09 02:08:10,616][88327] Updated weights for policy 1, policy_version 51240 (0.0007) -[2023-10-09 02:08:10,975][88327] Updated weights for policy 1, policy_version 51250 (0.0008) -[2023-10-09 02:08:11,336][88327] Updated weights for policy 1, policy_version 51260 (0.0007) -[2023-10-09 02:08:12,339][88326] Updated weights for policy 0, policy_version 51242 (0.0007) -[2023-10-09 02:08:12,716][88326] Updated weights for policy 0, policy_version 51252 (0.0008) -[2023-10-09 02:08:13,088][88326] Updated weights for policy 0, policy_version 51262 (0.0008) -[2023-10-09 02:08:13,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 104988672. Throughput: 0: 1692.6, 1: 1681.5. Samples: 26251868. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-09 02:08:13,975][87372] Avg episode reward: [(0, '5.670'), (1, '6.080')] -[2023-10-09 02:08:15,388][88327] Updated weights for policy 1, policy_version 51270 (0.0009) -[2023-10-09 02:08:15,766][88327] Updated weights for policy 1, policy_version 51280 (0.0011) -[2023-10-09 02:08:16,128][88327] Updated weights for policy 1, policy_version 51290 (0.0007) -[2023-10-09 02:08:17,158][88326] Updated weights for policy 0, policy_version 51272 (0.0008) -[2023-10-09 02:08:17,523][88326] Updated weights for policy 0, policy_version 51282 (0.0009) -[2023-10-09 02:08:17,889][88326] Updated weights for policy 0, policy_version 51292 (0.0011) -[2023-10-09 02:08:18,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 105054208. Throughput: 0: 1667.0, 1: 1710.5. Samples: 26271800. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-09 02:08:18,974][87372] Avg episode reward: [(0, '6.130'), (1, '6.510')] -[2023-10-09 02:08:20,033][88327] Updated weights for policy 1, policy_version 51300 (0.0009) -[2023-10-09 02:08:20,398][88327] Updated weights for policy 1, policy_version 51310 (0.0009) -[2023-10-09 02:08:20,765][88327] Updated weights for policy 1, policy_version 51320 (0.0010) -[2023-10-09 02:08:21,863][88326] Updated weights for policy 0, policy_version 51302 (0.0009) -[2023-10-09 02:08:22,241][88326] Updated weights for policy 0, policy_version 51312 (0.0009) -[2023-10-09 02:08:22,609][88326] Updated weights for policy 0, policy_version 51322 (0.0008) -[2023-10-09 02:08:23,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 105119744. Throughput: 0: 1700.5, 1: 1680.2. Samples: 26282326. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-09 02:08:23,975][87372] Avg episode reward: [(0, '6.410'), (1, '6.350')] -[2023-10-09 02:08:24,985][88327] Updated weights for policy 1, policy_version 51330 (0.0009) -[2023-10-09 02:08:25,358][88327] Updated weights for policy 1, policy_version 51340 (0.0009) -[2023-10-09 02:08:25,721][88327] Updated weights for policy 1, policy_version 51350 (0.0010) -[2023-10-09 02:08:26,089][88327] Updated weights for policy 1, policy_version 51360 (0.0010) -[2023-10-09 02:08:26,531][88326] Updated weights for policy 0, policy_version 51332 (0.0009) -[2023-10-09 02:08:26,902][88326] Updated weights for policy 0, policy_version 51342 (0.0010) -[2023-10-09 02:08:27,272][88326] Updated weights for policy 0, policy_version 51352 (0.0011) -[2023-10-09 02:08:28,974][87372] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 105185280. Throughput: 0: 1685.2, 1: 1691.1. Samples: 26302274. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-09 02:08:28,975][87372] Avg episode reward: [(0, '7.040'), (1, '5.960')] -[2023-10-09 02:08:30,163][88327] Updated weights for policy 1, policy_version 51370 (0.0008) -[2023-10-09 02:08:30,536][88327] Updated weights for policy 1, policy_version 51380 (0.0009) -[2023-10-09 02:08:30,904][88327] Updated weights for policy 1, policy_version 51390 (0.0008) -[2023-10-09 02:08:31,363][88326] Updated weights for policy 0, policy_version 51362 (0.0008) -[2023-10-09 02:08:31,729][88326] Updated weights for policy 0, policy_version 51372 (0.0009) -[2023-10-09 02:08:32,110][88326] Updated weights for policy 0, policy_version 51382 (0.0009) -[2023-10-09 02:08:32,479][88326] Updated weights for policy 0, policy_version 51392 (0.0009) -[2023-10-09 02:08:33,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 105250816. Throughput: 0: 1690.1, 1: 1706.3. Samples: 26322794. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-09 02:08:33,975][87372] Avg episode reward: [(0, '6.940'), (1, '6.150')] -[2023-10-09 02:08:33,985][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000051392_52625408.pth... -[2023-10-09 02:08:33,986][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000051392_52625408.pth... -[2023-10-09 02:08:34,026][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000049824_51019776.pth -[2023-10-09 02:08:34,030][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000049824_51019776.pth -[2023-10-09 02:08:34,689][88327] Updated weights for policy 1, policy_version 51400 (0.0008) -[2023-10-09 02:08:35,053][88327] Updated weights for policy 1, policy_version 51410 (0.0009) -[2023-10-09 02:08:35,411][88327] Updated weights for policy 1, policy_version 51420 (0.0009) -[2023-10-09 02:08:36,457][88326] Updated weights for policy 0, policy_version 51402 (0.0009) -[2023-10-09 02:08:36,826][88326] Updated weights for policy 0, policy_version 51412 (0.0008) -[2023-10-09 02:08:37,192][88326] Updated weights for policy 0, policy_version 51422 (0.0009) -[2023-10-09 02:08:38,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 105316352. Throughput: 0: 1705.9, 1: 1675.2. Samples: 26333052. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-09 02:08:38,975][87372] Avg episode reward: [(0, '6.160'), (1, '6.340')] -[2023-10-09 02:08:39,509][88327] Updated weights for policy 1, policy_version 51430 (0.0009) -[2023-10-09 02:08:39,878][88327] Updated weights for policy 1, policy_version 51440 (0.0008) -[2023-10-09 02:08:40,249][88327] Updated weights for policy 1, policy_version 51450 (0.0008) -[2023-10-09 02:08:41,217][88326] Updated weights for policy 0, policy_version 51432 (0.0007) -[2023-10-09 02:08:41,585][88326] Updated weights for policy 0, policy_version 51442 (0.0007) -[2023-10-09 02:08:41,951][88326] Updated weights for policy 0, policy_version 51452 (0.0009) -[2023-10-09 02:08:43,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 105381888. Throughput: 0: 1672.9, 1: 1704.9. Samples: 26352914. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-09 02:08:43,975][87372] Avg episode reward: [(0, '6.180'), (1, '6.180')] -[2023-10-09 02:08:44,226][88327] Updated weights for policy 1, policy_version 51460 (0.0009) -[2023-10-09 02:08:44,597][88327] Updated weights for policy 1, policy_version 51470 (0.0009) -[2023-10-09 02:08:44,961][88327] Updated weights for policy 1, policy_version 51480 (0.0008) -[2023-10-09 02:08:45,929][88326] Updated weights for policy 0, policy_version 51462 (0.0011) -[2023-10-09 02:08:46,301][88326] Updated weights for policy 0, policy_version 51472 (0.0010) -[2023-10-09 02:08:46,688][88326] Updated weights for policy 0, policy_version 51482 (0.0008) -[2023-10-09 02:08:48,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 105447424. Throughput: 0: 1697.1, 1: 1710.3. Samples: 26373914. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-09 02:08:48,975][87372] Avg episode reward: [(0, '5.580'), (1, '6.130')] -[2023-10-09 02:08:49,138][88327] Updated weights for policy 1, policy_version 51490 (0.0008) -[2023-10-09 02:08:49,501][88327] Updated weights for policy 1, policy_version 51500 (0.0008) -[2023-10-09 02:08:49,872][88327] Updated weights for policy 1, policy_version 51510 (0.0007) -[2023-10-09 02:08:50,238][88327] Updated weights for policy 1, policy_version 51520 (0.0008) -[2023-10-09 02:08:50,769][88326] Updated weights for policy 0, policy_version 51492 (0.0008) -[2023-10-09 02:08:51,129][88326] Updated weights for policy 0, policy_version 51502 (0.0008) -[2023-10-09 02:08:51,499][88326] Updated weights for policy 0, policy_version 51512 (0.0009) -[2023-10-09 02:08:53,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 105512960. Throughput: 0: 1684.1, 1: 1697.0. Samples: 26383658. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-09 02:08:53,975][87372] Avg episode reward: [(0, '5.980'), (1, '6.610')] -[2023-10-09 02:08:54,374][88327] Updated weights for policy 1, policy_version 51530 (0.0008) -[2023-10-09 02:08:54,736][88327] Updated weights for policy 1, policy_version 51540 (0.0009) -[2023-10-09 02:08:55,096][88327] Updated weights for policy 1, policy_version 51550 (0.0009) -[2023-10-09 02:08:55,380][88326] Updated weights for policy 0, policy_version 51522 (0.0008) -[2023-10-09 02:08:55,766][88326] Updated weights for policy 0, policy_version 51532 (0.0009) -[2023-10-09 02:08:56,135][88326] Updated weights for policy 0, policy_version 51542 (0.0008) -[2023-10-09 02:08:56,503][88326] Updated weights for policy 0, policy_version 51552 (0.0007) -[2023-10-09 02:08:58,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 105578496. Throughput: 0: 1678.5, 1: 1700.7. Samples: 26403930. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-09 02:08:58,975][87372] Avg episode reward: [(0, '6.460'), (1, '6.400')] -[2023-10-09 02:08:59,009][88327] Updated weights for policy 1, policy_version 51560 (0.0010) -[2023-10-09 02:08:59,379][88327] Updated weights for policy 1, policy_version 51570 (0.0008) -[2023-10-09 02:08:59,737][88327] Updated weights for policy 1, policy_version 51580 (0.0009) -[2023-10-09 02:09:00,447][88326] Updated weights for policy 0, policy_version 51562 (0.0007) -[2023-10-09 02:09:00,809][88326] Updated weights for policy 0, policy_version 51572 (0.0009) -[2023-10-09 02:09:01,175][88326] Updated weights for policy 0, policy_version 51582 (0.0008) -[2023-10-09 02:09:03,699][88327] Updated weights for policy 1, policy_version 51590 (0.0009) -[2023-10-09 02:09:03,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 105644032. Throughput: 0: 1707.2, 1: 1702.2. Samples: 26425224. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-09 02:09:03,974][87372] Avg episode reward: [(0, '6.160'), (1, '6.240')] -[2023-10-09 02:09:04,065][88327] Updated weights for policy 1, policy_version 51600 (0.0009) -[2023-10-09 02:09:04,426][88327] Updated weights for policy 1, policy_version 51610 (0.0007) -[2023-10-09 02:09:05,259][88326] Updated weights for policy 0, policy_version 51592 (0.0009) -[2023-10-09 02:09:05,619][88326] Updated weights for policy 0, policy_version 51602 (0.0007) -[2023-10-09 02:09:05,996][88326] Updated weights for policy 0, policy_version 51612 (0.0008) -[2023-10-09 02:09:08,546][88327] Updated weights for policy 1, policy_version 51620 (0.0007) -[2023-10-09 02:09:08,905][88327] Updated weights for policy 1, policy_version 51630 (0.0008) -[2023-10-09 02:09:08,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 105709568. Throughput: 0: 1678.5, 1: 1703.4. Samples: 26434514. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-09 02:09:08,975][87372] Avg episode reward: [(0, '6.760'), (1, '6.570')] -[2023-10-09 02:09:09,267][88327] Updated weights for policy 1, policy_version 51640 (0.0007) -[2023-10-09 02:09:09,957][88326] Updated weights for policy 0, policy_version 51622 (0.0007) -[2023-10-09 02:09:10,313][88326] Updated weights for policy 0, policy_version 51632 (0.0008) -[2023-10-09 02:09:10,686][88326] Updated weights for policy 0, policy_version 51642 (0.0009) -[2023-10-09 02:09:13,320][88327] Updated weights for policy 1, policy_version 51650 (0.0009) -[2023-10-09 02:09:13,695][88327] Updated weights for policy 1, policy_version 51660 (0.0009) -[2023-10-09 02:09:13,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 105775104. Throughput: 0: 1700.6, 1: 1705.5. Samples: 26455546. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-09 02:09:13,975][87372] Avg episode reward: [(0, '6.680'), (1, '6.070')] -[2023-10-09 02:09:14,054][88327] Updated weights for policy 1, policy_version 51670 (0.0011) -[2023-10-09 02:09:14,420][88327] Updated weights for policy 1, policy_version 51680 (0.0010) -[2023-10-09 02:09:14,829][88326] Updated weights for policy 0, policy_version 51652 (0.0010) -[2023-10-09 02:09:15,197][88326] Updated weights for policy 0, policy_version 51662 (0.0007) -[2023-10-09 02:09:15,570][88326] Updated weights for policy 0, policy_version 51672 (0.0008) -[2023-10-09 02:09:18,334][88327] Updated weights for policy 1, policy_version 51690 (0.0007) -[2023-10-09 02:09:18,710][88327] Updated weights for policy 1, policy_version 51700 (0.0009) -[2023-10-09 02:09:18,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 105840640. Throughput: 0: 1709.6, 1: 1705.4. Samples: 26476472. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:09:18,974][87372] Avg episode reward: [(0, '6.500'), (1, '6.370')] -[2023-10-09 02:09:19,077][88327] Updated weights for policy 1, policy_version 51710 (0.0009) -[2023-10-09 02:09:19,497][88326] Updated weights for policy 0, policy_version 51682 (0.0008) -[2023-10-09 02:09:19,872][88326] Updated weights for policy 0, policy_version 51692 (0.0007) -[2023-10-09 02:09:20,230][88326] Updated weights for policy 0, policy_version 51702 (0.0010) -[2023-10-09 02:09:20,600][88326] Updated weights for policy 0, policy_version 51712 (0.0010) -[2023-10-09 02:09:22,940][88327] Updated weights for policy 1, policy_version 51720 (0.0011) -[2023-10-09 02:09:23,310][88327] Updated weights for policy 1, policy_version 51730 (0.0007) -[2023-10-09 02:09:23,668][88327] Updated weights for policy 1, policy_version 51740 (0.0008) -[2023-10-09 02:09:23,974][87372] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 105938944. Throughput: 0: 1685.1, 1: 1716.6. Samples: 26486126. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:09:23,975][87372] Avg episode reward: [(0, '6.140'), (1, '6.670')] -[2023-10-09 02:09:24,696][88326] Updated weights for policy 0, policy_version 51722 (0.0007) -[2023-10-09 02:09:25,058][88326] Updated weights for policy 0, policy_version 51732 (0.0007) -[2023-10-09 02:09:25,427][88326] Updated weights for policy 0, policy_version 51742 (0.0010) -[2023-10-09 02:09:27,781][88327] Updated weights for policy 1, policy_version 51750 (0.0010) -[2023-10-09 02:09:28,146][88327] Updated weights for policy 1, policy_version 51760 (0.0008) -[2023-10-09 02:09:28,519][88327] Updated weights for policy 1, policy_version 51770 (0.0010) -[2023-10-09 02:09:28,974][87372] Fps is (10 sec: 16383.6, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 106004480. Throughput: 0: 1716.0, 1: 1711.8. Samples: 26507166. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:09:28,975][87372] Avg episode reward: [(0, '6.460'), (1, '6.020')] -[2023-10-09 02:09:29,471][88326] Updated weights for policy 0, policy_version 51752 (0.0007) -[2023-10-09 02:09:29,853][88326] Updated weights for policy 0, policy_version 51762 (0.0007) -[2023-10-09 02:09:30,226][88326] Updated weights for policy 0, policy_version 51772 (0.0007) -[2023-10-09 02:09:32,657][88327] Updated weights for policy 1, policy_version 51780 (0.0007) -[2023-10-09 02:09:33,021][88327] Updated weights for policy 1, policy_version 51790 (0.0007) -[2023-10-09 02:09:33,387][88327] Updated weights for policy 1, policy_version 51800 (0.0008) -[2023-10-09 02:09:33,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 106070016. Throughput: 0: 1716.9, 1: 1696.8. Samples: 26527530. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:09:33,975][87372] Avg episode reward: [(0, '5.830'), (1, '6.670')] -[2023-10-09 02:09:34,152][88326] Updated weights for policy 0, policy_version 51782 (0.0007) -[2023-10-09 02:09:34,516][88326] Updated weights for policy 0, policy_version 51792 (0.0008) -[2023-10-09 02:09:34,890][88326] Updated weights for policy 0, policy_version 51802 (0.0008) -[2023-10-09 02:09:37,207][88327] Updated weights for policy 1, policy_version 51810 (0.0007) -[2023-10-09 02:09:37,579][88327] Updated weights for policy 1, policy_version 51820 (0.0009) -[2023-10-09 02:09:37,946][88327] Updated weights for policy 1, policy_version 51830 (0.0010) -[2023-10-09 02:09:38,309][88327] Updated weights for policy 1, policy_version 51840 (0.0008) -[2023-10-09 02:09:38,820][88326] Updated weights for policy 0, policy_version 51812 (0.0009) -[2023-10-09 02:09:38,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 106135552. Throughput: 0: 1702.9, 1: 1715.5. Samples: 26537486. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:09:38,974][87372] Avg episode reward: [(0, '6.240'), (1, '6.660')] -[2023-10-09 02:09:39,183][88326] Updated weights for policy 0, policy_version 51822 (0.0009) -[2023-10-09 02:09:39,558][88326] Updated weights for policy 0, policy_version 51832 (0.0008) -[2023-10-09 02:09:42,337][88327] Updated weights for policy 1, policy_version 51850 (0.0008) -[2023-10-09 02:09:42,702][88327] Updated weights for policy 1, policy_version 51860 (0.0008) -[2023-10-09 02:09:43,074][88327] Updated weights for policy 1, policy_version 51870 (0.0007) -[2023-10-09 02:09:43,486][88326] Updated weights for policy 0, policy_version 51842 (0.0008) -[2023-10-09 02:09:43,846][88326] Updated weights for policy 0, policy_version 51852 (0.0008) -[2023-10-09 02:09:43,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 106201088. Throughput: 0: 1719.8, 1: 1714.2. Samples: 26558460. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:09:43,975][87372] Avg episode reward: [(0, '6.450'), (1, '6.210')] -[2023-10-09 02:09:44,215][88326] Updated weights for policy 0, policy_version 51862 (0.0007) -[2023-10-09 02:09:44,589][88326] Updated weights for policy 0, policy_version 51872 (0.0007) -[2023-10-09 02:09:47,073][88327] Updated weights for policy 1, policy_version 51880 (0.0010) -[2023-10-09 02:09:47,431][88327] Updated weights for policy 1, policy_version 51890 (0.0009) -[2023-10-09 02:09:47,794][88327] Updated weights for policy 1, policy_version 51900 (0.0010) -[2023-10-09 02:09:48,607][88326] Updated weights for policy 0, policy_version 51882 (0.0008) -[2023-10-09 02:09:48,971][88326] Updated weights for policy 0, policy_version 51892 (0.0008) -[2023-10-09 02:09:48,975][87372] Fps is (10 sec: 13106.6, 60 sec: 13653.2, 300 sec: 13551.5). Total num frames: 106266624. Throughput: 0: 1716.9, 1: 1688.7. Samples: 26578478. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:09:48,976][87372] Avg episode reward: [(0, '6.340'), (1, '6.720')] -[2023-10-09 02:09:49,336][88326] Updated weights for policy 0, policy_version 51902 (0.0009) -[2023-10-09 02:09:51,814][88327] Updated weights for policy 1, policy_version 51910 (0.0008) -[2023-10-09 02:09:52,193][88327] Updated weights for policy 1, policy_version 51920 (0.0008) -[2023-10-09 02:09:52,560][88327] Updated weights for policy 1, policy_version 51930 (0.0007) -[2023-10-09 02:09:53,117][88326] Updated weights for policy 0, policy_version 51912 (0.0008) -[2023-10-09 02:09:53,493][88326] Updated weights for policy 0, policy_version 51922 (0.0010) -[2023-10-09 02:09:53,868][88326] Updated weights for policy 0, policy_version 51932 (0.0008) -[2023-10-09 02:09:53,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 106332160. Throughput: 0: 1717.8, 1: 1719.3. Samples: 26589182. Policy #0 lag: (min: 6.0, avg: 11.1, max: 38.0) -[2023-10-09 02:09:53,975][87372] Avg episode reward: [(0, '6.390'), (1, '5.900')] -[2023-10-09 02:09:56,585][88327] Updated weights for policy 1, policy_version 51940 (0.0007) -[2023-10-09 02:09:56,944][88327] Updated weights for policy 1, policy_version 51950 (0.0010) -[2023-10-09 02:09:57,304][88327] Updated weights for policy 1, policy_version 51960 (0.0007) -[2023-10-09 02:09:57,983][88326] Updated weights for policy 0, policy_version 51942 (0.0008) -[2023-10-09 02:09:58,357][88326] Updated weights for policy 0, policy_version 51952 (0.0008) -[2023-10-09 02:09:58,721][88326] Updated weights for policy 0, policy_version 51962 (0.0008) -[2023-10-09 02:09:58,974][87372] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 106430464. Throughput: 0: 1715.8, 1: 1702.8. Samples: 26609386. Policy #0 lag: (min: 6.0, avg: 11.1, max: 38.0) -[2023-10-09 02:09:58,975][87372] Avg episode reward: [(0, '6.060'), (1, '6.230')] -[2023-10-09 02:10:01,331][88327] Updated weights for policy 1, policy_version 51970 (0.0007) -[2023-10-09 02:10:01,694][88327] Updated weights for policy 1, policy_version 51980 (0.0008) -[2023-10-09 02:10:02,058][88327] Updated weights for policy 1, policy_version 51990 (0.0008) -[2023-10-09 02:10:02,421][88327] Updated weights for policy 1, policy_version 52000 (0.0009) -[2023-10-09 02:10:02,772][88326] Updated weights for policy 0, policy_version 51972 (0.0008) -[2023-10-09 02:10:03,135][88326] Updated weights for policy 0, policy_version 51982 (0.0007) -[2023-10-09 02:10:03,495][88326] Updated weights for policy 0, policy_version 51992 (0.0009) -[2023-10-09 02:10:03,975][87372] Fps is (10 sec: 16383.2, 60 sec: 14199.3, 300 sec: 13551.5). Total num frames: 106496000. Throughput: 0: 1704.6, 1: 1688.4. Samples: 26629160. Policy #0 lag: (min: 6.0, avg: 11.1, max: 38.0) -[2023-10-09 02:10:03,976][87372] Avg episode reward: [(0, '5.650'), (1, '6.660')] -[2023-10-09 02:10:06,598][88327] Updated weights for policy 1, policy_version 52010 (0.0010) -[2023-10-09 02:10:06,966][88327] Updated weights for policy 1, policy_version 52020 (0.0008) -[2023-10-09 02:10:07,329][88327] Updated weights for policy 1, policy_version 52030 (0.0008) -[2023-10-09 02:10:07,482][88326] Updated weights for policy 0, policy_version 52002 (0.0009) -[2023-10-09 02:10:07,853][88326] Updated weights for policy 0, policy_version 52012 (0.0009) -[2023-10-09 02:10:08,229][88326] Updated weights for policy 0, policy_version 52022 (0.0007) -[2023-10-09 02:10:08,605][88326] Updated weights for policy 0, policy_version 52032 (0.0007) -[2023-10-09 02:10:08,974][87372] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 106561536. Throughput: 0: 1716.8, 1: 1707.1. Samples: 26640200. Policy #0 lag: (min: 6.0, avg: 11.1, max: 38.0) -[2023-10-09 02:10:08,974][87372] Avg episode reward: [(0, '5.830'), (1, '6.650')] -[2023-10-09 02:10:11,527][88327] Updated weights for policy 1, policy_version 52040 (0.0010) -[2023-10-09 02:10:11,900][88327] Updated weights for policy 1, policy_version 52050 (0.0007) -[2023-10-09 02:10:12,266][88327] Updated weights for policy 1, policy_version 52060 (0.0008) -[2023-10-09 02:10:12,664][88326] Updated weights for policy 0, policy_version 52042 (0.0011) -[2023-10-09 02:10:13,043][88326] Updated weights for policy 0, policy_version 52052 (0.0009) -[2023-10-09 02:10:13,407][88326] Updated weights for policy 0, policy_version 52062 (0.0010) -[2023-10-09 02:10:13,974][87372] Fps is (10 sec: 13107.8, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 106627072. Throughput: 0: 1712.4, 1: 1680.3. Samples: 26659836. Policy #0 lag: (min: 6.0, avg: 11.1, max: 38.0) -[2023-10-09 02:10:13,975][87372] Avg episode reward: [(0, '5.470'), (1, '7.360')] -[2023-10-09 02:10:13,975][88168] Saving new best policy, reward=7.360! -[2023-10-09 02:10:16,264][88327] Updated weights for policy 1, policy_version 52070 (0.0008) -[2023-10-09 02:10:16,632][88327] Updated weights for policy 1, policy_version 52080 (0.0009) -[2023-10-09 02:10:16,999][88327] Updated weights for policy 1, policy_version 52090 (0.0009) -[2023-10-09 02:10:17,583][88326] Updated weights for policy 0, policy_version 52072 (0.0010) -[2023-10-09 02:10:17,967][88326] Updated weights for policy 0, policy_version 52082 (0.0008) -[2023-10-09 02:10:18,339][88326] Updated weights for policy 0, policy_version 52092 (0.0008) -[2023-10-09 02:10:18,974][87372] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 106692608. Throughput: 0: 1687.8, 1: 1688.8. Samples: 26679478. Policy #0 lag: (min: 6.0, avg: 11.1, max: 38.0) -[2023-10-09 02:10:18,975][87372] Avg episode reward: [(0, '5.970'), (1, '6.590')] -[2023-10-09 02:10:21,055][88327] Updated weights for policy 1, policy_version 52100 (0.0009) -[2023-10-09 02:10:21,418][88327] Updated weights for policy 1, policy_version 52110 (0.0010) -[2023-10-09 02:10:21,783][88327] Updated weights for policy 1, policy_version 52120 (0.0009) -[2023-10-09 02:10:22,356][88326] Updated weights for policy 0, policy_version 52102 (0.0008) -[2023-10-09 02:10:22,710][88326] Updated weights for policy 0, policy_version 52112 (0.0009) -[2023-10-09 02:10:23,085][88326] Updated weights for policy 0, policy_version 52122 (0.0008) -[2023-10-09 02:10:23,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 106758144. Throughput: 0: 1709.5, 1: 1692.4. Samples: 26690574. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-09 02:10:23,974][87372] Avg episode reward: [(0, '6.610'), (1, '6.660')] -[2023-10-09 02:10:25,704][88327] Updated weights for policy 1, policy_version 52130 (0.0009) -[2023-10-09 02:10:26,077][88327] Updated weights for policy 1, policy_version 52140 (0.0008) -[2023-10-09 02:10:26,433][88327] Updated weights for policy 1, policy_version 52150 (0.0007) -[2023-10-09 02:10:26,794][88327] Updated weights for policy 1, policy_version 52160 (0.0007) -[2023-10-09 02:10:27,102][88326] Updated weights for policy 0, policy_version 52132 (0.0009) -[2023-10-09 02:10:27,468][88326] Updated weights for policy 0, policy_version 52142 (0.0011) -[2023-10-09 02:10:27,831][88326] Updated weights for policy 0, policy_version 52152 (0.0009) -[2023-10-09 02:10:28,974][87372] Fps is (10 sec: 13107.6, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 106823680. Throughput: 0: 1699.0, 1: 1675.4. Samples: 26710308. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-09 02:10:28,974][87372] Avg episode reward: [(0, '7.020'), (1, '6.360')] -[2023-10-09 02:10:30,770][88327] Updated weights for policy 1, policy_version 52170 (0.0008) -[2023-10-09 02:10:31,134][88327] Updated weights for policy 1, policy_version 52180 (0.0008) -[2023-10-09 02:10:31,505][88327] Updated weights for policy 1, policy_version 52190 (0.0008) -[2023-10-09 02:10:31,706][88326] Updated weights for policy 0, policy_version 52162 (0.0009) -[2023-10-09 02:10:32,073][88326] Updated weights for policy 0, policy_version 52172 (0.0008) -[2023-10-09 02:10:32,431][88326] Updated weights for policy 0, policy_version 52182 (0.0007) -[2023-10-09 02:10:32,797][88326] Updated weights for policy 0, policy_version 52192 (0.0008) -[2023-10-09 02:10:33,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 106889216. Throughput: 0: 1673.3, 1: 1700.0. Samples: 26730274. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-09 02:10:33,975][87372] Avg episode reward: [(0, '6.900'), (1, '5.920')] -[2023-10-09 02:10:33,984][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000052192_53444608.pth... -[2023-10-09 02:10:33,984][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000052192_53444608.pth... -[2023-10-09 02:10:34,021][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000050624_51838976.pth -[2023-10-09 02:10:34,026][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000050592_51806208.pth -[2023-10-09 02:10:35,612][88327] Updated weights for policy 1, policy_version 52200 (0.0009) -[2023-10-09 02:10:35,978][88327] Updated weights for policy 1, policy_version 52210 (0.0007) -[2023-10-09 02:10:36,343][88327] Updated weights for policy 1, policy_version 52220 (0.0008) -[2023-10-09 02:10:36,813][88326] Updated weights for policy 0, policy_version 52202 (0.0007) -[2023-10-09 02:10:37,174][88326] Updated weights for policy 0, policy_version 52212 (0.0008) -[2023-10-09 02:10:37,553][88326] Updated weights for policy 0, policy_version 52222 (0.0008) -[2023-10-09 02:10:38,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 106954752. Throughput: 0: 1702.0, 1: 1675.1. Samples: 26741150. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-09 02:10:38,975][87372] Avg episode reward: [(0, '6.510'), (1, '6.080')] -[2023-10-09 02:10:40,365][88327] Updated weights for policy 1, policy_version 52230 (0.0009) -[2023-10-09 02:10:40,729][88327] Updated weights for policy 1, policy_version 52240 (0.0010) -[2023-10-09 02:10:41,094][88327] Updated weights for policy 1, policy_version 52250 (0.0008) -[2023-10-09 02:10:41,540][88326] Updated weights for policy 0, policy_version 52232 (0.0007) -[2023-10-09 02:10:41,896][88326] Updated weights for policy 0, policy_version 52242 (0.0007) -[2023-10-09 02:10:42,271][88326] Updated weights for policy 0, policy_version 52252 (0.0008) -[2023-10-09 02:10:43,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 107020288. Throughput: 0: 1681.5, 1: 1685.7. Samples: 26760910. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-09 02:10:43,974][87372] Avg episode reward: [(0, '6.260'), (1, '6.000')] -[2023-10-09 02:10:45,055][88327] Updated weights for policy 1, policy_version 52260 (0.0009) -[2023-10-09 02:10:45,429][88327] Updated weights for policy 1, policy_version 52270 (0.0010) -[2023-10-09 02:10:45,788][88327] Updated weights for policy 1, policy_version 52280 (0.0010) -[2023-10-09 02:10:46,326][88326] Updated weights for policy 0, policy_version 52262 (0.0009) -[2023-10-09 02:10:46,696][88326] Updated weights for policy 0, policy_version 52272 (0.0009) -[2023-10-09 02:10:47,054][88326] Updated weights for policy 0, policy_version 52282 (0.0008) -[2023-10-09 02:10:48,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 107085824. Throughput: 0: 1682.4, 1: 1698.8. Samples: 26781310. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-09 02:10:48,975][87372] Avg episode reward: [(0, '6.080'), (1, '6.190')] -[2023-10-09 02:10:49,777][88327] Updated weights for policy 1, policy_version 52290 (0.0007) -[2023-10-09 02:10:50,143][88327] Updated weights for policy 1, policy_version 52300 (0.0008) -[2023-10-09 02:10:50,509][88327] Updated weights for policy 1, policy_version 52310 (0.0008) -[2023-10-09 02:10:50,876][88327] Updated weights for policy 1, policy_version 52320 (0.0009) -[2023-10-09 02:10:51,348][88326] Updated weights for policy 0, policy_version 52292 (0.0008) -[2023-10-09 02:10:51,721][88326] Updated weights for policy 0, policy_version 52302 (0.0009) -[2023-10-09 02:10:52,086][88326] Updated weights for policy 0, policy_version 52312 (0.0010) -[2023-10-09 02:10:53,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 107151360. Throughput: 0: 1694.1, 1: 1669.3. Samples: 26791554. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-09 02:10:53,975][87372] Avg episode reward: [(0, '6.420'), (1, '6.350')] -[2023-10-09 02:10:54,935][88327] Updated weights for policy 1, policy_version 52330 (0.0008) -[2023-10-09 02:10:55,301][88327] Updated weights for policy 1, policy_version 52340 (0.0008) -[2023-10-09 02:10:55,663][88327] Updated weights for policy 1, policy_version 52350 (0.0009) -[2023-10-09 02:10:55,892][88326] Updated weights for policy 0, policy_version 52322 (0.0010) -[2023-10-09 02:10:56,261][88326] Updated weights for policy 0, policy_version 52332 (0.0007) -[2023-10-09 02:10:56,630][88326] Updated weights for policy 0, policy_version 52342 (0.0008) -[2023-10-09 02:10:56,999][88326] Updated weights for policy 0, policy_version 52352 (0.0010) -[2023-10-09 02:10:58,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 107216896. Throughput: 0: 1665.2, 1: 1698.0. Samples: 26811182. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:10:58,975][87372] Avg episode reward: [(0, '6.160'), (1, '6.320')] -[2023-10-09 02:10:59,749][88327] Updated weights for policy 1, policy_version 52360 (0.0010) -[2023-10-09 02:11:00,109][88327] Updated weights for policy 1, policy_version 52370 (0.0007) -[2023-10-09 02:11:00,472][88327] Updated weights for policy 1, policy_version 52380 (0.0009) -[2023-10-09 02:11:01,060][88326] Updated weights for policy 0, policy_version 52362 (0.0010) -[2023-10-09 02:11:01,427][88326] Updated weights for policy 0, policy_version 52372 (0.0008) -[2023-10-09 02:11:01,784][88326] Updated weights for policy 0, policy_version 52382 (0.0009) -[2023-10-09 02:11:03,974][87372] Fps is (10 sec: 13106.8, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 107282432. Throughput: 0: 1684.6, 1: 1706.0. Samples: 26832054. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:11:03,976][87372] Avg episode reward: [(0, '5.880'), (1, '6.310')] -[2023-10-09 02:11:04,337][88327] Updated weights for policy 1, policy_version 52390 (0.0010) -[2023-10-09 02:11:04,705][88327] Updated weights for policy 1, policy_version 52400 (0.0011) -[2023-10-09 02:11:05,058][88327] Updated weights for policy 1, policy_version 52410 (0.0009) -[2023-10-09 02:11:06,013][88326] Updated weights for policy 0, policy_version 52392 (0.0009) -[2023-10-09 02:11:06,378][88326] Updated weights for policy 0, policy_version 52402 (0.0008) -[2023-10-09 02:11:06,751][88326] Updated weights for policy 0, policy_version 52412 (0.0007) -[2023-10-09 02:11:08,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 107347968. Throughput: 0: 1680.0, 1: 1683.6. Samples: 26841936. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:11:08,974][87372] Avg episode reward: [(0, '5.750'), (1, '6.690')] -[2023-10-09 02:11:09,031][88327] Updated weights for policy 1, policy_version 52420 (0.0011) -[2023-10-09 02:11:09,398][88327] Updated weights for policy 1, policy_version 52430 (0.0007) -[2023-10-09 02:11:09,766][88327] Updated weights for policy 1, policy_version 52440 (0.0007) -[2023-10-09 02:11:10,719][88326] Updated weights for policy 0, policy_version 52422 (0.0007) -[2023-10-09 02:11:11,086][88326] Updated weights for policy 0, policy_version 52432 (0.0008) -[2023-10-09 02:11:11,462][88326] Updated weights for policy 0, policy_version 52442 (0.0008) -[2023-10-09 02:11:13,643][88327] Updated weights for policy 1, policy_version 52450 (0.0009) -[2023-10-09 02:11:13,974][87372] Fps is (10 sec: 13107.8, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 107413504. Throughput: 0: 1664.5, 1: 1706.8. Samples: 26862016. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:11:13,975][87372] Avg episode reward: [(0, '6.380'), (1, '7.220')] -[2023-10-09 02:11:14,013][88327] Updated weights for policy 1, policy_version 52460 (0.0008) -[2023-10-09 02:11:14,377][88327] Updated weights for policy 1, policy_version 52470 (0.0009) -[2023-10-09 02:11:14,738][88327] Updated weights for policy 1, policy_version 52480 (0.0010) -[2023-10-09 02:11:15,379][88326] Updated weights for policy 0, policy_version 52452 (0.0008) -[2023-10-09 02:11:15,751][88326] Updated weights for policy 0, policy_version 52462 (0.0007) -[2023-10-09 02:11:16,118][88326] Updated weights for policy 0, policy_version 52472 (0.0007) -[2023-10-09 02:11:18,847][88327] Updated weights for policy 1, policy_version 52490 (0.0007) -[2023-10-09 02:11:18,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 107479040. Throughput: 0: 1690.8, 1: 1705.2. Samples: 26883094. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:11:18,975][87372] Avg episode reward: [(0, '6.250'), (1, '6.890')] -[2023-10-09 02:11:19,212][88327] Updated weights for policy 1, policy_version 52500 (0.0011) -[2023-10-09 02:11:19,578][88327] Updated weights for policy 1, policy_version 52510 (0.0009) -[2023-10-09 02:11:20,381][88326] Updated weights for policy 0, policy_version 52482 (0.0008) -[2023-10-09 02:11:20,764][88326] Updated weights for policy 0, policy_version 52492 (0.0007) -[2023-10-09 02:11:21,127][88326] Updated weights for policy 0, policy_version 52502 (0.0007) -[2023-10-09 02:11:21,498][88326] Updated weights for policy 0, policy_version 52512 (0.0009) -[2023-10-09 02:11:23,541][88327] Updated weights for policy 1, policy_version 52520 (0.0009) -[2023-10-09 02:11:23,902][88327] Updated weights for policy 1, policy_version 52530 (0.0007) -[2023-10-09 02:11:23,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 107544576. Throughput: 0: 1667.9, 1: 1697.7. Samples: 26892604. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:11:23,975][87372] Avg episode reward: [(0, '6.760'), (1, '6.930')] -[2023-10-09 02:11:24,264][88327] Updated weights for policy 1, policy_version 52540 (0.0009) -[2023-10-09 02:11:25,544][88326] Updated weights for policy 0, policy_version 52522 (0.0009) -[2023-10-09 02:11:25,904][88326] Updated weights for policy 0, policy_version 52532 (0.0008) -[2023-10-09 02:11:26,281][88326] Updated weights for policy 0, policy_version 52542 (0.0009) -[2023-10-09 02:11:28,217][88327] Updated weights for policy 1, policy_version 52550 (0.0007) -[2023-10-09 02:11:28,582][88327] Updated weights for policy 1, policy_version 52560 (0.0010) -[2023-10-09 02:11:28,942][88327] Updated weights for policy 1, policy_version 52570 (0.0009) -[2023-10-09 02:11:28,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 107610112. Throughput: 0: 1681.6, 1: 1708.8. Samples: 26913480. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:11:28,975][87372] Avg episode reward: [(0, '6.380'), (1, '6.170')] -[2023-10-09 02:11:30,497][88326] Updated weights for policy 0, policy_version 52552 (0.0008) -[2023-10-09 02:11:30,855][88326] Updated weights for policy 0, policy_version 52562 (0.0009) -[2023-10-09 02:11:31,231][88326] Updated weights for policy 0, policy_version 52572 (0.0009) -[2023-10-09 02:11:32,989][88327] Updated weights for policy 1, policy_version 52580 (0.0010) -[2023-10-09 02:11:33,356][88327] Updated weights for policy 1, policy_version 52590 (0.0009) -[2023-10-09 02:11:33,733][88327] Updated weights for policy 1, policy_version 52600 (0.0009) -[2023-10-09 02:11:33,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 107675648. Throughput: 0: 1685.9, 1: 1707.1. Samples: 26933994. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:11:33,975][87372] Avg episode reward: [(0, '6.360'), (1, '5.910')] -[2023-10-09 02:11:35,299][88326] Updated weights for policy 0, policy_version 52582 (0.0010) -[2023-10-09 02:11:35,667][88326] Updated weights for policy 0, policy_version 52592 (0.0009) -[2023-10-09 02:11:36,031][88326] Updated weights for policy 0, policy_version 52602 (0.0007) -[2023-10-09 02:11:37,647][88327] Updated weights for policy 1, policy_version 52610 (0.0008) -[2023-10-09 02:11:38,010][88327] Updated weights for policy 1, policy_version 52620 (0.0008) -[2023-10-09 02:11:38,386][88327] Updated weights for policy 1, policy_version 52630 (0.0008) -[2023-10-09 02:11:38,749][88327] Updated weights for policy 1, policy_version 52640 (0.0008) -[2023-10-09 02:11:38,974][87372] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 107773952. Throughput: 0: 1660.8, 1: 1717.4. Samples: 26943574. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:11:38,975][87372] Avg episode reward: [(0, '6.670'), (1, '5.600')] -[2023-10-09 02:11:40,091][88326] Updated weights for policy 0, policy_version 52612 (0.0008) -[2023-10-09 02:11:40,458][88326] Updated weights for policy 0, policy_version 52622 (0.0007) -[2023-10-09 02:11:40,825][88326] Updated weights for policy 0, policy_version 52632 (0.0008) -[2023-10-09 02:11:42,807][88327] Updated weights for policy 1, policy_version 52650 (0.0007) -[2023-10-09 02:11:43,175][88327] Updated weights for policy 1, policy_version 52660 (0.0009) -[2023-10-09 02:11:43,534][88327] Updated weights for policy 1, policy_version 52670 (0.0009) -[2023-10-09 02:11:43,974][87372] Fps is (10 sec: 16384.6, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 107839488. Throughput: 0: 1686.7, 1: 1719.7. Samples: 26964472. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:11:43,974][87372] Avg episode reward: [(0, '6.570'), (1, '6.390')] -[2023-10-09 02:11:44,759][88326] Updated weights for policy 0, policy_version 52642 (0.0009) -[2023-10-09 02:11:45,127][88326] Updated weights for policy 0, policy_version 52652 (0.0008) -[2023-10-09 02:11:45,493][88326] Updated weights for policy 0, policy_version 52662 (0.0009) -[2023-10-09 02:11:45,861][88326] Updated weights for policy 0, policy_version 52672 (0.0010) -[2023-10-09 02:11:47,588][88327] Updated weights for policy 1, policy_version 52680 (0.0007) -[2023-10-09 02:11:47,953][88327] Updated weights for policy 1, policy_version 52690 (0.0007) -[2023-10-09 02:11:48,319][88327] Updated weights for policy 1, policy_version 52700 (0.0008) -[2023-10-09 02:11:48,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 107905024. Throughput: 0: 1696.7, 1: 1696.1. Samples: 26984730. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:11:48,975][87372] Avg episode reward: [(0, '6.760'), (1, '6.090')] -[2023-10-09 02:11:49,874][88326] Updated weights for policy 0, policy_version 52682 (0.0009) -[2023-10-09 02:11:50,245][88326] Updated weights for policy 0, policy_version 52692 (0.0009) -[2023-10-09 02:11:50,602][88326] Updated weights for policy 0, policy_version 52702 (0.0009) -[2023-10-09 02:11:52,343][88327] Updated weights for policy 1, policy_version 52710 (0.0008) -[2023-10-09 02:11:52,710][88327] Updated weights for policy 1, policy_version 52720 (0.0009) -[2023-10-09 02:11:53,077][88327] Updated weights for policy 1, policy_version 52730 (0.0010) -[2023-10-09 02:11:53,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 107970560. Throughput: 0: 1680.1, 1: 1720.0. Samples: 26994940. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:11:53,974][87372] Avg episode reward: [(0, '6.590'), (1, '6.050')] -[2023-10-09 02:11:54,734][88326] Updated weights for policy 0, policy_version 52712 (0.0008) -[2023-10-09 02:11:55,117][88326] Updated weights for policy 0, policy_version 52722 (0.0007) -[2023-10-09 02:11:55,473][88326] Updated weights for policy 0, policy_version 52732 (0.0008) -[2023-10-09 02:11:57,113][88327] Updated weights for policy 1, policy_version 52740 (0.0010) -[2023-10-09 02:11:57,474][88327] Updated weights for policy 1, policy_version 52750 (0.0009) -[2023-10-09 02:11:57,840][88327] Updated weights for policy 1, policy_version 52760 (0.0010) -[2023-10-09 02:11:58,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 108036096. Throughput: 0: 1698.6, 1: 1711.2. Samples: 27015456. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:11:58,975][87372] Avg episode reward: [(0, '6.120'), (1, '6.870')] -[2023-10-09 02:11:59,425][88326] Updated weights for policy 0, policy_version 52742 (0.0010) -[2023-10-09 02:11:59,794][88326] Updated weights for policy 0, policy_version 52752 (0.0007) -[2023-10-09 02:12:00,157][88326] Updated weights for policy 0, policy_version 52762 (0.0009) -[2023-10-09 02:12:01,980][88327] Updated weights for policy 1, policy_version 52770 (0.0010) -[2023-10-09 02:12:02,351][88327] Updated weights for policy 1, policy_version 52780 (0.0007) -[2023-10-09 02:12:02,716][88327] Updated weights for policy 1, policy_version 52790 (0.0007) -[2023-10-09 02:12:03,087][88327] Updated weights for policy 1, policy_version 52800 (0.0007) -[2023-10-09 02:12:03,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 108101632. Throughput: 0: 1696.2, 1: 1683.0. Samples: 27035156. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:12:03,975][87372] Avg episode reward: [(0, '6.380'), (1, '6.290')] -[2023-10-09 02:12:04,177][88326] Updated weights for policy 0, policy_version 52772 (0.0007) -[2023-10-09 02:12:04,555][88326] Updated weights for policy 0, policy_version 52782 (0.0007) -[2023-10-09 02:12:04,918][88326] Updated weights for policy 0, policy_version 52792 (0.0009) -[2023-10-09 02:12:07,105][88327] Updated weights for policy 1, policy_version 52810 (0.0009) -[2023-10-09 02:12:07,479][88327] Updated weights for policy 1, policy_version 52820 (0.0008) -[2023-10-09 02:12:07,842][88327] Updated weights for policy 1, policy_version 52830 (0.0008) -[2023-10-09 02:12:08,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 108167168. Throughput: 0: 1687.1, 1: 1711.0. Samples: 27045518. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-09 02:12:08,975][87372] Avg episode reward: [(0, '6.570'), (1, '6.280')] -[2023-10-09 02:12:09,008][88326] Updated weights for policy 0, policy_version 52802 (0.0008) -[2023-10-09 02:12:09,370][88326] Updated weights for policy 0, policy_version 52812 (0.0010) -[2023-10-09 02:12:09,740][88326] Updated weights for policy 0, policy_version 52822 (0.0011) -[2023-10-09 02:12:10,100][88326] Updated weights for policy 0, policy_version 52832 (0.0007) -[2023-10-09 02:12:11,874][88327] Updated weights for policy 1, policy_version 52840 (0.0008) -[2023-10-09 02:12:12,246][88327] Updated weights for policy 1, policy_version 52850 (0.0008) -[2023-10-09 02:12:12,603][88327] Updated weights for policy 1, policy_version 52860 (0.0007) -[2023-10-09 02:12:13,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 108232704. Throughput: 0: 1691.0, 1: 1696.3. Samples: 27065908. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-09 02:12:13,975][87372] Avg episode reward: [(0, '6.540'), (1, '6.590')] -[2023-10-09 02:12:14,129][88326] Updated weights for policy 0, policy_version 52842 (0.0007) -[2023-10-09 02:12:14,487][88326] Updated weights for policy 0, policy_version 52852 (0.0007) -[2023-10-09 02:12:14,857][88326] Updated weights for policy 0, policy_version 52862 (0.0008) -[2023-10-09 02:12:16,711][88327] Updated weights for policy 1, policy_version 52870 (0.0007) -[2023-10-09 02:12:17,084][88327] Updated weights for policy 1, policy_version 52880 (0.0009) -[2023-10-09 02:12:17,451][88327] Updated weights for policy 1, policy_version 52890 (0.0007) -[2023-10-09 02:12:18,809][88326] Updated weights for policy 0, policy_version 52872 (0.0007) -[2023-10-09 02:12:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 108298240. Throughput: 0: 1702.4, 1: 1678.1. Samples: 27086116. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-09 02:12:18,975][87372] Avg episode reward: [(0, '6.760'), (1, '6.330')] -[2023-10-09 02:12:19,169][88326] Updated weights for policy 0, policy_version 52882 (0.0009) -[2023-10-09 02:12:19,540][88326] Updated weights for policy 0, policy_version 52892 (0.0009) -[2023-10-09 02:12:21,437][88327] Updated weights for policy 1, policy_version 52900 (0.0009) -[2023-10-09 02:12:21,800][88327] Updated weights for policy 1, policy_version 52910 (0.0008) -[2023-10-09 02:12:22,170][88327] Updated weights for policy 1, policy_version 52920 (0.0007) -[2023-10-09 02:12:23,676][88326] Updated weights for policy 0, policy_version 52902 (0.0009) -[2023-10-09 02:12:23,974][87372] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 108363776. Throughput: 0: 1699.6, 1: 1700.8. Samples: 27096594. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-09 02:12:23,975][87372] Avg episode reward: [(0, '6.230'), (1, '6.700')] -[2023-10-09 02:12:24,049][88326] Updated weights for policy 0, policy_version 52912 (0.0008) -[2023-10-09 02:12:24,427][88326] Updated weights for policy 0, policy_version 52922 (0.0009) -[2023-10-09 02:12:26,407][88327] Updated weights for policy 1, policy_version 52930 (0.0007) -[2023-10-09 02:12:26,780][88327] Updated weights for policy 1, policy_version 52940 (0.0007) -[2023-10-09 02:12:27,146][88327] Updated weights for policy 1, policy_version 52950 (0.0007) -[2023-10-09 02:12:27,509][88327] Updated weights for policy 1, policy_version 52960 (0.0009) -[2023-10-09 02:12:28,435][88326] Updated weights for policy 0, policy_version 52932 (0.0009) -[2023-10-09 02:12:28,802][88326] Updated weights for policy 0, policy_version 52942 (0.0008) -[2023-10-09 02:12:28,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 108429312. Throughput: 0: 1705.4, 1: 1675.2. Samples: 27116596. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-09 02:12:28,974][87372] Avg episode reward: [(0, '6.320'), (1, '6.620')] -[2023-10-09 02:12:29,178][88326] Updated weights for policy 0, policy_version 52952 (0.0007) -[2023-10-09 02:12:31,674][88327] Updated weights for policy 1, policy_version 52970 (0.0010) -[2023-10-09 02:12:32,030][88327] Updated weights for policy 1, policy_version 52980 (0.0008) -[2023-10-09 02:12:32,402][88327] Updated weights for policy 1, policy_version 52990 (0.0008) -[2023-10-09 02:12:33,154][88326] Updated weights for policy 0, policy_version 52962 (0.0008) -[2023-10-09 02:12:33,527][88326] Updated weights for policy 0, policy_version 52972 (0.0008) -[2023-10-09 02:12:33,899][88326] Updated weights for policy 0, policy_version 52982 (0.0008) -[2023-10-09 02:12:33,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 108494848. Throughput: 0: 1700.7, 1: 1681.4. Samples: 27136924. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-09 02:12:33,975][87372] Avg episode reward: [(0, '6.670'), (1, '6.320')] -[2023-10-09 02:12:33,986][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000052992_54263808.pth... -[2023-10-09 02:12:34,020][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000051392_52625408.pth -[2023-10-09 02:12:34,261][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000052992_54263808.pth... -[2023-10-09 02:12:34,267][88326] Updated weights for policy 0, policy_version 52992 (0.0008) -[2023-10-09 02:12:34,290][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000051392_52625408.pth -[2023-10-09 02:12:36,410][88327] Updated weights for policy 1, policy_version 53000 (0.0008) -[2023-10-09 02:12:36,789][88327] Updated weights for policy 1, policy_version 53010 (0.0008) -[2023-10-09 02:12:37,153][88327] Updated weights for policy 1, policy_version 53020 (0.0008) -[2023-10-09 02:12:38,281][88326] Updated weights for policy 0, policy_version 53002 (0.0008) -[2023-10-09 02:12:38,649][88326] Updated weights for policy 0, policy_version 53012 (0.0009) -[2023-10-09 02:12:38,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 108560384. Throughput: 0: 1704.9, 1: 1686.9. Samples: 27147572. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-09 02:12:38,975][87372] Avg episode reward: [(0, '7.180'), (1, '6.760')] -[2023-10-09 02:12:39,014][88326] Updated weights for policy 0, policy_version 53022 (0.0008) -[2023-10-09 02:12:41,284][88327] Updated weights for policy 1, policy_version 53030 (0.0009) -[2023-10-09 02:12:41,662][88327] Updated weights for policy 1, policy_version 53040 (0.0009) -[2023-10-09 02:12:42,018][88327] Updated weights for policy 1, policy_version 53050 (0.0008) -[2023-10-09 02:12:43,120][88326] Updated weights for policy 0, policy_version 53032 (0.0007) -[2023-10-09 02:12:43,504][88326] Updated weights for policy 0, policy_version 53042 (0.0008) -[2023-10-09 02:12:43,880][88326] Updated weights for policy 0, policy_version 53052 (0.0010) -[2023-10-09 02:12:43,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 108625920. Throughput: 0: 1712.9, 1: 1672.0. Samples: 27167778. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-09 02:12:43,975][87372] Avg episode reward: [(0, '7.080'), (1, '6.500')] -[2023-10-09 02:12:45,824][88327] Updated weights for policy 1, policy_version 53060 (0.0010) -[2023-10-09 02:12:46,200][88327] Updated weights for policy 1, policy_version 53070 (0.0009) -[2023-10-09 02:12:46,571][88327] Updated weights for policy 1, policy_version 53080 (0.0008) -[2023-10-09 02:12:47,799][88326] Updated weights for policy 0, policy_version 53062 (0.0008) -[2023-10-09 02:12:48,160][88326] Updated weights for policy 0, policy_version 53072 (0.0007) -[2023-10-09 02:12:48,532][88326] Updated weights for policy 0, policy_version 53082 (0.0008) -[2023-10-09 02:12:48,974][87372] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 108724224. Throughput: 0: 1692.5, 1: 1696.3. Samples: 27187652. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-09 02:12:48,975][87372] Avg episode reward: [(0, '6.530'), (1, '6.770')] -[2023-10-09 02:12:50,534][88327] Updated weights for policy 1, policy_version 53090 (0.0008) -[2023-10-09 02:12:50,905][88327] Updated weights for policy 1, policy_version 53100 (0.0008) -[2023-10-09 02:12:51,271][88327] Updated weights for policy 1, policy_version 53110 (0.0009) -[2023-10-09 02:12:51,641][88327] Updated weights for policy 1, policy_version 53120 (0.0008) -[2023-10-09 02:12:52,604][88326] Updated weights for policy 0, policy_version 53092 (0.0008) -[2023-10-09 02:12:52,976][88326] Updated weights for policy 0, policy_version 53102 (0.0011) -[2023-10-09 02:12:53,335][88326] Updated weights for policy 0, policy_version 53112 (0.0011) -[2023-10-09 02:12:53,974][87372] Fps is (10 sec: 16384.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 108789760. Throughput: 0: 1707.0, 1: 1685.3. Samples: 27198170. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-09 02:12:53,975][87372] Avg episode reward: [(0, '6.200'), (1, '7.000')] -[2023-10-09 02:12:55,495][88327] Updated weights for policy 1, policy_version 53130 (0.0009) -[2023-10-09 02:12:55,862][88327] Updated weights for policy 1, policy_version 53140 (0.0010) -[2023-10-09 02:12:56,217][88327] Updated weights for policy 1, policy_version 53150 (0.0007) -[2023-10-09 02:12:57,457][88326] Updated weights for policy 0, policy_version 53122 (0.0010) -[2023-10-09 02:12:57,829][88326] Updated weights for policy 0, policy_version 53132 (0.0008) -[2023-10-09 02:12:58,193][88326] Updated weights for policy 0, policy_version 53142 (0.0008) -[2023-10-09 02:12:58,559][88326] Updated weights for policy 0, policy_version 53152 (0.0008) -[2023-10-09 02:12:58,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 108855296. Throughput: 0: 1704.4, 1: 1689.2. Samples: 27218624. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-09 02:12:58,974][87372] Avg episode reward: [(0, '6.000'), (1, '6.540')] -[2023-10-09 02:13:00,273][88327] Updated weights for policy 1, policy_version 53160 (0.0009) -[2023-10-09 02:13:00,633][88327] Updated weights for policy 1, policy_version 53170 (0.0008) -[2023-10-09 02:13:00,999][88327] Updated weights for policy 1, policy_version 53180 (0.0009) -[2023-10-09 02:13:02,670][88326] Updated weights for policy 0, policy_version 53162 (0.0008) -[2023-10-09 02:13:03,040][88326] Updated weights for policy 0, policy_version 53172 (0.0009) -[2023-10-09 02:13:03,407][88326] Updated weights for policy 0, policy_version 53182 (0.0009) -[2023-10-09 02:13:03,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 108920832. Throughput: 0: 1673.5, 1: 1708.7. Samples: 27238318. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-09 02:13:03,975][87372] Avg episode reward: [(0, '6.170'), (1, '6.480')] -[2023-10-09 02:13:04,898][88327] Updated weights for policy 1, policy_version 53190 (0.0009) -[2023-10-09 02:13:05,261][88327] Updated weights for policy 1, policy_version 53200 (0.0008) -[2023-10-09 02:13:05,627][88327] Updated weights for policy 1, policy_version 53210 (0.0009) -[2023-10-09 02:13:07,296][88326] Updated weights for policy 0, policy_version 53192 (0.0008) -[2023-10-09 02:13:07,663][88326] Updated weights for policy 0, policy_version 53202 (0.0009) -[2023-10-09 02:13:08,023][88326] Updated weights for policy 0, policy_version 53212 (0.0010) -[2023-10-09 02:13:08,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 108986368. Throughput: 0: 1699.5, 1: 1678.6. Samples: 27248608. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-09 02:13:08,975][87372] Avg episode reward: [(0, '6.570'), (1, '6.490')] -[2023-10-09 02:13:09,742][88327] Updated weights for policy 1, policy_version 53220 (0.0008) -[2023-10-09 02:13:10,100][88327] Updated weights for policy 1, policy_version 53230 (0.0008) -[2023-10-09 02:13:10,465][88327] Updated weights for policy 1, policy_version 53240 (0.0007) -[2023-10-09 02:13:12,016][88326] Updated weights for policy 0, policy_version 53222 (0.0009) -[2023-10-09 02:13:12,390][88326] Updated weights for policy 0, policy_version 53232 (0.0009) -[2023-10-09 02:13:12,775][88326] Updated weights for policy 0, policy_version 53242 (0.0008) -[2023-10-09 02:13:13,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 109051904. Throughput: 0: 1691.6, 1: 1700.8. Samples: 27269254. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-09 02:13:13,974][87372] Avg episode reward: [(0, '6.970'), (1, '6.600')] -[2023-10-09 02:13:14,401][88327] Updated weights for policy 1, policy_version 53250 (0.0008) -[2023-10-09 02:13:14,769][88327] Updated weights for policy 1, policy_version 53260 (0.0007) -[2023-10-09 02:13:15,133][88327] Updated weights for policy 1, policy_version 53270 (0.0007) -[2023-10-09 02:13:15,500][88327] Updated weights for policy 1, policy_version 53280 (0.0009) -[2023-10-09 02:13:16,838][88326] Updated weights for policy 0, policy_version 53252 (0.0007) -[2023-10-09 02:13:17,207][88326] Updated weights for policy 0, policy_version 53262 (0.0008) -[2023-10-09 02:13:17,581][88326] Updated weights for policy 0, policy_version 53272 (0.0010) -[2023-10-09 02:13:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 109117440. Throughput: 0: 1675.2, 1: 1718.1. Samples: 27289620. Policy #0 lag: (min: 31.0, avg: 34.2, max: 63.0) -[2023-10-09 02:13:18,975][87372] Avg episode reward: [(0, '6.330'), (1, '6.720')] -[2023-10-09 02:13:19,714][88327] Updated weights for policy 1, policy_version 53290 (0.0009) -[2023-10-09 02:13:20,077][88327] Updated weights for policy 1, policy_version 53300 (0.0008) -[2023-10-09 02:13:20,438][88327] Updated weights for policy 1, policy_version 53310 (0.0010) -[2023-10-09 02:13:21,593][88326] Updated weights for policy 0, policy_version 53282 (0.0007) -[2023-10-09 02:13:21,965][88326] Updated weights for policy 0, policy_version 53292 (0.0010) -[2023-10-09 02:13:22,338][88326] Updated weights for policy 0, policy_version 53302 (0.0010) -[2023-10-09 02:13:22,710][88326] Updated weights for policy 0, policy_version 53312 (0.0008) -[2023-10-09 02:13:23,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 109182976. Throughput: 0: 1703.1, 1: 1682.2. Samples: 27299910. Policy #0 lag: (min: 31.0, avg: 34.2, max: 63.0) -[2023-10-09 02:13:23,975][87372] Avg episode reward: [(0, '6.450'), (1, '6.910')] -[2023-10-09 02:13:24,478][88327] Updated weights for policy 1, policy_version 53320 (0.0009) -[2023-10-09 02:13:24,860][88327] Updated weights for policy 1, policy_version 53330 (0.0010) -[2023-10-09 02:13:25,214][88327] Updated weights for policy 1, policy_version 53340 (0.0011) -[2023-10-09 02:13:26,702][88326] Updated weights for policy 0, policy_version 53322 (0.0009) -[2023-10-09 02:13:27,079][88326] Updated weights for policy 0, policy_version 53332 (0.0008) -[2023-10-09 02:13:27,444][88326] Updated weights for policy 0, policy_version 53342 (0.0007) -[2023-10-09 02:13:28,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 109248512. Throughput: 0: 1675.2, 1: 1702.7. Samples: 27319780. Policy #0 lag: (min: 31.0, avg: 34.2, max: 63.0) -[2023-10-09 02:13:28,975][87372] Avg episode reward: [(0, '6.840'), (1, '6.840')] -[2023-10-09 02:13:29,197][88327] Updated weights for policy 1, policy_version 53350 (0.0008) -[2023-10-09 02:13:29,573][88327] Updated weights for policy 1, policy_version 53360 (0.0009) -[2023-10-09 02:13:29,939][88327] Updated weights for policy 1, policy_version 53370 (0.0008) -[2023-10-09 02:13:31,485][88326] Updated weights for policy 0, policy_version 53352 (0.0009) -[2023-10-09 02:13:31,856][88326] Updated weights for policy 0, policy_version 53362 (0.0009) -[2023-10-09 02:13:32,228][88326] Updated weights for policy 0, policy_version 53372 (0.0007) -[2023-10-09 02:13:33,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 109314048. Throughput: 0: 1684.3, 1: 1704.4. Samples: 27340142. Policy #0 lag: (min: 31.0, avg: 34.2, max: 63.0) -[2023-10-09 02:13:33,975][87372] Avg episode reward: [(0, '6.570'), (1, '6.770')] -[2023-10-09 02:13:34,120][88327] Updated weights for policy 1, policy_version 53380 (0.0010) -[2023-10-09 02:13:34,474][88327] Updated weights for policy 1, policy_version 53390 (0.0008) -[2023-10-09 02:13:34,840][88327] Updated weights for policy 1, policy_version 53400 (0.0008) -[2023-10-09 02:13:36,236][88326] Updated weights for policy 0, policy_version 53382 (0.0007) -[2023-10-09 02:13:36,608][88326] Updated weights for policy 0, policy_version 53392 (0.0007) -[2023-10-09 02:13:36,983][88326] Updated weights for policy 0, policy_version 53402 (0.0008) -[2023-10-09 02:13:38,887][88327] Updated weights for policy 1, policy_version 53410 (0.0011) -[2023-10-09 02:13:38,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 109379584. Throughput: 0: 1693.4, 1: 1686.6. Samples: 27350270. Policy #0 lag: (min: 31.0, avg: 34.2, max: 63.0) -[2023-10-09 02:13:38,975][87372] Avg episode reward: [(0, '6.790'), (1, '6.810')] -[2023-10-09 02:13:39,263][88327] Updated weights for policy 1, policy_version 53420 (0.0008) -[2023-10-09 02:13:39,635][88327] Updated weights for policy 1, policy_version 53430 (0.0009) -[2023-10-09 02:13:39,995][88327] Updated weights for policy 1, policy_version 53440 (0.0009) -[2023-10-09 02:13:40,984][88326] Updated weights for policy 0, policy_version 53412 (0.0007) -[2023-10-09 02:13:41,360][88326] Updated weights for policy 0, policy_version 53422 (0.0009) -[2023-10-09 02:13:41,721][88326] Updated weights for policy 0, policy_version 53432 (0.0010) -[2023-10-09 02:13:43,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 109445120. Throughput: 0: 1672.5, 1: 1692.8. Samples: 27370060. Policy #0 lag: (min: 31.0, avg: 34.2, max: 63.0) -[2023-10-09 02:13:43,975][87372] Avg episode reward: [(0, '6.380'), (1, '6.430')] -[2023-10-09 02:13:43,986][88327] Updated weights for policy 1, policy_version 53450 (0.0008) -[2023-10-09 02:13:44,350][88327] Updated weights for policy 1, policy_version 53460 (0.0008) -[2023-10-09 02:13:44,715][88327] Updated weights for policy 1, policy_version 53470 (0.0009) -[2023-10-09 02:13:45,798][88326] Updated weights for policy 0, policy_version 53442 (0.0008) -[2023-10-09 02:13:46,172][88326] Updated weights for policy 0, policy_version 53452 (0.0008) -[2023-10-09 02:13:46,556][88326] Updated weights for policy 0, policy_version 53462 (0.0009) -[2023-10-09 02:13:46,912][88326] Updated weights for policy 0, policy_version 53472 (0.0009) -[2023-10-09 02:13:48,892][88327] Updated weights for policy 1, policy_version 53480 (0.0008) -[2023-10-09 02:13:48,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 109510656. Throughput: 0: 1697.5, 1: 1694.8. Samples: 27390970. Policy #0 lag: (min: 31.0, avg: 34.2, max: 63.0) -[2023-10-09 02:13:48,974][87372] Avg episode reward: [(0, '5.970'), (1, '6.190')] -[2023-10-09 02:13:49,260][88327] Updated weights for policy 1, policy_version 53490 (0.0008) -[2023-10-09 02:13:49,615][88327] Updated weights for policy 1, policy_version 53500 (0.0007) -[2023-10-09 02:13:50,968][88326] Updated weights for policy 0, policy_version 53482 (0.0008) -[2023-10-09 02:13:51,341][88326] Updated weights for policy 0, policy_version 53492 (0.0010) -[2023-10-09 02:13:51,711][88326] Updated weights for policy 0, policy_version 53502 (0.0010) -[2023-10-09 02:13:53,662][88327] Updated weights for policy 1, policy_version 53510 (0.0007) -[2023-10-09 02:13:53,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 109576192. Throughput: 0: 1688.5, 1: 1691.2. Samples: 27400692. Policy #0 lag: (min: 31.0, avg: 34.2, max: 63.0) -[2023-10-09 02:13:53,975][87372] Avg episode reward: [(0, '6.270'), (1, '6.720')] -[2023-10-09 02:13:54,026][88327] Updated weights for policy 1, policy_version 53520 (0.0008) -[2023-10-09 02:13:54,395][88327] Updated weights for policy 1, policy_version 53530 (0.0010) -[2023-10-09 02:13:55,755][88326] Updated weights for policy 0, policy_version 53512 (0.0009) -[2023-10-09 02:13:56,119][88326] Updated weights for policy 0, policy_version 53522 (0.0008) -[2023-10-09 02:13:56,492][88326] Updated weights for policy 0, policy_version 53532 (0.0007) -[2023-10-09 02:13:58,615][88327] Updated weights for policy 1, policy_version 53540 (0.0009) -[2023-10-09 02:13:58,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 109641728. Throughput: 0: 1682.1, 1: 1691.8. Samples: 27421080. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-10-09 02:13:58,974][87372] Avg episode reward: [(0, '6.640'), (1, '6.380')] -[2023-10-09 02:13:58,984][88327] Updated weights for policy 1, policy_version 53550 (0.0008) -[2023-10-09 02:13:59,352][88327] Updated weights for policy 1, policy_version 53560 (0.0009) -[2023-10-09 02:14:00,486][88326] Updated weights for policy 0, policy_version 53542 (0.0009) -[2023-10-09 02:14:00,850][88326] Updated weights for policy 0, policy_version 53552 (0.0011) -[2023-10-09 02:14:01,220][88326] Updated weights for policy 0, policy_version 53562 (0.0011) -[2023-10-09 02:14:03,208][88327] Updated weights for policy 1, policy_version 53570 (0.0009) -[2023-10-09 02:14:03,569][88327] Updated weights for policy 1, policy_version 53580 (0.0008) -[2023-10-09 02:14:03,930][88327] Updated weights for policy 1, policy_version 53590 (0.0009) -[2023-10-09 02:14:03,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 109707264. Throughput: 0: 1691.8, 1: 1686.5. Samples: 27441644. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-10-09 02:14:03,975][87372] Avg episode reward: [(0, '6.730'), (1, '6.340')] -[2023-10-09 02:14:04,300][88327] Updated weights for policy 1, policy_version 53600 (0.0009) -[2023-10-09 02:14:05,407][88326] Updated weights for policy 0, policy_version 53572 (0.0010) -[2023-10-09 02:14:05,773][88326] Updated weights for policy 0, policy_version 53582 (0.0010) -[2023-10-09 02:14:06,132][88326] Updated weights for policy 0, policy_version 53592 (0.0008) -[2023-10-09 02:14:08,411][88327] Updated weights for policy 1, policy_version 53610 (0.0008) -[2023-10-09 02:14:08,786][88327] Updated weights for policy 1, policy_version 53620 (0.0008) -[2023-10-09 02:14:08,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 109772800. Throughput: 0: 1666.6, 1: 1694.5. Samples: 27451160. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-10-09 02:14:08,975][87372] Avg episode reward: [(0, '6.640'), (1, '6.270')] -[2023-10-09 02:14:09,155][88327] Updated weights for policy 1, policy_version 53630 (0.0009) -[2023-10-09 02:14:10,207][88326] Updated weights for policy 0, policy_version 53602 (0.0010) -[2023-10-09 02:14:10,572][88326] Updated weights for policy 0, policy_version 53612 (0.0007) -[2023-10-09 02:14:10,940][88326] Updated weights for policy 0, policy_version 53622 (0.0009) -[2023-10-09 02:14:11,314][88326] Updated weights for policy 0, policy_version 53632 (0.0009) -[2023-10-09 02:14:13,092][88327] Updated weights for policy 1, policy_version 53640 (0.0007) -[2023-10-09 02:14:13,450][88327] Updated weights for policy 1, policy_version 53650 (0.0007) -[2023-10-09 02:14:13,819][88327] Updated weights for policy 1, policy_version 53660 (0.0008) -[2023-10-09 02:14:13,974][87372] Fps is (10 sec: 16383.7, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 109871104. Throughput: 0: 1682.1, 1: 1690.1. Samples: 27471530. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-10-09 02:14:13,975][87372] Avg episode reward: [(0, '6.490'), (1, '6.730')] -[2023-10-09 02:14:15,347][88326] Updated weights for policy 0, policy_version 53642 (0.0007) -[2023-10-09 02:14:15,717][88326] Updated weights for policy 0, policy_version 53652 (0.0008) -[2023-10-09 02:14:16,086][88326] Updated weights for policy 0, policy_version 53662 (0.0010) -[2023-10-09 02:14:17,838][88327] Updated weights for policy 1, policy_version 53670 (0.0009) -[2023-10-09 02:14:18,197][88327] Updated weights for policy 1, policy_version 53680 (0.0008) -[2023-10-09 02:14:18,572][88327] Updated weights for policy 1, policy_version 53690 (0.0010) -[2023-10-09 02:14:18,974][87372] Fps is (10 sec: 16384.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 109936640. Throughput: 0: 1693.7, 1: 1678.5. Samples: 27491886. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-10-09 02:14:18,975][87372] Avg episode reward: [(0, '6.170'), (1, '6.610')] -[2023-10-09 02:14:20,022][88326] Updated weights for policy 0, policy_version 53672 (0.0011) -[2023-10-09 02:14:20,402][88326] Updated weights for policy 0, policy_version 53682 (0.0010) -[2023-10-09 02:14:20,767][88326] Updated weights for policy 0, policy_version 53692 (0.0007) -[2023-10-09 02:14:22,557][88327] Updated weights for policy 1, policy_version 53700 (0.0009) -[2023-10-09 02:14:22,917][88327] Updated weights for policy 1, policy_version 53710 (0.0010) -[2023-10-09 02:14:23,276][88327] Updated weights for policy 1, policy_version 53720 (0.0011) -[2023-10-09 02:14:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 110002176. Throughput: 0: 1668.6, 1: 1692.3. Samples: 27501508. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-10-09 02:14:23,975][87372] Avg episode reward: [(0, '6.310'), (1, '6.490')] -[2023-10-09 02:14:24,594][88326] Updated weights for policy 0, policy_version 53702 (0.0007) -[2023-10-09 02:14:24,967][88326] Updated weights for policy 0, policy_version 53712 (0.0010) -[2023-10-09 02:14:25,334][88326] Updated weights for policy 0, policy_version 53722 (0.0009) -[2023-10-09 02:14:27,500][88327] Updated weights for policy 1, policy_version 53730 (0.0011) -[2023-10-09 02:14:27,867][88327] Updated weights for policy 1, policy_version 53740 (0.0010) -[2023-10-09 02:14:28,223][88327] Updated weights for policy 1, policy_version 53750 (0.0010) -[2023-10-09 02:14:28,588][88327] Updated weights for policy 1, policy_version 53760 (0.0011) -[2023-10-09 02:14:28,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 110067712. Throughput: 0: 1696.4, 1: 1690.1. Samples: 27522454. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-10-09 02:14:28,975][87372] Avg episode reward: [(0, '6.850'), (1, '6.840')] -[2023-10-09 02:14:29,532][88326] Updated weights for policy 0, policy_version 53732 (0.0010) -[2023-10-09 02:14:29,898][88326] Updated weights for policy 0, policy_version 53742 (0.0009) -[2023-10-09 02:14:30,272][88326] Updated weights for policy 0, policy_version 53752 (0.0011) -[2023-10-09 02:14:32,725][88327] Updated weights for policy 1, policy_version 53770 (0.0007) -[2023-10-09 02:14:33,090][88327] Updated weights for policy 1, policy_version 53780 (0.0007) -[2023-10-09 02:14:33,454][88327] Updated weights for policy 1, policy_version 53790 (0.0008) -[2023-10-09 02:14:33,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 110133248. Throughput: 0: 1698.7, 1: 1666.8. Samples: 27542420. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-10-09 02:14:33,975][87372] Avg episode reward: [(0, '6.370'), (1, '5.880')] -[2023-10-09 02:14:33,988][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000053760_55050240.pth... -[2023-10-09 02:14:33,989][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000053792_55083008.pth... -[2023-10-09 02:14:34,025][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000052192_53444608.pth -[2023-10-09 02:14:34,026][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000052192_53444608.pth -[2023-10-09 02:14:34,440][88326] Updated weights for policy 0, policy_version 53762 (0.0007) -[2023-10-09 02:14:34,799][88326] Updated weights for policy 0, policy_version 53772 (0.0008) -[2023-10-09 02:14:35,173][88326] Updated weights for policy 0, policy_version 53782 (0.0009) -[2023-10-09 02:14:35,537][88326] Updated weights for policy 0, policy_version 53792 (0.0010) -[2023-10-09 02:14:37,584][88327] Updated weights for policy 1, policy_version 53800 (0.0008) -[2023-10-09 02:14:37,942][88327] Updated weights for policy 1, policy_version 53810 (0.0009) -[2023-10-09 02:14:38,306][88327] Updated weights for policy 1, policy_version 53820 (0.0009) -[2023-10-09 02:14:38,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 110198784. Throughput: 0: 1682.8, 1: 1689.2. Samples: 27552430. Policy #0 lag: (min: 31.0, avg: 31.5, max: 46.0) -[2023-10-09 02:14:38,975][87372] Avg episode reward: [(0, '6.330'), (1, '6.080')] -[2023-10-09 02:14:39,579][88326] Updated weights for policy 0, policy_version 53802 (0.0008) -[2023-10-09 02:14:39,948][88326] Updated weights for policy 0, policy_version 53812 (0.0008) -[2023-10-09 02:14:40,323][88326] Updated weights for policy 0, policy_version 53822 (0.0009) -[2023-10-09 02:14:42,334][88327] Updated weights for policy 1, policy_version 53830 (0.0008) -[2023-10-09 02:14:42,696][88327] Updated weights for policy 1, policy_version 53840 (0.0007) -[2023-10-09 02:14:43,057][88327] Updated weights for policy 1, policy_version 53850 (0.0008) -[2023-10-09 02:14:43,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 110264320. Throughput: 0: 1695.9, 1: 1686.1. Samples: 27573268. Policy #0 lag: (min: 31.0, avg: 31.5, max: 46.0) -[2023-10-09 02:14:43,975][87372] Avg episode reward: [(0, '6.670'), (1, '6.520')] -[2023-10-09 02:14:44,358][88326] Updated weights for policy 0, policy_version 53832 (0.0009) -[2023-10-09 02:14:44,725][88326] Updated weights for policy 0, policy_version 53842 (0.0007) -[2023-10-09 02:14:45,098][88326] Updated weights for policy 0, policy_version 53852 (0.0007) -[2023-10-09 02:14:47,057][88327] Updated weights for policy 1, policy_version 53860 (0.0008) -[2023-10-09 02:14:47,424][88327] Updated weights for policy 1, policy_version 53870 (0.0010) -[2023-10-09 02:14:47,788][88327] Updated weights for policy 1, policy_version 53880 (0.0009) -[2023-10-09 02:14:48,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 110329856. Throughput: 0: 1709.1, 1: 1661.7. Samples: 27593334. Policy #0 lag: (min: 31.0, avg: 31.5, max: 46.0) -[2023-10-09 02:14:48,975][87372] Avg episode reward: [(0, '6.370'), (1, '6.310')] -[2023-10-09 02:14:48,997][88326] Updated weights for policy 0, policy_version 53862 (0.0009) -[2023-10-09 02:14:49,367][88326] Updated weights for policy 0, policy_version 53872 (0.0008) -[2023-10-09 02:14:49,740][88326] Updated weights for policy 0, policy_version 53882 (0.0009) -[2023-10-09 02:14:51,851][88327] Updated weights for policy 1, policy_version 53890 (0.0008) -[2023-10-09 02:14:52,210][88327] Updated weights for policy 1, policy_version 53900 (0.0008) -[2023-10-09 02:14:52,571][88327] Updated weights for policy 1, policy_version 53910 (0.0009) -[2023-10-09 02:14:52,941][88327] Updated weights for policy 1, policy_version 53920 (0.0009) -[2023-10-09 02:14:53,719][88326] Updated weights for policy 0, policy_version 53892 (0.0009) -[2023-10-09 02:14:53,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 110395392. Throughput: 0: 1703.4, 1: 1689.6. Samples: 27603844. Policy #0 lag: (min: 31.0, avg: 31.5, max: 46.0) -[2023-10-09 02:14:53,974][87372] Avg episode reward: [(0, '6.250'), (1, '6.410')] -[2023-10-09 02:14:54,090][88326] Updated weights for policy 0, policy_version 53902 (0.0009) -[2023-10-09 02:14:54,463][88326] Updated weights for policy 0, policy_version 53912 (0.0009) -[2023-10-09 02:14:57,077][88327] Updated weights for policy 1, policy_version 53930 (0.0008) -[2023-10-09 02:14:57,452][88327] Updated weights for policy 1, policy_version 53940 (0.0008) -[2023-10-09 02:14:57,813][88327] Updated weights for policy 1, policy_version 53950 (0.0009) -[2023-10-09 02:14:58,432][88326] Updated weights for policy 0, policy_version 53922 (0.0008) -[2023-10-09 02:14:58,794][88326] Updated weights for policy 0, policy_version 53932 (0.0010) -[2023-10-09 02:14:58,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13440.5). Total num frames: 110460928. Throughput: 0: 1715.0, 1: 1679.3. Samples: 27624274. Policy #0 lag: (min: 31.0, avg: 31.5, max: 46.0) -[2023-10-09 02:14:58,975][87372] Avg episode reward: [(0, '6.620'), (1, '6.620')] -[2023-10-09 02:14:59,156][88326] Updated weights for policy 0, policy_version 53942 (0.0011) -[2023-10-09 02:14:59,528][88326] Updated weights for policy 0, policy_version 53952 (0.0008) -[2023-10-09 02:15:01,847][88327] Updated weights for policy 1, policy_version 53960 (0.0010) -[2023-10-09 02:15:02,216][88327] Updated weights for policy 1, policy_version 53970 (0.0010) -[2023-10-09 02:15:02,588][88327] Updated weights for policy 1, policy_version 53980 (0.0008) -[2023-10-09 02:15:03,475][88326] Updated weights for policy 0, policy_version 53962 (0.0007) -[2023-10-09 02:15:03,857][88326] Updated weights for policy 0, policy_version 53972 (0.0009) -[2023-10-09 02:15:03,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 110526464. Throughput: 0: 1709.3, 1: 1670.0. Samples: 27643958. Policy #0 lag: (min: 31.0, avg: 31.5, max: 46.0) -[2023-10-09 02:15:03,975][87372] Avg episode reward: [(0, '6.440'), (1, '6.450')] -[2023-10-09 02:15:04,224][88326] Updated weights for policy 0, policy_version 53982 (0.0009) -[2023-10-09 02:15:06,616][88327] Updated weights for policy 1, policy_version 53990 (0.0008) -[2023-10-09 02:15:06,979][88327] Updated weights for policy 1, policy_version 54000 (0.0008) -[2023-10-09 02:15:07,352][88327] Updated weights for policy 1, policy_version 54010 (0.0009) -[2023-10-09 02:15:08,254][88326] Updated weights for policy 0, policy_version 53992 (0.0008) -[2023-10-09 02:15:08,621][88326] Updated weights for policy 0, policy_version 54002 (0.0009) -[2023-10-09 02:15:08,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 110592000. Throughput: 0: 1712.4, 1: 1688.4. Samples: 27654540. Policy #0 lag: (min: 31.0, avg: 31.5, max: 46.0) -[2023-10-09 02:15:08,974][87372] Avg episode reward: [(0, '6.970'), (1, '6.540')] -[2023-10-09 02:15:08,990][88326] Updated weights for policy 0, policy_version 54012 (0.0009) -[2023-10-09 02:15:11,546][88327] Updated weights for policy 1, policy_version 54020 (0.0008) -[2023-10-09 02:15:11,920][88327] Updated weights for policy 1, policy_version 54030 (0.0012) -[2023-10-09 02:15:12,280][88327] Updated weights for policy 1, policy_version 54040 (0.0008) -[2023-10-09 02:15:12,985][88326] Updated weights for policy 0, policy_version 54022 (0.0007) -[2023-10-09 02:15:13,356][88326] Updated weights for policy 0, policy_version 54032 (0.0007) -[2023-10-09 02:15:13,717][88326] Updated weights for policy 0, policy_version 54042 (0.0008) -[2023-10-09 02:15:13,974][87372] Fps is (10 sec: 16384.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 110690304. Throughput: 0: 1707.6, 1: 1669.6. Samples: 27674424. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:15:13,975][87372] Avg episode reward: [(0, '6.840'), (1, '6.840')] -[2023-10-09 02:15:16,209][88327] Updated weights for policy 1, policy_version 54050 (0.0009) -[2023-10-09 02:15:16,565][88327] Updated weights for policy 1, policy_version 54060 (0.0007) -[2023-10-09 02:15:16,931][88327] Updated weights for policy 1, policy_version 54070 (0.0009) -[2023-10-09 02:15:17,290][88327] Updated weights for policy 1, policy_version 54080 (0.0007) -[2023-10-09 02:15:17,769][88326] Updated weights for policy 0, policy_version 54052 (0.0009) -[2023-10-09 02:15:18,141][88326] Updated weights for policy 0, policy_version 54062 (0.0009) -[2023-10-09 02:15:18,505][88326] Updated weights for policy 0, policy_version 54072 (0.0009) -[2023-10-09 02:15:18,974][87372] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 110755840. Throughput: 0: 1693.6, 1: 1681.1. Samples: 27694280. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:15:18,975][87372] Avg episode reward: [(0, '6.600'), (1, '6.570')] -[2023-10-09 02:15:21,308][88327] Updated weights for policy 1, policy_version 54090 (0.0009) -[2023-10-09 02:15:21,671][88327] Updated weights for policy 1, policy_version 54100 (0.0009) -[2023-10-09 02:15:22,038][88327] Updated weights for policy 1, policy_version 54110 (0.0009) -[2023-10-09 02:15:22,620][88326] Updated weights for policy 0, policy_version 54082 (0.0008) -[2023-10-09 02:15:22,992][88326] Updated weights for policy 0, policy_version 54092 (0.0009) -[2023-10-09 02:15:23,373][88326] Updated weights for policy 0, policy_version 54102 (0.0007) -[2023-10-09 02:15:23,736][88326] Updated weights for policy 0, policy_version 54112 (0.0008) -[2023-10-09 02:15:23,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 110821376. Throughput: 0: 1706.4, 1: 1688.7. Samples: 27705210. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:15:23,975][87372] Avg episode reward: [(0, '6.610'), (1, '6.870')] -[2023-10-09 02:15:26,057][88327] Updated weights for policy 1, policy_version 54120 (0.0010) -[2023-10-09 02:15:26,419][88327] Updated weights for policy 1, policy_version 54130 (0.0011) -[2023-10-09 02:15:26,784][88327] Updated weights for policy 1, policy_version 54140 (0.0009) -[2023-10-09 02:15:27,816][88326] Updated weights for policy 0, policy_version 54122 (0.0009) -[2023-10-09 02:15:28,197][88326] Updated weights for policy 0, policy_version 54132 (0.0009) -[2023-10-09 02:15:28,566][88326] Updated weights for policy 0, policy_version 54142 (0.0008) -[2023-10-09 02:15:28,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 110886912. Throughput: 0: 1702.9, 1: 1665.5. Samples: 27724848. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:15:28,975][87372] Avg episode reward: [(0, '6.310'), (1, '6.700')] -[2023-10-09 02:15:30,698][88327] Updated weights for policy 1, policy_version 54150 (0.0009) -[2023-10-09 02:15:31,062][88327] Updated weights for policy 1, policy_version 54160 (0.0009) -[2023-10-09 02:15:31,429][88327] Updated weights for policy 1, policy_version 54170 (0.0008) -[2023-10-09 02:15:32,576][88326] Updated weights for policy 0, policy_version 54152 (0.0007) -[2023-10-09 02:15:32,943][88326] Updated weights for policy 0, policy_version 54162 (0.0007) -[2023-10-09 02:15:33,309][88326] Updated weights for policy 0, policy_version 54172 (0.0008) -[2023-10-09 02:15:33,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 110952448. Throughput: 0: 1674.1, 1: 1693.6. Samples: 27744876. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:15:33,975][87372] Avg episode reward: [(0, '6.520'), (1, '7.290')] -[2023-10-09 02:15:35,443][88327] Updated weights for policy 1, policy_version 54180 (0.0009) -[2023-10-09 02:15:35,797][88327] Updated weights for policy 1, policy_version 54190 (0.0007) -[2023-10-09 02:15:36,161][88327] Updated weights for policy 1, policy_version 54200 (0.0007) -[2023-10-09 02:15:37,294][88326] Updated weights for policy 0, policy_version 54182 (0.0009) -[2023-10-09 02:15:37,666][88326] Updated weights for policy 0, policy_version 54192 (0.0009) -[2023-10-09 02:15:38,044][88326] Updated weights for policy 0, policy_version 54202 (0.0009) -[2023-10-09 02:15:38,974][87372] Fps is (10 sec: 13107.6, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 111017984. Throughput: 0: 1697.3, 1: 1673.0. Samples: 27755508. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:15:38,974][87372] Avg episode reward: [(0, '6.950'), (1, '6.790')] -[2023-10-09 02:15:40,192][88327] Updated weights for policy 1, policy_version 54210 (0.0009) -[2023-10-09 02:15:40,554][88327] Updated weights for policy 1, policy_version 54220 (0.0011) -[2023-10-09 02:15:40,914][88327] Updated weights for policy 1, policy_version 54230 (0.0010) -[2023-10-09 02:15:41,282][88327] Updated weights for policy 1, policy_version 54240 (0.0009) -[2023-10-09 02:15:42,072][88326] Updated weights for policy 0, policy_version 54212 (0.0007) -[2023-10-09 02:15:42,431][88326] Updated weights for policy 0, policy_version 54222 (0.0007) -[2023-10-09 02:15:42,808][88326] Updated weights for policy 0, policy_version 54232 (0.0009) -[2023-10-09 02:15:43,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 111083520. Throughput: 0: 1683.6, 1: 1677.1. Samples: 27775504. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:15:43,975][87372] Avg episode reward: [(0, '6.370'), (1, '6.520')] -[2023-10-09 02:15:45,515][88327] Updated weights for policy 1, policy_version 54250 (0.0010) -[2023-10-09 02:15:45,878][88327] Updated weights for policy 1, policy_version 54260 (0.0009) -[2023-10-09 02:15:46,255][88327] Updated weights for policy 1, policy_version 54270 (0.0009) -[2023-10-09 02:15:46,818][88326] Updated weights for policy 0, policy_version 54242 (0.0009) -[2023-10-09 02:15:47,183][88326] Updated weights for policy 0, policy_version 54252 (0.0007) -[2023-10-09 02:15:47,552][88326] Updated weights for policy 0, policy_version 54262 (0.0011) -[2023-10-09 02:15:47,914][88326] Updated weights for policy 0, policy_version 54272 (0.0008) -[2023-10-09 02:15:48,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 111149056. Throughput: 0: 1667.0, 1: 1695.9. Samples: 27795288. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:15:48,975][87372] Avg episode reward: [(0, '6.520'), (1, '6.930')] -[2023-10-09 02:15:50,178][88327] Updated weights for policy 1, policy_version 54280 (0.0010) -[2023-10-09 02:15:50,534][88327] Updated weights for policy 1, policy_version 54290 (0.0010) -[2023-10-09 02:15:50,905][88327] Updated weights for policy 1, policy_version 54300 (0.0009) -[2023-10-09 02:15:51,965][88326] Updated weights for policy 0, policy_version 54282 (0.0008) -[2023-10-09 02:15:52,326][88326] Updated weights for policy 0, policy_version 54292 (0.0009) -[2023-10-09 02:15:52,698][88326] Updated weights for policy 0, policy_version 54302 (0.0007) -[2023-10-09 02:15:53,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 111214592. Throughput: 0: 1696.0, 1: 1668.9. Samples: 27805960. Policy #0 lag: (min: 19.0, avg: 25.2, max: 51.0) -[2023-10-09 02:15:53,975][87372] Avg episode reward: [(0, '6.020'), (1, '6.720')] -[2023-10-09 02:15:54,875][88327] Updated weights for policy 1, policy_version 54310 (0.0009) -[2023-10-09 02:15:55,242][88327] Updated weights for policy 1, policy_version 54320 (0.0009) -[2023-10-09 02:15:55,607][88327] Updated weights for policy 1, policy_version 54330 (0.0010) -[2023-10-09 02:15:56,914][88326] Updated weights for policy 0, policy_version 54312 (0.0009) -[2023-10-09 02:15:57,298][88326] Updated weights for policy 0, policy_version 54322 (0.0009) -[2023-10-09 02:15:57,661][88326] Updated weights for policy 0, policy_version 54332 (0.0007) -[2023-10-09 02:15:58,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 111280128. Throughput: 0: 1679.0, 1: 1695.7. Samples: 27826286. Policy #0 lag: (min: 19.0, avg: 25.2, max: 51.0) -[2023-10-09 02:15:58,975][87372] Avg episode reward: [(0, '6.160'), (1, '6.810')] -[2023-10-09 02:15:59,528][88327] Updated weights for policy 1, policy_version 54340 (0.0009) -[2023-10-09 02:15:59,892][88327] Updated weights for policy 1, policy_version 54350 (0.0007) -[2023-10-09 02:16:00,258][88327] Updated weights for policy 1, policy_version 54360 (0.0007) -[2023-10-09 02:16:01,696][88326] Updated weights for policy 0, policy_version 54342 (0.0008) -[2023-10-09 02:16:02,062][88326] Updated weights for policy 0, policy_version 54352 (0.0009) -[2023-10-09 02:16:02,443][88326] Updated weights for policy 0, policy_version 54362 (0.0007) -[2023-10-09 02:16:03,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 111345664. Throughput: 0: 1676.0, 1: 1707.6. Samples: 27846538. Policy #0 lag: (min: 19.0, avg: 25.2, max: 51.0) -[2023-10-09 02:16:03,975][87372] Avg episode reward: [(0, '5.820'), (1, '6.980')] -[2023-10-09 02:16:04,320][88327] Updated weights for policy 1, policy_version 54370 (0.0009) -[2023-10-09 02:16:04,683][88327] Updated weights for policy 1, policy_version 54380 (0.0007) -[2023-10-09 02:16:05,043][88327] Updated weights for policy 1, policy_version 54390 (0.0011) -[2023-10-09 02:16:05,409][88327] Updated weights for policy 1, policy_version 54400 (0.0008) -[2023-10-09 02:16:06,403][88326] Updated weights for policy 0, policy_version 54372 (0.0008) -[2023-10-09 02:16:06,766][88326] Updated weights for policy 0, policy_version 54382 (0.0007) -[2023-10-09 02:16:07,138][88326] Updated weights for policy 0, policy_version 54392 (0.0009) -[2023-10-09 02:16:08,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 111411200. Throughput: 0: 1693.5, 1: 1678.6. Samples: 27856952. Policy #0 lag: (min: 19.0, avg: 25.2, max: 51.0) -[2023-10-09 02:16:08,975][87372] Avg episode reward: [(0, '6.030'), (1, '6.730')] -[2023-10-09 02:16:09,674][88327] Updated weights for policy 1, policy_version 54410 (0.0007) -[2023-10-09 02:16:10,037][88327] Updated weights for policy 1, policy_version 54420 (0.0009) -[2023-10-09 02:16:10,407][88327] Updated weights for policy 1, policy_version 54430 (0.0010) -[2023-10-09 02:16:11,277][88326] Updated weights for policy 0, policy_version 54402 (0.0008) -[2023-10-09 02:16:11,649][88326] Updated weights for policy 0, policy_version 54412 (0.0008) -[2023-10-09 02:16:12,010][88326] Updated weights for policy 0, policy_version 54422 (0.0007) -[2023-10-09 02:16:12,376][88326] Updated weights for policy 0, policy_version 54432 (0.0008) -[2023-10-09 02:16:13,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 111476736. Throughput: 0: 1670.1, 1: 1702.1. Samples: 27876594. Policy #0 lag: (min: 19.0, avg: 25.2, max: 51.0) -[2023-10-09 02:16:13,975][87372] Avg episode reward: [(0, '6.860'), (1, '6.960')] -[2023-10-09 02:16:14,500][88327] Updated weights for policy 1, policy_version 54440 (0.0010) -[2023-10-09 02:16:14,865][88327] Updated weights for policy 1, policy_version 54450 (0.0011) -[2023-10-09 02:16:15,238][88327] Updated weights for policy 1, policy_version 54460 (0.0010) -[2023-10-09 02:16:16,349][88326] Updated weights for policy 0, policy_version 54442 (0.0009) -[2023-10-09 02:16:16,714][88326] Updated weights for policy 0, policy_version 54452 (0.0011) -[2023-10-09 02:16:17,089][88326] Updated weights for policy 0, policy_version 54462 (0.0011) -[2023-10-09 02:16:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 111542272. Throughput: 0: 1686.1, 1: 1700.6. Samples: 27897278. Policy #0 lag: (min: 19.0, avg: 25.2, max: 51.0) -[2023-10-09 02:16:18,975][87372] Avg episode reward: [(0, '6.380'), (1, '6.660')] -[2023-10-09 02:16:19,373][88327] Updated weights for policy 1, policy_version 54470 (0.0010) -[2023-10-09 02:16:19,741][88327] Updated weights for policy 1, policy_version 54480 (0.0009) -[2023-10-09 02:16:20,107][88327] Updated weights for policy 1, policy_version 54490 (0.0007) -[2023-10-09 02:16:20,915][88326] Updated weights for policy 0, policy_version 54472 (0.0009) -[2023-10-09 02:16:21,293][88326] Updated weights for policy 0, policy_version 54482 (0.0009) -[2023-10-09 02:16:21,664][88326] Updated weights for policy 0, policy_version 54492 (0.0009) -[2023-10-09 02:16:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 111607808. Throughput: 0: 1681.7, 1: 1691.3. Samples: 27907294. Policy #0 lag: (min: 19.0, avg: 25.2, max: 51.0) -[2023-10-09 02:16:23,975][87372] Avg episode reward: [(0, '6.610'), (1, '6.570')] -[2023-10-09 02:16:24,188][88327] Updated weights for policy 1, policy_version 54500 (0.0009) -[2023-10-09 02:16:24,542][88327] Updated weights for policy 1, policy_version 54510 (0.0010) -[2023-10-09 02:16:24,919][88327] Updated weights for policy 1, policy_version 54520 (0.0010) -[2023-10-09 02:16:25,757][88326] Updated weights for policy 0, policy_version 54502 (0.0009) -[2023-10-09 02:16:26,121][88326] Updated weights for policy 0, policy_version 54512 (0.0008) -[2023-10-09 02:16:26,490][88326] Updated weights for policy 0, policy_version 54522 (0.0007) -[2023-10-09 02:16:28,704][88327] Updated weights for policy 1, policy_version 54530 (0.0010) -[2023-10-09 02:16:28,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 111673344. Throughput: 0: 1672.1, 1: 1704.0. Samples: 27927428. Policy #0 lag: (min: 19.0, avg: 25.2, max: 51.0) -[2023-10-09 02:16:28,974][87372] Avg episode reward: [(0, '6.320'), (1, '6.770')] -[2023-10-09 02:16:29,072][88327] Updated weights for policy 1, policy_version 54540 (0.0010) -[2023-10-09 02:16:29,430][88327] Updated weights for policy 1, policy_version 54550 (0.0009) -[2023-10-09 02:16:29,798][88327] Updated weights for policy 1, policy_version 54560 (0.0008) -[2023-10-09 02:16:30,402][88326] Updated weights for policy 0, policy_version 54532 (0.0008) -[2023-10-09 02:16:30,769][88326] Updated weights for policy 0, policy_version 54542 (0.0007) -[2023-10-09 02:16:31,139][88326] Updated weights for policy 0, policy_version 54552 (0.0007) -[2023-10-09 02:16:33,845][88327] Updated weights for policy 1, policy_version 54570 (0.0008) -[2023-10-09 02:16:33,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 111738880. Throughput: 0: 1702.5, 1: 1708.8. Samples: 27948796. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:16:33,974][87372] Avg episode reward: [(0, '6.080'), (1, '6.710')] -[2023-10-09 02:16:33,983][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000054560_55869440.pth... -[2023-10-09 02:16:34,019][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000052992_54263808.pth -[2023-10-09 02:16:34,224][88327] Updated weights for policy 1, policy_version 54580 (0.0007) -[2023-10-09 02:16:34,593][88327] Updated weights for policy 1, policy_version 54590 (0.0009) -[2023-10-09 02:16:34,663][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000054592_55902208.pth... -[2023-10-09 02:16:34,700][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000052992_54263808.pth -[2023-10-09 02:16:35,170][88326] Updated weights for policy 0, policy_version 54562 (0.0008) -[2023-10-09 02:16:35,540][88326] Updated weights for policy 0, policy_version 54572 (0.0009) -[2023-10-09 02:16:35,907][88326] Updated weights for policy 0, policy_version 54582 (0.0008) -[2023-10-09 02:16:36,273][88326] Updated weights for policy 0, policy_version 54592 (0.0008) -[2023-10-09 02:16:38,541][88327] Updated weights for policy 1, policy_version 54600 (0.0007) -[2023-10-09 02:16:38,906][88327] Updated weights for policy 1, policy_version 54610 (0.0007) -[2023-10-09 02:16:38,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 111804416. Throughput: 0: 1674.0, 1: 1701.1. Samples: 27957838. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:16:38,974][87372] Avg episode reward: [(0, '6.270'), (1, '6.820')] -[2023-10-09 02:16:39,260][88327] Updated weights for policy 1, policy_version 54620 (0.0008) -[2023-10-09 02:16:40,325][88326] Updated weights for policy 0, policy_version 54602 (0.0008) -[2023-10-09 02:16:40,688][88326] Updated weights for policy 0, policy_version 54612 (0.0010) -[2023-10-09 02:16:41,053][88326] Updated weights for policy 0, policy_version 54622 (0.0009) -[2023-10-09 02:16:43,207][88327] Updated weights for policy 1, policy_version 54630 (0.0008) -[2023-10-09 02:16:43,577][88327] Updated weights for policy 1, policy_version 54640 (0.0009) -[2023-10-09 02:16:43,947][88327] Updated weights for policy 1, policy_version 54650 (0.0010) -[2023-10-09 02:16:43,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 111869952. Throughput: 0: 1690.6, 1: 1700.8. Samples: 27978902. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:16:43,975][87372] Avg episode reward: [(0, '6.430'), (1, '7.460')] -[2023-10-09 02:16:44,160][88168] Saving new best policy, reward=7.460! -[2023-10-09 02:16:45,204][88326] Updated weights for policy 0, policy_version 54632 (0.0010) -[2023-10-09 02:16:45,575][88326] Updated weights for policy 0, policy_version 54642 (0.0009) -[2023-10-09 02:16:45,954][88326] Updated weights for policy 0, policy_version 54652 (0.0007) -[2023-10-09 02:16:47,907][88327] Updated weights for policy 1, policy_version 54660 (0.0009) -[2023-10-09 02:16:48,265][88327] Updated weights for policy 1, policy_version 54670 (0.0009) -[2023-10-09 02:16:48,630][88327] Updated weights for policy 1, policy_version 54680 (0.0007) -[2023-10-09 02:16:48,974][87372] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 111968256. Throughput: 0: 1702.7, 1: 1694.2. Samples: 27999398. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:16:48,974][87372] Avg episode reward: [(0, '6.420'), (1, '6.630')] -[2023-10-09 02:16:49,931][88326] Updated weights for policy 0, policy_version 54662 (0.0009) -[2023-10-09 02:16:50,298][88326] Updated weights for policy 0, policy_version 54672 (0.0010) -[2023-10-09 02:16:50,674][88326] Updated weights for policy 0, policy_version 54682 (0.0009) -[2023-10-09 02:16:52,808][88327] Updated weights for policy 1, policy_version 54690 (0.0010) -[2023-10-09 02:16:53,165][88327] Updated weights for policy 1, policy_version 54700 (0.0011) -[2023-10-09 02:16:53,541][88327] Updated weights for policy 1, policy_version 54710 (0.0009) -[2023-10-09 02:16:53,905][88327] Updated weights for policy 1, policy_version 54720 (0.0009) -[2023-10-09 02:16:53,974][87372] Fps is (10 sec: 16384.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 112033792. Throughput: 0: 1675.9, 1: 1705.2. Samples: 28009104. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:16:53,974][87372] Avg episode reward: [(0, '6.330'), (1, '6.870')] -[2023-10-09 02:16:54,693][88326] Updated weights for policy 0, policy_version 54692 (0.0009) -[2023-10-09 02:16:55,065][88326] Updated weights for policy 0, policy_version 54702 (0.0007) -[2023-10-09 02:16:55,429][88326] Updated weights for policy 0, policy_version 54712 (0.0008) -[2023-10-09 02:16:58,023][88327] Updated weights for policy 1, policy_version 54730 (0.0009) -[2023-10-09 02:16:58,405][88327] Updated weights for policy 1, policy_version 54740 (0.0008) -[2023-10-09 02:16:58,770][88327] Updated weights for policy 1, policy_version 54750 (0.0009) -[2023-10-09 02:16:58,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 112099328. Throughput: 0: 1706.5, 1: 1702.1. Samples: 28029984. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:16:58,975][87372] Avg episode reward: [(0, '6.120'), (1, '6.390')] -[2023-10-09 02:16:59,509][88326] Updated weights for policy 0, policy_version 54722 (0.0008) -[2023-10-09 02:16:59,872][88326] Updated weights for policy 0, policy_version 54732 (0.0008) -[2023-10-09 02:17:00,246][88326] Updated weights for policy 0, policy_version 54742 (0.0008) -[2023-10-09 02:17:00,609][88326] Updated weights for policy 0, policy_version 54752 (0.0007) -[2023-10-09 02:17:02,793][88327] Updated weights for policy 1, policy_version 54760 (0.0009) -[2023-10-09 02:17:03,162][88327] Updated weights for policy 1, policy_version 54770 (0.0009) -[2023-10-09 02:17:03,522][88327] Updated weights for policy 1, policy_version 54780 (0.0009) -[2023-10-09 02:17:03,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 112164864. Throughput: 0: 1712.7, 1: 1688.2. Samples: 28050318. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:17:03,975][87372] Avg episode reward: [(0, '5.900'), (1, '6.420')] -[2023-10-09 02:17:04,470][88326] Updated weights for policy 0, policy_version 54762 (0.0009) -[2023-10-09 02:17:04,842][88326] Updated weights for policy 0, policy_version 54772 (0.0009) -[2023-10-09 02:17:05,201][88326] Updated weights for policy 0, policy_version 54782 (0.0007) -[2023-10-09 02:17:07,496][88327] Updated weights for policy 1, policy_version 54790 (0.0007) -[2023-10-09 02:17:07,859][88327] Updated weights for policy 1, policy_version 54800 (0.0010) -[2023-10-09 02:17:08,228][88327] Updated weights for policy 1, policy_version 54810 (0.0009) -[2023-10-09 02:17:08,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 112230400. Throughput: 0: 1698.5, 1: 1706.5. Samples: 28060520. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:17:08,974][87372] Avg episode reward: [(0, '7.010'), (1, '6.370')] -[2023-10-09 02:17:09,178][88326] Updated weights for policy 0, policy_version 54792 (0.0007) -[2023-10-09 02:17:09,544][88326] Updated weights for policy 0, policy_version 54802 (0.0009) -[2023-10-09 02:17:09,908][88326] Updated weights for policy 0, policy_version 54812 (0.0008) -[2023-10-09 02:17:12,380][88327] Updated weights for policy 1, policy_version 54820 (0.0008) -[2023-10-09 02:17:12,746][88327] Updated weights for policy 1, policy_version 54830 (0.0007) -[2023-10-09 02:17:13,111][88327] Updated weights for policy 1, policy_version 54840 (0.0009) -[2023-10-09 02:17:13,915][88326] Updated weights for policy 0, policy_version 54822 (0.0008) -[2023-10-09 02:17:13,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 112295936. Throughput: 0: 1720.6, 1: 1702.7. Samples: 28081476. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 02:17:13,975][87372] Avg episode reward: [(0, '6.920'), (1, '6.860')] -[2023-10-09 02:17:14,297][88326] Updated weights for policy 0, policy_version 54832 (0.0007) -[2023-10-09 02:17:14,660][88326] Updated weights for policy 0, policy_version 54842 (0.0007) -[2023-10-09 02:17:17,056][88327] Updated weights for policy 1, policy_version 54850 (0.0008) -[2023-10-09 02:17:17,414][88327] Updated weights for policy 1, policy_version 54860 (0.0007) -[2023-10-09 02:17:17,782][88327] Updated weights for policy 1, policy_version 54870 (0.0008) -[2023-10-09 02:17:18,144][88327] Updated weights for policy 1, policy_version 54880 (0.0009) -[2023-10-09 02:17:18,576][88326] Updated weights for policy 0, policy_version 54852 (0.0008) -[2023-10-09 02:17:18,943][88326] Updated weights for policy 0, policy_version 54862 (0.0009) -[2023-10-09 02:17:18,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 112361472. Throughput: 0: 1718.7, 1: 1676.1. Samples: 28101564. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 02:17:18,975][87372] Avg episode reward: [(0, '6.720'), (1, '6.280')] -[2023-10-09 02:17:19,308][88326] Updated weights for policy 0, policy_version 54872 (0.0011) -[2023-10-09 02:17:22,132][88327] Updated weights for policy 1, policy_version 54890 (0.0009) -[2023-10-09 02:17:22,496][88327] Updated weights for policy 1, policy_version 54900 (0.0009) -[2023-10-09 02:17:22,858][88327] Updated weights for policy 1, policy_version 54910 (0.0008) -[2023-10-09 02:17:23,245][88326] Updated weights for policy 0, policy_version 54882 (0.0009) -[2023-10-09 02:17:23,613][88326] Updated weights for policy 0, policy_version 54892 (0.0007) -[2023-10-09 02:17:23,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 112427008. Throughput: 0: 1715.9, 1: 1706.3. Samples: 28111838. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 02:17:23,975][87372] Avg episode reward: [(0, '6.770'), (1, '5.860')] -[2023-10-09 02:17:23,988][88326] Updated weights for policy 0, policy_version 54902 (0.0009) -[2023-10-09 02:17:24,356][88326] Updated weights for policy 0, policy_version 54912 (0.0010) -[2023-10-09 02:17:26,939][88327] Updated weights for policy 1, policy_version 54920 (0.0009) -[2023-10-09 02:17:27,305][88327] Updated weights for policy 1, policy_version 54930 (0.0011) -[2023-10-09 02:17:27,664][88327] Updated weights for policy 1, policy_version 54940 (0.0007) -[2023-10-09 02:17:28,375][88326] Updated weights for policy 0, policy_version 54922 (0.0009) -[2023-10-09 02:17:28,746][88326] Updated weights for policy 0, policy_version 54932 (0.0009) -[2023-10-09 02:17:28,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 112492544. Throughput: 0: 1716.7, 1: 1686.2. Samples: 28132034. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 02:17:28,974][87372] Avg episode reward: [(0, '6.380'), (1, '6.310')] -[2023-10-09 02:17:29,105][88326] Updated weights for policy 0, policy_version 54942 (0.0008) -[2023-10-09 02:17:31,821][88327] Updated weights for policy 1, policy_version 54950 (0.0009) -[2023-10-09 02:17:32,180][88327] Updated weights for policy 1, policy_version 54960 (0.0008) -[2023-10-09 02:17:32,547][88327] Updated weights for policy 1, policy_version 54970 (0.0010) -[2023-10-09 02:17:33,209][88326] Updated weights for policy 0, policy_version 54952 (0.0009) -[2023-10-09 02:17:33,589][88326] Updated weights for policy 0, policy_version 54962 (0.0010) -[2023-10-09 02:17:33,955][88326] Updated weights for policy 0, policy_version 54972 (0.0008) -[2023-10-09 02:17:33,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 112558080. Throughput: 0: 1709.7, 1: 1673.3. Samples: 28151636. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 02:17:33,974][87372] Avg episode reward: [(0, '6.520'), (1, '6.510')] -[2023-10-09 02:17:36,587][88327] Updated weights for policy 1, policy_version 54980 (0.0009) -[2023-10-09 02:17:36,957][88327] Updated weights for policy 1, policy_version 54990 (0.0007) -[2023-10-09 02:17:37,326][88327] Updated weights for policy 1, policy_version 55000 (0.0007) -[2023-10-09 02:17:38,027][88326] Updated weights for policy 0, policy_version 54982 (0.0008) -[2023-10-09 02:17:38,404][88326] Updated weights for policy 0, policy_version 54992 (0.0008) -[2023-10-09 02:17:38,774][88326] Updated weights for policy 0, policy_version 55002 (0.0008) -[2023-10-09 02:17:38,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 112623616. Throughput: 0: 1711.3, 1: 1694.7. Samples: 28162374. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 02:17:38,975][87372] Avg episode reward: [(0, '6.700'), (1, '6.350')] -[2023-10-09 02:17:41,523][88327] Updated weights for policy 1, policy_version 55010 (0.0008) -[2023-10-09 02:17:41,895][88327] Updated weights for policy 1, policy_version 55020 (0.0009) -[2023-10-09 02:17:42,270][88327] Updated weights for policy 1, policy_version 55030 (0.0008) -[2023-10-09 02:17:42,635][88327] Updated weights for policy 1, policy_version 55040 (0.0007) -[2023-10-09 02:17:42,958][88326] Updated weights for policy 0, policy_version 55012 (0.0009) -[2023-10-09 02:17:43,326][88326] Updated weights for policy 0, policy_version 55022 (0.0007) -[2023-10-09 02:17:43,699][88326] Updated weights for policy 0, policy_version 55032 (0.0008) -[2023-10-09 02:17:43,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 112689152. Throughput: 0: 1703.1, 1: 1678.7. Samples: 28182164. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 02:17:43,975][87372] Avg episode reward: [(0, '7.360'), (1, '6.700')] -[2023-10-09 02:17:46,595][88327] Updated weights for policy 1, policy_version 55050 (0.0009) -[2023-10-09 02:17:46,962][88327] Updated weights for policy 1, policy_version 55060 (0.0009) -[2023-10-09 02:17:47,345][88327] Updated weights for policy 1, policy_version 55070 (0.0010) -[2023-10-09 02:17:47,696][88326] Updated weights for policy 0, policy_version 55042 (0.0010) -[2023-10-09 02:17:48,069][88326] Updated weights for policy 0, policy_version 55052 (0.0009) -[2023-10-09 02:17:48,446][88326] Updated weights for policy 0, policy_version 55062 (0.0010) -[2023-10-09 02:17:48,824][88326] Updated weights for policy 0, policy_version 55072 (0.0009) -[2023-10-09 02:17:48,974][87372] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 112787456. Throughput: 0: 1685.6, 1: 1680.1. Samples: 28201776. Policy #0 lag: (min: 23.0, avg: 31.0, max: 55.0) -[2023-10-09 02:17:48,975][87372] Avg episode reward: [(0, '6.400'), (1, '6.380')] -[2023-10-09 02:17:51,327][88327] Updated weights for policy 1, policy_version 55080 (0.0008) -[2023-10-09 02:17:51,693][88327] Updated weights for policy 1, policy_version 55090 (0.0009) -[2023-10-09 02:17:52,054][88327] Updated weights for policy 1, policy_version 55100 (0.0009) -[2023-10-09 02:17:52,885][88326] Updated weights for policy 0, policy_version 55082 (0.0008) -[2023-10-09 02:17:53,252][88326] Updated weights for policy 0, policy_version 55092 (0.0010) -[2023-10-09 02:17:53,625][88326] Updated weights for policy 0, policy_version 55102 (0.0009) -[2023-10-09 02:17:53,974][87372] Fps is (10 sec: 16384.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 112852992. Throughput: 0: 1692.9, 1: 1690.3. Samples: 28212764. Policy #0 lag: (min: 23.0, avg: 31.0, max: 55.0) -[2023-10-09 02:17:53,975][87372] Avg episode reward: [(0, '6.610'), (1, '6.100')] -[2023-10-09 02:17:56,180][88327] Updated weights for policy 1, policy_version 55110 (0.0009) -[2023-10-09 02:17:56,546][88327] Updated weights for policy 1, policy_version 55120 (0.0008) -[2023-10-09 02:17:56,923][88327] Updated weights for policy 1, policy_version 55130 (0.0009) -[2023-10-09 02:17:57,687][88326] Updated weights for policy 0, policy_version 55112 (0.0008) -[2023-10-09 02:17:58,059][88326] Updated weights for policy 0, policy_version 55122 (0.0009) -[2023-10-09 02:17:58,427][88326] Updated weights for policy 0, policy_version 55132 (0.0008) -[2023-10-09 02:17:58,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 112918528. Throughput: 0: 1693.8, 1: 1665.5. Samples: 28232642. Policy #0 lag: (min: 23.0, avg: 31.0, max: 55.0) -[2023-10-09 02:17:58,975][87372] Avg episode reward: [(0, '7.100'), (1, '6.420')] -[2023-10-09 02:18:01,035][88327] Updated weights for policy 1, policy_version 55140 (0.0010) -[2023-10-09 02:18:01,405][88327] Updated weights for policy 1, policy_version 55150 (0.0009) -[2023-10-09 02:18:01,764][88327] Updated weights for policy 1, policy_version 55160 (0.0010) -[2023-10-09 02:18:02,302][88326] Updated weights for policy 0, policy_version 55142 (0.0009) -[2023-10-09 02:18:02,667][88326] Updated weights for policy 0, policy_version 55152 (0.0008) -[2023-10-09 02:18:03,038][88326] Updated weights for policy 0, policy_version 55162 (0.0008) -[2023-10-09 02:18:03,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 112984064. Throughput: 0: 1664.1, 1: 1688.8. Samples: 28252448. Policy #0 lag: (min: 23.0, avg: 31.0, max: 55.0) -[2023-10-09 02:18:03,975][87372] Avg episode reward: [(0, '6.310'), (1, '6.750')] -[2023-10-09 02:18:05,566][88327] Updated weights for policy 1, policy_version 55170 (0.0007) -[2023-10-09 02:18:05,932][88327] Updated weights for policy 1, policy_version 55180 (0.0010) -[2023-10-09 02:18:06,294][88327] Updated weights for policy 1, policy_version 55190 (0.0011) -[2023-10-09 02:18:06,663][88327] Updated weights for policy 1, policy_version 55200 (0.0009) -[2023-10-09 02:18:07,033][88326] Updated weights for policy 0, policy_version 55172 (0.0010) -[2023-10-09 02:18:07,410][88326] Updated weights for policy 0, policy_version 55182 (0.0008) -[2023-10-09 02:18:07,771][88326] Updated weights for policy 0, policy_version 55192 (0.0008) -[2023-10-09 02:18:08,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 113049600. Throughput: 0: 1693.5, 1: 1675.5. Samples: 28263444. Policy #0 lag: (min: 23.0, avg: 31.0, max: 55.0) -[2023-10-09 02:18:08,975][87372] Avg episode reward: [(0, '6.510'), (1, '7.220')] -[2023-10-09 02:18:10,753][88327] Updated weights for policy 1, policy_version 55210 (0.0008) -[2023-10-09 02:18:11,113][88327] Updated weights for policy 1, policy_version 55220 (0.0010) -[2023-10-09 02:18:11,484][88327] Updated weights for policy 1, policy_version 55230 (0.0009) -[2023-10-09 02:18:11,821][88326] Updated weights for policy 0, policy_version 55202 (0.0008) -[2023-10-09 02:18:12,196][88326] Updated weights for policy 0, policy_version 55212 (0.0007) -[2023-10-09 02:18:12,560][88326] Updated weights for policy 0, policy_version 55222 (0.0010) -[2023-10-09 02:18:12,931][88326] Updated weights for policy 0, policy_version 55232 (0.0011) -[2023-10-09 02:18:13,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 113115136. Throughput: 0: 1682.0, 1: 1677.3. Samples: 28283206. Policy #0 lag: (min: 23.0, avg: 31.0, max: 55.0) -[2023-10-09 02:18:13,975][87372] Avg episode reward: [(0, '6.220'), (1, '6.860')] -[2023-10-09 02:18:15,591][88327] Updated weights for policy 1, policy_version 55240 (0.0008) -[2023-10-09 02:18:15,957][88327] Updated weights for policy 1, policy_version 55250 (0.0009) -[2023-10-09 02:18:16,325][88327] Updated weights for policy 1, policy_version 55260 (0.0007) -[2023-10-09 02:18:17,134][88326] Updated weights for policy 0, policy_version 55242 (0.0009) -[2023-10-09 02:18:17,502][88326] Updated weights for policy 0, policy_version 55252 (0.0009) -[2023-10-09 02:18:17,875][88326] Updated weights for policy 0, policy_version 55262 (0.0008) -[2023-10-09 02:18:18,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 113180672. Throughput: 0: 1668.2, 1: 1695.5. Samples: 28303000. Policy #0 lag: (min: 23.0, avg: 31.0, max: 55.0) -[2023-10-09 02:18:18,975][87372] Avg episode reward: [(0, '5.970'), (1, '6.690')] -[2023-10-09 02:18:20,350][88327] Updated weights for policy 1, policy_version 55270 (0.0010) -[2023-10-09 02:18:20,715][88327] Updated weights for policy 1, policy_version 55280 (0.0008) -[2023-10-09 02:18:21,079][88327] Updated weights for policy 1, policy_version 55290 (0.0008) -[2023-10-09 02:18:21,861][88326] Updated weights for policy 0, policy_version 55272 (0.0008) -[2023-10-09 02:18:22,223][88326] Updated weights for policy 0, policy_version 55282 (0.0009) -[2023-10-09 02:18:22,605][88326] Updated weights for policy 0, policy_version 55292 (0.0008) -[2023-10-09 02:18:23,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 113246208. Throughput: 0: 1695.8, 1: 1668.2. Samples: 28313756. Policy #0 lag: (min: 23.0, avg: 31.0, max: 55.0) -[2023-10-09 02:18:23,975][87372] Avg episode reward: [(0, '5.940'), (1, '7.280')] -[2023-10-09 02:18:25,207][88327] Updated weights for policy 1, policy_version 55300 (0.0007) -[2023-10-09 02:18:25,565][88327] Updated weights for policy 1, policy_version 55310 (0.0009) -[2023-10-09 02:18:25,938][88327] Updated weights for policy 1, policy_version 55320 (0.0009) -[2023-10-09 02:18:26,564][88326] Updated weights for policy 0, policy_version 55302 (0.0008) -[2023-10-09 02:18:26,923][88326] Updated weights for policy 0, policy_version 55312 (0.0010) -[2023-10-09 02:18:27,288][88326] Updated weights for policy 0, policy_version 55322 (0.0010) -[2023-10-09 02:18:28,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 113311744. Throughput: 0: 1678.8, 1: 1689.2. Samples: 28333720. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:18:28,974][87372] Avg episode reward: [(0, '6.200'), (1, '6.910')] -[2023-10-09 02:18:29,856][88327] Updated weights for policy 1, policy_version 55330 (0.0009) -[2023-10-09 02:18:30,231][88327] Updated weights for policy 1, policy_version 55340 (0.0011) -[2023-10-09 02:18:30,608][88327] Updated weights for policy 1, policy_version 55350 (0.0009) -[2023-10-09 02:18:30,970][88327] Updated weights for policy 1, policy_version 55360 (0.0010) -[2023-10-09 02:18:31,417][88326] Updated weights for policy 0, policy_version 55332 (0.0010) -[2023-10-09 02:18:31,776][88326] Updated weights for policy 0, policy_version 55342 (0.0007) -[2023-10-09 02:18:32,149][88326] Updated weights for policy 0, policy_version 55352 (0.0007) -[2023-10-09 02:18:33,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 113377280. Throughput: 0: 1683.3, 1: 1700.0. Samples: 28354026. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:18:33,975][87372] Avg episode reward: [(0, '7.170'), (1, '7.440')] -[2023-10-09 02:18:33,983][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000055360_56688640.pth... -[2023-10-09 02:18:33,983][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000055360_56688640.pth... -[2023-10-09 02:18:34,024][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000053792_55083008.pth -[2023-10-09 02:18:34,024][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000053760_55050240.pth -[2023-10-09 02:18:34,030][88168] Saving a milestone ./train_atari/atari_battlezone_APPO/checkpoint_p1/milestones/checkpoint_000055360_56688640.pth -[2023-10-09 02:18:34,030][88088] Saving a milestone ./train_atari/atari_battlezone_APPO/checkpoint_p0/milestones/checkpoint_000055360_56688640.pth -[2023-10-09 02:18:34,833][88327] Updated weights for policy 1, policy_version 55370 (0.0011) -[2023-10-09 02:18:35,195][88327] Updated weights for policy 1, policy_version 55380 (0.0012) -[2023-10-09 02:18:35,555][88327] Updated weights for policy 1, policy_version 55390 (0.0009) -[2023-10-09 02:18:36,192][88326] Updated weights for policy 0, policy_version 55362 (0.0009) -[2023-10-09 02:18:36,569][88326] Updated weights for policy 0, policy_version 55372 (0.0009) -[2023-10-09 02:18:36,940][88326] Updated weights for policy 0, policy_version 55382 (0.0008) -[2023-10-09 02:18:37,310][88326] Updated weights for policy 0, policy_version 55392 (0.0010) -[2023-10-09 02:18:38,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 113442816. Throughput: 0: 1698.8, 1: 1671.8. Samples: 28364440. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:18:38,975][87372] Avg episode reward: [(0, '6.460'), (1, '7.000')] -[2023-10-09 02:18:39,804][88327] Updated weights for policy 1, policy_version 55400 (0.0009) -[2023-10-09 02:18:40,168][88327] Updated weights for policy 1, policy_version 55410 (0.0008) -[2023-10-09 02:18:40,540][88327] Updated weights for policy 1, policy_version 55420 (0.0007) -[2023-10-09 02:18:41,225][88326] Updated weights for policy 0, policy_version 55402 (0.0007) -[2023-10-09 02:18:41,585][88326] Updated weights for policy 0, policy_version 55412 (0.0010) -[2023-10-09 02:18:41,952][88326] Updated weights for policy 0, policy_version 55422 (0.0009) -[2023-10-09 02:18:43,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 113508352. Throughput: 0: 1667.3, 1: 1695.8. Samples: 28383982. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:18:43,975][87372] Avg episode reward: [(0, '6.940'), (1, '6.740')] -[2023-10-09 02:18:44,518][88327] Updated weights for policy 1, policy_version 55430 (0.0008) -[2023-10-09 02:18:44,883][88327] Updated weights for policy 1, policy_version 55440 (0.0009) -[2023-10-09 02:18:45,242][88327] Updated weights for policy 1, policy_version 55450 (0.0010) -[2023-10-09 02:18:45,899][88326] Updated weights for policy 0, policy_version 55432 (0.0010) -[2023-10-09 02:18:46,266][88326] Updated weights for policy 0, policy_version 55442 (0.0009) -[2023-10-09 02:18:46,630][88326] Updated weights for policy 0, policy_version 55452 (0.0007) -[2023-10-09 02:18:48,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 113573888. Throughput: 0: 1693.1, 1: 1696.3. Samples: 28404970. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:18:48,974][87372] Avg episode reward: [(0, '7.140'), (1, '6.810')] -[2023-10-09 02:18:49,432][88327] Updated weights for policy 1, policy_version 55460 (0.0009) -[2023-10-09 02:18:49,797][88327] Updated weights for policy 1, policy_version 55470 (0.0008) -[2023-10-09 02:18:50,172][88327] Updated weights for policy 1, policy_version 55480 (0.0010) -[2023-10-09 02:18:50,661][88326] Updated weights for policy 0, policy_version 55462 (0.0008) -[2023-10-09 02:18:51,031][88326] Updated weights for policy 0, policy_version 55472 (0.0007) -[2023-10-09 02:18:51,396][88326] Updated weights for policy 0, policy_version 55482 (0.0009) -[2023-10-09 02:18:53,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 113639424. Throughput: 0: 1674.5, 1: 1682.1. Samples: 28414492. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:18:53,974][87372] Avg episode reward: [(0, '6.960'), (1, '6.480')] -[2023-10-09 02:18:54,072][88327] Updated weights for policy 1, policy_version 55490 (0.0009) -[2023-10-09 02:18:54,436][88327] Updated weights for policy 1, policy_version 55500 (0.0010) -[2023-10-09 02:18:54,806][88327] Updated weights for policy 1, policy_version 55510 (0.0011) -[2023-10-09 02:18:55,173][88327] Updated weights for policy 1, policy_version 55520 (0.0008) -[2023-10-09 02:18:55,340][88326] Updated weights for policy 0, policy_version 55492 (0.0009) -[2023-10-09 02:18:55,712][88326] Updated weights for policy 0, policy_version 55502 (0.0009) -[2023-10-09 02:18:56,078][88326] Updated weights for policy 0, policy_version 55512 (0.0009) -[2023-10-09 02:18:58,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 113704960. Throughput: 0: 1673.1, 1: 1698.8. Samples: 28434940. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:18:58,974][87372] Avg episode reward: [(0, '6.940'), (1, '6.330')] -[2023-10-09 02:18:59,139][88327] Updated weights for policy 1, policy_version 55530 (0.0010) -[2023-10-09 02:18:59,493][88327] Updated weights for policy 1, policy_version 55540 (0.0011) -[2023-10-09 02:18:59,858][88327] Updated weights for policy 1, policy_version 55550 (0.0011) -[2023-10-09 02:19:00,185][88326] Updated weights for policy 0, policy_version 55522 (0.0009) -[2023-10-09 02:19:00,548][88326] Updated weights for policy 0, policy_version 55532 (0.0009) -[2023-10-09 02:19:00,926][88326] Updated weights for policy 0, policy_version 55542 (0.0008) -[2023-10-09 02:19:01,286][88326] Updated weights for policy 0, policy_version 55552 (0.0007) -[2023-10-09 02:19:03,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 113770496. Throughput: 0: 1699.4, 1: 1701.2. Samples: 28456026. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:19:03,975][87372] Avg episode reward: [(0, '6.780'), (1, '6.600')] -[2023-10-09 02:19:04,156][88327] Updated weights for policy 1, policy_version 55560 (0.0009) -[2023-10-09 02:19:04,525][88327] Updated weights for policy 1, policy_version 55570 (0.0008) -[2023-10-09 02:19:04,881][88327] Updated weights for policy 1, policy_version 55580 (0.0008) -[2023-10-09 02:19:05,245][88326] Updated weights for policy 0, policy_version 55562 (0.0008) -[2023-10-09 02:19:05,617][88326] Updated weights for policy 0, policy_version 55572 (0.0007) -[2023-10-09 02:19:05,983][88326] Updated weights for policy 0, policy_version 55582 (0.0007) -[2023-10-09 02:19:08,917][88327] Updated weights for policy 1, policy_version 55590 (0.0010) -[2023-10-09 02:19:08,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 113836032. Throughput: 0: 1671.7, 1: 1696.9. Samples: 28465342. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:19:08,974][87372] Avg episode reward: [(0, '7.010'), (1, '6.490')] -[2023-10-09 02:19:09,279][88327] Updated weights for policy 1, policy_version 55600 (0.0008) -[2023-10-09 02:19:09,637][88327] Updated weights for policy 1, policy_version 55610 (0.0008) -[2023-10-09 02:19:10,080][88326] Updated weights for policy 0, policy_version 55592 (0.0009) -[2023-10-09 02:19:10,443][88326] Updated weights for policy 0, policy_version 55602 (0.0010) -[2023-10-09 02:19:10,810][88326] Updated weights for policy 0, policy_version 55612 (0.0011) -[2023-10-09 02:19:13,552][88327] Updated weights for policy 1, policy_version 55620 (0.0008) -[2023-10-09 02:19:13,921][88327] Updated weights for policy 1, policy_version 55630 (0.0007) -[2023-10-09 02:19:13,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 113901568. Throughput: 0: 1693.4, 1: 1694.1. Samples: 28486158. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:19:13,974][87372] Avg episode reward: [(0, '6.990'), (1, '6.100')] -[2023-10-09 02:19:14,275][88327] Updated weights for policy 1, policy_version 55640 (0.0007) -[2023-10-09 02:19:14,937][88326] Updated weights for policy 0, policy_version 55622 (0.0007) -[2023-10-09 02:19:15,320][88326] Updated weights for policy 0, policy_version 55632 (0.0007) -[2023-10-09 02:19:15,686][88326] Updated weights for policy 0, policy_version 55642 (0.0010) -[2023-10-09 02:19:18,272][88327] Updated weights for policy 1, policy_version 55650 (0.0007) -[2023-10-09 02:19:18,627][88327] Updated weights for policy 1, policy_version 55660 (0.0008) -[2023-10-09 02:19:18,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 113967104. Throughput: 0: 1706.2, 1: 1699.4. Samples: 28507278. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:19:18,975][87372] Avg episode reward: [(0, '6.460'), (1, '6.740')] -[2023-10-09 02:19:18,990][88327] Updated weights for policy 1, policy_version 55670 (0.0009) -[2023-10-09 02:19:19,358][88327] Updated weights for policy 1, policy_version 55680 (0.0008) -[2023-10-09 02:19:19,741][88326] Updated weights for policy 0, policy_version 55652 (0.0010) -[2023-10-09 02:19:20,119][88326] Updated weights for policy 0, policy_version 55662 (0.0009) -[2023-10-09 02:19:20,481][88326] Updated weights for policy 0, policy_version 55672 (0.0008) -[2023-10-09 02:19:23,324][88327] Updated weights for policy 1, policy_version 55690 (0.0009) -[2023-10-09 02:19:23,691][88327] Updated weights for policy 1, policy_version 55700 (0.0009) -[2023-10-09 02:19:23,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 114032640. Throughput: 0: 1675.7, 1: 1702.1. Samples: 28516436. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:19:23,974][87372] Avg episode reward: [(0, '6.540'), (1, '6.880')] -[2023-10-09 02:19:24,058][88327] Updated weights for policy 1, policy_version 55710 (0.0008) -[2023-10-09 02:19:24,590][88326] Updated weights for policy 0, policy_version 55682 (0.0008) -[2023-10-09 02:19:24,951][88326] Updated weights for policy 0, policy_version 55692 (0.0010) -[2023-10-09 02:19:25,315][88326] Updated weights for policy 0, policy_version 55702 (0.0009) -[2023-10-09 02:19:25,676][88326] Updated weights for policy 0, policy_version 55712 (0.0009) -[2023-10-09 02:19:28,071][88327] Updated weights for policy 1, policy_version 55720 (0.0008) -[2023-10-09 02:19:28,432][88327] Updated weights for policy 1, policy_version 55730 (0.0010) -[2023-10-09 02:19:28,809][88327] Updated weights for policy 1, policy_version 55740 (0.0008) -[2023-10-09 02:19:28,974][87372] Fps is (10 sec: 16384.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 114130944. Throughput: 0: 1701.0, 1: 1707.7. Samples: 28537374. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:19:28,974][87372] Avg episode reward: [(0, '6.240'), (1, '6.660')] -[2023-10-09 02:19:29,738][88326] Updated weights for policy 0, policy_version 55722 (0.0007) -[2023-10-09 02:19:30,113][88326] Updated weights for policy 0, policy_version 55732 (0.0007) -[2023-10-09 02:19:30,478][88326] Updated weights for policy 0, policy_version 55742 (0.0008) -[2023-10-09 02:19:32,805][88327] Updated weights for policy 1, policy_version 55750 (0.0009) -[2023-10-09 02:19:33,171][88327] Updated weights for policy 1, policy_version 55760 (0.0008) -[2023-10-09 02:19:33,542][88327] Updated weights for policy 1, policy_version 55770 (0.0009) -[2023-10-09 02:19:33,974][87372] Fps is (10 sec: 16383.8, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 114196480. Throughput: 0: 1699.3, 1: 1697.1. Samples: 28557810. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:19:33,975][87372] Avg episode reward: [(0, '5.860'), (1, '6.730')] -[2023-10-09 02:19:34,439][88326] Updated weights for policy 0, policy_version 55752 (0.0008) -[2023-10-09 02:19:34,805][88326] Updated weights for policy 0, policy_version 55762 (0.0009) -[2023-10-09 02:19:35,179][88326] Updated weights for policy 0, policy_version 55772 (0.0009) -[2023-10-09 02:19:37,838][88327] Updated weights for policy 1, policy_version 55780 (0.0010) -[2023-10-09 02:19:38,201][88327] Updated weights for policy 1, policy_version 55790 (0.0009) -[2023-10-09 02:19:38,567][88327] Updated weights for policy 1, policy_version 55800 (0.0008) -[2023-10-09 02:19:38,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 114262016. Throughput: 0: 1690.0, 1: 1711.0. Samples: 28567534. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:19:38,974][87372] Avg episode reward: [(0, '6.790'), (1, '6.510')] -[2023-10-09 02:19:39,298][88326] Updated weights for policy 0, policy_version 55782 (0.0011) -[2023-10-09 02:19:39,665][88326] Updated weights for policy 0, policy_version 55792 (0.0009) -[2023-10-09 02:19:40,018][88326] Updated weights for policy 0, policy_version 55802 (0.0008) -[2023-10-09 02:19:42,635][88327] Updated weights for policy 1, policy_version 55810 (0.0008) -[2023-10-09 02:19:43,006][88327] Updated weights for policy 1, policy_version 55820 (0.0007) -[2023-10-09 02:19:43,366][88327] Updated weights for policy 1, policy_version 55830 (0.0007) -[2023-10-09 02:19:43,727][88327] Updated weights for policy 1, policy_version 55840 (0.0008) -[2023-10-09 02:19:43,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 114327552. Throughput: 0: 1698.5, 1: 1704.1. Samples: 28588058. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:19:43,975][87372] Avg episode reward: [(0, '6.480'), (1, '7.190')] -[2023-10-09 02:19:44,133][88326] Updated weights for policy 0, policy_version 55812 (0.0008) -[2023-10-09 02:19:44,511][88326] Updated weights for policy 0, policy_version 55822 (0.0007) -[2023-10-09 02:19:44,879][88326] Updated weights for policy 0, policy_version 55832 (0.0008) -[2023-10-09 02:19:47,796][88327] Updated weights for policy 1, policy_version 55850 (0.0008) -[2023-10-09 02:19:48,150][88327] Updated weights for policy 1, policy_version 55860 (0.0009) -[2023-10-09 02:19:48,513][88327] Updated weights for policy 1, policy_version 55870 (0.0011) -[2023-10-09 02:19:48,971][88326] Updated weights for policy 0, policy_version 55842 (0.0008) -[2023-10-09 02:19:48,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 114393088. Throughput: 0: 1700.3, 1: 1683.6. Samples: 28608302. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:19:48,975][87372] Avg episode reward: [(0, '6.850'), (1, '7.250')] -[2023-10-09 02:19:49,357][88326] Updated weights for policy 0, policy_version 55852 (0.0009) -[2023-10-09 02:19:49,736][88326] Updated weights for policy 0, policy_version 55862 (0.0009) -[2023-10-09 02:19:50,108][88326] Updated weights for policy 0, policy_version 55872 (0.0009) -[2023-10-09 02:19:52,659][88327] Updated weights for policy 1, policy_version 55880 (0.0008) -[2023-10-09 02:19:53,030][88327] Updated weights for policy 1, policy_version 55890 (0.0009) -[2023-10-09 02:19:53,416][88327] Updated weights for policy 1, policy_version 55900 (0.0011) -[2023-10-09 02:19:53,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 114458624. Throughput: 0: 1694.8, 1: 1703.5. Samples: 28618264. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:19:53,975][87372] Avg episode reward: [(0, '6.570'), (1, '6.810')] -[2023-10-09 02:19:54,092][88326] Updated weights for policy 0, policy_version 55882 (0.0007) -[2023-10-09 02:19:54,451][88326] Updated weights for policy 0, policy_version 55892 (0.0009) -[2023-10-09 02:19:54,817][88326] Updated weights for policy 0, policy_version 55902 (0.0009) -[2023-10-09 02:19:57,340][88327] Updated weights for policy 1, policy_version 55910 (0.0010) -[2023-10-09 02:19:57,716][88327] Updated weights for policy 1, policy_version 55920 (0.0011) -[2023-10-09 02:19:58,071][88327] Updated weights for policy 1, policy_version 55930 (0.0012) -[2023-10-09 02:19:58,713][88326] Updated weights for policy 0, policy_version 55912 (0.0008) -[2023-10-09 02:19:58,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 114524160. Throughput: 0: 1697.5, 1: 1699.3. Samples: 28639016. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:19:58,974][87372] Avg episode reward: [(0, '6.830'), (1, '7.180')] -[2023-10-09 02:19:59,079][88326] Updated weights for policy 0, policy_version 55922 (0.0008) -[2023-10-09 02:19:59,448][88326] Updated weights for policy 0, policy_version 55932 (0.0007) -[2023-10-09 02:20:02,030][88327] Updated weights for policy 1, policy_version 55940 (0.0009) -[2023-10-09 02:20:02,398][88327] Updated weights for policy 1, policy_version 55950 (0.0007) -[2023-10-09 02:20:02,758][88327] Updated weights for policy 1, policy_version 55960 (0.0007) -[2023-10-09 02:20:03,533][88326] Updated weights for policy 0, policy_version 55942 (0.0008) -[2023-10-09 02:20:03,908][88326] Updated weights for policy 0, policy_version 55952 (0.0008) -[2023-10-09 02:20:03,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 114589696. Throughput: 0: 1696.2, 1: 1670.9. Samples: 28658800. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:20:03,975][87372] Avg episode reward: [(0, '6.890'), (1, '7.000')] -[2023-10-09 02:20:04,273][88326] Updated weights for policy 0, policy_version 55962 (0.0008) -[2023-10-09 02:20:06,747][88327] Updated weights for policy 1, policy_version 55970 (0.0008) -[2023-10-09 02:20:07,114][88327] Updated weights for policy 1, policy_version 55980 (0.0008) -[2023-10-09 02:20:07,482][88327] Updated weights for policy 1, policy_version 55990 (0.0009) -[2023-10-09 02:20:07,846][88327] Updated weights for policy 1, policy_version 56000 (0.0008) -[2023-10-09 02:20:08,262][88326] Updated weights for policy 0, policy_version 55972 (0.0010) -[2023-10-09 02:20:08,633][88326] Updated weights for policy 0, policy_version 55982 (0.0009) -[2023-10-09 02:20:08,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 114655232. Throughput: 0: 1697.3, 1: 1698.4. Samples: 28669244. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:20:08,975][87372] Avg episode reward: [(0, '7.030'), (1, '6.500')] -[2023-10-09 02:20:09,001][88326] Updated weights for policy 0, policy_version 55992 (0.0008) -[2023-10-09 02:20:11,761][88327] Updated weights for policy 1, policy_version 56010 (0.0007) -[2023-10-09 02:20:12,127][88327] Updated weights for policy 1, policy_version 56020 (0.0007) -[2023-10-09 02:20:12,496][88327] Updated weights for policy 1, policy_version 56030 (0.0007) -[2023-10-09 02:20:13,024][88326] Updated weights for policy 0, policy_version 56002 (0.0008) -[2023-10-09 02:20:13,392][88326] Updated weights for policy 0, policy_version 56012 (0.0008) -[2023-10-09 02:20:13,765][88326] Updated weights for policy 0, policy_version 56022 (0.0009) -[2023-10-09 02:20:13,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 114720768. Throughput: 0: 1698.4, 1: 1682.3. Samples: 28689504. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:20:13,975][87372] Avg episode reward: [(0, '6.850'), (1, '6.780')] -[2023-10-09 02:20:14,124][88326] Updated weights for policy 0, policy_version 56032 (0.0007) -[2023-10-09 02:20:16,553][88327] Updated weights for policy 1, policy_version 56040 (0.0008) -[2023-10-09 02:20:16,917][88327] Updated weights for policy 1, policy_version 56050 (0.0008) -[2023-10-09 02:20:17,286][88327] Updated weights for policy 1, policy_version 56060 (0.0007) -[2023-10-09 02:20:18,052][88326] Updated weights for policy 0, policy_version 56042 (0.0009) -[2023-10-09 02:20:18,428][88326] Updated weights for policy 0, policy_version 56052 (0.0009) -[2023-10-09 02:20:18,791][88326] Updated weights for policy 0, policy_version 56062 (0.0011) -[2023-10-09 02:20:18,974][87372] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 114819072. Throughput: 0: 1691.7, 1: 1678.7. Samples: 28709480. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:20:18,975][87372] Avg episode reward: [(0, '6.450'), (1, '6.320')] -[2023-10-09 02:20:21,250][88327] Updated weights for policy 1, policy_version 56070 (0.0009) -[2023-10-09 02:20:21,611][88327] Updated weights for policy 1, policy_version 56080 (0.0009) -[2023-10-09 02:20:21,977][88327] Updated weights for policy 1, policy_version 56090 (0.0008) -[2023-10-09 02:20:22,934][88326] Updated weights for policy 0, policy_version 56072 (0.0008) -[2023-10-09 02:20:23,303][88326] Updated weights for policy 0, policy_version 56082 (0.0007) -[2023-10-09 02:20:23,677][88326] Updated weights for policy 0, policy_version 56092 (0.0009) -[2023-10-09 02:20:23,974][87372] Fps is (10 sec: 16384.1, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 114884608. Throughput: 0: 1700.4, 1: 1695.0. Samples: 28720324. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-09 02:20:23,975][87372] Avg episode reward: [(0, '6.580'), (1, '6.770')] -[2023-10-09 02:20:25,992][88327] Updated weights for policy 1, policy_version 56100 (0.0010) -[2023-10-09 02:20:26,358][88327] Updated weights for policy 1, policy_version 56110 (0.0009) -[2023-10-09 02:20:26,715][88327] Updated weights for policy 1, policy_version 56120 (0.0010) -[2023-10-09 02:20:27,519][88326] Updated weights for policy 0, policy_version 56102 (0.0008) -[2023-10-09 02:20:27,880][88326] Updated weights for policy 0, policy_version 56112 (0.0008) -[2023-10-09 02:20:28,242][88326] Updated weights for policy 0, policy_version 56122 (0.0007) -[2023-10-09 02:20:28,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 114950144. Throughput: 0: 1705.3, 1: 1673.8. Samples: 28740118. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-09 02:20:28,975][87372] Avg episode reward: [(0, '6.900'), (1, '7.180')] -[2023-10-09 02:20:30,822][88327] Updated weights for policy 1, policy_version 56130 (0.0008) -[2023-10-09 02:20:31,194][88327] Updated weights for policy 1, policy_version 56140 (0.0009) -[2023-10-09 02:20:31,549][88327] Updated weights for policy 1, policy_version 56150 (0.0010) -[2023-10-09 02:20:31,921][88327] Updated weights for policy 1, policy_version 56160 (0.0011) -[2023-10-09 02:20:32,238][88326] Updated weights for policy 0, policy_version 56132 (0.0008) -[2023-10-09 02:20:32,615][88326] Updated weights for policy 0, policy_version 56142 (0.0010) -[2023-10-09 02:20:32,991][88326] Updated weights for policy 0, policy_version 56152 (0.0008) -[2023-10-09 02:20:33,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 115015680. Throughput: 0: 1679.7, 1: 1692.4. Samples: 28760046. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-09 02:20:33,975][87372] Avg episode reward: [(0, '7.070'), (1, '6.880')] -[2023-10-09 02:20:33,988][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000056160_57507840.pth... -[2023-10-09 02:20:33,988][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000056160_57507840.pth... -[2023-10-09 02:20:34,028][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000054592_55902208.pth -[2023-10-09 02:20:34,033][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000054560_55869440.pth -[2023-10-09 02:20:35,986][88327] Updated weights for policy 1, policy_version 56170 (0.0007) -[2023-10-09 02:20:36,347][88327] Updated weights for policy 1, policy_version 56180 (0.0010) -[2023-10-09 02:20:36,720][88327] Updated weights for policy 1, policy_version 56190 (0.0009) -[2023-10-09 02:20:36,925][88326] Updated weights for policy 0, policy_version 56162 (0.0007) -[2023-10-09 02:20:37,290][88326] Updated weights for policy 0, policy_version 56172 (0.0009) -[2023-10-09 02:20:37,651][88326] Updated weights for policy 0, policy_version 56182 (0.0007) -[2023-10-09 02:20:38,026][88326] Updated weights for policy 0, policy_version 56192 (0.0007) -[2023-10-09 02:20:38,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 115081216. Throughput: 0: 1707.5, 1: 1688.5. Samples: 28771082. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-09 02:20:38,975][87372] Avg episode reward: [(0, '7.370'), (1, '7.020')] -[2023-10-09 02:20:40,824][88327] Updated weights for policy 1, policy_version 56200 (0.0009) -[2023-10-09 02:20:41,200][88327] Updated weights for policy 1, policy_version 56210 (0.0008) -[2023-10-09 02:20:41,570][88327] Updated weights for policy 1, policy_version 56220 (0.0008) -[2023-10-09 02:20:42,180][88326] Updated weights for policy 0, policy_version 56202 (0.0009) -[2023-10-09 02:20:42,548][88326] Updated weights for policy 0, policy_version 56212 (0.0010) -[2023-10-09 02:20:42,916][88326] Updated weights for policy 0, policy_version 56222 (0.0010) -[2023-10-09 02:20:43,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 115146752. Throughput: 0: 1693.9, 1: 1677.6. Samples: 28790736. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-09 02:20:43,975][87372] Avg episode reward: [(0, '7.500'), (1, '7.130')] -[2023-10-09 02:20:43,976][88088] Saving new best policy, reward=7.500! -[2023-10-09 02:20:45,670][88327] Updated weights for policy 1, policy_version 56230 (0.0008) -[2023-10-09 02:20:46,051][88327] Updated weights for policy 1, policy_version 56240 (0.0007) -[2023-10-09 02:20:46,410][88327] Updated weights for policy 1, policy_version 56250 (0.0007) -[2023-10-09 02:20:46,953][88326] Updated weights for policy 0, policy_version 56232 (0.0007) -[2023-10-09 02:20:47,317][88326] Updated weights for policy 0, policy_version 56242 (0.0009) -[2023-10-09 02:20:47,690][88326] Updated weights for policy 0, policy_version 56252 (0.0009) -[2023-10-09 02:20:48,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 115212288. Throughput: 0: 1675.9, 1: 1699.8. Samples: 28810704. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-09 02:20:48,975][87372] Avg episode reward: [(0, '6.980'), (1, '7.290')] -[2023-10-09 02:20:50,423][88327] Updated weights for policy 1, policy_version 56260 (0.0007) -[2023-10-09 02:20:50,779][88327] Updated weights for policy 1, policy_version 56270 (0.0010) -[2023-10-09 02:20:51,140][88327] Updated weights for policy 1, policy_version 56280 (0.0010) -[2023-10-09 02:20:51,760][88326] Updated weights for policy 0, policy_version 56262 (0.0007) -[2023-10-09 02:20:52,144][88326] Updated weights for policy 0, policy_version 56272 (0.0007) -[2023-10-09 02:20:52,509][88326] Updated weights for policy 0, policy_version 56282 (0.0009) -[2023-10-09 02:20:53,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 115277824. Throughput: 0: 1706.5, 1: 1677.1. Samples: 28821506. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-09 02:20:53,974][87372] Avg episode reward: [(0, '6.940'), (1, '7.070')] -[2023-10-09 02:20:55,201][88327] Updated weights for policy 1, policy_version 56290 (0.0009) -[2023-10-09 02:20:55,560][88327] Updated weights for policy 1, policy_version 56300 (0.0010) -[2023-10-09 02:20:55,928][88327] Updated weights for policy 1, policy_version 56310 (0.0008) -[2023-10-09 02:20:56,294][88327] Updated weights for policy 1, policy_version 56320 (0.0009) -[2023-10-09 02:20:56,559][88326] Updated weights for policy 0, policy_version 56292 (0.0007) -[2023-10-09 02:20:56,924][88326] Updated weights for policy 0, policy_version 56302 (0.0007) -[2023-10-09 02:20:57,285][88326] Updated weights for policy 0, policy_version 56312 (0.0007) -[2023-10-09 02:20:58,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 115343360. Throughput: 0: 1690.1, 1: 1682.8. Samples: 28841286. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-09 02:20:58,975][87372] Avg episode reward: [(0, '6.410'), (1, '6.740')] -[2023-10-09 02:21:00,274][88327] Updated weights for policy 1, policy_version 56330 (0.0008) -[2023-10-09 02:21:00,642][88327] Updated weights for policy 1, policy_version 56340 (0.0008) -[2023-10-09 02:21:01,003][88327] Updated weights for policy 1, policy_version 56350 (0.0010) -[2023-10-09 02:21:01,202][88326] Updated weights for policy 0, policy_version 56322 (0.0010) -[2023-10-09 02:21:01,579][88326] Updated weights for policy 0, policy_version 56332 (0.0008) -[2023-10-09 02:21:01,949][88326] Updated weights for policy 0, policy_version 56342 (0.0009) -[2023-10-09 02:21:02,323][88326] Updated weights for policy 0, policy_version 56352 (0.0009) -[2023-10-09 02:21:03,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 115408896. Throughput: 0: 1684.9, 1: 1701.4. Samples: 28861866. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-10-09 02:21:03,975][87372] Avg episode reward: [(0, '7.250'), (1, '6.980')] -[2023-10-09 02:21:04,957][88327] Updated weights for policy 1, policy_version 56360 (0.0008) -[2023-10-09 02:21:05,328][88327] Updated weights for policy 1, policy_version 56370 (0.0008) -[2023-10-09 02:21:05,692][88327] Updated weights for policy 1, policy_version 56380 (0.0008) -[2023-10-09 02:21:06,274][88326] Updated weights for policy 0, policy_version 56362 (0.0007) -[2023-10-09 02:21:06,643][88326] Updated weights for policy 0, policy_version 56372 (0.0007) -[2023-10-09 02:21:07,015][88326] Updated weights for policy 0, policy_version 56382 (0.0007) -[2023-10-09 02:21:08,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 115474432. Throughput: 0: 1699.0, 1: 1673.3. Samples: 28872076. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-10-09 02:21:08,974][87372] Avg episode reward: [(0, '8.050'), (1, '6.570')] -[2023-10-09 02:21:08,975][88088] Saving new best policy, reward=8.050! -[2023-10-09 02:21:09,570][88327] Updated weights for policy 1, policy_version 56390 (0.0007) -[2023-10-09 02:21:09,927][88327] Updated weights for policy 1, policy_version 56400 (0.0008) -[2023-10-09 02:21:10,298][88327] Updated weights for policy 1, policy_version 56410 (0.0008) -[2023-10-09 02:21:11,067][88326] Updated weights for policy 0, policy_version 56392 (0.0008) -[2023-10-09 02:21:11,442][88326] Updated weights for policy 0, policy_version 56402 (0.0010) -[2023-10-09 02:21:11,808][88326] Updated weights for policy 0, policy_version 56412 (0.0010) -[2023-10-09 02:21:13,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 115539968. Throughput: 0: 1676.0, 1: 1702.3. Samples: 28892144. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-10-09 02:21:13,975][87372] Avg episode reward: [(0, '7.390'), (1, '6.520')] -[2023-10-09 02:21:14,413][88327] Updated weights for policy 1, policy_version 56420 (0.0008) -[2023-10-09 02:21:14,785][88327] Updated weights for policy 1, policy_version 56430 (0.0009) -[2023-10-09 02:21:15,145][88327] Updated weights for policy 1, policy_version 56440 (0.0009) -[2023-10-09 02:21:15,925][88326] Updated weights for policy 0, policy_version 56422 (0.0008) -[2023-10-09 02:21:16,301][88326] Updated weights for policy 0, policy_version 56432 (0.0007) -[2023-10-09 02:21:16,668][88326] Updated weights for policy 0, policy_version 56442 (0.0007) -[2023-10-09 02:21:18,974][87372] Fps is (10 sec: 13106.8, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 115605504. Throughput: 0: 1697.3, 1: 1704.5. Samples: 28913128. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-10-09 02:21:18,975][87372] Avg episode reward: [(0, '7.140'), (1, '6.770')] -[2023-10-09 02:21:19,197][88327] Updated weights for policy 1, policy_version 56450 (0.0011) -[2023-10-09 02:21:19,555][88327] Updated weights for policy 1, policy_version 56460 (0.0011) -[2023-10-09 02:21:19,927][88327] Updated weights for policy 1, policy_version 56470 (0.0011) -[2023-10-09 02:21:20,298][88327] Updated weights for policy 1, policy_version 56480 (0.0010) -[2023-10-09 02:21:20,803][88326] Updated weights for policy 0, policy_version 56452 (0.0009) -[2023-10-09 02:21:21,177][88326] Updated weights for policy 0, policy_version 56462 (0.0010) -[2023-10-09 02:21:21,543][88326] Updated weights for policy 0, policy_version 56472 (0.0007) -[2023-10-09 02:21:23,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 115671040. Throughput: 0: 1685.6, 1: 1687.9. Samples: 28922892. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-10-09 02:21:23,975][87372] Avg episode reward: [(0, '6.380'), (1, '6.850')] -[2023-10-09 02:21:24,384][88327] Updated weights for policy 1, policy_version 56490 (0.0009) -[2023-10-09 02:21:24,764][88327] Updated weights for policy 1, policy_version 56500 (0.0008) -[2023-10-09 02:21:25,125][88327] Updated weights for policy 1, policy_version 56510 (0.0009) -[2023-10-09 02:21:25,548][88326] Updated weights for policy 0, policy_version 56482 (0.0008) -[2023-10-09 02:21:25,922][88326] Updated weights for policy 0, policy_version 56492 (0.0008) -[2023-10-09 02:21:26,297][88326] Updated weights for policy 0, policy_version 56502 (0.0007) -[2023-10-09 02:21:26,660][88326] Updated weights for policy 0, policy_version 56512 (0.0008) -[2023-10-09 02:21:28,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 115736576. Throughput: 0: 1681.3, 1: 1703.1. Samples: 28943036. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-10-09 02:21:28,975][87372] Avg episode reward: [(0, '6.120'), (1, '6.720')] -[2023-10-09 02:21:29,169][88327] Updated weights for policy 1, policy_version 56520 (0.0008) -[2023-10-09 02:21:29,543][88327] Updated weights for policy 1, policy_version 56530 (0.0008) -[2023-10-09 02:21:29,924][88327] Updated weights for policy 1, policy_version 56540 (0.0008) -[2023-10-09 02:21:30,840][88326] Updated weights for policy 0, policy_version 56522 (0.0007) -[2023-10-09 02:21:31,206][88326] Updated weights for policy 0, policy_version 56532 (0.0009) -[2023-10-09 02:21:31,570][88326] Updated weights for policy 0, policy_version 56542 (0.0008) -[2023-10-09 02:21:33,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 115802112. Throughput: 0: 1697.3, 1: 1704.7. Samples: 28963794. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-10-09 02:21:33,975][87372] Avg episode reward: [(0, '6.720'), (1, '7.100')] -[2023-10-09 02:21:34,005][88327] Updated weights for policy 1, policy_version 56550 (0.0008) -[2023-10-09 02:21:34,395][88327] Updated weights for policy 1, policy_version 56560 (0.0007) -[2023-10-09 02:21:34,765][88327] Updated weights for policy 1, policy_version 56570 (0.0007) -[2023-10-09 02:21:35,609][88326] Updated weights for policy 0, policy_version 56552 (0.0009) -[2023-10-09 02:21:35,987][88326] Updated weights for policy 0, policy_version 56562 (0.0010) -[2023-10-09 02:21:36,361][88326] Updated weights for policy 0, policy_version 56572 (0.0007) -[2023-10-09 02:21:38,832][88327] Updated weights for policy 1, policy_version 56580 (0.0008) -[2023-10-09 02:21:38,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 115867648. Throughput: 0: 1675.7, 1: 1695.1. Samples: 28973192. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-10-09 02:21:38,975][87372] Avg episode reward: [(0, '7.060'), (1, '7.120')] -[2023-10-09 02:21:39,192][88327] Updated weights for policy 1, policy_version 56590 (0.0010) -[2023-10-09 02:21:39,564][88327] Updated weights for policy 1, policy_version 56600 (0.0009) -[2023-10-09 02:21:40,465][88326] Updated weights for policy 0, policy_version 56582 (0.0007) -[2023-10-09 02:21:40,830][88326] Updated weights for policy 0, policy_version 56592 (0.0009) -[2023-10-09 02:21:41,200][88326] Updated weights for policy 0, policy_version 56602 (0.0008) -[2023-10-09 02:21:43,663][88327] Updated weights for policy 1, policy_version 56610 (0.0009) -[2023-10-09 02:21:43,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 115933184. Throughput: 0: 1683.6, 1: 1703.9. Samples: 28993720. Policy #0 lag: (min: 7.0, avg: 23.0, max: 39.0) -[2023-10-09 02:21:43,975][87372] Avg episode reward: [(0, '6.730'), (1, '7.400')] -[2023-10-09 02:21:44,019][88327] Updated weights for policy 1, policy_version 56620 (0.0008) -[2023-10-09 02:21:44,386][88327] Updated weights for policy 1, policy_version 56630 (0.0009) -[2023-10-09 02:21:44,746][88327] Updated weights for policy 1, policy_version 56640 (0.0008) -[2023-10-09 02:21:45,219][88326] Updated weights for policy 0, policy_version 56612 (0.0008) -[2023-10-09 02:21:45,615][88326] Updated weights for policy 0, policy_version 56622 (0.0008) -[2023-10-09 02:21:45,981][88326] Updated weights for policy 0, policy_version 56632 (0.0009) -[2023-10-09 02:21:48,810][88327] Updated weights for policy 1, policy_version 56650 (0.0008) -[2023-10-09 02:21:48,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 115998720. Throughput: 0: 1690.8, 1: 1695.2. Samples: 29014240. Policy #0 lag: (min: 7.0, avg: 23.0, max: 39.0) -[2023-10-09 02:21:48,975][87372] Avg episode reward: [(0, '7.060'), (1, '6.980')] -[2023-10-09 02:21:49,181][88327] Updated weights for policy 1, policy_version 56660 (0.0010) -[2023-10-09 02:21:49,550][88327] Updated weights for policy 1, policy_version 56670 (0.0011) -[2023-10-09 02:21:49,856][88326] Updated weights for policy 0, policy_version 56642 (0.0008) -[2023-10-09 02:21:50,219][88326] Updated weights for policy 0, policy_version 56652 (0.0011) -[2023-10-09 02:21:50,587][88326] Updated weights for policy 0, policy_version 56662 (0.0009) -[2023-10-09 02:21:50,949][88326] Updated weights for policy 0, policy_version 56672 (0.0010) -[2023-10-09 02:21:53,491][88327] Updated weights for policy 1, policy_version 56680 (0.0010) -[2023-10-09 02:21:53,865][88327] Updated weights for policy 1, policy_version 56690 (0.0008) -[2023-10-09 02:21:53,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 116064256. Throughput: 0: 1669.5, 1: 1695.0. Samples: 29023478. Policy #0 lag: (min: 7.0, avg: 23.0, max: 39.0) -[2023-10-09 02:21:53,975][87372] Avg episode reward: [(0, '6.190'), (1, '6.880')] -[2023-10-09 02:21:54,241][88327] Updated weights for policy 1, policy_version 56700 (0.0009) -[2023-10-09 02:21:55,142][88326] Updated weights for policy 0, policy_version 56682 (0.0010) -[2023-10-09 02:21:55,510][88326] Updated weights for policy 0, policy_version 56692 (0.0009) -[2023-10-09 02:21:55,882][88326] Updated weights for policy 0, policy_version 56702 (0.0008) -[2023-10-09 02:21:58,141][88327] Updated weights for policy 1, policy_version 56710 (0.0009) -[2023-10-09 02:21:58,500][88327] Updated weights for policy 1, policy_version 56720 (0.0007) -[2023-10-09 02:21:58,862][88327] Updated weights for policy 1, policy_version 56730 (0.0008) -[2023-10-09 02:21:58,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 116129792. Throughput: 0: 1691.7, 1: 1693.4. Samples: 29044472. Policy #0 lag: (min: 7.0, avg: 23.0, max: 39.0) -[2023-10-09 02:21:58,975][87372] Avg episode reward: [(0, '6.160'), (1, '7.000')] -[2023-10-09 02:21:59,827][88326] Updated weights for policy 0, policy_version 56712 (0.0007) -[2023-10-09 02:22:00,196][88326] Updated weights for policy 0, policy_version 56722 (0.0008) -[2023-10-09 02:22:00,568][88326] Updated weights for policy 0, policy_version 56732 (0.0007) -[2023-10-09 02:22:03,022][88327] Updated weights for policy 1, policy_version 56740 (0.0008) -[2023-10-09 02:22:03,380][88327] Updated weights for policy 1, policy_version 56750 (0.0008) -[2023-10-09 02:22:03,749][88327] Updated weights for policy 1, policy_version 56760 (0.0007) -[2023-10-09 02:22:03,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 116195328. Throughput: 0: 1698.8, 1: 1681.4. Samples: 29065238. Policy #0 lag: (min: 7.0, avg: 23.0, max: 39.0) -[2023-10-09 02:22:03,975][87372] Avg episode reward: [(0, '6.520'), (1, '6.820')] -[2023-10-09 02:22:04,456][88326] Updated weights for policy 0, policy_version 56742 (0.0008) -[2023-10-09 02:22:04,828][88326] Updated weights for policy 0, policy_version 56752 (0.0008) -[2023-10-09 02:22:05,202][88326] Updated weights for policy 0, policy_version 56762 (0.0009) -[2023-10-09 02:22:07,856][88327] Updated weights for policy 1, policy_version 56770 (0.0009) -[2023-10-09 02:22:08,220][88327] Updated weights for policy 1, policy_version 56780 (0.0011) -[2023-10-09 02:22:08,583][88327] Updated weights for policy 1, policy_version 56790 (0.0010) -[2023-10-09 02:22:08,956][88327] Updated weights for policy 1, policy_version 56800 (0.0011) -[2023-10-09 02:22:08,974][87372] Fps is (10 sec: 16384.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 116293632. Throughput: 0: 1686.4, 1: 1688.9. Samples: 29074784. Policy #0 lag: (min: 7.0, avg: 23.0, max: 39.0) -[2023-10-09 02:22:08,974][87372] Avg episode reward: [(0, '6.350'), (1, '6.680')] -[2023-10-09 02:22:08,978][88326] Updated weights for policy 0, policy_version 56772 (0.0010) -[2023-10-09 02:22:09,353][88326] Updated weights for policy 0, policy_version 56782 (0.0010) -[2023-10-09 02:22:09,731][88326] Updated weights for policy 0, policy_version 56792 (0.0009) -[2023-10-09 02:22:13,040][88327] Updated weights for policy 1, policy_version 56810 (0.0007) -[2023-10-09 02:22:13,405][88327] Updated weights for policy 1, policy_version 56820 (0.0008) -[2023-10-09 02:22:13,764][88327] Updated weights for policy 1, policy_version 56830 (0.0010) -[2023-10-09 02:22:13,974][87372] Fps is (10 sec: 16383.9, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 116359168. Throughput: 0: 1703.6, 1: 1687.3. Samples: 29095624. Policy #0 lag: (min: 7.0, avg: 23.0, max: 39.0) -[2023-10-09 02:22:13,975][87372] Avg episode reward: [(0, '6.350'), (1, '6.820')] -[2023-10-09 02:22:13,995][88326] Updated weights for policy 0, policy_version 56802 (0.0008) -[2023-10-09 02:22:14,363][88326] Updated weights for policy 0, policy_version 56812 (0.0007) -[2023-10-09 02:22:14,732][88326] Updated weights for policy 0, policy_version 56822 (0.0008) -[2023-10-09 02:22:15,093][88326] Updated weights for policy 0, policy_version 56832 (0.0007) -[2023-10-09 02:22:17,917][88327] Updated weights for policy 1, policy_version 56840 (0.0009) -[2023-10-09 02:22:18,273][88327] Updated weights for policy 1, policy_version 56850 (0.0010) -[2023-10-09 02:22:18,650][88327] Updated weights for policy 1, policy_version 56860 (0.0009) -[2023-10-09 02:22:18,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 116424704. Throughput: 0: 1708.0, 1: 1673.5. Samples: 29115958. Policy #0 lag: (min: 7.0, avg: 23.0, max: 39.0) -[2023-10-09 02:22:18,975][87372] Avg episode reward: [(0, '7.200'), (1, '6.660')] -[2023-10-09 02:22:19,126][88326] Updated weights for policy 0, policy_version 56842 (0.0007) -[2023-10-09 02:22:19,508][88326] Updated weights for policy 0, policy_version 56852 (0.0009) -[2023-10-09 02:22:19,870][88326] Updated weights for policy 0, policy_version 56862 (0.0008) -[2023-10-09 02:22:22,816][88327] Updated weights for policy 1, policy_version 56870 (0.0007) -[2023-10-09 02:22:23,200][88327] Updated weights for policy 1, policy_version 56880 (0.0008) -[2023-10-09 02:22:23,572][88327] Updated weights for policy 1, policy_version 56890 (0.0009) -[2023-10-09 02:22:23,794][88326] Updated weights for policy 0, policy_version 56872 (0.0010) -[2023-10-09 02:22:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 116490240. Throughput: 0: 1698.9, 1: 1689.9. Samples: 29125690. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-09 02:22:23,975][87372] Avg episode reward: [(0, '6.860'), (1, '7.170')] -[2023-10-09 02:22:24,168][88326] Updated weights for policy 0, policy_version 56882 (0.0010) -[2023-10-09 02:22:24,535][88326] Updated weights for policy 0, policy_version 56892 (0.0009) -[2023-10-09 02:22:27,531][88327] Updated weights for policy 1, policy_version 56900 (0.0011) -[2023-10-09 02:22:27,900][88327] Updated weights for policy 1, policy_version 56910 (0.0007) -[2023-10-09 02:22:28,256][88327] Updated weights for policy 1, policy_version 56920 (0.0008) -[2023-10-09 02:22:28,475][88326] Updated weights for policy 0, policy_version 56902 (0.0009) -[2023-10-09 02:22:28,848][88326] Updated weights for policy 0, policy_version 56912 (0.0008) -[2023-10-09 02:22:28,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 116555776. Throughput: 0: 1710.8, 1: 1687.5. Samples: 29146644. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-09 02:22:28,974][87372] Avg episode reward: [(0, '7.280'), (1, '7.180')] -[2023-10-09 02:22:29,221][88326] Updated weights for policy 0, policy_version 56922 (0.0011) -[2023-10-09 02:22:32,226][88327] Updated weights for policy 1, policy_version 56930 (0.0008) -[2023-10-09 02:22:32,590][88327] Updated weights for policy 1, policy_version 56940 (0.0009) -[2023-10-09 02:22:32,955][88327] Updated weights for policy 1, policy_version 56950 (0.0008) -[2023-10-09 02:22:33,310][88327] Updated weights for policy 1, policy_version 56960 (0.0007) -[2023-10-09 02:22:33,315][88326] Updated weights for policy 0, policy_version 56932 (0.0009) -[2023-10-09 02:22:33,691][88326] Updated weights for policy 0, policy_version 56942 (0.0010) -[2023-10-09 02:22:33,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 116621312. Throughput: 0: 1714.5, 1: 1674.2. Samples: 29166730. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-09 02:22:33,975][87372] Avg episode reward: [(0, '6.910'), (1, '6.500')] -[2023-10-09 02:22:33,987][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000056960_58327040.pth... -[2023-10-09 02:22:34,023][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000055360_56688640.pth -[2023-10-09 02:22:34,058][88326] Updated weights for policy 0, policy_version 56952 (0.0007) -[2023-10-09 02:22:34,345][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000056960_58327040.pth... -[2023-10-09 02:22:34,383][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000055360_56688640.pth -[2023-10-09 02:22:37,382][88327] Updated weights for policy 1, policy_version 56970 (0.0008) -[2023-10-09 02:22:37,752][88327] Updated weights for policy 1, policy_version 56980 (0.0007) -[2023-10-09 02:22:38,087][88326] Updated weights for policy 0, policy_version 56962 (0.0010) -[2023-10-09 02:22:38,113][88327] Updated weights for policy 1, policy_version 56990 (0.0009) -[2023-10-09 02:22:38,461][88326] Updated weights for policy 0, policy_version 56972 (0.0007) -[2023-10-09 02:22:38,821][88326] Updated weights for policy 0, policy_version 56982 (0.0009) -[2023-10-09 02:22:38,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 116686848. Throughput: 0: 1714.4, 1: 1697.4. Samples: 29177010. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-09 02:22:38,975][87372] Avg episode reward: [(0, '6.430'), (1, '6.760')] -[2023-10-09 02:22:39,197][88326] Updated weights for policy 0, policy_version 56992 (0.0011) -[2023-10-09 02:22:41,973][88327] Updated weights for policy 1, policy_version 57000 (0.0008) -[2023-10-09 02:22:42,337][88327] Updated weights for policy 1, policy_version 57010 (0.0008) -[2023-10-09 02:22:42,706][88327] Updated weights for policy 1, policy_version 57020 (0.0010) -[2023-10-09 02:22:43,334][88326] Updated weights for policy 0, policy_version 57002 (0.0009) -[2023-10-09 02:22:43,706][88326] Updated weights for policy 0, policy_version 57012 (0.0009) -[2023-10-09 02:22:43,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 116752384. Throughput: 0: 1713.7, 1: 1687.0. Samples: 29197502. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-09 02:22:43,975][87372] Avg episode reward: [(0, '6.710'), (1, '6.680')] -[2023-10-09 02:22:44,073][88326] Updated weights for policy 0, policy_version 57022 (0.0008) -[2023-10-09 02:22:46,618][88327] Updated weights for policy 1, policy_version 57030 (0.0008) -[2023-10-09 02:22:46,992][88327] Updated weights for policy 1, policy_version 57040 (0.0010) -[2023-10-09 02:22:47,357][88327] Updated weights for policy 1, policy_version 57050 (0.0009) -[2023-10-09 02:22:48,089][88326] Updated weights for policy 0, policy_version 57032 (0.0008) -[2023-10-09 02:22:48,463][88326] Updated weights for policy 0, policy_version 57042 (0.0009) -[2023-10-09 02:22:48,843][88326] Updated weights for policy 0, policy_version 57052 (0.0007) -[2023-10-09 02:22:48,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 116817920. Throughput: 0: 1694.7, 1: 1680.3. Samples: 29217112. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-09 02:22:48,975][87372] Avg episode reward: [(0, '7.360'), (1, '7.170')] -[2023-10-09 02:22:51,492][88327] Updated weights for policy 1, policy_version 57060 (0.0008) -[2023-10-09 02:22:51,860][88327] Updated weights for policy 1, policy_version 57070 (0.0009) -[2023-10-09 02:22:52,220][88327] Updated weights for policy 1, policy_version 57080 (0.0007) -[2023-10-09 02:22:52,805][88326] Updated weights for policy 0, policy_version 57062 (0.0009) -[2023-10-09 02:22:53,175][88326] Updated weights for policy 0, policy_version 57072 (0.0008) -[2023-10-09 02:22:53,540][88326] Updated weights for policy 0, policy_version 57082 (0.0010) -[2023-10-09 02:22:53,974][87372] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 116916224. Throughput: 0: 1700.1, 1: 1702.7. Samples: 29227910. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-09 02:22:53,975][87372] Avg episode reward: [(0, '7.260'), (1, '7.200')] -[2023-10-09 02:22:56,247][88327] Updated weights for policy 1, policy_version 57090 (0.0009) -[2023-10-09 02:22:56,609][88327] Updated weights for policy 1, policy_version 57100 (0.0007) -[2023-10-09 02:22:56,974][88327] Updated weights for policy 1, policy_version 57110 (0.0007) -[2023-10-09 02:22:57,338][88327] Updated weights for policy 1, policy_version 57120 (0.0007) -[2023-10-09 02:22:57,498][88326] Updated weights for policy 0, policy_version 57092 (0.0008) -[2023-10-09 02:22:57,864][88326] Updated weights for policy 0, policy_version 57102 (0.0008) -[2023-10-09 02:22:58,222][88326] Updated weights for policy 0, policy_version 57112 (0.0009) -[2023-10-09 02:22:58,974][87372] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 116981760. Throughput: 0: 1701.9, 1: 1682.8. Samples: 29247938. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-09 02:22:58,975][87372] Avg episode reward: [(0, '6.970'), (1, '7.190')] -[2023-10-09 02:23:01,577][88327] Updated weights for policy 1, policy_version 57130 (0.0007) -[2023-10-09 02:23:01,939][88327] Updated weights for policy 1, policy_version 57140 (0.0009) -[2023-10-09 02:23:02,069][88326] Updated weights for policy 0, policy_version 57122 (0.0009) -[2023-10-09 02:23:02,294][88327] Updated weights for policy 1, policy_version 57150 (0.0007) -[2023-10-09 02:23:02,434][88326] Updated weights for policy 0, policy_version 57132 (0.0009) -[2023-10-09 02:23:02,814][88326] Updated weights for policy 0, policy_version 57142 (0.0009) -[2023-10-09 02:23:03,181][88326] Updated weights for policy 0, policy_version 57152 (0.0009) -[2023-10-09 02:23:03,974][87372] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 117047296. Throughput: 0: 1676.1, 1: 1691.4. Samples: 29267498. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-09 02:23:03,975][87372] Avg episode reward: [(0, '6.990'), (1, '7.140')] -[2023-10-09 02:23:06,234][88327] Updated weights for policy 1, policy_version 57160 (0.0008) -[2023-10-09 02:23:06,596][88327] Updated weights for policy 1, policy_version 57170 (0.0007) -[2023-10-09 02:23:06,963][88327] Updated weights for policy 1, policy_version 57180 (0.0008) -[2023-10-09 02:23:07,286][88326] Updated weights for policy 0, policy_version 57162 (0.0009) -[2023-10-09 02:23:07,653][88326] Updated weights for policy 0, policy_version 57172 (0.0009) -[2023-10-09 02:23:08,015][88326] Updated weights for policy 0, policy_version 57182 (0.0007) -[2023-10-09 02:23:08,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 117112832. Throughput: 0: 1699.3, 1: 1705.8. Samples: 29278920. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-09 02:23:08,975][87372] Avg episode reward: [(0, '6.310'), (1, '6.020')] -[2023-10-09 02:23:10,899][88327] Updated weights for policy 1, policy_version 57190 (0.0009) -[2023-10-09 02:23:11,265][88327] Updated weights for policy 1, policy_version 57200 (0.0007) -[2023-10-09 02:23:11,631][88327] Updated weights for policy 1, policy_version 57210 (0.0007) -[2023-10-09 02:23:11,960][88326] Updated weights for policy 0, policy_version 57192 (0.0009) -[2023-10-09 02:23:12,324][88326] Updated weights for policy 0, policy_version 57202 (0.0009) -[2023-10-09 02:23:12,697][88326] Updated weights for policy 0, policy_version 57212 (0.0008) -[2023-10-09 02:23:13,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 117178368. Throughput: 0: 1692.1, 1: 1684.1. Samples: 29298574. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-09 02:23:13,975][87372] Avg episode reward: [(0, '6.580'), (1, '6.010')] -[2023-10-09 02:23:15,713][88327] Updated weights for policy 1, policy_version 57220 (0.0008) -[2023-10-09 02:23:16,121][88327] Updated weights for policy 1, policy_version 57230 (0.0010) -[2023-10-09 02:23:16,481][88327] Updated weights for policy 1, policy_version 57240 (0.0009) -[2023-10-09 02:23:16,717][88326] Updated weights for policy 0, policy_version 57222 (0.0008) -[2023-10-09 02:23:17,084][88326] Updated weights for policy 0, policy_version 57232 (0.0008) -[2023-10-09 02:23:17,448][88326] Updated weights for policy 0, policy_version 57242 (0.0010) -[2023-10-09 02:23:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 117243904. Throughput: 0: 1677.1, 1: 1696.7. Samples: 29318552. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-09 02:23:18,975][87372] Avg episode reward: [(0, '6.750'), (1, '6.770')] -[2023-10-09 02:23:20,615][88327] Updated weights for policy 1, policy_version 57250 (0.0008) -[2023-10-09 02:23:20,980][88327] Updated weights for policy 1, policy_version 57260 (0.0010) -[2023-10-09 02:23:21,344][88327] Updated weights for policy 1, policy_version 57270 (0.0011) -[2023-10-09 02:23:21,517][88326] Updated weights for policy 0, policy_version 57252 (0.0009) -[2023-10-09 02:23:21,706][88327] Updated weights for policy 1, policy_version 57280 (0.0009) -[2023-10-09 02:23:21,910][88326] Updated weights for policy 0, policy_version 57262 (0.0008) -[2023-10-09 02:23:22,275][88326] Updated weights for policy 0, policy_version 57272 (0.0008) -[2023-10-09 02:23:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 117309440. Throughput: 0: 1704.4, 1: 1688.2. Samples: 29329676. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-09 02:23:23,975][87372] Avg episode reward: [(0, '6.660'), (1, '6.370')] -[2023-10-09 02:23:25,657][88327] Updated weights for policy 1, policy_version 57290 (0.0010) -[2023-10-09 02:23:26,017][88327] Updated weights for policy 1, policy_version 57300 (0.0010) -[2023-10-09 02:23:26,289][88326] Updated weights for policy 0, policy_version 57282 (0.0007) -[2023-10-09 02:23:26,379][88327] Updated weights for policy 1, policy_version 57310 (0.0010) -[2023-10-09 02:23:26,660][88326] Updated weights for policy 0, policy_version 57292 (0.0010) -[2023-10-09 02:23:27,032][88326] Updated weights for policy 0, policy_version 57302 (0.0010) -[2023-10-09 02:23:27,393][88326] Updated weights for policy 0, policy_version 57312 (0.0008) -[2023-10-09 02:23:28,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 117374976. Throughput: 0: 1677.1, 1: 1682.4. Samples: 29348678. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-09 02:23:28,975][87372] Avg episode reward: [(0, '6.190'), (1, '6.470')] -[2023-10-09 02:23:30,488][88327] Updated weights for policy 1, policy_version 57320 (0.0008) -[2023-10-09 02:23:30,847][88327] Updated weights for policy 1, policy_version 57330 (0.0009) -[2023-10-09 02:23:31,223][88327] Updated weights for policy 1, policy_version 57340 (0.0009) -[2023-10-09 02:23:31,503][88326] Updated weights for policy 0, policy_version 57322 (0.0008) -[2023-10-09 02:23:31,864][88326] Updated weights for policy 0, policy_version 57332 (0.0009) -[2023-10-09 02:23:32,229][88326] Updated weights for policy 0, policy_version 57342 (0.0008) -[2023-10-09 02:23:33,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 117440512. Throughput: 0: 1686.1, 1: 1696.7. Samples: 29369338. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-09 02:23:33,975][87372] Avg episode reward: [(0, '6.290'), (1, '7.010')] -[2023-10-09 02:23:35,236][88327] Updated weights for policy 1, policy_version 57350 (0.0009) -[2023-10-09 02:23:35,601][88327] Updated weights for policy 1, policy_version 57360 (0.0008) -[2023-10-09 02:23:35,974][88327] Updated weights for policy 1, policy_version 57370 (0.0007) -[2023-10-09 02:23:36,243][88326] Updated weights for policy 0, policy_version 57352 (0.0007) -[2023-10-09 02:23:36,610][88326] Updated weights for policy 0, policy_version 57362 (0.0007) -[2023-10-09 02:23:36,982][88326] Updated weights for policy 0, policy_version 57372 (0.0007) -[2023-10-09 02:23:38,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 117506048. Throughput: 0: 1702.6, 1: 1672.5. Samples: 29379788. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-09 02:23:38,975][87372] Avg episode reward: [(0, '6.380'), (1, '7.090')] -[2023-10-09 02:23:40,046][88327] Updated weights for policy 1, policy_version 57380 (0.0007) -[2023-10-09 02:23:40,417][88327] Updated weights for policy 1, policy_version 57390 (0.0009) -[2023-10-09 02:23:40,779][88327] Updated weights for policy 1, policy_version 57400 (0.0010) -[2023-10-09 02:23:41,108][88326] Updated weights for policy 0, policy_version 57382 (0.0007) -[2023-10-09 02:23:41,480][88326] Updated weights for policy 0, policy_version 57392 (0.0008) -[2023-10-09 02:23:41,848][88326] Updated weights for policy 0, policy_version 57402 (0.0009) -[2023-10-09 02:23:43,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 117571584. Throughput: 0: 1676.7, 1: 1695.3. Samples: 29399676. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-09 02:23:43,975][87372] Avg episode reward: [(0, '6.350'), (1, '7.050')] -[2023-10-09 02:23:44,744][88327] Updated weights for policy 1, policy_version 57410 (0.0008) -[2023-10-09 02:23:45,115][88327] Updated weights for policy 1, policy_version 57420 (0.0007) -[2023-10-09 02:23:45,476][88327] Updated weights for policy 1, policy_version 57430 (0.0009) -[2023-10-09 02:23:45,799][88326] Updated weights for policy 0, policy_version 57412 (0.0008) -[2023-10-09 02:23:45,839][88327] Updated weights for policy 1, policy_version 57440 (0.0010) -[2023-10-09 02:23:46,171][88326] Updated weights for policy 0, policy_version 57422 (0.0009) -[2023-10-09 02:23:46,533][88326] Updated weights for policy 0, policy_version 57432 (0.0008) -[2023-10-09 02:23:48,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 117637120. Throughput: 0: 1702.4, 1: 1703.8. Samples: 29420778. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-09 02:23:48,975][87372] Avg episode reward: [(0, '6.770'), (1, '6.820')] -[2023-10-09 02:23:49,927][88327] Updated weights for policy 1, policy_version 57450 (0.0009) -[2023-10-09 02:23:50,286][88327] Updated weights for policy 1, policy_version 57460 (0.0007) -[2023-10-09 02:23:50,564][88326] Updated weights for policy 0, policy_version 57442 (0.0008) -[2023-10-09 02:23:50,666][88327] Updated weights for policy 1, policy_version 57470 (0.0009) -[2023-10-09 02:23:50,928][88326] Updated weights for policy 0, policy_version 57452 (0.0008) -[2023-10-09 02:23:51,301][88326] Updated weights for policy 0, policy_version 57462 (0.0008) -[2023-10-09 02:23:51,669][88326] Updated weights for policy 0, policy_version 57472 (0.0008) -[2023-10-09 02:23:53,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 117702656. Throughput: 0: 1692.7, 1: 1675.8. Samples: 29430500. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-09 02:23:53,975][87372] Avg episode reward: [(0, '7.290'), (1, '6.750')] -[2023-10-09 02:23:54,653][88327] Updated weights for policy 1, policy_version 57480 (0.0010) -[2023-10-09 02:23:55,019][88327] Updated weights for policy 1, policy_version 57490 (0.0011) -[2023-10-09 02:23:55,387][88327] Updated weights for policy 1, policy_version 57500 (0.0008) -[2023-10-09 02:23:55,791][88326] Updated weights for policy 0, policy_version 57482 (0.0009) -[2023-10-09 02:23:56,159][88326] Updated weights for policy 0, policy_version 57492 (0.0007) -[2023-10-09 02:23:56,524][88326] Updated weights for policy 0, policy_version 57502 (0.0008) -[2023-10-09 02:23:58,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 117768192. Throughput: 0: 1683.7, 1: 1699.3. Samples: 29450810. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-09 02:23:58,975][87372] Avg episode reward: [(0, '6.900'), (1, '6.930')] -[2023-10-09 02:23:59,359][88327] Updated weights for policy 1, policy_version 57510 (0.0008) -[2023-10-09 02:23:59,731][88327] Updated weights for policy 1, policy_version 57520 (0.0007) -[2023-10-09 02:24:00,111][88327] Updated weights for policy 1, policy_version 57530 (0.0007) -[2023-10-09 02:24:00,493][88326] Updated weights for policy 0, policy_version 57512 (0.0009) -[2023-10-09 02:24:00,860][88326] Updated weights for policy 0, policy_version 57522 (0.0009) -[2023-10-09 02:24:01,223][88326] Updated weights for policy 0, policy_version 57532 (0.0009) -[2023-10-09 02:24:03,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 117833728. Throughput: 0: 1699.7, 1: 1709.7. Samples: 29471978. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-09 02:24:03,975][87372] Avg episode reward: [(0, '6.530'), (1, '6.520')] -[2023-10-09 02:24:04,029][88327] Updated weights for policy 1, policy_version 57540 (0.0009) -[2023-10-09 02:24:04,410][88327] Updated weights for policy 1, policy_version 57550 (0.0009) -[2023-10-09 02:24:04,776][88327] Updated weights for policy 1, policy_version 57560 (0.0008) -[2023-10-09 02:24:05,249][88326] Updated weights for policy 0, policy_version 57542 (0.0009) -[2023-10-09 02:24:05,630][88326] Updated weights for policy 0, policy_version 57552 (0.0011) -[2023-10-09 02:24:06,006][88326] Updated weights for policy 0, policy_version 57562 (0.0008) -[2023-10-09 02:24:08,713][88327] Updated weights for policy 1, policy_version 57570 (0.0007) -[2023-10-09 02:24:08,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 117899264. Throughput: 0: 1673.9, 1: 1692.9. Samples: 29481182. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-09 02:24:08,975][87372] Avg episode reward: [(0, '6.410'), (1, '6.430')] -[2023-10-09 02:24:09,073][88327] Updated weights for policy 1, policy_version 57580 (0.0007) -[2023-10-09 02:24:09,439][88327] Updated weights for policy 1, policy_version 57590 (0.0008) -[2023-10-09 02:24:09,795][88327] Updated weights for policy 1, policy_version 57600 (0.0007) -[2023-10-09 02:24:10,022][88326] Updated weights for policy 0, policy_version 57572 (0.0009) -[2023-10-09 02:24:10,394][88326] Updated weights for policy 0, policy_version 57582 (0.0008) -[2023-10-09 02:24:10,754][88326] Updated weights for policy 0, policy_version 57592 (0.0007) -[2023-10-09 02:24:13,813][88327] Updated weights for policy 1, policy_version 57610 (0.0011) -[2023-10-09 02:24:13,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 117964800. Throughput: 0: 1703.0, 1: 1708.4. Samples: 29502190. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-09 02:24:13,975][87372] Avg episode reward: [(0, '6.690'), (1, '6.440')] -[2023-10-09 02:24:14,189][88327] Updated weights for policy 1, policy_version 57620 (0.0008) -[2023-10-09 02:24:14,541][88327] Updated weights for policy 1, policy_version 57630 (0.0010) -[2023-10-09 02:24:14,785][88326] Updated weights for policy 0, policy_version 57602 (0.0008) -[2023-10-09 02:24:15,142][88326] Updated weights for policy 0, policy_version 57612 (0.0008) -[2023-10-09 02:24:15,515][88326] Updated weights for policy 0, policy_version 57622 (0.0009) -[2023-10-09 02:24:15,882][88326] Updated weights for policy 0, policy_version 57632 (0.0009) -[2023-10-09 02:24:18,663][88327] Updated weights for policy 1, policy_version 57640 (0.0010) -[2023-10-09 02:24:18,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 118030336. Throughput: 0: 1702.1, 1: 1711.4. Samples: 29522944. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-09 02:24:18,975][87372] Avg episode reward: [(0, '7.160'), (1, '6.640')] -[2023-10-09 02:24:19,033][88327] Updated weights for policy 1, policy_version 57650 (0.0010) -[2023-10-09 02:24:19,392][88327] Updated weights for policy 1, policy_version 57660 (0.0009) -[2023-10-09 02:24:19,950][88326] Updated weights for policy 0, policy_version 57642 (0.0010) -[2023-10-09 02:24:20,330][88326] Updated weights for policy 0, policy_version 57652 (0.0010) -[2023-10-09 02:24:20,700][88326] Updated weights for policy 0, policy_version 57662 (0.0010) -[2023-10-09 02:24:23,573][88327] Updated weights for policy 1, policy_version 57670 (0.0009) -[2023-10-09 02:24:23,940][88327] Updated weights for policy 1, policy_version 57680 (0.0008) -[2023-10-09 02:24:23,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 118095872. Throughput: 0: 1678.4, 1: 1707.9. Samples: 29532174. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-09 02:24:23,975][87372] Avg episode reward: [(0, '7.020'), (1, '6.710')] -[2023-10-09 02:24:24,304][88327] Updated weights for policy 1, policy_version 57690 (0.0007) -[2023-10-09 02:24:24,614][88326] Updated weights for policy 0, policy_version 57672 (0.0009) -[2023-10-09 02:24:24,978][88326] Updated weights for policy 0, policy_version 57682 (0.0008) -[2023-10-09 02:24:25,353][88326] Updated weights for policy 0, policy_version 57692 (0.0009) -[2023-10-09 02:24:28,282][88327] Updated weights for policy 1, policy_version 57700 (0.0007) -[2023-10-09 02:24:28,642][88327] Updated weights for policy 1, policy_version 57710 (0.0008) -[2023-10-09 02:24:28,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 118161408. Throughput: 0: 1705.0, 1: 1709.4. Samples: 29553322. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-09 02:24:28,975][87372] Avg episode reward: [(0, '7.210'), (1, '6.880')] -[2023-10-09 02:24:29,003][88327] Updated weights for policy 1, policy_version 57720 (0.0009) -[2023-10-09 02:24:29,342][88326] Updated weights for policy 0, policy_version 57702 (0.0007) -[2023-10-09 02:24:29,714][88326] Updated weights for policy 0, policy_version 57712 (0.0007) -[2023-10-09 02:24:30,085][88326] Updated weights for policy 0, policy_version 57722 (0.0008) -[2023-10-09 02:24:33,080][88327] Updated weights for policy 1, policy_version 57730 (0.0007) -[2023-10-09 02:24:33,436][88327] Updated weights for policy 1, policy_version 57740 (0.0008) -[2023-10-09 02:24:33,809][88327] Updated weights for policy 1, policy_version 57750 (0.0009) -[2023-10-09 02:24:33,922][88326] Updated weights for policy 0, policy_version 57732 (0.0009) -[2023-10-09 02:24:33,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 118226944. Throughput: 0: 1712.4, 1: 1701.5. Samples: 29574406. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-09 02:24:33,975][87372] Avg episode reward: [(0, '7.010'), (1, '6.690')] -[2023-10-09 02:24:34,161][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000057760_59146240.pth... -[2023-10-09 02:24:34,163][88327] Updated weights for policy 1, policy_version 57760 (0.0008) -[2023-10-09 02:24:34,193][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000056160_57507840.pth -[2023-10-09 02:24:34,281][88326] Updated weights for policy 0, policy_version 57742 (0.0009) -[2023-10-09 02:24:34,645][88326] Updated weights for policy 0, policy_version 57752 (0.0008) -[2023-10-09 02:24:34,940][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000057760_59146240.pth... -[2023-10-09 02:24:34,977][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000056160_57507840.pth -[2023-10-09 02:24:38,044][88327] Updated weights for policy 1, policy_version 57770 (0.0008) -[2023-10-09 02:24:38,415][88327] Updated weights for policy 1, policy_version 57780 (0.0010) -[2023-10-09 02:24:38,758][88326] Updated weights for policy 0, policy_version 57762 (0.0007) -[2023-10-09 02:24:38,766][88327] Updated weights for policy 1, policy_version 57790 (0.0009) -[2023-10-09 02:24:38,974][87372] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 118325248. Throughput: 0: 1699.4, 1: 1706.9. Samples: 29583784. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-09 02:24:38,975][87372] Avg episode reward: [(0, '6.640'), (1, '6.730')] -[2023-10-09 02:24:39,127][88326] Updated weights for policy 0, policy_version 57772 (0.0009) -[2023-10-09 02:24:39,508][88326] Updated weights for policy 0, policy_version 57782 (0.0009) -[2023-10-09 02:24:39,877][88326] Updated weights for policy 0, policy_version 57792 (0.0011) -[2023-10-09 02:24:42,727][88327] Updated weights for policy 1, policy_version 57800 (0.0009) -[2023-10-09 02:24:43,096][88327] Updated weights for policy 1, policy_version 57810 (0.0008) -[2023-10-09 02:24:43,466][88327] Updated weights for policy 1, policy_version 57820 (0.0009) -[2023-10-09 02:24:43,817][88326] Updated weights for policy 0, policy_version 57802 (0.0008) -[2023-10-09 02:24:43,974][87372] Fps is (10 sec: 16384.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 118390784. Throughput: 0: 1716.6, 1: 1709.8. Samples: 29605000. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-09 02:24:43,974][87372] Avg episode reward: [(0, '6.730'), (1, '7.820')] -[2023-10-09 02:24:43,975][88168] Saving new best policy, reward=7.820! -[2023-10-09 02:24:44,187][88326] Updated weights for policy 0, policy_version 57812 (0.0007) -[2023-10-09 02:24:44,563][88326] Updated weights for policy 0, policy_version 57822 (0.0008) -[2023-10-09 02:24:47,535][88327] Updated weights for policy 1, policy_version 57830 (0.0008) -[2023-10-09 02:24:47,899][88327] Updated weights for policy 1, policy_version 57840 (0.0009) -[2023-10-09 02:24:48,259][88327] Updated weights for policy 1, policy_version 57850 (0.0009) -[2023-10-09 02:24:48,738][88326] Updated weights for policy 0, policy_version 57832 (0.0007) -[2023-10-09 02:24:48,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 118456320. Throughput: 0: 1711.3, 1: 1685.2. Samples: 29624820. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-09 02:24:48,975][87372] Avg episode reward: [(0, '7.090'), (1, '7.040')] -[2023-10-09 02:24:49,104][88326] Updated weights for policy 0, policy_version 57842 (0.0007) -[2023-10-09 02:24:49,474][88326] Updated weights for policy 0, policy_version 57852 (0.0008) -[2023-10-09 02:24:52,333][88327] Updated weights for policy 1, policy_version 57860 (0.0008) -[2023-10-09 02:24:52,736][88327] Updated weights for policy 1, policy_version 57870 (0.0008) -[2023-10-09 02:24:53,103][88327] Updated weights for policy 1, policy_version 57880 (0.0007) -[2023-10-09 02:24:53,490][88326] Updated weights for policy 0, policy_version 57862 (0.0009) -[2023-10-09 02:24:53,861][88326] Updated weights for policy 0, policy_version 57872 (0.0010) -[2023-10-09 02:24:53,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 118521856. Throughput: 0: 1707.7, 1: 1707.1. Samples: 29634846. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-09 02:24:53,975][87372] Avg episode reward: [(0, '6.860'), (1, '6.900')] -[2023-10-09 02:24:54,231][88326] Updated weights for policy 0, policy_version 57882 (0.0007) -[2023-10-09 02:24:57,225][88327] Updated weights for policy 1, policy_version 57890 (0.0008) -[2023-10-09 02:24:57,594][88327] Updated weights for policy 1, policy_version 57900 (0.0008) -[2023-10-09 02:24:57,967][88327] Updated weights for policy 1, policy_version 57910 (0.0010) -[2023-10-09 02:24:58,163][88326] Updated weights for policy 0, policy_version 57892 (0.0008) -[2023-10-09 02:24:58,328][88327] Updated weights for policy 1, policy_version 57920 (0.0007) -[2023-10-09 02:24:58,554][88326] Updated weights for policy 0, policy_version 57902 (0.0009) -[2023-10-09 02:24:58,920][88326] Updated weights for policy 0, policy_version 57912 (0.0010) -[2023-10-09 02:24:58,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 118587392. Throughput: 0: 1708.5, 1: 1703.2. Samples: 29655720. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-09 02:24:58,975][87372] Avg episode reward: [(0, '7.320'), (1, '7.960')] -[2023-10-09 02:24:58,976][88168] Saving new best policy, reward=7.960! -[2023-10-09 02:25:02,424][88327] Updated weights for policy 1, policy_version 57930 (0.0010) -[2023-10-09 02:25:02,786][88327] Updated weights for policy 1, policy_version 57940 (0.0010) -[2023-10-09 02:25:02,958][88326] Updated weights for policy 0, policy_version 57922 (0.0009) -[2023-10-09 02:25:03,152][88327] Updated weights for policy 1, policy_version 57950 (0.0008) -[2023-10-09 02:25:03,329][88326] Updated weights for policy 0, policy_version 57932 (0.0008) -[2023-10-09 02:25:03,703][88326] Updated weights for policy 0, policy_version 57942 (0.0007) -[2023-10-09 02:25:03,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 118652928. Throughput: 0: 1704.9, 1: 1672.3. Samples: 29674916. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-09 02:25:03,975][87372] Avg episode reward: [(0, '7.260'), (1, '6.110')] -[2023-10-09 02:25:04,077][88326] Updated weights for policy 0, policy_version 57952 (0.0011) -[2023-10-09 02:25:07,272][88327] Updated weights for policy 1, policy_version 57960 (0.0007) -[2023-10-09 02:25:07,641][88327] Updated weights for policy 1, policy_version 57970 (0.0008) -[2023-10-09 02:25:07,964][88326] Updated weights for policy 0, policy_version 57962 (0.0007) -[2023-10-09 02:25:08,014][88327] Updated weights for policy 1, policy_version 57980 (0.0009) -[2023-10-09 02:25:08,323][88326] Updated weights for policy 0, policy_version 57972 (0.0007) -[2023-10-09 02:25:08,699][88326] Updated weights for policy 0, policy_version 57982 (0.0010) -[2023-10-09 02:25:08,974][87372] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 118751232. Throughput: 0: 1710.8, 1: 1694.4. Samples: 29685408. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-09 02:25:08,975][87372] Avg episode reward: [(0, '7.440'), (1, '6.480')] -[2023-10-09 02:25:12,167][88327] Updated weights for policy 1, policy_version 57990 (0.0008) -[2023-10-09 02:25:12,531][88327] Updated weights for policy 1, policy_version 58000 (0.0008) -[2023-10-09 02:25:12,753][88326] Updated weights for policy 0, policy_version 57992 (0.0008) -[2023-10-09 02:25:12,887][88327] Updated weights for policy 1, policy_version 58010 (0.0008) -[2023-10-09 02:25:13,122][88326] Updated weights for policy 0, policy_version 58002 (0.0008) -[2023-10-09 02:25:13,500][88326] Updated weights for policy 0, policy_version 58012 (0.0007) -[2023-10-09 02:25:13,974][87372] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 118816768. Throughput: 0: 1707.9, 1: 1685.7. Samples: 29706034. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-09 02:25:13,975][87372] Avg episode reward: [(0, '6.990'), (1, '6.850')] -[2023-10-09 02:25:16,956][88327] Updated weights for policy 1, policy_version 58020 (0.0008) -[2023-10-09 02:25:17,325][88327] Updated weights for policy 1, policy_version 58030 (0.0008) -[2023-10-09 02:25:17,572][88326] Updated weights for policy 0, policy_version 58022 (0.0008) -[2023-10-09 02:25:17,689][88327] Updated weights for policy 1, policy_version 58040 (0.0009) -[2023-10-09 02:25:17,946][88326] Updated weights for policy 0, policy_version 58032 (0.0010) -[2023-10-09 02:25:18,309][88326] Updated weights for policy 0, policy_version 58042 (0.0010) -[2023-10-09 02:25:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 118882304. Throughput: 0: 1676.4, 1: 1666.7. Samples: 29724846. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-09 02:25:18,975][87372] Avg episode reward: [(0, '6.720'), (1, '7.470')] -[2023-10-09 02:25:21,802][88327] Updated weights for policy 1, policy_version 58050 (0.0008) -[2023-10-09 02:25:22,167][88327] Updated weights for policy 1, policy_version 58060 (0.0008) -[2023-10-09 02:25:22,356][88326] Updated weights for policy 0, policy_version 58052 (0.0010) -[2023-10-09 02:25:22,537][88327] Updated weights for policy 1, policy_version 58070 (0.0008) -[2023-10-09 02:25:22,728][88326] Updated weights for policy 0, policy_version 58062 (0.0007) -[2023-10-09 02:25:22,899][88327] Updated weights for policy 1, policy_version 58080 (0.0009) -[2023-10-09 02:25:23,092][88326] Updated weights for policy 0, policy_version 58072 (0.0009) -[2023-10-09 02:25:23,974][87372] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 118947840. Throughput: 0: 1696.1, 1: 1688.4. Samples: 29736086. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-09 02:25:23,975][87372] Avg episode reward: [(0, '6.260'), (1, '7.180')] -[2023-10-09 02:25:26,794][88327] Updated weights for policy 1, policy_version 58090 (0.0010) -[2023-10-09 02:25:27,159][88327] Updated weights for policy 1, policy_version 58100 (0.0010) -[2023-10-09 02:25:27,228][88326] Updated weights for policy 0, policy_version 58082 (0.0009) -[2023-10-09 02:25:27,530][88327] Updated weights for policy 1, policy_version 58110 (0.0010) -[2023-10-09 02:25:27,604][88326] Updated weights for policy 0, policy_version 58092 (0.0009) -[2023-10-09 02:25:27,972][88326] Updated weights for policy 0, policy_version 58102 (0.0009) -[2023-10-09 02:25:28,340][88326] Updated weights for policy 0, policy_version 58112 (0.0009) -[2023-10-09 02:25:28,974][87372] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 119013376. Throughput: 0: 1689.6, 1: 1672.3. Samples: 29756282. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-09 02:25:28,974][87372] Avg episode reward: [(0, '6.430'), (1, '7.390')] -[2023-10-09 02:25:31,399][88327] Updated weights for policy 1, policy_version 58120 (0.0009) -[2023-10-09 02:25:31,764][88327] Updated weights for policy 1, policy_version 58130 (0.0009) -[2023-10-09 02:25:32,133][88327] Updated weights for policy 1, policy_version 58140 (0.0009) -[2023-10-09 02:25:32,408][88326] Updated weights for policy 0, policy_version 58122 (0.0007) -[2023-10-09 02:25:32,771][88326] Updated weights for policy 0, policy_version 58132 (0.0007) -[2023-10-09 02:25:33,136][88326] Updated weights for policy 0, policy_version 58142 (0.0007) -[2023-10-09 02:25:33,974][87372] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 119078912. Throughput: 0: 1666.2, 1: 1685.6. Samples: 29775650. Policy #0 lag: (min: 16.0, avg: 33.7, max: 48.0) -[2023-10-09 02:25:33,975][87372] Avg episode reward: [(0, '7.040'), (1, '7.460')] -[2023-10-09 02:25:36,104][88327] Updated weights for policy 1, policy_version 58150 (0.0007) -[2023-10-09 02:25:36,473][88327] Updated weights for policy 1, policy_version 58160 (0.0007) -[2023-10-09 02:25:36,834][88327] Updated weights for policy 1, policy_version 58170 (0.0007) -[2023-10-09 02:25:37,190][88326] Updated weights for policy 0, policy_version 58152 (0.0009) -[2023-10-09 02:25:37,550][88326] Updated weights for policy 0, policy_version 58162 (0.0011) -[2023-10-09 02:25:37,914][88326] Updated weights for policy 0, policy_version 58172 (0.0010) -[2023-10-09 02:25:38,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 119144448. Throughput: 0: 1694.1, 1: 1685.8. Samples: 29786942. Policy #0 lag: (min: 16.0, avg: 33.7, max: 48.0) -[2023-10-09 02:25:38,974][87372] Avg episode reward: [(0, '6.900'), (1, '7.630')] -[2023-10-09 02:25:40,767][88327] Updated weights for policy 1, policy_version 58180 (0.0008) -[2023-10-09 02:25:41,143][88327] Updated weights for policy 1, policy_version 58190 (0.0008) -[2023-10-09 02:25:41,511][88327] Updated weights for policy 1, policy_version 58200 (0.0008) -[2023-10-09 02:25:42,195][88326] Updated weights for policy 0, policy_version 58182 (0.0009) -[2023-10-09 02:25:42,558][88326] Updated weights for policy 0, policy_version 58192 (0.0007) -[2023-10-09 02:25:42,923][88326] Updated weights for policy 0, policy_version 58202 (0.0007) -[2023-10-09 02:25:43,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 119209984. Throughput: 0: 1684.6, 1: 1667.0. Samples: 29806540. Policy #0 lag: (min: 16.0, avg: 33.7, max: 48.0) -[2023-10-09 02:25:43,975][87372] Avg episode reward: [(0, '6.920'), (1, '7.010')] -[2023-10-09 02:25:45,815][88327] Updated weights for policy 1, policy_version 58210 (0.0011) -[2023-10-09 02:25:46,240][88327] Updated weights for policy 1, policy_version 58220 (0.0007) -[2023-10-09 02:25:46,597][88327] Updated weights for policy 1, policy_version 58230 (0.0008) -[2023-10-09 02:25:46,960][88327] Updated weights for policy 1, policy_version 58240 (0.0009) -[2023-10-09 02:25:47,041][88326] Updated weights for policy 0, policy_version 58212 (0.0007) -[2023-10-09 02:25:47,432][88326] Updated weights for policy 0, policy_version 58222 (0.0007) -[2023-10-09 02:25:47,792][88326] Updated weights for policy 0, policy_version 58232 (0.0008) -[2023-10-09 02:25:48,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 119275520. Throughput: 0: 1665.4, 1: 1693.6. Samples: 29826070. Policy #0 lag: (min: 16.0, avg: 33.7, max: 48.0) -[2023-10-09 02:25:48,975][87372] Avg episode reward: [(0, '7.520'), (1, '6.770')] -[2023-10-09 02:25:50,872][88327] Updated weights for policy 1, policy_version 58250 (0.0009) -[2023-10-09 02:25:51,235][88327] Updated weights for policy 1, policy_version 58260 (0.0010) -[2023-10-09 02:25:51,590][88327] Updated weights for policy 1, policy_version 58270 (0.0009) -[2023-10-09 02:25:51,727][88326] Updated weights for policy 0, policy_version 58242 (0.0007) -[2023-10-09 02:25:52,089][88326] Updated weights for policy 0, policy_version 58252 (0.0008) -[2023-10-09 02:25:52,455][88326] Updated weights for policy 0, policy_version 58262 (0.0010) -[2023-10-09 02:25:52,817][88326] Updated weights for policy 0, policy_version 58272 (0.0010) -[2023-10-09 02:25:53,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 119341056. Throughput: 0: 1687.6, 1: 1682.1. Samples: 29837046. Policy #0 lag: (min: 16.0, avg: 33.7, max: 48.0) -[2023-10-09 02:25:53,975][87372] Avg episode reward: [(0, '6.890'), (1, '6.910')] -[2023-10-09 02:25:55,753][88327] Updated weights for policy 1, policy_version 58280 (0.0010) -[2023-10-09 02:25:56,116][88327] Updated weights for policy 1, policy_version 58290 (0.0008) -[2023-10-09 02:25:56,485][88327] Updated weights for policy 1, policy_version 58300 (0.0011) -[2023-10-09 02:25:56,949][88326] Updated weights for policy 0, policy_version 58282 (0.0007) -[2023-10-09 02:25:57,322][88326] Updated weights for policy 0, policy_version 58292 (0.0007) -[2023-10-09 02:25:57,684][88326] Updated weights for policy 0, policy_version 58302 (0.0010) -[2023-10-09 02:25:58,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 119406592. Throughput: 0: 1670.7, 1: 1672.5. Samples: 29856480. Policy #0 lag: (min: 16.0, avg: 33.7, max: 48.0) -[2023-10-09 02:25:58,975][87372] Avg episode reward: [(0, '6.670'), (1, '6.300')] -[2023-10-09 02:26:00,516][88327] Updated weights for policy 1, policy_version 58310 (0.0008) -[2023-10-09 02:26:00,881][88327] Updated weights for policy 1, policy_version 58320 (0.0008) -[2023-10-09 02:26:01,244][88327] Updated weights for policy 1, policy_version 58330 (0.0009) -[2023-10-09 02:26:01,851][88326] Updated weights for policy 0, policy_version 58312 (0.0007) -[2023-10-09 02:26:02,215][88326] Updated weights for policy 0, policy_version 58322 (0.0010) -[2023-10-09 02:26:02,595][88326] Updated weights for policy 0, policy_version 58332 (0.0009) -[2023-10-09 02:26:03,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 119472128. Throughput: 0: 1678.7, 1: 1698.6. Samples: 29876824. Policy #0 lag: (min: 16.0, avg: 33.7, max: 48.0) -[2023-10-09 02:26:03,975][87372] Avg episode reward: [(0, '6.820'), (1, '6.590')] -[2023-10-09 02:26:05,129][88327] Updated weights for policy 1, policy_version 58340 (0.0008) -[2023-10-09 02:26:05,493][88327] Updated weights for policy 1, policy_version 58350 (0.0009) -[2023-10-09 02:26:05,864][88327] Updated weights for policy 1, policy_version 58360 (0.0009) -[2023-10-09 02:26:06,675][88326] Updated weights for policy 0, policy_version 58342 (0.0008) -[2023-10-09 02:26:07,042][88326] Updated weights for policy 0, policy_version 58352 (0.0007) -[2023-10-09 02:26:07,405][88326] Updated weights for policy 0, policy_version 58362 (0.0010) -[2023-10-09 02:26:08,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 119537664. Throughput: 0: 1687.3, 1: 1676.6. Samples: 29887462. Policy #0 lag: (min: 16.0, avg: 33.7, max: 48.0) -[2023-10-09 02:26:08,975][87372] Avg episode reward: [(0, '6.290'), (1, '6.810')] -[2023-10-09 02:26:09,846][88327] Updated weights for policy 1, policy_version 58370 (0.0008) -[2023-10-09 02:26:10,205][88327] Updated weights for policy 1, policy_version 58380 (0.0011) -[2023-10-09 02:26:10,571][88327] Updated weights for policy 1, policy_version 58390 (0.0009) -[2023-10-09 02:26:10,939][88327] Updated weights for policy 1, policy_version 58400 (0.0009) -[2023-10-09 02:26:11,546][88326] Updated weights for policy 0, policy_version 58372 (0.0009) -[2023-10-09 02:26:11,903][88326] Updated weights for policy 0, policy_version 58382 (0.0007) -[2023-10-09 02:26:12,273][88326] Updated weights for policy 0, policy_version 58392 (0.0007) -[2023-10-09 02:26:13,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 119603200. Throughput: 0: 1669.5, 1: 1688.2. Samples: 29907378. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-09 02:26:13,975][87372] Avg episode reward: [(0, '6.410'), (1, '6.580')] -[2023-10-09 02:26:14,985][88327] Updated weights for policy 1, policy_version 58410 (0.0009) -[2023-10-09 02:26:15,347][88327] Updated weights for policy 1, policy_version 58420 (0.0010) -[2023-10-09 02:26:15,708][88327] Updated weights for policy 1, policy_version 58430 (0.0009) -[2023-10-09 02:26:16,192][88326] Updated weights for policy 0, policy_version 58402 (0.0007) -[2023-10-09 02:26:16,573][88326] Updated weights for policy 0, policy_version 58412 (0.0008) -[2023-10-09 02:26:16,942][88326] Updated weights for policy 0, policy_version 58422 (0.0011) -[2023-10-09 02:26:17,302][88326] Updated weights for policy 0, policy_version 58432 (0.0009) -[2023-10-09 02:26:18,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 119668736. Throughput: 0: 1688.0, 1: 1694.9. Samples: 29927880. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-09 02:26:18,975][87372] Avg episode reward: [(0, '6.370'), (1, '6.990')] -[2023-10-09 02:26:19,844][88327] Updated weights for policy 1, policy_version 58440 (0.0010) -[2023-10-09 02:26:20,206][88327] Updated weights for policy 1, policy_version 58450 (0.0010) -[2023-10-09 02:26:20,580][88327] Updated weights for policy 1, policy_version 58460 (0.0009) -[2023-10-09 02:26:21,379][88326] Updated weights for policy 0, policy_version 58442 (0.0007) -[2023-10-09 02:26:21,744][88326] Updated weights for policy 0, policy_version 58452 (0.0007) -[2023-10-09 02:26:22,118][88326] Updated weights for policy 0, policy_version 58462 (0.0008) -[2023-10-09 02:26:23,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 119734272. Throughput: 0: 1684.0, 1: 1675.1. Samples: 29938104. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-09 02:26:23,975][87372] Avg episode reward: [(0, '6.650'), (1, '6.800')] -[2023-10-09 02:26:24,459][88327] Updated weights for policy 1, policy_version 58470 (0.0008) -[2023-10-09 02:26:24,822][88327] Updated weights for policy 1, policy_version 58480 (0.0008) -[2023-10-09 02:26:25,182][88327] Updated weights for policy 1, policy_version 58490 (0.0010) -[2023-10-09 02:26:25,980][88326] Updated weights for policy 0, policy_version 58472 (0.0009) -[2023-10-09 02:26:26,346][88326] Updated weights for policy 0, policy_version 58482 (0.0008) -[2023-10-09 02:26:26,720][88326] Updated weights for policy 0, policy_version 58492 (0.0007) -[2023-10-09 02:26:28,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 119799808. Throughput: 0: 1669.0, 1: 1706.0. Samples: 29958414. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-09 02:26:28,975][87372] Avg episode reward: [(0, '6.980'), (1, '7.030')] -[2023-10-09 02:26:29,243][88327] Updated weights for policy 1, policy_version 58500 (0.0008) -[2023-10-09 02:26:29,608][88327] Updated weights for policy 1, policy_version 58510 (0.0007) -[2023-10-09 02:26:29,968][88327] Updated weights for policy 1, policy_version 58520 (0.0007) -[2023-10-09 02:26:30,691][88326] Updated weights for policy 0, policy_version 58502 (0.0007) -[2023-10-09 02:26:31,059][88326] Updated weights for policy 0, policy_version 58512 (0.0008) -[2023-10-09 02:26:31,429][88326] Updated weights for policy 0, policy_version 58522 (0.0007) -[2023-10-09 02:26:33,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 119865344. Throughput: 0: 1699.9, 1: 1712.2. Samples: 29979612. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-09 02:26:33,976][88327] Updated weights for policy 1, policy_version 58530 (0.0009) -[2023-10-09 02:26:33,975][87372] Avg episode reward: [(0, '6.720'), (1, '7.090')] -[2023-10-09 02:26:33,987][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000058528_59932672.pth... -[2023-10-09 02:26:34,023][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000056960_58327040.pth -[2023-10-09 02:26:34,408][88327] Updated weights for policy 1, policy_version 58540 (0.0008) -[2023-10-09 02:26:34,773][88327] Updated weights for policy 1, policy_version 58550 (0.0010) -[2023-10-09 02:26:35,138][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000058560_59965440.pth... -[2023-10-09 02:26:35,140][88327] Updated weights for policy 1, policy_version 58560 (0.0011) -[2023-10-09 02:26:35,177][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000056960_58327040.pth -[2023-10-09 02:26:35,432][88326] Updated weights for policy 0, policy_version 58532 (0.0008) -[2023-10-09 02:26:35,826][88326] Updated weights for policy 0, policy_version 58542 (0.0009) -[2023-10-09 02:26:36,198][88326] Updated weights for policy 0, policy_version 58552 (0.0009) -[2023-10-09 02:26:38,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 119930880. Throughput: 0: 1678.2, 1: 1698.0. Samples: 29988974. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-09 02:26:38,975][87372] Avg episode reward: [(0, '6.930'), (1, '7.190')] -[2023-10-09 02:26:39,113][88327] Updated weights for policy 1, policy_version 58570 (0.0008) -[2023-10-09 02:26:39,489][88327] Updated weights for policy 1, policy_version 58580 (0.0008) -[2023-10-09 02:26:39,858][88327] Updated weights for policy 1, policy_version 58590 (0.0008) -[2023-10-09 02:26:39,974][88326] Updated weights for policy 0, policy_version 58562 (0.0008) -[2023-10-09 02:26:40,354][88326] Updated weights for policy 0, policy_version 58572 (0.0010) -[2023-10-09 02:26:40,732][88326] Updated weights for policy 0, policy_version 58582 (0.0010) -[2023-10-09 02:26:41,092][88326] Updated weights for policy 0, policy_version 58592 (0.0010) -[2023-10-09 02:26:43,875][88327] Updated weights for policy 1, policy_version 58600 (0.0010) -[2023-10-09 02:26:43,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 119996416. Throughput: 0: 1688.8, 1: 1715.5. Samples: 30009672. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-09 02:26:43,975][87372] Avg episode reward: [(0, '6.480'), (1, '6.930')] -[2023-10-09 02:26:44,232][88327] Updated weights for policy 1, policy_version 58610 (0.0009) -[2023-10-09 02:26:44,598][88327] Updated weights for policy 1, policy_version 58620 (0.0008) -[2023-10-09 02:26:45,130][88326] Updated weights for policy 0, policy_version 58602 (0.0007) -[2023-10-09 02:26:45,500][88326] Updated weights for policy 0, policy_version 58612 (0.0008) -[2023-10-09 02:26:45,866][88326] Updated weights for policy 0, policy_version 58622 (0.0007) -[2023-10-09 02:26:48,661][88327] Updated weights for policy 1, policy_version 58630 (0.0007) -[2023-10-09 02:26:48,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 120061952. Throughput: 0: 1702.7, 1: 1716.1. Samples: 30030672. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-09 02:26:48,975][87372] Avg episode reward: [(0, '6.410'), (1, '7.250')] -[2023-10-09 02:26:49,027][88327] Updated weights for policy 1, policy_version 58640 (0.0008) -[2023-10-09 02:26:49,390][88327] Updated weights for policy 1, policy_version 58650 (0.0009) -[2023-10-09 02:26:49,939][88326] Updated weights for policy 0, policy_version 58632 (0.0010) -[2023-10-09 02:26:50,301][88326] Updated weights for policy 0, policy_version 58642 (0.0011) -[2023-10-09 02:26:50,670][88326] Updated weights for policy 0, policy_version 58652 (0.0011) -[2023-10-09 02:26:53,328][88327] Updated weights for policy 1, policy_version 58660 (0.0010) -[2023-10-09 02:26:53,687][88327] Updated weights for policy 1, policy_version 58670 (0.0009) -[2023-10-09 02:26:53,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 120127488. Throughput: 0: 1675.8, 1: 1710.8. Samples: 30039856. Policy #0 lag: (min: 26.0, avg: 33.9, max: 58.0) -[2023-10-09 02:26:53,974][87372] Avg episode reward: [(0, '7.160'), (1, '6.920')] -[2023-10-09 02:26:54,049][88327] Updated weights for policy 1, policy_version 58680 (0.0008) -[2023-10-09 02:26:54,620][88326] Updated weights for policy 0, policy_version 58662 (0.0007) -[2023-10-09 02:26:54,984][88326] Updated weights for policy 0, policy_version 58672 (0.0008) -[2023-10-09 02:26:55,342][88326] Updated weights for policy 0, policy_version 58682 (0.0009) -[2023-10-09 02:26:58,173][88327] Updated weights for policy 1, policy_version 58690 (0.0008) -[2023-10-09 02:26:58,543][88327] Updated weights for policy 1, policy_version 58700 (0.0008) -[2023-10-09 02:26:58,910][88327] Updated weights for policy 1, policy_version 58710 (0.0007) -[2023-10-09 02:26:58,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 120193024. Throughput: 0: 1702.2, 1: 1709.8. Samples: 30060918. Policy #0 lag: (min: 26.0, avg: 33.9, max: 58.0) -[2023-10-09 02:26:58,975][87372] Avg episode reward: [(0, '6.680'), (1, '6.490')] -[2023-10-09 02:26:59,274][88327] Updated weights for policy 1, policy_version 58720 (0.0009) -[2023-10-09 02:26:59,333][88326] Updated weights for policy 0, policy_version 58692 (0.0008) -[2023-10-09 02:26:59,701][88326] Updated weights for policy 0, policy_version 58702 (0.0008) -[2023-10-09 02:27:00,070][88326] Updated weights for policy 0, policy_version 58712 (0.0008) -[2023-10-09 02:27:03,230][88327] Updated weights for policy 1, policy_version 58730 (0.0009) -[2023-10-09 02:27:03,598][88327] Updated weights for policy 1, policy_version 58740 (0.0009) -[2023-10-09 02:27:03,966][88327] Updated weights for policy 1, policy_version 58750 (0.0010) -[2023-10-09 02:27:03,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 120258560. Throughput: 0: 1711.7, 1: 1706.0. Samples: 30081676. Policy #0 lag: (min: 26.0, avg: 33.9, max: 58.0) -[2023-10-09 02:27:03,975][87372] Avg episode reward: [(0, '7.300'), (1, '7.030')] -[2023-10-09 02:27:04,106][88326] Updated weights for policy 0, policy_version 58722 (0.0010) -[2023-10-09 02:27:04,471][88326] Updated weights for policy 0, policy_version 58732 (0.0008) -[2023-10-09 02:27:04,849][88326] Updated weights for policy 0, policy_version 58742 (0.0009) -[2023-10-09 02:27:05,212][88326] Updated weights for policy 0, policy_version 58752 (0.0008) -[2023-10-09 02:27:07,966][88327] Updated weights for policy 1, policy_version 58760 (0.0010) -[2023-10-09 02:27:08,327][88327] Updated weights for policy 1, policy_version 58770 (0.0007) -[2023-10-09 02:27:08,691][88327] Updated weights for policy 1, policy_version 58780 (0.0007) -[2023-10-09 02:27:08,974][87372] Fps is (10 sec: 16384.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 120356864. Throughput: 0: 1687.3, 1: 1712.2. Samples: 30091082. Policy #0 lag: (min: 26.0, avg: 33.9, max: 58.0) -[2023-10-09 02:27:08,974][87372] Avg episode reward: [(0, '7.300'), (1, '7.180')] -[2023-10-09 02:27:09,223][88326] Updated weights for policy 0, policy_version 58762 (0.0008) -[2023-10-09 02:27:09,598][88326] Updated weights for policy 0, policy_version 58772 (0.0008) -[2023-10-09 02:27:09,959][88326] Updated weights for policy 0, policy_version 58782 (0.0008) -[2023-10-09 02:27:12,645][88327] Updated weights for policy 1, policy_version 58790 (0.0009) -[2023-10-09 02:27:13,012][88327] Updated weights for policy 1, policy_version 58800 (0.0009) -[2023-10-09 02:27:13,381][88327] Updated weights for policy 1, policy_version 58810 (0.0010) -[2023-10-09 02:27:13,974][87372] Fps is (10 sec: 16384.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 120422400. Throughput: 0: 1713.2, 1: 1705.9. Samples: 30112274. Policy #0 lag: (min: 26.0, avg: 33.9, max: 58.0) -[2023-10-09 02:27:13,975][87372] Avg episode reward: [(0, '6.950'), (1, '6.700')] -[2023-10-09 02:27:13,996][88326] Updated weights for policy 0, policy_version 58792 (0.0007) -[2023-10-09 02:27:14,361][88326] Updated weights for policy 0, policy_version 58802 (0.0008) -[2023-10-09 02:27:14,729][88326] Updated weights for policy 0, policy_version 58812 (0.0009) -[2023-10-09 02:27:17,408][88327] Updated weights for policy 1, policy_version 58820 (0.0009) -[2023-10-09 02:27:17,781][88327] Updated weights for policy 1, policy_version 58830 (0.0010) -[2023-10-09 02:27:18,147][88327] Updated weights for policy 1, policy_version 58840 (0.0011) -[2023-10-09 02:27:18,534][88326] Updated weights for policy 0, policy_version 58822 (0.0008) -[2023-10-09 02:27:18,901][88326] Updated weights for policy 0, policy_version 58832 (0.0008) -[2023-10-09 02:27:18,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 120487936. Throughput: 0: 1717.6, 1: 1681.2. Samples: 30132558. Policy #0 lag: (min: 26.0, avg: 33.9, max: 58.0) -[2023-10-09 02:27:18,975][87372] Avg episode reward: [(0, '6.320'), (1, '6.680')] -[2023-10-09 02:27:19,267][88326] Updated weights for policy 0, policy_version 58842 (0.0007) -[2023-10-09 02:27:22,287][88327] Updated weights for policy 1, policy_version 58850 (0.0007) -[2023-10-09 02:27:22,658][88327] Updated weights for policy 1, policy_version 58860 (0.0008) -[2023-10-09 02:27:23,030][88327] Updated weights for policy 1, policy_version 58870 (0.0011) -[2023-10-09 02:27:23,396][88327] Updated weights for policy 1, policy_version 58880 (0.0008) -[2023-10-09 02:27:23,469][88326] Updated weights for policy 0, policy_version 58852 (0.0008) -[2023-10-09 02:27:23,855][88326] Updated weights for policy 0, policy_version 58862 (0.0008) -[2023-10-09 02:27:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 120553472. Throughput: 0: 1709.0, 1: 1703.9. Samples: 30142554. Policy #0 lag: (min: 26.0, avg: 33.9, max: 58.0) -[2023-10-09 02:27:23,975][87372] Avg episode reward: [(0, '6.770'), (1, '6.360')] -[2023-10-09 02:27:24,216][88326] Updated weights for policy 0, policy_version 58872 (0.0008) -[2023-10-09 02:27:27,265][88327] Updated weights for policy 1, policy_version 58890 (0.0007) -[2023-10-09 02:27:27,631][88327] Updated weights for policy 1, policy_version 58900 (0.0009) -[2023-10-09 02:27:28,008][88327] Updated weights for policy 1, policy_version 58910 (0.0010) -[2023-10-09 02:27:28,127][88326] Updated weights for policy 0, policy_version 58882 (0.0011) -[2023-10-09 02:27:28,498][88326] Updated weights for policy 0, policy_version 58892 (0.0008) -[2023-10-09 02:27:28,866][88326] Updated weights for policy 0, policy_version 58902 (0.0009) -[2023-10-09 02:27:28,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 120619008. Throughput: 0: 1712.3, 1: 1696.6. Samples: 30163072. Policy #0 lag: (min: 26.0, avg: 33.9, max: 58.0) -[2023-10-09 02:27:28,975][87372] Avg episode reward: [(0, '6.270'), (1, '6.130')] -[2023-10-09 02:27:29,244][88326] Updated weights for policy 0, policy_version 58912 (0.0008) -[2023-10-09 02:27:32,080][88327] Updated weights for policy 1, policy_version 58920 (0.0008) -[2023-10-09 02:27:32,450][88327] Updated weights for policy 1, policy_version 58930 (0.0009) -[2023-10-09 02:27:32,822][88327] Updated weights for policy 1, policy_version 58940 (0.0008) -[2023-10-09 02:27:33,271][88326] Updated weights for policy 0, policy_version 58922 (0.0009) -[2023-10-09 02:27:33,648][88326] Updated weights for policy 0, policy_version 58932 (0.0009) -[2023-10-09 02:27:33,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 120684544. Throughput: 0: 1707.0, 1: 1668.7. Samples: 30182578. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-09 02:27:33,975][87372] Avg episode reward: [(0, '6.260'), (1, '6.260')] -[2023-10-09 02:27:34,011][88326] Updated weights for policy 0, policy_version 58942 (0.0008) -[2023-10-09 02:27:36,959][88327] Updated weights for policy 1, policy_version 58950 (0.0008) -[2023-10-09 02:27:37,320][88327] Updated weights for policy 1, policy_version 58960 (0.0010) -[2023-10-09 02:27:37,696][88327] Updated weights for policy 1, policy_version 58970 (0.0008) -[2023-10-09 02:27:37,962][88326] Updated weights for policy 0, policy_version 58952 (0.0008) -[2023-10-09 02:27:38,329][88326] Updated weights for policy 0, policy_version 58962 (0.0009) -[2023-10-09 02:27:38,696][88326] Updated weights for policy 0, policy_version 58972 (0.0008) -[2023-10-09 02:27:38,974][87372] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 120782848. Throughput: 0: 1714.4, 1: 1696.3. Samples: 30193338. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-09 02:27:38,975][87372] Avg episode reward: [(0, '6.710'), (1, '6.430')] -[2023-10-09 02:27:41,731][88327] Updated weights for policy 1, policy_version 58980 (0.0008) -[2023-10-09 02:27:42,090][88327] Updated weights for policy 1, policy_version 58990 (0.0009) -[2023-10-09 02:27:42,461][88327] Updated weights for policy 1, policy_version 59000 (0.0008) -[2023-10-09 02:27:42,651][88326] Updated weights for policy 0, policy_version 58982 (0.0007) -[2023-10-09 02:27:43,030][88326] Updated weights for policy 0, policy_version 58992 (0.0007) -[2023-10-09 02:27:43,393][88326] Updated weights for policy 0, policy_version 59002 (0.0007) -[2023-10-09 02:27:43,974][87372] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 120848384. Throughput: 0: 1717.5, 1: 1684.6. Samples: 30214012. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-09 02:27:43,974][87372] Avg episode reward: [(0, '6.290'), (1, '6.540')] -[2023-10-09 02:27:46,474][88327] Updated weights for policy 1, policy_version 59010 (0.0008) -[2023-10-09 02:27:46,836][88327] Updated weights for policy 1, policy_version 59020 (0.0009) -[2023-10-09 02:27:47,185][88326] Updated weights for policy 0, policy_version 59012 (0.0007) -[2023-10-09 02:27:47,198][88327] Updated weights for policy 1, policy_version 59030 (0.0009) -[2023-10-09 02:27:47,551][88326] Updated weights for policy 0, policy_version 59022 (0.0009) -[2023-10-09 02:27:47,564][88327] Updated weights for policy 1, policy_version 59040 (0.0008) -[2023-10-09 02:27:47,925][88326] Updated weights for policy 0, policy_version 59032 (0.0008) -[2023-10-09 02:27:48,974][87372] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 120913920. Throughput: 0: 1693.1, 1: 1676.6. Samples: 30233314. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-09 02:27:48,975][87372] Avg episode reward: [(0, '6.850'), (1, '6.960')] -[2023-10-09 02:27:51,711][88327] Updated weights for policy 1, policy_version 59050 (0.0010) -[2023-10-09 02:27:52,066][88327] Updated weights for policy 1, policy_version 59060 (0.0007) -[2023-10-09 02:27:52,085][88326] Updated weights for policy 0, policy_version 59042 (0.0009) -[2023-10-09 02:27:52,433][88327] Updated weights for policy 1, policy_version 59070 (0.0008) -[2023-10-09 02:27:52,451][88326] Updated weights for policy 0, policy_version 59052 (0.0008) -[2023-10-09 02:27:52,827][88326] Updated weights for policy 0, policy_version 59062 (0.0010) -[2023-10-09 02:27:53,190][88326] Updated weights for policy 0, policy_version 59072 (0.0010) -[2023-10-09 02:27:53,974][87372] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 120979456. Throughput: 0: 1721.1, 1: 1697.8. Samples: 30244932. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-09 02:27:53,975][87372] Avg episode reward: [(0, '6.800'), (1, '6.810')] -[2023-10-09 02:27:56,470][88327] Updated weights for policy 1, policy_version 59080 (0.0007) -[2023-10-09 02:27:56,837][88327] Updated weights for policy 1, policy_version 59090 (0.0008) -[2023-10-09 02:27:57,201][88327] Updated weights for policy 1, policy_version 59100 (0.0008) -[2023-10-09 02:27:57,284][88326] Updated weights for policy 0, policy_version 59082 (0.0010) -[2023-10-09 02:27:57,654][88326] Updated weights for policy 0, policy_version 59092 (0.0009) -[2023-10-09 02:27:58,030][88326] Updated weights for policy 0, policy_version 59102 (0.0008) -[2023-10-09 02:27:58,974][87372] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 121044992. Throughput: 0: 1708.3, 1: 1676.4. Samples: 30264584. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-09 02:27:58,974][87372] Avg episode reward: [(0, '6.680'), (1, '6.530')] -[2023-10-09 02:28:01,293][88327] Updated weights for policy 1, policy_version 59110 (0.0007) -[2023-10-09 02:28:01,662][88327] Updated weights for policy 1, policy_version 59120 (0.0009) -[2023-10-09 02:28:02,030][88327] Updated weights for policy 1, policy_version 59130 (0.0009) -[2023-10-09 02:28:02,218][88326] Updated weights for policy 0, policy_version 59112 (0.0008) -[2023-10-09 02:28:02,587][88326] Updated weights for policy 0, policy_version 59122 (0.0009) -[2023-10-09 02:28:02,966][88326] Updated weights for policy 0, policy_version 59132 (0.0007) -[2023-10-09 02:28:03,974][87372] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 121110528. Throughput: 0: 1671.7, 1: 1693.6. Samples: 30283996. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-09 02:28:03,975][87372] Avg episode reward: [(0, '6.370'), (1, '6.500')] -[2023-10-09 02:28:06,080][88327] Updated weights for policy 1, policy_version 59140 (0.0009) -[2023-10-09 02:28:06,452][88327] Updated weights for policy 1, policy_version 59150 (0.0010) -[2023-10-09 02:28:06,811][88327] Updated weights for policy 1, policy_version 59160 (0.0009) -[2023-10-09 02:28:06,956][88326] Updated weights for policy 0, policy_version 59142 (0.0007) -[2023-10-09 02:28:07,325][88326] Updated weights for policy 0, policy_version 59152 (0.0007) -[2023-10-09 02:28:07,693][88326] Updated weights for policy 0, policy_version 59162 (0.0010) -[2023-10-09 02:28:08,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 121176064. Throughput: 0: 1703.5, 1: 1698.0. Samples: 30295620. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-09 02:28:08,975][87372] Avg episode reward: [(0, '6.190'), (1, '6.800')] -[2023-10-09 02:28:10,896][88327] Updated weights for policy 1, policy_version 59170 (0.0010) -[2023-10-09 02:28:11,257][88327] Updated weights for policy 1, policy_version 59180 (0.0008) -[2023-10-09 02:28:11,621][88327] Updated weights for policy 1, policy_version 59190 (0.0008) -[2023-10-09 02:28:11,823][88326] Updated weights for policy 0, policy_version 59172 (0.0008) -[2023-10-09 02:28:11,983][88327] Updated weights for policy 1, policy_version 59200 (0.0008) -[2023-10-09 02:28:12,185][88326] Updated weights for policy 0, policy_version 59182 (0.0010) -[2023-10-09 02:28:12,556][88326] Updated weights for policy 0, policy_version 59192 (0.0009) -[2023-10-09 02:28:13,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 121241600. Throughput: 0: 1691.5, 1: 1682.0. Samples: 30314878. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-09 02:28:13,975][87372] Avg episode reward: [(0, '6.560'), (1, '6.870')] -[2023-10-09 02:28:16,002][88327] Updated weights for policy 1, policy_version 59210 (0.0009) -[2023-10-09 02:28:16,373][88327] Updated weights for policy 1, policy_version 59220 (0.0007) -[2023-10-09 02:28:16,572][88326] Updated weights for policy 0, policy_version 59202 (0.0007) -[2023-10-09 02:28:16,731][88327] Updated weights for policy 1, policy_version 59230 (0.0008) -[2023-10-09 02:28:16,933][88326] Updated weights for policy 0, policy_version 59212 (0.0008) -[2023-10-09 02:28:17,303][88326] Updated weights for policy 0, policy_version 59222 (0.0007) -[2023-10-09 02:28:17,669][88326] Updated weights for policy 0, policy_version 59232 (0.0008) -[2023-10-09 02:28:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 121307136. Throughput: 0: 1682.7, 1: 1707.2. Samples: 30335124. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-09 02:28:18,975][87372] Avg episode reward: [(0, '6.570'), (1, '7.000')] -[2023-10-09 02:28:20,635][88327] Updated weights for policy 1, policy_version 59240 (0.0008) -[2023-10-09 02:28:20,997][88327] Updated weights for policy 1, policy_version 59250 (0.0009) -[2023-10-09 02:28:21,371][88327] Updated weights for policy 1, policy_version 59260 (0.0009) -[2023-10-09 02:28:21,693][88326] Updated weights for policy 0, policy_version 59242 (0.0007) -[2023-10-09 02:28:22,057][88326] Updated weights for policy 0, policy_version 59252 (0.0007) -[2023-10-09 02:28:22,428][88326] Updated weights for policy 0, policy_version 59262 (0.0007) -[2023-10-09 02:28:23,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 121372672. Throughput: 0: 1706.1, 1: 1688.3. Samples: 30346086. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-09 02:28:23,974][87372] Avg episode reward: [(0, '7.170'), (1, '6.910')] -[2023-10-09 02:28:25,526][88327] Updated weights for policy 1, policy_version 59270 (0.0007) -[2023-10-09 02:28:25,892][88327] Updated weights for policy 1, policy_version 59280 (0.0009) -[2023-10-09 02:28:26,257][88327] Updated weights for policy 1, policy_version 59290 (0.0009) -[2023-10-09 02:28:26,466][88326] Updated weights for policy 0, policy_version 59272 (0.0009) -[2023-10-09 02:28:26,833][88326] Updated weights for policy 0, policy_version 59282 (0.0009) -[2023-10-09 02:28:27,202][88326] Updated weights for policy 0, policy_version 59292 (0.0008) -[2023-10-09 02:28:28,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 121438208. Throughput: 0: 1674.2, 1: 1694.9. Samples: 30365624. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-09 02:28:28,975][87372] Avg episode reward: [(0, '6.670'), (1, '6.910')] -[2023-10-09 02:28:30,304][88327] Updated weights for policy 1, policy_version 59300 (0.0009) -[2023-10-09 02:28:30,662][88327] Updated weights for policy 1, policy_version 59310 (0.0010) -[2023-10-09 02:28:30,852][88326] Updated weights for policy 0, policy_version 59302 (0.0010) -[2023-10-09 02:28:31,031][88327] Updated weights for policy 1, policy_version 59320 (0.0009) -[2023-10-09 02:28:31,217][88326] Updated weights for policy 0, policy_version 59312 (0.0009) -[2023-10-09 02:28:31,590][88326] Updated weights for policy 0, policy_version 59322 (0.0007) -[2023-10-09 02:28:33,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 121503744. Throughput: 0: 1697.5, 1: 1703.5. Samples: 30386358. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-09 02:28:33,975][87372] Avg episode reward: [(0, '7.000'), (1, '7.300')] -[2023-10-09 02:28:33,986][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000059328_60751872.pth... -[2023-10-09 02:28:33,986][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000059328_60751872.pth... -[2023-10-09 02:28:34,023][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000057760_59146240.pth -[2023-10-09 02:28:34,025][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000057760_59146240.pth -[2023-10-09 02:28:34,793][88327] Updated weights for policy 1, policy_version 59330 (0.0009) -[2023-10-09 02:28:35,159][88327] Updated weights for policy 1, policy_version 59340 (0.0007) -[2023-10-09 02:28:35,528][88327] Updated weights for policy 1, policy_version 59350 (0.0009) -[2023-10-09 02:28:35,672][88326] Updated weights for policy 0, policy_version 59332 (0.0009) -[2023-10-09 02:28:35,892][88327] Updated weights for policy 1, policy_version 59360 (0.0009) -[2023-10-09 02:28:36,039][88326] Updated weights for policy 0, policy_version 59342 (0.0007) -[2023-10-09 02:28:36,411][88326] Updated weights for policy 0, policy_version 59352 (0.0008) -[2023-10-09 02:28:38,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 121569280. Throughput: 0: 1686.4, 1: 1681.6. Samples: 30396496. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-09 02:28:38,975][87372] Avg episode reward: [(0, '7.050'), (1, '7.450')] -[2023-10-09 02:28:40,023][88327] Updated weights for policy 1, policy_version 59370 (0.0007) -[2023-10-09 02:28:40,388][88327] Updated weights for policy 1, policy_version 59380 (0.0009) -[2023-10-09 02:28:40,573][88326] Updated weights for policy 0, policy_version 59362 (0.0008) -[2023-10-09 02:28:40,758][88327] Updated weights for policy 1, policy_version 59390 (0.0008) -[2023-10-09 02:28:40,932][88326] Updated weights for policy 0, policy_version 59372 (0.0009) -[2023-10-09 02:28:41,294][88326] Updated weights for policy 0, policy_version 59382 (0.0010) -[2023-10-09 02:28:41,658][88326] Updated weights for policy 0, policy_version 59392 (0.0010) -[2023-10-09 02:28:43,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 121634816. Throughput: 0: 1681.5, 1: 1703.2. Samples: 30416894. Policy #0 lag: (min: 31.0, avg: 31.6, max: 48.0) -[2023-10-09 02:28:43,975][87372] Avg episode reward: [(0, '7.580'), (1, '6.700')] -[2023-10-09 02:28:44,609][88327] Updated weights for policy 1, policy_version 59400 (0.0008) -[2023-10-09 02:28:44,977][88327] Updated weights for policy 1, policy_version 59410 (0.0011) -[2023-10-09 02:28:45,345][88327] Updated weights for policy 1, policy_version 59420 (0.0010) -[2023-10-09 02:28:45,755][88326] Updated weights for policy 0, policy_version 59402 (0.0011) -[2023-10-09 02:28:46,133][88326] Updated weights for policy 0, policy_version 59412 (0.0007) -[2023-10-09 02:28:46,504][88326] Updated weights for policy 0, policy_version 59422 (0.0009) -[2023-10-09 02:28:48,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 121700352. Throughput: 0: 1706.0, 1: 1708.6. Samples: 30437656. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) -[2023-10-09 02:28:48,975][87372] Avg episode reward: [(0, '7.200'), (1, '7.340')] -[2023-10-09 02:28:49,433][88327] Updated weights for policy 1, policy_version 59430 (0.0009) -[2023-10-09 02:28:49,805][88327] Updated weights for policy 1, policy_version 59440 (0.0010) -[2023-10-09 02:28:50,178][88327] Updated weights for policy 1, policy_version 59450 (0.0011) -[2023-10-09 02:28:50,517][88326] Updated weights for policy 0, policy_version 59432 (0.0011) -[2023-10-09 02:28:50,874][88326] Updated weights for policy 0, policy_version 59442 (0.0010) -[2023-10-09 02:28:51,243][88326] Updated weights for policy 0, policy_version 59452 (0.0011) -[2023-10-09 02:28:53,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 121765888. Throughput: 0: 1677.4, 1: 1685.0. Samples: 30446930. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) -[2023-10-09 02:28:53,975][87372] Avg episode reward: [(0, '7.400'), (1, '7.320')] -[2023-10-09 02:28:54,013][88327] Updated weights for policy 1, policy_version 59460 (0.0008) -[2023-10-09 02:28:54,373][88327] Updated weights for policy 1, policy_version 59470 (0.0009) -[2023-10-09 02:28:54,733][88327] Updated weights for policy 1, policy_version 59480 (0.0009) -[2023-10-09 02:28:55,396][88326] Updated weights for policy 0, policy_version 59462 (0.0008) -[2023-10-09 02:28:55,763][88326] Updated weights for policy 0, policy_version 59472 (0.0007) -[2023-10-09 02:28:56,138][88326] Updated weights for policy 0, policy_version 59482 (0.0008) -[2023-10-09 02:28:58,869][88327] Updated weights for policy 1, policy_version 59490 (0.0009) -[2023-10-09 02:28:58,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 121831424. Throughput: 0: 1685.3, 1: 1709.8. Samples: 30467656. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) -[2023-10-09 02:28:58,975][87372] Avg episode reward: [(0, '6.580'), (1, '6.980')] -[2023-10-09 02:28:59,277][88327] Updated weights for policy 1, policy_version 59500 (0.0008) -[2023-10-09 02:28:59,646][88327] Updated weights for policy 1, policy_version 59510 (0.0007) -[2023-10-09 02:29:00,020][88327] Updated weights for policy 1, policy_version 59520 (0.0009) -[2023-10-09 02:29:00,263][88326] Updated weights for policy 0, policy_version 59492 (0.0008) -[2023-10-09 02:29:00,646][88326] Updated weights for policy 0, policy_version 59502 (0.0010) -[2023-10-09 02:29:01,012][88326] Updated weights for policy 0, policy_version 59512 (0.0008) -[2023-10-09 02:29:03,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 121896960. Throughput: 0: 1696.9, 1: 1709.7. Samples: 30488418. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) -[2023-10-09 02:29:03,975][87372] Avg episode reward: [(0, '7.020'), (1, '7.460')] -[2023-10-09 02:29:04,027][88327] Updated weights for policy 1, policy_version 59530 (0.0008) -[2023-10-09 02:29:04,385][88327] Updated weights for policy 1, policy_version 59540 (0.0007) -[2023-10-09 02:29:04,751][88327] Updated weights for policy 1, policy_version 59550 (0.0007) -[2023-10-09 02:29:04,857][88326] Updated weights for policy 0, policy_version 59522 (0.0009) -[2023-10-09 02:29:05,232][88326] Updated weights for policy 0, policy_version 59532 (0.0009) -[2023-10-09 02:29:05,598][88326] Updated weights for policy 0, policy_version 59542 (0.0008) -[2023-10-09 02:29:05,969][88326] Updated weights for policy 0, policy_version 59552 (0.0007) -[2023-10-09 02:29:08,777][88327] Updated weights for policy 1, policy_version 59560 (0.0009) -[2023-10-09 02:29:08,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 121962496. Throughput: 0: 1668.5, 1: 1701.1. Samples: 30497718. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) -[2023-10-09 02:29:08,975][87372] Avg episode reward: [(0, '6.360'), (1, '6.930')] -[2023-10-09 02:29:09,145][88327] Updated weights for policy 1, policy_version 59570 (0.0009) -[2023-10-09 02:29:09,507][88327] Updated weights for policy 1, policy_version 59580 (0.0007) -[2023-10-09 02:29:10,068][88326] Updated weights for policy 0, policy_version 59562 (0.0009) -[2023-10-09 02:29:10,431][88326] Updated weights for policy 0, policy_version 59572 (0.0008) -[2023-10-09 02:29:10,809][88326] Updated weights for policy 0, policy_version 59582 (0.0009) -[2023-10-09 02:29:13,394][88327] Updated weights for policy 1, policy_version 59590 (0.0007) -[2023-10-09 02:29:13,767][88327] Updated weights for policy 1, policy_version 59600 (0.0009) -[2023-10-09 02:29:13,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 122028032. Throughput: 0: 1690.4, 1: 1713.4. Samples: 30518794. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) -[2023-10-09 02:29:13,975][87372] Avg episode reward: [(0, '6.770'), (1, '6.690')] -[2023-10-09 02:29:14,123][88327] Updated weights for policy 1, policy_version 59610 (0.0009) -[2023-10-09 02:29:14,694][88326] Updated weights for policy 0, policy_version 59592 (0.0008) -[2023-10-09 02:29:15,059][88326] Updated weights for policy 0, policy_version 59602 (0.0010) -[2023-10-09 02:29:15,431][88326] Updated weights for policy 0, policy_version 59612 (0.0010) -[2023-10-09 02:29:18,270][88327] Updated weights for policy 1, policy_version 59620 (0.0009) -[2023-10-09 02:29:18,629][88327] Updated weights for policy 1, policy_version 59630 (0.0009) -[2023-10-09 02:29:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 122093568. Throughput: 0: 1693.6, 1: 1715.2. Samples: 30539754. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) -[2023-10-09 02:29:18,975][87372] Avg episode reward: [(0, '7.310'), (1, '6.700')] -[2023-10-09 02:29:19,002][88327] Updated weights for policy 1, policy_version 59640 (0.0007) -[2023-10-09 02:29:19,425][88326] Updated weights for policy 0, policy_version 59622 (0.0008) -[2023-10-09 02:29:19,792][88326] Updated weights for policy 0, policy_version 59632 (0.0009) -[2023-10-09 02:29:20,143][88326] Updated weights for policy 0, policy_version 59642 (0.0009) -[2023-10-09 02:29:23,082][88327] Updated weights for policy 1, policy_version 59650 (0.0009) -[2023-10-09 02:29:23,444][88327] Updated weights for policy 1, policy_version 59660 (0.0010) -[2023-10-09 02:29:23,806][88327] Updated weights for policy 1, policy_version 59670 (0.0010) -[2023-10-09 02:29:23,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 122159104. Throughput: 0: 1679.2, 1: 1707.8. Samples: 30548910. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) -[2023-10-09 02:29:23,975][87372] Avg episode reward: [(0, '6.960'), (1, '6.330')] -[2023-10-09 02:29:24,171][88327] Updated weights for policy 1, policy_version 59680 (0.0008) -[2023-10-09 02:29:24,175][88326] Updated weights for policy 0, policy_version 59652 (0.0007) -[2023-10-09 02:29:24,541][88326] Updated weights for policy 0, policy_version 59662 (0.0009) -[2023-10-09 02:29:24,904][88326] Updated weights for policy 0, policy_version 59672 (0.0009) -[2023-10-09 02:29:28,138][88327] Updated weights for policy 1, policy_version 59690 (0.0007) -[2023-10-09 02:29:28,508][88327] Updated weights for policy 1, policy_version 59700 (0.0011) -[2023-10-09 02:29:28,870][88327] Updated weights for policy 1, policy_version 59710 (0.0009) -[2023-10-09 02:29:28,904][88326] Updated weights for policy 0, policy_version 59682 (0.0010) -[2023-10-09 02:29:28,974][87372] Fps is (10 sec: 16384.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 122257408. Throughput: 0: 1695.9, 1: 1702.7. Samples: 30569828. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-09 02:29:28,975][87372] Avg episode reward: [(0, '6.870'), (1, '6.720')] -[2023-10-09 02:29:29,280][88326] Updated weights for policy 0, policy_version 59692 (0.0010) -[2023-10-09 02:29:29,646][88326] Updated weights for policy 0, policy_version 59702 (0.0010) -[2023-10-09 02:29:30,014][88326] Updated weights for policy 0, policy_version 59712 (0.0007) -[2023-10-09 02:29:32,938][88327] Updated weights for policy 1, policy_version 59720 (0.0010) -[2023-10-09 02:29:33,295][88327] Updated weights for policy 1, policy_version 59730 (0.0010) -[2023-10-09 02:29:33,658][88327] Updated weights for policy 1, policy_version 59740 (0.0010) -[2023-10-09 02:29:33,974][87372] Fps is (10 sec: 16384.0, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 122322944. Throughput: 0: 1702.0, 1: 1692.0. Samples: 30590386. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-09 02:29:33,975][87372] Avg episode reward: [(0, '7.200'), (1, '7.060')] -[2023-10-09 02:29:34,123][88326] Updated weights for policy 0, policy_version 59722 (0.0009) -[2023-10-09 02:29:34,506][88326] Updated weights for policy 0, policy_version 59732 (0.0008) -[2023-10-09 02:29:34,882][88326] Updated weights for policy 0, policy_version 59742 (0.0009) -[2023-10-09 02:29:37,546][88327] Updated weights for policy 1, policy_version 59750 (0.0008) -[2023-10-09 02:29:37,918][88327] Updated weights for policy 1, policy_version 59760 (0.0008) -[2023-10-09 02:29:38,276][88327] Updated weights for policy 1, policy_version 59770 (0.0008) -[2023-10-09 02:29:38,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 122388480. Throughput: 0: 1699.4, 1: 1705.3. Samples: 30600142. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-09 02:29:38,975][87372] Avg episode reward: [(0, '6.660'), (1, '6.420')] -[2023-10-09 02:29:38,999][88326] Updated weights for policy 0, policy_version 59752 (0.0008) -[2023-10-09 02:29:39,375][88326] Updated weights for policy 0, policy_version 59762 (0.0009) -[2023-10-09 02:29:39,750][88326] Updated weights for policy 0, policy_version 59772 (0.0010) -[2023-10-09 02:29:42,192][88327] Updated weights for policy 1, policy_version 59780 (0.0008) -[2023-10-09 02:29:42,563][88327] Updated weights for policy 1, policy_version 59790 (0.0008) -[2023-10-09 02:29:42,928][88327] Updated weights for policy 1, policy_version 59800 (0.0008) -[2023-10-09 02:29:43,848][88326] Updated weights for policy 0, policy_version 59782 (0.0009) -[2023-10-09 02:29:43,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 122454016. Throughput: 0: 1700.8, 1: 1706.1. Samples: 30620968. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-09 02:29:43,975][87372] Avg episode reward: [(0, '6.550'), (1, '6.980')] -[2023-10-09 02:29:44,225][88326] Updated weights for policy 0, policy_version 59792 (0.0009) -[2023-10-09 02:29:44,595][88326] Updated weights for policy 0, policy_version 59802 (0.0007) -[2023-10-09 02:29:46,888][88327] Updated weights for policy 1, policy_version 59810 (0.0009) -[2023-10-09 02:29:47,300][88327] Updated weights for policy 1, policy_version 59820 (0.0009) -[2023-10-09 02:29:47,666][88327] Updated weights for policy 1, policy_version 59830 (0.0007) -[2023-10-09 02:29:48,027][88327] Updated weights for policy 1, policy_version 59840 (0.0009) -[2023-10-09 02:29:48,588][88326] Updated weights for policy 0, policy_version 59812 (0.0007) -[2023-10-09 02:29:48,961][88326] Updated weights for policy 0, policy_version 59822 (0.0009) -[2023-10-09 02:29:48,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 122519552. Throughput: 0: 1709.5, 1: 1677.9. Samples: 30640850. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-09 02:29:48,975][87372] Avg episode reward: [(0, '6.710'), (1, '7.320')] -[2023-10-09 02:29:49,330][88326] Updated weights for policy 0, policy_version 59832 (0.0009) -[2023-10-09 02:29:52,036][88327] Updated weights for policy 1, policy_version 59850 (0.0010) -[2023-10-09 02:29:52,395][88327] Updated weights for policy 1, policy_version 59860 (0.0011) -[2023-10-09 02:29:52,755][88327] Updated weights for policy 1, policy_version 59870 (0.0010) -[2023-10-09 02:29:53,407][88326] Updated weights for policy 0, policy_version 59842 (0.0012) -[2023-10-09 02:29:53,782][88326] Updated weights for policy 0, policy_version 59852 (0.0010) -[2023-10-09 02:29:53,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 122585088. Throughput: 0: 1703.6, 1: 1707.6. Samples: 30651220. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-09 02:29:53,975][87372] Avg episode reward: [(0, '7.520'), (1, '7.240')] -[2023-10-09 02:29:54,150][88326] Updated weights for policy 0, policy_version 59862 (0.0008) -[2023-10-09 02:29:54,526][88326] Updated weights for policy 0, policy_version 59872 (0.0009) -[2023-10-09 02:29:56,792][88327] Updated weights for policy 1, policy_version 59880 (0.0010) -[2023-10-09 02:29:57,163][88327] Updated weights for policy 1, policy_version 59890 (0.0010) -[2023-10-09 02:29:57,526][88327] Updated weights for policy 1, policy_version 59900 (0.0010) -[2023-10-09 02:29:58,668][88326] Updated weights for policy 0, policy_version 59882 (0.0008) -[2023-10-09 02:29:58,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 122650624. Throughput: 0: 1705.4, 1: 1686.0. Samples: 30671404. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-09 02:29:58,975][87372] Avg episode reward: [(0, '6.750'), (1, '7.300')] -[2023-10-09 02:29:59,028][88326] Updated weights for policy 0, policy_version 59892 (0.0009) -[2023-10-09 02:29:59,395][88326] Updated weights for policy 0, policy_version 59902 (0.0010) -[2023-10-09 02:30:01,557][88327] Updated weights for policy 1, policy_version 59910 (0.0008) -[2023-10-09 02:30:01,910][88327] Updated weights for policy 1, policy_version 59920 (0.0008) -[2023-10-09 02:30:02,270][88327] Updated weights for policy 1, policy_version 59930 (0.0007) -[2023-10-09 02:30:03,432][88326] Updated weights for policy 0, policy_version 59912 (0.0010) -[2023-10-09 02:30:03,796][88326] Updated weights for policy 0, policy_version 59922 (0.0009) -[2023-10-09 02:30:03,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 122716160. Throughput: 0: 1699.1, 1: 1674.8. Samples: 30691580. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-09 02:30:03,975][87372] Avg episode reward: [(0, '7.210'), (1, '7.500')] -[2023-10-09 02:30:04,165][88326] Updated weights for policy 0, policy_version 59932 (0.0008) -[2023-10-09 02:30:06,262][88327] Updated weights for policy 1, policy_version 59940 (0.0008) -[2023-10-09 02:30:06,629][88327] Updated weights for policy 1, policy_version 59950 (0.0008) -[2023-10-09 02:30:07,000][88327] Updated weights for policy 1, policy_version 59960 (0.0009) -[2023-10-09 02:30:08,318][88326] Updated weights for policy 0, policy_version 59942 (0.0009) -[2023-10-09 02:30:08,677][88326] Updated weights for policy 0, policy_version 59952 (0.0009) -[2023-10-09 02:30:08,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 122781696. Throughput: 0: 1696.4, 1: 1708.9. Samples: 30702148. Policy #0 lag: (min: 31.0, avg: 41.6, max: 63.0) -[2023-10-09 02:30:08,975][87372] Avg episode reward: [(0, '6.970'), (1, '7.320')] -[2023-10-09 02:30:09,050][88326] Updated weights for policy 0, policy_version 59962 (0.0009) -[2023-10-09 02:30:11,162][88327] Updated weights for policy 1, policy_version 59970 (0.0009) -[2023-10-09 02:30:11,529][88327] Updated weights for policy 1, policy_version 59980 (0.0007) -[2023-10-09 02:30:11,897][88327] Updated weights for policy 1, policy_version 59990 (0.0009) -[2023-10-09 02:30:12,266][88327] Updated weights for policy 1, policy_version 60000 (0.0008) -[2023-10-09 02:30:13,113][88326] Updated weights for policy 0, policy_version 59972 (0.0008) -[2023-10-09 02:30:13,479][88326] Updated weights for policy 0, policy_version 59982 (0.0010) -[2023-10-09 02:30:13,860][88326] Updated weights for policy 0, policy_version 59992 (0.0008) -[2023-10-09 02:30:13,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 122847232. Throughput: 0: 1693.9, 1: 1685.8. Samples: 30721916. Policy #0 lag: (min: 31.0, avg: 41.6, max: 63.0) -[2023-10-09 02:30:13,974][87372] Avg episode reward: [(0, '7.600'), (1, '7.260')] -[2023-10-09 02:30:16,212][88327] Updated weights for policy 1, policy_version 60010 (0.0007) -[2023-10-09 02:30:16,583][88327] Updated weights for policy 1, policy_version 60020 (0.0009) -[2023-10-09 02:30:16,951][88327] Updated weights for policy 1, policy_version 60030 (0.0010) -[2023-10-09 02:30:17,559][88326] Updated weights for policy 0, policy_version 60002 (0.0010) -[2023-10-09 02:30:17,920][88326] Updated weights for policy 0, policy_version 60012 (0.0010) -[2023-10-09 02:30:18,282][88326] Updated weights for policy 0, policy_version 60022 (0.0011) -[2023-10-09 02:30:18,653][88326] Updated weights for policy 0, policy_version 60032 (0.0010) -[2023-10-09 02:30:18,974][87372] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 122945536. Throughput: 0: 1675.4, 1: 1691.2. Samples: 30741884. Policy #0 lag: (min: 31.0, avg: 41.6, max: 63.0) -[2023-10-09 02:30:18,975][87372] Avg episode reward: [(0, '6.790'), (1, '6.880')] -[2023-10-09 02:30:20,973][88327] Updated weights for policy 1, policy_version 60040 (0.0008) -[2023-10-09 02:30:21,337][88327] Updated weights for policy 1, policy_version 60050 (0.0010) -[2023-10-09 02:30:21,707][88327] Updated weights for policy 1, policy_version 60060 (0.0010) -[2023-10-09 02:30:22,773][88326] Updated weights for policy 0, policy_version 60042 (0.0008) -[2023-10-09 02:30:23,151][88326] Updated weights for policy 0, policy_version 60052 (0.0010) -[2023-10-09 02:30:23,522][88326] Updated weights for policy 0, policy_version 60062 (0.0010) -[2023-10-09 02:30:23,974][87372] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 123011072. Throughput: 0: 1692.0, 1: 1696.5. Samples: 30752624. Policy #0 lag: (min: 31.0, avg: 41.6, max: 63.0) -[2023-10-09 02:30:23,975][87372] Avg episode reward: [(0, '6.290'), (1, '6.810')] -[2023-10-09 02:30:25,552][88327] Updated weights for policy 1, policy_version 60070 (0.0009) -[2023-10-09 02:30:25,924][88327] Updated weights for policy 1, policy_version 60080 (0.0008) -[2023-10-09 02:30:26,298][88327] Updated weights for policy 1, policy_version 60090 (0.0008) -[2023-10-09 02:30:27,551][88326] Updated weights for policy 0, policy_version 60072 (0.0008) -[2023-10-09 02:30:27,913][88326] Updated weights for policy 0, policy_version 60082 (0.0007) -[2023-10-09 02:30:28,285][88326] Updated weights for policy 0, policy_version 60092 (0.0007) -[2023-10-09 02:30:28,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 123076608. Throughput: 0: 1691.5, 1: 1681.6. Samples: 30772758. Policy #0 lag: (min: 31.0, avg: 41.6, max: 63.0) -[2023-10-09 02:30:28,975][87372] Avg episode reward: [(0, '6.150'), (1, '7.030')] -[2023-10-09 02:30:30,359][88327] Updated weights for policy 1, policy_version 60100 (0.0009) -[2023-10-09 02:30:30,727][88327] Updated weights for policy 1, policy_version 60110 (0.0010) -[2023-10-09 02:30:31,094][88327] Updated weights for policy 1, policy_version 60120 (0.0010) -[2023-10-09 02:30:32,294][88326] Updated weights for policy 0, policy_version 60102 (0.0008) -[2023-10-09 02:30:32,662][88326] Updated weights for policy 0, policy_version 60112 (0.0008) -[2023-10-09 02:30:33,038][88326] Updated weights for policy 0, policy_version 60122 (0.0010) -[2023-10-09 02:30:33,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 123142144. Throughput: 0: 1660.0, 1: 1714.2. Samples: 30792690. Policy #0 lag: (min: 31.0, avg: 41.6, max: 63.0) -[2023-10-09 02:30:33,975][87372] Avg episode reward: [(0, '5.880'), (1, '6.730')] -[2023-10-09 02:30:33,984][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000060128_61571072.pth... -[2023-10-09 02:30:33,984][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000060128_61571072.pth... -[2023-10-09 02:30:34,015][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000058528_59932672.pth -[2023-10-09 02:30:34,021][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000058560_59965440.pth -[2023-10-09 02:30:35,109][88327] Updated weights for policy 1, policy_version 60130 (0.0008) -[2023-10-09 02:30:35,518][88327] Updated weights for policy 1, policy_version 60140 (0.0009) -[2023-10-09 02:30:35,888][88327] Updated weights for policy 1, policy_version 60150 (0.0011) -[2023-10-09 02:30:36,247][88327] Updated weights for policy 1, policy_version 60160 (0.0007) -[2023-10-09 02:30:37,198][88326] Updated weights for policy 0, policy_version 60132 (0.0008) -[2023-10-09 02:30:37,595][88326] Updated weights for policy 0, policy_version 60142 (0.0009) -[2023-10-09 02:30:37,962][88326] Updated weights for policy 0, policy_version 60152 (0.0008) -[2023-10-09 02:30:38,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 123207680. Throughput: 0: 1689.3, 1: 1684.0. Samples: 30803018. Policy #0 lag: (min: 31.0, avg: 41.6, max: 63.0) -[2023-10-09 02:30:38,975][87372] Avg episode reward: [(0, '6.340'), (1, '6.890')] -[2023-10-09 02:30:40,043][88327] Updated weights for policy 1, policy_version 60170 (0.0011) -[2023-10-09 02:30:40,412][88327] Updated weights for policy 1, policy_version 60180 (0.0009) -[2023-10-09 02:30:40,779][88327] Updated weights for policy 1, policy_version 60190 (0.0008) -[2023-10-09 02:30:42,025][88326] Updated weights for policy 0, policy_version 60162 (0.0008) -[2023-10-09 02:30:42,406][88326] Updated weights for policy 0, policy_version 60172 (0.0010) -[2023-10-09 02:30:42,776][88326] Updated weights for policy 0, policy_version 60182 (0.0008) -[2023-10-09 02:30:43,142][88326] Updated weights for policy 0, policy_version 60192 (0.0009) -[2023-10-09 02:30:43,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 123273216. Throughput: 0: 1675.3, 1: 1703.0. Samples: 30823430. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:30:43,975][87372] Avg episode reward: [(0, '7.010'), (1, '6.820')] -[2023-10-09 02:30:44,878][88327] Updated weights for policy 1, policy_version 60200 (0.0007) -[2023-10-09 02:30:45,243][88327] Updated weights for policy 1, policy_version 60210 (0.0007) -[2023-10-09 02:30:45,596][88327] Updated weights for policy 1, policy_version 60220 (0.0011) -[2023-10-09 02:30:47,131][88326] Updated weights for policy 0, policy_version 60202 (0.0008) -[2023-10-09 02:30:47,503][88326] Updated weights for policy 0, policy_version 60212 (0.0009) -[2023-10-09 02:30:47,868][88326] Updated weights for policy 0, policy_version 60222 (0.0008) -[2023-10-09 02:30:48,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 123338752. Throughput: 0: 1657.3, 1: 1719.6. Samples: 30843544. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:30:48,975][87372] Avg episode reward: [(0, '6.890'), (1, '7.320')] -[2023-10-09 02:30:49,721][88327] Updated weights for policy 1, policy_version 60230 (0.0008) -[2023-10-09 02:30:50,093][88327] Updated weights for policy 1, policy_version 60240 (0.0009) -[2023-10-09 02:30:50,464][88327] Updated weights for policy 1, policy_version 60250 (0.0009) -[2023-10-09 02:30:51,853][88326] Updated weights for policy 0, policy_version 60232 (0.0009) -[2023-10-09 02:30:52,215][88326] Updated weights for policy 0, policy_version 60242 (0.0009) -[2023-10-09 02:30:52,583][88326] Updated weights for policy 0, policy_version 60252 (0.0008) -[2023-10-09 02:30:53,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 123404288. Throughput: 0: 1689.8, 1: 1686.7. Samples: 30854092. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:30:53,975][87372] Avg episode reward: [(0, '6.870'), (1, '6.810')] -[2023-10-09 02:30:54,328][88327] Updated weights for policy 1, policy_version 60260 (0.0008) -[2023-10-09 02:30:54,690][88327] Updated weights for policy 1, policy_version 60270 (0.0007) -[2023-10-09 02:30:55,063][88327] Updated weights for policy 1, policy_version 60280 (0.0009) -[2023-10-09 02:30:56,761][88326] Updated weights for policy 0, policy_version 60262 (0.0010) -[2023-10-09 02:30:57,131][88326] Updated weights for policy 0, policy_version 60272 (0.0009) -[2023-10-09 02:30:57,505][88326] Updated weights for policy 0, policy_version 60282 (0.0009) -[2023-10-09 02:30:58,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 123469824. Throughput: 0: 1669.0, 1: 1717.5. Samples: 30874310. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:30:58,975][87372] Avg episode reward: [(0, '6.270'), (1, '6.980')] -[2023-10-09 02:30:59,028][88327] Updated weights for policy 1, policy_version 60290 (0.0009) -[2023-10-09 02:30:59,398][88327] Updated weights for policy 1, policy_version 60300 (0.0009) -[2023-10-09 02:30:59,763][88327] Updated weights for policy 1, policy_version 60310 (0.0010) -[2023-10-09 02:31:00,126][88327] Updated weights for policy 1, policy_version 60320 (0.0010) -[2023-10-09 02:31:01,647][88326] Updated weights for policy 0, policy_version 60292 (0.0010) -[2023-10-09 02:31:02,017][88326] Updated weights for policy 0, policy_version 60302 (0.0007) -[2023-10-09 02:31:02,396][88326] Updated weights for policy 0, policy_version 60312 (0.0008) -[2023-10-09 02:31:03,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 123535360. Throughput: 0: 1670.8, 1: 1721.8. Samples: 30894548. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:31:03,975][87372] Avg episode reward: [(0, '6.750'), (1, '6.820')] -[2023-10-09 02:31:04,212][88327] Updated weights for policy 1, policy_version 60330 (0.0009) -[2023-10-09 02:31:04,588][88327] Updated weights for policy 1, policy_version 60340 (0.0008) -[2023-10-09 02:31:04,965][88327] Updated weights for policy 1, policy_version 60350 (0.0008) -[2023-10-09 02:31:06,485][88326] Updated weights for policy 0, policy_version 60322 (0.0007) -[2023-10-09 02:31:06,856][88326] Updated weights for policy 0, policy_version 60332 (0.0007) -[2023-10-09 02:31:07,221][88326] Updated weights for policy 0, policy_version 60342 (0.0008) -[2023-10-09 02:31:07,586][88326] Updated weights for policy 0, policy_version 60352 (0.0007) -[2023-10-09 02:31:08,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 123600896. Throughput: 0: 1685.7, 1: 1700.7. Samples: 30905012. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:31:08,975][87372] Avg episode reward: [(0, '6.270'), (1, '7.190')] -[2023-10-09 02:31:09,081][88327] Updated weights for policy 1, policy_version 60360 (0.0010) -[2023-10-09 02:31:09,446][88327] Updated weights for policy 1, policy_version 60370 (0.0007) -[2023-10-09 02:31:09,813][88327] Updated weights for policy 1, policy_version 60380 (0.0007) -[2023-10-09 02:31:11,594][88326] Updated weights for policy 0, policy_version 60362 (0.0007) -[2023-10-09 02:31:11,958][88326] Updated weights for policy 0, policy_version 60372 (0.0010) -[2023-10-09 02:31:12,323][88326] Updated weights for policy 0, policy_version 60382 (0.0008) -[2023-10-09 02:31:13,831][88327] Updated weights for policy 1, policy_version 60390 (0.0007) -[2023-10-09 02:31:13,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 123666432. Throughput: 0: 1667.2, 1: 1712.9. Samples: 30924864. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:31:13,974][87372] Avg episode reward: [(0, '6.070'), (1, '7.160')] -[2023-10-09 02:31:14,190][88327] Updated weights for policy 1, policy_version 60400 (0.0007) -[2023-10-09 02:31:14,563][88327] Updated weights for policy 1, policy_version 60410 (0.0009) -[2023-10-09 02:31:16,386][88326] Updated weights for policy 0, policy_version 60392 (0.0008) -[2023-10-09 02:31:16,761][88326] Updated weights for policy 0, policy_version 60402 (0.0008) -[2023-10-09 02:31:17,122][88326] Updated weights for policy 0, policy_version 60412 (0.0008) -[2023-10-09 02:31:18,483][88327] Updated weights for policy 1, policy_version 60420 (0.0009) -[2023-10-09 02:31:18,850][88327] Updated weights for policy 1, policy_version 60430 (0.0008) -[2023-10-09 02:31:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 123731968. Throughput: 0: 1689.4, 1: 1713.6. Samples: 30945822. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:31:18,975][87372] Avg episode reward: [(0, '6.680'), (1, '7.210')] -[2023-10-09 02:31:19,216][88327] Updated weights for policy 1, policy_version 60440 (0.0010) -[2023-10-09 02:31:21,068][88326] Updated weights for policy 0, policy_version 60422 (0.0008) -[2023-10-09 02:31:21,425][88326] Updated weights for policy 0, policy_version 60432 (0.0008) -[2023-10-09 02:31:21,794][88326] Updated weights for policy 0, policy_version 60442 (0.0008) -[2023-10-09 02:31:23,281][88327] Updated weights for policy 1, policy_version 60450 (0.0011) -[2023-10-09 02:31:23,697][88327] Updated weights for policy 1, policy_version 60460 (0.0008) -[2023-10-09 02:31:23,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 123797504. Throughput: 0: 1683.0, 1: 1713.2. Samples: 30955846. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-10-09 02:31:23,975][87372] Avg episode reward: [(0, '5.840'), (1, '7.130')] -[2023-10-09 02:31:24,065][88327] Updated weights for policy 1, policy_version 60470 (0.0009) -[2023-10-09 02:31:24,437][88327] Updated weights for policy 1, policy_version 60480 (0.0009) -[2023-10-09 02:31:25,799][88326] Updated weights for policy 0, policy_version 60452 (0.0007) -[2023-10-09 02:31:26,192][88326] Updated weights for policy 0, policy_version 60462 (0.0010) -[2023-10-09 02:31:26,555][88326] Updated weights for policy 0, policy_version 60472 (0.0008) -[2023-10-09 02:31:28,559][88327] Updated weights for policy 1, policy_version 60490 (0.0009) -[2023-10-09 02:31:28,929][88327] Updated weights for policy 1, policy_version 60500 (0.0007) -[2023-10-09 02:31:28,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 123863040. Throughput: 0: 1675.5, 1: 1708.2. Samples: 30975696. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-10-09 02:31:28,974][87372] Avg episode reward: [(0, '6.440'), (1, '7.460')] -[2023-10-09 02:31:29,296][88327] Updated weights for policy 1, policy_version 60510 (0.0007) -[2023-10-09 02:31:30,562][88326] Updated weights for policy 0, policy_version 60482 (0.0010) -[2023-10-09 02:31:30,921][88326] Updated weights for policy 0, policy_version 60492 (0.0010) -[2023-10-09 02:31:31,294][88326] Updated weights for policy 0, policy_version 60502 (0.0010) -[2023-10-09 02:31:31,657][88326] Updated weights for policy 0, policy_version 60512 (0.0011) -[2023-10-09 02:31:33,144][88327] Updated weights for policy 1, policy_version 60520 (0.0010) -[2023-10-09 02:31:33,520][88327] Updated weights for policy 1, policy_version 60530 (0.0010) -[2023-10-09 02:31:33,885][88327] Updated weights for policy 1, policy_version 60540 (0.0008) -[2023-10-09 02:31:33,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 123928576. Throughput: 0: 1693.9, 1: 1704.1. Samples: 30996452. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-10-09 02:31:33,975][87372] Avg episode reward: [(0, '6.880'), (1, '7.120')] -[2023-10-09 02:31:35,592][88326] Updated weights for policy 0, policy_version 60522 (0.0010) -[2023-10-09 02:31:35,958][88326] Updated weights for policy 0, policy_version 60532 (0.0010) -[2023-10-09 02:31:36,324][88326] Updated weights for policy 0, policy_version 60542 (0.0009) -[2023-10-09 02:31:37,875][88327] Updated weights for policy 1, policy_version 60550 (0.0008) -[2023-10-09 02:31:38,243][88327] Updated weights for policy 1, policy_version 60560 (0.0008) -[2023-10-09 02:31:38,617][88327] Updated weights for policy 1, policy_version 60570 (0.0010) -[2023-10-09 02:31:38,974][87372] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 124026880. Throughput: 0: 1671.7, 1: 1711.8. Samples: 31006352. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-10-09 02:31:38,975][87372] Avg episode reward: [(0, '6.730'), (1, '7.010')] -[2023-10-09 02:31:40,431][88326] Updated weights for policy 0, policy_version 60552 (0.0010) -[2023-10-09 02:31:40,808][88326] Updated weights for policy 0, policy_version 60562 (0.0008) -[2023-10-09 02:31:41,170][88326] Updated weights for policy 0, policy_version 60572 (0.0009) -[2023-10-09 02:31:42,614][88327] Updated weights for policy 1, policy_version 60580 (0.0007) -[2023-10-09 02:31:42,981][88327] Updated weights for policy 1, policy_version 60590 (0.0008) -[2023-10-09 02:31:43,355][88327] Updated weights for policy 1, policy_version 60600 (0.0008) -[2023-10-09 02:31:43,974][87372] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 124092416. Throughput: 0: 1687.5, 1: 1705.3. Samples: 31026986. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-10-09 02:31:43,975][87372] Avg episode reward: [(0, '7.180'), (1, '7.220')] -[2023-10-09 02:31:45,228][88326] Updated weights for policy 0, policy_version 60582 (0.0008) -[2023-10-09 02:31:45,593][88326] Updated weights for policy 0, policy_version 60592 (0.0009) -[2023-10-09 02:31:45,961][88326] Updated weights for policy 0, policy_version 60602 (0.0008) -[2023-10-09 02:31:47,405][88327] Updated weights for policy 1, policy_version 60610 (0.0010) -[2023-10-09 02:31:47,769][88327] Updated weights for policy 1, policy_version 60620 (0.0009) -[2023-10-09 02:31:48,145][88327] Updated weights for policy 1, policy_version 60630 (0.0009) -[2023-10-09 02:31:48,509][88327] Updated weights for policy 1, policy_version 60640 (0.0008) -[2023-10-09 02:31:48,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 124157952. Throughput: 0: 1706.3, 1: 1691.0. Samples: 31047426. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-10-09 02:31:48,975][87372] Avg episode reward: [(0, '7.720'), (1, '7.150')] -[2023-10-09 02:31:49,796][88326] Updated weights for policy 0, policy_version 60612 (0.0008) -[2023-10-09 02:31:50,153][88326] Updated weights for policy 0, policy_version 60622 (0.0009) -[2023-10-09 02:31:50,533][88326] Updated weights for policy 0, policy_version 60632 (0.0010) -[2023-10-09 02:31:52,727][88327] Updated weights for policy 1, policy_version 60650 (0.0008) -[2023-10-09 02:31:53,086][88327] Updated weights for policy 1, policy_version 60660 (0.0007) -[2023-10-09 02:31:53,458][88327] Updated weights for policy 1, policy_version 60670 (0.0007) -[2023-10-09 02:31:53,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 124223488. Throughput: 0: 1676.8, 1: 1711.6. Samples: 31057492. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-10-09 02:31:53,975][87372] Avg episode reward: [(0, '6.700'), (1, '6.840')] -[2023-10-09 02:31:54,713][88326] Updated weights for policy 0, policy_version 60642 (0.0009) -[2023-10-09 02:31:55,075][88326] Updated weights for policy 0, policy_version 60652 (0.0010) -[2023-10-09 02:31:55,442][88326] Updated weights for policy 0, policy_version 60662 (0.0007) -[2023-10-09 02:31:55,811][88326] Updated weights for policy 0, policy_version 60672 (0.0008) -[2023-10-09 02:31:57,515][88327] Updated weights for policy 1, policy_version 60680 (0.0008) -[2023-10-09 02:31:57,874][88327] Updated weights for policy 1, policy_version 60690 (0.0010) -[2023-10-09 02:31:58,242][88327] Updated weights for policy 1, policy_version 60700 (0.0009) -[2023-10-09 02:31:58,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 124289024. Throughput: 0: 1701.2, 1: 1712.7. Samples: 31078490. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-10-09 02:31:58,975][87372] Avg episode reward: [(0, '7.130'), (1, '6.980')] -[2023-10-09 02:31:59,818][88326] Updated weights for policy 0, policy_version 60682 (0.0008) -[2023-10-09 02:32:00,186][88326] Updated weights for policy 0, policy_version 60692 (0.0008) -[2023-10-09 02:32:00,555][88326] Updated weights for policy 0, policy_version 60702 (0.0007) -[2023-10-09 02:32:02,355][88327] Updated weights for policy 1, policy_version 60710 (0.0009) -[2023-10-09 02:32:02,713][88327] Updated weights for policy 1, policy_version 60720 (0.0010) -[2023-10-09 02:32:03,076][88327] Updated weights for policy 1, policy_version 60730 (0.0011) -[2023-10-09 02:32:03,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 124354560. Throughput: 0: 1706.1, 1: 1682.7. Samples: 31098316. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-09 02:32:03,975][87372] Avg episode reward: [(0, '6.670'), (1, '6.410')] -[2023-10-09 02:32:04,539][88326] Updated weights for policy 0, policy_version 60712 (0.0009) -[2023-10-09 02:32:04,906][88326] Updated weights for policy 0, policy_version 60722 (0.0009) -[2023-10-09 02:32:05,272][88326] Updated weights for policy 0, policy_version 60732 (0.0008) -[2023-10-09 02:32:07,041][88327] Updated weights for policy 1, policy_version 60740 (0.0008) -[2023-10-09 02:32:07,404][88327] Updated weights for policy 1, policy_version 60750 (0.0007) -[2023-10-09 02:32:07,763][88327] Updated weights for policy 1, policy_version 60760 (0.0009) -[2023-10-09 02:32:08,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 124420096. Throughput: 0: 1687.5, 1: 1706.1. Samples: 31108558. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-09 02:32:08,975][87372] Avg episode reward: [(0, '6.210'), (1, '6.980')] -[2023-10-09 02:32:09,382][88326] Updated weights for policy 0, policy_version 60742 (0.0011) -[2023-10-09 02:32:09,757][88326] Updated weights for policy 0, policy_version 60752 (0.0010) -[2023-10-09 02:32:10,112][88326] Updated weights for policy 0, policy_version 60762 (0.0009) -[2023-10-09 02:32:11,568][88327] Updated weights for policy 1, policy_version 60770 (0.0009) -[2023-10-09 02:32:11,962][88327] Updated weights for policy 1, policy_version 60780 (0.0008) -[2023-10-09 02:32:12,327][88327] Updated weights for policy 1, policy_version 60790 (0.0007) -[2023-10-09 02:32:12,696][88327] Updated weights for policy 1, policy_version 60800 (0.0008) -[2023-10-09 02:32:13,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 124485632. Throughput: 0: 1710.1, 1: 1698.2. Samples: 31129070. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-09 02:32:13,974][87372] Avg episode reward: [(0, '6.320'), (1, '6.920')] -[2023-10-09 02:32:14,287][88326] Updated weights for policy 0, policy_version 60772 (0.0008) -[2023-10-09 02:32:14,684][88326] Updated weights for policy 0, policy_version 60782 (0.0008) -[2023-10-09 02:32:15,056][88326] Updated weights for policy 0, policy_version 60792 (0.0008) -[2023-10-09 02:32:16,778][88327] Updated weights for policy 1, policy_version 60810 (0.0009) -[2023-10-09 02:32:17,145][88327] Updated weights for policy 1, policy_version 60820 (0.0007) -[2023-10-09 02:32:17,503][88327] Updated weights for policy 1, policy_version 60830 (0.0009) -[2023-10-09 02:32:18,914][88326] Updated weights for policy 0, policy_version 60802 (0.0010) -[2023-10-09 02:32:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 124551168. Throughput: 0: 1715.6, 1: 1685.9. Samples: 31149522. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-09 02:32:18,975][87372] Avg episode reward: [(0, '6.250'), (1, '6.520')] -[2023-10-09 02:32:19,290][88326] Updated weights for policy 0, policy_version 60812 (0.0009) -[2023-10-09 02:32:19,665][88326] Updated weights for policy 0, policy_version 60822 (0.0007) -[2023-10-09 02:32:20,040][88326] Updated weights for policy 0, policy_version 60832 (0.0008) -[2023-10-09 02:32:21,554][88327] Updated weights for policy 1, policy_version 60840 (0.0009) -[2023-10-09 02:32:21,914][88327] Updated weights for policy 1, policy_version 60850 (0.0008) -[2023-10-09 02:32:22,279][88327] Updated weights for policy 1, policy_version 60860 (0.0009) -[2023-10-09 02:32:23,864][88326] Updated weights for policy 0, policy_version 60842 (0.0010) -[2023-10-09 02:32:23,974][87372] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 124616704. Throughput: 0: 1703.3, 1: 1709.8. Samples: 31159942. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-09 02:32:23,975][87372] Avg episode reward: [(0, '6.670'), (1, '7.150')] -[2023-10-09 02:32:24,236][88326] Updated weights for policy 0, policy_version 60852 (0.0010) -[2023-10-09 02:32:24,597][88326] Updated weights for policy 0, policy_version 60862 (0.0009) -[2023-10-09 02:32:26,172][88327] Updated weights for policy 1, policy_version 60870 (0.0008) -[2023-10-09 02:32:26,537][88327] Updated weights for policy 1, policy_version 60880 (0.0008) -[2023-10-09 02:32:26,898][88327] Updated weights for policy 1, policy_version 60890 (0.0009) -[2023-10-09 02:32:28,507][88326] Updated weights for policy 0, policy_version 60872 (0.0007) -[2023-10-09 02:32:28,879][88326] Updated weights for policy 0, policy_version 60882 (0.0008) -[2023-10-09 02:32:28,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 124682240. Throughput: 0: 1711.3, 1: 1689.5. Samples: 31180020. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-09 02:32:28,975][87372] Avg episode reward: [(0, '6.630'), (1, '6.560')] -[2023-10-09 02:32:29,255][88326] Updated weights for policy 0, policy_version 60892 (0.0010) -[2023-10-09 02:32:30,892][88327] Updated weights for policy 1, policy_version 60900 (0.0007) -[2023-10-09 02:32:31,247][88327] Updated weights for policy 1, policy_version 60910 (0.0007) -[2023-10-09 02:32:31,622][88327] Updated weights for policy 1, policy_version 60920 (0.0007) -[2023-10-09 02:32:33,291][88326] Updated weights for policy 0, policy_version 60902 (0.0009) -[2023-10-09 02:32:33,664][88326] Updated weights for policy 0, policy_version 60912 (0.0010) -[2023-10-09 02:32:33,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 124747776. Throughput: 0: 1706.5, 1: 1706.7. Samples: 31201020. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-09 02:32:33,975][87372] Avg episode reward: [(0, '7.180'), (1, '6.260')] -[2023-10-09 02:32:33,984][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000060928_62390272.pth... -[2023-10-09 02:32:34,020][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000059328_60751872.pth -[2023-10-09 02:32:34,032][88326] Updated weights for policy 0, policy_version 60922 (0.0010) -[2023-10-09 02:32:34,248][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000060928_62390272.pth... -[2023-10-09 02:32:34,278][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000059328_60751872.pth -[2023-10-09 02:32:35,602][88327] Updated weights for policy 1, policy_version 60930 (0.0008) -[2023-10-09 02:32:35,965][88327] Updated weights for policy 1, policy_version 60940 (0.0009) -[2023-10-09 02:32:36,333][88327] Updated weights for policy 1, policy_version 60950 (0.0007) -[2023-10-09 02:32:36,700][88327] Updated weights for policy 1, policy_version 60960 (0.0007) -[2023-10-09 02:32:38,156][88326] Updated weights for policy 0, policy_version 60932 (0.0007) -[2023-10-09 02:32:38,517][88326] Updated weights for policy 0, policy_version 60942 (0.0007) -[2023-10-09 02:32:38,885][88326] Updated weights for policy 0, policy_version 60952 (0.0007) -[2023-10-09 02:32:38,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 124813312. Throughput: 0: 1706.4, 1: 1703.4. Samples: 31210932. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-09 02:32:38,975][87372] Avg episode reward: [(0, '7.310'), (1, '6.390')] -[2023-10-09 02:32:40,613][88327] Updated weights for policy 1, policy_version 60970 (0.0010) -[2023-10-09 02:32:40,984][88327] Updated weights for policy 1, policy_version 60980 (0.0009) -[2023-10-09 02:32:41,343][88327] Updated weights for policy 1, policy_version 60990 (0.0008) -[2023-10-09 02:32:43,059][88326] Updated weights for policy 0, policy_version 60962 (0.0009) -[2023-10-09 02:32:43,439][88326] Updated weights for policy 0, policy_version 60972 (0.0009) -[2023-10-09 02:32:43,818][88326] Updated weights for policy 0, policy_version 60982 (0.0007) -[2023-10-09 02:32:43,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 124878848. Throughput: 0: 1702.1, 1: 1689.6. Samples: 31231114. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:32:43,975][87372] Avg episode reward: [(0, '7.230'), (1, '6.500')] -[2023-10-09 02:32:44,183][88326] Updated weights for policy 0, policy_version 60992 (0.0009) -[2023-10-09 02:32:45,207][88327] Updated weights for policy 1, policy_version 61000 (0.0009) -[2023-10-09 02:32:45,577][88327] Updated weights for policy 1, policy_version 61010 (0.0009) -[2023-10-09 02:32:45,943][88327] Updated weights for policy 1, policy_version 61020 (0.0010) -[2023-10-09 02:32:47,957][88326] Updated weights for policy 0, policy_version 61002 (0.0009) -[2023-10-09 02:32:48,327][88326] Updated weights for policy 0, policy_version 61012 (0.0008) -[2023-10-09 02:32:48,695][88326] Updated weights for policy 0, policy_version 61022 (0.0009) -[2023-10-09 02:32:48,974][87372] Fps is (10 sec: 16384.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 124977152. Throughput: 0: 1689.4, 1: 1718.0. Samples: 31251650. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:32:48,974][87372] Avg episode reward: [(0, '7.150'), (1, '6.470')] -[2023-10-09 02:32:50,013][88327] Updated weights for policy 1, policy_version 61030 (0.0008) -[2023-10-09 02:32:50,369][88327] Updated weights for policy 1, policy_version 61040 (0.0008) -[2023-10-09 02:32:50,726][88327] Updated weights for policy 1, policy_version 61050 (0.0007) -[2023-10-09 02:32:52,797][88326] Updated weights for policy 0, policy_version 61032 (0.0008) -[2023-10-09 02:32:53,156][88326] Updated weights for policy 0, policy_version 61042 (0.0009) -[2023-10-09 02:32:53,520][88326] Updated weights for policy 0, policy_version 61052 (0.0009) -[2023-10-09 02:32:53,974][87372] Fps is (10 sec: 16384.0, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 125042688. Throughput: 0: 1704.7, 1: 1697.4. Samples: 31261652. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:32:53,974][87372] Avg episode reward: [(0, '6.650'), (1, '6.760')] -[2023-10-09 02:32:54,601][88327] Updated weights for policy 1, policy_version 61060 (0.0009) -[2023-10-09 02:32:54,965][88327] Updated weights for policy 1, policy_version 61070 (0.0009) -[2023-10-09 02:32:55,339][88327] Updated weights for policy 1, policy_version 61080 (0.0009) -[2023-10-09 02:32:57,524][88326] Updated weights for policy 0, policy_version 61062 (0.0010) -[2023-10-09 02:32:57,893][88326] Updated weights for policy 0, policy_version 61072 (0.0010) -[2023-10-09 02:32:58,261][88326] Updated weights for policy 0, policy_version 61082 (0.0010) -[2023-10-09 02:32:58,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 125108224. Throughput: 0: 1707.5, 1: 1710.8. Samples: 31282894. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:32:58,975][87372] Avg episode reward: [(0, '6.700'), (1, '7.370')] -[2023-10-09 02:32:59,400][88327] Updated weights for policy 1, policy_version 61090 (0.0008) -[2023-10-09 02:32:59,786][88327] Updated weights for policy 1, policy_version 61100 (0.0010) -[2023-10-09 02:33:00,153][88327] Updated weights for policy 1, policy_version 61110 (0.0008) -[2023-10-09 02:33:00,524][88327] Updated weights for policy 1, policy_version 61120 (0.0009) -[2023-10-09 02:33:02,399][88326] Updated weights for policy 0, policy_version 61092 (0.0008) -[2023-10-09 02:33:02,784][88326] Updated weights for policy 0, policy_version 61102 (0.0008) -[2023-10-09 02:33:03,157][88326] Updated weights for policy 0, policy_version 61112 (0.0010) -[2023-10-09 02:33:03,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 125173760. Throughput: 0: 1684.4, 1: 1720.7. Samples: 31302754. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:33:03,974][87372] Avg episode reward: [(0, '6.870'), (1, '7.580')] -[2023-10-09 02:33:04,600][88327] Updated weights for policy 1, policy_version 61130 (0.0007) -[2023-10-09 02:33:04,971][88327] Updated weights for policy 1, policy_version 61140 (0.0007) -[2023-10-09 02:33:05,337][88327] Updated weights for policy 1, policy_version 61150 (0.0008) -[2023-10-09 02:33:07,142][88326] Updated weights for policy 0, policy_version 61122 (0.0008) -[2023-10-09 02:33:07,515][88326] Updated weights for policy 0, policy_version 61132 (0.0010) -[2023-10-09 02:33:07,878][88326] Updated weights for policy 0, policy_version 61142 (0.0007) -[2023-10-09 02:33:08,255][88326] Updated weights for policy 0, policy_version 61152 (0.0009) -[2023-10-09 02:33:08,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 125239296. Throughput: 0: 1707.9, 1: 1691.8. Samples: 31312928. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:33:08,975][87372] Avg episode reward: [(0, '6.760'), (1, '7.640')] -[2023-10-09 02:33:09,270][88327] Updated weights for policy 1, policy_version 61160 (0.0009) -[2023-10-09 02:33:09,636][88327] Updated weights for policy 1, policy_version 61170 (0.0008) -[2023-10-09 02:33:10,010][88327] Updated weights for policy 1, policy_version 61180 (0.0007) -[2023-10-09 02:33:12,230][88326] Updated weights for policy 0, policy_version 61162 (0.0007) -[2023-10-09 02:33:12,591][88326] Updated weights for policy 0, policy_version 61172 (0.0008) -[2023-10-09 02:33:12,973][88326] Updated weights for policy 0, policy_version 61182 (0.0009) -[2023-10-09 02:33:13,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 125304832. Throughput: 0: 1698.8, 1: 1711.7. Samples: 31333490. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:33:13,975][87372] Avg episode reward: [(0, '6.690'), (1, '7.230')] -[2023-10-09 02:33:13,996][88327] Updated weights for policy 1, policy_version 61190 (0.0009) -[2023-10-09 02:33:14,367][88327] Updated weights for policy 1, policy_version 61200 (0.0010) -[2023-10-09 02:33:14,745][88327] Updated weights for policy 1, policy_version 61210 (0.0008) -[2023-10-09 02:33:16,994][88326] Updated weights for policy 0, policy_version 61192 (0.0009) -[2023-10-09 02:33:17,359][88326] Updated weights for policy 0, policy_version 61202 (0.0007) -[2023-10-09 02:33:17,735][88326] Updated weights for policy 0, policy_version 61212 (0.0010) -[2023-10-09 02:33:18,949][88327] Updated weights for policy 1, policy_version 61220 (0.0009) -[2023-10-09 02:33:18,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 125370368. Throughput: 0: 1679.2, 1: 1709.6. Samples: 31353512. Policy #0 lag: (min: 30.0, avg: 36.3, max: 62.0) -[2023-10-09 02:33:18,974][87372] Avg episode reward: [(0, '7.000'), (1, '7.180')] -[2023-10-09 02:33:19,306][88327] Updated weights for policy 1, policy_version 61230 (0.0007) -[2023-10-09 02:33:19,670][88327] Updated weights for policy 1, policy_version 61240 (0.0007) -[2023-10-09 02:33:21,735][88326] Updated weights for policy 0, policy_version 61222 (0.0008) -[2023-10-09 02:33:22,103][88326] Updated weights for policy 0, policy_version 61232 (0.0008) -[2023-10-09 02:33:22,464][88326] Updated weights for policy 0, policy_version 61242 (0.0007) -[2023-10-09 02:33:23,453][88327] Updated weights for policy 1, policy_version 61250 (0.0008) -[2023-10-09 02:33:23,823][88327] Updated weights for policy 1, policy_version 61260 (0.0009) -[2023-10-09 02:33:23,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 125435904. Throughput: 0: 1704.7, 1: 1694.2. Samples: 31363882. Policy #0 lag: (min: 30.0, avg: 36.3, max: 62.0) -[2023-10-09 02:33:23,975][87372] Avg episode reward: [(0, '7.190'), (1, '7.340')] -[2023-10-09 02:33:24,189][88327] Updated weights for policy 1, policy_version 61270 (0.0010) -[2023-10-09 02:33:24,566][88327] Updated weights for policy 1, policy_version 61280 (0.0010) -[2023-10-09 02:33:26,498][88326] Updated weights for policy 0, policy_version 61252 (0.0008) -[2023-10-09 02:33:26,878][88326] Updated weights for policy 0, policy_version 61262 (0.0009) -[2023-10-09 02:33:27,237][88326] Updated weights for policy 0, policy_version 61272 (0.0008) -[2023-10-09 02:33:28,696][88327] Updated weights for policy 1, policy_version 61290 (0.0008) -[2023-10-09 02:33:28,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 125501440. Throughput: 0: 1685.9, 1: 1714.8. Samples: 31384144. Policy #0 lag: (min: 30.0, avg: 36.3, max: 62.0) -[2023-10-09 02:33:28,975][87372] Avg episode reward: [(0, '6.870'), (1, '6.530')] -[2023-10-09 02:33:29,056][88327] Updated weights for policy 1, policy_version 61300 (0.0008) -[2023-10-09 02:33:29,422][88327] Updated weights for policy 1, policy_version 61310 (0.0007) -[2023-10-09 02:33:31,362][88326] Updated weights for policy 0, policy_version 61282 (0.0007) -[2023-10-09 02:33:31,734][88326] Updated weights for policy 0, policy_version 61292 (0.0009) -[2023-10-09 02:33:32,103][88326] Updated weights for policy 0, policy_version 61302 (0.0009) -[2023-10-09 02:33:32,474][88326] Updated weights for policy 0, policy_version 61312 (0.0008) -[2023-10-09 02:33:33,431][88327] Updated weights for policy 1, policy_version 61320 (0.0009) -[2023-10-09 02:33:33,791][88327] Updated weights for policy 1, policy_version 61330 (0.0009) -[2023-10-09 02:33:33,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 125566976. Throughput: 0: 1688.5, 1: 1712.1. Samples: 31404678. Policy #0 lag: (min: 30.0, avg: 36.3, max: 62.0) -[2023-10-09 02:33:33,975][87372] Avg episode reward: [(0, '7.110'), (1, '7.080')] -[2023-10-09 02:33:34,153][88327] Updated weights for policy 1, policy_version 61340 (0.0009) -[2023-10-09 02:33:36,556][88326] Updated weights for policy 0, policy_version 61322 (0.0007) -[2023-10-09 02:33:36,923][88326] Updated weights for policy 0, policy_version 61332 (0.0007) -[2023-10-09 02:33:37,291][88326] Updated weights for policy 0, policy_version 61342 (0.0007) -[2023-10-09 02:33:38,010][88327] Updated weights for policy 1, policy_version 61350 (0.0010) -[2023-10-09 02:33:38,371][88327] Updated weights for policy 1, policy_version 61360 (0.0010) -[2023-10-09 02:33:38,729][88327] Updated weights for policy 1, policy_version 61370 (0.0011) -[2023-10-09 02:33:38,974][87372] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 125665280. Throughput: 0: 1702.1, 1: 1710.6. Samples: 31415224. Policy #0 lag: (min: 30.0, avg: 36.3, max: 62.0) -[2023-10-09 02:33:38,975][87372] Avg episode reward: [(0, '7.440'), (1, '7.410')] -[2023-10-09 02:33:41,102][88326] Updated weights for policy 0, policy_version 61352 (0.0008) -[2023-10-09 02:33:41,474][88326] Updated weights for policy 0, policy_version 61362 (0.0011) -[2023-10-09 02:33:41,842][88326] Updated weights for policy 0, policy_version 61372 (0.0010) -[2023-10-09 02:33:42,882][88327] Updated weights for policy 1, policy_version 61380 (0.0009) -[2023-10-09 02:33:43,253][88327] Updated weights for policy 1, policy_version 61390 (0.0007) -[2023-10-09 02:33:43,627][88327] Updated weights for policy 1, policy_version 61400 (0.0008) -[2023-10-09 02:33:43,974][87372] Fps is (10 sec: 16384.3, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 125730816. Throughput: 0: 1674.4, 1: 1707.6. Samples: 31435080. Policy #0 lag: (min: 30.0, avg: 36.3, max: 62.0) -[2023-10-09 02:33:43,975][87372] Avg episode reward: [(0, '7.160'), (1, '7.760')] -[2023-10-09 02:33:45,899][88326] Updated weights for policy 0, policy_version 61382 (0.0008) -[2023-10-09 02:33:46,277][88326] Updated weights for policy 0, policy_version 61392 (0.0008) -[2023-10-09 02:33:46,649][88326] Updated weights for policy 0, policy_version 61402 (0.0008) -[2023-10-09 02:33:47,702][88327] Updated weights for policy 1, policy_version 61410 (0.0010) -[2023-10-09 02:33:48,128][88327] Updated weights for policy 1, policy_version 61420 (0.0009) -[2023-10-09 02:33:48,506][88327] Updated weights for policy 1, policy_version 61430 (0.0008) -[2023-10-09 02:33:48,872][88327] Updated weights for policy 1, policy_version 61440 (0.0008) -[2023-10-09 02:33:48,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 125796352. Throughput: 0: 1695.2, 1: 1697.6. Samples: 31455430. Policy #0 lag: (min: 30.0, avg: 36.3, max: 62.0) -[2023-10-09 02:33:48,975][87372] Avg episode reward: [(0, '7.660'), (1, '7.370')] -[2023-10-09 02:33:50,776][88326] Updated weights for policy 0, policy_version 61412 (0.0009) -[2023-10-09 02:33:51,180][88326] Updated weights for policy 0, policy_version 61422 (0.0010) -[2023-10-09 02:33:51,555][88326] Updated weights for policy 0, policy_version 61432 (0.0010) -[2023-10-09 02:33:52,707][88327] Updated weights for policy 1, policy_version 61450 (0.0009) -[2023-10-09 02:33:53,076][88327] Updated weights for policy 1, policy_version 61460 (0.0007) -[2023-10-09 02:33:53,433][88327] Updated weights for policy 1, policy_version 61470 (0.0007) -[2023-10-09 02:33:53,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 125861888. Throughput: 0: 1686.2, 1: 1706.4. Samples: 31465596. Policy #0 lag: (min: 30.0, avg: 36.3, max: 62.0) -[2023-10-09 02:33:53,975][87372] Avg episode reward: [(0, '7.320'), (1, '7.640')] -[2023-10-09 02:33:55,635][88326] Updated weights for policy 0, policy_version 61442 (0.0009) -[2023-10-09 02:33:56,005][88326] Updated weights for policy 0, policy_version 61452 (0.0010) -[2023-10-09 02:33:56,373][88326] Updated weights for policy 0, policy_version 61462 (0.0009) -[2023-10-09 02:33:56,752][88326] Updated weights for policy 0, policy_version 61472 (0.0008) -[2023-10-09 02:33:57,359][88327] Updated weights for policy 1, policy_version 61480 (0.0007) -[2023-10-09 02:33:57,716][88327] Updated weights for policy 1, policy_version 61490 (0.0007) -[2023-10-09 02:33:58,070][88327] Updated weights for policy 1, policy_version 61500 (0.0009) -[2023-10-09 02:33:58,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 125927424. Throughput: 0: 1672.8, 1: 1709.8. Samples: 31485704. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:33:58,974][87372] Avg episode reward: [(0, '7.290'), (1, '7.560')] -[2023-10-09 02:34:00,758][88326] Updated weights for policy 0, policy_version 61482 (0.0007) -[2023-10-09 02:34:01,126][88326] Updated weights for policy 0, policy_version 61492 (0.0008) -[2023-10-09 02:34:01,484][88326] Updated weights for policy 0, policy_version 61502 (0.0009) -[2023-10-09 02:34:02,246][88327] Updated weights for policy 1, policy_version 61510 (0.0009) -[2023-10-09 02:34:02,612][88327] Updated weights for policy 1, policy_version 61520 (0.0008) -[2023-10-09 02:34:02,974][88327] Updated weights for policy 1, policy_version 61530 (0.0007) -[2023-10-09 02:34:03,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 125992960. Throughput: 0: 1695.8, 1: 1682.0. Samples: 31505512. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:34:03,975][87372] Avg episode reward: [(0, '7.880'), (1, '7.590')] -[2023-10-09 02:34:05,485][88326] Updated weights for policy 0, policy_version 61512 (0.0010) -[2023-10-09 02:34:05,853][88326] Updated weights for policy 0, policy_version 61522 (0.0011) -[2023-10-09 02:34:06,218][88326] Updated weights for policy 0, policy_version 61532 (0.0007) -[2023-10-09 02:34:06,859][88327] Updated weights for policy 1, policy_version 61540 (0.0008) -[2023-10-09 02:34:07,219][88327] Updated weights for policy 1, policy_version 61550 (0.0007) -[2023-10-09 02:34:07,591][88327] Updated weights for policy 1, policy_version 61560 (0.0008) -[2023-10-09 02:34:08,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 126058496. Throughput: 0: 1673.9, 1: 1708.8. Samples: 31516104. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:34:08,975][87372] Avg episode reward: [(0, '7.610'), (1, '7.120')] -[2023-10-09 02:34:10,295][88326] Updated weights for policy 0, policy_version 61542 (0.0007) -[2023-10-09 02:34:10,667][88326] Updated weights for policy 0, policy_version 61552 (0.0008) -[2023-10-09 02:34:11,033][88326] Updated weights for policy 0, policy_version 61562 (0.0007) -[2023-10-09 02:34:11,541][88327] Updated weights for policy 1, policy_version 61570 (0.0008) -[2023-10-09 02:34:11,906][88327] Updated weights for policy 1, policy_version 61580 (0.0008) -[2023-10-09 02:34:12,264][88327] Updated weights for policy 1, policy_version 61590 (0.0009) -[2023-10-09 02:34:12,628][88327] Updated weights for policy 1, policy_version 61600 (0.0007) -[2023-10-09 02:34:13,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 126124032. Throughput: 0: 1693.3, 1: 1688.4. Samples: 31536322. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:34:13,975][87372] Avg episode reward: [(0, '7.260'), (1, '7.760')] -[2023-10-09 02:34:15,086][88326] Updated weights for policy 0, policy_version 61572 (0.0008) -[2023-10-09 02:34:15,458][88326] Updated weights for policy 0, policy_version 61582 (0.0009) -[2023-10-09 02:34:15,818][88326] Updated weights for policy 0, policy_version 61592 (0.0011) -[2023-10-09 02:34:16,701][88327] Updated weights for policy 1, policy_version 61610 (0.0007) -[2023-10-09 02:34:17,061][88327] Updated weights for policy 1, policy_version 61620 (0.0008) -[2023-10-09 02:34:17,431][88327] Updated weights for policy 1, policy_version 61630 (0.0009) -[2023-10-09 02:34:18,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 126189568. Throughput: 0: 1707.1, 1: 1676.3. Samples: 31556928. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:34:18,975][87372] Avg episode reward: [(0, '7.250'), (1, '7.370')] -[2023-10-09 02:34:19,794][88326] Updated weights for policy 0, policy_version 61602 (0.0008) -[2023-10-09 02:34:20,178][88326] Updated weights for policy 0, policy_version 61612 (0.0009) -[2023-10-09 02:34:20,541][88326] Updated weights for policy 0, policy_version 61622 (0.0009) -[2023-10-09 02:34:20,904][88326] Updated weights for policy 0, policy_version 61632 (0.0008) -[2023-10-09 02:34:21,664][88327] Updated weights for policy 1, policy_version 61640 (0.0008) -[2023-10-09 02:34:22,040][88327] Updated weights for policy 1, policy_version 61650 (0.0009) -[2023-10-09 02:34:22,408][88327] Updated weights for policy 1, policy_version 61660 (0.0010) -[2023-10-09 02:34:23,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 126255104. Throughput: 0: 1674.7, 1: 1701.1. Samples: 31567136. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:34:23,975][87372] Avg episode reward: [(0, '6.620'), (1, '7.000')] -[2023-10-09 02:34:24,830][88326] Updated weights for policy 0, policy_version 61642 (0.0011) -[2023-10-09 02:34:25,210][88326] Updated weights for policy 0, policy_version 61652 (0.0009) -[2023-10-09 02:34:25,565][88326] Updated weights for policy 0, policy_version 61662 (0.0009) -[2023-10-09 02:34:26,306][88327] Updated weights for policy 1, policy_version 61670 (0.0012) -[2023-10-09 02:34:26,675][88327] Updated weights for policy 1, policy_version 61680 (0.0011) -[2023-10-09 02:34:27,039][88327] Updated weights for policy 1, policy_version 61690 (0.0010) -[2023-10-09 02:34:28,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 126320640. Throughput: 0: 1699.7, 1: 1676.1. Samples: 31586990. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:34:28,974][87372] Avg episode reward: [(0, '6.960'), (1, '6.850')] -[2023-10-09 02:34:29,559][88326] Updated weights for policy 0, policy_version 61672 (0.0009) -[2023-10-09 02:34:29,926][88326] Updated weights for policy 0, policy_version 61682 (0.0009) -[2023-10-09 02:34:30,292][88326] Updated weights for policy 0, policy_version 61692 (0.0007) -[2023-10-09 02:34:31,247][88327] Updated weights for policy 1, policy_version 61700 (0.0009) -[2023-10-09 02:34:31,609][88327] Updated weights for policy 1, policy_version 61710 (0.0008) -[2023-10-09 02:34:31,974][88327] Updated weights for policy 1, policy_version 61720 (0.0007) -[2023-10-09 02:34:33,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 126386176. Throughput: 0: 1697.6, 1: 1682.7. Samples: 31607540. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:34:33,975][87372] Avg episode reward: [(0, '6.990'), (1, '6.700')] -[2023-10-09 02:34:33,983][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000061696_63176704.pth... -[2023-10-09 02:34:33,983][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000061728_63209472.pth... -[2023-10-09 02:34:34,014][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000060128_61571072.pth -[2023-10-09 02:34:34,024][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000060128_61571072.pth -[2023-10-09 02:34:34,531][88326] Updated weights for policy 0, policy_version 61702 (0.0010) -[2023-10-09 02:34:34,907][88326] Updated weights for policy 0, policy_version 61712 (0.0010) -[2023-10-09 02:34:35,272][88326] Updated weights for policy 0, policy_version 61722 (0.0010) -[2023-10-09 02:34:36,108][88327] Updated weights for policy 1, policy_version 61730 (0.0008) -[2023-10-09 02:34:36,533][88327] Updated weights for policy 1, policy_version 61740 (0.0007) -[2023-10-09 02:34:36,906][88327] Updated weights for policy 1, policy_version 61750 (0.0009) -[2023-10-09 02:34:37,277][88327] Updated weights for policy 1, policy_version 61760 (0.0008) -[2023-10-09 02:34:38,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 126451712. Throughput: 0: 1684.0, 1: 1698.0. Samples: 31617790. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:34:38,975][87372] Avg episode reward: [(0, '7.390'), (1, '6.870')] -[2023-10-09 02:34:39,426][88326] Updated weights for policy 0, policy_version 61732 (0.0007) -[2023-10-09 02:34:39,808][88326] Updated weights for policy 0, policy_version 61742 (0.0008) -[2023-10-09 02:34:40,176][88326] Updated weights for policy 0, policy_version 61752 (0.0007) -[2023-10-09 02:34:41,156][88327] Updated weights for policy 1, policy_version 61770 (0.0008) -[2023-10-09 02:34:41,529][88327] Updated weights for policy 1, policy_version 61780 (0.0009) -[2023-10-09 02:34:41,889][88327] Updated weights for policy 1, policy_version 61790 (0.0009) -[2023-10-09 02:34:43,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 126517248. Throughput: 0: 1704.8, 1: 1667.9. Samples: 31637476. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 02:34:43,975][87372] Avg episode reward: [(0, '7.150'), (1, '6.890')] -[2023-10-09 02:34:44,196][88326] Updated weights for policy 0, policy_version 61762 (0.0008) -[2023-10-09 02:34:44,572][88326] Updated weights for policy 0, policy_version 61772 (0.0008) -[2023-10-09 02:34:44,941][88326] Updated weights for policy 0, policy_version 61782 (0.0008) -[2023-10-09 02:34:45,310][88326] Updated weights for policy 0, policy_version 61792 (0.0008) -[2023-10-09 02:34:45,922][88327] Updated weights for policy 1, policy_version 61800 (0.0010) -[2023-10-09 02:34:46,287][88327] Updated weights for policy 1, policy_version 61810 (0.0008) -[2023-10-09 02:34:46,654][88327] Updated weights for policy 1, policy_version 61820 (0.0007) -[2023-10-09 02:34:48,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 126582784. Throughput: 0: 1699.7, 1: 1697.4. Samples: 31658384. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 02:34:48,974][87372] Avg episode reward: [(0, '7.760'), (1, '6.920')] -[2023-10-09 02:34:49,299][88326] Updated weights for policy 0, policy_version 61802 (0.0009) -[2023-10-09 02:34:49,671][88326] Updated weights for policy 0, policy_version 61812 (0.0007) -[2023-10-09 02:34:50,040][88326] Updated weights for policy 0, policy_version 61822 (0.0009) -[2023-10-09 02:34:50,885][88327] Updated weights for policy 1, policy_version 61830 (0.0009) -[2023-10-09 02:34:51,252][88327] Updated weights for policy 1, policy_version 61840 (0.0009) -[2023-10-09 02:34:51,611][88327] Updated weights for policy 1, policy_version 61850 (0.0010) -[2023-10-09 02:34:53,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 126648320. Throughput: 0: 1690.7, 1: 1688.3. Samples: 31668164. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 02:34:53,975][87372] Avg episode reward: [(0, '7.860'), (1, '7.960')] -[2023-10-09 02:34:54,256][88326] Updated weights for policy 0, policy_version 61832 (0.0010) -[2023-10-09 02:34:54,618][88326] Updated weights for policy 0, policy_version 61842 (0.0011) -[2023-10-09 02:34:54,984][88326] Updated weights for policy 0, policy_version 61852 (0.0010) -[2023-10-09 02:34:55,581][88327] Updated weights for policy 1, policy_version 61860 (0.0011) -[2023-10-09 02:34:55,961][88327] Updated weights for policy 1, policy_version 61870 (0.0009) -[2023-10-09 02:34:56,323][88327] Updated weights for policy 1, policy_version 61880 (0.0009) -[2023-10-09 02:34:58,911][88326] Updated weights for policy 0, policy_version 61862 (0.0009) -[2023-10-09 02:34:58,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 126713856. Throughput: 0: 1690.1, 1: 1682.9. Samples: 31688108. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 02:34:58,975][87372] Avg episode reward: [(0, '7.750'), (1, '7.480')] -[2023-10-09 02:34:59,282][88326] Updated weights for policy 0, policy_version 61872 (0.0009) -[2023-10-09 02:34:59,653][88326] Updated weights for policy 0, policy_version 61882 (0.0008) -[2023-10-09 02:35:00,566][88327] Updated weights for policy 1, policy_version 61890 (0.0009) -[2023-10-09 02:35:00,925][88327] Updated weights for policy 1, policy_version 61900 (0.0011) -[2023-10-09 02:35:01,294][88327] Updated weights for policy 1, policy_version 61910 (0.0007) -[2023-10-09 02:35:01,666][88327] Updated weights for policy 1, policy_version 61920 (0.0010) -[2023-10-09 02:35:03,716][88326] Updated weights for policy 0, policy_version 61892 (0.0009) -[2023-10-09 02:35:03,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 126779392. Throughput: 0: 1683.8, 1: 1689.1. Samples: 31708706. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 02:35:03,975][87372] Avg episode reward: [(0, '7.230'), (1, '7.450')] -[2023-10-09 02:35:04,090][88326] Updated weights for policy 0, policy_version 61902 (0.0007) -[2023-10-09 02:35:04,451][88326] Updated weights for policy 0, policy_version 61912 (0.0007) -[2023-10-09 02:35:05,862][88327] Updated weights for policy 1, policy_version 61930 (0.0011) -[2023-10-09 02:35:06,227][88327] Updated weights for policy 1, policy_version 61940 (0.0010) -[2023-10-09 02:35:06,598][88327] Updated weights for policy 1, policy_version 61950 (0.0007) -[2023-10-09 02:35:08,560][88326] Updated weights for policy 0, policy_version 61922 (0.0007) -[2023-10-09 02:35:08,926][88326] Updated weights for policy 0, policy_version 61932 (0.0010) -[2023-10-09 02:35:08,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 126844928. Throughput: 0: 1686.8, 1: 1672.5. Samples: 31718306. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 02:35:08,975][87372] Avg episode reward: [(0, '6.620'), (1, '7.310')] -[2023-10-09 02:35:09,301][88326] Updated weights for policy 0, policy_version 61942 (0.0007) -[2023-10-09 02:35:09,660][88326] Updated weights for policy 0, policy_version 61952 (0.0007) -[2023-10-09 02:35:10,577][88327] Updated weights for policy 1, policy_version 61960 (0.0009) -[2023-10-09 02:35:10,943][88327] Updated weights for policy 1, policy_version 61970 (0.0010) -[2023-10-09 02:35:11,320][88327] Updated weights for policy 1, policy_version 61980 (0.0008) -[2023-10-09 02:35:13,754][88326] Updated weights for policy 0, policy_version 61962 (0.0008) -[2023-10-09 02:35:13,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.3, 300 sec: 13440.4). Total num frames: 126910464. Throughput: 0: 1686.3, 1: 1684.2. Samples: 31738660. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 02:35:13,975][87372] Avg episode reward: [(0, '6.380'), (1, '6.810')] -[2023-10-09 02:35:14,122][88326] Updated weights for policy 0, policy_version 61972 (0.0010) -[2023-10-09 02:35:14,485][88326] Updated weights for policy 0, policy_version 61982 (0.0009) -[2023-10-09 02:35:15,093][88327] Updated weights for policy 1, policy_version 61990 (0.0010) -[2023-10-09 02:35:15,454][88327] Updated weights for policy 1, policy_version 62000 (0.0009) -[2023-10-09 02:35:15,827][88327] Updated weights for policy 1, policy_version 62010 (0.0009) -[2023-10-09 02:35:18,198][88326] Updated weights for policy 0, policy_version 61992 (0.0009) -[2023-10-09 02:35:18,575][88326] Updated weights for policy 0, policy_version 62002 (0.0008) -[2023-10-09 02:35:18,944][88326] Updated weights for policy 0, policy_version 62012 (0.0008) -[2023-10-09 02:35:18,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 126976000. Throughput: 0: 1685.2, 1: 1695.8. Samples: 31759684. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 02:35:18,974][87372] Avg episode reward: [(0, '6.170'), (1, '6.920')] -[2023-10-09 02:35:19,902][88327] Updated weights for policy 1, policy_version 62020 (0.0008) -[2023-10-09 02:35:20,269][88327] Updated weights for policy 1, policy_version 62030 (0.0007) -[2023-10-09 02:35:20,640][88327] Updated weights for policy 1, policy_version 62040 (0.0008) -[2023-10-09 02:35:22,842][88326] Updated weights for policy 0, policy_version 62022 (0.0007) -[2023-10-09 02:35:23,206][88326] Updated weights for policy 0, policy_version 62032 (0.0007) -[2023-10-09 02:35:23,572][88326] Updated weights for policy 0, policy_version 62042 (0.0008) -[2023-10-09 02:35:23,974][87372] Fps is (10 sec: 16383.8, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 127074304. Throughput: 0: 1696.7, 1: 1670.6. Samples: 31769318. Policy #0 lag: (min: 26.0, avg: 41.5, max: 58.0) -[2023-10-09 02:35:23,975][87372] Avg episode reward: [(0, '6.480'), (1, '7.200')] -[2023-10-09 02:35:24,647][88327] Updated weights for policy 1, policy_version 62050 (0.0009) -[2023-10-09 02:35:25,073][88327] Updated weights for policy 1, policy_version 62060 (0.0007) -[2023-10-09 02:35:25,442][88327] Updated weights for policy 1, policy_version 62070 (0.0008) -[2023-10-09 02:35:25,808][88327] Updated weights for policy 1, policy_version 62080 (0.0010) -[2023-10-09 02:35:27,690][88326] Updated weights for policy 0, policy_version 62052 (0.0008) -[2023-10-09 02:35:28,074][88326] Updated weights for policy 0, policy_version 62062 (0.0010) -[2023-10-09 02:35:28,449][88326] Updated weights for policy 0, policy_version 62072 (0.0010) -[2023-10-09 02:35:28,974][87372] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 127139840. Throughput: 0: 1699.3, 1: 1700.5. Samples: 31790464. Policy #0 lag: (min: 26.0, avg: 41.5, max: 58.0) -[2023-10-09 02:35:28,975][87372] Avg episode reward: [(0, '6.810'), (1, '7.670')] -[2023-10-09 02:35:29,657][88327] Updated weights for policy 1, policy_version 62090 (0.0007) -[2023-10-09 02:35:30,020][88327] Updated weights for policy 1, policy_version 62100 (0.0007) -[2023-10-09 02:35:30,385][88327] Updated weights for policy 1, policy_version 62110 (0.0007) -[2023-10-09 02:35:32,573][88326] Updated weights for policy 0, policy_version 62082 (0.0009) -[2023-10-09 02:35:32,946][88326] Updated weights for policy 0, policy_version 62092 (0.0009) -[2023-10-09 02:35:33,304][88326] Updated weights for policy 0, policy_version 62102 (0.0009) -[2023-10-09 02:35:33,670][88326] Updated weights for policy 0, policy_version 62112 (0.0008) -[2023-10-09 02:35:33,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 127205376. Throughput: 0: 1678.6, 1: 1704.3. Samples: 31810612. Policy #0 lag: (min: 26.0, avg: 41.5, max: 58.0) -[2023-10-09 02:35:33,975][87372] Avg episode reward: [(0, '7.140'), (1, '7.050')] -[2023-10-09 02:35:34,408][88327] Updated weights for policy 1, policy_version 62120 (0.0010) -[2023-10-09 02:35:34,771][88327] Updated weights for policy 1, policy_version 62130 (0.0011) -[2023-10-09 02:35:35,142][88327] Updated weights for policy 1, policy_version 62140 (0.0009) -[2023-10-09 02:35:37,601][88326] Updated weights for policy 0, policy_version 62122 (0.0009) -[2023-10-09 02:35:37,963][88326] Updated weights for policy 0, policy_version 62132 (0.0008) -[2023-10-09 02:35:38,331][88326] Updated weights for policy 0, policy_version 62142 (0.0008) -[2023-10-09 02:35:38,882][88327] Updated weights for policy 1, policy_version 62150 (0.0009) -[2023-10-09 02:35:38,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 127270912. Throughput: 0: 1699.4, 1: 1687.2. Samples: 31820558. Policy #0 lag: (min: 26.0, avg: 41.5, max: 58.0) -[2023-10-09 02:35:38,974][87372] Avg episode reward: [(0, '7.200'), (1, '7.090')] -[2023-10-09 02:35:39,260][88327] Updated weights for policy 1, policy_version 62160 (0.0008) -[2023-10-09 02:35:39,622][88327] Updated weights for policy 1, policy_version 62170 (0.0008) -[2023-10-09 02:35:42,282][88326] Updated weights for policy 0, policy_version 62152 (0.0009) -[2023-10-09 02:35:42,650][88326] Updated weights for policy 0, policy_version 62162 (0.0007) -[2023-10-09 02:35:43,020][88326] Updated weights for policy 0, policy_version 62172 (0.0007) -[2023-10-09 02:35:43,680][88327] Updated weights for policy 1, policy_version 62180 (0.0009) -[2023-10-09 02:35:43,974][87372] Fps is (10 sec: 13107.6, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 127336448. Throughput: 0: 1698.8, 1: 1705.0. Samples: 31841276. Policy #0 lag: (min: 26.0, avg: 41.5, max: 58.0) -[2023-10-09 02:35:43,974][87372] Avg episode reward: [(0, '7.510'), (1, '6.620')] -[2023-10-09 02:35:44,049][88327] Updated weights for policy 1, policy_version 62190 (0.0007) -[2023-10-09 02:35:44,405][88327] Updated weights for policy 1, policy_version 62200 (0.0008) -[2023-10-09 02:35:46,908][88326] Updated weights for policy 0, policy_version 62182 (0.0007) -[2023-10-09 02:35:47,268][88326] Updated weights for policy 0, policy_version 62192 (0.0008) -[2023-10-09 02:35:47,637][88326] Updated weights for policy 0, policy_version 62202 (0.0008) -[2023-10-09 02:35:48,685][88327] Updated weights for policy 1, policy_version 62210 (0.0009) -[2023-10-09 02:35:48,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 127401984. Throughput: 0: 1682.0, 1: 1709.7. Samples: 31861330. Policy #0 lag: (min: 26.0, avg: 41.5, max: 58.0) -[2023-10-09 02:35:48,975][87372] Avg episode reward: [(0, '7.710'), (1, '7.400')] -[2023-10-09 02:35:49,047][88327] Updated weights for policy 1, policy_version 62220 (0.0011) -[2023-10-09 02:35:49,408][88327] Updated weights for policy 1, policy_version 62230 (0.0009) -[2023-10-09 02:35:49,776][88327] Updated weights for policy 1, policy_version 62240 (0.0011) -[2023-10-09 02:35:51,588][88326] Updated weights for policy 0, policy_version 62212 (0.0008) -[2023-10-09 02:35:51,958][88326] Updated weights for policy 0, policy_version 62222 (0.0007) -[2023-10-09 02:35:52,326][88326] Updated weights for policy 0, policy_version 62232 (0.0009) -[2023-10-09 02:35:53,764][88327] Updated weights for policy 1, policy_version 62250 (0.0009) -[2023-10-09 02:35:53,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 127467520. Throughput: 0: 1714.9, 1: 1699.0. Samples: 31871932. Policy #0 lag: (min: 26.0, avg: 41.5, max: 58.0) -[2023-10-09 02:35:53,975][87372] Avg episode reward: [(0, '7.080'), (1, '7.240')] -[2023-10-09 02:35:54,134][88327] Updated weights for policy 1, policy_version 62260 (0.0010) -[2023-10-09 02:35:54,490][88327] Updated weights for policy 1, policy_version 62270 (0.0010) -[2023-10-09 02:35:56,366][88326] Updated weights for policy 0, policy_version 62242 (0.0007) -[2023-10-09 02:35:56,744][88326] Updated weights for policy 0, policy_version 62252 (0.0007) -[2023-10-09 02:35:57,111][88326] Updated weights for policy 0, policy_version 62262 (0.0008) -[2023-10-09 02:35:57,480][88326] Updated weights for policy 0, policy_version 62272 (0.0007) -[2023-10-09 02:35:58,604][88327] Updated weights for policy 1, policy_version 62280 (0.0008) -[2023-10-09 02:35:58,965][88327] Updated weights for policy 1, policy_version 62290 (0.0010) -[2023-10-09 02:35:58,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 127533056. Throughput: 0: 1693.2, 1: 1713.9. Samples: 31891978. Policy #0 lag: (min: 26.0, avg: 41.5, max: 58.0) -[2023-10-09 02:35:58,975][87372] Avg episode reward: [(0, '7.150'), (1, '7.330')] -[2023-10-09 02:35:59,332][88327] Updated weights for policy 1, policy_version 62300 (0.0009) -[2023-10-09 02:36:01,474][88326] Updated weights for policy 0, policy_version 62282 (0.0010) -[2023-10-09 02:36:01,845][88326] Updated weights for policy 0, policy_version 62292 (0.0009) -[2023-10-09 02:36:02,215][88326] Updated weights for policy 0, policy_version 62302 (0.0008) -[2023-10-09 02:36:03,260][88327] Updated weights for policy 1, policy_version 62310 (0.0008) -[2023-10-09 02:36:03,622][88327] Updated weights for policy 1, policy_version 62320 (0.0007) -[2023-10-09 02:36:03,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 127598592. Throughput: 0: 1688.3, 1: 1707.0. Samples: 31912470. Policy #0 lag: (min: 26.0, avg: 41.5, max: 58.0) -[2023-10-09 02:36:03,975][87372] Avg episode reward: [(0, '6.520'), (1, '7.380')] -[2023-10-09 02:36:03,986][88327] Updated weights for policy 1, policy_version 62330 (0.0009) -[2023-10-09 02:36:06,390][88326] Updated weights for policy 0, policy_version 62312 (0.0007) -[2023-10-09 02:36:06,758][88326] Updated weights for policy 0, policy_version 62322 (0.0009) -[2023-10-09 02:36:07,126][88326] Updated weights for policy 0, policy_version 62332 (0.0010) -[2023-10-09 02:36:07,955][88327] Updated weights for policy 1, policy_version 62340 (0.0010) -[2023-10-09 02:36:08,328][88327] Updated weights for policy 1, policy_version 62350 (0.0008) -[2023-10-09 02:36:08,686][88327] Updated weights for policy 1, policy_version 62360 (0.0009) -[2023-10-09 02:36:08,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 127664128. Throughput: 0: 1703.9, 1: 1710.4. Samples: 31922962. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-09 02:36:08,975][87372] Avg episode reward: [(0, '6.350'), (1, '7.340')] -[2023-10-09 02:36:11,301][88326] Updated weights for policy 0, policy_version 62342 (0.0008) -[2023-10-09 02:36:11,670][88326] Updated weights for policy 0, policy_version 62352 (0.0009) -[2023-10-09 02:36:12,044][88326] Updated weights for policy 0, policy_version 62362 (0.0010) -[2023-10-09 02:36:12,794][88327] Updated weights for policy 1, policy_version 62370 (0.0008) -[2023-10-09 02:36:13,198][88327] Updated weights for policy 1, policy_version 62380 (0.0008) -[2023-10-09 02:36:13,563][88327] Updated weights for policy 1, policy_version 62390 (0.0009) -[2023-10-09 02:36:13,925][88327] Updated weights for policy 1, policy_version 62400 (0.0008) -[2023-10-09 02:36:13,974][87372] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 127762432. Throughput: 0: 1673.5, 1: 1714.0. Samples: 31942902. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-09 02:36:13,974][87372] Avg episode reward: [(0, '6.690'), (1, '6.220')] -[2023-10-09 02:36:16,224][88326] Updated weights for policy 0, policy_version 62372 (0.0009) -[2023-10-09 02:36:16,619][88326] Updated weights for policy 0, policy_version 62382 (0.0007) -[2023-10-09 02:36:16,991][88326] Updated weights for policy 0, policy_version 62392 (0.0008) -[2023-10-09 02:36:17,775][88327] Updated weights for policy 1, policy_version 62410 (0.0007) -[2023-10-09 02:36:18,132][88327] Updated weights for policy 1, policy_version 62420 (0.0007) -[2023-10-09 02:36:18,501][88327] Updated weights for policy 1, policy_version 62430 (0.0010) -[2023-10-09 02:36:18,974][87372] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 127827968. Throughput: 0: 1690.3, 1: 1692.6. Samples: 31962842. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-09 02:36:18,975][87372] Avg episode reward: [(0, '7.150'), (1, '6.390')] -[2023-10-09 02:36:20,993][88326] Updated weights for policy 0, policy_version 62402 (0.0008) -[2023-10-09 02:36:21,361][88326] Updated weights for policy 0, policy_version 62412 (0.0008) -[2023-10-09 02:36:21,729][88326] Updated weights for policy 0, policy_version 62422 (0.0011) -[2023-10-09 02:36:22,091][88326] Updated weights for policy 0, policy_version 62432 (0.0009) -[2023-10-09 02:36:22,526][88327] Updated weights for policy 1, policy_version 62440 (0.0010) -[2023-10-09 02:36:22,897][88327] Updated weights for policy 1, policy_version 62450 (0.0012) -[2023-10-09 02:36:23,262][88327] Updated weights for policy 1, policy_version 62460 (0.0011) -[2023-10-09 02:36:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 127893504. Throughput: 0: 1695.2, 1: 1710.9. Samples: 31973832. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-09 02:36:23,974][87372] Avg episode reward: [(0, '7.030'), (1, '6.950')] -[2023-10-09 02:36:26,143][88326] Updated weights for policy 0, policy_version 62442 (0.0008) -[2023-10-09 02:36:26,504][88326] Updated weights for policy 0, policy_version 62452 (0.0007) -[2023-10-09 02:36:26,876][88326] Updated weights for policy 0, policy_version 62462 (0.0007) -[2023-10-09 02:36:27,203][88327] Updated weights for policy 1, policy_version 62470 (0.0011) -[2023-10-09 02:36:27,572][88327] Updated weights for policy 1, policy_version 62480 (0.0011) -[2023-10-09 02:36:27,940][88327] Updated weights for policy 1, policy_version 62490 (0.0010) -[2023-10-09 02:36:28,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 127959040. Throughput: 0: 1678.2, 1: 1707.4. Samples: 31993626. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-09 02:36:28,975][87372] Avg episode reward: [(0, '7.100'), (1, '6.560')] -[2023-10-09 02:36:30,820][88326] Updated weights for policy 0, policy_version 62472 (0.0008) -[2023-10-09 02:36:31,189][88326] Updated weights for policy 0, policy_version 62482 (0.0009) -[2023-10-09 02:36:31,562][88326] Updated weights for policy 0, policy_version 62492 (0.0010) -[2023-10-09 02:36:32,198][88327] Updated weights for policy 1, policy_version 62500 (0.0009) -[2023-10-09 02:36:32,563][88327] Updated weights for policy 1, policy_version 62510 (0.0007) -[2023-10-09 02:36:32,923][88327] Updated weights for policy 1, policy_version 62520 (0.0008) -[2023-10-09 02:36:33,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 128024576. Throughput: 0: 1703.1, 1: 1678.9. Samples: 32013518. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-09 02:36:33,975][87372] Avg episode reward: [(0, '7.170'), (1, '6.880')] -[2023-10-09 02:36:33,984][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000062528_64028672.pth... -[2023-10-09 02:36:33,984][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000062496_63995904.pth... -[2023-10-09 02:36:34,019][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000060928_62390272.pth -[2023-10-09 02:36:34,020][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000060928_62390272.pth -[2023-10-09 02:36:35,328][88326] Updated weights for policy 0, policy_version 62502 (0.0009) -[2023-10-09 02:36:35,696][88326] Updated weights for policy 0, policy_version 62512 (0.0009) -[2023-10-09 02:36:36,071][88326] Updated weights for policy 0, policy_version 62522 (0.0010) -[2023-10-09 02:36:37,042][88327] Updated weights for policy 1, policy_version 62530 (0.0007) -[2023-10-09 02:36:37,396][88327] Updated weights for policy 1, policy_version 62540 (0.0008) -[2023-10-09 02:36:37,761][88327] Updated weights for policy 1, policy_version 62550 (0.0009) -[2023-10-09 02:36:38,128][88327] Updated weights for policy 1, policy_version 62560 (0.0011) -[2023-10-09 02:36:38,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 128090112. Throughput: 0: 1674.6, 1: 1703.3. Samples: 32023936. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-09 02:36:38,975][87372] Avg episode reward: [(0, '7.000'), (1, '7.450')] -[2023-10-09 02:36:40,165][88326] Updated weights for policy 0, policy_version 62532 (0.0009) -[2023-10-09 02:36:40,530][88326] Updated weights for policy 0, policy_version 62542 (0.0011) -[2023-10-09 02:36:40,901][88326] Updated weights for policy 0, policy_version 62552 (0.0010) -[2023-10-09 02:36:42,270][88327] Updated weights for policy 1, policy_version 62570 (0.0009) -[2023-10-09 02:36:42,638][88327] Updated weights for policy 1, policy_version 62580 (0.0007) -[2023-10-09 02:36:43,001][88327] Updated weights for policy 1, policy_version 62590 (0.0010) -[2023-10-09 02:36:43,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 128155648. Throughput: 0: 1691.2, 1: 1697.5. Samples: 32044470. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-09 02:36:43,975][87372] Avg episode reward: [(0, '6.810'), (1, '7.060')] -[2023-10-09 02:36:44,937][88326] Updated weights for policy 0, policy_version 62562 (0.0008) -[2023-10-09 02:36:45,305][88326] Updated weights for policy 0, policy_version 62572 (0.0008) -[2023-10-09 02:36:45,681][88326] Updated weights for policy 0, policy_version 62582 (0.0009) -[2023-10-09 02:36:46,050][88326] Updated weights for policy 0, policy_version 62592 (0.0010) -[2023-10-09 02:36:46,995][88327] Updated weights for policy 1, policy_version 62600 (0.0008) -[2023-10-09 02:36:47,362][88327] Updated weights for policy 1, policy_version 62610 (0.0008) -[2023-10-09 02:36:47,727][88327] Updated weights for policy 1, policy_version 62620 (0.0008) -[2023-10-09 02:36:48,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 128221184. Throughput: 0: 1701.9, 1: 1675.6. Samples: 32064458. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-09 02:36:48,975][87372] Avg episode reward: [(0, '7.420'), (1, '6.950')] -[2023-10-09 02:36:50,014][88326] Updated weights for policy 0, policy_version 62602 (0.0007) -[2023-10-09 02:36:50,379][88326] Updated weights for policy 0, policy_version 62612 (0.0008) -[2023-10-09 02:36:50,752][88326] Updated weights for policy 0, policy_version 62622 (0.0009) -[2023-10-09 02:36:51,823][88327] Updated weights for policy 1, policy_version 62630 (0.0008) -[2023-10-09 02:36:52,192][88327] Updated weights for policy 1, policy_version 62640 (0.0008) -[2023-10-09 02:36:52,555][88327] Updated weights for policy 1, policy_version 62650 (0.0008) -[2023-10-09 02:36:53,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 128286720. Throughput: 0: 1676.5, 1: 1698.8. Samples: 32074850. Policy #0 lag: (min: 30.0, avg: 42.1, max: 62.0) -[2023-10-09 02:36:53,975][87372] Avg episode reward: [(0, '6.560'), (1, '6.690')] -[2023-10-09 02:36:54,750][88326] Updated weights for policy 0, policy_version 62632 (0.0009) -[2023-10-09 02:36:55,114][88326] Updated weights for policy 0, policy_version 62642 (0.0009) -[2023-10-09 02:36:55,482][88326] Updated weights for policy 0, policy_version 62652 (0.0011) -[2023-10-09 02:36:56,557][88327] Updated weights for policy 1, policy_version 62660 (0.0007) -[2023-10-09 02:36:56,920][88327] Updated weights for policy 1, policy_version 62670 (0.0010) -[2023-10-09 02:36:57,292][88327] Updated weights for policy 1, policy_version 62680 (0.0010) -[2023-10-09 02:36:58,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 128352256. Throughput: 0: 1703.9, 1: 1678.6. Samples: 32095114. Policy #0 lag: (min: 30.0, avg: 42.1, max: 62.0) -[2023-10-09 02:36:58,974][87372] Avg episode reward: [(0, '6.740'), (1, '7.190')] -[2023-10-09 02:36:59,548][88326] Updated weights for policy 0, policy_version 62662 (0.0008) -[2023-10-09 02:36:59,917][88326] Updated weights for policy 0, policy_version 62672 (0.0008) -[2023-10-09 02:37:00,287][88326] Updated weights for policy 0, policy_version 62682 (0.0007) -[2023-10-09 02:37:01,151][88327] Updated weights for policy 1, policy_version 62690 (0.0010) -[2023-10-09 02:37:01,553][88327] Updated weights for policy 1, policy_version 62700 (0.0008) -[2023-10-09 02:37:01,924][88327] Updated weights for policy 1, policy_version 62710 (0.0009) -[2023-10-09 02:37:02,298][88327] Updated weights for policy 1, policy_version 62720 (0.0008) -[2023-10-09 02:37:03,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 128417792. Throughput: 0: 1712.6, 1: 1678.6. Samples: 32115448. Policy #0 lag: (min: 30.0, avg: 42.1, max: 62.0) -[2023-10-09 02:37:03,975][87372] Avg episode reward: [(0, '7.230'), (1, '6.950')] -[2023-10-09 02:37:04,348][88326] Updated weights for policy 0, policy_version 62692 (0.0008) -[2023-10-09 02:37:04,730][88326] Updated weights for policy 0, policy_version 62702 (0.0008) -[2023-10-09 02:37:05,096][88326] Updated weights for policy 0, policy_version 62712 (0.0007) -[2023-10-09 02:37:06,314][88327] Updated weights for policy 1, policy_version 62730 (0.0007) -[2023-10-09 02:37:06,680][88327] Updated weights for policy 1, policy_version 62740 (0.0007) -[2023-10-09 02:37:07,052][88327] Updated weights for policy 1, policy_version 62750 (0.0010) -[2023-10-09 02:37:08,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 128483328. Throughput: 0: 1687.0, 1: 1686.0. Samples: 32125616. Policy #0 lag: (min: 30.0, avg: 42.1, max: 62.0) -[2023-10-09 02:37:08,975][87372] Avg episode reward: [(0, '7.030'), (1, '6.880')] -[2023-10-09 02:37:09,034][88326] Updated weights for policy 0, policy_version 62722 (0.0008) -[2023-10-09 02:37:09,404][88326] Updated weights for policy 0, policy_version 62732 (0.0007) -[2023-10-09 02:37:09,768][88326] Updated weights for policy 0, policy_version 62742 (0.0008) -[2023-10-09 02:37:10,130][88326] Updated weights for policy 0, policy_version 62752 (0.0007) -[2023-10-09 02:37:11,293][88327] Updated weights for policy 1, policy_version 62760 (0.0007) -[2023-10-09 02:37:11,657][88327] Updated weights for policy 1, policy_version 62770 (0.0008) -[2023-10-09 02:37:12,020][88327] Updated weights for policy 1, policy_version 62780 (0.0010) -[2023-10-09 02:37:13,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 128548864. Throughput: 0: 1710.3, 1: 1663.2. Samples: 32145430. Policy #0 lag: (min: 30.0, avg: 42.1, max: 62.0) -[2023-10-09 02:37:13,975][87372] Avg episode reward: [(0, '6.840'), (1, '7.400')] -[2023-10-09 02:37:14,277][88326] Updated weights for policy 0, policy_version 62762 (0.0008) -[2023-10-09 02:37:14,658][88326] Updated weights for policy 0, policy_version 62772 (0.0008) -[2023-10-09 02:37:15,019][88326] Updated weights for policy 0, policy_version 62782 (0.0008) -[2023-10-09 02:37:15,934][88327] Updated weights for policy 1, policy_version 62790 (0.0008) -[2023-10-09 02:37:16,301][88327] Updated weights for policy 1, policy_version 62800 (0.0007) -[2023-10-09 02:37:16,667][88327] Updated weights for policy 1, policy_version 62810 (0.0008) -[2023-10-09 02:37:18,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 128614400. Throughput: 0: 1703.6, 1: 1693.7. Samples: 32166394. Policy #0 lag: (min: 30.0, avg: 42.1, max: 62.0) -[2023-10-09 02:37:18,975][87372] Avg episode reward: [(0, '7.100'), (1, '7.640')] -[2023-10-09 02:37:19,051][88326] Updated weights for policy 0, policy_version 62792 (0.0009) -[2023-10-09 02:37:19,419][88326] Updated weights for policy 0, policy_version 62802 (0.0008) -[2023-10-09 02:37:19,787][88326] Updated weights for policy 0, policy_version 62812 (0.0008) -[2023-10-09 02:37:20,740][88327] Updated weights for policy 1, policy_version 62820 (0.0011) -[2023-10-09 02:37:21,098][88327] Updated weights for policy 1, policy_version 62830 (0.0011) -[2023-10-09 02:37:21,460][88327] Updated weights for policy 1, policy_version 62840 (0.0009) -[2023-10-09 02:37:23,788][88326] Updated weights for policy 0, policy_version 62822 (0.0011) -[2023-10-09 02:37:23,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 128679936. Throughput: 0: 1698.7, 1: 1689.8. Samples: 32176418. Policy #0 lag: (min: 30.0, avg: 42.1, max: 62.0) -[2023-10-09 02:37:23,975][87372] Avg episode reward: [(0, '6.560'), (1, '7.180')] -[2023-10-09 02:37:24,160][88326] Updated weights for policy 0, policy_version 62832 (0.0010) -[2023-10-09 02:37:24,529][88326] Updated weights for policy 0, policy_version 62842 (0.0009) -[2023-10-09 02:37:25,363][88327] Updated weights for policy 1, policy_version 62850 (0.0011) -[2023-10-09 02:37:25,732][88327] Updated weights for policy 1, policy_version 62860 (0.0010) -[2023-10-09 02:37:26,090][88327] Updated weights for policy 1, policy_version 62870 (0.0007) -[2023-10-09 02:37:26,456][88327] Updated weights for policy 1, policy_version 62880 (0.0007) -[2023-10-09 02:37:28,551][88326] Updated weights for policy 0, policy_version 62852 (0.0007) -[2023-10-09 02:37:28,926][88326] Updated weights for policy 0, policy_version 62862 (0.0008) -[2023-10-09 02:37:28,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 128745472. Throughput: 0: 1706.2, 1: 1681.4. Samples: 32196912. Policy #0 lag: (min: 30.0, avg: 42.1, max: 62.0) -[2023-10-09 02:37:28,975][87372] Avg episode reward: [(0, '6.860'), (1, '7.100')] -[2023-10-09 02:37:29,289][88326] Updated weights for policy 0, policy_version 62872 (0.0009) -[2023-10-09 02:37:30,334][88327] Updated weights for policy 1, policy_version 62890 (0.0007) -[2023-10-09 02:37:30,699][88327] Updated weights for policy 1, policy_version 62900 (0.0008) -[2023-10-09 02:37:31,064][88327] Updated weights for policy 1, policy_version 62910 (0.0007) -[2023-10-09 02:37:33,303][88326] Updated weights for policy 0, policy_version 62882 (0.0009) -[2023-10-09 02:37:33,667][88326] Updated weights for policy 0, policy_version 62892 (0.0010) -[2023-10-09 02:37:33,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 128811008. Throughput: 0: 1704.5, 1: 1709.8. Samples: 32218104. Policy #0 lag: (min: 30.0, avg: 42.1, max: 62.0) -[2023-10-09 02:37:33,974][87372] Avg episode reward: [(0, '6.780'), (1, '7.280')] -[2023-10-09 02:37:34,039][88326] Updated weights for policy 0, policy_version 62902 (0.0010) -[2023-10-09 02:37:34,397][88326] Updated weights for policy 0, policy_version 62912 (0.0007) -[2023-10-09 02:37:35,184][88327] Updated weights for policy 1, policy_version 62920 (0.0007) -[2023-10-09 02:37:35,553][88327] Updated weights for policy 1, policy_version 62930 (0.0009) -[2023-10-09 02:37:35,922][88327] Updated weights for policy 1, policy_version 62940 (0.0009) -[2023-10-09 02:37:38,428][88326] Updated weights for policy 0, policy_version 62922 (0.0009) -[2023-10-09 02:37:38,791][88326] Updated weights for policy 0, policy_version 62932 (0.0008) -[2023-10-09 02:37:38,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 128876544. Throughput: 0: 1706.6, 1: 1684.3. Samples: 32227440. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-09 02:37:38,974][87372] Avg episode reward: [(0, '6.690'), (1, '6.360')] -[2023-10-09 02:37:39,163][88326] Updated weights for policy 0, policy_version 62942 (0.0010) -[2023-10-09 02:37:39,793][88327] Updated weights for policy 1, policy_version 62950 (0.0009) -[2023-10-09 02:37:40,168][88327] Updated weights for policy 1, policy_version 62960 (0.0008) -[2023-10-09 02:37:40,531][88327] Updated weights for policy 1, policy_version 62970 (0.0008) -[2023-10-09 02:37:43,260][88326] Updated weights for policy 0, policy_version 62952 (0.0008) -[2023-10-09 02:37:43,632][88326] Updated weights for policy 0, policy_version 62962 (0.0008) -[2023-10-09 02:37:43,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 128942080. Throughput: 0: 1703.7, 1: 1705.6. Samples: 32248534. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-09 02:37:43,974][87372] Avg episode reward: [(0, '6.450'), (1, '6.620')] -[2023-10-09 02:37:43,993][88326] Updated weights for policy 0, policy_version 62972 (0.0009) -[2023-10-09 02:37:44,367][88327] Updated weights for policy 1, policy_version 62980 (0.0010) -[2023-10-09 02:37:44,734][88327] Updated weights for policy 1, policy_version 62990 (0.0008) -[2023-10-09 02:37:45,106][88327] Updated weights for policy 1, policy_version 63000 (0.0008) -[2023-10-09 02:37:47,990][88326] Updated weights for policy 0, policy_version 62982 (0.0010) -[2023-10-09 02:37:48,360][88326] Updated weights for policy 0, policy_version 62992 (0.0010) -[2023-10-09 02:37:48,737][88326] Updated weights for policy 0, policy_version 63002 (0.0010) -[2023-10-09 02:37:48,974][87372] Fps is (10 sec: 16384.0, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 129040384. Throughput: 0: 1692.0, 1: 1729.5. Samples: 32269412. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-09 02:37:48,974][87372] Avg episode reward: [(0, '7.150'), (1, '7.270')] -[2023-10-09 02:37:49,015][88327] Updated weights for policy 1, policy_version 63010 (0.0010) -[2023-10-09 02:37:49,402][88327] Updated weights for policy 1, policy_version 63020 (0.0008) -[2023-10-09 02:37:49,781][88327] Updated weights for policy 1, policy_version 63030 (0.0009) -[2023-10-09 02:37:50,150][88327] Updated weights for policy 1, policy_version 63040 (0.0010) -[2023-10-09 02:37:52,711][88326] Updated weights for policy 0, policy_version 63012 (0.0008) -[2023-10-09 02:37:53,110][88326] Updated weights for policy 0, policy_version 63022 (0.0009) -[2023-10-09 02:37:53,473][88326] Updated weights for policy 0, policy_version 63032 (0.0007) -[2023-10-09 02:37:53,974][87372] Fps is (10 sec: 16383.6, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 129105920. Throughput: 0: 1707.2, 1: 1702.3. Samples: 32279042. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-09 02:37:53,975][87372] Avg episode reward: [(0, '7.500'), (1, '6.800')] -[2023-10-09 02:37:54,142][88327] Updated weights for policy 1, policy_version 63050 (0.0009) -[2023-10-09 02:37:54,513][88327] Updated weights for policy 1, policy_version 63060 (0.0009) -[2023-10-09 02:37:54,884][88327] Updated weights for policy 1, policy_version 63070 (0.0011) -[2023-10-09 02:37:57,448][88326] Updated weights for policy 0, policy_version 63042 (0.0008) -[2023-10-09 02:37:57,815][88326] Updated weights for policy 0, policy_version 63052 (0.0011) -[2023-10-09 02:37:58,190][88326] Updated weights for policy 0, policy_version 63062 (0.0010) -[2023-10-09 02:37:58,555][88326] Updated weights for policy 0, policy_version 63072 (0.0008) -[2023-10-09 02:37:58,702][88327] Updated weights for policy 1, policy_version 63080 (0.0010) -[2023-10-09 02:37:58,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 129171456. Throughput: 0: 1700.4, 1: 1731.2. Samples: 32299854. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-09 02:37:58,975][87372] Avg episode reward: [(0, '7.510'), (1, '7.060')] -[2023-10-09 02:37:59,076][88327] Updated weights for policy 1, policy_version 63090 (0.0008) -[2023-10-09 02:37:59,436][88327] Updated weights for policy 1, policy_version 63100 (0.0007) -[2023-10-09 02:38:02,695][88326] Updated weights for policy 0, policy_version 63082 (0.0008) -[2023-10-09 02:38:03,067][88326] Updated weights for policy 0, policy_version 63092 (0.0010) -[2023-10-09 02:38:03,439][88326] Updated weights for policy 0, policy_version 63102 (0.0008) -[2023-10-09 02:38:03,530][88327] Updated weights for policy 1, policy_version 63110 (0.0007) -[2023-10-09 02:38:03,894][88327] Updated weights for policy 1, policy_version 63120 (0.0009) -[2023-10-09 02:38:03,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 129236992. Throughput: 0: 1678.4, 1: 1730.9. Samples: 32319814. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-09 02:38:03,975][87372] Avg episode reward: [(0, '7.490'), (1, '7.170')] -[2023-10-09 02:38:04,268][88327] Updated weights for policy 1, policy_version 63130 (0.0011) -[2023-10-09 02:38:07,367][88326] Updated weights for policy 0, policy_version 63112 (0.0010) -[2023-10-09 02:38:07,733][88326] Updated weights for policy 0, policy_version 63122 (0.0010) -[2023-10-09 02:38:08,099][88326] Updated weights for policy 0, policy_version 63132 (0.0010) -[2023-10-09 02:38:08,473][88327] Updated weights for policy 1, policy_version 63140 (0.0010) -[2023-10-09 02:38:08,839][88327] Updated weights for policy 1, policy_version 63150 (0.0008) -[2023-10-09 02:38:08,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 129302528. Throughput: 0: 1698.6, 1: 1709.8. Samples: 32329794. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-09 02:38:08,975][87372] Avg episode reward: [(0, '6.880'), (1, '7.200')] -[2023-10-09 02:38:09,206][88327] Updated weights for policy 1, policy_version 63160 (0.0009) -[2023-10-09 02:38:12,027][88326] Updated weights for policy 0, policy_version 63142 (0.0009) -[2023-10-09 02:38:12,389][88326] Updated weights for policy 0, policy_version 63152 (0.0007) -[2023-10-09 02:38:12,772][88326] Updated weights for policy 0, policy_version 63162 (0.0008) -[2023-10-09 02:38:13,206][88327] Updated weights for policy 1, policy_version 63170 (0.0008) -[2023-10-09 02:38:13,573][88327] Updated weights for policy 1, policy_version 63180 (0.0009) -[2023-10-09 02:38:13,949][88327] Updated weights for policy 1, policy_version 63190 (0.0010) -[2023-10-09 02:38:13,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 129368064. Throughput: 0: 1689.8, 1: 1717.4. Samples: 32350236. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-09 02:38:13,974][87372] Avg episode reward: [(0, '6.850'), (1, '7.430')] -[2023-10-09 02:38:14,305][88327] Updated weights for policy 1, policy_version 63200 (0.0010) -[2023-10-09 02:38:16,681][88326] Updated weights for policy 0, policy_version 63172 (0.0009) -[2023-10-09 02:38:17,046][88326] Updated weights for policy 0, policy_version 63182 (0.0007) -[2023-10-09 02:38:17,420][88326] Updated weights for policy 0, policy_version 63192 (0.0007) -[2023-10-09 02:38:18,430][88327] Updated weights for policy 1, policy_version 63210 (0.0009) -[2023-10-09 02:38:18,788][88327] Updated weights for policy 1, policy_version 63220 (0.0008) -[2023-10-09 02:38:18,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 129433600. Throughput: 0: 1669.2, 1: 1710.8. Samples: 32370208. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-09 02:38:18,975][87372] Avg episode reward: [(0, '6.670'), (1, '7.220')] -[2023-10-09 02:38:19,157][88327] Updated weights for policy 1, policy_version 63230 (0.0007) -[2023-10-09 02:38:21,472][88326] Updated weights for policy 0, policy_version 63202 (0.0007) -[2023-10-09 02:38:21,837][88326] Updated weights for policy 0, policy_version 63212 (0.0008) -[2023-10-09 02:38:22,207][88326] Updated weights for policy 0, policy_version 63222 (0.0009) -[2023-10-09 02:38:22,575][88326] Updated weights for policy 0, policy_version 63232 (0.0009) -[2023-10-09 02:38:23,123][88327] Updated weights for policy 1, policy_version 63240 (0.0007) -[2023-10-09 02:38:23,482][88327] Updated weights for policy 1, policy_version 63250 (0.0009) -[2023-10-09 02:38:23,853][88327] Updated weights for policy 1, policy_version 63260 (0.0009) -[2023-10-09 02:38:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 129499136. Throughput: 0: 1700.5, 1: 1709.9. Samples: 32380908. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-09 02:38:23,974][87372] Avg episode reward: [(0, '6.770'), (1, '7.200')] -[2023-10-09 02:38:26,549][88326] Updated weights for policy 0, policy_version 63242 (0.0008) -[2023-10-09 02:38:26,916][88326] Updated weights for policy 0, policy_version 63252 (0.0009) -[2023-10-09 02:38:27,277][88326] Updated weights for policy 0, policy_version 63262 (0.0009) -[2023-10-09 02:38:27,963][88327] Updated weights for policy 1, policy_version 63270 (0.0010) -[2023-10-09 02:38:28,326][88327] Updated weights for policy 1, policy_version 63280 (0.0008) -[2023-10-09 02:38:28,687][88327] Updated weights for policy 1, policy_version 63290 (0.0007) -[2023-10-09 02:38:28,974][87372] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 129597440. Throughput: 0: 1682.5, 1: 1704.7. Samples: 32400956. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-09 02:38:28,974][87372] Avg episode reward: [(0, '7.170'), (1, '7.370')] -[2023-10-09 02:38:31,389][88326] Updated weights for policy 0, policy_version 63272 (0.0008) -[2023-10-09 02:38:31,756][88326] Updated weights for policy 0, policy_version 63282 (0.0009) -[2023-10-09 02:38:32,126][88326] Updated weights for policy 0, policy_version 63292 (0.0010) -[2023-10-09 02:38:32,715][88327] Updated weights for policy 1, policy_version 63300 (0.0007) -[2023-10-09 02:38:33,085][88327] Updated weights for policy 1, policy_version 63310 (0.0008) -[2023-10-09 02:38:33,453][88327] Updated weights for policy 1, policy_version 63320 (0.0007) -[2023-10-09 02:38:33,974][87372] Fps is (10 sec: 16383.3, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 129662976. Throughput: 0: 1684.0, 1: 1683.7. Samples: 32420960. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-09 02:38:33,975][87372] Avg episode reward: [(0, '7.540'), (1, '7.240')] -[2023-10-09 02:38:33,985][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000063328_64847872.pth... -[2023-10-09 02:38:33,985][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000063296_64815104.pth... -[2023-10-09 02:38:34,015][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000061728_63209472.pth -[2023-10-09 02:38:34,020][88168] Saving a milestone ./train_atari/atari_battlezone_APPO/checkpoint_p1/milestones/checkpoint_000063328_64847872.pth -[2023-10-09 02:38:34,025][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000061696_63176704.pth -[2023-10-09 02:38:34,031][88088] Saving a milestone ./train_atari/atari_battlezone_APPO/checkpoint_p0/milestones/checkpoint_000063296_64815104.pth -[2023-10-09 02:38:36,251][88326] Updated weights for policy 0, policy_version 63302 (0.0007) -[2023-10-09 02:38:36,616][88326] Updated weights for policy 0, policy_version 63312 (0.0010) -[2023-10-09 02:38:36,985][88326] Updated weights for policy 0, policy_version 63322 (0.0009) -[2023-10-09 02:38:37,667][88327] Updated weights for policy 1, policy_version 63330 (0.0008) -[2023-10-09 02:38:38,089][88327] Updated weights for policy 1, policy_version 63340 (0.0008) -[2023-10-09 02:38:38,462][88327] Updated weights for policy 1, policy_version 63350 (0.0010) -[2023-10-09 02:38:38,821][88327] Updated weights for policy 1, policy_version 63360 (0.0010) -[2023-10-09 02:38:38,974][87372] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 129728512. Throughput: 0: 1696.1, 1: 1693.8. Samples: 32431584. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-09 02:38:38,975][87372] Avg episode reward: [(0, '7.810'), (1, '7.060')] -[2023-10-09 02:38:41,045][88326] Updated weights for policy 0, policy_version 63332 (0.0008) -[2023-10-09 02:38:41,414][88326] Updated weights for policy 0, policy_version 63342 (0.0007) -[2023-10-09 02:38:41,783][88326] Updated weights for policy 0, policy_version 63352 (0.0009) -[2023-10-09 02:38:42,779][88327] Updated weights for policy 1, policy_version 63370 (0.0007) -[2023-10-09 02:38:43,146][88327] Updated weights for policy 1, policy_version 63380 (0.0009) -[2023-10-09 02:38:43,502][88327] Updated weights for policy 1, policy_version 63390 (0.0007) -[2023-10-09 02:38:43,974][87372] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 129794048. Throughput: 0: 1677.9, 1: 1689.5. Samples: 32451388. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-09 02:38:43,974][87372] Avg episode reward: [(0, '7.530'), (1, '7.560')] -[2023-10-09 02:38:45,809][88326] Updated weights for policy 0, policy_version 63362 (0.0010) -[2023-10-09 02:38:46,229][88326] Updated weights for policy 0, policy_version 63372 (0.0010) -[2023-10-09 02:38:46,600][88326] Updated weights for policy 0, policy_version 63382 (0.0007) -[2023-10-09 02:38:46,973][88326] Updated weights for policy 0, policy_version 63392 (0.0007) -[2023-10-09 02:38:47,375][88327] Updated weights for policy 1, policy_version 63400 (0.0009) -[2023-10-09 02:38:47,738][88327] Updated weights for policy 1, policy_version 63410 (0.0009) -[2023-10-09 02:38:48,108][88327] Updated weights for policy 1, policy_version 63420 (0.0008) -[2023-10-09 02:38:48,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 129859584. Throughput: 0: 1698.9, 1: 1665.4. Samples: 32471204. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-09 02:38:48,975][87372] Avg episode reward: [(0, '7.740'), (1, '7.170')] -[2023-10-09 02:38:50,946][88326] Updated weights for policy 0, policy_version 63402 (0.0007) -[2023-10-09 02:38:51,303][88326] Updated weights for policy 0, policy_version 63412 (0.0011) -[2023-10-09 02:38:51,673][88326] Updated weights for policy 0, policy_version 63422 (0.0011) -[2023-10-09 02:38:52,206][88327] Updated weights for policy 1, policy_version 63430 (0.0008) -[2023-10-09 02:38:52,559][88327] Updated weights for policy 1, policy_version 63440 (0.0007) -[2023-10-09 02:38:52,928][88327] Updated weights for policy 1, policy_version 63450 (0.0008) -[2023-10-09 02:38:53,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 129925120. Throughput: 0: 1692.4, 1: 1694.1. Samples: 32482188. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-09 02:38:53,975][87372] Avg episode reward: [(0, '7.040'), (1, '6.460')] -[2023-10-09 02:38:55,586][88326] Updated weights for policy 0, policy_version 63432 (0.0010) -[2023-10-09 02:38:55,953][88326] Updated weights for policy 0, policy_version 63442 (0.0009) -[2023-10-09 02:38:56,313][88326] Updated weights for policy 0, policy_version 63452 (0.0008) -[2023-10-09 02:38:56,917][88327] Updated weights for policy 1, policy_version 63460 (0.0009) -[2023-10-09 02:38:57,282][88327] Updated weights for policy 1, policy_version 63470 (0.0009) -[2023-10-09 02:38:57,650][88327] Updated weights for policy 1, policy_version 63480 (0.0009) -[2023-10-09 02:38:58,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 129990656. Throughput: 0: 1682.8, 1: 1694.3. Samples: 32502202. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-09 02:38:58,975][87372] Avg episode reward: [(0, '6.870'), (1, '7.020')] -[2023-10-09 02:39:00,469][88326] Updated weights for policy 0, policy_version 63462 (0.0009) -[2023-10-09 02:39:00,827][88326] Updated weights for policy 0, policy_version 63472 (0.0011) -[2023-10-09 02:39:01,195][88326] Updated weights for policy 0, policy_version 63482 (0.0008) -[2023-10-09 02:39:01,680][88327] Updated weights for policy 1, policy_version 63490 (0.0009) -[2023-10-09 02:39:02,044][88327] Updated weights for policy 1, policy_version 63500 (0.0008) -[2023-10-09 02:39:02,413][88327] Updated weights for policy 1, policy_version 63510 (0.0008) -[2023-10-09 02:39:02,773][88327] Updated weights for policy 1, policy_version 63520 (0.0007) -[2023-10-09 02:39:03,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 130056192. Throughput: 0: 1702.0, 1: 1682.4. Samples: 32522504. Policy #0 lag: (min: 31.0, avg: 44.1, max: 63.0) -[2023-10-09 02:39:03,974][87372] Avg episode reward: [(0, '6.720'), (1, '7.180')] -[2023-10-09 02:39:05,173][88326] Updated weights for policy 0, policy_version 63492 (0.0009) -[2023-10-09 02:39:05,538][88326] Updated weights for policy 0, policy_version 63502 (0.0008) -[2023-10-09 02:39:05,917][88326] Updated weights for policy 0, policy_version 63512 (0.0007) -[2023-10-09 02:39:06,798][88327] Updated weights for policy 1, policy_version 63530 (0.0009) -[2023-10-09 02:39:07,160][88327] Updated weights for policy 1, policy_version 63540 (0.0009) -[2023-10-09 02:39:07,518][88327] Updated weights for policy 1, policy_version 63550 (0.0007) -[2023-10-09 02:39:08,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 130121728. Throughput: 0: 1672.3, 1: 1710.1. Samples: 32533116. Policy #0 lag: (min: 31.0, avg: 44.1, max: 63.0) -[2023-10-09 02:39:08,975][87372] Avg episode reward: [(0, '6.450'), (1, '6.800')] -[2023-10-09 02:39:09,966][88326] Updated weights for policy 0, policy_version 63522 (0.0007) -[2023-10-09 02:39:10,330][88326] Updated weights for policy 0, policy_version 63532 (0.0007) -[2023-10-09 02:39:10,692][88326] Updated weights for policy 0, policy_version 63542 (0.0009) -[2023-10-09 02:39:11,062][88326] Updated weights for policy 0, policy_version 63552 (0.0009) -[2023-10-09 02:39:11,507][88327] Updated weights for policy 1, policy_version 63560 (0.0007) -[2023-10-09 02:39:11,868][88327] Updated weights for policy 1, policy_version 63570 (0.0010) -[2023-10-09 02:39:12,235][88327] Updated weights for policy 1, policy_version 63580 (0.0008) -[2023-10-09 02:39:13,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 130187264. Throughput: 0: 1689.1, 1: 1693.6. Samples: 32553176. Policy #0 lag: (min: 31.0, avg: 44.1, max: 63.0) -[2023-10-09 02:39:13,975][87372] Avg episode reward: [(0, '6.600'), (1, '7.460')] -[2023-10-09 02:39:15,164][88326] Updated weights for policy 0, policy_version 63562 (0.0007) -[2023-10-09 02:39:15,531][88326] Updated weights for policy 0, policy_version 63572 (0.0009) -[2023-10-09 02:39:15,906][88326] Updated weights for policy 0, policy_version 63582 (0.0010) -[2023-10-09 02:39:16,248][88327] Updated weights for policy 1, policy_version 63590 (0.0008) -[2023-10-09 02:39:16,619][88327] Updated weights for policy 1, policy_version 63600 (0.0011) -[2023-10-09 02:39:16,990][88327] Updated weights for policy 1, policy_version 63610 (0.0010) -[2023-10-09 02:39:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 130252800. Throughput: 0: 1699.3, 1: 1697.6. Samples: 32573820. Policy #0 lag: (min: 31.0, avg: 44.1, max: 63.0) -[2023-10-09 02:39:18,975][87372] Avg episode reward: [(0, '6.980'), (1, '7.290')] -[2023-10-09 02:39:19,869][88326] Updated weights for policy 0, policy_version 63592 (0.0011) -[2023-10-09 02:39:20,245][88326] Updated weights for policy 0, policy_version 63602 (0.0009) -[2023-10-09 02:39:20,611][88326] Updated weights for policy 0, policy_version 63612 (0.0009) -[2023-10-09 02:39:20,878][88327] Updated weights for policy 1, policy_version 63620 (0.0011) -[2023-10-09 02:39:21,240][88327] Updated weights for policy 1, policy_version 63630 (0.0010) -[2023-10-09 02:39:21,608][88327] Updated weights for policy 1, policy_version 63640 (0.0008) -[2023-10-09 02:39:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 130318336. Throughput: 0: 1673.0, 1: 1709.9. Samples: 32583814. Policy #0 lag: (min: 31.0, avg: 44.1, max: 63.0) -[2023-10-09 02:39:23,975][87372] Avg episode reward: [(0, '6.930'), (1, '7.480')] -[2023-10-09 02:39:24,641][88326] Updated weights for policy 0, policy_version 63622 (0.0009) -[2023-10-09 02:39:25,019][88326] Updated weights for policy 0, policy_version 63632 (0.0008) -[2023-10-09 02:39:25,377][88326] Updated weights for policy 0, policy_version 63642 (0.0008) -[2023-10-09 02:39:25,547][88327] Updated weights for policy 1, policy_version 63650 (0.0007) -[2023-10-09 02:39:25,968][88327] Updated weights for policy 1, policy_version 63660 (0.0008) -[2023-10-09 02:39:26,341][88327] Updated weights for policy 1, policy_version 63670 (0.0009) -[2023-10-09 02:39:26,720][88327] Updated weights for policy 1, policy_version 63680 (0.0008) -[2023-10-09 02:39:28,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 130383872. Throughput: 0: 1695.4, 1: 1692.7. Samples: 32603852. Policy #0 lag: (min: 31.0, avg: 44.1, max: 63.0) -[2023-10-09 02:39:28,975][87372] Avg episode reward: [(0, '7.150'), (1, '6.770')] -[2023-10-09 02:39:29,526][88326] Updated weights for policy 0, policy_version 63652 (0.0008) -[2023-10-09 02:39:29,890][88326] Updated weights for policy 0, policy_version 63662 (0.0008) -[2023-10-09 02:39:30,260][88326] Updated weights for policy 0, policy_version 63672 (0.0009) -[2023-10-09 02:39:30,731][88327] Updated weights for policy 1, policy_version 63690 (0.0011) -[2023-10-09 02:39:31,108][88327] Updated weights for policy 1, policy_version 63700 (0.0010) -[2023-10-09 02:39:31,467][88327] Updated weights for policy 1, policy_version 63710 (0.0010) -[2023-10-09 02:39:33,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 130449408. Throughput: 0: 1696.7, 1: 1714.0. Samples: 32624684. Policy #0 lag: (min: 31.0, avg: 44.1, max: 63.0) -[2023-10-09 02:39:33,975][87372] Avg episode reward: [(0, '7.160'), (1, '6.830')] -[2023-10-09 02:39:34,226][88326] Updated weights for policy 0, policy_version 63682 (0.0008) -[2023-10-09 02:39:34,614][88326] Updated weights for policy 0, policy_version 63692 (0.0010) -[2023-10-09 02:39:34,985][88326] Updated weights for policy 0, policy_version 63702 (0.0007) -[2023-10-09 02:39:35,344][88326] Updated weights for policy 0, policy_version 63712 (0.0007) -[2023-10-09 02:39:35,400][88327] Updated weights for policy 1, policy_version 63720 (0.0010) -[2023-10-09 02:39:35,760][88327] Updated weights for policy 1, policy_version 63730 (0.0010) -[2023-10-09 02:39:36,128][88327] Updated weights for policy 1, policy_version 63740 (0.0011) -[2023-10-09 02:39:38,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 130514944. Throughput: 0: 1679.7, 1: 1692.9. Samples: 32633956. Policy #0 lag: (min: 31.0, avg: 44.1, max: 63.0) -[2023-10-09 02:39:38,974][87372] Avg episode reward: [(0, '7.230'), (1, '7.020')] -[2023-10-09 02:39:39,414][88326] Updated weights for policy 0, policy_version 63722 (0.0008) -[2023-10-09 02:39:39,782][88326] Updated weights for policy 0, policy_version 63732 (0.0008) -[2023-10-09 02:39:40,161][88326] Updated weights for policy 0, policy_version 63742 (0.0010) -[2023-10-09 02:39:40,313][88327] Updated weights for policy 1, policy_version 63750 (0.0010) -[2023-10-09 02:39:40,679][88327] Updated weights for policy 1, policy_version 63760 (0.0010) -[2023-10-09 02:39:41,049][88327] Updated weights for policy 1, policy_version 63770 (0.0010) -[2023-10-09 02:39:43,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 130580480. Throughput: 0: 1694.3, 1: 1690.7. Samples: 32654524. Policy #0 lag: (min: 31.0, avg: 44.1, max: 63.0) -[2023-10-09 02:39:43,975][87372] Avg episode reward: [(0, '6.870'), (1, '6.330')] -[2023-10-09 02:39:44,348][88326] Updated weights for policy 0, policy_version 63752 (0.0008) -[2023-10-09 02:39:44,711][88326] Updated weights for policy 0, policy_version 63762 (0.0011) -[2023-10-09 02:39:45,087][88326] Updated weights for policy 0, policy_version 63772 (0.0010) -[2023-10-09 02:39:45,152][88327] Updated weights for policy 1, policy_version 63780 (0.0007) -[2023-10-09 02:39:45,525][88327] Updated weights for policy 1, policy_version 63790 (0.0008) -[2023-10-09 02:39:45,878][88327] Updated weights for policy 1, policy_version 63800 (0.0010) -[2023-10-09 02:39:48,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 130646016. Throughput: 0: 1688.8, 1: 1706.7. Samples: 32675300. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:39:48,975][87372] Avg episode reward: [(0, '6.820'), (1, '6.580')] -[2023-10-09 02:39:49,184][88326] Updated weights for policy 0, policy_version 63782 (0.0008) -[2023-10-09 02:39:49,549][88326] Updated weights for policy 0, policy_version 63792 (0.0009) -[2023-10-09 02:39:49,873][88327] Updated weights for policy 1, policy_version 63810 (0.0008) -[2023-10-09 02:39:49,919][88326] Updated weights for policy 0, policy_version 63802 (0.0010) -[2023-10-09 02:39:50,231][88327] Updated weights for policy 1, policy_version 63820 (0.0009) -[2023-10-09 02:39:50,596][88327] Updated weights for policy 1, policy_version 63830 (0.0007) -[2023-10-09 02:39:50,952][88327] Updated weights for policy 1, policy_version 63840 (0.0007) -[2023-10-09 02:39:53,893][88326] Updated weights for policy 0, policy_version 63812 (0.0008) -[2023-10-09 02:39:53,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 130711552. Throughput: 0: 1685.4, 1: 1677.8. Samples: 32684460. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:39:53,975][87372] Avg episode reward: [(0, '6.630'), (1, '6.880')] -[2023-10-09 02:39:54,265][88326] Updated weights for policy 0, policy_version 63822 (0.0009) -[2023-10-09 02:39:54,628][88326] Updated weights for policy 0, policy_version 63832 (0.0010) -[2023-10-09 02:39:54,956][88327] Updated weights for policy 1, policy_version 63850 (0.0007) -[2023-10-09 02:39:55,325][88327] Updated weights for policy 1, policy_version 63860 (0.0008) -[2023-10-09 02:39:55,689][88327] Updated weights for policy 1, policy_version 63870 (0.0008) -[2023-10-09 02:39:58,678][88326] Updated weights for policy 0, policy_version 63842 (0.0008) -[2023-10-09 02:39:58,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 130777088. Throughput: 0: 1688.6, 1: 1696.3. Samples: 32705496. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:39:58,975][87372] Avg episode reward: [(0, '7.020'), (1, '6.960')] -[2023-10-09 02:39:59,044][88326] Updated weights for policy 0, policy_version 63852 (0.0010) -[2023-10-09 02:39:59,407][88326] Updated weights for policy 0, policy_version 63862 (0.0008) -[2023-10-09 02:39:59,720][88327] Updated weights for policy 1, policy_version 63880 (0.0009) -[2023-10-09 02:39:59,769][88326] Updated weights for policy 0, policy_version 63872 (0.0008) -[2023-10-09 02:40:00,090][88327] Updated weights for policy 1, policy_version 63890 (0.0011) -[2023-10-09 02:40:00,441][88327] Updated weights for policy 1, policy_version 63900 (0.0011) -[2023-10-09 02:40:03,937][88326] Updated weights for policy 0, policy_version 63882 (0.0008) -[2023-10-09 02:40:03,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 130842624. Throughput: 0: 1684.5, 1: 1701.5. Samples: 32726190. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:40:03,974][87372] Avg episode reward: [(0, '7.620'), (1, '7.280')] -[2023-10-09 02:40:04,306][88326] Updated weights for policy 0, policy_version 63892 (0.0008) -[2023-10-09 02:40:04,513][88327] Updated weights for policy 1, policy_version 63910 (0.0009) -[2023-10-09 02:40:04,670][88326] Updated weights for policy 0, policy_version 63902 (0.0007) -[2023-10-09 02:40:04,883][88327] Updated weights for policy 1, policy_version 63920 (0.0011) -[2023-10-09 02:40:05,247][88327] Updated weights for policy 1, policy_version 63930 (0.0008) -[2023-10-09 02:40:08,727][88326] Updated weights for policy 0, policy_version 63912 (0.0007) -[2023-10-09 02:40:08,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 130908160. Throughput: 0: 1686.2, 1: 1679.6. Samples: 32735274. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:40:08,975][87372] Avg episode reward: [(0, '7.010'), (1, '6.870')] -[2023-10-09 02:40:09,098][88326] Updated weights for policy 0, policy_version 63922 (0.0008) -[2023-10-09 02:40:09,332][88327] Updated weights for policy 1, policy_version 63940 (0.0008) -[2023-10-09 02:40:09,464][88326] Updated weights for policy 0, policy_version 63932 (0.0008) -[2023-10-09 02:40:09,697][88327] Updated weights for policy 1, policy_version 63950 (0.0008) -[2023-10-09 02:40:10,070][88327] Updated weights for policy 1, policy_version 63960 (0.0009) -[2023-10-09 02:40:13,588][88326] Updated weights for policy 0, policy_version 63942 (0.0009) -[2023-10-09 02:40:13,953][88326] Updated weights for policy 0, policy_version 63952 (0.0009) -[2023-10-09 02:40:13,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 130973696. Throughput: 0: 1682.4, 1: 1699.4. Samples: 32756036. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:40:13,975][87372] Avg episode reward: [(0, '7.130'), (1, '7.050')] -[2023-10-09 02:40:14,110][88327] Updated weights for policy 1, policy_version 63970 (0.0008) -[2023-10-09 02:40:14,318][88326] Updated weights for policy 0, policy_version 63962 (0.0007) -[2023-10-09 02:40:14,504][88327] Updated weights for policy 1, policy_version 63980 (0.0008) -[2023-10-09 02:40:14,862][88327] Updated weights for policy 1, policy_version 63990 (0.0007) -[2023-10-09 02:40:15,237][88327] Updated weights for policy 1, policy_version 64000 (0.0009) -[2023-10-09 02:40:18,331][88326] Updated weights for policy 0, policy_version 63972 (0.0007) -[2023-10-09 02:40:18,709][88326] Updated weights for policy 0, policy_version 63982 (0.0007) -[2023-10-09 02:40:18,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 131039232. Throughput: 0: 1681.0, 1: 1696.4. Samples: 32776668. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:40:18,975][87372] Avg episode reward: [(0, '6.680'), (1, '7.700')] -[2023-10-09 02:40:19,068][88326] Updated weights for policy 0, policy_version 63992 (0.0008) -[2023-10-09 02:40:19,323][88327] Updated weights for policy 1, policy_version 64010 (0.0008) -[2023-10-09 02:40:19,689][88327] Updated weights for policy 1, policy_version 64020 (0.0008) -[2023-10-09 02:40:20,051][88327] Updated weights for policy 1, policy_version 64030 (0.0007) -[2023-10-09 02:40:23,270][88326] Updated weights for policy 0, policy_version 64002 (0.0009) -[2023-10-09 02:40:23,671][88326] Updated weights for policy 0, policy_version 64012 (0.0008) -[2023-10-09 02:40:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 131104768. Throughput: 0: 1682.9, 1: 1690.8. Samples: 32785772. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:40:23,974][87372] Avg episode reward: [(0, '6.560'), (1, '7.120')] -[2023-10-09 02:40:23,994][88327] Updated weights for policy 1, policy_version 64040 (0.0007) -[2023-10-09 02:40:24,047][88326] Updated weights for policy 0, policy_version 64022 (0.0008) -[2023-10-09 02:40:24,365][88327] Updated weights for policy 1, policy_version 64050 (0.0008) -[2023-10-09 02:40:24,413][88326] Updated weights for policy 0, policy_version 64032 (0.0009) -[2023-10-09 02:40:24,724][88327] Updated weights for policy 1, policy_version 64060 (0.0008) -[2023-10-09 02:40:28,496][88326] Updated weights for policy 0, policy_version 64042 (0.0007) -[2023-10-09 02:40:28,813][88327] Updated weights for policy 1, policy_version 64070 (0.0008) -[2023-10-09 02:40:28,862][88326] Updated weights for policy 0, policy_version 64052 (0.0008) -[2023-10-09 02:40:28,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 131170304. Throughput: 0: 1678.4, 1: 1694.9. Samples: 32806322. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:40:28,975][87372] Avg episode reward: [(0, '6.470'), (1, '6.930')] -[2023-10-09 02:40:29,176][88327] Updated weights for policy 1, policy_version 64080 (0.0008) -[2023-10-09 02:40:29,233][88326] Updated weights for policy 0, policy_version 64062 (0.0009) -[2023-10-09 02:40:29,548][88327] Updated weights for policy 1, policy_version 64090 (0.0008) -[2023-10-09 02:40:33,309][88326] Updated weights for policy 0, policy_version 64072 (0.0007) -[2023-10-09 02:40:33,540][88327] Updated weights for policy 1, policy_version 64100 (0.0008) -[2023-10-09 02:40:33,676][88326] Updated weights for policy 0, policy_version 64082 (0.0008) -[2023-10-09 02:40:33,900][88327] Updated weights for policy 1, policy_version 64110 (0.0008) -[2023-10-09 02:40:33,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 131235840. Throughput: 0: 1677.9, 1: 1694.7. Samples: 32827064. Policy #0 lag: (min: 16.0, avg: 44.1, max: 48.0) -[2023-10-09 02:40:33,975][87372] Avg episode reward: [(0, '6.750'), (1, '7.380')] -[2023-10-09 02:40:34,047][88326] Updated weights for policy 0, policy_version 64092 (0.0008) -[2023-10-09 02:40:34,188][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000064096_65634304.pth... -[2023-10-09 02:40:34,218][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000062496_63995904.pth -[2023-10-09 02:40:34,266][88327] Updated weights for policy 1, policy_version 64120 (0.0008) -[2023-10-09 02:40:34,552][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000064128_65667072.pth... -[2023-10-09 02:40:34,581][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000062528_64028672.pth -[2023-10-09 02:40:38,064][88326] Updated weights for policy 0, policy_version 64102 (0.0009) -[2023-10-09 02:40:38,273][88327] Updated weights for policy 1, policy_version 64130 (0.0008) -[2023-10-09 02:40:38,428][88326] Updated weights for policy 0, policy_version 64112 (0.0007) -[2023-10-09 02:40:38,636][88327] Updated weights for policy 1, policy_version 64140 (0.0008) -[2023-10-09 02:40:38,794][88326] Updated weights for policy 0, policy_version 64122 (0.0007) -[2023-10-09 02:40:38,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 131301376. Throughput: 0: 1684.9, 1: 1696.4. Samples: 32836620. Policy #0 lag: (min: 16.0, avg: 44.1, max: 48.0) -[2023-10-09 02:40:38,975][87372] Avg episode reward: [(0, '6.850'), (1, '6.360')] -[2023-10-09 02:40:38,988][88327] Updated weights for policy 1, policy_version 64150 (0.0008) -[2023-10-09 02:40:39,360][88327] Updated weights for policy 1, policy_version 64160 (0.0010) -[2023-10-09 02:40:42,869][88326] Updated weights for policy 0, policy_version 64132 (0.0009) -[2023-10-09 02:40:43,243][88326] Updated weights for policy 0, policy_version 64142 (0.0010) -[2023-10-09 02:40:43,472][88327] Updated weights for policy 1, policy_version 64170 (0.0007) -[2023-10-09 02:40:43,626][88326] Updated weights for policy 0, policy_version 64152 (0.0009) -[2023-10-09 02:40:43,835][88327] Updated weights for policy 1, policy_version 64180 (0.0009) -[2023-10-09 02:40:43,974][87372] Fps is (10 sec: 16383.9, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 131399680. Throughput: 0: 1682.4, 1: 1692.4. Samples: 32857362. Policy #0 lag: (min: 16.0, avg: 44.1, max: 48.0) -[2023-10-09 02:40:43,975][87372] Avg episode reward: [(0, '7.250'), (1, '6.960')] -[2023-10-09 02:40:44,202][88327] Updated weights for policy 1, policy_version 64190 (0.0008) -[2023-10-09 02:40:47,504][88326] Updated weights for policy 0, policy_version 64162 (0.0008) -[2023-10-09 02:40:47,875][88326] Updated weights for policy 0, policy_version 64172 (0.0010) -[2023-10-09 02:40:48,249][88326] Updated weights for policy 0, policy_version 64182 (0.0008) -[2023-10-09 02:40:48,306][88327] Updated weights for policy 1, policy_version 64200 (0.0008) -[2023-10-09 02:40:48,621][88326] Updated weights for policy 0, policy_version 64192 (0.0007) -[2023-10-09 02:40:48,669][88327] Updated weights for policy 1, policy_version 64210 (0.0008) -[2023-10-09 02:40:48,974][87372] Fps is (10 sec: 16384.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 131465216. Throughput: 0: 1662.0, 1: 1690.9. Samples: 32877074. Policy #0 lag: (min: 16.0, avg: 44.1, max: 48.0) -[2023-10-09 02:40:48,974][87372] Avg episode reward: [(0, '7.110'), (1, '7.000')] -[2023-10-09 02:40:49,033][88327] Updated weights for policy 1, policy_version 64220 (0.0010) -[2023-10-09 02:40:52,820][88326] Updated weights for policy 0, policy_version 64202 (0.0007) -[2023-10-09 02:40:53,025][88327] Updated weights for policy 1, policy_version 64230 (0.0010) -[2023-10-09 02:40:53,188][88326] Updated weights for policy 0, policy_version 64212 (0.0008) -[2023-10-09 02:40:53,395][88327] Updated weights for policy 1, policy_version 64240 (0.0008) -[2023-10-09 02:40:53,551][88326] Updated weights for policy 0, policy_version 64222 (0.0008) -[2023-10-09 02:40:53,763][88327] Updated weights for policy 1, policy_version 64250 (0.0008) -[2023-10-09 02:40:53,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 131530752. Throughput: 0: 1680.4, 1: 1695.0. Samples: 32887166. Policy #0 lag: (min: 16.0, avg: 44.1, max: 48.0) -[2023-10-09 02:40:53,974][87372] Avg episode reward: [(0, '7.560'), (1, '7.330')] -[2023-10-09 02:40:57,566][88326] Updated weights for policy 0, policy_version 64232 (0.0009) -[2023-10-09 02:40:57,790][88327] Updated weights for policy 1, policy_version 64260 (0.0008) -[2023-10-09 02:40:57,935][88326] Updated weights for policy 0, policy_version 64242 (0.0008) -[2023-10-09 02:40:58,149][88327] Updated weights for policy 1, policy_version 64270 (0.0007) -[2023-10-09 02:40:58,293][88326] Updated weights for policy 0, policy_version 64252 (0.0008) -[2023-10-09 02:40:58,513][88327] Updated weights for policy 1, policy_version 64280 (0.0007) -[2023-10-09 02:40:58,974][87372] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 131629056. Throughput: 0: 1683.5, 1: 1697.1. Samples: 32908162. Policy #0 lag: (min: 16.0, avg: 44.1, max: 48.0) -[2023-10-09 02:40:58,975][87372] Avg episode reward: [(0, '7.350'), (1, '7.210')] -[2023-10-09 02:41:02,350][88326] Updated weights for policy 0, policy_version 64262 (0.0008) -[2023-10-09 02:41:02,710][88327] Updated weights for policy 1, policy_version 64290 (0.0007) -[2023-10-09 02:41:02,717][88326] Updated weights for policy 0, policy_version 64272 (0.0008) -[2023-10-09 02:41:03,090][88326] Updated weights for policy 0, policy_version 64282 (0.0008) -[2023-10-09 02:41:03,120][88327] Updated weights for policy 1, policy_version 64300 (0.0009) -[2023-10-09 02:41:03,486][88327] Updated weights for policy 1, policy_version 64310 (0.0009) -[2023-10-09 02:41:03,858][88327] Updated weights for policy 1, policy_version 64320 (0.0010) -[2023-10-09 02:41:03,974][87372] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 131694592. Throughput: 0: 1662.6, 1: 1683.9. Samples: 32927258. Policy #0 lag: (min: 16.0, avg: 44.1, max: 48.0) -[2023-10-09 02:41:03,974][87372] Avg episode reward: [(0, '7.430'), (1, '7.240')] -[2023-10-09 02:41:07,072][88326] Updated weights for policy 0, policy_version 64292 (0.0008) -[2023-10-09 02:41:07,444][88326] Updated weights for policy 0, policy_version 64302 (0.0008) -[2023-10-09 02:41:07,787][88327] Updated weights for policy 1, policy_version 64330 (0.0008) -[2023-10-09 02:41:07,812][88326] Updated weights for policy 0, policy_version 64312 (0.0009) -[2023-10-09 02:41:08,159][88327] Updated weights for policy 1, policy_version 64340 (0.0007) -[2023-10-09 02:41:08,518][88327] Updated weights for policy 1, policy_version 64350 (0.0009) -[2023-10-09 02:41:08,974][87372] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 131760128. Throughput: 0: 1690.3, 1: 1693.6. Samples: 32938048. Policy #0 lag: (min: 16.0, avg: 44.1, max: 48.0) -[2023-10-09 02:41:08,974][87372] Avg episode reward: [(0, '7.500'), (1, '7.340')] -[2023-10-09 02:41:11,977][88326] Updated weights for policy 0, policy_version 64322 (0.0009) -[2023-10-09 02:41:12,353][88326] Updated weights for policy 0, policy_version 64332 (0.0008) -[2023-10-09 02:41:12,697][88327] Updated weights for policy 1, policy_version 64360 (0.0009) -[2023-10-09 02:41:12,710][88326] Updated weights for policy 0, policy_version 64342 (0.0009) -[2023-10-09 02:41:13,067][88327] Updated weights for policy 1, policy_version 64370 (0.0009) -[2023-10-09 02:41:13,078][88326] Updated weights for policy 0, policy_version 64352 (0.0007) -[2023-10-09 02:41:13,430][88327] Updated weights for policy 1, policy_version 64380 (0.0007) -[2023-10-09 02:41:13,974][87372] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 131825664. Throughput: 0: 1686.6, 1: 1697.2. Samples: 32958590. Policy #0 lag: (min: 17.0, avg: 21.7, max: 49.0) -[2023-10-09 02:41:13,975][87372] Avg episode reward: [(0, '7.180'), (1, '7.400')] -[2023-10-09 02:41:16,990][88326] Updated weights for policy 0, policy_version 64362 (0.0008) -[2023-10-09 02:41:17,333][88327] Updated weights for policy 1, policy_version 64390 (0.0008) -[2023-10-09 02:41:17,351][88326] Updated weights for policy 0, policy_version 64372 (0.0008) -[2023-10-09 02:41:17,701][88327] Updated weights for policy 1, policy_version 64400 (0.0008) -[2023-10-09 02:41:17,731][88326] Updated weights for policy 0, policy_version 64382 (0.0007) -[2023-10-09 02:41:18,059][88327] Updated weights for policy 1, policy_version 64410 (0.0010) -[2023-10-09 02:41:18,974][87372] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 131891200. Throughput: 0: 1671.4, 1: 1674.3. Samples: 32977620. Policy #0 lag: (min: 17.0, avg: 21.7, max: 49.0) -[2023-10-09 02:41:18,975][87372] Avg episode reward: [(0, '6.980'), (1, '7.070')] -[2023-10-09 02:41:21,623][88326] Updated weights for policy 0, policy_version 64392 (0.0010) -[2023-10-09 02:41:21,988][88326] Updated weights for policy 0, policy_version 64402 (0.0009) -[2023-10-09 02:41:22,197][88327] Updated weights for policy 1, policy_version 64420 (0.0009) -[2023-10-09 02:41:22,356][88326] Updated weights for policy 0, policy_version 64412 (0.0007) -[2023-10-09 02:41:22,566][88327] Updated weights for policy 1, policy_version 64430 (0.0008) -[2023-10-09 02:41:22,931][88327] Updated weights for policy 1, policy_version 64440 (0.0008) -[2023-10-09 02:41:23,974][87372] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 131956736. Throughput: 0: 1697.2, 1: 1693.0. Samples: 32989182. Policy #0 lag: (min: 17.0, avg: 21.7, max: 49.0) -[2023-10-09 02:41:23,975][87372] Avg episode reward: [(0, '7.190'), (1, '7.010')] -[2023-10-09 02:41:26,338][88326] Updated weights for policy 0, policy_version 64422 (0.0008) -[2023-10-09 02:41:26,712][88326] Updated weights for policy 0, policy_version 64432 (0.0007) -[2023-10-09 02:41:26,968][88327] Updated weights for policy 1, policy_version 64450 (0.0007) -[2023-10-09 02:41:27,095][88326] Updated weights for policy 0, policy_version 64442 (0.0007) -[2023-10-09 02:41:27,340][88327] Updated weights for policy 1, policy_version 64460 (0.0007) -[2023-10-09 02:41:27,700][88327] Updated weights for policy 1, policy_version 64470 (0.0007) -[2023-10-09 02:41:28,064][88327] Updated weights for policy 1, policy_version 64480 (0.0010) -[2023-10-09 02:41:28,974][87372] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 132022272. Throughput: 0: 1678.9, 1: 1686.0. Samples: 33008780. Policy #0 lag: (min: 17.0, avg: 21.7, max: 49.0) -[2023-10-09 02:41:28,975][87372] Avg episode reward: [(0, '6.620'), (1, '7.160')] -[2023-10-09 02:41:31,099][88326] Updated weights for policy 0, policy_version 64452 (0.0007) -[2023-10-09 02:41:31,461][88326] Updated weights for policy 0, policy_version 64462 (0.0007) -[2023-10-09 02:41:31,836][88326] Updated weights for policy 0, policy_version 64472 (0.0008) -[2023-10-09 02:41:32,237][88327] Updated weights for policy 1, policy_version 64490 (0.0009) -[2023-10-09 02:41:32,601][88327] Updated weights for policy 1, policy_version 64500 (0.0009) -[2023-10-09 02:41:32,962][88327] Updated weights for policy 1, policy_version 64510 (0.0008) -[2023-10-09 02:41:33,974][87372] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 132087808. Throughput: 0: 1702.6, 1: 1666.4. Samples: 33028678. Policy #0 lag: (min: 17.0, avg: 21.7, max: 49.0) -[2023-10-09 02:41:33,975][87372] Avg episode reward: [(0, '6.470'), (1, '7.010')] -[2023-10-09 02:41:35,687][88326] Updated weights for policy 0, policy_version 64482 (0.0008) -[2023-10-09 02:41:36,053][88326] Updated weights for policy 0, policy_version 64492 (0.0008) -[2023-10-09 02:41:36,425][88326] Updated weights for policy 0, policy_version 64502 (0.0008) -[2023-10-09 02:41:36,796][88326] Updated weights for policy 0, policy_version 64512 (0.0007) -[2023-10-09 02:41:36,890][88327] Updated weights for policy 1, policy_version 64520 (0.0008) -[2023-10-09 02:41:37,261][88327] Updated weights for policy 1, policy_version 64530 (0.0010) -[2023-10-09 02:41:37,612][88327] Updated weights for policy 1, policy_version 64540 (0.0011) -[2023-10-09 02:41:38,974][87372] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 132153344. Throughput: 0: 1703.1, 1: 1694.1. Samples: 33040044. Policy #0 lag: (min: 17.0, avg: 21.7, max: 49.0) -[2023-10-09 02:41:38,975][87372] Avg episode reward: [(0, '7.020'), (1, '7.420')] -[2023-10-09 02:41:40,868][88326] Updated weights for policy 0, policy_version 64522 (0.0007) -[2023-10-09 02:41:41,229][88326] Updated weights for policy 0, policy_version 64532 (0.0009) -[2023-10-09 02:41:41,586][88327] Updated weights for policy 1, policy_version 64550 (0.0010) -[2023-10-09 02:41:41,602][88326] Updated weights for policy 0, policy_version 64542 (0.0007) -[2023-10-09 02:41:41,946][88327] Updated weights for policy 1, policy_version 64560 (0.0010) -[2023-10-09 02:41:42,308][88327] Updated weights for policy 1, policy_version 64570 (0.0012) -[2023-10-09 02:41:43,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 132218880. Throughput: 0: 1689.7, 1: 1676.9. Samples: 33059660. Policy #0 lag: (min: 17.0, avg: 21.7, max: 49.0) -[2023-10-09 02:41:43,975][87372] Avg episode reward: [(0, '6.890'), (1, '7.350')] -[2023-10-09 02:41:45,755][88326] Updated weights for policy 0, policy_version 64552 (0.0010) -[2023-10-09 02:41:46,124][88326] Updated weights for policy 0, policy_version 64562 (0.0008) -[2023-10-09 02:41:46,432][88327] Updated weights for policy 1, policy_version 64580 (0.0010) -[2023-10-09 02:41:46,499][88326] Updated weights for policy 0, policy_version 64572 (0.0007) -[2023-10-09 02:41:46,796][88327] Updated weights for policy 1, policy_version 64590 (0.0008) -[2023-10-09 02:41:47,163][88327] Updated weights for policy 1, policy_version 64600 (0.0007) -[2023-10-09 02:41:48,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 132284416. Throughput: 0: 1707.4, 1: 1682.9. Samples: 33079820. Policy #0 lag: (min: 17.0, avg: 21.7, max: 49.0) -[2023-10-09 02:41:48,974][87372] Avg episode reward: [(0, '6.810'), (1, '7.180')] -[2023-10-09 02:41:50,585][88326] Updated weights for policy 0, policy_version 64582 (0.0007) -[2023-10-09 02:41:50,949][88326] Updated weights for policy 0, policy_version 64592 (0.0010) -[2023-10-09 02:41:51,153][88327] Updated weights for policy 1, policy_version 64610 (0.0008) -[2023-10-09 02:41:51,318][88326] Updated weights for policy 0, policy_version 64602 (0.0009) -[2023-10-09 02:41:51,531][88327] Updated weights for policy 1, policy_version 64620 (0.0007) -[2023-10-09 02:41:51,894][88327] Updated weights for policy 1, policy_version 64630 (0.0009) -[2023-10-09 02:41:52,257][88327] Updated weights for policy 1, policy_version 64640 (0.0009) -[2023-10-09 02:41:53,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 132349952. Throughput: 0: 1686.0, 1: 1700.0. Samples: 33090418. Policy #0 lag: (min: 17.0, avg: 21.7, max: 49.0) -[2023-10-09 02:41:53,975][87372] Avg episode reward: [(0, '7.220'), (1, '7.390')] -[2023-10-09 02:41:55,275][88326] Updated weights for policy 0, policy_version 64612 (0.0009) -[2023-10-09 02:41:55,645][88326] Updated weights for policy 0, policy_version 64622 (0.0010) -[2023-10-09 02:41:56,017][88326] Updated weights for policy 0, policy_version 64632 (0.0008) -[2023-10-09 02:41:56,114][88327] Updated weights for policy 1, policy_version 64650 (0.0007) -[2023-10-09 02:41:56,481][88327] Updated weights for policy 1, policy_version 64660 (0.0007) -[2023-10-09 02:41:56,849][88327] Updated weights for policy 1, policy_version 64670 (0.0007) -[2023-10-09 02:41:58,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 132415488. Throughput: 0: 1688.6, 1: 1676.1. Samples: 33109998. Policy #0 lag: (min: 23.0, avg: 23.4, max: 37.0) -[2023-10-09 02:41:58,974][87372] Avg episode reward: [(0, '7.610'), (1, '6.760')] -[2023-10-09 02:42:00,132][88326] Updated weights for policy 0, policy_version 64642 (0.0008) -[2023-10-09 02:42:00,554][88326] Updated weights for policy 0, policy_version 64652 (0.0008) -[2023-10-09 02:42:00,918][88326] Updated weights for policy 0, policy_version 64662 (0.0008) -[2023-10-09 02:42:00,955][88327] Updated weights for policy 1, policy_version 64680 (0.0008) -[2023-10-09 02:42:01,283][88326] Updated weights for policy 0, policy_version 64672 (0.0008) -[2023-10-09 02:42:01,321][88327] Updated weights for policy 1, policy_version 64690 (0.0009) -[2023-10-09 02:42:01,682][88327] Updated weights for policy 1, policy_version 64700 (0.0007) -[2023-10-09 02:42:03,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 132481024. Throughput: 0: 1706.2, 1: 1697.3. Samples: 33130776. Policy #0 lag: (min: 23.0, avg: 23.4, max: 37.0) -[2023-10-09 02:42:03,974][87372] Avg episode reward: [(0, '7.600'), (1, '6.890')] -[2023-10-09 02:42:05,395][88326] Updated weights for policy 0, policy_version 64682 (0.0008) -[2023-10-09 02:42:05,700][88327] Updated weights for policy 1, policy_version 64710 (0.0008) -[2023-10-09 02:42:05,766][88326] Updated weights for policy 0, policy_version 64692 (0.0008) -[2023-10-09 02:42:06,068][88327] Updated weights for policy 1, policy_version 64720 (0.0008) -[2023-10-09 02:42:06,133][88326] Updated weights for policy 0, policy_version 64702 (0.0008) -[2023-10-09 02:42:06,438][88327] Updated weights for policy 1, policy_version 64730 (0.0009) -[2023-10-09 02:42:08,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 132546560. Throughput: 0: 1670.7, 1: 1690.6. Samples: 33140440. Policy #0 lag: (min: 23.0, avg: 23.4, max: 37.0) -[2023-10-09 02:42:08,975][87372] Avg episode reward: [(0, '7.060'), (1, '7.000')] -[2023-10-09 02:42:10,315][88326] Updated weights for policy 0, policy_version 64712 (0.0009) -[2023-10-09 02:42:10,433][88327] Updated weights for policy 1, policy_version 64740 (0.0008) -[2023-10-09 02:42:10,679][88326] Updated weights for policy 0, policy_version 64722 (0.0009) -[2023-10-09 02:42:10,789][88327] Updated weights for policy 1, policy_version 64750 (0.0007) -[2023-10-09 02:42:11,039][88326] Updated weights for policy 0, policy_version 64732 (0.0007) -[2023-10-09 02:42:11,147][88327] Updated weights for policy 1, policy_version 64760 (0.0008) -[2023-10-09 02:42:13,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 132612096. Throughput: 0: 1687.2, 1: 1685.4. Samples: 33160544. Policy #0 lag: (min: 23.0, avg: 23.4, max: 37.0) -[2023-10-09 02:42:13,975][87372] Avg episode reward: [(0, '6.630'), (1, '7.850')] -[2023-10-09 02:42:15,153][88326] Updated weights for policy 0, policy_version 64742 (0.0009) -[2023-10-09 02:42:15,278][88327] Updated weights for policy 1, policy_version 64770 (0.0008) -[2023-10-09 02:42:15,517][88326] Updated weights for policy 0, policy_version 64752 (0.0010) -[2023-10-09 02:42:15,640][88327] Updated weights for policy 1, policy_version 64780 (0.0008) -[2023-10-09 02:42:15,881][88326] Updated weights for policy 0, policy_version 64762 (0.0009) -[2023-10-09 02:42:16,000][88327] Updated weights for policy 1, policy_version 64790 (0.0008) -[2023-10-09 02:42:16,360][88327] Updated weights for policy 1, policy_version 64800 (0.0007) -[2023-10-09 02:42:18,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 132677632. Throughput: 0: 1689.3, 1: 1709.1. Samples: 33181606. Policy #0 lag: (min: 23.0, avg: 23.4, max: 37.0) -[2023-10-09 02:42:18,975][87372] Avg episode reward: [(0, '7.220'), (1, '7.560')] -[2023-10-09 02:42:19,835][88326] Updated weights for policy 0, policy_version 64772 (0.0009) -[2023-10-09 02:42:20,206][88326] Updated weights for policy 0, policy_version 64782 (0.0008) -[2023-10-09 02:42:20,390][88327] Updated weights for policy 1, policy_version 64810 (0.0007) -[2023-10-09 02:42:20,565][88326] Updated weights for policy 0, policy_version 64792 (0.0010) -[2023-10-09 02:42:20,766][88327] Updated weights for policy 1, policy_version 64820 (0.0009) -[2023-10-09 02:42:21,119][88327] Updated weights for policy 1, policy_version 64830 (0.0009) -[2023-10-09 02:42:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 132743168. Throughput: 0: 1671.6, 1: 1678.2. Samples: 33190788. Policy #0 lag: (min: 23.0, avg: 23.4, max: 37.0) -[2023-10-09 02:42:23,975][87372] Avg episode reward: [(0, '6.950'), (1, '7.250')] -[2023-10-09 02:42:24,676][88326] Updated weights for policy 0, policy_version 64802 (0.0009) -[2023-10-09 02:42:25,053][88326] Updated weights for policy 0, policy_version 64812 (0.0009) -[2023-10-09 02:42:25,229][88327] Updated weights for policy 1, policy_version 64840 (0.0008) -[2023-10-09 02:42:25,419][88326] Updated weights for policy 0, policy_version 64822 (0.0008) -[2023-10-09 02:42:25,589][88327] Updated weights for policy 1, policy_version 64850 (0.0007) -[2023-10-09 02:42:25,786][88326] Updated weights for policy 0, policy_version 64832 (0.0008) -[2023-10-09 02:42:25,958][88327] Updated weights for policy 1, policy_version 64860 (0.0007) -[2023-10-09 02:42:28,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 132808704. Throughput: 0: 1685.9, 1: 1692.6. Samples: 33211690. Policy #0 lag: (min: 23.0, avg: 23.4, max: 37.0) -[2023-10-09 02:42:28,975][87372] Avg episode reward: [(0, '7.250'), (1, '7.730')] -[2023-10-09 02:42:29,742][88326] Updated weights for policy 0, policy_version 64842 (0.0009) -[2023-10-09 02:42:29,943][88327] Updated weights for policy 1, policy_version 64870 (0.0009) -[2023-10-09 02:42:30,109][88326] Updated weights for policy 0, policy_version 64852 (0.0010) -[2023-10-09 02:42:30,303][88327] Updated weights for policy 1, policy_version 64880 (0.0008) -[2023-10-09 02:42:30,474][88326] Updated weights for policy 0, policy_version 64862 (0.0007) -[2023-10-09 02:42:30,678][88327] Updated weights for policy 1, policy_version 64890 (0.0009) -[2023-10-09 02:42:33,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 132874240. Throughput: 0: 1688.9, 1: 1708.5. Samples: 33232704. Policy #0 lag: (min: 23.0, avg: 23.4, max: 37.0) -[2023-10-09 02:42:33,975][87372] Avg episode reward: [(0, '7.190'), (1, '6.760')] -[2023-10-09 02:42:33,987][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000064896_66453504.pth... -[2023-10-09 02:42:33,987][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000064864_66420736.pth... -[2023-10-09 02:42:34,025][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000063328_64847872.pth -[2023-10-09 02:42:34,027][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000063296_64815104.pth -[2023-10-09 02:42:34,452][88326] Updated weights for policy 0, policy_version 64872 (0.0007) -[2023-10-09 02:42:34,548][88327] Updated weights for policy 1, policy_version 64900 (0.0009) -[2023-10-09 02:42:34,826][88326] Updated weights for policy 0, policy_version 64882 (0.0009) -[2023-10-09 02:42:34,914][88327] Updated weights for policy 1, policy_version 64910 (0.0007) -[2023-10-09 02:42:35,189][88326] Updated weights for policy 0, policy_version 64892 (0.0008) -[2023-10-09 02:42:35,278][88327] Updated weights for policy 1, policy_version 64920 (0.0008) -[2023-10-09 02:42:38,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 132939776. Throughput: 0: 1680.7, 1: 1683.6. Samples: 33241814. Policy #0 lag: (min: 23.0, avg: 23.4, max: 37.0) -[2023-10-09 02:42:38,975][87372] Avg episode reward: [(0, '7.830'), (1, '6.730')] -[2023-10-09 02:42:39,290][88327] Updated weights for policy 1, policy_version 64930 (0.0010) -[2023-10-09 02:42:39,336][88326] Updated weights for policy 0, policy_version 64902 (0.0007) -[2023-10-09 02:42:39,657][88327] Updated weights for policy 1, policy_version 64940 (0.0008) -[2023-10-09 02:42:39,703][88326] Updated weights for policy 0, policy_version 64912 (0.0008) -[2023-10-09 02:42:40,021][88327] Updated weights for policy 1, policy_version 64950 (0.0007) -[2023-10-09 02:42:40,064][88326] Updated weights for policy 0, policy_version 64922 (0.0008) -[2023-10-09 02:42:40,376][88327] Updated weights for policy 1, policy_version 64960 (0.0009) -[2023-10-09 02:42:43,974][87372] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 133005312. Throughput: 0: 1685.9, 1: 1706.7. Samples: 33262664. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:42:43,975][87372] Avg episode reward: [(0, '7.040'), (1, '7.090')] -[2023-10-09 02:42:44,131][88326] Updated weights for policy 0, policy_version 64932 (0.0008) -[2023-10-09 02:42:44,480][88327] Updated weights for policy 1, policy_version 64970 (0.0008) -[2023-10-09 02:42:44,513][88326] Updated weights for policy 0, policy_version 64942 (0.0008) -[2023-10-09 02:42:44,849][88327] Updated weights for policy 1, policy_version 64980 (0.0007) -[2023-10-09 02:42:44,880][88326] Updated weights for policy 0, policy_version 64952 (0.0008) -[2023-10-09 02:42:45,205][88327] Updated weights for policy 1, policy_version 64990 (0.0010) -[2023-10-09 02:42:48,913][88326] Updated weights for policy 0, policy_version 64962 (0.0008) -[2023-10-09 02:42:48,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 133070848. Throughput: 0: 1691.1, 1: 1698.2. Samples: 33283294. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:42:48,975][87372] Avg episode reward: [(0, '7.000'), (1, '7.310')] -[2023-10-09 02:42:49,318][88326] Updated weights for policy 0, policy_version 64972 (0.0009) -[2023-10-09 02:42:49,370][88327] Updated weights for policy 1, policy_version 65000 (0.0008) -[2023-10-09 02:42:49,690][88326] Updated weights for policy 0, policy_version 64982 (0.0009) -[2023-10-09 02:42:49,739][88327] Updated weights for policy 1, policy_version 65010 (0.0007) -[2023-10-09 02:42:50,058][88326] Updated weights for policy 0, policy_version 64992 (0.0007) -[2023-10-09 02:42:50,100][88327] Updated weights for policy 1, policy_version 65020 (0.0007) -[2023-10-09 02:42:53,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 133136384. Throughput: 0: 1689.6, 1: 1681.6. Samples: 33292142. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:42:53,974][87372] Avg episode reward: [(0, '6.830'), (1, '7.270')] -[2023-10-09 02:42:54,147][88327] Updated weights for policy 1, policy_version 65030 (0.0009) -[2023-10-09 02:42:54,157][88326] Updated weights for policy 0, policy_version 65002 (0.0008) -[2023-10-09 02:42:54,505][88327] Updated weights for policy 1, policy_version 65040 (0.0007) -[2023-10-09 02:42:54,514][88326] Updated weights for policy 0, policy_version 65012 (0.0010) -[2023-10-09 02:42:54,858][88327] Updated weights for policy 1, policy_version 65050 (0.0009) -[2023-10-09 02:42:54,879][88326] Updated weights for policy 0, policy_version 65022 (0.0009) -[2023-10-09 02:42:58,853][88327] Updated weights for policy 1, policy_version 65060 (0.0009) -[2023-10-09 02:42:58,946][88326] Updated weights for policy 0, policy_version 65032 (0.0010) -[2023-10-09 02:42:58,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 133201920. Throughput: 0: 1696.0, 1: 1692.6. Samples: 33313032. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:42:58,974][87372] Avg episode reward: [(0, '7.310'), (1, '7.700')] -[2023-10-09 02:42:59,206][88327] Updated weights for policy 1, policy_version 65070 (0.0009) -[2023-10-09 02:42:59,309][88326] Updated weights for policy 0, policy_version 65042 (0.0008) -[2023-10-09 02:42:59,567][88327] Updated weights for policy 1, policy_version 65080 (0.0009) -[2023-10-09 02:42:59,672][88326] Updated weights for policy 0, policy_version 65052 (0.0008) -[2023-10-09 02:43:03,552][88327] Updated weights for policy 1, policy_version 65090 (0.0007) -[2023-10-09 02:43:03,826][88326] Updated weights for policy 0, policy_version 65062 (0.0009) -[2023-10-09 02:43:03,919][88327] Updated weights for policy 1, policy_version 65100 (0.0008) -[2023-10-09 02:43:03,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 133267456. Throughput: 0: 1686.9, 1: 1701.4. Samples: 33334080. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:43:03,975][87372] Avg episode reward: [(0, '7.420'), (1, '7.220')] -[2023-10-09 02:43:04,191][88326] Updated weights for policy 0, policy_version 65072 (0.0007) -[2023-10-09 02:43:04,284][88327] Updated weights for policy 1, policy_version 65110 (0.0007) -[2023-10-09 02:43:04,562][88326] Updated weights for policy 0, policy_version 65082 (0.0008) -[2023-10-09 02:43:04,644][88327] Updated weights for policy 1, policy_version 65120 (0.0007) -[2023-10-09 02:43:08,549][88326] Updated weights for policy 0, policy_version 65092 (0.0008) -[2023-10-09 02:43:08,597][88327] Updated weights for policy 1, policy_version 65130 (0.0008) -[2023-10-09 02:43:08,915][88326] Updated weights for policy 0, policy_version 65102 (0.0008) -[2023-10-09 02:43:08,958][88327] Updated weights for policy 1, policy_version 65140 (0.0007) -[2023-10-09 02:43:08,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 133332992. Throughput: 0: 1687.2, 1: 1704.4. Samples: 33343410. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:43:08,974][87372] Avg episode reward: [(0, '6.910'), (1, '7.480')] -[2023-10-09 02:43:09,290][88326] Updated weights for policy 0, policy_version 65112 (0.0007) -[2023-10-09 02:43:09,324][88327] Updated weights for policy 1, policy_version 65150 (0.0009) -[2023-10-09 02:43:13,330][88326] Updated weights for policy 0, policy_version 65122 (0.0007) -[2023-10-09 02:43:13,560][88327] Updated weights for policy 1, policy_version 65160 (0.0009) -[2023-10-09 02:43:13,707][88326] Updated weights for policy 0, policy_version 65132 (0.0009) -[2023-10-09 02:43:13,923][88327] Updated weights for policy 1, policy_version 65170 (0.0008) -[2023-10-09 02:43:13,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 133398528. Throughput: 0: 1686.4, 1: 1700.7. Samples: 33364108. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:43:13,975][87372] Avg episode reward: [(0, '6.820'), (1, '7.320')] -[2023-10-09 02:43:14,069][88326] Updated weights for policy 0, policy_version 65142 (0.0008) -[2023-10-09 02:43:14,300][88327] Updated weights for policy 1, policy_version 65180 (0.0008) -[2023-10-09 02:43:14,438][88326] Updated weights for policy 0, policy_version 65152 (0.0008) -[2023-10-09 02:43:18,333][88327] Updated weights for policy 1, policy_version 65190 (0.0009) -[2023-10-09 02:43:18,401][88326] Updated weights for policy 0, policy_version 65162 (0.0009) -[2023-10-09 02:43:18,693][88327] Updated weights for policy 1, policy_version 65200 (0.0008) -[2023-10-09 02:43:18,776][88326] Updated weights for policy 0, policy_version 65172 (0.0007) -[2023-10-09 02:43:18,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 133464064. Throughput: 0: 1682.2, 1: 1694.1. Samples: 33384636. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:43:18,975][87372] Avg episode reward: [(0, '7.040'), (1, '7.650')] -[2023-10-09 02:43:19,059][88327] Updated weights for policy 1, policy_version 65210 (0.0008) -[2023-10-09 02:43:19,153][88326] Updated weights for policy 0, policy_version 65182 (0.0009) -[2023-10-09 02:43:23,108][88326] Updated weights for policy 0, policy_version 65192 (0.0009) -[2023-10-09 02:43:23,132][88327] Updated weights for policy 1, policy_version 65220 (0.0008) -[2023-10-09 02:43:23,481][88326] Updated weights for policy 0, policy_version 65202 (0.0008) -[2023-10-09 02:43:23,485][88327] Updated weights for policy 1, policy_version 65230 (0.0008) -[2023-10-09 02:43:23,851][88327] Updated weights for policy 1, policy_version 65240 (0.0008) -[2023-10-09 02:43:23,852][88326] Updated weights for policy 0, policy_version 65212 (0.0007) -[2023-10-09 02:43:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 133529600. Throughput: 0: 1687.9, 1: 1694.1. Samples: 33394004. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:43:23,975][87372] Avg episode reward: [(0, '6.460'), (1, '7.320')] -[2023-10-09 02:43:27,774][88327] Updated weights for policy 1, policy_version 65250 (0.0008) -[2023-10-09 02:43:27,878][88326] Updated weights for policy 0, policy_version 65222 (0.0007) -[2023-10-09 02:43:28,199][88327] Updated weights for policy 1, policy_version 65260 (0.0008) -[2023-10-09 02:43:28,259][88326] Updated weights for policy 0, policy_version 65232 (0.0007) -[2023-10-09 02:43:28,566][88327] Updated weights for policy 1, policy_version 65270 (0.0007) -[2023-10-09 02:43:28,630][88326] Updated weights for policy 0, policy_version 65242 (0.0008) -[2023-10-09 02:43:28,930][88327] Updated weights for policy 1, policy_version 65280 (0.0009) -[2023-10-09 02:43:28,974][87372] Fps is (10 sec: 19660.8, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 133660672. Throughput: 0: 1691.0, 1: 1699.6. Samples: 33415238. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:43:28,975][87372] Avg episode reward: [(0, '6.540'), (1, '7.570')] -[2023-10-09 02:43:32,807][88326] Updated weights for policy 0, policy_version 65252 (0.0008) -[2023-10-09 02:43:32,973][88327] Updated weights for policy 1, policy_version 65290 (0.0009) -[2023-10-09 02:43:33,179][88326] Updated weights for policy 0, policy_version 65262 (0.0007) -[2023-10-09 02:43:33,342][88327] Updated weights for policy 1, policy_version 65300 (0.0009) -[2023-10-09 02:43:33,541][88326] Updated weights for policy 0, policy_version 65272 (0.0008) -[2023-10-09 02:43:33,708][88327] Updated weights for policy 1, policy_version 65310 (0.0008) -[2023-10-09 02:43:33,974][87372] Fps is (10 sec: 19660.7, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 133726208. Throughput: 0: 1672.4, 1: 1692.5. Samples: 33434714. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:43:33,975][87372] Avg episode reward: [(0, '6.160'), (1, '7.200')] -[2023-10-09 02:43:37,608][88326] Updated weights for policy 0, policy_version 65282 (0.0009) -[2023-10-09 02:43:37,803][88327] Updated weights for policy 1, policy_version 65320 (0.0008) -[2023-10-09 02:43:38,016][88326] Updated weights for policy 0, policy_version 65292 (0.0008) -[2023-10-09 02:43:38,166][88327] Updated weights for policy 1, policy_version 65330 (0.0009) -[2023-10-09 02:43:38,381][88326] Updated weights for policy 0, policy_version 65302 (0.0007) -[2023-10-09 02:43:38,528][88327] Updated weights for policy 1, policy_version 65340 (0.0007) -[2023-10-09 02:43:38,741][88326] Updated weights for policy 0, policy_version 65312 (0.0007) -[2023-10-09 02:43:38,974][87372] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 133791744. Throughput: 0: 1689.3, 1: 1705.7. Samples: 33444916. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:43:38,974][87372] Avg episode reward: [(0, '6.670'), (1, '7.000')] -[2023-10-09 02:43:42,657][88327] Updated weights for policy 1, policy_version 65350 (0.0009) -[2023-10-09 02:43:42,698][88326] Updated weights for policy 0, policy_version 65322 (0.0007) -[2023-10-09 02:43:43,028][88327] Updated weights for policy 1, policy_version 65360 (0.0009) -[2023-10-09 02:43:43,059][88326] Updated weights for policy 0, policy_version 65332 (0.0008) -[2023-10-09 02:43:43,391][88327] Updated weights for policy 1, policy_version 65370 (0.0009) -[2023-10-09 02:43:43,426][88326] Updated weights for policy 0, policy_version 65342 (0.0008) -[2023-10-09 02:43:43,974][87372] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 133857280. Throughput: 0: 1681.6, 1: 1706.7. Samples: 33465506. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:43:43,975][87372] Avg episode reward: [(0, '6.800'), (1, '7.020')] -[2023-10-09 02:43:47,477][88327] Updated weights for policy 1, policy_version 65380 (0.0009) -[2023-10-09 02:43:47,493][88326] Updated weights for policy 0, policy_version 65352 (0.0007) -[2023-10-09 02:43:47,847][88327] Updated weights for policy 1, policy_version 65390 (0.0008) -[2023-10-09 02:43:47,872][88326] Updated weights for policy 0, policy_version 65362 (0.0009) -[2023-10-09 02:43:48,209][88327] Updated weights for policy 1, policy_version 65400 (0.0009) -[2023-10-09 02:43:48,241][88326] Updated weights for policy 0, policy_version 65372 (0.0008) -[2023-10-09 02:43:48,974][87372] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 133922816. Throughput: 0: 1660.0, 1: 1675.7. Samples: 33484186. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:43:48,974][87372] Avg episode reward: [(0, '6.800'), (1, '6.970')] -[2023-10-09 02:43:52,210][88326] Updated weights for policy 0, policy_version 65382 (0.0009) -[2023-10-09 02:43:52,231][88327] Updated weights for policy 1, policy_version 65410 (0.0008) -[2023-10-09 02:43:52,575][88326] Updated weights for policy 0, policy_version 65392 (0.0010) -[2023-10-09 02:43:52,598][88327] Updated weights for policy 1, policy_version 65420 (0.0008) -[2023-10-09 02:43:52,941][88326] Updated weights for policy 0, policy_version 65402 (0.0008) -[2023-10-09 02:43:52,959][88327] Updated weights for policy 1, policy_version 65430 (0.0008) -[2023-10-09 02:43:53,335][88327] Updated weights for policy 1, policy_version 65440 (0.0008) -[2023-10-09 02:43:53,974][87372] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 133988352. Throughput: 0: 1684.8, 1: 1689.8. Samples: 33495266. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:43:53,975][87372] Avg episode reward: [(0, '7.420'), (1, '6.680')] -[2023-10-09 02:43:57,161][88326] Updated weights for policy 0, policy_version 65412 (0.0008) -[2023-10-09 02:43:57,466][88327] Updated weights for policy 1, policy_version 65450 (0.0009) -[2023-10-09 02:43:57,536][88326] Updated weights for policy 0, policy_version 65422 (0.0007) -[2023-10-09 02:43:57,825][88327] Updated weights for policy 1, policy_version 65460 (0.0010) -[2023-10-09 02:43:57,916][88326] Updated weights for policy 0, policy_version 65432 (0.0008) -[2023-10-09 02:43:58,192][88327] Updated weights for policy 1, policy_version 65470 (0.0007) -[2023-10-09 02:43:58,974][87372] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 134053888. Throughput: 0: 1676.0, 1: 1689.3. Samples: 33515548. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:43:58,975][87372] Avg episode reward: [(0, '7.500'), (1, '6.690')] -[2023-10-09 02:44:01,992][88326] Updated weights for policy 0, policy_version 65442 (0.0009) -[2023-10-09 02:44:02,203][88327] Updated weights for policy 1, policy_version 65480 (0.0009) -[2023-10-09 02:44:02,354][88326] Updated weights for policy 0, policy_version 65452 (0.0007) -[2023-10-09 02:44:02,562][88327] Updated weights for policy 1, policy_version 65490 (0.0007) -[2023-10-09 02:44:02,723][88326] Updated weights for policy 0, policy_version 65462 (0.0009) -[2023-10-09 02:44:02,938][88327] Updated weights for policy 1, policy_version 65500 (0.0007) -[2023-10-09 02:44:03,089][88326] Updated weights for policy 0, policy_version 65472 (0.0007) -[2023-10-09 02:44:03,974][87372] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 134119424. Throughput: 0: 1656.5, 1: 1663.0. Samples: 33534014. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:44:03,975][87372] Avg episode reward: [(0, '6.880'), (1, '6.530')] -[2023-10-09 02:44:06,869][88327] Updated weights for policy 1, policy_version 65510 (0.0007) -[2023-10-09 02:44:07,239][88327] Updated weights for policy 1, policy_version 65520 (0.0007) -[2023-10-09 02:44:07,261][88326] Updated weights for policy 0, policy_version 65482 (0.0008) -[2023-10-09 02:44:07,607][88327] Updated weights for policy 1, policy_version 65530 (0.0007) -[2023-10-09 02:44:07,637][88326] Updated weights for policy 0, policy_version 65492 (0.0008) -[2023-10-09 02:44:07,999][88326] Updated weights for policy 0, policy_version 65502 (0.0008) -[2023-10-09 02:44:08,974][87372] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 134184960. Throughput: 0: 1678.8, 1: 1691.3. Samples: 33545660. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:44:08,975][87372] Avg episode reward: [(0, '7.360'), (1, '6.940')] -[2023-10-09 02:44:11,765][88327] Updated weights for policy 1, policy_version 65540 (0.0007) -[2023-10-09 02:44:12,144][88327] Updated weights for policy 1, policy_version 65550 (0.0008) -[2023-10-09 02:44:12,155][88326] Updated weights for policy 0, policy_version 65512 (0.0009) -[2023-10-09 02:44:12,507][88327] Updated weights for policy 1, policy_version 65560 (0.0008) -[2023-10-09 02:44:12,520][88326] Updated weights for policy 0, policy_version 65522 (0.0008) -[2023-10-09 02:44:12,882][88326] Updated weights for policy 0, policy_version 65532 (0.0010) -[2023-10-09 02:44:13,974][87372] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 134250496. Throughput: 0: 1663.8, 1: 1673.4. Samples: 33565412. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:44:13,975][87372] Avg episode reward: [(0, '7.170'), (1, '7.180')] -[2023-10-09 02:44:16,392][88327] Updated weights for policy 1, policy_version 65570 (0.0008) -[2023-10-09 02:44:16,798][88327] Updated weights for policy 1, policy_version 65580 (0.0009) -[2023-10-09 02:44:16,828][88326] Updated weights for policy 0, policy_version 65542 (0.0009) -[2023-10-09 02:44:17,171][88327] Updated weights for policy 1, policy_version 65590 (0.0009) -[2023-10-09 02:44:17,195][88326] Updated weights for policy 0, policy_version 65552 (0.0008) -[2023-10-09 02:44:17,526][88327] Updated weights for policy 1, policy_version 65600 (0.0008) -[2023-10-09 02:44:17,554][88326] Updated weights for policy 0, policy_version 65562 (0.0007) -[2023-10-09 02:44:18,974][87372] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 134316032. Throughput: 0: 1662.9, 1: 1672.3. Samples: 33584796. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:44:18,975][87372] Avg episode reward: [(0, '6.640'), (1, '7.630')] -[2023-10-09 02:44:21,495][88327] Updated weights for policy 1, policy_version 65610 (0.0010) -[2023-10-09 02:44:21,622][88326] Updated weights for policy 0, policy_version 65572 (0.0008) -[2023-10-09 02:44:21,862][88327] Updated weights for policy 1, policy_version 65620 (0.0009) -[2023-10-09 02:44:21,988][88326] Updated weights for policy 0, policy_version 65582 (0.0008) -[2023-10-09 02:44:22,225][88327] Updated weights for policy 1, policy_version 65630 (0.0007) -[2023-10-09 02:44:22,351][88326] Updated weights for policy 0, policy_version 65592 (0.0008) -[2023-10-09 02:44:23,974][87372] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 134381568. Throughput: 0: 1678.8, 1: 1692.4. Samples: 33596620. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:44:23,975][87372] Avg episode reward: [(0, '6.960'), (1, '7.110')] -[2023-10-09 02:44:26,169][88327] Updated weights for policy 1, policy_version 65640 (0.0009) -[2023-10-09 02:44:26,311][88326] Updated weights for policy 0, policy_version 65602 (0.0007) -[2023-10-09 02:44:26,531][88327] Updated weights for policy 1, policy_version 65650 (0.0009) -[2023-10-09 02:44:26,719][88326] Updated weights for policy 0, policy_version 65612 (0.0007) -[2023-10-09 02:44:26,901][88327] Updated weights for policy 1, policy_version 65660 (0.0009) -[2023-10-09 02:44:27,090][88326] Updated weights for policy 0, policy_version 65622 (0.0008) -[2023-10-09 02:44:27,444][88326] Updated weights for policy 0, policy_version 65632 (0.0010) -[2023-10-09 02:44:28,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 134447104. Throughput: 0: 1662.4, 1: 1668.7. Samples: 33615408. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:44:28,975][87372] Avg episode reward: [(0, '6.310'), (1, '6.580')] -[2023-10-09 02:44:31,043][88327] Updated weights for policy 1, policy_version 65670 (0.0008) -[2023-10-09 02:44:31,406][88326] Updated weights for policy 0, policy_version 65642 (0.0009) -[2023-10-09 02:44:31,413][88327] Updated weights for policy 1, policy_version 65680 (0.0007) -[2023-10-09 02:44:31,769][88326] Updated weights for policy 0, policy_version 65652 (0.0008) -[2023-10-09 02:44:31,774][88327] Updated weights for policy 1, policy_version 65690 (0.0009) -[2023-10-09 02:44:32,135][88326] Updated weights for policy 0, policy_version 65662 (0.0011) -[2023-10-09 02:44:33,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 134512640. Throughput: 0: 1685.9, 1: 1691.7. Samples: 33636180. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:44:33,975][87372] Avg episode reward: [(0, '7.060'), (1, '7.440')] -[2023-10-09 02:44:33,983][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000065664_67239936.pth... -[2023-10-09 02:44:33,983][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000065696_67272704.pth... -[2023-10-09 02:44:34,022][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000064096_65634304.pth -[2023-10-09 02:44:34,023][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000064128_65667072.pth -[2023-10-09 02:44:35,618][88327] Updated weights for policy 1, policy_version 65700 (0.0008) -[2023-10-09 02:44:35,984][88327] Updated weights for policy 1, policy_version 65710 (0.0010) -[2023-10-09 02:44:36,311][88326] Updated weights for policy 0, policy_version 65672 (0.0010) -[2023-10-09 02:44:36,343][88327] Updated weights for policy 1, policy_version 65720 (0.0008) -[2023-10-09 02:44:36,686][88326] Updated weights for policy 0, policy_version 65682 (0.0008) -[2023-10-09 02:44:37,051][88326] Updated weights for policy 0, policy_version 65692 (0.0007) -[2023-10-09 02:44:38,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 134578176. Throughput: 0: 1684.5, 1: 1690.4. Samples: 33647136. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:44:38,975][87372] Avg episode reward: [(0, '7.450'), (1, '7.090')] -[2023-10-09 02:44:40,380][88327] Updated weights for policy 1, policy_version 65730 (0.0008) -[2023-10-09 02:44:40,738][88327] Updated weights for policy 1, policy_version 65740 (0.0009) -[2023-10-09 02:44:41,078][88326] Updated weights for policy 0, policy_version 65702 (0.0008) -[2023-10-09 02:44:41,102][88327] Updated weights for policy 1, policy_version 65750 (0.0007) -[2023-10-09 02:44:41,448][88326] Updated weights for policy 0, policy_version 65712 (0.0008) -[2023-10-09 02:44:41,472][88327] Updated weights for policy 1, policy_version 65760 (0.0007) -[2023-10-09 02:44:41,810][88326] Updated weights for policy 0, policy_version 65722 (0.0011) -[2023-10-09 02:44:43,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 134643712. Throughput: 0: 1668.1, 1: 1687.4. Samples: 33666544. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:44:43,975][87372] Avg episode reward: [(0, '6.550'), (1, '7.570')] -[2023-10-09 02:44:45,454][88327] Updated weights for policy 1, policy_version 65770 (0.0010) -[2023-10-09 02:44:45,807][88326] Updated weights for policy 0, policy_version 65732 (0.0010) -[2023-10-09 02:44:45,811][88327] Updated weights for policy 1, policy_version 65780 (0.0008) -[2023-10-09 02:44:46,176][88326] Updated weights for policy 0, policy_version 65742 (0.0007) -[2023-10-09 02:44:46,181][88327] Updated weights for policy 1, policy_version 65790 (0.0009) -[2023-10-09 02:44:46,544][88326] Updated weights for policy 0, policy_version 65752 (0.0007) -[2023-10-09 02:44:48,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 134709248. Throughput: 0: 1690.2, 1: 1718.2. Samples: 33687392. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:44:48,975][87372] Avg episode reward: [(0, '6.790'), (1, '7.900')] -[2023-10-09 02:44:50,149][88327] Updated weights for policy 1, policy_version 65800 (0.0007) -[2023-10-09 02:44:50,514][88327] Updated weights for policy 1, policy_version 65810 (0.0008) -[2023-10-09 02:44:50,557][88326] Updated weights for policy 0, policy_version 65762 (0.0008) -[2023-10-09 02:44:50,888][88327] Updated weights for policy 1, policy_version 65820 (0.0008) -[2023-10-09 02:44:50,924][88326] Updated weights for policy 0, policy_version 65772 (0.0008) -[2023-10-09 02:44:51,296][88326] Updated weights for policy 0, policy_version 65782 (0.0008) -[2023-10-09 02:44:51,663][88326] Updated weights for policy 0, policy_version 65792 (0.0008) -[2023-10-09 02:44:53,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 134774784. Throughput: 0: 1679.4, 1: 1686.7. Samples: 33697134. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-09 02:44:53,975][87372] Avg episode reward: [(0, '6.100'), (1, '7.410')] -[2023-10-09 02:44:54,965][88327] Updated weights for policy 1, policy_version 65830 (0.0009) -[2023-10-09 02:44:55,334][88327] Updated weights for policy 1, policy_version 65840 (0.0008) -[2023-10-09 02:44:55,699][88327] Updated weights for policy 1, policy_version 65850 (0.0008) -[2023-10-09 02:44:55,764][88326] Updated weights for policy 0, policy_version 65802 (0.0008) -[2023-10-09 02:44:56,133][88326] Updated weights for policy 0, policy_version 65812 (0.0007) -[2023-10-09 02:44:56,509][88326] Updated weights for policy 0, policy_version 65822 (0.0007) -[2023-10-09 02:44:58,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 134840320. Throughput: 0: 1681.2, 1: 1698.8. Samples: 33717510. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-09 02:44:58,974][87372] Avg episode reward: [(0, '6.270'), (1, '6.950')] -[2023-10-09 02:44:59,762][88327] Updated weights for policy 1, policy_version 65860 (0.0007) -[2023-10-09 02:45:00,124][88327] Updated weights for policy 1, policy_version 65870 (0.0010) -[2023-10-09 02:45:00,490][88327] Updated weights for policy 1, policy_version 65880 (0.0010) -[2023-10-09 02:45:00,533][88326] Updated weights for policy 0, policy_version 65832 (0.0009) -[2023-10-09 02:45:00,898][88326] Updated weights for policy 0, policy_version 65842 (0.0010) -[2023-10-09 02:45:01,267][88326] Updated weights for policy 0, policy_version 65852 (0.0009) -[2023-10-09 02:45:03,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 134905856. Throughput: 0: 1700.0, 1: 1713.9. Samples: 33738422. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-09 02:45:03,975][87372] Avg episode reward: [(0, '7.260'), (1, '7.050')] -[2023-10-09 02:45:04,599][88327] Updated weights for policy 1, policy_version 65890 (0.0009) -[2023-10-09 02:45:05,006][88327] Updated weights for policy 1, policy_version 65900 (0.0010) -[2023-10-09 02:45:05,330][88326] Updated weights for policy 0, policy_version 65862 (0.0009) -[2023-10-09 02:45:05,373][88327] Updated weights for policy 1, policy_version 65910 (0.0008) -[2023-10-09 02:45:05,687][88326] Updated weights for policy 0, policy_version 65872 (0.0008) -[2023-10-09 02:45:05,732][88327] Updated weights for policy 1, policy_version 65920 (0.0008) -[2023-10-09 02:45:06,060][88326] Updated weights for policy 0, policy_version 65882 (0.0008) -[2023-10-09 02:45:08,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 134971392. Throughput: 0: 1675.6, 1: 1679.2. Samples: 33747588. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-09 02:45:08,975][87372] Avg episode reward: [(0, '7.050'), (1, '6.820')] -[2023-10-09 02:45:09,577][88327] Updated weights for policy 1, policy_version 65930 (0.0008) -[2023-10-09 02:45:09,933][88327] Updated weights for policy 1, policy_version 65940 (0.0008) -[2023-10-09 02:45:10,024][88326] Updated weights for policy 0, policy_version 65892 (0.0008) -[2023-10-09 02:45:10,296][88327] Updated weights for policy 1, policy_version 65950 (0.0007) -[2023-10-09 02:45:10,391][88326] Updated weights for policy 0, policy_version 65902 (0.0009) -[2023-10-09 02:45:10,757][88326] Updated weights for policy 0, policy_version 65912 (0.0011) -[2023-10-09 02:45:13,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 135036928. Throughput: 0: 1695.9, 1: 1709.9. Samples: 33768666. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-09 02:45:13,975][87372] Avg episode reward: [(0, '7.190'), (1, '7.140')] -[2023-10-09 02:45:14,150][88327] Updated weights for policy 1, policy_version 65960 (0.0009) -[2023-10-09 02:45:14,511][88327] Updated weights for policy 1, policy_version 65970 (0.0009) -[2023-10-09 02:45:14,878][88327] Updated weights for policy 1, policy_version 65980 (0.0008) -[2023-10-09 02:45:14,909][88326] Updated weights for policy 0, policy_version 65922 (0.0010) -[2023-10-09 02:45:15,295][88326] Updated weights for policy 0, policy_version 65932 (0.0008) -[2023-10-09 02:45:15,661][88326] Updated weights for policy 0, policy_version 65942 (0.0008) -[2023-10-09 02:45:16,020][88326] Updated weights for policy 0, policy_version 65952 (0.0009) -[2023-10-09 02:45:18,911][88327] Updated weights for policy 1, policy_version 65990 (0.0008) -[2023-10-09 02:45:18,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 135102464. Throughput: 0: 1696.8, 1: 1711.6. Samples: 33789560. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-09 02:45:18,974][87372] Avg episode reward: [(0, '7.110'), (1, '6.930')] -[2023-10-09 02:45:19,274][88327] Updated weights for policy 1, policy_version 66000 (0.0009) -[2023-10-09 02:45:19,646][88327] Updated weights for policy 1, policy_version 66010 (0.0007) -[2023-10-09 02:45:20,199][88326] Updated weights for policy 0, policy_version 65962 (0.0009) -[2023-10-09 02:45:20,567][88326] Updated weights for policy 0, policy_version 65972 (0.0010) -[2023-10-09 02:45:20,939][88326] Updated weights for policy 0, policy_version 65982 (0.0010) -[2023-10-09 02:45:23,648][88327] Updated weights for policy 1, policy_version 66020 (0.0009) -[2023-10-09 02:45:23,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 135168000. Throughput: 0: 1672.0, 1: 1696.0. Samples: 33798698. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-09 02:45:23,975][87372] Avg episode reward: [(0, '6.370'), (1, '7.020')] -[2023-10-09 02:45:24,015][88327] Updated weights for policy 1, policy_version 66030 (0.0009) -[2023-10-09 02:45:24,377][88327] Updated weights for policy 1, policy_version 66040 (0.0008) -[2023-10-09 02:45:25,105][88326] Updated weights for policy 0, policy_version 65992 (0.0010) -[2023-10-09 02:45:25,467][88326] Updated weights for policy 0, policy_version 66002 (0.0009) -[2023-10-09 02:45:25,841][88326] Updated weights for policy 0, policy_version 66012 (0.0011) -[2023-10-09 02:45:28,254][88327] Updated weights for policy 1, policy_version 66050 (0.0009) -[2023-10-09 02:45:28,626][88327] Updated weights for policy 1, policy_version 66060 (0.0009) -[2023-10-09 02:45:28,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 135233536. Throughput: 0: 1697.6, 1: 1705.0. Samples: 33819660. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-09 02:45:28,975][87372] Avg episode reward: [(0, '6.580'), (1, '6.990')] -[2023-10-09 02:45:28,991][88327] Updated weights for policy 1, policy_version 66070 (0.0008) -[2023-10-09 02:45:29,344][88327] Updated weights for policy 1, policy_version 66080 (0.0009) -[2023-10-09 02:45:29,812][88326] Updated weights for policy 0, policy_version 66022 (0.0010) -[2023-10-09 02:45:30,181][88326] Updated weights for policy 0, policy_version 66032 (0.0009) -[2023-10-09 02:45:30,547][88326] Updated weights for policy 0, policy_version 66042 (0.0007) -[2023-10-09 02:45:33,628][88327] Updated weights for policy 1, policy_version 66090 (0.0007) -[2023-10-09 02:45:33,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 135299072. Throughput: 0: 1698.7, 1: 1702.6. Samples: 33840450. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-09 02:45:33,975][87372] Avg episode reward: [(0, '7.350'), (1, '6.800')] -[2023-10-09 02:45:33,993][88327] Updated weights for policy 1, policy_version 66100 (0.0008) -[2023-10-09 02:45:34,362][88327] Updated weights for policy 1, policy_version 66110 (0.0009) -[2023-10-09 02:45:34,640][88326] Updated weights for policy 0, policy_version 66052 (0.0009) -[2023-10-09 02:45:35,016][88326] Updated weights for policy 0, policy_version 66062 (0.0010) -[2023-10-09 02:45:35,383][88326] Updated weights for policy 0, policy_version 66072 (0.0010) -[2023-10-09 02:45:38,498][88327] Updated weights for policy 1, policy_version 66120 (0.0009) -[2023-10-09 02:45:38,875][88327] Updated weights for policy 1, policy_version 66130 (0.0008) -[2023-10-09 02:45:38,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 135364608. Throughput: 0: 1683.7, 1: 1704.6. Samples: 33849608. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:45:38,975][87372] Avg episode reward: [(0, '7.020'), (1, '7.300')] -[2023-10-09 02:45:39,234][88327] Updated weights for policy 1, policy_version 66140 (0.0008) -[2023-10-09 02:45:39,406][88326] Updated weights for policy 0, policy_version 66082 (0.0008) -[2023-10-09 02:45:39,777][88326] Updated weights for policy 0, policy_version 66092 (0.0007) -[2023-10-09 02:45:40,140][88326] Updated weights for policy 0, policy_version 66102 (0.0009) -[2023-10-09 02:45:40,503][88326] Updated weights for policy 0, policy_version 66112 (0.0010) -[2023-10-09 02:45:43,437][88327] Updated weights for policy 1, policy_version 66150 (0.0007) -[2023-10-09 02:45:43,805][88327] Updated weights for policy 1, policy_version 66160 (0.0007) -[2023-10-09 02:45:43,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 135430144. Throughput: 0: 1690.0, 1: 1705.9. Samples: 33870326. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:45:43,975][87372] Avg episode reward: [(0, '6.940'), (1, '7.280')] -[2023-10-09 02:45:44,173][88327] Updated weights for policy 1, policy_version 66170 (0.0007) -[2023-10-09 02:45:44,593][88326] Updated weights for policy 0, policy_version 66122 (0.0008) -[2023-10-09 02:45:44,959][88326] Updated weights for policy 0, policy_version 66132 (0.0010) -[2023-10-09 02:45:45,339][88326] Updated weights for policy 0, policy_version 66142 (0.0008) -[2023-10-09 02:45:48,179][88327] Updated weights for policy 1, policy_version 66180 (0.0007) -[2023-10-09 02:45:48,554][88327] Updated weights for policy 1, policy_version 66190 (0.0008) -[2023-10-09 02:45:48,917][88327] Updated weights for policy 1, policy_version 66200 (0.0008) -[2023-10-09 02:45:48,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 135495680. Throughput: 0: 1691.1, 1: 1703.6. Samples: 33891182. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:45:48,975][87372] Avg episode reward: [(0, '7.260'), (1, '7.000')] -[2023-10-09 02:45:49,166][88326] Updated weights for policy 0, policy_version 66152 (0.0008) -[2023-10-09 02:45:49,532][88326] Updated weights for policy 0, policy_version 66162 (0.0009) -[2023-10-09 02:45:49,893][88326] Updated weights for policy 0, policy_version 66172 (0.0008) -[2023-10-09 02:45:52,938][88327] Updated weights for policy 1, policy_version 66210 (0.0008) -[2023-10-09 02:45:53,364][88327] Updated weights for policy 1, policy_version 66220 (0.0009) -[2023-10-09 02:45:53,735][88327] Updated weights for policy 1, policy_version 66230 (0.0007) -[2023-10-09 02:45:53,971][88326] Updated weights for policy 0, policy_version 66182 (0.0008) -[2023-10-09 02:45:53,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 135561216. Throughput: 0: 1686.0, 1: 1710.8. Samples: 33900442. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:45:53,975][87372] Avg episode reward: [(0, '6.980'), (1, '6.950')] -[2023-10-09 02:45:54,092][88327] Updated weights for policy 1, policy_version 66240 (0.0009) -[2023-10-09 02:45:54,347][88326] Updated weights for policy 0, policy_version 66192 (0.0008) -[2023-10-09 02:45:54,724][88326] Updated weights for policy 0, policy_version 66202 (0.0008) -[2023-10-09 02:45:58,118][88327] Updated weights for policy 1, policy_version 66250 (0.0008) -[2023-10-09 02:45:58,482][88327] Updated weights for policy 1, policy_version 66260 (0.0009) -[2023-10-09 02:45:58,855][88327] Updated weights for policy 1, policy_version 66270 (0.0008) -[2023-10-09 02:45:58,885][88326] Updated weights for policy 0, policy_version 66212 (0.0008) -[2023-10-09 02:45:58,974][87372] Fps is (10 sec: 16384.2, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 135659520. Throughput: 0: 1687.6, 1: 1699.0. Samples: 33921062. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:45:58,975][87372] Avg episode reward: [(0, '6.930'), (1, '7.510')] -[2023-10-09 02:45:59,265][88326] Updated weights for policy 0, policy_version 66222 (0.0010) -[2023-10-09 02:45:59,638][88326] Updated weights for policy 0, policy_version 66232 (0.0008) -[2023-10-09 02:46:02,847][88327] Updated weights for policy 1, policy_version 66280 (0.0007) -[2023-10-09 02:46:03,220][88327] Updated weights for policy 1, policy_version 66290 (0.0010) -[2023-10-09 02:46:03,531][88326] Updated weights for policy 0, policy_version 66242 (0.0008) -[2023-10-09 02:46:03,580][88327] Updated weights for policy 1, policy_version 66300 (0.0009) -[2023-10-09 02:46:03,943][88326] Updated weights for policy 0, policy_version 66252 (0.0009) -[2023-10-09 02:46:03,974][87372] Fps is (10 sec: 16383.9, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 135725056. Throughput: 0: 1695.1, 1: 1685.8. Samples: 33941698. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:46:03,975][87372] Avg episode reward: [(0, '6.770'), (1, '7.030')] -[2023-10-09 02:46:04,314][88326] Updated weights for policy 0, policy_version 66262 (0.0008) -[2023-10-09 02:46:04,685][88326] Updated weights for policy 0, policy_version 66272 (0.0008) -[2023-10-09 02:46:07,517][88327] Updated weights for policy 1, policy_version 66310 (0.0008) -[2023-10-09 02:46:07,892][88327] Updated weights for policy 1, policy_version 66320 (0.0007) -[2023-10-09 02:46:08,249][88327] Updated weights for policy 1, policy_version 66330 (0.0010) -[2023-10-09 02:46:08,578][88326] Updated weights for policy 0, policy_version 66282 (0.0008) -[2023-10-09 02:46:08,946][88326] Updated weights for policy 0, policy_version 66292 (0.0008) -[2023-10-09 02:46:08,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 135790592. Throughput: 0: 1694.9, 1: 1699.9. Samples: 33951464. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:46:08,974][87372] Avg episode reward: [(0, '7.120'), (1, '7.620')] -[2023-10-09 02:46:09,321][88326] Updated weights for policy 0, policy_version 66302 (0.0007) -[2023-10-09 02:46:12,126][88327] Updated weights for policy 1, policy_version 66340 (0.0007) -[2023-10-09 02:46:12,490][88327] Updated weights for policy 1, policy_version 66350 (0.0008) -[2023-10-09 02:46:12,852][88327] Updated weights for policy 1, policy_version 66360 (0.0008) -[2023-10-09 02:46:13,359][88326] Updated weights for policy 0, policy_version 66312 (0.0008) -[2023-10-09 02:46:13,728][88326] Updated weights for policy 0, policy_version 66322 (0.0008) -[2023-10-09 02:46:13,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 135856128. Throughput: 0: 1697.9, 1: 1698.5. Samples: 33972500. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:46:13,975][87372] Avg episode reward: [(0, '7.230'), (1, '7.820')] -[2023-10-09 02:46:14,098][88326] Updated weights for policy 0, policy_version 66332 (0.0007) -[2023-10-09 02:46:16,983][88327] Updated weights for policy 1, policy_version 66370 (0.0008) -[2023-10-09 02:46:17,354][88327] Updated weights for policy 1, policy_version 66380 (0.0007) -[2023-10-09 02:46:17,713][88327] Updated weights for policy 1, policy_version 66390 (0.0007) -[2023-10-09 02:46:18,078][88327] Updated weights for policy 1, policy_version 66400 (0.0010) -[2023-10-09 02:46:18,120][88326] Updated weights for policy 0, policy_version 66342 (0.0007) -[2023-10-09 02:46:18,491][88326] Updated weights for policy 0, policy_version 66352 (0.0009) -[2023-10-09 02:46:18,857][88326] Updated weights for policy 0, policy_version 66362 (0.0009) -[2023-10-09 02:46:18,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 135921664. Throughput: 0: 1694.3, 1: 1676.7. Samples: 33992144. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:46:18,975][87372] Avg episode reward: [(0, '7.260'), (1, '8.160')] -[2023-10-09 02:46:18,983][88168] Saving new best policy, reward=8.160! -[2023-10-09 02:46:22,076][88327] Updated weights for policy 1, policy_version 66410 (0.0008) -[2023-10-09 02:46:22,441][88327] Updated weights for policy 1, policy_version 66420 (0.0009) -[2023-10-09 02:46:22,789][88326] Updated weights for policy 0, policy_version 66372 (0.0009) -[2023-10-09 02:46:22,803][88327] Updated weights for policy 1, policy_version 66430 (0.0008) -[2023-10-09 02:46:23,161][88326] Updated weights for policy 0, policy_version 66382 (0.0007) -[2023-10-09 02:46:23,539][88326] Updated weights for policy 0, policy_version 66392 (0.0008) -[2023-10-09 02:46:23,974][87372] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 136019968. Throughput: 0: 1700.0, 1: 1708.3. Samples: 34002980. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 02:46:23,974][87372] Avg episode reward: [(0, '7.030'), (1, '7.490')] -[2023-10-09 02:46:26,863][88327] Updated weights for policy 1, policy_version 66440 (0.0008) -[2023-10-09 02:46:27,235][88327] Updated weights for policy 1, policy_version 66450 (0.0007) -[2023-10-09 02:46:27,600][88327] Updated weights for policy 1, policy_version 66460 (0.0007) -[2023-10-09 02:46:27,606][88326] Updated weights for policy 0, policy_version 66402 (0.0008) -[2023-10-09 02:46:27,967][88326] Updated weights for policy 0, policy_version 66412 (0.0009) -[2023-10-09 02:46:28,331][88326] Updated weights for policy 0, policy_version 66422 (0.0009) -[2023-10-09 02:46:28,700][88326] Updated weights for policy 0, policy_version 66432 (0.0009) -[2023-10-09 02:46:28,974][87372] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 136085504. Throughput: 0: 1708.4, 1: 1694.8. Samples: 34023470. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 02:46:28,975][87372] Avg episode reward: [(0, '7.370'), (1, '7.950')] -[2023-10-09 02:46:31,627][88327] Updated weights for policy 1, policy_version 66470 (0.0009) -[2023-10-09 02:46:31,988][88327] Updated weights for policy 1, policy_version 66480 (0.0011) -[2023-10-09 02:46:32,350][88327] Updated weights for policy 1, policy_version 66490 (0.0009) -[2023-10-09 02:46:32,681][88326] Updated weights for policy 0, policy_version 66442 (0.0009) -[2023-10-09 02:46:33,047][88326] Updated weights for policy 0, policy_version 66452 (0.0008) -[2023-10-09 02:46:33,417][88326] Updated weights for policy 0, policy_version 66462 (0.0008) -[2023-10-09 02:46:33,974][87372] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 136151040. Throughput: 0: 1685.5, 1: 1684.8. Samples: 34042844. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 02:46:33,975][87372] Avg episode reward: [(0, '6.400'), (1, '7.400')] -[2023-10-09 02:46:33,985][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000066496_68091904.pth... -[2023-10-09 02:46:33,985][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000066464_68059136.pth... -[2023-10-09 02:46:34,018][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000064864_66420736.pth -[2023-10-09 02:46:34,025][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000064896_66453504.pth -[2023-10-09 02:46:36,221][88327] Updated weights for policy 1, policy_version 66500 (0.0008) -[2023-10-09 02:46:36,591][88327] Updated weights for policy 1, policy_version 66510 (0.0007) -[2023-10-09 02:46:36,957][88327] Updated weights for policy 1, policy_version 66520 (0.0009) -[2023-10-09 02:46:37,354][88326] Updated weights for policy 0, policy_version 66472 (0.0007) -[2023-10-09 02:46:37,718][88326] Updated weights for policy 0, policy_version 66482 (0.0010) -[2023-10-09 02:46:38,085][88326] Updated weights for policy 0, policy_version 66492 (0.0009) -[2023-10-09 02:46:38,974][87372] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 136216576. Throughput: 0: 1709.7, 1: 1709.9. Samples: 34054326. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 02:46:38,975][87372] Avg episode reward: [(0, '6.650'), (1, '6.940')] -[2023-10-09 02:46:40,866][88327] Updated weights for policy 1, policy_version 66530 (0.0009) -[2023-10-09 02:46:41,232][88327] Updated weights for policy 1, policy_version 66540 (0.0009) -[2023-10-09 02:46:41,609][88327] Updated weights for policy 1, policy_version 66550 (0.0008) -[2023-10-09 02:46:41,979][88327] Updated weights for policy 1, policy_version 66560 (0.0010) -[2023-10-09 02:46:42,088][88326] Updated weights for policy 0, policy_version 66502 (0.0007) -[2023-10-09 02:46:42,459][88326] Updated weights for policy 0, policy_version 66512 (0.0008) -[2023-10-09 02:46:42,825][88326] Updated weights for policy 0, policy_version 66522 (0.0011) -[2023-10-09 02:46:43,974][87372] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 136282112. Throughput: 0: 1706.7, 1: 1688.6. Samples: 34073852. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 02:46:43,975][87372] Avg episode reward: [(0, '7.130'), (1, '7.180')] -[2023-10-09 02:46:45,951][88327] Updated weights for policy 1, policy_version 66570 (0.0009) -[2023-10-09 02:46:46,310][88327] Updated weights for policy 1, policy_version 66580 (0.0009) -[2023-10-09 02:46:46,687][88327] Updated weights for policy 1, policy_version 66590 (0.0009) -[2023-10-09 02:46:46,898][88326] Updated weights for policy 0, policy_version 66532 (0.0008) -[2023-10-09 02:46:47,262][88326] Updated weights for policy 0, policy_version 66542 (0.0007) -[2023-10-09 02:46:47,633][88326] Updated weights for policy 0, policy_version 66552 (0.0009) -[2023-10-09 02:46:48,974][87372] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 136347648. Throughput: 0: 1680.2, 1: 1705.4. Samples: 34094050. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 02:46:48,975][87372] Avg episode reward: [(0, '6.640'), (1, '6.780')] -[2023-10-09 02:46:50,615][88327] Updated weights for policy 1, policy_version 66600 (0.0008) -[2023-10-09 02:46:50,974][88327] Updated weights for policy 1, policy_version 66610 (0.0009) -[2023-10-09 02:46:51,342][88327] Updated weights for policy 1, policy_version 66620 (0.0007) -[2023-10-09 02:46:51,704][88326] Updated weights for policy 0, policy_version 66562 (0.0010) -[2023-10-09 02:46:52,112][88326] Updated weights for policy 0, policy_version 66572 (0.0007) -[2023-10-09 02:46:52,486][88326] Updated weights for policy 0, policy_version 66582 (0.0007) -[2023-10-09 02:46:52,856][88326] Updated weights for policy 0, policy_version 66592 (0.0007) -[2023-10-09 02:46:53,974][87372] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 136413184. Throughput: 0: 1710.5, 1: 1702.0. Samples: 34105030. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 02:46:53,975][87372] Avg episode reward: [(0, '6.590'), (1, '8.070')] -[2023-10-09 02:46:55,535][88327] Updated weights for policy 1, policy_version 66630 (0.0009) -[2023-10-09 02:46:55,897][88327] Updated weights for policy 1, policy_version 66640 (0.0009) -[2023-10-09 02:46:56,261][88327] Updated weights for policy 1, policy_version 66650 (0.0009) -[2023-10-09 02:46:56,859][88326] Updated weights for policy 0, policy_version 66602 (0.0008) -[2023-10-09 02:46:57,222][88326] Updated weights for policy 0, policy_version 66612 (0.0008) -[2023-10-09 02:46:57,590][88326] Updated weights for policy 0, policy_version 66622 (0.0007) -[2023-10-09 02:46:58,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 136478720. Throughput: 0: 1690.0, 1: 1691.3. Samples: 34124660. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 02:46:58,975][87372] Avg episode reward: [(0, '7.150'), (1, '7.350')] -[2023-10-09 02:47:00,311][88327] Updated weights for policy 1, policy_version 66660 (0.0008) -[2023-10-09 02:47:00,675][88327] Updated weights for policy 1, policy_version 66670 (0.0008) -[2023-10-09 02:47:01,050][88327] Updated weights for policy 1, policy_version 66680 (0.0012) -[2023-10-09 02:47:01,726][88326] Updated weights for policy 0, policy_version 66632 (0.0009) -[2023-10-09 02:47:02,102][88326] Updated weights for policy 0, policy_version 66642 (0.0008) -[2023-10-09 02:47:02,477][88326] Updated weights for policy 0, policy_version 66652 (0.0007) -[2023-10-09 02:47:03,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 136544256. Throughput: 0: 1681.4, 1: 1713.5. Samples: 34144912. Policy #0 lag: (min: 17.0, avg: 25.0, max: 49.0) -[2023-10-09 02:47:03,974][87372] Avg episode reward: [(0, '6.890'), (1, '6.530')] -[2023-10-09 02:47:05,087][88327] Updated weights for policy 1, policy_version 66690 (0.0010) -[2023-10-09 02:47:05,445][88327] Updated weights for policy 1, policy_version 66700 (0.0010) -[2023-10-09 02:47:05,810][88327] Updated weights for policy 1, policy_version 66710 (0.0008) -[2023-10-09 02:47:06,173][88327] Updated weights for policy 1, policy_version 66720 (0.0009) -[2023-10-09 02:47:06,556][88326] Updated weights for policy 0, policy_version 66662 (0.0008) -[2023-10-09 02:47:06,928][88326] Updated weights for policy 0, policy_version 66672 (0.0009) -[2023-10-09 02:47:07,307][88326] Updated weights for policy 0, policy_version 66682 (0.0009) -[2023-10-09 02:47:08,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 136609792. Throughput: 0: 1704.9, 1: 1680.7. Samples: 34155332. Policy #0 lag: (min: 17.0, avg: 25.0, max: 49.0) -[2023-10-09 02:47:08,975][87372] Avg episode reward: [(0, '6.320'), (1, '7.210')] -[2023-10-09 02:47:10,178][88327] Updated weights for policy 1, policy_version 66730 (0.0009) -[2023-10-09 02:47:10,538][88327] Updated weights for policy 1, policy_version 66740 (0.0010) -[2023-10-09 02:47:10,900][88327] Updated weights for policy 1, policy_version 66750 (0.0008) -[2023-10-09 02:47:11,311][88326] Updated weights for policy 0, policy_version 66692 (0.0009) -[2023-10-09 02:47:11,671][88326] Updated weights for policy 0, policy_version 66702 (0.0010) -[2023-10-09 02:47:12,040][88326] Updated weights for policy 0, policy_version 66712 (0.0008) -[2023-10-09 02:47:13,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 136675328. Throughput: 0: 1676.8, 1: 1694.1. Samples: 34175158. Policy #0 lag: (min: 17.0, avg: 25.0, max: 49.0) -[2023-10-09 02:47:13,975][87372] Avg episode reward: [(0, '6.720'), (1, '7.400')] -[2023-10-09 02:47:14,813][88327] Updated weights for policy 1, policy_version 66760 (0.0009) -[2023-10-09 02:47:15,176][88327] Updated weights for policy 1, policy_version 66770 (0.0008) -[2023-10-09 02:47:15,542][88327] Updated weights for policy 1, policy_version 66780 (0.0009) -[2023-10-09 02:47:15,775][88326] Updated weights for policy 0, policy_version 66722 (0.0008) -[2023-10-09 02:47:16,134][88326] Updated weights for policy 0, policy_version 66732 (0.0010) -[2023-10-09 02:47:16,512][88326] Updated weights for policy 0, policy_version 66742 (0.0011) -[2023-10-09 02:47:16,877][88326] Updated weights for policy 0, policy_version 66752 (0.0008) -[2023-10-09 02:47:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 136740864. Throughput: 0: 1694.8, 1: 1712.8. Samples: 34196184. Policy #0 lag: (min: 17.0, avg: 25.0, max: 49.0) -[2023-10-09 02:47:18,975][87372] Avg episode reward: [(0, '6.720'), (1, '6.790')] -[2023-10-09 02:47:19,459][88327] Updated weights for policy 1, policy_version 66790 (0.0008) -[2023-10-09 02:47:19,824][88327] Updated weights for policy 1, policy_version 66800 (0.0010) -[2023-10-09 02:47:20,189][88327] Updated weights for policy 1, policy_version 66810 (0.0009) -[2023-10-09 02:47:20,997][88326] Updated weights for policy 0, policy_version 66762 (0.0011) -[2023-10-09 02:47:21,366][88326] Updated weights for policy 0, policy_version 66772 (0.0010) -[2023-10-09 02:47:21,733][88326] Updated weights for policy 0, policy_version 66782 (0.0010) -[2023-10-09 02:47:23,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 136806400. Throughput: 0: 1686.8, 1: 1682.7. Samples: 34205950. Policy #0 lag: (min: 17.0, avg: 25.0, max: 49.0) -[2023-10-09 02:47:23,975][87372] Avg episode reward: [(0, '6.590'), (1, '7.500')] -[2023-10-09 02:47:24,383][88327] Updated weights for policy 1, policy_version 66820 (0.0009) -[2023-10-09 02:47:24,750][88327] Updated weights for policy 1, policy_version 66830 (0.0008) -[2023-10-09 02:47:25,119][88327] Updated weights for policy 1, policy_version 66840 (0.0010) -[2023-10-09 02:47:25,577][88326] Updated weights for policy 0, policy_version 66792 (0.0008) -[2023-10-09 02:47:25,935][88326] Updated weights for policy 0, policy_version 66802 (0.0007) -[2023-10-09 02:47:26,307][88326] Updated weights for policy 0, policy_version 66812 (0.0007) -[2023-10-09 02:47:28,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 136871936. Throughput: 0: 1682.3, 1: 1706.9. Samples: 34226366. Policy #0 lag: (min: 17.0, avg: 25.0, max: 49.0) -[2023-10-09 02:47:28,975][87372] Avg episode reward: [(0, '7.130'), (1, '7.280')] -[2023-10-09 02:47:29,347][88327] Updated weights for policy 1, policy_version 66850 (0.0008) -[2023-10-09 02:47:29,714][88327] Updated weights for policy 1, policy_version 66860 (0.0007) -[2023-10-09 02:47:30,072][88327] Updated weights for policy 1, policy_version 66870 (0.0007) -[2023-10-09 02:47:30,395][88326] Updated weights for policy 0, policy_version 66822 (0.0009) -[2023-10-09 02:47:30,431][88327] Updated weights for policy 1, policy_version 66880 (0.0009) -[2023-10-09 02:47:30,765][88326] Updated weights for policy 0, policy_version 66832 (0.0008) -[2023-10-09 02:47:31,128][88326] Updated weights for policy 0, policy_version 66842 (0.0010) -[2023-10-09 02:47:33,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 136937472. Throughput: 0: 1698.0, 1: 1699.4. Samples: 34246934. Policy #0 lag: (min: 17.0, avg: 25.0, max: 49.0) -[2023-10-09 02:47:33,975][87372] Avg episode reward: [(0, '7.120'), (1, '7.060')] -[2023-10-09 02:47:34,480][88327] Updated weights for policy 1, policy_version 66890 (0.0010) -[2023-10-09 02:47:34,839][88327] Updated weights for policy 1, policy_version 66900 (0.0010) -[2023-10-09 02:47:35,217][88327] Updated weights for policy 1, policy_version 66910 (0.0008) -[2023-10-09 02:47:35,326][88326] Updated weights for policy 0, policy_version 66852 (0.0010) -[2023-10-09 02:47:35,703][88326] Updated weights for policy 0, policy_version 66862 (0.0010) -[2023-10-09 02:47:36,062][88326] Updated weights for policy 0, policy_version 66872 (0.0010) -[2023-10-09 02:47:38,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 137003008. Throughput: 0: 1674.9, 1: 1685.0. Samples: 34256224. Policy #0 lag: (min: 17.0, avg: 25.0, max: 49.0) -[2023-10-09 02:47:38,975][87372] Avg episode reward: [(0, '7.050'), (1, '7.210')] -[2023-10-09 02:47:39,336][88327] Updated weights for policy 1, policy_version 66920 (0.0008) -[2023-10-09 02:47:39,710][88327] Updated weights for policy 1, policy_version 66930 (0.0007) -[2023-10-09 02:47:40,069][88327] Updated weights for policy 1, policy_version 66940 (0.0008) -[2023-10-09 02:47:40,109][88326] Updated weights for policy 0, policy_version 66882 (0.0011) -[2023-10-09 02:47:40,474][88326] Updated weights for policy 0, policy_version 66892 (0.0009) -[2023-10-09 02:47:40,842][88326] Updated weights for policy 0, policy_version 66902 (0.0008) -[2023-10-09 02:47:41,213][88326] Updated weights for policy 0, policy_version 66912 (0.0009) -[2023-10-09 02:47:43,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 137068544. Throughput: 0: 1686.0, 1: 1691.2. Samples: 34276636. Policy #0 lag: (min: 17.0, avg: 25.0, max: 49.0) -[2023-10-09 02:47:43,975][87372] Avg episode reward: [(0, '7.010'), (1, '7.590')] -[2023-10-09 02:47:44,032][88327] Updated weights for policy 1, policy_version 66950 (0.0009) -[2023-10-09 02:47:44,393][88327] Updated weights for policy 1, policy_version 66960 (0.0007) -[2023-10-09 02:47:44,753][88327] Updated weights for policy 1, policy_version 66970 (0.0011) -[2023-10-09 02:47:45,363][88326] Updated weights for policy 0, policy_version 66922 (0.0008) -[2023-10-09 02:47:45,741][88326] Updated weights for policy 0, policy_version 66932 (0.0010) -[2023-10-09 02:47:46,119][88326] Updated weights for policy 0, policy_version 66942 (0.0007) -[2023-10-09 02:47:48,783][88327] Updated weights for policy 1, policy_version 66980 (0.0009) -[2023-10-09 02:47:48,974][87372] Fps is (10 sec: 13106.7, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 137134080. Throughput: 0: 1696.8, 1: 1694.7. Samples: 34297530. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:47:48,976][87372] Avg episode reward: [(0, '6.510'), (1, '7.180')] -[2023-10-09 02:47:49,148][88327] Updated weights for policy 1, policy_version 66990 (0.0010) -[2023-10-09 02:47:49,510][88327] Updated weights for policy 1, policy_version 67000 (0.0010) -[2023-10-09 02:47:50,101][88326] Updated weights for policy 0, policy_version 66952 (0.0007) -[2023-10-09 02:47:50,468][88326] Updated weights for policy 0, policy_version 66962 (0.0007) -[2023-10-09 02:47:50,842][88326] Updated weights for policy 0, policy_version 66972 (0.0009) -[2023-10-09 02:47:53,593][88327] Updated weights for policy 1, policy_version 67010 (0.0009) -[2023-10-09 02:47:53,955][88327] Updated weights for policy 1, policy_version 67020 (0.0010) -[2023-10-09 02:47:53,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 137199616. Throughput: 0: 1668.9, 1: 1693.8. Samples: 34306652. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:47:53,974][87372] Avg episode reward: [(0, '6.370'), (1, '6.980')] -[2023-10-09 02:47:54,318][88327] Updated weights for policy 1, policy_version 67030 (0.0008) -[2023-10-09 02:47:54,687][88327] Updated weights for policy 1, policy_version 67040 (0.0007) -[2023-10-09 02:47:54,969][88326] Updated weights for policy 0, policy_version 66982 (0.0008) -[2023-10-09 02:47:55,335][88326] Updated weights for policy 0, policy_version 66992 (0.0008) -[2023-10-09 02:47:55,691][88326] Updated weights for policy 0, policy_version 67002 (0.0009) -[2023-10-09 02:47:58,798][88327] Updated weights for policy 1, policy_version 67050 (0.0010) -[2023-10-09 02:47:58,974][87372] Fps is (10 sec: 13107.8, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 137265152. Throughput: 0: 1693.3, 1: 1696.5. Samples: 34327700. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:47:58,974][87372] Avg episode reward: [(0, '6.570'), (1, '7.200')] -[2023-10-09 02:47:59,163][88327] Updated weights for policy 1, policy_version 67060 (0.0010) -[2023-10-09 02:47:59,532][88327] Updated weights for policy 1, policy_version 67070 (0.0008) -[2023-10-09 02:47:59,750][88326] Updated weights for policy 0, policy_version 67012 (0.0008) -[2023-10-09 02:48:00,116][88326] Updated weights for policy 0, policy_version 67022 (0.0009) -[2023-10-09 02:48:00,486][88326] Updated weights for policy 0, policy_version 67032 (0.0007) -[2023-10-09 02:48:03,524][88327] Updated weights for policy 1, policy_version 67080 (0.0008) -[2023-10-09 02:48:03,888][88327] Updated weights for policy 1, policy_version 67090 (0.0008) -[2023-10-09 02:48:03,974][87372] Fps is (10 sec: 13106.7, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 137330688. Throughput: 0: 1697.5, 1: 1689.1. Samples: 34348580. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:48:03,975][87372] Avg episode reward: [(0, '6.810'), (1, '7.040')] -[2023-10-09 02:48:04,248][88327] Updated weights for policy 1, policy_version 67100 (0.0011) -[2023-10-09 02:48:04,710][88326] Updated weights for policy 0, policy_version 67042 (0.0009) -[2023-10-09 02:48:05,077][88326] Updated weights for policy 0, policy_version 67052 (0.0007) -[2023-10-09 02:48:05,439][88326] Updated weights for policy 0, policy_version 67062 (0.0009) -[2023-10-09 02:48:05,816][88326] Updated weights for policy 0, policy_version 67072 (0.0010) -[2023-10-09 02:48:08,403][88327] Updated weights for policy 1, policy_version 67110 (0.0009) -[2023-10-09 02:48:08,770][88327] Updated weights for policy 1, policy_version 67120 (0.0011) -[2023-10-09 02:48:08,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 137396224. Throughput: 0: 1679.8, 1: 1689.9. Samples: 34357586. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:48:08,975][87372] Avg episode reward: [(0, '7.190'), (1, '7.140')] -[2023-10-09 02:48:09,142][88327] Updated weights for policy 1, policy_version 67130 (0.0007) -[2023-10-09 02:48:09,809][88326] Updated weights for policy 0, policy_version 67082 (0.0008) -[2023-10-09 02:48:10,167][88326] Updated weights for policy 0, policy_version 67092 (0.0009) -[2023-10-09 02:48:10,547][88326] Updated weights for policy 0, policy_version 67102 (0.0007) -[2023-10-09 02:48:13,349][88327] Updated weights for policy 1, policy_version 67140 (0.0008) -[2023-10-09 02:48:13,708][88327] Updated weights for policy 1, policy_version 67150 (0.0008) -[2023-10-09 02:48:13,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 137461760. Throughput: 0: 1688.7, 1: 1692.1. Samples: 34378502. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:48:13,975][87372] Avg episode reward: [(0, '7.430'), (1, '7.230')] -[2023-10-09 02:48:14,084][88327] Updated weights for policy 1, policy_version 67160 (0.0010) -[2023-10-09 02:48:14,703][88326] Updated weights for policy 0, policy_version 67112 (0.0009) -[2023-10-09 02:48:15,082][88326] Updated weights for policy 0, policy_version 67122 (0.0008) -[2023-10-09 02:48:15,451][88326] Updated weights for policy 0, policy_version 67132 (0.0008) -[2023-10-09 02:48:18,093][88327] Updated weights for policy 1, policy_version 67170 (0.0010) -[2023-10-09 02:48:18,450][88327] Updated weights for policy 1, policy_version 67180 (0.0007) -[2023-10-09 02:48:18,822][88327] Updated weights for policy 1, policy_version 67190 (0.0008) -[2023-10-09 02:48:18,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 137527296. Throughput: 0: 1694.2, 1: 1689.5. Samples: 34399198. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:48:18,975][87372] Avg episode reward: [(0, '7.730'), (1, '6.980')] -[2023-10-09 02:48:19,183][88327] Updated weights for policy 1, policy_version 67200 (0.0008) -[2023-10-09 02:48:19,295][88326] Updated weights for policy 0, policy_version 67142 (0.0009) -[2023-10-09 02:48:19,668][88326] Updated weights for policy 0, policy_version 67152 (0.0009) -[2023-10-09 02:48:20,040][88326] Updated weights for policy 0, policy_version 67162 (0.0011) -[2023-10-09 02:48:23,332][88327] Updated weights for policy 1, policy_version 67210 (0.0007) -[2023-10-09 02:48:23,700][88327] Updated weights for policy 1, policy_version 67220 (0.0010) -[2023-10-09 02:48:23,913][88326] Updated weights for policy 0, policy_version 67172 (0.0007) -[2023-10-09 02:48:23,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 137592832. Throughput: 0: 1688.8, 1: 1694.9. Samples: 34408492. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:48:23,975][87372] Avg episode reward: [(0, '7.270'), (1, '6.830')] -[2023-10-09 02:48:24,066][88327] Updated weights for policy 1, policy_version 67230 (0.0008) -[2023-10-09 02:48:24,284][88326] Updated weights for policy 0, policy_version 67182 (0.0007) -[2023-10-09 02:48:24,656][88326] Updated weights for policy 0, policy_version 67192 (0.0009) -[2023-10-09 02:48:28,135][88327] Updated weights for policy 1, policy_version 67240 (0.0009) -[2023-10-09 02:48:28,505][88327] Updated weights for policy 1, policy_version 67250 (0.0008) -[2023-10-09 02:48:28,778][88326] Updated weights for policy 0, policy_version 67202 (0.0010) -[2023-10-09 02:48:28,873][88327] Updated weights for policy 1, policy_version 67260 (0.0008) -[2023-10-09 02:48:28,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.3, 300 sec: 13329.4). Total num frames: 137658368. Throughput: 0: 1696.8, 1: 1690.6. Samples: 34429066. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:48:28,975][87372] Avg episode reward: [(0, '7.200'), (1, '6.680')] -[2023-10-09 02:48:29,146][88326] Updated weights for policy 0, policy_version 67212 (0.0009) -[2023-10-09 02:48:29,506][88326] Updated weights for policy 0, policy_version 67222 (0.0008) -[2023-10-09 02:48:29,881][88326] Updated weights for policy 0, policy_version 67232 (0.0008) -[2023-10-09 02:48:32,956][88327] Updated weights for policy 1, policy_version 67270 (0.0008) -[2023-10-09 02:48:33,320][88327] Updated weights for policy 1, policy_version 67280 (0.0007) -[2023-10-09 02:48:33,691][88327] Updated weights for policy 1, policy_version 67290 (0.0007) -[2023-10-09 02:48:33,866][88326] Updated weights for policy 0, policy_version 67242 (0.0009) -[2023-10-09 02:48:33,974][87372] Fps is (10 sec: 16383.9, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 137756672. Throughput: 0: 1701.6, 1: 1675.3. Samples: 34449488. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) -[2023-10-09 02:48:33,975][87372] Avg episode reward: [(0, '7.250'), (1, '7.150')] -[2023-10-09 02:48:33,984][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000067296_68911104.pth... -[2023-10-09 02:48:34,021][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000065696_67272704.pth -[2023-10-09 02:48:34,228][88326] Updated weights for policy 0, policy_version 67252 (0.0008) -[2023-10-09 02:48:34,608][88326] Updated weights for policy 0, policy_version 67262 (0.0007) -[2023-10-09 02:48:34,674][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000067264_68878336.pth... -[2023-10-09 02:48:34,703][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000065664_67239936.pth -[2023-10-09 02:48:37,701][88327] Updated weights for policy 1, policy_version 67300 (0.0007) -[2023-10-09 02:48:38,061][88327] Updated weights for policy 1, policy_version 67310 (0.0008) -[2023-10-09 02:48:38,427][88327] Updated weights for policy 1, policy_version 67320 (0.0009) -[2023-10-09 02:48:38,665][88326] Updated weights for policy 0, policy_version 67272 (0.0008) -[2023-10-09 02:48:38,974][87372] Fps is (10 sec: 16384.1, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 137822208. Throughput: 0: 1694.7, 1: 1687.1. Samples: 34458830. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) -[2023-10-09 02:48:38,974][87372] Avg episode reward: [(0, '6.720'), (1, '6.630')] -[2023-10-09 02:48:39,033][88326] Updated weights for policy 0, policy_version 67282 (0.0010) -[2023-10-09 02:48:39,399][88326] Updated weights for policy 0, policy_version 67292 (0.0007) -[2023-10-09 02:48:42,524][88327] Updated weights for policy 1, policy_version 67330 (0.0007) -[2023-10-09 02:48:42,889][88327] Updated weights for policy 1, policy_version 67340 (0.0007) -[2023-10-09 02:48:43,253][88327] Updated weights for policy 1, policy_version 67350 (0.0008) -[2023-10-09 02:48:43,400][88326] Updated weights for policy 0, policy_version 67302 (0.0010) -[2023-10-09 02:48:43,629][88327] Updated weights for policy 1, policy_version 67360 (0.0008) -[2023-10-09 02:48:43,760][88326] Updated weights for policy 0, policy_version 67312 (0.0009) -[2023-10-09 02:48:43,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 137887744. Throughput: 0: 1692.7, 1: 1682.0. Samples: 34479560. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) -[2023-10-09 02:48:43,975][87372] Avg episode reward: [(0, '7.500'), (1, '6.600')] -[2023-10-09 02:48:44,136][88326] Updated weights for policy 0, policy_version 67322 (0.0010) -[2023-10-09 02:48:47,649][88327] Updated weights for policy 1, policy_version 67370 (0.0007) -[2023-10-09 02:48:48,006][88327] Updated weights for policy 1, policy_version 67380 (0.0009) -[2023-10-09 02:48:48,319][88326] Updated weights for policy 0, policy_version 67332 (0.0009) -[2023-10-09 02:48:48,375][88327] Updated weights for policy 1, policy_version 67390 (0.0010) -[2023-10-09 02:48:48,687][88326] Updated weights for policy 0, policy_version 67342 (0.0007) -[2023-10-09 02:48:48,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 137953280. Throughput: 0: 1688.8, 1: 1661.8. Samples: 34499356. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) -[2023-10-09 02:48:48,975][87372] Avg episode reward: [(0, '7.310'), (1, '7.540')] -[2023-10-09 02:48:49,061][88326] Updated weights for policy 0, policy_version 67352 (0.0011) -[2023-10-09 02:48:52,411][88327] Updated weights for policy 1, policy_version 67400 (0.0008) -[2023-10-09 02:48:52,772][88327] Updated weights for policy 1, policy_version 67410 (0.0008) -[2023-10-09 02:48:53,080][88326] Updated weights for policy 0, policy_version 67362 (0.0008) -[2023-10-09 02:48:53,127][88327] Updated weights for policy 1, policy_version 67420 (0.0007) -[2023-10-09 02:48:53,452][88326] Updated weights for policy 0, policy_version 67372 (0.0009) -[2023-10-09 02:48:53,829][88326] Updated weights for policy 0, policy_version 67382 (0.0008) -[2023-10-09 02:48:53,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 138018816. Throughput: 0: 1691.2, 1: 1684.8. Samples: 34509508. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) -[2023-10-09 02:48:53,975][87372] Avg episode reward: [(0, '6.770'), (1, '7.450')] -[2023-10-09 02:48:54,186][88326] Updated weights for policy 0, policy_version 67392 (0.0007) -[2023-10-09 02:48:57,097][88327] Updated weights for policy 1, policy_version 67430 (0.0007) -[2023-10-09 02:48:57,466][88327] Updated weights for policy 1, policy_version 67440 (0.0008) -[2023-10-09 02:48:57,832][88327] Updated weights for policy 1, policy_version 67450 (0.0008) -[2023-10-09 02:48:58,199][88326] Updated weights for policy 0, policy_version 67402 (0.0008) -[2023-10-09 02:48:58,570][88326] Updated weights for policy 0, policy_version 67412 (0.0009) -[2023-10-09 02:48:58,939][88326] Updated weights for policy 0, policy_version 67422 (0.0009) -[2023-10-09 02:48:58,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 138084352. Throughput: 0: 1689.6, 1: 1678.3. Samples: 34530058. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) -[2023-10-09 02:48:58,974][87372] Avg episode reward: [(0, '7.120'), (1, '7.220')] -[2023-10-09 02:49:01,828][88327] Updated weights for policy 1, policy_version 67460 (0.0009) -[2023-10-09 02:49:02,192][88327] Updated weights for policy 1, policy_version 67470 (0.0007) -[2023-10-09 02:49:02,559][88327] Updated weights for policy 1, policy_version 67480 (0.0008) -[2023-10-09 02:49:03,017][88326] Updated weights for policy 0, policy_version 67432 (0.0009) -[2023-10-09 02:49:03,390][88326] Updated weights for policy 0, policy_version 67442 (0.0010) -[2023-10-09 02:49:03,762][88326] Updated weights for policy 0, policy_version 67452 (0.0009) -[2023-10-09 02:49:03,974][87372] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 138182656. Throughput: 0: 1674.8, 1: 1662.3. Samples: 34549370. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) -[2023-10-09 02:49:03,975][87372] Avg episode reward: [(0, '6.530'), (1, '7.820')] -[2023-10-09 02:49:06,521][88327] Updated weights for policy 1, policy_version 67490 (0.0008) -[2023-10-09 02:49:06,891][88327] Updated weights for policy 1, policy_version 67500 (0.0008) -[2023-10-09 02:49:07,243][88327] Updated weights for policy 1, policy_version 67510 (0.0007) -[2023-10-09 02:49:07,614][88327] Updated weights for policy 1, policy_version 67520 (0.0009) -[2023-10-09 02:49:07,827][88326] Updated weights for policy 0, policy_version 67462 (0.0010) -[2023-10-09 02:49:08,192][88326] Updated weights for policy 0, policy_version 67472 (0.0011) -[2023-10-09 02:49:08,559][88326] Updated weights for policy 0, policy_version 67482 (0.0011) -[2023-10-09 02:49:08,974][87372] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 138248192. Throughput: 0: 1685.5, 1: 1693.3. Samples: 34560538. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) -[2023-10-09 02:49:08,975][87372] Avg episode reward: [(0, '6.800'), (1, '7.790')] -[2023-10-09 02:49:11,628][88327] Updated weights for policy 1, policy_version 67530 (0.0007) -[2023-10-09 02:49:11,988][88327] Updated weights for policy 1, policy_version 67540 (0.0010) -[2023-10-09 02:49:12,357][88327] Updated weights for policy 1, policy_version 67550 (0.0010) -[2023-10-09 02:49:12,517][88326] Updated weights for policy 0, policy_version 67492 (0.0011) -[2023-10-09 02:49:12,885][88326] Updated weights for policy 0, policy_version 67502 (0.0010) -[2023-10-09 02:49:13,251][88326] Updated weights for policy 0, policy_version 67512 (0.0007) -[2023-10-09 02:49:13,974][87372] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 138313728. Throughput: 0: 1683.2, 1: 1680.1. Samples: 34580416. Policy #0 lag: (min: 10.0, avg: 16.2, max: 42.0) -[2023-10-09 02:49:13,974][87372] Avg episode reward: [(0, '7.660'), (1, '7.880')] -[2023-10-09 02:49:16,554][88327] Updated weights for policy 1, policy_version 67560 (0.0009) -[2023-10-09 02:49:16,929][88327] Updated weights for policy 1, policy_version 67570 (0.0010) -[2023-10-09 02:49:17,175][88326] Updated weights for policy 0, policy_version 67522 (0.0008) -[2023-10-09 02:49:17,295][88327] Updated weights for policy 1, policy_version 67580 (0.0008) -[2023-10-09 02:49:17,549][88326] Updated weights for policy 0, policy_version 67532 (0.0007) -[2023-10-09 02:49:17,911][88326] Updated weights for policy 0, policy_version 67542 (0.0010) -[2023-10-09 02:49:18,279][88326] Updated weights for policy 0, policy_version 67552 (0.0010) -[2023-10-09 02:49:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 138379264. Throughput: 0: 1659.5, 1: 1683.1. Samples: 34599904. Policy #0 lag: (min: 10.0, avg: 16.2, max: 42.0) -[2023-10-09 02:49:18,975][87372] Avg episode reward: [(0, '7.440'), (1, '7.550')] -[2023-10-09 02:49:21,307][88327] Updated weights for policy 1, policy_version 67590 (0.0007) -[2023-10-09 02:49:21,662][88327] Updated weights for policy 1, policy_version 67600 (0.0009) -[2023-10-09 02:49:22,021][88327] Updated weights for policy 1, policy_version 67610 (0.0009) -[2023-10-09 02:49:22,335][88326] Updated weights for policy 0, policy_version 67562 (0.0010) -[2023-10-09 02:49:22,699][88326] Updated weights for policy 0, policy_version 67572 (0.0007) -[2023-10-09 02:49:23,062][88326] Updated weights for policy 0, policy_version 67582 (0.0011) -[2023-10-09 02:49:23,974][87372] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 138444800. Throughput: 0: 1692.6, 1: 1701.3. Samples: 34611556. Policy #0 lag: (min: 10.0, avg: 16.2, max: 42.0) -[2023-10-09 02:49:23,975][87372] Avg episode reward: [(0, '7.580'), (1, '7.180')] -[2023-10-09 02:49:26,121][88327] Updated weights for policy 1, policy_version 67620 (0.0008) -[2023-10-09 02:49:26,488][88327] Updated weights for policy 1, policy_version 67630 (0.0008) -[2023-10-09 02:49:26,845][88327] Updated weights for policy 1, policy_version 67640 (0.0009) -[2023-10-09 02:49:27,089][88326] Updated weights for policy 0, policy_version 67592 (0.0008) -[2023-10-09 02:49:27,460][88326] Updated weights for policy 0, policy_version 67602 (0.0008) -[2023-10-09 02:49:27,823][88326] Updated weights for policy 0, policy_version 67612 (0.0008) -[2023-10-09 02:49:28,974][87372] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 138510336. Throughput: 0: 1690.9, 1: 1674.4. Samples: 34631000. Policy #0 lag: (min: 10.0, avg: 16.2, max: 42.0) -[2023-10-09 02:49:28,974][87372] Avg episode reward: [(0, '7.300'), (1, '7.050')] -[2023-10-09 02:49:30,839][88327] Updated weights for policy 1, policy_version 67650 (0.0009) -[2023-10-09 02:49:31,207][88327] Updated weights for policy 1, policy_version 67660 (0.0010) -[2023-10-09 02:49:31,571][88327] Updated weights for policy 1, policy_version 67670 (0.0010) -[2023-10-09 02:49:31,935][88327] Updated weights for policy 1, policy_version 67680 (0.0009) -[2023-10-09 02:49:31,970][88326] Updated weights for policy 0, policy_version 67622 (0.0010) -[2023-10-09 02:49:32,341][88326] Updated weights for policy 0, policy_version 67632 (0.0010) -[2023-10-09 02:49:32,709][88326] Updated weights for policy 0, policy_version 67642 (0.0007) -[2023-10-09 02:49:33,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 138575872. Throughput: 0: 1673.3, 1: 1697.0. Samples: 34651020. Policy #0 lag: (min: 10.0, avg: 16.2, max: 42.0) -[2023-10-09 02:49:33,975][87372] Avg episode reward: [(0, '7.410'), (1, '6.790')] -[2023-10-09 02:49:35,915][88327] Updated weights for policy 1, policy_version 67690 (0.0008) -[2023-10-09 02:49:36,272][88327] Updated weights for policy 1, policy_version 67700 (0.0009) -[2023-10-09 02:49:36,629][88327] Updated weights for policy 1, policy_version 67710 (0.0009) -[2023-10-09 02:49:36,769][88326] Updated weights for policy 0, policy_version 67652 (0.0007) -[2023-10-09 02:49:37,148][88326] Updated weights for policy 0, policy_version 67662 (0.0007) -[2023-10-09 02:49:37,518][88326] Updated weights for policy 0, policy_version 67672 (0.0007) -[2023-10-09 02:49:38,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 138641408. Throughput: 0: 1702.8, 1: 1692.4. Samples: 34662290. Policy #0 lag: (min: 10.0, avg: 16.2, max: 42.0) -[2023-10-09 02:49:38,975][87372] Avg episode reward: [(0, '7.010'), (1, '7.130')] -[2023-10-09 02:49:40,697][88327] Updated weights for policy 1, policy_version 67720 (0.0009) -[2023-10-09 02:49:41,053][88327] Updated weights for policy 1, policy_version 67730 (0.0008) -[2023-10-09 02:49:41,424][88327] Updated weights for policy 1, policy_version 67740 (0.0007) -[2023-10-09 02:49:41,517][88326] Updated weights for policy 0, policy_version 67682 (0.0007) -[2023-10-09 02:49:41,882][88326] Updated weights for policy 0, policy_version 67692 (0.0007) -[2023-10-09 02:49:42,252][88326] Updated weights for policy 0, policy_version 67702 (0.0007) -[2023-10-09 02:49:42,614][88326] Updated weights for policy 0, policy_version 67712 (0.0008) -[2023-10-09 02:49:43,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 138706944. Throughput: 0: 1688.1, 1: 1682.6. Samples: 34681742. Policy #0 lag: (min: 10.0, avg: 16.2, max: 42.0) -[2023-10-09 02:49:43,976][87372] Avg episode reward: [(0, '7.270'), (1, '7.700')] -[2023-10-09 02:49:45,350][88327] Updated weights for policy 1, policy_version 67750 (0.0008) -[2023-10-09 02:49:45,713][88327] Updated weights for policy 1, policy_version 67760 (0.0009) -[2023-10-09 02:49:46,089][88327] Updated weights for policy 1, policy_version 67770 (0.0011) -[2023-10-09 02:49:46,708][88326] Updated weights for policy 0, policy_version 67722 (0.0007) -[2023-10-09 02:49:47,086][88326] Updated weights for policy 0, policy_version 67732 (0.0008) -[2023-10-09 02:49:47,451][88326] Updated weights for policy 0, policy_version 67742 (0.0008) -[2023-10-09 02:49:48,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 138772480. Throughput: 0: 1689.9, 1: 1705.8. Samples: 34702174. Policy #0 lag: (min: 10.0, avg: 16.2, max: 42.0) -[2023-10-09 02:49:48,975][87372] Avg episode reward: [(0, '7.200'), (1, '8.500')] -[2023-10-09 02:49:48,983][88168] Saving new best policy, reward=8.500! -[2023-10-09 02:49:50,109][88327] Updated weights for policy 1, policy_version 67780 (0.0009) -[2023-10-09 02:49:50,466][88327] Updated weights for policy 1, policy_version 67790 (0.0010) -[2023-10-09 02:49:50,829][88327] Updated weights for policy 1, policy_version 67800 (0.0007) -[2023-10-09 02:49:51,355][88326] Updated weights for policy 0, policy_version 67752 (0.0008) -[2023-10-09 02:49:51,724][88326] Updated weights for policy 0, policy_version 67762 (0.0010) -[2023-10-09 02:49:52,098][88326] Updated weights for policy 0, policy_version 67772 (0.0010) -[2023-10-09 02:49:53,974][87372] Fps is (10 sec: 13107.6, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 138838016. Throughput: 0: 1705.3, 1: 1671.9. Samples: 34712510. Policy #0 lag: (min: 10.0, avg: 16.2, max: 42.0) -[2023-10-09 02:49:53,974][87372] Avg episode reward: [(0, '6.450'), (1, '7.320')] -[2023-10-09 02:49:54,866][88327] Updated weights for policy 1, policy_version 67810 (0.0007) -[2023-10-09 02:49:55,230][88327] Updated weights for policy 1, policy_version 67820 (0.0008) -[2023-10-09 02:49:55,596][88327] Updated weights for policy 1, policy_version 67830 (0.0009) -[2023-10-09 02:49:55,965][88327] Updated weights for policy 1, policy_version 67840 (0.0009) -[2023-10-09 02:49:56,260][88326] Updated weights for policy 0, policy_version 67782 (0.0010) -[2023-10-09 02:49:56,636][88326] Updated weights for policy 0, policy_version 67792 (0.0008) -[2023-10-09 02:49:57,017][88326] Updated weights for policy 0, policy_version 67802 (0.0008) -[2023-10-09 02:49:58,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 138903552. Throughput: 0: 1677.3, 1: 1695.1. Samples: 34732176. Policy #0 lag: (min: 8.0, avg: 27.0, max: 40.0) -[2023-10-09 02:49:58,975][87372] Avg episode reward: [(0, '6.560'), (1, '7.450')] -[2023-10-09 02:50:00,131][88327] Updated weights for policy 1, policy_version 67850 (0.0007) -[2023-10-09 02:50:00,488][88327] Updated weights for policy 1, policy_version 67860 (0.0008) -[2023-10-09 02:50:00,849][88327] Updated weights for policy 1, policy_version 67870 (0.0008) -[2023-10-09 02:50:01,033][88326] Updated weights for policy 0, policy_version 67812 (0.0009) -[2023-10-09 02:50:01,410][88326] Updated weights for policy 0, policy_version 67822 (0.0009) -[2023-10-09 02:50:01,783][88326] Updated weights for policy 0, policy_version 67832 (0.0008) -[2023-10-09 02:50:03,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 138969088. Throughput: 0: 1701.5, 1: 1703.7. Samples: 34753134. Policy #0 lag: (min: 8.0, avg: 27.0, max: 40.0) -[2023-10-09 02:50:03,975][87372] Avg episode reward: [(0, '7.060'), (1, '7.620')] -[2023-10-09 02:50:04,816][88327] Updated weights for policy 1, policy_version 67880 (0.0008) -[2023-10-09 02:50:05,196][88327] Updated weights for policy 1, policy_version 67890 (0.0008) -[2023-10-09 02:50:05,561][88327] Updated weights for policy 1, policy_version 67900 (0.0008) -[2023-10-09 02:50:05,842][88326] Updated weights for policy 0, policy_version 67842 (0.0008) -[2023-10-09 02:50:06,209][88326] Updated weights for policy 0, policy_version 67852 (0.0009) -[2023-10-09 02:50:06,572][88326] Updated weights for policy 0, policy_version 67862 (0.0008) -[2023-10-09 02:50:06,943][88326] Updated weights for policy 0, policy_version 67872 (0.0007) -[2023-10-09 02:50:08,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 139034624. Throughput: 0: 1691.4, 1: 1673.6. Samples: 34762980. Policy #0 lag: (min: 8.0, avg: 27.0, max: 40.0) -[2023-10-09 02:50:08,975][87372] Avg episode reward: [(0, '7.090'), (1, '7.450')] -[2023-10-09 02:50:09,648][88327] Updated weights for policy 1, policy_version 67910 (0.0010) -[2023-10-09 02:50:10,017][88327] Updated weights for policy 1, policy_version 67920 (0.0010) -[2023-10-09 02:50:10,383][88327] Updated weights for policy 1, policy_version 67930 (0.0009) -[2023-10-09 02:50:10,731][88326] Updated weights for policy 0, policy_version 67882 (0.0009) -[2023-10-09 02:50:11,102][88326] Updated weights for policy 0, policy_version 67892 (0.0010) -[2023-10-09 02:50:11,482][88326] Updated weights for policy 0, policy_version 67902 (0.0008) -[2023-10-09 02:50:13,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 139100160. Throughput: 0: 1687.2, 1: 1699.0. Samples: 34783382. Policy #0 lag: (min: 8.0, avg: 27.0, max: 40.0) -[2023-10-09 02:50:13,975][87372] Avg episode reward: [(0, '7.380'), (1, '7.300')] -[2023-10-09 02:50:14,477][88327] Updated weights for policy 1, policy_version 67940 (0.0009) -[2023-10-09 02:50:14,852][88327] Updated weights for policy 1, policy_version 67950 (0.0010) -[2023-10-09 02:50:15,217][88327] Updated weights for policy 1, policy_version 67960 (0.0010) -[2023-10-09 02:50:15,501][88326] Updated weights for policy 0, policy_version 67912 (0.0009) -[2023-10-09 02:50:15,873][88326] Updated weights for policy 0, policy_version 67922 (0.0010) -[2023-10-09 02:50:16,245][88326] Updated weights for policy 0, policy_version 67932 (0.0010) -[2023-10-09 02:50:18,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 139165696. Throughput: 0: 1708.0, 1: 1696.0. Samples: 34804202. Policy #0 lag: (min: 8.0, avg: 27.0, max: 40.0) -[2023-10-09 02:50:18,975][87372] Avg episode reward: [(0, '7.170'), (1, '7.320')] -[2023-10-09 02:50:19,289][88327] Updated weights for policy 1, policy_version 67970 (0.0008) -[2023-10-09 02:50:19,655][88327] Updated weights for policy 1, policy_version 67980 (0.0009) -[2023-10-09 02:50:20,027][88327] Updated weights for policy 1, policy_version 67990 (0.0008) -[2023-10-09 02:50:20,206][88326] Updated weights for policy 0, policy_version 67942 (0.0009) -[2023-10-09 02:50:20,388][88327] Updated weights for policy 1, policy_version 68000 (0.0008) -[2023-10-09 02:50:20,572][88326] Updated weights for policy 0, policy_version 67952 (0.0007) -[2023-10-09 02:50:20,951][88326] Updated weights for policy 0, policy_version 67962 (0.0008) -[2023-10-09 02:50:23,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 139231232. Throughput: 0: 1680.0, 1: 1676.5. Samples: 34813330. Policy #0 lag: (min: 8.0, avg: 27.0, max: 40.0) -[2023-10-09 02:50:23,975][87372] Avg episode reward: [(0, '6.840'), (1, '7.380')] -[2023-10-09 02:50:24,660][88327] Updated weights for policy 1, policy_version 68010 (0.0007) -[2023-10-09 02:50:25,018][88326] Updated weights for policy 0, policy_version 67972 (0.0010) -[2023-10-09 02:50:25,026][88327] Updated weights for policy 1, policy_version 68020 (0.0007) -[2023-10-09 02:50:25,384][88326] Updated weights for policy 0, policy_version 67982 (0.0008) -[2023-10-09 02:50:25,392][88327] Updated weights for policy 1, policy_version 68030 (0.0008) -[2023-10-09 02:50:25,744][88326] Updated weights for policy 0, policy_version 67992 (0.0010) -[2023-10-09 02:50:28,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 139296768. Throughput: 0: 1691.6, 1: 1694.8. Samples: 34834128. Policy #0 lag: (min: 8.0, avg: 27.0, max: 40.0) -[2023-10-09 02:50:28,974][87372] Avg episode reward: [(0, '6.420'), (1, '8.060')] -[2023-10-09 02:50:29,448][88327] Updated weights for policy 1, policy_version 68040 (0.0007) -[2023-10-09 02:50:29,821][88327] Updated weights for policy 1, policy_version 68050 (0.0007) -[2023-10-09 02:50:29,831][88326] Updated weights for policy 0, policy_version 68002 (0.0009) -[2023-10-09 02:50:30,184][88327] Updated weights for policy 1, policy_version 68060 (0.0007) -[2023-10-09 02:50:30,189][88326] Updated weights for policy 0, policy_version 68012 (0.0007) -[2023-10-09 02:50:30,562][88326] Updated weights for policy 0, policy_version 68022 (0.0009) -[2023-10-09 02:50:30,939][88326] Updated weights for policy 0, policy_version 68032 (0.0010) -[2023-10-09 02:50:33,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 139362304. Throughput: 0: 1702.8, 1: 1690.3. Samples: 34854864. Policy #0 lag: (min: 8.0, avg: 27.0, max: 40.0) -[2023-10-09 02:50:33,975][87372] Avg episode reward: [(0, '7.010'), (1, '7.470')] -[2023-10-09 02:50:33,984][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000068032_69664768.pth... -[2023-10-09 02:50:34,020][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000066464_68059136.pth -[2023-10-09 02:50:34,191][88327] Updated weights for policy 1, policy_version 68070 (0.0009) -[2023-10-09 02:50:34,558][88327] Updated weights for policy 1, policy_version 68080 (0.0009) -[2023-10-09 02:50:34,919][88327] Updated weights for policy 1, policy_version 68090 (0.0008) -[2023-10-09 02:50:35,004][88326] Updated weights for policy 0, policy_version 68042 (0.0009) -[2023-10-09 02:50:35,140][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000068096_69730304.pth... -[2023-10-09 02:50:35,169][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000066496_68091904.pth -[2023-10-09 02:50:35,378][88326] Updated weights for policy 0, policy_version 68052 (0.0007) -[2023-10-09 02:50:35,742][88326] Updated weights for policy 0, policy_version 68062 (0.0008) -[2023-10-09 02:50:38,974][88327] Updated weights for policy 1, policy_version 68100 (0.0008) -[2023-10-09 02:50:38,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 139427840. Throughput: 0: 1676.4, 1: 1689.6. Samples: 34863978. Policy #0 lag: (min: 8.0, avg: 27.0, max: 40.0) -[2023-10-09 02:50:38,975][87372] Avg episode reward: [(0, '6.990'), (1, '6.830')] -[2023-10-09 02:50:39,347][88327] Updated weights for policy 1, policy_version 68110 (0.0007) -[2023-10-09 02:50:39,713][88327] Updated weights for policy 1, policy_version 68120 (0.0007) -[2023-10-09 02:50:39,787][88326] Updated weights for policy 0, policy_version 68072 (0.0009) -[2023-10-09 02:50:40,156][88326] Updated weights for policy 0, policy_version 68082 (0.0010) -[2023-10-09 02:50:40,522][88326] Updated weights for policy 0, policy_version 68092 (0.0007) -[2023-10-09 02:50:43,654][88327] Updated weights for policy 1, policy_version 68130 (0.0009) -[2023-10-09 02:50:43,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 139493376. Throughput: 0: 1707.7, 1: 1685.6. Samples: 34884872. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:50:43,975][87372] Avg episode reward: [(0, '6.530'), (1, '6.900')] -[2023-10-09 02:50:44,011][88327] Updated weights for policy 1, policy_version 68140 (0.0008) -[2023-10-09 02:50:44,374][88327] Updated weights for policy 1, policy_version 68150 (0.0007) -[2023-10-09 02:50:44,636][88326] Updated weights for policy 0, policy_version 68102 (0.0007) -[2023-10-09 02:50:44,732][88327] Updated weights for policy 1, policy_version 68160 (0.0007) -[2023-10-09 02:50:45,002][88326] Updated weights for policy 0, policy_version 68112 (0.0008) -[2023-10-09 02:50:45,371][88326] Updated weights for policy 0, policy_version 68122 (0.0008) -[2023-10-09 02:50:48,830][88327] Updated weights for policy 1, policy_version 68170 (0.0010) -[2023-10-09 02:50:48,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 139558912. Throughput: 0: 1703.8, 1: 1686.4. Samples: 34905692. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:50:48,975][87372] Avg episode reward: [(0, '6.890'), (1, '6.630')] -[2023-10-09 02:50:49,205][88327] Updated weights for policy 1, policy_version 68180 (0.0009) -[2023-10-09 02:50:49,298][88326] Updated weights for policy 0, policy_version 68132 (0.0009) -[2023-10-09 02:50:49,561][88327] Updated weights for policy 1, policy_version 68190 (0.0007) -[2023-10-09 02:50:49,665][88326] Updated weights for policy 0, policy_version 68142 (0.0007) -[2023-10-09 02:50:50,037][88326] Updated weights for policy 0, policy_version 68152 (0.0007) -[2023-10-09 02:50:53,650][88327] Updated weights for policy 1, policy_version 68200 (0.0008) -[2023-10-09 02:50:53,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 139624448. Throughput: 0: 1685.7, 1: 1687.3. Samples: 34914766. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:50:53,975][87372] Avg episode reward: [(0, '6.290'), (1, '6.730')] -[2023-10-09 02:50:53,976][88326] Updated weights for policy 0, policy_version 68162 (0.0007) -[2023-10-09 02:50:54,018][88327] Updated weights for policy 1, policy_version 68210 (0.0009) -[2023-10-09 02:50:54,346][88326] Updated weights for policy 0, policy_version 68172 (0.0008) -[2023-10-09 02:50:54,391][88327] Updated weights for policy 1, policy_version 68220 (0.0008) -[2023-10-09 02:50:54,718][88326] Updated weights for policy 0, policy_version 68182 (0.0007) -[2023-10-09 02:50:55,076][88326] Updated weights for policy 0, policy_version 68192 (0.0007) -[2023-10-09 02:50:58,481][88327] Updated weights for policy 1, policy_version 68230 (0.0008) -[2023-10-09 02:50:58,852][88327] Updated weights for policy 1, policy_version 68240 (0.0007) -[2023-10-09 02:50:58,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 139689984. Throughput: 0: 1698.3, 1: 1688.1. Samples: 34935770. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:50:58,975][87372] Avg episode reward: [(0, '6.610'), (1, '7.220')] -[2023-10-09 02:50:58,999][88326] Updated weights for policy 0, policy_version 68202 (0.0008) -[2023-10-09 02:50:59,218][88327] Updated weights for policy 1, policy_version 68250 (0.0009) -[2023-10-09 02:50:59,366][88326] Updated weights for policy 0, policy_version 68212 (0.0009) -[2023-10-09 02:50:59,730][88326] Updated weights for policy 0, policy_version 68222 (0.0007) -[2023-10-09 02:51:03,339][88327] Updated weights for policy 1, policy_version 68260 (0.0009) -[2023-10-09 02:51:03,703][88327] Updated weights for policy 1, policy_version 68270 (0.0008) -[2023-10-09 02:51:03,845][88326] Updated weights for policy 0, policy_version 68232 (0.0009) -[2023-10-09 02:51:03,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 139755520. Throughput: 0: 1705.0, 1: 1688.9. Samples: 34956926. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:51:03,975][87372] Avg episode reward: [(0, '6.560'), (1, '7.420')] -[2023-10-09 02:51:04,071][88327] Updated weights for policy 1, policy_version 68280 (0.0009) -[2023-10-09 02:51:04,223][88326] Updated weights for policy 0, policy_version 68242 (0.0009) -[2023-10-09 02:51:04,587][88326] Updated weights for policy 0, policy_version 68252 (0.0009) -[2023-10-09 02:51:07,847][88327] Updated weights for policy 1, policy_version 68290 (0.0008) -[2023-10-09 02:51:08,203][88327] Updated weights for policy 1, policy_version 68300 (0.0008) -[2023-10-09 02:51:08,571][88327] Updated weights for policy 1, policy_version 68310 (0.0007) -[2023-10-09 02:51:08,849][88326] Updated weights for policy 0, policy_version 68262 (0.0009) -[2023-10-09 02:51:08,942][88327] Updated weights for policy 1, policy_version 68320 (0.0008) -[2023-10-09 02:51:08,974][87372] Fps is (10 sec: 16384.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 139853824. Throughput: 0: 1698.5, 1: 1691.9. Samples: 34965898. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:51:08,975][87372] Avg episode reward: [(0, '7.340'), (1, '6.980')] -[2023-10-09 02:51:09,223][88326] Updated weights for policy 0, policy_version 68272 (0.0008) -[2023-10-09 02:51:09,598][88326] Updated weights for policy 0, policy_version 68282 (0.0009) -[2023-10-09 02:51:12,885][88327] Updated weights for policy 1, policy_version 68330 (0.0009) -[2023-10-09 02:51:13,258][88327] Updated weights for policy 1, policy_version 68340 (0.0009) -[2023-10-09 02:51:13,574][88326] Updated weights for policy 0, policy_version 68292 (0.0008) -[2023-10-09 02:51:13,618][88327] Updated weights for policy 1, policy_version 68350 (0.0009) -[2023-10-09 02:51:13,950][88326] Updated weights for policy 0, policy_version 68302 (0.0008) -[2023-10-09 02:51:13,974][87372] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 139919360. Throughput: 0: 1701.1, 1: 1696.5. Samples: 34987022. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:51:13,975][87372] Avg episode reward: [(0, '6.760'), (1, '7.400')] -[2023-10-09 02:51:14,308][88326] Updated weights for policy 0, policy_version 68312 (0.0008) -[2023-10-09 02:51:17,511][88327] Updated weights for policy 1, policy_version 68360 (0.0009) -[2023-10-09 02:51:17,880][88327] Updated weights for policy 1, policy_version 68370 (0.0008) -[2023-10-09 02:51:18,242][88327] Updated weights for policy 1, policy_version 68380 (0.0007) -[2023-10-09 02:51:18,402][88326] Updated weights for policy 0, policy_version 68322 (0.0008) -[2023-10-09 02:51:18,773][88326] Updated weights for policy 0, policy_version 68332 (0.0009) -[2023-10-09 02:51:18,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 139984896. Throughput: 0: 1705.6, 1: 1687.7. Samples: 35007562. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:51:18,975][87372] Avg episode reward: [(0, '6.930'), (1, '7.830')] -[2023-10-09 02:51:19,140][88326] Updated weights for policy 0, policy_version 68342 (0.0009) -[2023-10-09 02:51:19,503][88326] Updated weights for policy 0, policy_version 68352 (0.0010) -[2023-10-09 02:51:22,135][88327] Updated weights for policy 1, policy_version 68390 (0.0007) -[2023-10-09 02:51:22,498][88327] Updated weights for policy 1, policy_version 68400 (0.0009) -[2023-10-09 02:51:22,870][88327] Updated weights for policy 1, policy_version 68410 (0.0007) -[2023-10-09 02:51:23,441][88326] Updated weights for policy 0, policy_version 68362 (0.0009) -[2023-10-09 02:51:23,815][88326] Updated weights for policy 0, policy_version 68372 (0.0008) -[2023-10-09 02:51:23,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 140050432. Throughput: 0: 1704.1, 1: 1709.3. Samples: 35017582. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:51:23,975][87372] Avg episode reward: [(0, '6.850'), (1, '7.620')] -[2023-10-09 02:51:24,177][88326] Updated weights for policy 0, policy_version 68382 (0.0010) -[2023-10-09 02:51:26,757][88327] Updated weights for policy 1, policy_version 68420 (0.0010) -[2023-10-09 02:51:27,126][88327] Updated weights for policy 1, policy_version 68430 (0.0008) -[2023-10-09 02:51:27,485][88327] Updated weights for policy 1, policy_version 68440 (0.0007) -[2023-10-09 02:51:28,085][88326] Updated weights for policy 0, policy_version 68392 (0.0008) -[2023-10-09 02:51:28,450][88326] Updated weights for policy 0, policy_version 68402 (0.0007) -[2023-10-09 02:51:28,810][88326] Updated weights for policy 0, policy_version 68412 (0.0008) -[2023-10-09 02:51:28,974][87372] Fps is (10 sec: 16384.2, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 140148736. Throughput: 0: 1703.5, 1: 1705.2. Samples: 35038262. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:51:28,975][87372] Avg episode reward: [(0, '6.030'), (1, '7.580')] -[2023-10-09 02:51:31,594][88327] Updated weights for policy 1, policy_version 68450 (0.0009) -[2023-10-09 02:51:31,959][88327] Updated weights for policy 1, policy_version 68460 (0.0007) -[2023-10-09 02:51:32,343][88327] Updated weights for policy 1, policy_version 68470 (0.0007) -[2023-10-09 02:51:32,700][88327] Updated weights for policy 1, policy_version 68480 (0.0010) -[2023-10-09 02:51:32,730][88326] Updated weights for policy 0, policy_version 68422 (0.0009) -[2023-10-09 02:51:33,107][88326] Updated weights for policy 0, policy_version 68432 (0.0008) -[2023-10-09 02:51:33,472][88326] Updated weights for policy 0, policy_version 68442 (0.0008) -[2023-10-09 02:51:33,975][87372] Fps is (10 sec: 16383.1, 60 sec: 14199.3, 300 sec: 13551.5). Total num frames: 140214272. Throughput: 0: 1689.8, 1: 1691.4. Samples: 35057848. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:51:33,976][87372] Avg episode reward: [(0, '6.410'), (1, '7.390')] -[2023-10-09 02:51:36,688][88327] Updated weights for policy 1, policy_version 68490 (0.0009) -[2023-10-09 02:51:37,046][88327] Updated weights for policy 1, policy_version 68500 (0.0009) -[2023-10-09 02:51:37,413][88327] Updated weights for policy 1, policy_version 68510 (0.0007) -[2023-10-09 02:51:37,498][88326] Updated weights for policy 0, policy_version 68452 (0.0008) -[2023-10-09 02:51:37,873][88326] Updated weights for policy 0, policy_version 68462 (0.0010) -[2023-10-09 02:51:38,239][88326] Updated weights for policy 0, policy_version 68472 (0.0010) -[2023-10-09 02:51:38,974][87372] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 140279808. Throughput: 0: 1704.8, 1: 1721.2. Samples: 35068938. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:51:38,975][87372] Avg episode reward: [(0, '6.670'), (1, '6.440')] -[2023-10-09 02:51:41,513][88327] Updated weights for policy 1, policy_version 68520 (0.0009) -[2023-10-09 02:51:41,879][88327] Updated weights for policy 1, policy_version 68530 (0.0008) -[2023-10-09 02:51:42,246][88327] Updated weights for policy 1, policy_version 68540 (0.0012) -[2023-10-09 02:51:42,327][88326] Updated weights for policy 0, policy_version 68482 (0.0010) -[2023-10-09 02:51:42,691][88326] Updated weights for policy 0, policy_version 68492 (0.0007) -[2023-10-09 02:51:43,059][88326] Updated weights for policy 0, policy_version 68502 (0.0009) -[2023-10-09 02:51:43,427][88326] Updated weights for policy 0, policy_version 68512 (0.0009) -[2023-10-09 02:51:43,974][87372] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 140345344. Throughput: 0: 1700.6, 1: 1705.9. Samples: 35089064. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:51:43,975][87372] Avg episode reward: [(0, '6.880'), (1, '6.490')] -[2023-10-09 02:51:46,275][88327] Updated weights for policy 1, policy_version 68550 (0.0008) -[2023-10-09 02:51:46,672][88327] Updated weights for policy 1, policy_version 68560 (0.0009) -[2023-10-09 02:51:47,038][88327] Updated weights for policy 1, policy_version 68570 (0.0007) -[2023-10-09 02:51:47,567][88326] Updated weights for policy 0, policy_version 68522 (0.0009) -[2023-10-09 02:51:47,922][88326] Updated weights for policy 0, policy_version 68532 (0.0009) -[2023-10-09 02:51:48,292][88326] Updated weights for policy 0, policy_version 68542 (0.0007) -[2023-10-09 02:51:48,974][87372] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 140410880. Throughput: 0: 1669.2, 1: 1701.2. Samples: 35108598. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:51:48,976][87372] Avg episode reward: [(0, '6.660'), (1, '6.620')] -[2023-10-09 02:51:50,978][88327] Updated weights for policy 1, policy_version 68580 (0.0009) -[2023-10-09 02:51:51,340][88327] Updated weights for policy 1, policy_version 68590 (0.0009) -[2023-10-09 02:51:51,703][88327] Updated weights for policy 1, policy_version 68600 (0.0010) -[2023-10-09 02:51:52,557][88326] Updated weights for policy 0, policy_version 68552 (0.0009) -[2023-10-09 02:51:52,931][88326] Updated weights for policy 0, policy_version 68562 (0.0009) -[2023-10-09 02:51:53,305][88326] Updated weights for policy 0, policy_version 68572 (0.0011) -[2023-10-09 02:51:53,974][87372] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 140476416. Throughput: 0: 1698.0, 1: 1722.8. Samples: 35119834. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:51:53,975][87372] Avg episode reward: [(0, '7.180'), (1, '6.550')] -[2023-10-09 02:51:55,594][88327] Updated weights for policy 1, policy_version 68610 (0.0010) -[2023-10-09 02:51:55,969][88327] Updated weights for policy 1, policy_version 68620 (0.0009) -[2023-10-09 02:51:56,333][88327] Updated weights for policy 1, policy_version 68630 (0.0008) -[2023-10-09 02:51:56,703][88327] Updated weights for policy 1, policy_version 68640 (0.0008) -[2023-10-09 02:51:57,420][88326] Updated weights for policy 0, policy_version 68582 (0.0010) -[2023-10-09 02:51:57,786][88326] Updated weights for policy 0, policy_version 68592 (0.0010) -[2023-10-09 02:51:58,151][88326] Updated weights for policy 0, policy_version 68602 (0.0012) -[2023-10-09 02:51:58,974][87372] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 140541952. Throughput: 0: 1692.8, 1: 1699.4. Samples: 35139672. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:51:58,975][87372] Avg episode reward: [(0, '7.010'), (1, '6.520')] -[2023-10-09 02:52:00,900][88327] Updated weights for policy 1, policy_version 68650 (0.0009) -[2023-10-09 02:52:01,255][88327] Updated weights for policy 1, policy_version 68660 (0.0010) -[2023-10-09 02:52:01,623][88327] Updated weights for policy 1, policy_version 68670 (0.0007) -[2023-10-09 02:52:02,263][88326] Updated weights for policy 0, policy_version 68612 (0.0009) -[2023-10-09 02:52:02,616][88326] Updated weights for policy 0, policy_version 68622 (0.0010) -[2023-10-09 02:52:02,995][88326] Updated weights for policy 0, policy_version 68632 (0.0011) -[2023-10-09 02:52:03,974][87372] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 140607488. Throughput: 0: 1665.0, 1: 1714.1. Samples: 35159622. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:52:03,975][87372] Avg episode reward: [(0, '6.170'), (1, '6.990')] -[2023-10-09 02:52:05,417][88327] Updated weights for policy 1, policy_version 68680 (0.0008) -[2023-10-09 02:52:05,789][88327] Updated weights for policy 1, policy_version 68690 (0.0008) -[2023-10-09 02:52:06,152][88327] Updated weights for policy 1, policy_version 68700 (0.0008) -[2023-10-09 02:52:06,959][88326] Updated weights for policy 0, policy_version 68642 (0.0009) -[2023-10-09 02:52:07,324][88326] Updated weights for policy 0, policy_version 68652 (0.0009) -[2023-10-09 02:52:07,694][88326] Updated weights for policy 0, policy_version 68662 (0.0010) -[2023-10-09 02:52:08,064][88326] Updated weights for policy 0, policy_version 68672 (0.0008) -[2023-10-09 02:52:08,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 140673024. Throughput: 0: 1691.7, 1: 1696.9. Samples: 35170068. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-09 02:52:08,974][87372] Avg episode reward: [(0, '6.750'), (1, '6.930')] -[2023-10-09 02:52:10,335][88327] Updated weights for policy 1, policy_version 68710 (0.0008) -[2023-10-09 02:52:10,706][88327] Updated weights for policy 1, policy_version 68720 (0.0009) -[2023-10-09 02:52:11,065][88327] Updated weights for policy 1, policy_version 68730 (0.0007) -[2023-10-09 02:52:11,987][88326] Updated weights for policy 0, policy_version 68682 (0.0007) -[2023-10-09 02:52:12,352][88326] Updated weights for policy 0, policy_version 68692 (0.0010) -[2023-10-09 02:52:12,724][88326] Updated weights for policy 0, policy_version 68702 (0.0009) -[2023-10-09 02:52:13,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 140738560. Throughput: 0: 1678.8, 1: 1699.6. Samples: 35190294. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-09 02:52:13,974][87372] Avg episode reward: [(0, '6.190'), (1, '6.390')] -[2023-10-09 02:52:15,118][88327] Updated weights for policy 1, policy_version 68740 (0.0009) -[2023-10-09 02:52:15,480][88327] Updated weights for policy 1, policy_version 68750 (0.0009) -[2023-10-09 02:52:15,841][88327] Updated weights for policy 1, policy_version 68760 (0.0007) -[2023-10-09 02:52:16,433][88326] Updated weights for policy 0, policy_version 68712 (0.0009) -[2023-10-09 02:52:16,807][88326] Updated weights for policy 0, policy_version 68722 (0.0007) -[2023-10-09 02:52:17,166][88326] Updated weights for policy 0, policy_version 68732 (0.0008) -[2023-10-09 02:52:18,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 140804096. Throughput: 0: 1685.0, 1: 1713.0. Samples: 35210758. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-09 02:52:18,975][87372] Avg episode reward: [(0, '6.330'), (1, '7.090')] -[2023-10-09 02:52:19,900][88327] Updated weights for policy 1, policy_version 68770 (0.0008) -[2023-10-09 02:52:20,266][88327] Updated weights for policy 1, policy_version 68780 (0.0008) -[2023-10-09 02:52:20,630][88327] Updated weights for policy 1, policy_version 68790 (0.0008) -[2023-10-09 02:52:20,986][88327] Updated weights for policy 1, policy_version 68800 (0.0007) -[2023-10-09 02:52:21,216][88326] Updated weights for policy 0, policy_version 68742 (0.0008) -[2023-10-09 02:52:21,578][88326] Updated weights for policy 0, policy_version 68752 (0.0008) -[2023-10-09 02:52:21,943][88326] Updated weights for policy 0, policy_version 68762 (0.0009) -[2023-10-09 02:52:23,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 140869632. Throughput: 0: 1695.1, 1: 1683.5. Samples: 35220974. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-09 02:52:23,975][87372] Avg episode reward: [(0, '6.470'), (1, '7.020')] -[2023-10-09 02:52:24,837][88327] Updated weights for policy 1, policy_version 68810 (0.0009) -[2023-10-09 02:52:25,191][88327] Updated weights for policy 1, policy_version 68820 (0.0009) -[2023-10-09 02:52:25,552][88327] Updated weights for policy 1, policy_version 68830 (0.0009) -[2023-10-09 02:52:26,125][88326] Updated weights for policy 0, policy_version 68772 (0.0010) -[2023-10-09 02:52:26,478][88326] Updated weights for policy 0, policy_version 68782 (0.0007) -[2023-10-09 02:52:26,849][88326] Updated weights for policy 0, policy_version 68792 (0.0007) -[2023-10-09 02:52:28,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 140935168. Throughput: 0: 1671.9, 1: 1704.6. Samples: 35241006. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-09 02:52:28,975][87372] Avg episode reward: [(0, '6.380'), (1, '7.010')] -[2023-10-09 02:52:29,538][88327] Updated weights for policy 1, policy_version 68840 (0.0008) -[2023-10-09 02:52:29,911][88327] Updated weights for policy 1, policy_version 68850 (0.0007) -[2023-10-09 02:52:30,279][88327] Updated weights for policy 1, policy_version 68860 (0.0008) -[2023-10-09 02:52:31,046][88326] Updated weights for policy 0, policy_version 68802 (0.0008) -[2023-10-09 02:52:31,416][88326] Updated weights for policy 0, policy_version 68812 (0.0011) -[2023-10-09 02:52:31,790][88326] Updated weights for policy 0, policy_version 68822 (0.0011) -[2023-10-09 02:52:32,157][88326] Updated weights for policy 0, policy_version 68832 (0.0009) -[2023-10-09 02:52:33,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 141000704. Throughput: 0: 1691.7, 1: 1711.2. Samples: 35261726. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-09 02:52:33,975][87372] Avg episode reward: [(0, '6.690'), (1, '7.370')] -[2023-10-09 02:52:33,985][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000068832_70483968.pth... -[2023-10-09 02:52:34,021][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000067264_68878336.pth -[2023-10-09 02:52:34,325][88327] Updated weights for policy 1, policy_version 68870 (0.0010) -[2023-10-09 02:52:34,677][88327] Updated weights for policy 1, policy_version 68880 (0.0010) -[2023-10-09 02:52:35,044][88327] Updated weights for policy 1, policy_version 68890 (0.0011) -[2023-10-09 02:52:35,254][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000068896_70549504.pth... -[2023-10-09 02:52:35,283][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000067296_68911104.pth -[2023-10-09 02:52:36,283][88326] Updated weights for policy 0, policy_version 68842 (0.0008) -[2023-10-09 02:52:36,647][88326] Updated weights for policy 0, policy_version 68852 (0.0007) -[2023-10-09 02:52:37,018][88326] Updated weights for policy 0, policy_version 68862 (0.0008) -[2023-10-09 02:52:38,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 141066240. Throughput: 0: 1690.4, 1: 1686.4. Samples: 35271786. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-09 02:52:38,975][87372] Avg episode reward: [(0, '6.440'), (1, '7.280')] -[2023-10-09 02:52:39,078][88327] Updated weights for policy 1, policy_version 68900 (0.0010) -[2023-10-09 02:52:39,448][88327] Updated weights for policy 1, policy_version 68910 (0.0008) -[2023-10-09 02:52:39,812][88327] Updated weights for policy 1, policy_version 68920 (0.0010) -[2023-10-09 02:52:40,935][88326] Updated weights for policy 0, policy_version 68872 (0.0008) -[2023-10-09 02:52:41,291][88326] Updated weights for policy 0, policy_version 68882 (0.0007) -[2023-10-09 02:52:41,667][88326] Updated weights for policy 0, policy_version 68892 (0.0009) -[2023-10-09 02:52:43,797][88327] Updated weights for policy 1, policy_version 68930 (0.0009) -[2023-10-09 02:52:43,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 141131776. Throughput: 0: 1679.1, 1: 1705.5. Samples: 35291978. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-09 02:52:43,974][87372] Avg episode reward: [(0, '6.880'), (1, '6.830')] -[2023-10-09 02:52:44,161][88327] Updated weights for policy 1, policy_version 68940 (0.0009) -[2023-10-09 02:52:44,533][88327] Updated weights for policy 1, policy_version 68950 (0.0007) -[2023-10-09 02:52:44,894][88327] Updated weights for policy 1, policy_version 68960 (0.0009) -[2023-10-09 02:52:45,724][88326] Updated weights for policy 0, policy_version 68902 (0.0008) -[2023-10-09 02:52:46,094][88326] Updated weights for policy 0, policy_version 68912 (0.0007) -[2023-10-09 02:52:46,463][88326] Updated weights for policy 0, policy_version 68922 (0.0009) -[2023-10-09 02:52:48,866][88327] Updated weights for policy 1, policy_version 68970 (0.0011) -[2023-10-09 02:52:48,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 141197312. Throughput: 0: 1709.0, 1: 1705.9. Samples: 35313292. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-09 02:52:48,975][87372] Avg episode reward: [(0, '7.350'), (1, '7.690')] -[2023-10-09 02:52:49,241][88327] Updated weights for policy 1, policy_version 68980 (0.0011) -[2023-10-09 02:52:49,595][88327] Updated weights for policy 1, policy_version 68990 (0.0010) -[2023-10-09 02:52:50,248][88326] Updated weights for policy 0, policy_version 68932 (0.0008) -[2023-10-09 02:52:50,617][88326] Updated weights for policy 0, policy_version 68942 (0.0007) -[2023-10-09 02:52:50,992][88326] Updated weights for policy 0, policy_version 68952 (0.0011) -[2023-10-09 02:52:53,686][88327] Updated weights for policy 1, policy_version 69000 (0.0008) -[2023-10-09 02:52:53,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 141262848. Throughput: 0: 1688.7, 1: 1701.8. Samples: 35322640. Policy #0 lag: (min: 31.0, avg: 31.6, max: 49.0) -[2023-10-09 02:52:53,975][87372] Avg episode reward: [(0, '7.500'), (1, '6.860')] -[2023-10-09 02:52:54,047][88327] Updated weights for policy 1, policy_version 69010 (0.0008) -[2023-10-09 02:52:54,409][88327] Updated weights for policy 1, policy_version 69020 (0.0008) -[2023-10-09 02:52:55,112][88326] Updated weights for policy 0, policy_version 68962 (0.0007) -[2023-10-09 02:52:55,481][88326] Updated weights for policy 0, policy_version 68972 (0.0008) -[2023-10-09 02:52:55,853][88326] Updated weights for policy 0, policy_version 68982 (0.0008) -[2023-10-09 02:52:56,215][88326] Updated weights for policy 0, policy_version 68992 (0.0009) -[2023-10-09 02:52:58,231][88327] Updated weights for policy 1, policy_version 69030 (0.0008) -[2023-10-09 02:52:58,592][88327] Updated weights for policy 1, policy_version 69040 (0.0010) -[2023-10-09 02:52:58,957][88327] Updated weights for policy 1, policy_version 69050 (0.0011) -[2023-10-09 02:52:58,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 141328384. Throughput: 0: 1692.9, 1: 1716.1. Samples: 35343698. Policy #0 lag: (min: 31.0, avg: 31.6, max: 49.0) -[2023-10-09 02:52:58,975][87372] Avg episode reward: [(0, '7.570'), (1, '7.140')] -[2023-10-09 02:53:00,128][88326] Updated weights for policy 0, policy_version 69002 (0.0009) -[2023-10-09 02:53:00,483][88326] Updated weights for policy 0, policy_version 69012 (0.0008) -[2023-10-09 02:53:00,849][88326] Updated weights for policy 0, policy_version 69022 (0.0008) -[2023-10-09 02:53:02,999][88327] Updated weights for policy 1, policy_version 69060 (0.0008) -[2023-10-09 02:53:03,365][88327] Updated weights for policy 1, policy_version 69070 (0.0007) -[2023-10-09 02:53:03,728][88327] Updated weights for policy 1, policy_version 69080 (0.0008) -[2023-10-09 02:53:03,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 141393920. Throughput: 0: 1707.0, 1: 1711.7. Samples: 35364602. Policy #0 lag: (min: 31.0, avg: 31.6, max: 49.0) -[2023-10-09 02:53:03,974][87372] Avg episode reward: [(0, '7.720'), (1, '6.690')] -[2023-10-09 02:53:04,863][88326] Updated weights for policy 0, policy_version 69032 (0.0008) -[2023-10-09 02:53:05,228][88326] Updated weights for policy 0, policy_version 69042 (0.0007) -[2023-10-09 02:53:05,595][88326] Updated weights for policy 0, policy_version 69052 (0.0009) -[2023-10-09 02:53:07,721][88327] Updated weights for policy 1, policy_version 69090 (0.0007) -[2023-10-09 02:53:08,086][88327] Updated weights for policy 1, policy_version 69100 (0.0009) -[2023-10-09 02:53:08,465][88327] Updated weights for policy 1, policy_version 69110 (0.0009) -[2023-10-09 02:53:08,821][88327] Updated weights for policy 1, policy_version 69120 (0.0008) -[2023-10-09 02:53:08,974][87372] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 141492224. Throughput: 0: 1685.0, 1: 1718.4. Samples: 35374124. Policy #0 lag: (min: 31.0, avg: 31.6, max: 49.0) -[2023-10-09 02:53:08,975][87372] Avg episode reward: [(0, '6.840'), (1, '6.580')] -[2023-10-09 02:53:09,634][88326] Updated weights for policy 0, policy_version 69062 (0.0009) -[2023-10-09 02:53:10,016][88326] Updated weights for policy 0, policy_version 69072 (0.0010) -[2023-10-09 02:53:10,377][88326] Updated weights for policy 0, policy_version 69082 (0.0010) -[2023-10-09 02:53:12,673][88327] Updated weights for policy 1, policy_version 69130 (0.0009) -[2023-10-09 02:53:13,031][88327] Updated weights for policy 1, policy_version 69140 (0.0008) -[2023-10-09 02:53:13,405][88327] Updated weights for policy 1, policy_version 69150 (0.0008) -[2023-10-09 02:53:13,974][87372] Fps is (10 sec: 16383.7, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 141557760. Throughput: 0: 1706.2, 1: 1720.0. Samples: 35395184. Policy #0 lag: (min: 31.0, avg: 31.6, max: 49.0) -[2023-10-09 02:53:13,975][87372] Avg episode reward: [(0, '6.720'), (1, '7.160')] -[2023-10-09 02:53:14,399][88326] Updated weights for policy 0, policy_version 69092 (0.0009) -[2023-10-09 02:53:14,766][88326] Updated weights for policy 0, policy_version 69102 (0.0008) -[2023-10-09 02:53:15,143][88326] Updated weights for policy 0, policy_version 69112 (0.0007) -[2023-10-09 02:53:17,419][88327] Updated weights for policy 1, policy_version 69160 (0.0009) -[2023-10-09 02:53:17,788][88327] Updated weights for policy 1, policy_version 69170 (0.0009) -[2023-10-09 02:53:18,145][88327] Updated weights for policy 1, policy_version 69180 (0.0010) -[2023-10-09 02:53:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 141623296. Throughput: 0: 1710.4, 1: 1697.0. Samples: 35415058. Policy #0 lag: (min: 31.0, avg: 31.6, max: 49.0) -[2023-10-09 02:53:18,975][87372] Avg episode reward: [(0, '6.830'), (1, '7.120')] -[2023-10-09 02:53:19,250][88326] Updated weights for policy 0, policy_version 69122 (0.0009) -[2023-10-09 02:53:19,620][88326] Updated weights for policy 0, policy_version 69132 (0.0011) -[2023-10-09 02:53:19,987][88326] Updated weights for policy 0, policy_version 69142 (0.0010) -[2023-10-09 02:53:20,353][88326] Updated weights for policy 0, policy_version 69152 (0.0010) -[2023-10-09 02:53:22,340][88327] Updated weights for policy 1, policy_version 69190 (0.0008) -[2023-10-09 02:53:22,730][88327] Updated weights for policy 1, policy_version 69200 (0.0008) -[2023-10-09 02:53:23,090][88327] Updated weights for policy 1, policy_version 69210 (0.0011) -[2023-10-09 02:53:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 141688832. Throughput: 0: 1688.0, 1: 1724.8. Samples: 35425362. Policy #0 lag: (min: 31.0, avg: 31.6, max: 49.0) -[2023-10-09 02:53:23,975][87372] Avg episode reward: [(0, '6.470'), (1, '7.330')] -[2023-10-09 02:53:24,114][88326] Updated weights for policy 0, policy_version 69162 (0.0008) -[2023-10-09 02:53:24,485][88326] Updated weights for policy 0, policy_version 69172 (0.0007) -[2023-10-09 02:53:24,862][88326] Updated weights for policy 0, policy_version 69182 (0.0007) -[2023-10-09 02:53:27,031][88327] Updated weights for policy 1, policy_version 69220 (0.0007) -[2023-10-09 02:53:27,395][88327] Updated weights for policy 1, policy_version 69230 (0.0008) -[2023-10-09 02:53:27,761][88327] Updated weights for policy 1, policy_version 69240 (0.0010) -[2023-10-09 02:53:28,969][88326] Updated weights for policy 0, policy_version 69192 (0.0009) -[2023-10-09 02:53:28,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 141754368. Throughput: 0: 1713.1, 1: 1714.6. Samples: 35446228. Policy #0 lag: (min: 31.0, avg: 31.6, max: 49.0) -[2023-10-09 02:53:28,975][87372] Avg episode reward: [(0, '6.640'), (1, '7.070')] -[2023-10-09 02:53:29,347][88326] Updated weights for policy 0, policy_version 69202 (0.0009) -[2023-10-09 02:53:29,714][88326] Updated weights for policy 0, policy_version 69212 (0.0007) -[2023-10-09 02:53:31,887][88327] Updated weights for policy 1, policy_version 69250 (0.0011) -[2023-10-09 02:53:32,251][88327] Updated weights for policy 1, policy_version 69260 (0.0007) -[2023-10-09 02:53:32,604][88327] Updated weights for policy 1, policy_version 69270 (0.0007) -[2023-10-09 02:53:32,973][88327] Updated weights for policy 1, policy_version 69280 (0.0009) -[2023-10-09 02:53:33,793][88326] Updated weights for policy 0, policy_version 69222 (0.0009) -[2023-10-09 02:53:33,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 141819904. Throughput: 0: 1707.2, 1: 1686.9. Samples: 35466024. Policy #0 lag: (min: 31.0, avg: 31.6, max: 49.0) -[2023-10-09 02:53:33,974][87372] Avg episode reward: [(0, '7.100'), (1, '7.340')] -[2023-10-09 02:53:34,167][88326] Updated weights for policy 0, policy_version 69232 (0.0010) -[2023-10-09 02:53:34,546][88326] Updated weights for policy 0, policy_version 69242 (0.0008) -[2023-10-09 02:53:36,990][88327] Updated weights for policy 1, policy_version 69290 (0.0007) -[2023-10-09 02:53:37,353][88327] Updated weights for policy 1, policy_version 69300 (0.0007) -[2023-10-09 02:53:37,711][88327] Updated weights for policy 1, policy_version 69310 (0.0008) -[2023-10-09 02:53:38,533][88326] Updated weights for policy 0, policy_version 69252 (0.0007) -[2023-10-09 02:53:38,899][88326] Updated weights for policy 0, policy_version 69262 (0.0008) -[2023-10-09 02:53:38,974][87372] Fps is (10 sec: 13107.6, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 141885440. Throughput: 0: 1696.5, 1: 1715.5. Samples: 35476176. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:53:38,974][87372] Avg episode reward: [(0, '6.440'), (1, '7.270')] -[2023-10-09 02:53:39,266][88326] Updated weights for policy 0, policy_version 69272 (0.0009) -[2023-10-09 02:53:41,717][88327] Updated weights for policy 1, policy_version 69320 (0.0008) -[2023-10-09 02:53:42,080][88327] Updated weights for policy 1, policy_version 69330 (0.0007) -[2023-10-09 02:53:42,443][88327] Updated weights for policy 1, policy_version 69340 (0.0009) -[2023-10-09 02:53:43,310][88326] Updated weights for policy 0, policy_version 69282 (0.0008) -[2023-10-09 02:53:43,684][88326] Updated weights for policy 0, policy_version 69292 (0.0008) -[2023-10-09 02:53:43,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 141950976. Throughput: 0: 1707.1, 1: 1690.8. Samples: 35496604. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:53:43,974][87372] Avg episode reward: [(0, '7.010'), (1, '7.080')] -[2023-10-09 02:53:44,050][88326] Updated weights for policy 0, policy_version 69302 (0.0010) -[2023-10-09 02:53:44,410][88326] Updated weights for policy 0, policy_version 69312 (0.0008) -[2023-10-09 02:53:46,568][88327] Updated weights for policy 1, policy_version 69350 (0.0009) -[2023-10-09 02:53:46,934][88327] Updated weights for policy 1, policy_version 69360 (0.0009) -[2023-10-09 02:53:47,297][88327] Updated weights for policy 1, policy_version 69370 (0.0009) -[2023-10-09 02:53:48,407][88326] Updated weights for policy 0, policy_version 69322 (0.0009) -[2023-10-09 02:53:48,771][88326] Updated weights for policy 0, policy_version 69332 (0.0009) -[2023-10-09 02:53:48,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 142016512. Throughput: 0: 1701.4, 1: 1682.7. Samples: 35516884. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:53:48,974][87372] Avg episode reward: [(0, '6.660'), (1, '7.160')] -[2023-10-09 02:53:49,142][88326] Updated weights for policy 0, policy_version 69342 (0.0007) -[2023-10-09 02:53:51,421][88327] Updated weights for policy 1, policy_version 69380 (0.0009) -[2023-10-09 02:53:51,786][88327] Updated weights for policy 1, policy_version 69390 (0.0009) -[2023-10-09 02:53:52,159][88327] Updated weights for policy 1, policy_version 69400 (0.0009) -[2023-10-09 02:53:53,117][88326] Updated weights for policy 0, policy_version 69352 (0.0009) -[2023-10-09 02:53:53,489][88326] Updated weights for policy 0, policy_version 69362 (0.0008) -[2023-10-09 02:53:53,857][88326] Updated weights for policy 0, policy_version 69372 (0.0007) -[2023-10-09 02:53:53,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 142082048. Throughput: 0: 1702.2, 1: 1706.9. Samples: 35527534. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:53:53,975][87372] Avg episode reward: [(0, '6.470'), (1, '7.440')] -[2023-10-09 02:53:56,169][88327] Updated weights for policy 1, policy_version 69410 (0.0010) -[2023-10-09 02:53:56,526][88327] Updated weights for policy 1, policy_version 69420 (0.0007) -[2023-10-09 02:53:56,898][88327] Updated weights for policy 1, policy_version 69430 (0.0009) -[2023-10-09 02:53:57,262][88327] Updated weights for policy 1, policy_version 69440 (0.0008) -[2023-10-09 02:53:57,966][88326] Updated weights for policy 0, policy_version 69382 (0.0008) -[2023-10-09 02:53:58,340][88326] Updated weights for policy 0, policy_version 69392 (0.0007) -[2023-10-09 02:53:58,717][88326] Updated weights for policy 0, policy_version 69402 (0.0009) -[2023-10-09 02:53:58,974][87372] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 142180352. Throughput: 0: 1710.2, 1: 1680.2. Samples: 35547752. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:53:58,975][87372] Avg episode reward: [(0, '6.500'), (1, '7.440')] -[2023-10-09 02:54:01,371][88327] Updated weights for policy 1, policy_version 69450 (0.0008) -[2023-10-09 02:54:01,731][88327] Updated weights for policy 1, policy_version 69460 (0.0007) -[2023-10-09 02:54:02,093][88327] Updated weights for policy 1, policy_version 69470 (0.0007) -[2023-10-09 02:54:02,742][88326] Updated weights for policy 0, policy_version 69412 (0.0009) -[2023-10-09 02:54:03,113][88326] Updated weights for policy 0, policy_version 69422 (0.0009) -[2023-10-09 02:54:03,484][88326] Updated weights for policy 0, policy_version 69432 (0.0009) -[2023-10-09 02:54:03,974][87372] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 142245888. Throughput: 0: 1697.6, 1: 1700.8. Samples: 35567986. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:54:03,975][87372] Avg episode reward: [(0, '6.440'), (1, '7.680')] -[2023-10-09 02:54:06,138][88327] Updated weights for policy 1, policy_version 69480 (0.0008) -[2023-10-09 02:54:06,510][88327] Updated weights for policy 1, policy_version 69490 (0.0009) -[2023-10-09 02:54:06,887][88327] Updated weights for policy 1, policy_version 69500 (0.0008) -[2023-10-09 02:54:07,367][88326] Updated weights for policy 0, policy_version 69442 (0.0008) -[2023-10-09 02:54:07,744][88326] Updated weights for policy 0, policy_version 69452 (0.0007) -[2023-10-09 02:54:08,109][88326] Updated weights for policy 0, policy_version 69462 (0.0008) -[2023-10-09 02:54:08,484][88326] Updated weights for policy 0, policy_version 69472 (0.0009) -[2023-10-09 02:54:08,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 142311424. Throughput: 0: 1711.3, 1: 1695.2. Samples: 35578656. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:54:08,975][87372] Avg episode reward: [(0, '6.400'), (1, '7.240')] -[2023-10-09 02:54:10,913][88327] Updated weights for policy 1, policy_version 69510 (0.0008) -[2023-10-09 02:54:11,270][88327] Updated weights for policy 1, policy_version 69520 (0.0010) -[2023-10-09 02:54:11,639][88327] Updated weights for policy 1, policy_version 69530 (0.0009) -[2023-10-09 02:54:12,575][88326] Updated weights for policy 0, policy_version 69482 (0.0009) -[2023-10-09 02:54:12,952][88326] Updated weights for policy 0, policy_version 69492 (0.0009) -[2023-10-09 02:54:13,310][88326] Updated weights for policy 0, policy_version 69502 (0.0008) -[2023-10-09 02:54:13,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 142376960. Throughput: 0: 1703.0, 1: 1682.7. Samples: 35598586. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:54:13,975][87372] Avg episode reward: [(0, '6.870'), (1, '7.390')] -[2023-10-09 02:54:15,615][88327] Updated weights for policy 1, policy_version 69540 (0.0009) -[2023-10-09 02:54:16,024][88327] Updated weights for policy 1, policy_version 69550 (0.0011) -[2023-10-09 02:54:16,393][88327] Updated weights for policy 1, policy_version 69560 (0.0011) -[2023-10-09 02:54:17,379][88326] Updated weights for policy 0, policy_version 69512 (0.0008) -[2023-10-09 02:54:17,734][88326] Updated weights for policy 0, policy_version 69522 (0.0008) -[2023-10-09 02:54:18,111][88326] Updated weights for policy 0, policy_version 69532 (0.0007) -[2023-10-09 02:54:18,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 142442496. Throughput: 0: 1676.8, 1: 1707.7. Samples: 35618326. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:54:18,975][87372] Avg episode reward: [(0, '7.160'), (1, '7.220')] -[2023-10-09 02:54:20,344][88327] Updated weights for policy 1, policy_version 69570 (0.0010) -[2023-10-09 02:54:20,700][88327] Updated weights for policy 1, policy_version 69580 (0.0010) -[2023-10-09 02:54:21,068][88327] Updated weights for policy 1, policy_version 69590 (0.0010) -[2023-10-09 02:54:21,439][88327] Updated weights for policy 1, policy_version 69600 (0.0007) -[2023-10-09 02:54:22,160][88326] Updated weights for policy 0, policy_version 69542 (0.0010) -[2023-10-09 02:54:22,529][88326] Updated weights for policy 0, policy_version 69552 (0.0009) -[2023-10-09 02:54:22,903][88326] Updated weights for policy 0, policy_version 69562 (0.0010) -[2023-10-09 02:54:23,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 142508032. Throughput: 0: 1709.2, 1: 1686.0. Samples: 35628962. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:54:23,975][87372] Avg episode reward: [(0, '6.970'), (1, '7.560')] -[2023-10-09 02:54:25,322][88327] Updated weights for policy 1, policy_version 69610 (0.0007) -[2023-10-09 02:54:25,684][88327] Updated weights for policy 1, policy_version 69620 (0.0010) -[2023-10-09 02:54:26,048][88327] Updated weights for policy 1, policy_version 69630 (0.0011) -[2023-10-09 02:54:26,808][88326] Updated weights for policy 0, policy_version 69572 (0.0010) -[2023-10-09 02:54:27,175][88326] Updated weights for policy 0, policy_version 69582 (0.0010) -[2023-10-09 02:54:27,542][88326] Updated weights for policy 0, policy_version 69592 (0.0010) -[2023-10-09 02:54:28,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 142573568. Throughput: 0: 1690.5, 1: 1693.4. Samples: 35648880. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:54:28,975][87372] Avg episode reward: [(0, '6.720'), (1, '7.110')] -[2023-10-09 02:54:30,010][88327] Updated weights for policy 1, policy_version 69640 (0.0011) -[2023-10-09 02:54:30,377][88327] Updated weights for policy 1, policy_version 69650 (0.0009) -[2023-10-09 02:54:30,740][88327] Updated weights for policy 1, policy_version 69660 (0.0007) -[2023-10-09 02:54:31,662][88326] Updated weights for policy 0, policy_version 69602 (0.0011) -[2023-10-09 02:54:32,029][88326] Updated weights for policy 0, policy_version 69612 (0.0010) -[2023-10-09 02:54:32,401][88326] Updated weights for policy 0, policy_version 69622 (0.0007) -[2023-10-09 02:54:32,764][88326] Updated weights for policy 0, policy_version 69632 (0.0010) -[2023-10-09 02:54:33,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 142639104. Throughput: 0: 1669.2, 1: 1710.4. Samples: 35668968. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:54:33,975][87372] Avg episode reward: [(0, '6.460'), (1, '7.980')] -[2023-10-09 02:54:33,982][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000069632_71303168.pth... -[2023-10-09 02:54:33,982][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000069664_71335936.pth... -[2023-10-09 02:54:34,018][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000068096_69730304.pth -[2023-10-09 02:54:34,023][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000068032_69664768.pth -[2023-10-09 02:54:34,771][88327] Updated weights for policy 1, policy_version 69670 (0.0008) -[2023-10-09 02:54:35,150][88327] Updated weights for policy 1, policy_version 69680 (0.0009) -[2023-10-09 02:54:35,516][88327] Updated weights for policy 1, policy_version 69690 (0.0010) -[2023-10-09 02:54:36,985][88326] Updated weights for policy 0, policy_version 69642 (0.0011) -[2023-10-09 02:54:37,340][88326] Updated weights for policy 0, policy_version 69652 (0.0008) -[2023-10-09 02:54:37,715][88326] Updated weights for policy 0, policy_version 69662 (0.0008) -[2023-10-09 02:54:38,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 142704640. Throughput: 0: 1693.7, 1: 1678.3. Samples: 35679274. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:54:38,975][87372] Avg episode reward: [(0, '6.060'), (1, '7.220')] -[2023-10-09 02:54:39,595][88327] Updated weights for policy 1, policy_version 69700 (0.0008) -[2023-10-09 02:54:39,976][88327] Updated weights for policy 1, policy_version 69710 (0.0008) -[2023-10-09 02:54:40,331][88327] Updated weights for policy 1, policy_version 69720 (0.0009) -[2023-10-09 02:54:41,608][88326] Updated weights for policy 0, policy_version 69672 (0.0007) -[2023-10-09 02:54:41,977][88326] Updated weights for policy 0, policy_version 69682 (0.0007) -[2023-10-09 02:54:42,348][88326] Updated weights for policy 0, policy_version 69692 (0.0007) -[2023-10-09 02:54:43,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 142770176. Throughput: 0: 1668.9, 1: 1701.6. Samples: 35699424. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:54:43,975][87372] Avg episode reward: [(0, '6.760'), (1, '6.710')] -[2023-10-09 02:54:44,474][88327] Updated weights for policy 1, policy_version 69730 (0.0010) -[2023-10-09 02:54:44,825][88327] Updated weights for policy 1, policy_version 69740 (0.0009) -[2023-10-09 02:54:45,190][88327] Updated weights for policy 1, policy_version 69750 (0.0008) -[2023-10-09 02:54:45,553][88327] Updated weights for policy 1, policy_version 69760 (0.0008) -[2023-10-09 02:54:46,517][88326] Updated weights for policy 0, policy_version 69702 (0.0009) -[2023-10-09 02:54:46,879][88326] Updated weights for policy 0, policy_version 69712 (0.0010) -[2023-10-09 02:54:47,253][88326] Updated weights for policy 0, policy_version 69722 (0.0007) -[2023-10-09 02:54:48,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 142835712. Throughput: 0: 1672.4, 1: 1702.3. Samples: 35719850. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:54:48,975][87372] Avg episode reward: [(0, '6.740'), (1, '7.520')] -[2023-10-09 02:54:49,519][88327] Updated weights for policy 1, policy_version 69770 (0.0007) -[2023-10-09 02:54:49,883][88327] Updated weights for policy 1, policy_version 69780 (0.0008) -[2023-10-09 02:54:50,245][88327] Updated weights for policy 1, policy_version 69790 (0.0008) -[2023-10-09 02:54:51,317][88326] Updated weights for policy 0, policy_version 69732 (0.0007) -[2023-10-09 02:54:51,676][88326] Updated weights for policy 0, policy_version 69742 (0.0008) -[2023-10-09 02:54:52,046][88326] Updated weights for policy 0, policy_version 69752 (0.0008) -[2023-10-09 02:54:53,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 142901248. Throughput: 0: 1686.8, 1: 1681.7. Samples: 35730240. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:54:53,975][87372] Avg episode reward: [(0, '6.710'), (1, '7.220')] -[2023-10-09 02:54:54,366][88327] Updated weights for policy 1, policy_version 69800 (0.0008) -[2023-10-09 02:54:54,729][88327] Updated weights for policy 1, policy_version 69810 (0.0009) -[2023-10-09 02:54:55,095][88327] Updated weights for policy 1, policy_version 69820 (0.0007) -[2023-10-09 02:54:56,207][88326] Updated weights for policy 0, policy_version 69762 (0.0008) -[2023-10-09 02:54:56,570][88326] Updated weights for policy 0, policy_version 69772 (0.0009) -[2023-10-09 02:54:56,945][88326] Updated weights for policy 0, policy_version 69782 (0.0007) -[2023-10-09 02:54:57,311][88326] Updated weights for policy 0, policy_version 69792 (0.0007) -[2023-10-09 02:54:58,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 142966784. Throughput: 0: 1663.4, 1: 1704.1. Samples: 35750122. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:54:58,974][87372] Avg episode reward: [(0, '6.840'), (1, '7.090')] -[2023-10-09 02:54:59,030][88327] Updated weights for policy 1, policy_version 69830 (0.0008) -[2023-10-09 02:54:59,395][88327] Updated weights for policy 1, policy_version 69840 (0.0007) -[2023-10-09 02:54:59,758][88327] Updated weights for policy 1, policy_version 69850 (0.0007) -[2023-10-09 02:55:01,336][88326] Updated weights for policy 0, policy_version 69802 (0.0007) -[2023-10-09 02:55:01,697][88326] Updated weights for policy 0, policy_version 69812 (0.0007) -[2023-10-09 02:55:02,074][88326] Updated weights for policy 0, policy_version 69822 (0.0009) -[2023-10-09 02:55:03,961][88327] Updated weights for policy 1, policy_version 69860 (0.0008) -[2023-10-09 02:55:03,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 143032320. Throughput: 0: 1684.4, 1: 1701.6. Samples: 35770698. Policy #0 lag: (min: 42.0, avg: 55.6, max: 56.0) -[2023-10-09 02:55:03,975][87372] Avg episode reward: [(0, '6.750'), (1, '8.050')] -[2023-10-09 02:55:04,355][88327] Updated weights for policy 1, policy_version 69870 (0.0010) -[2023-10-09 02:55:04,722][88327] Updated weights for policy 1, policy_version 69880 (0.0008) -[2023-10-09 02:55:06,106][88326] Updated weights for policy 0, policy_version 69832 (0.0009) -[2023-10-09 02:55:06,484][88326] Updated weights for policy 0, policy_version 69842 (0.0010) -[2023-10-09 02:55:06,862][88326] Updated weights for policy 0, policy_version 69852 (0.0010) -[2023-10-09 02:55:08,814][88327] Updated weights for policy 1, policy_version 69890 (0.0009) -[2023-10-09 02:55:08,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 143097856. Throughput: 0: 1676.1, 1: 1692.5. Samples: 35780548. Policy #0 lag: (min: 42.0, avg: 55.6, max: 56.0) -[2023-10-09 02:55:08,975][87372] Avg episode reward: [(0, '6.610'), (1, '7.770')] -[2023-10-09 02:55:09,178][88327] Updated weights for policy 1, policy_version 69900 (0.0009) -[2023-10-09 02:55:09,541][88327] Updated weights for policy 1, policy_version 69910 (0.0010) -[2023-10-09 02:55:09,912][88327] Updated weights for policy 1, policy_version 69920 (0.0007) -[2023-10-09 02:55:10,793][88326] Updated weights for policy 0, policy_version 69862 (0.0008) -[2023-10-09 02:55:11,163][88326] Updated weights for policy 0, policy_version 69872 (0.0007) -[2023-10-09 02:55:11,534][88326] Updated weights for policy 0, policy_version 69882 (0.0007) -[2023-10-09 02:55:13,921][88327] Updated weights for policy 1, policy_version 69930 (0.0009) -[2023-10-09 02:55:13,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 143163392. Throughput: 0: 1672.1, 1: 1696.9. Samples: 35800488. Policy #0 lag: (min: 42.0, avg: 55.6, max: 56.0) -[2023-10-09 02:55:13,975][87372] Avg episode reward: [(0, '7.150'), (1, '7.060')] -[2023-10-09 02:55:14,288][88327] Updated weights for policy 1, policy_version 69940 (0.0009) -[2023-10-09 02:55:14,650][88327] Updated weights for policy 1, policy_version 69950 (0.0009) -[2023-10-09 02:55:15,375][88326] Updated weights for policy 0, policy_version 69892 (0.0009) -[2023-10-09 02:55:15,757][88326] Updated weights for policy 0, policy_version 69902 (0.0007) -[2023-10-09 02:55:16,122][88326] Updated weights for policy 0, policy_version 69912 (0.0009) -[2023-10-09 02:55:18,461][88327] Updated weights for policy 1, policy_version 69960 (0.0008) -[2023-10-09 02:55:18,816][88327] Updated weights for policy 1, policy_version 69970 (0.0007) -[2023-10-09 02:55:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 143228928. Throughput: 0: 1699.2, 1: 1696.2. Samples: 35821760. Policy #0 lag: (min: 42.0, avg: 55.6, max: 56.0) -[2023-10-09 02:55:18,975][87372] Avg episode reward: [(0, '6.510'), (1, '7.200')] -[2023-10-09 02:55:19,184][88327] Updated weights for policy 1, policy_version 69980 (0.0008) -[2023-10-09 02:55:20,068][88326] Updated weights for policy 0, policy_version 69922 (0.0010) -[2023-10-09 02:55:20,442][88326] Updated weights for policy 0, policy_version 69932 (0.0011) -[2023-10-09 02:55:20,807][88326] Updated weights for policy 0, policy_version 69942 (0.0009) -[2023-10-09 02:55:21,180][88326] Updated weights for policy 0, policy_version 69952 (0.0008) -[2023-10-09 02:55:23,183][88327] Updated weights for policy 1, policy_version 69990 (0.0008) -[2023-10-09 02:55:23,552][88327] Updated weights for policy 1, policy_version 70000 (0.0009) -[2023-10-09 02:55:23,923][88327] Updated weights for policy 1, policy_version 70010 (0.0008) -[2023-10-09 02:55:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 143294464. Throughput: 0: 1674.3, 1: 1698.2. Samples: 35831038. Policy #0 lag: (min: 42.0, avg: 55.6, max: 56.0) -[2023-10-09 02:55:23,975][87372] Avg episode reward: [(0, '7.470'), (1, '6.830')] -[2023-10-09 02:55:25,136][88326] Updated weights for policy 0, policy_version 69962 (0.0008) -[2023-10-09 02:55:25,499][88326] Updated weights for policy 0, policy_version 69972 (0.0008) -[2023-10-09 02:55:25,870][88326] Updated weights for policy 0, policy_version 69982 (0.0008) -[2023-10-09 02:55:28,080][88327] Updated weights for policy 1, policy_version 70020 (0.0008) -[2023-10-09 02:55:28,450][88327] Updated weights for policy 1, policy_version 70030 (0.0009) -[2023-10-09 02:55:28,815][88327] Updated weights for policy 1, policy_version 70040 (0.0008) -[2023-10-09 02:55:28,974][87372] Fps is (10 sec: 13106.8, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 143360000. Throughput: 0: 1694.5, 1: 1696.0. Samples: 35851996. Policy #0 lag: (min: 42.0, avg: 55.6, max: 56.0) -[2023-10-09 02:55:28,975][87372] Avg episode reward: [(0, '7.920'), (1, '6.720')] -[2023-10-09 02:55:29,894][88326] Updated weights for policy 0, policy_version 69992 (0.0009) -[2023-10-09 02:55:30,263][88326] Updated weights for policy 0, policy_version 70002 (0.0009) -[2023-10-09 02:55:30,636][88326] Updated weights for policy 0, policy_version 70012 (0.0011) -[2023-10-09 02:55:32,703][88327] Updated weights for policy 1, policy_version 70050 (0.0008) -[2023-10-09 02:55:33,061][88327] Updated weights for policy 1, policy_version 70060 (0.0008) -[2023-10-09 02:55:33,431][88327] Updated weights for policy 1, policy_version 70070 (0.0008) -[2023-10-09 02:55:33,792][88327] Updated weights for policy 1, policy_version 70080 (0.0008) -[2023-10-09 02:55:33,974][87372] Fps is (10 sec: 16384.0, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 143458304. Throughput: 0: 1700.6, 1: 1687.5. Samples: 35872314. Policy #0 lag: (min: 42.0, avg: 55.6, max: 56.0) -[2023-10-09 02:55:33,975][87372] Avg episode reward: [(0, '7.950'), (1, '6.810')] -[2023-10-09 02:55:34,842][88326] Updated weights for policy 0, policy_version 70022 (0.0007) -[2023-10-09 02:55:35,212][88326] Updated weights for policy 0, policy_version 70032 (0.0008) -[2023-10-09 02:55:35,577][88326] Updated weights for policy 0, policy_version 70042 (0.0008) -[2023-10-09 02:55:37,853][88327] Updated weights for policy 1, policy_version 70090 (0.0007) -[2023-10-09 02:55:38,222][88327] Updated weights for policy 1, policy_version 70100 (0.0008) -[2023-10-09 02:55:38,588][88327] Updated weights for policy 1, policy_version 70110 (0.0008) -[2023-10-09 02:55:38,974][87372] Fps is (10 sec: 16384.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 143523840. Throughput: 0: 1671.0, 1: 1702.0. Samples: 35882026. Policy #0 lag: (min: 42.0, avg: 55.6, max: 56.0) -[2023-10-09 02:55:38,975][87372] Avg episode reward: [(0, '7.250'), (1, '6.780')] -[2023-10-09 02:55:39,523][88326] Updated weights for policy 0, policy_version 70052 (0.0009) -[2023-10-09 02:55:39,885][88326] Updated weights for policy 0, policy_version 70062 (0.0009) -[2023-10-09 02:55:40,264][88326] Updated weights for policy 0, policy_version 70072 (0.0009) -[2023-10-09 02:55:42,662][88327] Updated weights for policy 1, policy_version 70120 (0.0008) -[2023-10-09 02:55:43,025][88327] Updated weights for policy 1, policy_version 70130 (0.0007) -[2023-10-09 02:55:43,394][88327] Updated weights for policy 1, policy_version 70140 (0.0008) -[2023-10-09 02:55:43,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 143589376. Throughput: 0: 1698.3, 1: 1698.0. Samples: 35902954. Policy #0 lag: (min: 42.0, avg: 55.6, max: 56.0) -[2023-10-09 02:55:43,975][87372] Avg episode reward: [(0, '5.990'), (1, '6.940')] -[2023-10-09 02:55:44,197][88326] Updated weights for policy 0, policy_version 70082 (0.0007) -[2023-10-09 02:55:44,571][88326] Updated weights for policy 0, policy_version 70092 (0.0009) -[2023-10-09 02:55:44,935][88326] Updated weights for policy 0, policy_version 70102 (0.0010) -[2023-10-09 02:55:45,309][88326] Updated weights for policy 0, policy_version 70112 (0.0010) -[2023-10-09 02:55:47,403][88327] Updated weights for policy 1, policy_version 70150 (0.0007) -[2023-10-09 02:55:47,775][88327] Updated weights for policy 1, policy_version 70160 (0.0008) -[2023-10-09 02:55:48,137][88327] Updated weights for policy 1, policy_version 70170 (0.0008) -[2023-10-09 02:55:48,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 143654912. Throughput: 0: 1705.6, 1: 1677.6. Samples: 35922942. Policy #0 lag: (min: 42.0, avg: 55.6, max: 56.0) -[2023-10-09 02:55:48,975][87372] Avg episode reward: [(0, '6.000'), (1, '7.560')] -[2023-10-09 02:55:49,410][88326] Updated weights for policy 0, policy_version 70122 (0.0008) -[2023-10-09 02:55:49,782][88326] Updated weights for policy 0, policy_version 70132 (0.0009) -[2023-10-09 02:55:50,151][88326] Updated weights for policy 0, policy_version 70142 (0.0009) -[2023-10-09 02:55:52,294][88327] Updated weights for policy 1, policy_version 70180 (0.0010) -[2023-10-09 02:55:52,694][88327] Updated weights for policy 1, policy_version 70190 (0.0008) -[2023-10-09 02:55:53,059][88327] Updated weights for policy 1, policy_version 70200 (0.0007) -[2023-10-09 02:55:53,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 143720448. Throughput: 0: 1686.1, 1: 1701.2. Samples: 35932980. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:55:53,975][87372] Avg episode reward: [(0, '6.280'), (1, '6.950')] -[2023-10-09 02:55:54,305][88326] Updated weights for policy 0, policy_version 70152 (0.0008) -[2023-10-09 02:55:54,670][88326] Updated weights for policy 0, policy_version 70162 (0.0008) -[2023-10-09 02:55:55,036][88326] Updated weights for policy 0, policy_version 70172 (0.0011) -[2023-10-09 02:55:57,107][88327] Updated weights for policy 1, policy_version 70210 (0.0010) -[2023-10-09 02:55:57,474][88327] Updated weights for policy 1, policy_version 70220 (0.0011) -[2023-10-09 02:55:57,823][88327] Updated weights for policy 1, policy_version 70230 (0.0010) -[2023-10-09 02:55:58,183][88327] Updated weights for policy 1, policy_version 70240 (0.0008) -[2023-10-09 02:55:58,939][88326] Updated weights for policy 0, policy_version 70182 (0.0011) -[2023-10-09 02:55:58,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 143785984. Throughput: 0: 1707.2, 1: 1696.9. Samples: 35953670. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:55:58,974][87372] Avg episode reward: [(0, '6.700'), (1, '6.720')] -[2023-10-09 02:55:59,317][88326] Updated weights for policy 0, policy_version 70192 (0.0010) -[2023-10-09 02:55:59,682][88326] Updated weights for policy 0, policy_version 70202 (0.0007) -[2023-10-09 02:56:02,071][88327] Updated weights for policy 1, policy_version 70250 (0.0009) -[2023-10-09 02:56:02,434][88327] Updated weights for policy 1, policy_version 70260 (0.0009) -[2023-10-09 02:56:02,812][88327] Updated weights for policy 1, policy_version 70270 (0.0007) -[2023-10-09 02:56:03,879][88326] Updated weights for policy 0, policy_version 70212 (0.0008) -[2023-10-09 02:56:03,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 143851520. Throughput: 0: 1706.6, 1: 1670.9. Samples: 35973748. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:56:03,975][87372] Avg episode reward: [(0, '7.140'), (1, '7.180')] -[2023-10-09 02:56:04,270][88326] Updated weights for policy 0, policy_version 70222 (0.0008) -[2023-10-09 02:56:04,637][88326] Updated weights for policy 0, policy_version 70232 (0.0008) -[2023-10-09 02:56:06,784][88327] Updated weights for policy 1, policy_version 70280 (0.0008) -[2023-10-09 02:56:07,148][88327] Updated weights for policy 1, policy_version 70290 (0.0009) -[2023-10-09 02:56:07,507][88327] Updated weights for policy 1, policy_version 70300 (0.0008) -[2023-10-09 02:56:08,724][88326] Updated weights for policy 0, policy_version 70242 (0.0007) -[2023-10-09 02:56:08,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 143917056. Throughput: 0: 1701.7, 1: 1700.3. Samples: 35984126. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:56:08,975][87372] Avg episode reward: [(0, '6.960'), (1, '6.960')] -[2023-10-09 02:56:09,095][88326] Updated weights for policy 0, policy_version 70252 (0.0009) -[2023-10-09 02:56:09,463][88326] Updated weights for policy 0, policy_version 70262 (0.0007) -[2023-10-09 02:56:09,845][88326] Updated weights for policy 0, policy_version 70272 (0.0008) -[2023-10-09 02:56:11,525][88327] Updated weights for policy 1, policy_version 70310 (0.0009) -[2023-10-09 02:56:11,892][88327] Updated weights for policy 1, policy_version 70320 (0.0009) -[2023-10-09 02:56:12,256][88327] Updated weights for policy 1, policy_version 70330 (0.0009) -[2023-10-09 02:56:13,658][88326] Updated weights for policy 0, policy_version 70282 (0.0008) -[2023-10-09 02:56:13,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 143982592. Throughput: 0: 1705.2, 1: 1679.2. Samples: 36004294. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:56:13,975][87372] Avg episode reward: [(0, '7.000'), (1, '6.980')] -[2023-10-09 02:56:14,025][88326] Updated weights for policy 0, policy_version 70292 (0.0008) -[2023-10-09 02:56:14,391][88326] Updated weights for policy 0, policy_version 70302 (0.0008) -[2023-10-09 02:56:16,250][88327] Updated weights for policy 1, policy_version 70340 (0.0009) -[2023-10-09 02:56:16,614][88327] Updated weights for policy 1, policy_version 70350 (0.0008) -[2023-10-09 02:56:16,975][88327] Updated weights for policy 1, policy_version 70360 (0.0008) -[2023-10-09 02:56:18,352][88326] Updated weights for policy 0, policy_version 70312 (0.0007) -[2023-10-09 02:56:18,717][88326] Updated weights for policy 0, policy_version 70322 (0.0007) -[2023-10-09 02:56:18,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 144048128. Throughput: 0: 1705.3, 1: 1681.6. Samples: 36024724. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:56:18,975][87372] Avg episode reward: [(0, '7.130'), (1, '7.260')] -[2023-10-09 02:56:19,099][88326] Updated weights for policy 0, policy_version 70332 (0.0010) -[2023-10-09 02:56:21,134][88327] Updated weights for policy 1, policy_version 70370 (0.0007) -[2023-10-09 02:56:21,497][88327] Updated weights for policy 1, policy_version 70380 (0.0007) -[2023-10-09 02:56:21,870][88327] Updated weights for policy 1, policy_version 70390 (0.0009) -[2023-10-09 02:56:22,237][88327] Updated weights for policy 1, policy_version 70400 (0.0008) -[2023-10-09 02:56:23,025][88326] Updated weights for policy 0, policy_version 70342 (0.0008) -[2023-10-09 02:56:23,392][88326] Updated weights for policy 0, policy_version 70352 (0.0010) -[2023-10-09 02:56:23,751][88326] Updated weights for policy 0, policy_version 70362 (0.0008) -[2023-10-09 02:56:23,974][87372] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 144146432. Throughput: 0: 1710.2, 1: 1695.5. Samples: 36035282. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:56:23,975][87372] Avg episode reward: [(0, '6.890'), (1, '7.750')] -[2023-10-09 02:56:26,286][88327] Updated weights for policy 1, policy_version 70410 (0.0007) -[2023-10-09 02:56:26,648][88327] Updated weights for policy 1, policy_version 70420 (0.0007) -[2023-10-09 02:56:27,021][88327] Updated weights for policy 1, policy_version 70430 (0.0009) -[2023-10-09 02:56:27,656][88326] Updated weights for policy 0, policy_version 70372 (0.0008) -[2023-10-09 02:56:28,019][88326] Updated weights for policy 0, policy_version 70382 (0.0007) -[2023-10-09 02:56:28,393][88326] Updated weights for policy 0, policy_version 70392 (0.0010) -[2023-10-09 02:56:28,974][87372] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 144211968. Throughput: 0: 1714.0, 1: 1674.4. Samples: 36055434. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:56:28,975][87372] Avg episode reward: [(0, '6.960'), (1, '7.610')] -[2023-10-09 02:56:31,021][88327] Updated weights for policy 1, policy_version 70440 (0.0008) -[2023-10-09 02:56:31,397][88327] Updated weights for policy 1, policy_version 70450 (0.0011) -[2023-10-09 02:56:31,758][88327] Updated weights for policy 1, policy_version 70460 (0.0009) -[2023-10-09 02:56:32,317][88326] Updated weights for policy 0, policy_version 70402 (0.0007) -[2023-10-09 02:56:32,686][88326] Updated weights for policy 0, policy_version 70412 (0.0007) -[2023-10-09 02:56:33,059][88326] Updated weights for policy 0, policy_version 70422 (0.0010) -[2023-10-09 02:56:33,425][88326] Updated weights for policy 0, policy_version 70432 (0.0009) -[2023-10-09 02:56:33,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 144277504. Throughput: 0: 1691.5, 1: 1696.0. Samples: 36075378. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:56:33,975][87372] Avg episode reward: [(0, '7.090'), (1, '7.470')] -[2023-10-09 02:56:33,983][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000070432_72122368.pth... -[2023-10-09 02:56:33,984][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000070464_72155136.pth... -[2023-10-09 02:56:34,014][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000068896_70549504.pth -[2023-10-09 02:56:34,015][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000068832_70483968.pth -[2023-10-09 02:56:35,894][88327] Updated weights for policy 1, policy_version 70470 (0.0009) -[2023-10-09 02:56:36,254][88327] Updated weights for policy 1, policy_version 70480 (0.0010) -[2023-10-09 02:56:36,612][88327] Updated weights for policy 1, policy_version 70490 (0.0009) -[2023-10-09 02:56:37,410][88326] Updated weights for policy 0, policy_version 70442 (0.0008) -[2023-10-09 02:56:37,785][88326] Updated weights for policy 0, policy_version 70452 (0.0010) -[2023-10-09 02:56:38,153][88326] Updated weights for policy 0, policy_version 70462 (0.0009) -[2023-10-09 02:56:38,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 144343040. Throughput: 0: 1716.4, 1: 1689.7. Samples: 36086256. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-09 02:56:38,974][87372] Avg episode reward: [(0, '7.060'), (1, '7.760')] -[2023-10-09 02:56:40,662][88327] Updated weights for policy 1, policy_version 70500 (0.0008) -[2023-10-09 02:56:41,031][88327] Updated weights for policy 1, policy_version 70510 (0.0008) -[2023-10-09 02:56:41,396][88327] Updated weights for policy 1, policy_version 70520 (0.0008) -[2023-10-09 02:56:42,223][88326] Updated weights for policy 0, policy_version 70472 (0.0007) -[2023-10-09 02:56:42,597][88326] Updated weights for policy 0, policy_version 70482 (0.0007) -[2023-10-09 02:56:42,971][88326] Updated weights for policy 0, policy_version 70492 (0.0007) -[2023-10-09 02:56:43,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 144408576. Throughput: 0: 1712.5, 1: 1681.4. Samples: 36106394. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-09 02:56:43,975][87372] Avg episode reward: [(0, '7.060'), (1, '7.030')] -[2023-10-09 02:56:45,359][88327] Updated weights for policy 1, policy_version 70530 (0.0008) -[2023-10-09 02:56:45,785][88327] Updated weights for policy 1, policy_version 70540 (0.0008) -[2023-10-09 02:56:46,158][88327] Updated weights for policy 1, policy_version 70550 (0.0008) -[2023-10-09 02:56:46,527][88327] Updated weights for policy 1, policy_version 70560 (0.0009) -[2023-10-09 02:56:47,090][88326] Updated weights for policy 0, policy_version 70502 (0.0008) -[2023-10-09 02:56:47,461][88326] Updated weights for policy 0, policy_version 70512 (0.0009) -[2023-10-09 02:56:47,836][88326] Updated weights for policy 0, policy_version 70522 (0.0009) -[2023-10-09 02:56:48,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 144474112. Throughput: 0: 1687.3, 1: 1704.5. Samples: 36126380. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-09 02:56:48,975][87372] Avg episode reward: [(0, '7.100'), (1, '6.630')] -[2023-10-09 02:56:50,450][88327] Updated weights for policy 1, policy_version 70570 (0.0007) -[2023-10-09 02:56:50,820][88327] Updated weights for policy 1, policy_version 70580 (0.0008) -[2023-10-09 02:56:51,200][88327] Updated weights for policy 1, policy_version 70590 (0.0009) -[2023-10-09 02:56:51,944][88326] Updated weights for policy 0, policy_version 70532 (0.0010) -[2023-10-09 02:56:52,333][88326] Updated weights for policy 0, policy_version 70542 (0.0009) -[2023-10-09 02:56:52,699][88326] Updated weights for policy 0, policy_version 70552 (0.0008) -[2023-10-09 02:56:53,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 144539648. Throughput: 0: 1716.5, 1: 1681.7. Samples: 36137046. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-09 02:56:53,975][87372] Avg episode reward: [(0, '6.760'), (1, '6.630')] -[2023-10-09 02:56:55,104][88327] Updated weights for policy 1, policy_version 70600 (0.0009) -[2023-10-09 02:56:55,471][88327] Updated weights for policy 1, policy_version 70610 (0.0010) -[2023-10-09 02:56:55,830][88327] Updated weights for policy 1, policy_version 70620 (0.0009) -[2023-10-09 02:56:56,741][88326] Updated weights for policy 0, policy_version 70562 (0.0008) -[2023-10-09 02:56:57,108][88326] Updated weights for policy 0, policy_version 70572 (0.0010) -[2023-10-09 02:56:57,479][88326] Updated weights for policy 0, policy_version 70582 (0.0009) -[2023-10-09 02:56:57,847][88326] Updated weights for policy 0, policy_version 70592 (0.0008) -[2023-10-09 02:56:58,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 144605184. Throughput: 0: 1695.0, 1: 1701.4. Samples: 36157134. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-09 02:56:58,975][87372] Avg episode reward: [(0, '6.360'), (1, '7.760')] -[2023-10-09 02:56:59,886][88327] Updated weights for policy 1, policy_version 70630 (0.0010) -[2023-10-09 02:57:00,251][88327] Updated weights for policy 1, policy_version 70640 (0.0010) -[2023-10-09 02:57:00,623][88327] Updated weights for policy 1, policy_version 70650 (0.0010) -[2023-10-09 02:57:01,864][88326] Updated weights for policy 0, policy_version 70602 (0.0008) -[2023-10-09 02:57:02,243][88326] Updated weights for policy 0, policy_version 70612 (0.0009) -[2023-10-09 02:57:02,612][88326] Updated weights for policy 0, policy_version 70622 (0.0008) -[2023-10-09 02:57:03,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 144670720. Throughput: 0: 1683.4, 1: 1714.1. Samples: 36177610. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-09 02:57:03,975][87372] Avg episode reward: [(0, '6.770'), (1, '7.450')] -[2023-10-09 02:57:04,517][88327] Updated weights for policy 1, policy_version 70660 (0.0009) -[2023-10-09 02:57:04,883][88327] Updated weights for policy 1, policy_version 70670 (0.0008) -[2023-10-09 02:57:05,240][88327] Updated weights for policy 1, policy_version 70680 (0.0007) -[2023-10-09 02:57:06,679][88326] Updated weights for policy 0, policy_version 70632 (0.0008) -[2023-10-09 02:57:07,054][88326] Updated weights for policy 0, policy_version 70642 (0.0008) -[2023-10-09 02:57:07,423][88326] Updated weights for policy 0, policy_version 70652 (0.0008) -[2023-10-09 02:57:08,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 144736256. Throughput: 0: 1708.8, 1: 1682.8. Samples: 36187904. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-09 02:57:08,975][87372] Avg episode reward: [(0, '6.780'), (1, '7.160')] -[2023-10-09 02:57:09,164][88327] Updated weights for policy 1, policy_version 70690 (0.0008) -[2023-10-09 02:57:09,529][88327] Updated weights for policy 1, policy_version 70700 (0.0008) -[2023-10-09 02:57:09,899][88327] Updated weights for policy 1, policy_version 70710 (0.0007) -[2023-10-09 02:57:10,271][88327] Updated weights for policy 1, policy_version 70720 (0.0007) -[2023-10-09 02:57:11,473][88326] Updated weights for policy 0, policy_version 70662 (0.0008) -[2023-10-09 02:57:11,838][88326] Updated weights for policy 0, policy_version 70672 (0.0011) -[2023-10-09 02:57:12,209][88326] Updated weights for policy 0, policy_version 70682 (0.0010) -[2023-10-09 02:57:13,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 144801792. Throughput: 0: 1679.7, 1: 1709.9. Samples: 36207968. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-09 02:57:13,974][87372] Avg episode reward: [(0, '7.050'), (1, '7.150')] -[2023-10-09 02:57:14,314][88327] Updated weights for policy 1, policy_version 70730 (0.0009) -[2023-10-09 02:57:14,685][88327] Updated weights for policy 1, policy_version 70740 (0.0008) -[2023-10-09 02:57:15,054][88327] Updated weights for policy 1, policy_version 70750 (0.0009) -[2023-10-09 02:57:16,359][88326] Updated weights for policy 0, policy_version 70692 (0.0010) -[2023-10-09 02:57:16,722][88326] Updated weights for policy 0, policy_version 70702 (0.0010) -[2023-10-09 02:57:17,091][88326] Updated weights for policy 0, policy_version 70712 (0.0010) -[2023-10-09 02:57:18,896][88327] Updated weights for policy 1, policy_version 70760 (0.0010) -[2023-10-09 02:57:18,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 144867328. Throughput: 0: 1693.3, 1: 1713.8. Samples: 36228698. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-09 02:57:18,975][87372] Avg episode reward: [(0, '7.050'), (1, '7.080')] -[2023-10-09 02:57:19,267][88327] Updated weights for policy 1, policy_version 70770 (0.0007) -[2023-10-09 02:57:19,635][88327] Updated weights for policy 1, policy_version 70780 (0.0007) -[2023-10-09 02:57:20,998][88326] Updated weights for policy 0, policy_version 70722 (0.0008) -[2023-10-09 02:57:21,362][88326] Updated weights for policy 0, policy_version 70732 (0.0007) -[2023-10-09 02:57:21,721][88326] Updated weights for policy 0, policy_version 70742 (0.0007) -[2023-10-09 02:57:22,083][88326] Updated weights for policy 0, policy_version 70752 (0.0009) -[2023-10-09 02:57:23,597][88327] Updated weights for policy 1, policy_version 70790 (0.0009) -[2023-10-09 02:57:23,960][88327] Updated weights for policy 1, policy_version 70800 (0.0010) -[2023-10-09 02:57:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 144932864. Throughput: 0: 1691.9, 1: 1700.1. Samples: 36238898. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-09 02:57:23,975][87372] Avg episode reward: [(0, '6.930'), (1, '7.530')] -[2023-10-09 02:57:24,328][88327] Updated weights for policy 1, policy_version 70810 (0.0008) -[2023-10-09 02:57:26,143][88326] Updated weights for policy 0, policy_version 70762 (0.0008) -[2023-10-09 02:57:26,508][88326] Updated weights for policy 0, policy_version 70772 (0.0007) -[2023-10-09 02:57:26,879][88326] Updated weights for policy 0, policy_version 70782 (0.0008) -[2023-10-09 02:57:28,405][88327] Updated weights for policy 1, policy_version 70820 (0.0008) -[2023-10-09 02:57:28,764][88327] Updated weights for policy 1, policy_version 70830 (0.0008) -[2023-10-09 02:57:28,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 144998400. Throughput: 0: 1674.6, 1: 1717.6. Samples: 36259044. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:57:28,975][87372] Avg episode reward: [(0, '6.860'), (1, '7.370')] -[2023-10-09 02:57:29,132][88327] Updated weights for policy 1, policy_version 70840 (0.0010) -[2023-10-09 02:57:30,657][88326] Updated weights for policy 0, policy_version 70792 (0.0007) -[2023-10-09 02:57:31,031][88326] Updated weights for policy 0, policy_version 70802 (0.0009) -[2023-10-09 02:57:31,403][88326] Updated weights for policy 0, policy_version 70812 (0.0011) -[2023-10-09 02:57:33,263][88327] Updated weights for policy 1, policy_version 70850 (0.0007) -[2023-10-09 02:57:33,684][88327] Updated weights for policy 1, policy_version 70860 (0.0007) -[2023-10-09 02:57:33,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 145063936. Throughput: 0: 1699.0, 1: 1716.2. Samples: 36280064. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:57:33,975][87372] Avg episode reward: [(0, '7.330'), (1, '7.840')] -[2023-10-09 02:57:34,044][88327] Updated weights for policy 1, policy_version 70870 (0.0009) -[2023-10-09 02:57:34,418][88327] Updated weights for policy 1, policy_version 70880 (0.0008) -[2023-10-09 02:57:35,421][88326] Updated weights for policy 0, policy_version 70822 (0.0008) -[2023-10-09 02:57:35,790][88326] Updated weights for policy 0, policy_version 70832 (0.0008) -[2023-10-09 02:57:36,155][88326] Updated weights for policy 0, policy_version 70842 (0.0007) -[2023-10-09 02:57:38,330][88327] Updated weights for policy 1, policy_version 70890 (0.0007) -[2023-10-09 02:57:38,684][88327] Updated weights for policy 1, policy_version 70900 (0.0007) -[2023-10-09 02:57:38,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 145129472. Throughput: 0: 1678.3, 1: 1709.2. Samples: 36289482. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:57:38,975][87372] Avg episode reward: [(0, '7.200'), (1, '8.080')] -[2023-10-09 02:57:39,050][88327] Updated weights for policy 1, policy_version 70910 (0.0008) -[2023-10-09 02:57:40,279][88326] Updated weights for policy 0, policy_version 70852 (0.0010) -[2023-10-09 02:57:40,651][88326] Updated weights for policy 0, policy_version 70862 (0.0010) -[2023-10-09 02:57:41,022][88326] Updated weights for policy 0, policy_version 70872 (0.0009) -[2023-10-09 02:57:43,126][88327] Updated weights for policy 1, policy_version 70920 (0.0009) -[2023-10-09 02:57:43,491][88327] Updated weights for policy 1, policy_version 70930 (0.0007) -[2023-10-09 02:57:43,855][88327] Updated weights for policy 1, policy_version 70940 (0.0009) -[2023-10-09 02:57:43,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 145195008. Throughput: 0: 1689.6, 1: 1714.0. Samples: 36310292. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:57:43,975][87372] Avg episode reward: [(0, '7.600'), (1, '7.700')] -[2023-10-09 02:57:45,029][88326] Updated weights for policy 0, policy_version 70882 (0.0010) -[2023-10-09 02:57:45,433][88326] Updated weights for policy 0, policy_version 70892 (0.0010) -[2023-10-09 02:57:45,806][88326] Updated weights for policy 0, policy_version 70902 (0.0008) -[2023-10-09 02:57:46,173][88326] Updated weights for policy 0, policy_version 70912 (0.0009) -[2023-10-09 02:57:47,821][88327] Updated weights for policy 1, policy_version 70950 (0.0008) -[2023-10-09 02:57:48,184][88327] Updated weights for policy 1, policy_version 70960 (0.0009) -[2023-10-09 02:57:48,545][88327] Updated weights for policy 1, policy_version 70970 (0.0009) -[2023-10-09 02:57:48,974][87372] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 145293312. Throughput: 0: 1707.0, 1: 1697.6. Samples: 36330816. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:57:48,975][87372] Avg episode reward: [(0, '6.930'), (1, '7.520')] -[2023-10-09 02:57:50,203][88326] Updated weights for policy 0, policy_version 70922 (0.0007) -[2023-10-09 02:57:50,566][88326] Updated weights for policy 0, policy_version 70932 (0.0007) -[2023-10-09 02:57:50,932][88326] Updated weights for policy 0, policy_version 70942 (0.0009) -[2023-10-09 02:57:52,677][88327] Updated weights for policy 1, policy_version 70980 (0.0009) -[2023-10-09 02:57:53,029][88327] Updated weights for policy 1, policy_version 70990 (0.0009) -[2023-10-09 02:57:53,397][88327] Updated weights for policy 1, policy_version 71000 (0.0009) -[2023-10-09 02:57:53,974][87372] Fps is (10 sec: 16384.1, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 145358848. Throughput: 0: 1678.2, 1: 1712.8. Samples: 36340498. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:57:53,975][87372] Avg episode reward: [(0, '7.000'), (1, '7.460')] -[2023-10-09 02:57:54,865][88326] Updated weights for policy 0, policy_version 70952 (0.0007) -[2023-10-09 02:57:55,232][88326] Updated weights for policy 0, policy_version 70962 (0.0009) -[2023-10-09 02:57:55,603][88326] Updated weights for policy 0, policy_version 70972 (0.0007) -[2023-10-09 02:57:57,392][88327] Updated weights for policy 1, policy_version 71010 (0.0009) -[2023-10-09 02:57:57,754][88327] Updated weights for policy 1, policy_version 71020 (0.0008) -[2023-10-09 02:57:58,119][88327] Updated weights for policy 1, policy_version 71030 (0.0008) -[2023-10-09 02:57:58,480][88327] Updated weights for policy 1, policy_version 71040 (0.0009) -[2023-10-09 02:57:58,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 145424384. Throughput: 0: 1703.7, 1: 1715.1. Samples: 36361814. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:57:58,975][87372] Avg episode reward: [(0, '6.450'), (1, '6.670')] -[2023-10-09 02:57:59,492][88326] Updated weights for policy 0, policy_version 70982 (0.0008) -[2023-10-09 02:57:59,863][88326] Updated weights for policy 0, policy_version 70992 (0.0007) -[2023-10-09 02:58:00,240][88326] Updated weights for policy 0, policy_version 71002 (0.0009) -[2023-10-09 02:58:02,507][88327] Updated weights for policy 1, policy_version 71050 (0.0011) -[2023-10-09 02:58:02,869][88327] Updated weights for policy 1, policy_version 71060 (0.0009) -[2023-10-09 02:58:03,231][88327] Updated weights for policy 1, policy_version 71070 (0.0010) -[2023-10-09 02:58:03,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 145489920. Throughput: 0: 1716.0, 1: 1685.0. Samples: 36381744. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:58:03,975][87372] Avg episode reward: [(0, '6.030'), (1, '6.930')] -[2023-10-09 02:58:04,249][88326] Updated weights for policy 0, policy_version 71012 (0.0007) -[2023-10-09 02:58:04,624][88326] Updated weights for policy 0, policy_version 71022 (0.0008) -[2023-10-09 02:58:04,980][88326] Updated weights for policy 0, policy_version 71032 (0.0010) -[2023-10-09 02:58:07,436][88327] Updated weights for policy 1, policy_version 71080 (0.0008) -[2023-10-09 02:58:07,806][88327] Updated weights for policy 1, policy_version 71090 (0.0008) -[2023-10-09 02:58:08,174][88327] Updated weights for policy 1, policy_version 71100 (0.0007) -[2023-10-09 02:58:08,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 145555456. Throughput: 0: 1692.7, 1: 1708.8. Samples: 36391966. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:58:08,974][87372] Avg episode reward: [(0, '6.770'), (1, '6.960')] -[2023-10-09 02:58:09,074][88326] Updated weights for policy 0, policy_version 71042 (0.0010) -[2023-10-09 02:58:09,445][88326] Updated weights for policy 0, policy_version 71052 (0.0009) -[2023-10-09 02:58:09,818][88326] Updated weights for policy 0, policy_version 71062 (0.0008) -[2023-10-09 02:58:10,181][88326] Updated weights for policy 0, policy_version 71072 (0.0007) -[2023-10-09 02:58:12,134][88327] Updated weights for policy 1, policy_version 71110 (0.0009) -[2023-10-09 02:58:12,497][88327] Updated weights for policy 1, policy_version 71120 (0.0010) -[2023-10-09 02:58:12,863][88327] Updated weights for policy 1, policy_version 71130 (0.0007) -[2023-10-09 02:58:13,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 145620992. Throughput: 0: 1712.0, 1: 1706.8. Samples: 36412890. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:58:13,975][87372] Avg episode reward: [(0, '6.460'), (1, '7.770')] -[2023-10-09 02:58:14,129][88326] Updated weights for policy 0, policy_version 71082 (0.0007) -[2023-10-09 02:58:14,505][88326] Updated weights for policy 0, policy_version 71092 (0.0009) -[2023-10-09 02:58:14,873][88326] Updated weights for policy 0, policy_version 71102 (0.0008) -[2023-10-09 02:58:16,758][88327] Updated weights for policy 1, policy_version 71140 (0.0009) -[2023-10-09 02:58:17,122][88327] Updated weights for policy 1, policy_version 71150 (0.0007) -[2023-10-09 02:58:17,484][88327] Updated weights for policy 1, policy_version 71160 (0.0008) -[2023-10-09 02:58:18,846][88326] Updated weights for policy 0, policy_version 71112 (0.0009) -[2023-10-09 02:58:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 145686528. Throughput: 0: 1713.5, 1: 1684.4. Samples: 36432968. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-10-09 02:58:18,975][87372] Avg episode reward: [(0, '6.570'), (1, '7.630')] -[2023-10-09 02:58:19,220][88326] Updated weights for policy 0, policy_version 71122 (0.0008) -[2023-10-09 02:58:19,598][88326] Updated weights for policy 0, policy_version 71132 (0.0008) -[2023-10-09 02:58:21,547][88327] Updated weights for policy 1, policy_version 71170 (0.0010) -[2023-10-09 02:58:21,951][88327] Updated weights for policy 1, policy_version 71180 (0.0010) -[2023-10-09 02:58:22,316][88327] Updated weights for policy 1, policy_version 71190 (0.0009) -[2023-10-09 02:58:22,683][88327] Updated weights for policy 1, policy_version 71200 (0.0009) -[2023-10-09 02:58:23,558][88326] Updated weights for policy 0, policy_version 71142 (0.0008) -[2023-10-09 02:58:23,925][88326] Updated weights for policy 0, policy_version 71152 (0.0008) -[2023-10-09 02:58:23,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 145752064. Throughput: 0: 1704.9, 1: 1717.8. Samples: 36443504. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-10-09 02:58:23,975][87372] Avg episode reward: [(0, '6.770'), (1, '7.540')] -[2023-10-09 02:58:24,303][88326] Updated weights for policy 0, policy_version 71162 (0.0009) -[2023-10-09 02:58:26,625][88327] Updated weights for policy 1, policy_version 71210 (0.0008) -[2023-10-09 02:58:26,986][88327] Updated weights for policy 1, policy_version 71220 (0.0008) -[2023-10-09 02:58:27,355][88327] Updated weights for policy 1, policy_version 71230 (0.0007) -[2023-10-09 02:58:28,316][88326] Updated weights for policy 0, policy_version 71172 (0.0007) -[2023-10-09 02:58:28,688][88326] Updated weights for policy 0, policy_version 71182 (0.0008) -[2023-10-09 02:58:28,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 145817600. Throughput: 0: 1714.5, 1: 1691.7. Samples: 36463570. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-10-09 02:58:28,975][87372] Avg episode reward: [(0, '6.320'), (1, '6.930')] -[2023-10-09 02:58:29,067][88326] Updated weights for policy 0, policy_version 71192 (0.0010) -[2023-10-09 02:58:31,270][88327] Updated weights for policy 1, policy_version 71240 (0.0007) -[2023-10-09 02:58:31,635][88327] Updated weights for policy 1, policy_version 71250 (0.0008) -[2023-10-09 02:58:32,003][88327] Updated weights for policy 1, policy_version 71260 (0.0009) -[2023-10-09 02:58:33,190][88326] Updated weights for policy 0, policy_version 71202 (0.0007) -[2023-10-09 02:58:33,569][88326] Updated weights for policy 0, policy_version 71212 (0.0007) -[2023-10-09 02:58:33,935][88326] Updated weights for policy 0, policy_version 71222 (0.0007) -[2023-10-09 02:58:33,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 145883136. Throughput: 0: 1704.0, 1: 1698.0. Samples: 36483906. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-10-09 02:58:33,975][87372] Avg episode reward: [(0, '6.820'), (1, '6.480')] -[2023-10-09 02:58:33,987][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000071264_72974336.pth... -[2023-10-09 02:58:34,027][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000069664_71335936.pth -[2023-10-09 02:58:34,033][88168] Saving a milestone ./train_atari/atari_battlezone_APPO/checkpoint_p1/milestones/checkpoint_000071264_72974336.pth -[2023-10-09 02:58:34,294][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000071232_72941568.pth... -[2023-10-09 02:58:34,297][88326] Updated weights for policy 0, policy_version 71232 (0.0007) -[2023-10-09 02:58:34,335][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000069632_71303168.pth -[2023-10-09 02:58:34,340][88088] Saving a milestone ./train_atari/atari_battlezone_APPO/checkpoint_p0/milestones/checkpoint_000071232_72941568.pth -[2023-10-09 02:58:36,010][88327] Updated weights for policy 1, policy_version 71270 (0.0008) -[2023-10-09 02:58:36,371][88327] Updated weights for policy 1, policy_version 71280 (0.0009) -[2023-10-09 02:58:36,730][88327] Updated weights for policy 1, policy_version 71290 (0.0009) -[2023-10-09 02:58:38,269][88326] Updated weights for policy 0, policy_version 71242 (0.0009) -[2023-10-09 02:58:38,634][88326] Updated weights for policy 0, policy_version 71252 (0.0007) -[2023-10-09 02:58:38,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 145948672. Throughput: 0: 1706.2, 1: 1706.5. Samples: 36494070. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-10-09 02:58:38,975][87372] Avg episode reward: [(0, '7.230'), (1, '6.810')] -[2023-10-09 02:58:39,013][88326] Updated weights for policy 0, policy_version 71262 (0.0007) -[2023-10-09 02:58:40,832][88327] Updated weights for policy 1, policy_version 71300 (0.0009) -[2023-10-09 02:58:41,200][88327] Updated weights for policy 1, policy_version 71310 (0.0010) -[2023-10-09 02:58:41,565][88327] Updated weights for policy 1, policy_version 71320 (0.0009) -[2023-10-09 02:58:43,171][88326] Updated weights for policy 0, policy_version 71272 (0.0008) -[2023-10-09 02:58:43,539][88326] Updated weights for policy 0, policy_version 71282 (0.0008) -[2023-10-09 02:58:43,907][88326] Updated weights for policy 0, policy_version 71292 (0.0008) -[2023-10-09 02:58:43,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 146014208. Throughput: 0: 1702.3, 1: 1676.0. Samples: 36513836. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-10-09 02:58:43,975][87372] Avg episode reward: [(0, '7.660'), (1, '6.770')] -[2023-10-09 02:58:45,742][88327] Updated weights for policy 1, policy_version 71330 (0.0008) -[2023-10-09 02:58:46,115][88327] Updated weights for policy 1, policy_version 71340 (0.0009) -[2023-10-09 02:58:46,472][88327] Updated weights for policy 1, policy_version 71350 (0.0008) -[2023-10-09 02:58:46,842][88327] Updated weights for policy 1, policy_version 71360 (0.0008) -[2023-10-09 02:58:47,815][88326] Updated weights for policy 0, policy_version 71302 (0.0008) -[2023-10-09 02:58:48,177][88326] Updated weights for policy 0, policy_version 71312 (0.0010) -[2023-10-09 02:58:48,551][88326] Updated weights for policy 0, policy_version 71322 (0.0007) -[2023-10-09 02:58:48,974][87372] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 146112512. Throughput: 0: 1687.8, 1: 1702.3. Samples: 36534296. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-10-09 02:58:48,975][87372] Avg episode reward: [(0, '7.250'), (1, '7.560')] -[2023-10-09 02:58:50,813][88327] Updated weights for policy 1, policy_version 71370 (0.0009) -[2023-10-09 02:58:51,179][88327] Updated weights for policy 1, policy_version 71380 (0.0007) -[2023-10-09 02:58:51,545][88327] Updated weights for policy 1, policy_version 71390 (0.0010) -[2023-10-09 02:58:52,521][88326] Updated weights for policy 0, policy_version 71332 (0.0007) -[2023-10-09 02:58:52,887][88326] Updated weights for policy 0, policy_version 71342 (0.0009) -[2023-10-09 02:58:53,253][88326] Updated weights for policy 0, policy_version 71352 (0.0009) -[2023-10-09 02:58:53,974][87372] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 146178048. Throughput: 0: 1706.5, 1: 1691.6. Samples: 36544884. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-10-09 02:58:53,975][87372] Avg episode reward: [(0, '6.130'), (1, '7.780')] -[2023-10-09 02:58:55,663][88327] Updated weights for policy 1, policy_version 71400 (0.0010) -[2023-10-09 02:58:56,030][88327] Updated weights for policy 1, policy_version 71410 (0.0008) -[2023-10-09 02:58:56,393][88327] Updated weights for policy 1, policy_version 71420 (0.0009) -[2023-10-09 02:58:57,436][88326] Updated weights for policy 0, policy_version 71362 (0.0007) -[2023-10-09 02:58:57,807][88326] Updated weights for policy 0, policy_version 71372 (0.0007) -[2023-10-09 02:58:58,170][88326] Updated weights for policy 0, policy_version 71382 (0.0007) -[2023-10-09 02:58:58,530][88326] Updated weights for policy 0, policy_version 71392 (0.0007) -[2023-10-09 02:58:58,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 146243584. Throughput: 0: 1705.1, 1: 1679.8. Samples: 36565210. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-10-09 02:58:58,975][87372] Avg episode reward: [(0, '6.700'), (1, '7.750')] -[2023-10-09 02:59:00,407][88327] Updated weights for policy 1, policy_version 71430 (0.0010) -[2023-10-09 02:59:00,771][88327] Updated weights for policy 1, policy_version 71440 (0.0010) -[2023-10-09 02:59:01,130][88327] Updated weights for policy 1, policy_version 71450 (0.0009) -[2023-10-09 02:59:02,575][88326] Updated weights for policy 0, policy_version 71402 (0.0007) -[2023-10-09 02:59:02,940][88326] Updated weights for policy 0, policy_version 71412 (0.0011) -[2023-10-09 02:59:03,324][88326] Updated weights for policy 0, policy_version 71422 (0.0009) -[2023-10-09 02:59:03,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 146309120. Throughput: 0: 1677.5, 1: 1709.2. Samples: 36585366. Policy #0 lag: (min: 15.0, avg: 15.1, max: 23.0) -[2023-10-09 02:59:03,975][87372] Avg episode reward: [(0, '6.880'), (1, '7.180')] -[2023-10-09 02:59:04,940][88327] Updated weights for policy 1, policy_version 71460 (0.0011) -[2023-10-09 02:59:05,314][88327] Updated weights for policy 1, policy_version 71470 (0.0008) -[2023-10-09 02:59:05,683][88327] Updated weights for policy 1, policy_version 71480 (0.0008) -[2023-10-09 02:59:07,233][88326] Updated weights for policy 0, policy_version 71432 (0.0009) -[2023-10-09 02:59:07,603][88326] Updated weights for policy 0, policy_version 71442 (0.0010) -[2023-10-09 02:59:07,982][88326] Updated weights for policy 0, policy_version 71452 (0.0008) -[2023-10-09 02:59:08,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 146374656. Throughput: 0: 1704.1, 1: 1675.7. Samples: 36595596. Policy #0 lag: (min: 15.0, avg: 15.1, max: 23.0) -[2023-10-09 02:59:08,975][87372] Avg episode reward: [(0, '6.810'), (1, '6.960')] -[2023-10-09 02:59:09,861][88327] Updated weights for policy 1, policy_version 71490 (0.0008) -[2023-10-09 02:59:10,228][88327] Updated weights for policy 1, policy_version 71500 (0.0009) -[2023-10-09 02:59:10,578][88327] Updated weights for policy 1, policy_version 71510 (0.0009) -[2023-10-09 02:59:10,949][88327] Updated weights for policy 1, policy_version 71520 (0.0008) -[2023-10-09 02:59:11,933][88326] Updated weights for policy 0, policy_version 71462 (0.0009) -[2023-10-09 02:59:12,298][88326] Updated weights for policy 0, policy_version 71472 (0.0009) -[2023-10-09 02:59:12,679][88326] Updated weights for policy 0, policy_version 71482 (0.0009) -[2023-10-09 02:59:13,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 146440192. Throughput: 0: 1687.9, 1: 1697.2. Samples: 36615896. Policy #0 lag: (min: 15.0, avg: 15.1, max: 23.0) -[2023-10-09 02:59:13,975][87372] Avg episode reward: [(0, '6.960'), (1, '6.490')] -[2023-10-09 02:59:14,904][88327] Updated weights for policy 1, policy_version 71530 (0.0007) -[2023-10-09 02:59:15,265][88327] Updated weights for policy 1, policy_version 71540 (0.0009) -[2023-10-09 02:59:15,635][88327] Updated weights for policy 1, policy_version 71550 (0.0010) -[2023-10-09 02:59:16,736][88326] Updated weights for policy 0, policy_version 71492 (0.0008) -[2023-10-09 02:59:17,107][88326] Updated weights for policy 0, policy_version 71502 (0.0007) -[2023-10-09 02:59:17,478][88326] Updated weights for policy 0, policy_version 71512 (0.0007) -[2023-10-09 02:59:18,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 146505728. Throughput: 0: 1680.3, 1: 1707.0. Samples: 36636336. Policy #0 lag: (min: 15.0, avg: 15.1, max: 23.0) -[2023-10-09 02:59:18,974][87372] Avg episode reward: [(0, '6.770'), (1, '6.280')] -[2023-10-09 02:59:19,484][88327] Updated weights for policy 1, policy_version 71560 (0.0009) -[2023-10-09 02:59:19,855][88327] Updated weights for policy 1, policy_version 71570 (0.0007) -[2023-10-09 02:59:20,216][88327] Updated weights for policy 1, policy_version 71580 (0.0008) -[2023-10-09 02:59:21,603][88326] Updated weights for policy 0, policy_version 71522 (0.0008) -[2023-10-09 02:59:22,015][88326] Updated weights for policy 0, policy_version 71532 (0.0009) -[2023-10-09 02:59:22,380][88326] Updated weights for policy 0, policy_version 71542 (0.0007) -[2023-10-09 02:59:22,749][88326] Updated weights for policy 0, policy_version 71552 (0.0007) -[2023-10-09 02:59:23,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 146571264. Throughput: 0: 1708.0, 1: 1684.3. Samples: 36646724. Policy #0 lag: (min: 15.0, avg: 15.1, max: 23.0) -[2023-10-09 02:59:23,975][87372] Avg episode reward: [(0, '6.750'), (1, '6.830')] -[2023-10-09 02:59:24,076][88327] Updated weights for policy 1, policy_version 71590 (0.0008) -[2023-10-09 02:59:24,437][88327] Updated weights for policy 1, policy_version 71600 (0.0007) -[2023-10-09 02:59:24,805][88327] Updated weights for policy 1, policy_version 71610 (0.0008) -[2023-10-09 02:59:26,650][88326] Updated weights for policy 0, policy_version 71562 (0.0011) -[2023-10-09 02:59:27,016][88326] Updated weights for policy 0, policy_version 71572 (0.0009) -[2023-10-09 02:59:27,396][88326] Updated weights for policy 0, policy_version 71582 (0.0007) -[2023-10-09 02:59:28,972][88327] Updated weights for policy 1, policy_version 71620 (0.0008) -[2023-10-09 02:59:28,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 146636800. Throughput: 0: 1687.0, 1: 1713.4. Samples: 36666854. Policy #0 lag: (min: 15.0, avg: 15.1, max: 23.0) -[2023-10-09 02:59:28,974][87372] Avg episode reward: [(0, '6.970'), (1, '7.710')] -[2023-10-09 02:59:29,339][88327] Updated weights for policy 1, policy_version 71630 (0.0010) -[2023-10-09 02:59:29,705][88327] Updated weights for policy 1, policy_version 71640 (0.0008) -[2023-10-09 02:59:31,509][88326] Updated weights for policy 0, policy_version 71592 (0.0009) -[2023-10-09 02:59:31,881][88326] Updated weights for policy 0, policy_version 71602 (0.0009) -[2023-10-09 02:59:32,246][88326] Updated weights for policy 0, policy_version 71612 (0.0010) -[2023-10-09 02:59:33,877][88327] Updated weights for policy 1, policy_version 71650 (0.0007) -[2023-10-09 02:59:33,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 146702336. Throughput: 0: 1688.0, 1: 1711.6. Samples: 36687278. Policy #0 lag: (min: 15.0, avg: 15.1, max: 23.0) -[2023-10-09 02:59:33,975][87372] Avg episode reward: [(0, '6.840'), (1, '7.740')] -[2023-10-09 02:59:34,237][88327] Updated weights for policy 1, policy_version 71660 (0.0008) -[2023-10-09 02:59:34,602][88327] Updated weights for policy 1, policy_version 71670 (0.0009) -[2023-10-09 02:59:34,962][88327] Updated weights for policy 1, policy_version 71680 (0.0007) -[2023-10-09 02:59:36,302][88326] Updated weights for policy 0, policy_version 71622 (0.0008) -[2023-10-09 02:59:36,671][88326] Updated weights for policy 0, policy_version 71632 (0.0009) -[2023-10-09 02:59:37,038][88326] Updated weights for policy 0, policy_version 71642 (0.0009) -[2023-10-09 02:59:38,782][88327] Updated weights for policy 1, policy_version 71690 (0.0008) -[2023-10-09 02:59:38,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 146767872. Throughput: 0: 1696.5, 1: 1698.6. Samples: 36697664. Policy #0 lag: (min: 15.0, avg: 15.1, max: 23.0) -[2023-10-09 02:59:38,974][87372] Avg episode reward: [(0, '6.800'), (1, '7.670')] -[2023-10-09 02:59:39,143][88327] Updated weights for policy 1, policy_version 71700 (0.0008) -[2023-10-09 02:59:39,504][88327] Updated weights for policy 1, policy_version 71710 (0.0008) -[2023-10-09 02:59:41,082][88326] Updated weights for policy 0, policy_version 71652 (0.0009) -[2023-10-09 02:59:41,448][88326] Updated weights for policy 0, policy_version 71662 (0.0007) -[2023-10-09 02:59:41,813][88326] Updated weights for policy 0, policy_version 71672 (0.0009) -[2023-10-09 02:59:43,660][88327] Updated weights for policy 1, policy_version 71720 (0.0009) -[2023-10-09 02:59:43,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 146833408. Throughput: 0: 1669.9, 1: 1713.3. Samples: 36717454. Policy #0 lag: (min: 15.0, avg: 15.1, max: 23.0) -[2023-10-09 02:59:43,975][87372] Avg episode reward: [(0, '6.770'), (1, '7.410')] -[2023-10-09 02:59:44,019][88327] Updated weights for policy 1, policy_version 71730 (0.0009) -[2023-10-09 02:59:44,382][88327] Updated weights for policy 1, policy_version 71740 (0.0007) -[2023-10-09 02:59:45,763][88326] Updated weights for policy 0, policy_version 71682 (0.0009) -[2023-10-09 02:59:46,145][88326] Updated weights for policy 0, policy_version 71692 (0.0008) -[2023-10-09 02:59:46,515][88326] Updated weights for policy 0, policy_version 71702 (0.0007) -[2023-10-09 02:59:46,889][88326] Updated weights for policy 0, policy_version 71712 (0.0009) -[2023-10-09 02:59:48,432][88327] Updated weights for policy 1, policy_version 71750 (0.0008) -[2023-10-09 02:59:48,803][88327] Updated weights for policy 1, policy_version 71760 (0.0007) -[2023-10-09 02:59:48,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 146898944. Throughput: 0: 1693.7, 1: 1707.0. Samples: 36738398. Policy #0 lag: (min: 15.0, avg: 15.1, max: 23.0) -[2023-10-09 02:59:48,975][87372] Avg episode reward: [(0, '6.840'), (1, '7.230')] -[2023-10-09 02:59:49,173][88327] Updated weights for policy 1, policy_version 71770 (0.0010) -[2023-10-09 02:59:50,943][88326] Updated weights for policy 0, policy_version 71722 (0.0010) -[2023-10-09 02:59:51,315][88326] Updated weights for policy 0, policy_version 71732 (0.0008) -[2023-10-09 02:59:51,700][88326] Updated weights for policy 0, policy_version 71742 (0.0008) -[2023-10-09 02:59:53,202][88327] Updated weights for policy 1, policy_version 71780 (0.0009) -[2023-10-09 02:59:53,569][88327] Updated weights for policy 1, policy_version 71790 (0.0008) -[2023-10-09 02:59:53,926][88327] Updated weights for policy 1, policy_version 71800 (0.0009) -[2023-10-09 02:59:53,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 146964480. Throughput: 0: 1686.0, 1: 1706.5. Samples: 36748260. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:59:53,974][87372] Avg episode reward: [(0, '6.600'), (1, '7.660')] -[2023-10-09 02:59:55,738][88326] Updated weights for policy 0, policy_version 71752 (0.0009) -[2023-10-09 02:59:56,107][88326] Updated weights for policy 0, policy_version 71762 (0.0010) -[2023-10-09 02:59:56,482][88326] Updated weights for policy 0, policy_version 71772 (0.0009) -[2023-10-09 02:59:58,079][88327] Updated weights for policy 1, policy_version 71810 (0.0011) -[2023-10-09 02:59:58,433][88327] Updated weights for policy 1, policy_version 71820 (0.0009) -[2023-10-09 02:59:58,812][88327] Updated weights for policy 1, policy_version 71830 (0.0009) -[2023-10-09 02:59:58,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 147030016. Throughput: 0: 1685.4, 1: 1706.4. Samples: 36768524. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 02:59:58,975][87372] Avg episode reward: [(0, '7.150'), (1, '7.170')] -[2023-10-09 02:59:59,177][88327] Updated weights for policy 1, policy_version 71840 (0.0009) -[2023-10-09 03:00:00,382][88326] Updated weights for policy 0, policy_version 71782 (0.0008) -[2023-10-09 03:00:00,742][88326] Updated weights for policy 0, policy_version 71792 (0.0010) -[2023-10-09 03:00:01,106][88326] Updated weights for policy 0, policy_version 71802 (0.0009) -[2023-10-09 03:00:03,337][88327] Updated weights for policy 1, policy_version 71850 (0.0009) -[2023-10-09 03:00:03,707][88327] Updated weights for policy 1, policy_version 71860 (0.0009) -[2023-10-09 03:00:03,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 147095552. Throughput: 0: 1703.0, 1: 1693.7. Samples: 36789186. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:00:03,975][87372] Avg episode reward: [(0, '6.320'), (1, '7.330')] -[2023-10-09 03:00:04,071][88327] Updated weights for policy 1, policy_version 71870 (0.0009) -[2023-10-09 03:00:05,111][88326] Updated weights for policy 0, policy_version 71812 (0.0008) -[2023-10-09 03:00:05,470][88326] Updated weights for policy 0, policy_version 71822 (0.0009) -[2023-10-09 03:00:05,840][88326] Updated weights for policy 0, policy_version 71832 (0.0011) -[2023-10-09 03:00:08,168][88327] Updated weights for policy 1, policy_version 71880 (0.0009) -[2023-10-09 03:00:08,527][88327] Updated weights for policy 1, policy_version 71890 (0.0010) -[2023-10-09 03:00:08,893][88327] Updated weights for policy 1, policy_version 71900 (0.0008) -[2023-10-09 03:00:08,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 147161088. Throughput: 0: 1677.0, 1: 1699.1. Samples: 36798650. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:00:08,975][87372] Avg episode reward: [(0, '6.590'), (1, '7.500')] -[2023-10-09 03:00:09,790][88326] Updated weights for policy 0, policy_version 71842 (0.0009) -[2023-10-09 03:00:10,169][88326] Updated weights for policy 0, policy_version 71852 (0.0008) -[2023-10-09 03:00:10,536][88326] Updated weights for policy 0, policy_version 71862 (0.0007) -[2023-10-09 03:00:10,906][88326] Updated weights for policy 0, policy_version 71872 (0.0009) -[2023-10-09 03:00:12,851][88327] Updated weights for policy 1, policy_version 71910 (0.0009) -[2023-10-09 03:00:13,230][88327] Updated weights for policy 1, policy_version 71920 (0.0009) -[2023-10-09 03:00:13,593][88327] Updated weights for policy 1, policy_version 71930 (0.0009) -[2023-10-09 03:00:13,974][87372] Fps is (10 sec: 16384.2, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 147259392. Throughput: 0: 1706.1, 1: 1695.7. Samples: 36819936. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:00:13,975][87372] Avg episode reward: [(0, '6.350'), (1, '7.440')] -[2023-10-09 03:00:14,946][88326] Updated weights for policy 0, policy_version 71882 (0.0007) -[2023-10-09 03:00:15,324][88326] Updated weights for policy 0, policy_version 71892 (0.0007) -[2023-10-09 03:00:15,687][88326] Updated weights for policy 0, policy_version 71902 (0.0009) -[2023-10-09 03:00:17,750][88327] Updated weights for policy 1, policy_version 71940 (0.0008) -[2023-10-09 03:00:18,115][88327] Updated weights for policy 1, policy_version 71950 (0.0007) -[2023-10-09 03:00:18,481][88327] Updated weights for policy 1, policy_version 71960 (0.0007) -[2023-10-09 03:00:18,974][87372] Fps is (10 sec: 16383.8, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 147324928. Throughput: 0: 1714.9, 1: 1684.8. Samples: 36840262. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:00:18,975][87372] Avg episode reward: [(0, '6.370'), (1, '7.260')] -[2023-10-09 03:00:19,674][88326] Updated weights for policy 0, policy_version 71912 (0.0009) -[2023-10-09 03:00:20,035][88326] Updated weights for policy 0, policy_version 71922 (0.0008) -[2023-10-09 03:00:20,398][88326] Updated weights for policy 0, policy_version 71932 (0.0008) -[2023-10-09 03:00:22,613][88327] Updated weights for policy 1, policy_version 71970 (0.0008) -[2023-10-09 03:00:22,986][88327] Updated weights for policy 1, policy_version 71980 (0.0009) -[2023-10-09 03:00:23,345][88327] Updated weights for policy 1, policy_version 71990 (0.0009) -[2023-10-09 03:00:23,700][88327] Updated weights for policy 1, policy_version 72000 (0.0009) -[2023-10-09 03:00:23,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 147390464. Throughput: 0: 1687.3, 1: 1693.8. Samples: 36849814. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:00:23,975][87372] Avg episode reward: [(0, '6.890'), (1, '6.870')] -[2023-10-09 03:00:24,332][88326] Updated weights for policy 0, policy_version 71942 (0.0009) -[2023-10-09 03:00:24,710][88326] Updated weights for policy 0, policy_version 71952 (0.0008) -[2023-10-09 03:00:25,086][88326] Updated weights for policy 0, policy_version 71962 (0.0007) -[2023-10-09 03:00:27,574][88327] Updated weights for policy 1, policy_version 72010 (0.0009) -[2023-10-09 03:00:27,938][88327] Updated weights for policy 1, policy_version 72020 (0.0008) -[2023-10-09 03:00:28,310][88327] Updated weights for policy 1, policy_version 72030 (0.0010) -[2023-10-09 03:00:28,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 147456000. Throughput: 0: 1710.7, 1: 1693.5. Samples: 36870642. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:00:28,974][87372] Avg episode reward: [(0, '7.280'), (1, '7.640')] -[2023-10-09 03:00:29,204][88326] Updated weights for policy 0, policy_version 71972 (0.0008) -[2023-10-09 03:00:29,575][88326] Updated weights for policy 0, policy_version 71982 (0.0007) -[2023-10-09 03:00:29,942][88326] Updated weights for policy 0, policy_version 71992 (0.0008) -[2023-10-09 03:00:32,335][88327] Updated weights for policy 1, policy_version 72040 (0.0008) -[2023-10-09 03:00:32,702][88327] Updated weights for policy 1, policy_version 72050 (0.0009) -[2023-10-09 03:00:33,073][88327] Updated weights for policy 1, policy_version 72060 (0.0009) -[2023-10-09 03:00:33,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 147521536. Throughput: 0: 1711.1, 1: 1665.5. Samples: 36890342. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:00:33,975][87372] Avg episode reward: [(0, '6.630'), (1, '7.730')] -[2023-10-09 03:00:33,984][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000072064_73793536.pth... -[2023-10-09 03:00:34,020][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000070464_72155136.pth -[2023-10-09 03:00:34,027][88326] Updated weights for policy 0, policy_version 72002 (0.0009) -[2023-10-09 03:00:34,406][88326] Updated weights for policy 0, policy_version 72012 (0.0009) -[2023-10-09 03:00:34,777][88326] Updated weights for policy 0, policy_version 72022 (0.0009) -[2023-10-09 03:00:35,150][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000072032_73760768.pth... -[2023-10-09 03:00:35,154][88326] Updated weights for policy 0, policy_version 72032 (0.0009) -[2023-10-09 03:00:35,179][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000070432_72122368.pth -[2023-10-09 03:00:37,120][88327] Updated weights for policy 1, policy_version 72070 (0.0009) -[2023-10-09 03:00:37,484][88327] Updated weights for policy 1, policy_version 72080 (0.0010) -[2023-10-09 03:00:37,846][88327] Updated weights for policy 1, policy_version 72090 (0.0008) -[2023-10-09 03:00:38,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 147587072. Throughput: 0: 1693.5, 1: 1693.7. Samples: 36900688. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:00:38,975][87372] Avg episode reward: [(0, '7.090'), (1, '7.150')] -[2023-10-09 03:00:39,159][88326] Updated weights for policy 0, policy_version 72042 (0.0010) -[2023-10-09 03:00:39,535][88326] Updated weights for policy 0, policy_version 72052 (0.0009) -[2023-10-09 03:00:39,905][88326] Updated weights for policy 0, policy_version 72062 (0.0010) -[2023-10-09 03:00:41,983][88327] Updated weights for policy 1, policy_version 72100 (0.0009) -[2023-10-09 03:00:42,360][88327] Updated weights for policy 1, policy_version 72110 (0.0009) -[2023-10-09 03:00:42,724][88327] Updated weights for policy 1, policy_version 72120 (0.0009) -[2023-10-09 03:00:43,841][88326] Updated weights for policy 0, policy_version 72072 (0.0009) -[2023-10-09 03:00:43,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 147652608. Throughput: 0: 1705.2, 1: 1684.2. Samples: 36921044. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-09 03:00:43,975][87372] Avg episode reward: [(0, '7.040'), (1, '7.600')] -[2023-10-09 03:00:44,208][88326] Updated weights for policy 0, policy_version 72082 (0.0010) -[2023-10-09 03:00:44,588][88326] Updated weights for policy 0, policy_version 72092 (0.0011) -[2023-10-09 03:00:46,698][88327] Updated weights for policy 1, policy_version 72130 (0.0008) -[2023-10-09 03:00:47,066][88327] Updated weights for policy 1, policy_version 72140 (0.0011) -[2023-10-09 03:00:47,424][88327] Updated weights for policy 1, policy_version 72150 (0.0011) -[2023-10-09 03:00:47,791][88327] Updated weights for policy 1, policy_version 72160 (0.0009) -[2023-10-09 03:00:48,692][88326] Updated weights for policy 0, policy_version 72102 (0.0011) -[2023-10-09 03:00:48,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 147718144. Throughput: 0: 1699.9, 1: 1672.5. Samples: 36940944. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-09 03:00:48,975][87372] Avg episode reward: [(0, '7.200'), (1, '7.740')] -[2023-10-09 03:00:49,062][88326] Updated weights for policy 0, policy_version 72112 (0.0010) -[2023-10-09 03:00:49,440][88326] Updated weights for policy 0, policy_version 72122 (0.0009) -[2023-10-09 03:00:52,039][88327] Updated weights for policy 1, policy_version 72170 (0.0007) -[2023-10-09 03:00:52,416][88327] Updated weights for policy 1, policy_version 72180 (0.0008) -[2023-10-09 03:00:52,773][88327] Updated weights for policy 1, policy_version 72190 (0.0010) -[2023-10-09 03:00:53,444][88326] Updated weights for policy 0, policy_version 72132 (0.0008) -[2023-10-09 03:00:53,803][88326] Updated weights for policy 0, policy_version 72142 (0.0011) -[2023-10-09 03:00:53,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 147783680. Throughput: 0: 1694.2, 1: 1696.7. Samples: 36951238. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-09 03:00:53,975][87372] Avg episode reward: [(0, '7.120'), (1, '6.990')] -[2023-10-09 03:00:54,175][88326] Updated weights for policy 0, policy_version 72152 (0.0011) -[2023-10-09 03:00:56,834][88327] Updated weights for policy 1, policy_version 72200 (0.0009) -[2023-10-09 03:00:57,194][88327] Updated weights for policy 1, policy_version 72210 (0.0010) -[2023-10-09 03:00:57,559][88327] Updated weights for policy 1, policy_version 72220 (0.0010) -[2023-10-09 03:00:58,355][88326] Updated weights for policy 0, policy_version 72162 (0.0010) -[2023-10-09 03:00:58,718][88326] Updated weights for policy 0, policy_version 72172 (0.0009) -[2023-10-09 03:00:58,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 147849216. Throughput: 0: 1686.0, 1: 1679.2. Samples: 36971368. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-09 03:00:58,975][87372] Avg episode reward: [(0, '7.270'), (1, '6.960')] -[2023-10-09 03:00:59,092][88326] Updated weights for policy 0, policy_version 72182 (0.0010) -[2023-10-09 03:00:59,450][88326] Updated weights for policy 0, policy_version 72192 (0.0011) -[2023-10-09 03:01:01,600][88327] Updated weights for policy 1, policy_version 72230 (0.0009) -[2023-10-09 03:01:01,969][88327] Updated weights for policy 1, policy_version 72240 (0.0010) -[2023-10-09 03:01:02,330][88327] Updated weights for policy 1, policy_version 72250 (0.0009) -[2023-10-09 03:01:03,658][88326] Updated weights for policy 0, policy_version 72202 (0.0009) -[2023-10-09 03:01:03,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 147914752. Throughput: 0: 1684.8, 1: 1670.2. Samples: 36991236. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-09 03:01:03,975][87372] Avg episode reward: [(0, '7.560'), (1, '7.190')] -[2023-10-09 03:01:04,017][88326] Updated weights for policy 0, policy_version 72212 (0.0009) -[2023-10-09 03:01:04,382][88326] Updated weights for policy 0, policy_version 72222 (0.0007) -[2023-10-09 03:01:06,361][88327] Updated weights for policy 1, policy_version 72260 (0.0009) -[2023-10-09 03:01:06,725][88327] Updated weights for policy 1, policy_version 72270 (0.0007) -[2023-10-09 03:01:07,081][88327] Updated weights for policy 1, policy_version 72280 (0.0008) -[2023-10-09 03:01:08,316][88326] Updated weights for policy 0, policy_version 72232 (0.0009) -[2023-10-09 03:01:08,685][88326] Updated weights for policy 0, policy_version 72242 (0.0009) -[2023-10-09 03:01:08,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 147980288. Throughput: 0: 1683.2, 1: 1686.8. Samples: 37001464. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-09 03:01:08,975][87372] Avg episode reward: [(0, '6.260'), (1, '7.220')] -[2023-10-09 03:01:09,054][88326] Updated weights for policy 0, policy_version 72252 (0.0007) -[2023-10-09 03:01:11,175][88327] Updated weights for policy 1, policy_version 72290 (0.0008) -[2023-10-09 03:01:11,536][88327] Updated weights for policy 1, policy_version 72300 (0.0008) -[2023-10-09 03:01:11,901][88327] Updated weights for policy 1, policy_version 72310 (0.0009) -[2023-10-09 03:01:12,273][88327] Updated weights for policy 1, policy_version 72320 (0.0008) -[2023-10-09 03:01:13,172][88326] Updated weights for policy 0, policy_version 72262 (0.0010) -[2023-10-09 03:01:13,548][88326] Updated weights for policy 0, policy_version 72272 (0.0011) -[2023-10-09 03:01:13,919][88326] Updated weights for policy 0, policy_version 72282 (0.0011) -[2023-10-09 03:01:13,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 148045824. Throughput: 0: 1691.5, 1: 1659.6. Samples: 37021442. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-09 03:01:13,975][87372] Avg episode reward: [(0, '6.190'), (1, '7.640')] -[2023-10-09 03:01:16,268][88327] Updated weights for policy 1, policy_version 72330 (0.0008) -[2023-10-09 03:01:16,640][88327] Updated weights for policy 1, policy_version 72340 (0.0007) -[2023-10-09 03:01:17,003][88327] Updated weights for policy 1, policy_version 72350 (0.0009) -[2023-10-09 03:01:17,776][88326] Updated weights for policy 0, policy_version 72292 (0.0008) -[2023-10-09 03:01:18,149][88326] Updated weights for policy 0, policy_version 72302 (0.0011) -[2023-10-09 03:01:18,503][88326] Updated weights for policy 0, policy_version 72312 (0.0011) -[2023-10-09 03:01:18,974][87372] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 148144128. Throughput: 0: 1675.0, 1: 1681.7. Samples: 37041396. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-09 03:01:18,975][87372] Avg episode reward: [(0, '6.350'), (1, '7.610')] -[2023-10-09 03:01:20,943][88327] Updated weights for policy 1, policy_version 72360 (0.0009) -[2023-10-09 03:01:21,314][88327] Updated weights for policy 1, policy_version 72370 (0.0008) -[2023-10-09 03:01:21,677][88327] Updated weights for policy 1, policy_version 72380 (0.0008) -[2023-10-09 03:01:22,756][88326] Updated weights for policy 0, policy_version 72322 (0.0008) -[2023-10-09 03:01:23,133][88326] Updated weights for policy 0, policy_version 72332 (0.0009) -[2023-10-09 03:01:23,492][88326] Updated weights for policy 0, policy_version 72342 (0.0008) -[2023-10-09 03:01:23,857][88326] Updated weights for policy 0, policy_version 72352 (0.0008) -[2023-10-09 03:01:23,974][87372] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 148209664. Throughput: 0: 1683.4, 1: 1675.6. Samples: 37051844. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-09 03:01:23,975][87372] Avg episode reward: [(0, '6.290'), (1, '7.670')] -[2023-10-09 03:01:25,681][88327] Updated weights for policy 1, policy_version 72390 (0.0009) -[2023-10-09 03:01:26,041][88327] Updated weights for policy 1, policy_version 72400 (0.0008) -[2023-10-09 03:01:26,413][88327] Updated weights for policy 1, policy_version 72410 (0.0007) -[2023-10-09 03:01:27,918][88326] Updated weights for policy 0, policy_version 72362 (0.0010) -[2023-10-09 03:01:28,287][88326] Updated weights for policy 0, policy_version 72372 (0.0011) -[2023-10-09 03:01:28,653][88326] Updated weights for policy 0, policy_version 72382 (0.0011) -[2023-10-09 03:01:28,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 148275200. Throughput: 0: 1683.2, 1: 1675.7. Samples: 37072192. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:01:28,975][87372] Avg episode reward: [(0, '6.740'), (1, '7.140')] -[2023-10-09 03:01:30,517][88327] Updated weights for policy 1, policy_version 72420 (0.0010) -[2023-10-09 03:01:30,887][88327] Updated weights for policy 1, policy_version 72430 (0.0011) -[2023-10-09 03:01:31,261][88327] Updated weights for policy 1, policy_version 72440 (0.0010) -[2023-10-09 03:01:32,884][88326] Updated weights for policy 0, policy_version 72392 (0.0008) -[2023-10-09 03:01:33,243][88326] Updated weights for policy 0, policy_version 72402 (0.0008) -[2023-10-09 03:01:33,620][88326] Updated weights for policy 0, policy_version 72412 (0.0007) -[2023-10-09 03:01:33,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 148340736. Throughput: 0: 1667.2, 1: 1698.5. Samples: 37092400. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:01:33,975][87372] Avg episode reward: [(0, '6.940'), (1, '6.840')] -[2023-10-09 03:01:35,278][88327] Updated weights for policy 1, policy_version 72450 (0.0009) -[2023-10-09 03:01:35,642][88327] Updated weights for policy 1, policy_version 72460 (0.0010) -[2023-10-09 03:01:36,013][88327] Updated weights for policy 1, policy_version 72470 (0.0009) -[2023-10-09 03:01:36,382][88327] Updated weights for policy 1, policy_version 72480 (0.0008) -[2023-10-09 03:01:37,529][88326] Updated weights for policy 0, policy_version 72422 (0.0007) -[2023-10-09 03:01:37,894][88326] Updated weights for policy 0, policy_version 72432 (0.0008) -[2023-10-09 03:01:38,256][88326] Updated weights for policy 0, policy_version 72442 (0.0009) -[2023-10-09 03:01:38,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 148406272. Throughput: 0: 1684.2, 1: 1676.9. Samples: 37102486. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:01:38,974][87372] Avg episode reward: [(0, '6.810'), (1, '7.540')] -[2023-10-09 03:01:40,327][88327] Updated weights for policy 1, policy_version 72490 (0.0010) -[2023-10-09 03:01:40,693][88327] Updated weights for policy 1, policy_version 72500 (0.0013) -[2023-10-09 03:01:41,060][88327] Updated weights for policy 1, policy_version 72510 (0.0009) -[2023-10-09 03:01:42,390][88326] Updated weights for policy 0, policy_version 72452 (0.0008) -[2023-10-09 03:01:42,756][88326] Updated weights for policy 0, policy_version 72462 (0.0007) -[2023-10-09 03:01:43,117][88326] Updated weights for policy 0, policy_version 72472 (0.0007) -[2023-10-09 03:01:43,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 148471808. Throughput: 0: 1684.8, 1: 1686.6. Samples: 37123082. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:01:43,975][87372] Avg episode reward: [(0, '7.250'), (1, '7.820')] -[2023-10-09 03:01:45,180][88327] Updated weights for policy 1, policy_version 72520 (0.0007) -[2023-10-09 03:01:45,553][88327] Updated weights for policy 1, policy_version 72530 (0.0011) -[2023-10-09 03:01:45,923][88327] Updated weights for policy 1, policy_version 72540 (0.0009) -[2023-10-09 03:01:47,126][88326] Updated weights for policy 0, policy_version 72482 (0.0007) -[2023-10-09 03:01:47,491][88326] Updated weights for policy 0, policy_version 72492 (0.0009) -[2023-10-09 03:01:47,867][88326] Updated weights for policy 0, policy_version 72502 (0.0010) -[2023-10-09 03:01:48,231][88326] Updated weights for policy 0, policy_version 72512 (0.0010) -[2023-10-09 03:01:48,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 148537344. Throughput: 0: 1659.1, 1: 1703.0. Samples: 37142530. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:01:48,975][87372] Avg episode reward: [(0, '7.050'), (1, '7.590')] -[2023-10-09 03:01:49,815][88327] Updated weights for policy 1, policy_version 72550 (0.0009) -[2023-10-09 03:01:50,179][88327] Updated weights for policy 1, policy_version 72560 (0.0008) -[2023-10-09 03:01:50,549][88327] Updated weights for policy 1, policy_version 72570 (0.0009) -[2023-10-09 03:01:52,594][88326] Updated weights for policy 0, policy_version 72522 (0.0010) -[2023-10-09 03:01:52,954][88326] Updated weights for policy 0, policy_version 72532 (0.0007) -[2023-10-09 03:01:53,336][88326] Updated weights for policy 0, policy_version 72542 (0.0008) -[2023-10-09 03:01:53,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 148602880. Throughput: 0: 1687.9, 1: 1674.5. Samples: 37152768. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:01:53,974][87372] Avg episode reward: [(0, '7.270'), (1, '7.810')] -[2023-10-09 03:01:54,760][88327] Updated weights for policy 1, policy_version 72580 (0.0009) -[2023-10-09 03:01:55,130][88327] Updated weights for policy 1, policy_version 72590 (0.0008) -[2023-10-09 03:01:55,490][88327] Updated weights for policy 1, policy_version 72600 (0.0009) -[2023-10-09 03:01:57,278][88326] Updated weights for policy 0, policy_version 72552 (0.0009) -[2023-10-09 03:01:57,641][88326] Updated weights for policy 0, policy_version 72562 (0.0008) -[2023-10-09 03:01:58,002][88326] Updated weights for policy 0, policy_version 72572 (0.0009) -[2023-10-09 03:01:58,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 148668416. Throughput: 0: 1675.9, 1: 1702.0. Samples: 37173450. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:01:58,975][87372] Avg episode reward: [(0, '7.300'), (1, '8.220')] -[2023-10-09 03:01:59,418][88327] Updated weights for policy 1, policy_version 72610 (0.0008) -[2023-10-09 03:01:59,796][88327] Updated weights for policy 1, policy_version 72620 (0.0007) -[2023-10-09 03:02:00,162][88327] Updated weights for policy 1, policy_version 72630 (0.0010) -[2023-10-09 03:02:00,527][88327] Updated weights for policy 1, policy_version 72640 (0.0010) -[2023-10-09 03:02:02,018][88326] Updated weights for policy 0, policy_version 72582 (0.0008) -[2023-10-09 03:02:02,379][88326] Updated weights for policy 0, policy_version 72592 (0.0007) -[2023-10-09 03:02:02,756][88326] Updated weights for policy 0, policy_version 72602 (0.0009) -[2023-10-09 03:02:03,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 148733952. Throughput: 0: 1667.0, 1: 1704.1. Samples: 37193096. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:02:03,975][87372] Avg episode reward: [(0, '6.410'), (1, '8.180')] -[2023-10-09 03:02:04,757][88327] Updated weights for policy 1, policy_version 72650 (0.0008) -[2023-10-09 03:02:05,128][88327] Updated weights for policy 1, policy_version 72660 (0.0009) -[2023-10-09 03:02:05,494][88327] Updated weights for policy 1, policy_version 72670 (0.0009) -[2023-10-09 03:02:06,670][88326] Updated weights for policy 0, policy_version 72612 (0.0010) -[2023-10-09 03:02:07,049][88326] Updated weights for policy 0, policy_version 72622 (0.0008) -[2023-10-09 03:02:07,418][88326] Updated weights for policy 0, policy_version 72632 (0.0007) -[2023-10-09 03:02:08,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 148799488. Throughput: 0: 1687.2, 1: 1681.4. Samples: 37203428. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:02:08,974][87372] Avg episode reward: [(0, '6.930'), (1, '7.470')] -[2023-10-09 03:02:09,587][88327] Updated weights for policy 1, policy_version 72680 (0.0008) -[2023-10-09 03:02:09,939][88327] Updated weights for policy 1, policy_version 72690 (0.0010) -[2023-10-09 03:02:10,306][88327] Updated weights for policy 1, policy_version 72700 (0.0009) -[2023-10-09 03:02:11,352][88326] Updated weights for policy 0, policy_version 72642 (0.0008) -[2023-10-09 03:02:11,716][88326] Updated weights for policy 0, policy_version 72652 (0.0011) -[2023-10-09 03:02:12,081][88326] Updated weights for policy 0, policy_version 72662 (0.0009) -[2023-10-09 03:02:12,456][88326] Updated weights for policy 0, policy_version 72672 (0.0010) -[2023-10-09 03:02:13,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 148865024. Throughput: 0: 1665.2, 1: 1694.0. Samples: 37223358. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:02:13,975][87372] Avg episode reward: [(0, '6.570'), (1, '7.740')] -[2023-10-09 03:02:14,445][88327] Updated weights for policy 1, policy_version 72710 (0.0009) -[2023-10-09 03:02:14,812][88327] Updated weights for policy 1, policy_version 72720 (0.0007) -[2023-10-09 03:02:15,168][88327] Updated weights for policy 1, policy_version 72730 (0.0008) -[2023-10-09 03:02:16,529][88326] Updated weights for policy 0, policy_version 72682 (0.0008) -[2023-10-09 03:02:16,895][88326] Updated weights for policy 0, policy_version 72692 (0.0007) -[2023-10-09 03:02:17,268][88326] Updated weights for policy 0, policy_version 72702 (0.0007) -[2023-10-09 03:02:18,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 148930560. Throughput: 0: 1677.1, 1: 1692.4. Samples: 37244024. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-09 03:02:18,975][87372] Avg episode reward: [(0, '6.430'), (1, '7.700')] -[2023-10-09 03:02:19,225][88327] Updated weights for policy 1, policy_version 72740 (0.0008) -[2023-10-09 03:02:19,601][88327] Updated weights for policy 1, policy_version 72750 (0.0007) -[2023-10-09 03:02:19,967][88327] Updated weights for policy 1, policy_version 72760 (0.0009) -[2023-10-09 03:02:21,552][88326] Updated weights for policy 0, policy_version 72712 (0.0007) -[2023-10-09 03:02:21,911][88326] Updated weights for policy 0, policy_version 72722 (0.0009) -[2023-10-09 03:02:22,280][88326] Updated weights for policy 0, policy_version 72732 (0.0009) -[2023-10-09 03:02:23,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 148996096. Throughput: 0: 1689.9, 1: 1683.4. Samples: 37254286. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-09 03:02:23,975][87372] Avg episode reward: [(0, '7.150'), (1, '7.470')] -[2023-10-09 03:02:24,048][88327] Updated weights for policy 1, policy_version 72770 (0.0007) -[2023-10-09 03:02:24,412][88327] Updated weights for policy 1, policy_version 72780 (0.0007) -[2023-10-09 03:02:24,783][88327] Updated weights for policy 1, policy_version 72790 (0.0009) -[2023-10-09 03:02:25,151][88327] Updated weights for policy 1, policy_version 72800 (0.0008) -[2023-10-09 03:02:26,374][88326] Updated weights for policy 0, policy_version 72742 (0.0009) -[2023-10-09 03:02:26,745][88326] Updated weights for policy 0, policy_version 72752 (0.0007) -[2023-10-09 03:02:27,125][88326] Updated weights for policy 0, policy_version 72762 (0.0008) -[2023-10-09 03:02:28,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 149061632. Throughput: 0: 1666.8, 1: 1690.3. Samples: 37274150. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-09 03:02:28,974][87372] Avg episode reward: [(0, '6.550'), (1, '7.560')] -[2023-10-09 03:02:28,983][88327] Updated weights for policy 1, policy_version 72810 (0.0011) -[2023-10-09 03:02:29,352][88327] Updated weights for policy 1, policy_version 72820 (0.0010) -[2023-10-09 03:02:29,714][88327] Updated weights for policy 1, policy_version 72830 (0.0007) -[2023-10-09 03:02:31,134][88326] Updated weights for policy 0, policy_version 72772 (0.0008) -[2023-10-09 03:02:31,506][88326] Updated weights for policy 0, policy_version 72782 (0.0009) -[2023-10-09 03:02:31,883][88326] Updated weights for policy 0, policy_version 72792 (0.0007) -[2023-10-09 03:02:33,748][88327] Updated weights for policy 1, policy_version 72840 (0.0010) -[2023-10-09 03:02:33,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 149127168. Throughput: 0: 1686.7, 1: 1701.3. Samples: 37294988. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-09 03:02:33,975][87372] Avg episode reward: [(0, '6.570'), (1, '7.150')] -[2023-10-09 03:02:33,982][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000072800_74547200.pth... -[2023-10-09 03:02:34,014][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000071232_72941568.pth -[2023-10-09 03:02:34,116][88327] Updated weights for policy 1, policy_version 72850 (0.0011) -[2023-10-09 03:02:34,480][88327] Updated weights for policy 1, policy_version 72860 (0.0011) -[2023-10-09 03:02:34,622][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000072864_74612736.pth... -[2023-10-09 03:02:34,662][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000071264_72974336.pth -[2023-10-09 03:02:35,923][88326] Updated weights for policy 0, policy_version 72802 (0.0010) -[2023-10-09 03:02:36,292][88326] Updated weights for policy 0, policy_version 72812 (0.0008) -[2023-10-09 03:02:36,659][88326] Updated weights for policy 0, policy_version 72822 (0.0009) -[2023-10-09 03:02:37,031][88326] Updated weights for policy 0, policy_version 72832 (0.0008) -[2023-10-09 03:02:38,325][88327] Updated weights for policy 1, policy_version 72870 (0.0009) -[2023-10-09 03:02:38,694][88327] Updated weights for policy 1, policy_version 72880 (0.0007) -[2023-10-09 03:02:38,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 149192704. Throughput: 0: 1678.9, 1: 1701.0. Samples: 37304866. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-09 03:02:38,975][87372] Avg episode reward: [(0, '6.760'), (1, '7.150')] -[2023-10-09 03:02:39,056][88327] Updated weights for policy 1, policy_version 72890 (0.0009) -[2023-10-09 03:02:40,994][88326] Updated weights for policy 0, policy_version 72842 (0.0008) -[2023-10-09 03:02:41,354][88326] Updated weights for policy 0, policy_version 72852 (0.0008) -[2023-10-09 03:02:41,726][88326] Updated weights for policy 0, policy_version 72862 (0.0009) -[2023-10-09 03:02:42,943][88327] Updated weights for policy 1, policy_version 72900 (0.0008) -[2023-10-09 03:02:43,310][88327] Updated weights for policy 1, policy_version 72910 (0.0008) -[2023-10-09 03:02:43,674][88327] Updated weights for policy 1, policy_version 72920 (0.0008) -[2023-10-09 03:02:43,974][87372] Fps is (10 sec: 16383.8, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 149291008. Throughput: 0: 1669.4, 1: 1701.1. Samples: 37325120. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-09 03:02:43,975][87372] Avg episode reward: [(0, '6.250'), (1, '7.260')] -[2023-10-09 03:02:45,654][88326] Updated weights for policy 0, policy_version 72872 (0.0010) -[2023-10-09 03:02:46,028][88326] Updated weights for policy 0, policy_version 72882 (0.0009) -[2023-10-09 03:02:46,401][88326] Updated weights for policy 0, policy_version 72892 (0.0009) -[2023-10-09 03:02:47,735][88327] Updated weights for policy 1, policy_version 72930 (0.0007) -[2023-10-09 03:02:48,095][88327] Updated weights for policy 1, policy_version 72940 (0.0008) -[2023-10-09 03:02:48,458][88327] Updated weights for policy 1, policy_version 72950 (0.0008) -[2023-10-09 03:02:48,823][88327] Updated weights for policy 1, policy_version 72960 (0.0007) -[2023-10-09 03:02:48,974][87372] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 149356544. Throughput: 0: 1696.4, 1: 1698.0. Samples: 37345844. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-09 03:02:48,975][87372] Avg episode reward: [(0, '6.800'), (1, '7.060')] -[2023-10-09 03:02:50,436][88326] Updated weights for policy 0, policy_version 72902 (0.0008) -[2023-10-09 03:02:50,802][88326] Updated weights for policy 0, policy_version 72912 (0.0008) -[2023-10-09 03:02:51,172][88326] Updated weights for policy 0, policy_version 72922 (0.0008) -[2023-10-09 03:02:52,826][88327] Updated weights for policy 1, policy_version 72970 (0.0010) -[2023-10-09 03:02:53,194][88327] Updated weights for policy 1, policy_version 72980 (0.0008) -[2023-10-09 03:02:53,566][88327] Updated weights for policy 1, policy_version 72990 (0.0009) -[2023-10-09 03:02:53,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 149422080. Throughput: 0: 1672.3, 1: 1712.6. Samples: 37355748. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-09 03:02:53,975][87372] Avg episode reward: [(0, '7.370'), (1, '7.240')] -[2023-10-09 03:02:55,207][88326] Updated weights for policy 0, policy_version 72932 (0.0008) -[2023-10-09 03:02:55,568][88326] Updated weights for policy 0, policy_version 72942 (0.0010) -[2023-10-09 03:02:55,946][88326] Updated weights for policy 0, policy_version 72952 (0.0010) -[2023-10-09 03:02:57,530][88327] Updated weights for policy 1, policy_version 73000 (0.0008) -[2023-10-09 03:02:57,901][88327] Updated weights for policy 1, policy_version 73010 (0.0008) -[2023-10-09 03:02:58,268][88327] Updated weights for policy 1, policy_version 73020 (0.0007) -[2023-10-09 03:02:58,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 149487616. Throughput: 0: 1691.1, 1: 1712.2. Samples: 37376506. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-09 03:02:58,975][87372] Avg episode reward: [(0, '6.840'), (1, '7.840')] -[2023-10-09 03:03:00,045][88326] Updated weights for policy 0, policy_version 72962 (0.0009) -[2023-10-09 03:03:00,411][88326] Updated weights for policy 0, policy_version 72972 (0.0009) -[2023-10-09 03:03:00,777][88326] Updated weights for policy 0, policy_version 72982 (0.0009) -[2023-10-09 03:03:01,143][88326] Updated weights for policy 0, policy_version 72992 (0.0011) -[2023-10-09 03:03:02,379][88327] Updated weights for policy 1, policy_version 73030 (0.0008) -[2023-10-09 03:03:02,743][88327] Updated weights for policy 1, policy_version 73040 (0.0009) -[2023-10-09 03:03:03,104][88327] Updated weights for policy 1, policy_version 73050 (0.0008) -[2023-10-09 03:03:03,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 149553152. Throughput: 0: 1698.4, 1: 1688.6. Samples: 37396436. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-09 03:03:03,975][87372] Avg episode reward: [(0, '6.720'), (1, '7.690')] -[2023-10-09 03:03:05,052][88326] Updated weights for policy 0, policy_version 73002 (0.0007) -[2023-10-09 03:03:05,424][88326] Updated weights for policy 0, policy_version 73012 (0.0007) -[2023-10-09 03:03:05,794][88326] Updated weights for policy 0, policy_version 73022 (0.0008) -[2023-10-09 03:03:07,009][88327] Updated weights for policy 1, policy_version 73060 (0.0010) -[2023-10-09 03:03:07,372][88327] Updated weights for policy 1, policy_version 73070 (0.0012) -[2023-10-09 03:03:07,742][88327] Updated weights for policy 1, policy_version 73080 (0.0007) -[2023-10-09 03:03:08,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 149618688. Throughput: 0: 1670.2, 1: 1719.0. Samples: 37406802. Policy #0 lag: (min: 25.0, avg: 32.2, max: 57.0) -[2023-10-09 03:03:08,975][87372] Avg episode reward: [(0, '6.760'), (1, '7.500')] -[2023-10-09 03:03:09,759][88326] Updated weights for policy 0, policy_version 73032 (0.0010) -[2023-10-09 03:03:10,118][88326] Updated weights for policy 0, policy_version 73042 (0.0009) -[2023-10-09 03:03:10,493][88326] Updated weights for policy 0, policy_version 73052 (0.0007) -[2023-10-09 03:03:11,884][88327] Updated weights for policy 1, policy_version 73090 (0.0009) -[2023-10-09 03:03:12,246][88327] Updated weights for policy 1, policy_version 73100 (0.0008) -[2023-10-09 03:03:12,618][88327] Updated weights for policy 1, policy_version 73110 (0.0010) -[2023-10-09 03:03:12,983][88327] Updated weights for policy 1, policy_version 73120 (0.0007) -[2023-10-09 03:03:13,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 149684224. Throughput: 0: 1696.5, 1: 1709.3. Samples: 37427414. Policy #0 lag: (min: 25.0, avg: 32.2, max: 57.0) -[2023-10-09 03:03:13,975][87372] Avg episode reward: [(0, '6.290'), (1, '7.770')] -[2023-10-09 03:03:14,453][88326] Updated weights for policy 0, policy_version 73062 (0.0008) -[2023-10-09 03:03:14,827][88326] Updated weights for policy 0, policy_version 73072 (0.0009) -[2023-10-09 03:03:15,195][88326] Updated weights for policy 0, policy_version 73082 (0.0007) -[2023-10-09 03:03:16,917][88327] Updated weights for policy 1, policy_version 73130 (0.0007) -[2023-10-09 03:03:17,281][88327] Updated weights for policy 1, policy_version 73140 (0.0007) -[2023-10-09 03:03:17,649][88327] Updated weights for policy 1, policy_version 73150 (0.0007) -[2023-10-09 03:03:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 149749760. Throughput: 0: 1704.9, 1: 1685.5. Samples: 37447554. Policy #0 lag: (min: 25.0, avg: 32.2, max: 57.0) -[2023-10-09 03:03:18,975][87372] Avg episode reward: [(0, '6.320'), (1, '7.110')] -[2023-10-09 03:03:19,351][88326] Updated weights for policy 0, policy_version 73092 (0.0008) -[2023-10-09 03:03:19,724][88326] Updated weights for policy 0, policy_version 73102 (0.0008) -[2023-10-09 03:03:20,099][88326] Updated weights for policy 0, policy_version 73112 (0.0007) -[2023-10-09 03:03:21,730][88327] Updated weights for policy 1, policy_version 73160 (0.0008) -[2023-10-09 03:03:22,102][88327] Updated weights for policy 1, policy_version 73170 (0.0008) -[2023-10-09 03:03:22,461][88327] Updated weights for policy 1, policy_version 73180 (0.0010) -[2023-10-09 03:03:23,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 149815296. Throughput: 0: 1681.3, 1: 1719.9. Samples: 37457920. Policy #0 lag: (min: 25.0, avg: 32.2, max: 57.0) -[2023-10-09 03:03:23,975][87372] Avg episode reward: [(0, '6.480'), (1, '6.860')] -[2023-10-09 03:03:24,069][88326] Updated weights for policy 0, policy_version 73122 (0.0008) -[2023-10-09 03:03:24,440][88326] Updated weights for policy 0, policy_version 73132 (0.0007) -[2023-10-09 03:03:24,812][88326] Updated weights for policy 0, policy_version 73142 (0.0009) -[2023-10-09 03:03:25,181][88326] Updated weights for policy 0, policy_version 73152 (0.0007) -[2023-10-09 03:03:26,458][88327] Updated weights for policy 1, policy_version 73190 (0.0008) -[2023-10-09 03:03:26,825][88327] Updated weights for policy 1, policy_version 73200 (0.0007) -[2023-10-09 03:03:27,187][88327] Updated weights for policy 1, policy_version 73210 (0.0007) -[2023-10-09 03:03:28,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 149880832. Throughput: 0: 1704.1, 1: 1694.7. Samples: 37478064. Policy #0 lag: (min: 25.0, avg: 32.2, max: 57.0) -[2023-10-09 03:03:28,975][87372] Avg episode reward: [(0, '6.550'), (1, '7.010')] -[2023-10-09 03:03:29,179][88326] Updated weights for policy 0, policy_version 73162 (0.0010) -[2023-10-09 03:03:29,544][88326] Updated weights for policy 0, policy_version 73172 (0.0010) -[2023-10-09 03:03:29,925][88326] Updated weights for policy 0, policy_version 73182 (0.0011) -[2023-10-09 03:03:31,100][88327] Updated weights for policy 1, policy_version 73220 (0.0008) -[2023-10-09 03:03:31,479][88327] Updated weights for policy 1, policy_version 73230 (0.0007) -[2023-10-09 03:03:31,837][88327] Updated weights for policy 1, policy_version 73240 (0.0007) -[2023-10-09 03:03:33,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 149946368. Throughput: 0: 1699.4, 1: 1696.3. Samples: 37498650. Policy #0 lag: (min: 25.0, avg: 32.2, max: 57.0) -[2023-10-09 03:03:33,975][87372] Avg episode reward: [(0, '6.390'), (1, '6.900')] -[2023-10-09 03:03:34,087][88326] Updated weights for policy 0, policy_version 73192 (0.0007) -[2023-10-09 03:03:34,456][88326] Updated weights for policy 0, policy_version 73202 (0.0007) -[2023-10-09 03:03:34,828][88326] Updated weights for policy 0, policy_version 73212 (0.0008) -[2023-10-09 03:03:35,998][88327] Updated weights for policy 1, policy_version 73250 (0.0007) -[2023-10-09 03:03:36,370][88327] Updated weights for policy 1, policy_version 73260 (0.0008) -[2023-10-09 03:03:36,735][88327] Updated weights for policy 1, policy_version 73270 (0.0007) -[2023-10-09 03:03:37,101][88327] Updated weights for policy 1, policy_version 73280 (0.0009) -[2023-10-09 03:03:38,884][88326] Updated weights for policy 0, policy_version 73222 (0.0009) -[2023-10-09 03:03:38,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 150011904. Throughput: 0: 1694.2, 1: 1704.3. Samples: 37508680. Policy #0 lag: (min: 25.0, avg: 32.2, max: 57.0) -[2023-10-09 03:03:38,975][87372] Avg episode reward: [(0, '6.610'), (1, '6.920')] -[2023-10-09 03:03:39,256][88326] Updated weights for policy 0, policy_version 73232 (0.0010) -[2023-10-09 03:03:39,626][88326] Updated weights for policy 0, policy_version 73242 (0.0009) -[2023-10-09 03:03:41,077][88327] Updated weights for policy 1, policy_version 73290 (0.0010) -[2023-10-09 03:03:41,450][88327] Updated weights for policy 1, policy_version 73300 (0.0010) -[2023-10-09 03:03:41,812][88327] Updated weights for policy 1, policy_version 73310 (0.0009) -[2023-10-09 03:03:43,744][88326] Updated weights for policy 0, policy_version 73252 (0.0010) -[2023-10-09 03:03:43,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 150077440. Throughput: 0: 1698.7, 1: 1677.6. Samples: 37528440. Policy #0 lag: (min: 25.0, avg: 32.2, max: 57.0) -[2023-10-09 03:03:43,975][87372] Avg episode reward: [(0, '6.710'), (1, '7.310')] -[2023-10-09 03:03:44,108][88326] Updated weights for policy 0, policy_version 73262 (0.0008) -[2023-10-09 03:03:44,476][88326] Updated weights for policy 0, policy_version 73272 (0.0008) -[2023-10-09 03:03:45,926][88327] Updated weights for policy 1, policy_version 73320 (0.0008) -[2023-10-09 03:03:46,294][88327] Updated weights for policy 1, policy_version 73330 (0.0008) -[2023-10-09 03:03:46,668][88327] Updated weights for policy 1, policy_version 73340 (0.0009) -[2023-10-09 03:03:48,695][88326] Updated weights for policy 0, policy_version 73282 (0.0008) -[2023-10-09 03:03:48,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 150142976. Throughput: 0: 1696.1, 1: 1695.9. Samples: 37549076. Policy #0 lag: (min: 25.0, avg: 32.2, max: 57.0) -[2023-10-09 03:03:48,975][87372] Avg episode reward: [(0, '6.720'), (1, '7.140')] -[2023-10-09 03:03:49,061][88326] Updated weights for policy 0, policy_version 73292 (0.0010) -[2023-10-09 03:03:49,431][88326] Updated weights for policy 0, policy_version 73302 (0.0009) -[2023-10-09 03:03:49,795][88326] Updated weights for policy 0, policy_version 73312 (0.0011) -[2023-10-09 03:03:50,656][88327] Updated weights for policy 1, policy_version 73350 (0.0008) -[2023-10-09 03:03:51,021][88327] Updated weights for policy 1, policy_version 73360 (0.0008) -[2023-10-09 03:03:51,375][88327] Updated weights for policy 1, policy_version 73370 (0.0009) -[2023-10-09 03:03:53,775][88326] Updated weights for policy 0, policy_version 73322 (0.0008) -[2023-10-09 03:03:53,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 150208512. Throughput: 0: 1696.7, 1: 1682.0. Samples: 37558844. Policy #0 lag: (min: 25.0, avg: 32.2, max: 57.0) -[2023-10-09 03:03:53,975][87372] Avg episode reward: [(0, '6.830'), (1, '7.680')] -[2023-10-09 03:03:54,139][88326] Updated weights for policy 0, policy_version 73332 (0.0010) -[2023-10-09 03:03:54,520][88326] Updated weights for policy 0, policy_version 73342 (0.0011) -[2023-10-09 03:03:55,386][88327] Updated weights for policy 1, policy_version 73380 (0.0009) -[2023-10-09 03:03:55,742][88327] Updated weights for policy 1, policy_version 73390 (0.0011) -[2023-10-09 03:03:56,111][88327] Updated weights for policy 1, policy_version 73400 (0.0008) -[2023-10-09 03:03:58,445][88326] Updated weights for policy 0, policy_version 73352 (0.0008) -[2023-10-09 03:03:58,814][88326] Updated weights for policy 0, policy_version 73362 (0.0010) -[2023-10-09 03:03:58,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 150274048. Throughput: 0: 1698.6, 1: 1684.0. Samples: 37579630. Policy #0 lag: (min: 8.0, avg: 28.5, max: 40.0) -[2023-10-09 03:03:58,974][87372] Avg episode reward: [(0, '6.610'), (1, '8.160')] -[2023-10-09 03:03:59,179][88326] Updated weights for policy 0, policy_version 73372 (0.0010) -[2023-10-09 03:04:00,081][88327] Updated weights for policy 1, policy_version 73410 (0.0008) -[2023-10-09 03:04:00,445][88327] Updated weights for policy 1, policy_version 73420 (0.0009) -[2023-10-09 03:04:00,808][88327] Updated weights for policy 1, policy_version 73430 (0.0010) -[2023-10-09 03:04:01,168][88327] Updated weights for policy 1, policy_version 73440 (0.0011) -[2023-10-09 03:04:03,171][88326] Updated weights for policy 0, policy_version 73382 (0.0008) -[2023-10-09 03:04:03,541][88326] Updated weights for policy 0, policy_version 73392 (0.0007) -[2023-10-09 03:04:03,911][88326] Updated weights for policy 0, policy_version 73402 (0.0009) -[2023-10-09 03:04:03,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 150339584. Throughput: 0: 1692.9, 1: 1705.9. Samples: 37600498. Policy #0 lag: (min: 8.0, avg: 28.5, max: 40.0) -[2023-10-09 03:04:03,974][87372] Avg episode reward: [(0, '6.940'), (1, '8.250')] -[2023-10-09 03:04:05,034][88327] Updated weights for policy 1, policy_version 73450 (0.0008) -[2023-10-09 03:04:05,396][88327] Updated weights for policy 1, policy_version 73460 (0.0009) -[2023-10-09 03:04:05,757][88327] Updated weights for policy 1, policy_version 73470 (0.0011) -[2023-10-09 03:04:08,018][88326] Updated weights for policy 0, policy_version 73412 (0.0009) -[2023-10-09 03:04:08,377][88326] Updated weights for policy 0, policy_version 73422 (0.0008) -[2023-10-09 03:04:08,750][88326] Updated weights for policy 0, policy_version 73432 (0.0008) -[2023-10-09 03:04:08,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 150405120. Throughput: 0: 1706.0, 1: 1674.0. Samples: 37610020. Policy #0 lag: (min: 8.0, avg: 28.5, max: 40.0) -[2023-10-09 03:04:08,975][87372] Avg episode reward: [(0, '7.190'), (1, '7.910')] -[2023-10-09 03:04:09,999][88327] Updated weights for policy 1, policy_version 73480 (0.0008) -[2023-10-09 03:04:10,363][88327] Updated weights for policy 1, policy_version 73490 (0.0009) -[2023-10-09 03:04:10,724][88327] Updated weights for policy 1, policy_version 73500 (0.0011) -[2023-10-09 03:04:12,738][88326] Updated weights for policy 0, policy_version 73442 (0.0008) -[2023-10-09 03:04:13,102][88326] Updated weights for policy 0, policy_version 73452 (0.0007) -[2023-10-09 03:04:13,460][88326] Updated weights for policy 0, policy_version 73462 (0.0007) -[2023-10-09 03:04:13,832][88326] Updated weights for policy 0, policy_version 73472 (0.0008) -[2023-10-09 03:04:13,974][87372] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 150503424. Throughput: 0: 1701.9, 1: 1689.3. Samples: 37630668. Policy #0 lag: (min: 8.0, avg: 28.5, max: 40.0) -[2023-10-09 03:04:13,975][87372] Avg episode reward: [(0, '6.470'), (1, '7.440')] -[2023-10-09 03:04:14,878][88327] Updated weights for policy 1, policy_version 73510 (0.0009) -[2023-10-09 03:04:15,268][88327] Updated weights for policy 1, policy_version 73520 (0.0010) -[2023-10-09 03:04:15,637][88327] Updated weights for policy 1, policy_version 73530 (0.0007) -[2023-10-09 03:04:17,703][88326] Updated weights for policy 0, policy_version 73482 (0.0009) -[2023-10-09 03:04:18,076][88326] Updated weights for policy 0, policy_version 73492 (0.0008) -[2023-10-09 03:04:18,441][88326] Updated weights for policy 0, policy_version 73502 (0.0009) -[2023-10-09 03:04:18,974][87372] Fps is (10 sec: 16383.8, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 150568960. Throughput: 0: 1684.5, 1: 1693.6. Samples: 37650666. Policy #0 lag: (min: 8.0, avg: 28.5, max: 40.0) -[2023-10-09 03:04:18,975][87372] Avg episode reward: [(0, '6.380'), (1, '7.520')] -[2023-10-09 03:04:19,689][88327] Updated weights for policy 1, policy_version 73540 (0.0007) -[2023-10-09 03:04:20,056][88327] Updated weights for policy 1, policy_version 73550 (0.0009) -[2023-10-09 03:04:20,422][88327] Updated weights for policy 1, policy_version 73560 (0.0009) -[2023-10-09 03:04:22,722][88326] Updated weights for policy 0, policy_version 73512 (0.0009) -[2023-10-09 03:04:23,105][88326] Updated weights for policy 0, policy_version 73522 (0.0009) -[2023-10-09 03:04:23,474][88326] Updated weights for policy 0, policy_version 73532 (0.0010) -[2023-10-09 03:04:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 150634496. Throughput: 0: 1705.5, 1: 1672.0. Samples: 37660668. Policy #0 lag: (min: 8.0, avg: 28.5, max: 40.0) -[2023-10-09 03:04:23,975][87372] Avg episode reward: [(0, '6.550'), (1, '7.510')] -[2023-10-09 03:04:24,439][88327] Updated weights for policy 1, policy_version 73570 (0.0008) -[2023-10-09 03:04:24,813][88327] Updated weights for policy 1, policy_version 73580 (0.0008) -[2023-10-09 03:04:25,168][88327] Updated weights for policy 1, policy_version 73590 (0.0009) -[2023-10-09 03:04:25,530][88327] Updated weights for policy 1, policy_version 73600 (0.0009) -[2023-10-09 03:04:27,493][88326] Updated weights for policy 0, policy_version 73542 (0.0010) -[2023-10-09 03:04:27,864][88326] Updated weights for policy 0, policy_version 73552 (0.0010) -[2023-10-09 03:04:28,223][88326] Updated weights for policy 0, policy_version 73562 (0.0009) -[2023-10-09 03:04:28,974][87372] Fps is (10 sec: 13107.6, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 150700032. Throughput: 0: 1698.2, 1: 1703.2. Samples: 37681500. Policy #0 lag: (min: 8.0, avg: 28.5, max: 40.0) -[2023-10-09 03:04:28,974][87372] Avg episode reward: [(0, '6.860'), (1, '7.060')] -[2023-10-09 03:04:29,500][88327] Updated weights for policy 1, policy_version 73610 (0.0010) -[2023-10-09 03:04:29,878][88327] Updated weights for policy 1, policy_version 73620 (0.0011) -[2023-10-09 03:04:30,240][88327] Updated weights for policy 1, policy_version 73630 (0.0010) -[2023-10-09 03:04:32,290][88326] Updated weights for policy 0, policy_version 73572 (0.0007) -[2023-10-09 03:04:32,641][88326] Updated weights for policy 0, policy_version 73582 (0.0007) -[2023-10-09 03:04:33,009][88326] Updated weights for policy 0, policy_version 73592 (0.0007) -[2023-10-09 03:04:33,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 150765568. Throughput: 0: 1674.2, 1: 1708.7. Samples: 37701304. Policy #0 lag: (min: 8.0, avg: 28.5, max: 40.0) -[2023-10-09 03:04:33,975][87372] Avg episode reward: [(0, '7.060'), (1, '7.520')] -[2023-10-09 03:04:33,984][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000073600_75366400.pth... -[2023-10-09 03:04:34,019][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000072032_73760768.pth -[2023-10-09 03:04:34,154][88327] Updated weights for policy 1, policy_version 73640 (0.0009) -[2023-10-09 03:04:34,526][88327] Updated weights for policy 1, policy_version 73650 (0.0011) -[2023-10-09 03:04:34,888][88327] Updated weights for policy 1, policy_version 73660 (0.0008) -[2023-10-09 03:04:35,033][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000073664_75431936.pth... -[2023-10-09 03:04:35,062][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000072064_73793536.pth -[2023-10-09 03:04:36,929][88326] Updated weights for policy 0, policy_version 73602 (0.0008) -[2023-10-09 03:04:37,305][88326] Updated weights for policy 0, policy_version 73612 (0.0010) -[2023-10-09 03:04:37,677][88326] Updated weights for policy 0, policy_version 73622 (0.0010) -[2023-10-09 03:04:38,041][88326] Updated weights for policy 0, policy_version 73632 (0.0010) -[2023-10-09 03:04:38,951][88327] Updated weights for policy 1, policy_version 73670 (0.0010) -[2023-10-09 03:04:38,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 150831104. Throughput: 0: 1701.4, 1: 1693.0. Samples: 37711590. Policy #0 lag: (min: 8.0, avg: 28.5, max: 40.0) -[2023-10-09 03:04:38,975][87372] Avg episode reward: [(0, '7.060'), (1, '7.850')] -[2023-10-09 03:04:39,319][88327] Updated weights for policy 1, policy_version 73680 (0.0007) -[2023-10-09 03:04:39,684][88327] Updated weights for policy 1, policy_version 73690 (0.0008) -[2023-10-09 03:04:41,946][88326] Updated weights for policy 0, policy_version 73642 (0.0011) -[2023-10-09 03:04:42,310][88326] Updated weights for policy 0, policy_version 73652 (0.0011) -[2023-10-09 03:04:42,677][88326] Updated weights for policy 0, policy_version 73662 (0.0011) -[2023-10-09 03:04:43,689][88327] Updated weights for policy 1, policy_version 73700 (0.0009) -[2023-10-09 03:04:43,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 150896640. Throughput: 0: 1683.4, 1: 1700.7. Samples: 37731916. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 03:04:43,974][87372] Avg episode reward: [(0, '7.380'), (1, '6.960')] -[2023-10-09 03:04:44,054][88327] Updated weights for policy 1, policy_version 73710 (0.0010) -[2023-10-09 03:04:44,421][88327] Updated weights for policy 1, policy_version 73720 (0.0010) -[2023-10-09 03:04:46,800][88326] Updated weights for policy 0, policy_version 73672 (0.0009) -[2023-10-09 03:04:47,163][88326] Updated weights for policy 0, policy_version 73682 (0.0010) -[2023-10-09 03:04:47,532][88326] Updated weights for policy 0, policy_version 73692 (0.0010) -[2023-10-09 03:04:48,580][88327] Updated weights for policy 1, policy_version 73730 (0.0010) -[2023-10-09 03:04:48,942][88327] Updated weights for policy 1, policy_version 73740 (0.0007) -[2023-10-09 03:04:48,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 150962176. Throughput: 0: 1671.6, 1: 1698.9. Samples: 37752174. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 03:04:48,975][87372] Avg episode reward: [(0, '7.300'), (1, '6.760')] -[2023-10-09 03:04:49,309][88327] Updated weights for policy 1, policy_version 73750 (0.0011) -[2023-10-09 03:04:49,663][88327] Updated weights for policy 1, policy_version 73760 (0.0010) -[2023-10-09 03:04:51,694][88326] Updated weights for policy 0, policy_version 73702 (0.0009) -[2023-10-09 03:04:52,056][88326] Updated weights for policy 0, policy_version 73712 (0.0007) -[2023-10-09 03:04:52,425][88326] Updated weights for policy 0, policy_version 73722 (0.0007) -[2023-10-09 03:04:53,622][88327] Updated weights for policy 1, policy_version 73770 (0.0007) -[2023-10-09 03:04:53,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 151027712. Throughput: 0: 1690.7, 1: 1697.1. Samples: 37762468. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 03:04:53,975][87372] Avg episode reward: [(0, '6.850'), (1, '7.340')] -[2023-10-09 03:04:53,989][88327] Updated weights for policy 1, policy_version 73780 (0.0010) -[2023-10-09 03:04:54,363][88327] Updated weights for policy 1, policy_version 73790 (0.0010) -[2023-10-09 03:04:56,416][88326] Updated weights for policy 0, policy_version 73732 (0.0007) -[2023-10-09 03:04:56,781][88326] Updated weights for policy 0, policy_version 73742 (0.0010) -[2023-10-09 03:04:57,143][88326] Updated weights for policy 0, policy_version 73752 (0.0008) -[2023-10-09 03:04:58,540][88327] Updated weights for policy 1, policy_version 73800 (0.0009) -[2023-10-09 03:04:58,903][88327] Updated weights for policy 1, policy_version 73810 (0.0009) -[2023-10-09 03:04:58,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 151093248. Throughput: 0: 1668.5, 1: 1704.6. Samples: 37782458. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 03:04:58,974][87372] Avg episode reward: [(0, '6.930'), (1, '6.970')] -[2023-10-09 03:04:59,258][88327] Updated weights for policy 1, policy_version 73820 (0.0008) -[2023-10-09 03:05:01,109][88326] Updated weights for policy 0, policy_version 73762 (0.0007) -[2023-10-09 03:05:01,469][88326] Updated weights for policy 0, policy_version 73772 (0.0007) -[2023-10-09 03:05:01,846][88326] Updated weights for policy 0, policy_version 73782 (0.0009) -[2023-10-09 03:05:02,217][88326] Updated weights for policy 0, policy_version 73792 (0.0008) -[2023-10-09 03:05:03,309][88327] Updated weights for policy 1, policy_version 73830 (0.0007) -[2023-10-09 03:05:03,694][88327] Updated weights for policy 1, policy_version 73840 (0.0008) -[2023-10-09 03:05:03,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 151158784. Throughput: 0: 1685.2, 1: 1702.9. Samples: 37803128. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 03:05:03,975][87372] Avg episode reward: [(0, '6.560'), (1, '7.060')] -[2023-10-09 03:05:04,056][88327] Updated weights for policy 1, policy_version 73850 (0.0011) -[2023-10-09 03:05:06,293][88326] Updated weights for policy 0, policy_version 73802 (0.0011) -[2023-10-09 03:05:06,657][88326] Updated weights for policy 0, policy_version 73812 (0.0008) -[2023-10-09 03:05:07,044][88326] Updated weights for policy 0, policy_version 73822 (0.0008) -[2023-10-09 03:05:08,051][88327] Updated weights for policy 1, policy_version 73860 (0.0010) -[2023-10-09 03:05:08,404][88327] Updated weights for policy 1, policy_version 73870 (0.0008) -[2023-10-09 03:05:08,778][88327] Updated weights for policy 1, policy_version 73880 (0.0011) -[2023-10-09 03:05:08,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 151224320. Throughput: 0: 1686.7, 1: 1702.5. Samples: 37813182. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 03:05:08,975][87372] Avg episode reward: [(0, '6.700'), (1, '6.980')] -[2023-10-09 03:05:11,237][88326] Updated weights for policy 0, policy_version 73832 (0.0010) -[2023-10-09 03:05:11,613][88326] Updated weights for policy 0, policy_version 73842 (0.0008) -[2023-10-09 03:05:11,972][88326] Updated weights for policy 0, policy_version 73852 (0.0008) -[2023-10-09 03:05:12,860][88327] Updated weights for policy 1, policy_version 73890 (0.0009) -[2023-10-09 03:05:13,226][88327] Updated weights for policy 1, policy_version 73900 (0.0007) -[2023-10-09 03:05:13,596][88327] Updated weights for policy 1, policy_version 73910 (0.0008) -[2023-10-09 03:05:13,953][88327] Updated weights for policy 1, policy_version 73920 (0.0009) -[2023-10-09 03:05:13,974][87372] Fps is (10 sec: 16383.7, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 151322624. Throughput: 0: 1669.5, 1: 1700.0. Samples: 37833128. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 03:05:13,976][87372] Avg episode reward: [(0, '6.310'), (1, '7.710')] -[2023-10-09 03:05:15,942][88326] Updated weights for policy 0, policy_version 73862 (0.0010) -[2023-10-09 03:05:16,324][88326] Updated weights for policy 0, policy_version 73872 (0.0009) -[2023-10-09 03:05:16,688][88326] Updated weights for policy 0, policy_version 73882 (0.0007) -[2023-10-09 03:05:17,714][88327] Updated weights for policy 1, policy_version 73930 (0.0007) -[2023-10-09 03:05:18,082][88327] Updated weights for policy 1, policy_version 73940 (0.0007) -[2023-10-09 03:05:18,438][88327] Updated weights for policy 1, policy_version 73950 (0.0007) -[2023-10-09 03:05:18,974][87372] Fps is (10 sec: 16383.9, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 151388160. Throughput: 0: 1695.2, 1: 1688.9. Samples: 37853586. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 03:05:18,975][87372] Avg episode reward: [(0, '6.940'), (1, '7.580')] -[2023-10-09 03:05:20,844][88326] Updated weights for policy 0, policy_version 73892 (0.0008) -[2023-10-09 03:05:21,206][88326] Updated weights for policy 0, policy_version 73902 (0.0009) -[2023-10-09 03:05:21,570][88326] Updated weights for policy 0, policy_version 73912 (0.0008) -[2023-10-09 03:05:22,384][88327] Updated weights for policy 1, policy_version 73960 (0.0007) -[2023-10-09 03:05:22,740][88327] Updated weights for policy 1, policy_version 73970 (0.0010) -[2023-10-09 03:05:23,115][88327] Updated weights for policy 1, policy_version 73980 (0.0010) -[2023-10-09 03:05:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 151453696. Throughput: 0: 1678.5, 1: 1707.3. Samples: 37863954. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 03:05:23,975][87372] Avg episode reward: [(0, '6.800'), (1, '7.110')] -[2023-10-09 03:05:25,543][88326] Updated weights for policy 0, policy_version 73922 (0.0009) -[2023-10-09 03:05:25,918][88326] Updated weights for policy 0, policy_version 73932 (0.0008) -[2023-10-09 03:05:26,287][88326] Updated weights for policy 0, policy_version 73942 (0.0008) -[2023-10-09 03:05:26,657][88326] Updated weights for policy 0, policy_version 73952 (0.0007) -[2023-10-09 03:05:27,273][88327] Updated weights for policy 1, policy_version 73990 (0.0007) -[2023-10-09 03:05:27,633][88327] Updated weights for policy 1, policy_version 74000 (0.0007) -[2023-10-09 03:05:28,005][88327] Updated weights for policy 1, policy_version 74010 (0.0007) -[2023-10-09 03:05:28,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 151519232. Throughput: 0: 1675.9, 1: 1705.1. Samples: 37884060. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-09 03:05:28,975][87372] Avg episode reward: [(0, '6.410'), (1, '7.080')] -[2023-10-09 03:05:30,766][88326] Updated weights for policy 0, policy_version 73962 (0.0009) -[2023-10-09 03:05:31,138][88326] Updated weights for policy 0, policy_version 73972 (0.0009) -[2023-10-09 03:05:31,507][88326] Updated weights for policy 0, policy_version 73982 (0.0010) -[2023-10-09 03:05:32,021][88327] Updated weights for policy 1, policy_version 74020 (0.0009) -[2023-10-09 03:05:32,391][88327] Updated weights for policy 1, policy_version 74030 (0.0011) -[2023-10-09 03:05:32,747][88327] Updated weights for policy 1, policy_version 74040 (0.0010) -[2023-10-09 03:05:33,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 151584768. Throughput: 0: 1690.5, 1: 1677.6. Samples: 37903738. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:05:33,975][87372] Avg episode reward: [(0, '6.620'), (1, '6.970')] -[2023-10-09 03:05:35,446][88326] Updated weights for policy 0, policy_version 73992 (0.0007) -[2023-10-09 03:05:35,816][88326] Updated weights for policy 0, policy_version 74002 (0.0008) -[2023-10-09 03:05:36,175][88326] Updated weights for policy 0, policy_version 74012 (0.0009) -[2023-10-09 03:05:36,543][88327] Updated weights for policy 1, policy_version 74050 (0.0008) -[2023-10-09 03:05:36,904][88327] Updated weights for policy 1, policy_version 74060 (0.0007) -[2023-10-09 03:05:37,271][88327] Updated weights for policy 1, policy_version 74070 (0.0010) -[2023-10-09 03:05:37,635][88327] Updated weights for policy 1, policy_version 74080 (0.0010) -[2023-10-09 03:05:38,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 151650304. Throughput: 0: 1666.2, 1: 1713.5. Samples: 37914556. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:05:38,975][87372] Avg episode reward: [(0, '6.160'), (1, '7.310')] -[2023-10-09 03:05:40,284][88326] Updated weights for policy 0, policy_version 74022 (0.0008) -[2023-10-09 03:05:40,644][88326] Updated weights for policy 0, policy_version 74032 (0.0009) -[2023-10-09 03:05:41,024][88326] Updated weights for policy 0, policy_version 74042 (0.0007) -[2023-10-09 03:05:41,877][88327] Updated weights for policy 1, policy_version 74090 (0.0010) -[2023-10-09 03:05:42,252][88327] Updated weights for policy 1, policy_version 74100 (0.0009) -[2023-10-09 03:05:42,610][88327] Updated weights for policy 1, policy_version 74110 (0.0008) -[2023-10-09 03:05:43,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 151715840. Throughput: 0: 1680.2, 1: 1694.4. Samples: 37934314. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:05:43,974][87372] Avg episode reward: [(0, '6.290'), (1, '7.670')] -[2023-10-09 03:05:45,115][88326] Updated weights for policy 0, policy_version 74052 (0.0008) -[2023-10-09 03:05:45,486][88326] Updated weights for policy 0, policy_version 74062 (0.0011) -[2023-10-09 03:05:45,860][88326] Updated weights for policy 0, policy_version 74072 (0.0008) -[2023-10-09 03:05:46,718][88327] Updated weights for policy 1, policy_version 74120 (0.0007) -[2023-10-09 03:05:47,081][88327] Updated weights for policy 1, policy_version 74130 (0.0007) -[2023-10-09 03:05:47,446][88327] Updated weights for policy 1, policy_version 74140 (0.0009) -[2023-10-09 03:05:48,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 151781376. Throughput: 0: 1686.7, 1: 1679.8. Samples: 37954620. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:05:48,975][87372] Avg episode reward: [(0, '6.430'), (1, '7.570')] -[2023-10-09 03:05:49,902][88326] Updated weights for policy 0, policy_version 74082 (0.0007) -[2023-10-09 03:05:50,283][88326] Updated weights for policy 0, policy_version 74092 (0.0009) -[2023-10-09 03:05:50,644][88326] Updated weights for policy 0, policy_version 74102 (0.0007) -[2023-10-09 03:05:51,008][88326] Updated weights for policy 0, policy_version 74112 (0.0008) -[2023-10-09 03:05:51,531][88327] Updated weights for policy 1, policy_version 74150 (0.0008) -[2023-10-09 03:05:51,885][88327] Updated weights for policy 1, policy_version 74160 (0.0010) -[2023-10-09 03:05:52,262][88327] Updated weights for policy 1, policy_version 74170 (0.0007) -[2023-10-09 03:05:53,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 151846912. Throughput: 0: 1664.3, 1: 1710.5. Samples: 37965048. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:05:53,975][87372] Avg episode reward: [(0, '6.660'), (1, '7.090')] -[2023-10-09 03:05:55,046][88326] Updated weights for policy 0, policy_version 74122 (0.0007) -[2023-10-09 03:05:55,404][88326] Updated weights for policy 0, policy_version 74132 (0.0008) -[2023-10-09 03:05:55,770][88326] Updated weights for policy 0, policy_version 74142 (0.0008) -[2023-10-09 03:05:56,399][88327] Updated weights for policy 1, policy_version 74180 (0.0008) -[2023-10-09 03:05:56,775][88327] Updated weights for policy 1, policy_version 74190 (0.0009) -[2023-10-09 03:05:57,134][88327] Updated weights for policy 1, policy_version 74200 (0.0008) -[2023-10-09 03:05:58,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 151912448. Throughput: 0: 1692.4, 1: 1680.5. Samples: 37984906. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:05:58,975][87372] Avg episode reward: [(0, '6.790'), (1, '7.130')] -[2023-10-09 03:05:59,614][88326] Updated weights for policy 0, policy_version 74152 (0.0007) -[2023-10-09 03:05:59,981][88326] Updated weights for policy 0, policy_version 74162 (0.0008) -[2023-10-09 03:06:00,351][88326] Updated weights for policy 0, policy_version 74172 (0.0009) -[2023-10-09 03:06:01,117][88327] Updated weights for policy 1, policy_version 74210 (0.0007) -[2023-10-09 03:06:01,484][88327] Updated weights for policy 1, policy_version 74220 (0.0009) -[2023-10-09 03:06:01,846][88327] Updated weights for policy 1, policy_version 74230 (0.0007) -[2023-10-09 03:06:02,221][88327] Updated weights for policy 1, policy_version 74240 (0.0007) -[2023-10-09 03:06:03,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 151977984. Throughput: 0: 1694.8, 1: 1682.4. Samples: 38005558. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:06:03,974][87372] Avg episode reward: [(0, '6.530'), (1, '6.870')] -[2023-10-09 03:06:04,480][88326] Updated weights for policy 0, policy_version 74182 (0.0009) -[2023-10-09 03:06:04,864][88326] Updated weights for policy 0, policy_version 74192 (0.0007) -[2023-10-09 03:06:05,233][88326] Updated weights for policy 0, policy_version 74202 (0.0008) -[2023-10-09 03:06:06,095][88327] Updated weights for policy 1, policy_version 74250 (0.0009) -[2023-10-09 03:06:06,457][88327] Updated weights for policy 1, policy_version 74260 (0.0008) -[2023-10-09 03:06:06,816][88327] Updated weights for policy 1, policy_version 74270 (0.0010) -[2023-10-09 03:06:08,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 152043520. Throughput: 0: 1683.5, 1: 1688.1. Samples: 38015672. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:06:08,974][87372] Avg episode reward: [(0, '7.570'), (1, '7.370')] -[2023-10-09 03:06:09,236][88326] Updated weights for policy 0, policy_version 74212 (0.0008) -[2023-10-09 03:06:09,615][88326] Updated weights for policy 0, policy_version 74222 (0.0008) -[2023-10-09 03:06:09,983][88326] Updated weights for policy 0, policy_version 74232 (0.0007) -[2023-10-09 03:06:10,870][88327] Updated weights for policy 1, policy_version 74280 (0.0009) -[2023-10-09 03:06:11,229][88327] Updated weights for policy 1, policy_version 74290 (0.0007) -[2023-10-09 03:06:11,603][88327] Updated weights for policy 1, policy_version 74300 (0.0007) -[2023-10-09 03:06:13,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 152109056. Throughput: 0: 1701.2, 1: 1668.9. Samples: 38035714. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:06:13,975][87372] Avg episode reward: [(0, '7.540'), (1, '8.080')] -[2023-10-09 03:06:14,022][88326] Updated weights for policy 0, policy_version 74242 (0.0008) -[2023-10-09 03:06:14,398][88326] Updated weights for policy 0, policy_version 74252 (0.0007) -[2023-10-09 03:06:14,769][88326] Updated weights for policy 0, policy_version 74262 (0.0007) -[2023-10-09 03:06:15,139][88326] Updated weights for policy 0, policy_version 74272 (0.0007) -[2023-10-09 03:06:15,673][88327] Updated weights for policy 1, policy_version 74310 (0.0008) -[2023-10-09 03:06:16,042][88327] Updated weights for policy 1, policy_version 74320 (0.0008) -[2023-10-09 03:06:16,402][88327] Updated weights for policy 1, policy_version 74330 (0.0008) -[2023-10-09 03:06:18,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 152174592. Throughput: 0: 1702.7, 1: 1696.6. Samples: 38056706. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:06:18,975][87372] Avg episode reward: [(0, '7.470'), (1, '8.000')] -[2023-10-09 03:06:19,148][88326] Updated weights for policy 0, policy_version 74282 (0.0008) -[2023-10-09 03:06:19,516][88326] Updated weights for policy 0, policy_version 74292 (0.0009) -[2023-10-09 03:06:19,881][88326] Updated weights for policy 0, policy_version 74302 (0.0008) -[2023-10-09 03:06:20,528][88327] Updated weights for policy 1, policy_version 74340 (0.0008) -[2023-10-09 03:06:20,888][88327] Updated weights for policy 1, policy_version 74350 (0.0007) -[2023-10-09 03:06:21,260][88327] Updated weights for policy 1, policy_version 74360 (0.0009) -[2023-10-09 03:06:23,933][88326] Updated weights for policy 0, policy_version 74312 (0.0007) -[2023-10-09 03:06:23,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.3, 300 sec: 13440.4). Total num frames: 152240128. Throughput: 0: 1700.4, 1: 1672.1. Samples: 38066318. Policy #0 lag: (min: 31.0, avg: 34.3, max: 63.0) -[2023-10-09 03:06:23,974][87372] Avg episode reward: [(0, '7.840'), (1, '7.750')] -[2023-10-09 03:06:24,311][88326] Updated weights for policy 0, policy_version 74322 (0.0008) -[2023-10-09 03:06:24,694][88326] Updated weights for policy 0, policy_version 74332 (0.0008) -[2023-10-09 03:06:25,279][88327] Updated weights for policy 1, policy_version 74370 (0.0010) -[2023-10-09 03:06:25,642][88327] Updated weights for policy 1, policy_version 74380 (0.0010) -[2023-10-09 03:06:26,009][88327] Updated weights for policy 1, policy_version 74390 (0.0010) -[2023-10-09 03:06:26,376][88327] Updated weights for policy 1, policy_version 74400 (0.0009) -[2023-10-09 03:06:28,661][88326] Updated weights for policy 0, policy_version 74342 (0.0009) -[2023-10-09 03:06:28,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.3, 300 sec: 13440.4). Total num frames: 152305664. Throughput: 0: 1708.3, 1: 1680.9. Samples: 38086830. Policy #0 lag: (min: 31.0, avg: 34.3, max: 63.0) -[2023-10-09 03:06:28,974][87372] Avg episode reward: [(0, '6.670'), (1, '8.160')] -[2023-10-09 03:06:29,034][88326] Updated weights for policy 0, policy_version 74352 (0.0008) -[2023-10-09 03:06:29,396][88326] Updated weights for policy 0, policy_version 74362 (0.0009) -[2023-10-09 03:06:30,403][88327] Updated weights for policy 1, policy_version 74410 (0.0010) -[2023-10-09 03:06:30,765][88327] Updated weights for policy 1, policy_version 74420 (0.0011) -[2023-10-09 03:06:31,123][88327] Updated weights for policy 1, policy_version 74430 (0.0009) -[2023-10-09 03:06:33,399][88326] Updated weights for policy 0, policy_version 74372 (0.0009) -[2023-10-09 03:06:33,763][88326] Updated weights for policy 0, policy_version 74382 (0.0009) -[2023-10-09 03:06:33,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 152371200. Throughput: 0: 1707.3, 1: 1696.0. Samples: 38107766. Policy #0 lag: (min: 31.0, avg: 34.3, max: 63.0) -[2023-10-09 03:06:33,974][87372] Avg episode reward: [(0, '6.550'), (1, '7.490')] -[2023-10-09 03:06:33,984][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000074432_76218368.pth... -[2023-10-09 03:06:34,020][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000072864_74612736.pth -[2023-10-09 03:06:34,125][88326] Updated weights for policy 0, policy_version 74392 (0.0009) -[2023-10-09 03:06:34,419][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000074400_76185600.pth... -[2023-10-09 03:06:34,449][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000072800_74547200.pth -[2023-10-09 03:06:35,237][88327] Updated weights for policy 1, policy_version 74440 (0.0010) -[2023-10-09 03:06:35,596][88327] Updated weights for policy 1, policy_version 74450 (0.0011) -[2023-10-09 03:06:35,969][88327] Updated weights for policy 1, policy_version 74460 (0.0008) -[2023-10-09 03:06:38,220][88326] Updated weights for policy 0, policy_version 74402 (0.0008) -[2023-10-09 03:06:38,585][88326] Updated weights for policy 0, policy_version 74412 (0.0008) -[2023-10-09 03:06:38,969][88326] Updated weights for policy 0, policy_version 74422 (0.0008) -[2023-10-09 03:06:38,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 152436736. Throughput: 0: 1707.1, 1: 1665.5. Samples: 38116814. Policy #0 lag: (min: 31.0, avg: 34.3, max: 63.0) -[2023-10-09 03:06:38,975][87372] Avg episode reward: [(0, '6.960'), (1, '6.960')] -[2023-10-09 03:06:39,346][88326] Updated weights for policy 0, policy_version 74432 (0.0009) -[2023-10-09 03:06:40,000][88327] Updated weights for policy 1, policy_version 74470 (0.0008) -[2023-10-09 03:06:40,367][88327] Updated weights for policy 1, policy_version 74480 (0.0007) -[2023-10-09 03:06:40,728][88327] Updated weights for policy 1, policy_version 74490 (0.0008) -[2023-10-09 03:06:43,278][88326] Updated weights for policy 0, policy_version 74442 (0.0007) -[2023-10-09 03:06:43,645][88326] Updated weights for policy 0, policy_version 74452 (0.0007) -[2023-10-09 03:06:43,974][87372] Fps is (10 sec: 13106.8, 60 sec: 13107.1, 300 sec: 13440.4). Total num frames: 152502272. Throughput: 0: 1708.1, 1: 1694.8. Samples: 38138036. Policy #0 lag: (min: 31.0, avg: 34.3, max: 63.0) -[2023-10-09 03:06:43,976][87372] Avg episode reward: [(0, '7.360'), (1, '7.440')] -[2023-10-09 03:06:44,016][88326] Updated weights for policy 0, policy_version 74462 (0.0010) -[2023-10-09 03:06:44,494][88327] Updated weights for policy 1, policy_version 74500 (0.0007) -[2023-10-09 03:06:44,885][88327] Updated weights for policy 1, policy_version 74510 (0.0008) -[2023-10-09 03:06:45,248][88327] Updated weights for policy 1, policy_version 74520 (0.0009) -[2023-10-09 03:06:47,872][88326] Updated weights for policy 0, policy_version 74472 (0.0008) -[2023-10-09 03:06:48,238][88326] Updated weights for policy 0, policy_version 74482 (0.0007) -[2023-10-09 03:06:48,603][88326] Updated weights for policy 0, policy_version 74492 (0.0009) -[2023-10-09 03:06:48,974][87372] Fps is (10 sec: 16384.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 152600576. Throughput: 0: 1694.8, 1: 1704.6. Samples: 38158534. Policy #0 lag: (min: 31.0, avg: 34.3, max: 63.0) -[2023-10-09 03:06:48,975][87372] Avg episode reward: [(0, '7.080'), (1, '7.350')] -[2023-10-09 03:06:49,180][88327] Updated weights for policy 1, policy_version 74530 (0.0008) -[2023-10-09 03:06:49,547][88327] Updated weights for policy 1, policy_version 74540 (0.0008) -[2023-10-09 03:06:49,915][88327] Updated weights for policy 1, policy_version 74550 (0.0008) -[2023-10-09 03:06:50,275][88327] Updated weights for policy 1, policy_version 74560 (0.0008) -[2023-10-09 03:06:52,812][88326] Updated weights for policy 0, policy_version 74502 (0.0009) -[2023-10-09 03:06:53,200][88326] Updated weights for policy 0, policy_version 74512 (0.0008) -[2023-10-09 03:06:53,578][88326] Updated weights for policy 0, policy_version 74522 (0.0007) -[2023-10-09 03:06:53,974][87372] Fps is (10 sec: 16384.5, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 152666112. Throughput: 0: 1707.6, 1: 1681.8. Samples: 38168194. Policy #0 lag: (min: 31.0, avg: 34.3, max: 63.0) -[2023-10-09 03:06:53,975][87372] Avg episode reward: [(0, '7.660'), (1, '6.800')] -[2023-10-09 03:06:54,434][88327] Updated weights for policy 1, policy_version 74570 (0.0009) -[2023-10-09 03:06:54,799][88327] Updated weights for policy 1, policy_version 74580 (0.0007) -[2023-10-09 03:06:55,167][88327] Updated weights for policy 1, policy_version 74590 (0.0007) -[2023-10-09 03:06:57,550][88326] Updated weights for policy 0, policy_version 74532 (0.0010) -[2023-10-09 03:06:57,917][88326] Updated weights for policy 0, policy_version 74542 (0.0007) -[2023-10-09 03:06:58,276][88326] Updated weights for policy 0, policy_version 74552 (0.0008) -[2023-10-09 03:06:58,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 152731648. Throughput: 0: 1701.2, 1: 1703.3. Samples: 38188920. Policy #0 lag: (min: 31.0, avg: 34.3, max: 63.0) -[2023-10-09 03:06:58,975][87372] Avg episode reward: [(0, '8.260'), (1, '7.150')] -[2023-10-09 03:06:58,976][88088] Saving new best policy, reward=8.260! -[2023-10-09 03:06:59,348][88327] Updated weights for policy 1, policy_version 74600 (0.0011) -[2023-10-09 03:06:59,722][88327] Updated weights for policy 1, policy_version 74610 (0.0011) -[2023-10-09 03:07:00,089][88327] Updated weights for policy 1, policy_version 74620 (0.0010) -[2023-10-09 03:07:02,617][88326] Updated weights for policy 0, policy_version 74562 (0.0011) -[2023-10-09 03:07:02,992][88326] Updated weights for policy 0, policy_version 74572 (0.0008) -[2023-10-09 03:07:03,360][88326] Updated weights for policy 0, policy_version 74582 (0.0009) -[2023-10-09 03:07:03,718][88326] Updated weights for policy 0, policy_version 74592 (0.0009) -[2023-10-09 03:07:03,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 152797184. Throughput: 0: 1677.2, 1: 1701.2. Samples: 38208738. Policy #0 lag: (min: 31.0, avg: 34.3, max: 63.0) -[2023-10-09 03:07:03,975][87372] Avg episode reward: [(0, '7.190'), (1, '7.780')] -[2023-10-09 03:07:04,282][88327] Updated weights for policy 1, policy_version 74630 (0.0008) -[2023-10-09 03:07:04,637][88327] Updated weights for policy 1, policy_version 74640 (0.0009) -[2023-10-09 03:07:04,998][88327] Updated weights for policy 1, policy_version 74650 (0.0010) -[2023-10-09 03:07:07,601][88326] Updated weights for policy 0, policy_version 74602 (0.0008) -[2023-10-09 03:07:07,970][88326] Updated weights for policy 0, policy_version 74612 (0.0010) -[2023-10-09 03:07:08,340][88326] Updated weights for policy 0, policy_version 74622 (0.0009) -[2023-10-09 03:07:08,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 152862720. Throughput: 0: 1695.6, 1: 1690.1. Samples: 38218676. Policy #0 lag: (min: 10.0, avg: 10.0, max: 14.0) -[2023-10-09 03:07:08,974][87372] Avg episode reward: [(0, '6.940'), (1, '8.010')] -[2023-10-09 03:07:09,064][88327] Updated weights for policy 1, policy_version 74660 (0.0009) -[2023-10-09 03:07:09,432][88327] Updated weights for policy 1, policy_version 74670 (0.0007) -[2023-10-09 03:07:09,790][88327] Updated weights for policy 1, policy_version 74680 (0.0009) -[2023-10-09 03:07:12,301][88326] Updated weights for policy 0, policy_version 74632 (0.0009) -[2023-10-09 03:07:12,667][88326] Updated weights for policy 0, policy_version 74642 (0.0009) -[2023-10-09 03:07:13,034][88326] Updated weights for policy 0, policy_version 74652 (0.0008) -[2023-10-09 03:07:13,866][88327] Updated weights for policy 1, policy_version 74690 (0.0009) -[2023-10-09 03:07:13,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 152928256. Throughput: 0: 1692.1, 1: 1698.0. Samples: 38239386. Policy #0 lag: (min: 10.0, avg: 10.0, max: 14.0) -[2023-10-09 03:07:13,975][87372] Avg episode reward: [(0, '6.750'), (1, '7.460')] -[2023-10-09 03:07:14,236][88327] Updated weights for policy 1, policy_version 74700 (0.0010) -[2023-10-09 03:07:14,604][88327] Updated weights for policy 1, policy_version 74710 (0.0008) -[2023-10-09 03:07:14,975][88327] Updated weights for policy 1, policy_version 74720 (0.0009) -[2023-10-09 03:07:17,191][88326] Updated weights for policy 0, policy_version 74662 (0.0008) -[2023-10-09 03:07:17,559][88326] Updated weights for policy 0, policy_version 74672 (0.0008) -[2023-10-09 03:07:17,933][88326] Updated weights for policy 0, policy_version 74682 (0.0009) -[2023-10-09 03:07:18,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 152993792. Throughput: 0: 1662.9, 1: 1702.8. Samples: 38259224. Policy #0 lag: (min: 10.0, avg: 10.0, max: 14.0) -[2023-10-09 03:07:18,975][87372] Avg episode reward: [(0, '5.790'), (1, '7.660')] -[2023-10-09 03:07:19,035][88327] Updated weights for policy 1, policy_version 74730 (0.0008) -[2023-10-09 03:07:19,405][88327] Updated weights for policy 1, policy_version 74740 (0.0009) -[2023-10-09 03:07:19,757][88327] Updated weights for policy 1, policy_version 74750 (0.0009) -[2023-10-09 03:07:21,904][88326] Updated weights for policy 0, policy_version 74692 (0.0009) -[2023-10-09 03:07:22,270][88326] Updated weights for policy 0, policy_version 74702 (0.0010) -[2023-10-09 03:07:22,634][88326] Updated weights for policy 0, policy_version 74712 (0.0011) -[2023-10-09 03:07:23,817][88327] Updated weights for policy 1, policy_version 74760 (0.0008) -[2023-10-09 03:07:23,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 153059328. Throughput: 0: 1692.7, 1: 1703.1. Samples: 38269622. Policy #0 lag: (min: 10.0, avg: 10.0, max: 14.0) -[2023-10-09 03:07:23,975][87372] Avg episode reward: [(0, '6.130'), (1, '7.280')] -[2023-10-09 03:07:24,186][88327] Updated weights for policy 1, policy_version 74770 (0.0007) -[2023-10-09 03:07:24,558][88327] Updated weights for policy 1, policy_version 74780 (0.0007) -[2023-10-09 03:07:26,664][88326] Updated weights for policy 0, policy_version 74722 (0.0007) -[2023-10-09 03:07:27,032][88326] Updated weights for policy 0, policy_version 74732 (0.0008) -[2023-10-09 03:07:27,407][88326] Updated weights for policy 0, policy_version 74742 (0.0009) -[2023-10-09 03:07:27,782][88326] Updated weights for policy 0, policy_version 74752 (0.0008) -[2023-10-09 03:07:28,573][88327] Updated weights for policy 1, policy_version 74790 (0.0008) -[2023-10-09 03:07:28,944][88327] Updated weights for policy 1, policy_version 74800 (0.0010) -[2023-10-09 03:07:28,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 153124864. Throughput: 0: 1675.9, 1: 1700.6. Samples: 38289980. Policy #0 lag: (min: 10.0, avg: 10.0, max: 14.0) -[2023-10-09 03:07:28,975][87372] Avg episode reward: [(0, '6.420'), (1, '7.710')] -[2023-10-09 03:07:29,307][88327] Updated weights for policy 1, policy_version 74810 (0.0010) -[2023-10-09 03:07:31,858][88326] Updated weights for policy 0, policy_version 74762 (0.0009) -[2023-10-09 03:07:32,222][88326] Updated weights for policy 0, policy_version 74772 (0.0009) -[2023-10-09 03:07:32,589][88326] Updated weights for policy 0, policy_version 74782 (0.0009) -[2023-10-09 03:07:33,180][88327] Updated weights for policy 1, policy_version 74820 (0.0009) -[2023-10-09 03:07:33,540][88327] Updated weights for policy 1, policy_version 74830 (0.0010) -[2023-10-09 03:07:33,909][88327] Updated weights for policy 1, policy_version 74840 (0.0008) -[2023-10-09 03:07:33,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 153190400. Throughput: 0: 1671.2, 1: 1697.1. Samples: 38310106. Policy #0 lag: (min: 10.0, avg: 10.0, max: 14.0) -[2023-10-09 03:07:33,975][87372] Avg episode reward: [(0, '6.540'), (1, '7.370')] -[2023-10-09 03:07:36,657][88326] Updated weights for policy 0, policy_version 74792 (0.0008) -[2023-10-09 03:07:37,021][88326] Updated weights for policy 0, policy_version 74802 (0.0007) -[2023-10-09 03:07:37,379][88326] Updated weights for policy 0, policy_version 74812 (0.0007) -[2023-10-09 03:07:37,873][88327] Updated weights for policy 1, policy_version 74850 (0.0008) -[2023-10-09 03:07:38,239][88327] Updated weights for policy 1, policy_version 74860 (0.0008) -[2023-10-09 03:07:38,608][88327] Updated weights for policy 1, policy_version 74870 (0.0011) -[2023-10-09 03:07:38,973][88327] Updated weights for policy 1, policy_version 74880 (0.0009) -[2023-10-09 03:07:38,974][87372] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 153288704. Throughput: 0: 1684.6, 1: 1703.2. Samples: 38320646. Policy #0 lag: (min: 10.0, avg: 10.0, max: 14.0) -[2023-10-09 03:07:38,975][87372] Avg episode reward: [(0, '6.570'), (1, '7.040')] -[2023-10-09 03:07:41,489][88326] Updated weights for policy 0, policy_version 74822 (0.0008) -[2023-10-09 03:07:41,849][88326] Updated weights for policy 0, policy_version 74832 (0.0008) -[2023-10-09 03:07:42,220][88326] Updated weights for policy 0, policy_version 74842 (0.0007) -[2023-10-09 03:07:43,063][88327] Updated weights for policy 1, policy_version 74890 (0.0007) -[2023-10-09 03:07:43,423][88327] Updated weights for policy 1, policy_version 74900 (0.0008) -[2023-10-09 03:07:43,782][88327] Updated weights for policy 1, policy_version 74910 (0.0009) -[2023-10-09 03:07:43,974][87372] Fps is (10 sec: 16384.5, 60 sec: 14199.6, 300 sec: 13551.5). Total num frames: 153354240. Throughput: 0: 1668.7, 1: 1699.5. Samples: 38340490. Policy #0 lag: (min: 10.0, avg: 10.0, max: 14.0) -[2023-10-09 03:07:43,974][87372] Avg episode reward: [(0, '7.470'), (1, '7.380')] -[2023-10-09 03:07:46,238][88326] Updated weights for policy 0, policy_version 74852 (0.0007) -[2023-10-09 03:07:46,614][88326] Updated weights for policy 0, policy_version 74862 (0.0007) -[2023-10-09 03:07:46,995][88326] Updated weights for policy 0, policy_version 74872 (0.0008) -[2023-10-09 03:07:47,692][88327] Updated weights for policy 1, policy_version 74920 (0.0008) -[2023-10-09 03:07:48,057][88327] Updated weights for policy 1, policy_version 74930 (0.0009) -[2023-10-09 03:07:48,416][88327] Updated weights for policy 1, policy_version 74940 (0.0010) -[2023-10-09 03:07:48,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 153419776. Throughput: 0: 1685.5, 1: 1687.2. Samples: 38360512. Policy #0 lag: (min: 10.0, avg: 10.0, max: 14.0) -[2023-10-09 03:07:48,975][87372] Avg episode reward: [(0, '6.930'), (1, '7.130')] -[2023-10-09 03:07:50,903][88326] Updated weights for policy 0, policy_version 74882 (0.0009) -[2023-10-09 03:07:51,277][88326] Updated weights for policy 0, policy_version 74892 (0.0007) -[2023-10-09 03:07:51,649][88326] Updated weights for policy 0, policy_version 74902 (0.0008) -[2023-10-09 03:07:52,031][88326] Updated weights for policy 0, policy_version 74912 (0.0010) -[2023-10-09 03:07:52,518][88327] Updated weights for policy 1, policy_version 74950 (0.0008) -[2023-10-09 03:07:52,883][88327] Updated weights for policy 1, policy_version 74960 (0.0009) -[2023-10-09 03:07:53,240][88327] Updated weights for policy 1, policy_version 74970 (0.0009) -[2023-10-09 03:07:53,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 153485312. Throughput: 0: 1686.5, 1: 1705.7. Samples: 38371328. Policy #0 lag: (min: 10.0, avg: 10.0, max: 14.0) -[2023-10-09 03:07:53,975][87372] Avg episode reward: [(0, '7.020'), (1, '7.320')] -[2023-10-09 03:07:56,094][88326] Updated weights for policy 0, policy_version 74922 (0.0007) -[2023-10-09 03:07:56,465][88326] Updated weights for policy 0, policy_version 74932 (0.0008) -[2023-10-09 03:07:56,829][88326] Updated weights for policy 0, policy_version 74942 (0.0007) -[2023-10-09 03:07:57,386][88327] Updated weights for policy 1, policy_version 74980 (0.0010) -[2023-10-09 03:07:57,752][88327] Updated weights for policy 1, policy_version 74990 (0.0009) -[2023-10-09 03:07:58,105][88327] Updated weights for policy 1, policy_version 75000 (0.0010) -[2023-10-09 03:07:58,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 153550848. Throughput: 0: 1669.3, 1: 1706.5. Samples: 38391298. Policy #0 lag: (min: 17.0, avg: 29.7, max: 49.0) -[2023-10-09 03:07:58,975][87372] Avg episode reward: [(0, '7.310'), (1, '6.770')] -[2023-10-09 03:08:00,798][88326] Updated weights for policy 0, policy_version 74952 (0.0008) -[2023-10-09 03:08:01,173][88326] Updated weights for policy 0, policy_version 74962 (0.0009) -[2023-10-09 03:08:01,545][88326] Updated weights for policy 0, policy_version 74972 (0.0009) -[2023-10-09 03:08:02,276][88327] Updated weights for policy 1, policy_version 75010 (0.0009) -[2023-10-09 03:08:02,646][88327] Updated weights for policy 1, policy_version 75020 (0.0007) -[2023-10-09 03:08:03,011][88327] Updated weights for policy 1, policy_version 75030 (0.0007) -[2023-10-09 03:08:03,376][88327] Updated weights for policy 1, policy_version 75040 (0.0007) -[2023-10-09 03:08:03,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 153616384. Throughput: 0: 1700.3, 1: 1677.9. Samples: 38411242. Policy #0 lag: (min: 17.0, avg: 29.7, max: 49.0) -[2023-10-09 03:08:03,975][87372] Avg episode reward: [(0, '6.740'), (1, '7.620')] -[2023-10-09 03:08:05,388][88326] Updated weights for policy 0, policy_version 74982 (0.0009) -[2023-10-09 03:08:05,753][88326] Updated weights for policy 0, policy_version 74992 (0.0007) -[2023-10-09 03:08:06,115][88326] Updated weights for policy 0, policy_version 75002 (0.0007) -[2023-10-09 03:08:07,429][88327] Updated weights for policy 1, policy_version 75050 (0.0008) -[2023-10-09 03:08:07,795][88327] Updated weights for policy 1, policy_version 75060 (0.0010) -[2023-10-09 03:08:08,163][88327] Updated weights for policy 1, policy_version 75070 (0.0009) -[2023-10-09 03:08:08,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 153681920. Throughput: 0: 1678.4, 1: 1699.1. Samples: 38421612. Policy #0 lag: (min: 17.0, avg: 29.7, max: 49.0) -[2023-10-09 03:08:08,975][87372] Avg episode reward: [(0, '6.420'), (1, '7.830')] -[2023-10-09 03:08:10,293][88326] Updated weights for policy 0, policy_version 75012 (0.0008) -[2023-10-09 03:08:10,650][88326] Updated weights for policy 0, policy_version 75022 (0.0007) -[2023-10-09 03:08:11,015][88326] Updated weights for policy 0, policy_version 75032 (0.0009) -[2023-10-09 03:08:12,137][88327] Updated weights for policy 1, policy_version 75080 (0.0008) -[2023-10-09 03:08:12,500][88327] Updated weights for policy 1, policy_version 75090 (0.0010) -[2023-10-09 03:08:12,873][88327] Updated weights for policy 1, policy_version 75100 (0.0008) -[2023-10-09 03:08:13,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 153747456. Throughput: 0: 1686.5, 1: 1690.1. Samples: 38441928. Policy #0 lag: (min: 17.0, avg: 29.7, max: 49.0) -[2023-10-09 03:08:13,975][87372] Avg episode reward: [(0, '7.320'), (1, '7.220')] -[2023-10-09 03:08:15,003][88326] Updated weights for policy 0, policy_version 75042 (0.0007) -[2023-10-09 03:08:15,370][88326] Updated weights for policy 0, policy_version 75052 (0.0009) -[2023-10-09 03:08:15,725][88326] Updated weights for policy 0, policy_version 75062 (0.0008) -[2023-10-09 03:08:16,093][88326] Updated weights for policy 0, policy_version 75072 (0.0009) -[2023-10-09 03:08:16,744][88327] Updated weights for policy 1, policy_version 75110 (0.0008) -[2023-10-09 03:08:17,113][88327] Updated weights for policy 1, policy_version 75120 (0.0008) -[2023-10-09 03:08:17,485][88327] Updated weights for policy 1, policy_version 75130 (0.0007) -[2023-10-09 03:08:18,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 153812992. Throughput: 0: 1708.4, 1: 1672.1. Samples: 38462228. Policy #0 lag: (min: 17.0, avg: 29.7, max: 49.0) -[2023-10-09 03:08:18,975][87372] Avg episode reward: [(0, '6.700'), (1, '7.730')] -[2023-10-09 03:08:20,006][88326] Updated weights for policy 0, policy_version 75082 (0.0008) -[2023-10-09 03:08:20,373][88326] Updated weights for policy 0, policy_version 75092 (0.0007) -[2023-10-09 03:08:20,738][88326] Updated weights for policy 0, policy_version 75102 (0.0010) -[2023-10-09 03:08:21,795][88327] Updated weights for policy 1, policy_version 75140 (0.0009) -[2023-10-09 03:08:22,198][88327] Updated weights for policy 1, policy_version 75150 (0.0008) -[2023-10-09 03:08:22,574][88327] Updated weights for policy 1, policy_version 75160 (0.0007) -[2023-10-09 03:08:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 153878528. Throughput: 0: 1681.0, 1: 1693.2. Samples: 38472486. Policy #0 lag: (min: 17.0, avg: 29.7, max: 49.0) -[2023-10-09 03:08:23,975][87372] Avg episode reward: [(0, '6.640'), (1, '7.830')] -[2023-10-09 03:08:25,026][88326] Updated weights for policy 0, policy_version 75112 (0.0010) -[2023-10-09 03:08:25,395][88326] Updated weights for policy 0, policy_version 75122 (0.0009) -[2023-10-09 03:08:25,765][88326] Updated weights for policy 0, policy_version 75132 (0.0009) -[2023-10-09 03:08:26,555][88327] Updated weights for policy 1, policy_version 75170 (0.0008) -[2023-10-09 03:08:26,926][88327] Updated weights for policy 1, policy_version 75180 (0.0009) -[2023-10-09 03:08:27,287][88327] Updated weights for policy 1, policy_version 75190 (0.0009) -[2023-10-09 03:08:27,652][88327] Updated weights for policy 1, policy_version 75200 (0.0009) -[2023-10-09 03:08:28,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 153944064. Throughput: 0: 1704.6, 1: 1674.1. Samples: 38492534. Policy #0 lag: (min: 17.0, avg: 29.7, max: 49.0) -[2023-10-09 03:08:28,975][87372] Avg episode reward: [(0, '7.070'), (1, '7.070')] -[2023-10-09 03:08:29,745][88326] Updated weights for policy 0, policy_version 75142 (0.0009) -[2023-10-09 03:08:30,123][88326] Updated weights for policy 0, policy_version 75152 (0.0009) -[2023-10-09 03:08:30,482][88326] Updated weights for policy 0, policy_version 75162 (0.0009) -[2023-10-09 03:08:31,550][88327] Updated weights for policy 1, policy_version 75210 (0.0009) -[2023-10-09 03:08:31,912][88327] Updated weights for policy 1, policy_version 75220 (0.0008) -[2023-10-09 03:08:32,281][88327] Updated weights for policy 1, policy_version 75230 (0.0010) -[2023-10-09 03:08:33,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 154009600. Throughput: 0: 1712.5, 1: 1675.8. Samples: 38512988. Policy #0 lag: (min: 17.0, avg: 29.7, max: 49.0) -[2023-10-09 03:08:33,975][87372] Avg episode reward: [(0, '6.280'), (1, '6.910')] -[2023-10-09 03:08:33,985][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000075232_77037568.pth... -[2023-10-09 03:08:33,985][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000075168_76972032.pth... -[2023-10-09 03:08:34,016][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000073664_75431936.pth -[2023-10-09 03:08:34,020][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000073600_75366400.pth -[2023-10-09 03:08:34,600][88326] Updated weights for policy 0, policy_version 75172 (0.0007) -[2023-10-09 03:08:34,995][88326] Updated weights for policy 0, policy_version 75182 (0.0010) -[2023-10-09 03:08:35,365][88326] Updated weights for policy 0, policy_version 75192 (0.0007) -[2023-10-09 03:08:36,448][88327] Updated weights for policy 1, policy_version 75240 (0.0009) -[2023-10-09 03:08:36,820][88327] Updated weights for policy 1, policy_version 75250 (0.0007) -[2023-10-09 03:08:37,184][88327] Updated weights for policy 1, policy_version 75260 (0.0009) -[2023-10-09 03:08:38,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 154075136. Throughput: 0: 1688.9, 1: 1687.6. Samples: 38523270. Policy #0 lag: (min: 17.0, avg: 29.7, max: 49.0) -[2023-10-09 03:08:38,975][87372] Avg episode reward: [(0, '7.060'), (1, '7.610')] -[2023-10-09 03:08:39,481][88326] Updated weights for policy 0, policy_version 75202 (0.0008) -[2023-10-09 03:08:39,851][88326] Updated weights for policy 0, policy_version 75212 (0.0010) -[2023-10-09 03:08:40,224][88326] Updated weights for policy 0, policy_version 75222 (0.0008) -[2023-10-09 03:08:40,600][88326] Updated weights for policy 0, policy_version 75232 (0.0009) -[2023-10-09 03:08:41,158][88327] Updated weights for policy 1, policy_version 75270 (0.0009) -[2023-10-09 03:08:41,525][88327] Updated weights for policy 1, policy_version 75280 (0.0008) -[2023-10-09 03:08:41,880][88327] Updated weights for policy 1, policy_version 75290 (0.0010) -[2023-10-09 03:08:43,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 154140672. Throughput: 0: 1707.2, 1: 1665.2. Samples: 38543058. Policy #0 lag: (min: 17.0, avg: 29.7, max: 49.0) -[2023-10-09 03:08:43,975][87372] Avg episode reward: [(0, '6.850'), (1, '7.740')] -[2023-10-09 03:08:44,552][88326] Updated weights for policy 0, policy_version 75242 (0.0008) -[2023-10-09 03:08:44,929][88326] Updated weights for policy 0, policy_version 75252 (0.0007) -[2023-10-09 03:08:45,309][88326] Updated weights for policy 0, policy_version 75262 (0.0007) -[2023-10-09 03:08:46,018][88327] Updated weights for policy 1, policy_version 75300 (0.0009) -[2023-10-09 03:08:46,377][88327] Updated weights for policy 1, policy_version 75310 (0.0008) -[2023-10-09 03:08:46,748][88327] Updated weights for policy 1, policy_version 75320 (0.0008) -[2023-10-09 03:08:48,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 154206208. Throughput: 0: 1705.7, 1: 1689.2. Samples: 38564014. Policy #0 lag: (min: 24.0, avg: 45.7, max: 48.0) -[2023-10-09 03:08:48,975][87372] Avg episode reward: [(0, '7.150'), (1, '7.330')] -[2023-10-09 03:08:49,293][88326] Updated weights for policy 0, policy_version 75272 (0.0008) -[2023-10-09 03:08:49,662][88326] Updated weights for policy 0, policy_version 75282 (0.0007) -[2023-10-09 03:08:50,028][88326] Updated weights for policy 0, policy_version 75292 (0.0008) -[2023-10-09 03:08:50,733][88327] Updated weights for policy 1, policy_version 75330 (0.0008) -[2023-10-09 03:08:51,095][88327] Updated weights for policy 1, policy_version 75340 (0.0009) -[2023-10-09 03:08:51,463][88327] Updated weights for policy 1, policy_version 75350 (0.0011) -[2023-10-09 03:08:51,822][88327] Updated weights for policy 1, policy_version 75360 (0.0009) -[2023-10-09 03:08:53,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 154271744. Throughput: 0: 1698.1, 1: 1685.4. Samples: 38573872. Policy #0 lag: (min: 24.0, avg: 45.7, max: 48.0) -[2023-10-09 03:08:53,975][87372] Avg episode reward: [(0, '7.450'), (1, '7.460')] -[2023-10-09 03:08:54,187][88326] Updated weights for policy 0, policy_version 75302 (0.0009) -[2023-10-09 03:08:54,553][88326] Updated weights for policy 0, policy_version 75312 (0.0011) -[2023-10-09 03:08:54,922][88326] Updated weights for policy 0, policy_version 75322 (0.0010) -[2023-10-09 03:08:55,623][88327] Updated weights for policy 1, policy_version 75370 (0.0011) -[2023-10-09 03:08:56,001][88327] Updated weights for policy 1, policy_version 75380 (0.0008) -[2023-10-09 03:08:56,361][88327] Updated weights for policy 1, policy_version 75390 (0.0009) -[2023-10-09 03:08:58,842][88326] Updated weights for policy 0, policy_version 75332 (0.0008) -[2023-10-09 03:08:58,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 154337280. Throughput: 0: 1703.5, 1: 1678.0. Samples: 38594096. Policy #0 lag: (min: 24.0, avg: 45.7, max: 48.0) -[2023-10-09 03:08:58,975][87372] Avg episode reward: [(0, '6.630'), (1, '7.310')] -[2023-10-09 03:08:59,207][88326] Updated weights for policy 0, policy_version 75342 (0.0007) -[2023-10-09 03:08:59,573][88326] Updated weights for policy 0, policy_version 75352 (0.0007) -[2023-10-09 03:09:00,436][88327] Updated weights for policy 1, policy_version 75400 (0.0008) -[2023-10-09 03:09:00,809][88327] Updated weights for policy 1, policy_version 75410 (0.0007) -[2023-10-09 03:09:01,167][88327] Updated weights for policy 1, policy_version 75420 (0.0010) -[2023-10-09 03:09:03,516][88326] Updated weights for policy 0, policy_version 75362 (0.0009) -[2023-10-09 03:09:03,889][88326] Updated weights for policy 0, policy_version 75372 (0.0008) -[2023-10-09 03:09:03,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 154402816. Throughput: 0: 1697.8, 1: 1700.1. Samples: 38615130. Policy #0 lag: (min: 24.0, avg: 45.7, max: 48.0) -[2023-10-09 03:09:03,975][87372] Avg episode reward: [(0, '7.280'), (1, '6.560')] -[2023-10-09 03:09:04,255][88326] Updated weights for policy 0, policy_version 75382 (0.0007) -[2023-10-09 03:09:04,616][88326] Updated weights for policy 0, policy_version 75392 (0.0007) -[2023-10-09 03:09:05,281][88327] Updated weights for policy 1, policy_version 75430 (0.0010) -[2023-10-09 03:09:05,649][88327] Updated weights for policy 1, policy_version 75440 (0.0008) -[2023-10-09 03:09:06,014][88327] Updated weights for policy 1, policy_version 75450 (0.0008) -[2023-10-09 03:09:08,675][88326] Updated weights for policy 0, policy_version 75402 (0.0008) -[2023-10-09 03:09:08,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 154468352. Throughput: 0: 1699.8, 1: 1676.1. Samples: 38624404. Policy #0 lag: (min: 24.0, avg: 45.7, max: 48.0) -[2023-10-09 03:09:08,975][87372] Avg episode reward: [(0, '7.760'), (1, '7.290')] -[2023-10-09 03:09:09,057][88326] Updated weights for policy 0, policy_version 75412 (0.0009) -[2023-10-09 03:09:09,430][88326] Updated weights for policy 0, policy_version 75422 (0.0009) -[2023-10-09 03:09:10,281][88327] Updated weights for policy 1, policy_version 75460 (0.0009) -[2023-10-09 03:09:10,645][88327] Updated weights for policy 1, policy_version 75470 (0.0007) -[2023-10-09 03:09:11,010][88327] Updated weights for policy 1, policy_version 75480 (0.0008) -[2023-10-09 03:09:13,454][88326] Updated weights for policy 0, policy_version 75432 (0.0010) -[2023-10-09 03:09:13,833][88326] Updated weights for policy 0, policy_version 75442 (0.0008) -[2023-10-09 03:09:13,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 154533888. Throughput: 0: 1695.8, 1: 1689.7. Samples: 38644882. Policy #0 lag: (min: 24.0, avg: 45.7, max: 48.0) -[2023-10-09 03:09:13,975][87372] Avg episode reward: [(0, '6.910'), (1, '7.940')] -[2023-10-09 03:09:14,190][88326] Updated weights for policy 0, policy_version 75452 (0.0009) -[2023-10-09 03:09:15,072][88327] Updated weights for policy 1, policy_version 75490 (0.0009) -[2023-10-09 03:09:15,461][88327] Updated weights for policy 1, policy_version 75500 (0.0010) -[2023-10-09 03:09:15,825][88327] Updated weights for policy 1, policy_version 75510 (0.0009) -[2023-10-09 03:09:16,199][88327] Updated weights for policy 1, policy_version 75520 (0.0009) -[2023-10-09 03:09:18,225][88326] Updated weights for policy 0, policy_version 75462 (0.0009) -[2023-10-09 03:09:18,594][88326] Updated weights for policy 0, policy_version 75472 (0.0010) -[2023-10-09 03:09:18,960][88326] Updated weights for policy 0, policy_version 75482 (0.0010) -[2023-10-09 03:09:18,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.3, 300 sec: 13440.4). Total num frames: 154599424. Throughput: 0: 1687.9, 1: 1701.5. Samples: 38665510. Policy #0 lag: (min: 24.0, avg: 45.7, max: 48.0) -[2023-10-09 03:09:18,974][87372] Avg episode reward: [(0, '6.890'), (1, '7.510')] -[2023-10-09 03:09:20,096][88327] Updated weights for policy 1, policy_version 75530 (0.0007) -[2023-10-09 03:09:20,465][88327] Updated weights for policy 1, policy_version 75540 (0.0009) -[2023-10-09 03:09:20,826][88327] Updated weights for policy 1, policy_version 75550 (0.0009) -[2023-10-09 03:09:23,016][88326] Updated weights for policy 0, policy_version 75492 (0.0010) -[2023-10-09 03:09:23,396][88326] Updated weights for policy 0, policy_version 75502 (0.0008) -[2023-10-09 03:09:23,760][88326] Updated weights for policy 0, policy_version 75512 (0.0008) -[2023-10-09 03:09:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 154664960. Throughput: 0: 1697.0, 1: 1674.1. Samples: 38674970. Policy #0 lag: (min: 24.0, avg: 45.7, max: 48.0) -[2023-10-09 03:09:23,975][87372] Avg episode reward: [(0, '6.740'), (1, '6.810')] -[2023-10-09 03:09:24,739][88327] Updated weights for policy 1, policy_version 75560 (0.0008) -[2023-10-09 03:09:25,109][88327] Updated weights for policy 1, policy_version 75570 (0.0007) -[2023-10-09 03:09:25,465][88327] Updated weights for policy 1, policy_version 75580 (0.0011) -[2023-10-09 03:09:27,802][88326] Updated weights for policy 0, policy_version 75522 (0.0008) -[2023-10-09 03:09:28,158][88326] Updated weights for policy 0, policy_version 75532 (0.0011) -[2023-10-09 03:09:28,532][88326] Updated weights for policy 0, policy_version 75542 (0.0009) -[2023-10-09 03:09:28,894][88326] Updated weights for policy 0, policy_version 75552 (0.0007) -[2023-10-09 03:09:28,974][87372] Fps is (10 sec: 16383.8, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 154763264. Throughput: 0: 1696.1, 1: 1699.8. Samples: 38695872. Policy #0 lag: (min: 24.0, avg: 45.7, max: 48.0) -[2023-10-09 03:09:28,975][87372] Avg episode reward: [(0, '7.010'), (1, '7.720')] -[2023-10-09 03:09:29,523][88327] Updated weights for policy 1, policy_version 75590 (0.0011) -[2023-10-09 03:09:29,892][88327] Updated weights for policy 1, policy_version 75600 (0.0011) -[2023-10-09 03:09:30,253][88327] Updated weights for policy 1, policy_version 75610 (0.0011) -[2023-10-09 03:09:32,863][88326] Updated weights for policy 0, policy_version 75562 (0.0009) -[2023-10-09 03:09:33,227][88326] Updated weights for policy 0, policy_version 75572 (0.0007) -[2023-10-09 03:09:33,597][88326] Updated weights for policy 0, policy_version 75582 (0.0007) -[2023-10-09 03:09:33,974][87372] Fps is (10 sec: 16384.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 154828800. Throughput: 0: 1680.4, 1: 1703.3. Samples: 38716278. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-09 03:09:33,975][87372] Avg episode reward: [(0, '6.980'), (1, '7.290')] -[2023-10-09 03:09:34,232][88327] Updated weights for policy 1, policy_version 75620 (0.0008) -[2023-10-09 03:09:34,601][88327] Updated weights for policy 1, policy_version 75630 (0.0008) -[2023-10-09 03:09:34,968][88327] Updated weights for policy 1, policy_version 75640 (0.0010) -[2023-10-09 03:09:37,645][88326] Updated weights for policy 0, policy_version 75592 (0.0008) -[2023-10-09 03:09:38,018][88326] Updated weights for policy 0, policy_version 75602 (0.0007) -[2023-10-09 03:09:38,392][88326] Updated weights for policy 0, policy_version 75612 (0.0008) -[2023-10-09 03:09:38,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 154894336. Throughput: 0: 1697.5, 1: 1682.8. Samples: 38725988. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-09 03:09:38,975][87372] Avg episode reward: [(0, '6.400'), (1, '7.090')] -[2023-10-09 03:09:39,150][88327] Updated weights for policy 1, policy_version 75650 (0.0008) -[2023-10-09 03:09:39,509][88327] Updated weights for policy 1, policy_version 75660 (0.0010) -[2023-10-09 03:09:39,874][88327] Updated weights for policy 1, policy_version 75670 (0.0008) -[2023-10-09 03:09:40,238][88327] Updated weights for policy 1, policy_version 75680 (0.0011) -[2023-10-09 03:09:42,455][88326] Updated weights for policy 0, policy_version 75622 (0.0008) -[2023-10-09 03:09:42,838][88326] Updated weights for policy 0, policy_version 75632 (0.0008) -[2023-10-09 03:09:43,208][88326] Updated weights for policy 0, policy_version 75642 (0.0009) -[2023-10-09 03:09:43,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 154959872. Throughput: 0: 1695.5, 1: 1695.6. Samples: 38746698. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-09 03:09:43,974][87372] Avg episode reward: [(0, '6.590'), (1, '7.240')] -[2023-10-09 03:09:44,348][88327] Updated weights for policy 1, policy_version 75690 (0.0008) -[2023-10-09 03:09:44,711][88327] Updated weights for policy 1, policy_version 75700 (0.0008) -[2023-10-09 03:09:45,080][88327] Updated weights for policy 1, policy_version 75710 (0.0008) -[2023-10-09 03:09:47,072][88326] Updated weights for policy 0, policy_version 75652 (0.0008) -[2023-10-09 03:09:47,432][88326] Updated weights for policy 0, policy_version 75662 (0.0007) -[2023-10-09 03:09:47,803][88326] Updated weights for policy 0, policy_version 75672 (0.0010) -[2023-10-09 03:09:48,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 155025408. Throughput: 0: 1668.0, 1: 1692.9. Samples: 38766370. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-09 03:09:48,974][87372] Avg episode reward: [(0, '6.450'), (1, '7.750')] -[2023-10-09 03:09:49,071][88327] Updated weights for policy 1, policy_version 75720 (0.0011) -[2023-10-09 03:09:49,432][88327] Updated weights for policy 1, policy_version 75730 (0.0009) -[2023-10-09 03:09:49,802][88327] Updated weights for policy 1, policy_version 75740 (0.0009) -[2023-10-09 03:09:51,914][88326] Updated weights for policy 0, policy_version 75682 (0.0009) -[2023-10-09 03:09:52,280][88326] Updated weights for policy 0, policy_version 75692 (0.0009) -[2023-10-09 03:09:52,648][88326] Updated weights for policy 0, policy_version 75702 (0.0009) -[2023-10-09 03:09:53,011][88326] Updated weights for policy 0, policy_version 75712 (0.0008) -[2023-10-09 03:09:53,840][88327] Updated weights for policy 1, policy_version 75750 (0.0008) -[2023-10-09 03:09:53,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 155090944. Throughput: 0: 1694.8, 1: 1688.1. Samples: 38776638. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-09 03:09:53,974][87372] Avg episode reward: [(0, '6.700'), (1, '7.640')] -[2023-10-09 03:09:54,204][88327] Updated weights for policy 1, policy_version 75760 (0.0008) -[2023-10-09 03:09:54,571][88327] Updated weights for policy 1, policy_version 75770 (0.0009) -[2023-10-09 03:09:57,082][88326] Updated weights for policy 0, policy_version 75722 (0.0008) -[2023-10-09 03:09:57,449][88326] Updated weights for policy 0, policy_version 75732 (0.0007) -[2023-10-09 03:09:57,812][88326] Updated weights for policy 0, policy_version 75742 (0.0007) -[2023-10-09 03:09:58,670][88327] Updated weights for policy 1, policy_version 75780 (0.0008) -[2023-10-09 03:09:58,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 155156480. Throughput: 0: 1682.3, 1: 1696.7. Samples: 38796940. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-09 03:09:58,975][87372] Avg episode reward: [(0, '6.600'), (1, '6.940')] -[2023-10-09 03:09:59,029][88327] Updated weights for policy 1, policy_version 75790 (0.0009) -[2023-10-09 03:09:59,397][88327] Updated weights for policy 1, policy_version 75800 (0.0008) -[2023-10-09 03:10:01,870][88326] Updated weights for policy 0, policy_version 75752 (0.0007) -[2023-10-09 03:10:02,238][88326] Updated weights for policy 0, policy_version 75762 (0.0007) -[2023-10-09 03:10:02,606][88326] Updated weights for policy 0, policy_version 75772 (0.0007) -[2023-10-09 03:10:03,185][88327] Updated weights for policy 1, policy_version 75810 (0.0009) -[2023-10-09 03:10:03,567][88327] Updated weights for policy 1, policy_version 75820 (0.0009) -[2023-10-09 03:10:03,927][88327] Updated weights for policy 1, policy_version 75830 (0.0007) -[2023-10-09 03:10:03,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 155222016. Throughput: 0: 1674.7, 1: 1699.6. Samples: 38817354. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-09 03:10:03,974][87372] Avg episode reward: [(0, '6.530'), (1, '7.260')] -[2023-10-09 03:10:04,289][88327] Updated weights for policy 1, policy_version 75840 (0.0007) -[2023-10-09 03:10:06,606][88326] Updated weights for policy 0, policy_version 75782 (0.0009) -[2023-10-09 03:10:06,970][88326] Updated weights for policy 0, policy_version 75792 (0.0008) -[2023-10-09 03:10:07,335][88326] Updated weights for policy 0, policy_version 75802 (0.0010) -[2023-10-09 03:10:08,248][88327] Updated weights for policy 1, policy_version 75850 (0.0008) -[2023-10-09 03:10:08,612][88327] Updated weights for policy 1, policy_version 75860 (0.0007) -[2023-10-09 03:10:08,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 155287552. Throughput: 0: 1697.3, 1: 1696.7. Samples: 38827700. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-09 03:10:08,974][87372] Avg episode reward: [(0, '7.020'), (1, '8.120')] -[2023-10-09 03:10:08,980][88327] Updated weights for policy 1, policy_version 75870 (0.0008) -[2023-10-09 03:10:11,271][88326] Updated weights for policy 0, policy_version 75812 (0.0011) -[2023-10-09 03:10:11,640][88326] Updated weights for policy 0, policy_version 75822 (0.0008) -[2023-10-09 03:10:12,003][88326] Updated weights for policy 0, policy_version 75832 (0.0008) -[2023-10-09 03:10:13,068][88327] Updated weights for policy 1, policy_version 75880 (0.0010) -[2023-10-09 03:10:13,433][88327] Updated weights for policy 1, policy_version 75890 (0.0009) -[2023-10-09 03:10:13,792][88327] Updated weights for policy 1, policy_version 75900 (0.0008) -[2023-10-09 03:10:13,974][87372] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 155385856. Throughput: 0: 1678.9, 1: 1698.7. Samples: 38847864. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-09 03:10:13,975][87372] Avg episode reward: [(0, '7.110'), (1, '7.970')] -[2023-10-09 03:10:16,016][88326] Updated weights for policy 0, policy_version 75842 (0.0007) -[2023-10-09 03:10:16,430][88326] Updated weights for policy 0, policy_version 75852 (0.0008) -[2023-10-09 03:10:16,795][88326] Updated weights for policy 0, policy_version 75862 (0.0010) -[2023-10-09 03:10:17,170][88326] Updated weights for policy 0, policy_version 75872 (0.0007) -[2023-10-09 03:10:17,939][88327] Updated weights for policy 1, policy_version 75910 (0.0009) -[2023-10-09 03:10:18,304][88327] Updated weights for policy 1, policy_version 75920 (0.0008) -[2023-10-09 03:10:18,674][88327] Updated weights for policy 1, policy_version 75930 (0.0008) -[2023-10-09 03:10:18,974][87372] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 155451392. Throughput: 0: 1687.6, 1: 1693.3. Samples: 38868420. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-09 03:10:18,975][87372] Avg episode reward: [(0, '7.280'), (1, '7.520')] -[2023-10-09 03:10:21,168][88326] Updated weights for policy 0, policy_version 75882 (0.0009) -[2023-10-09 03:10:21,543][88326] Updated weights for policy 0, policy_version 75892 (0.0008) -[2023-10-09 03:10:21,911][88326] Updated weights for policy 0, policy_version 75902 (0.0009) -[2023-10-09 03:10:22,641][88327] Updated weights for policy 1, policy_version 75940 (0.0009) -[2023-10-09 03:10:23,001][88327] Updated weights for policy 1, policy_version 75950 (0.0009) -[2023-10-09 03:10:23,374][88327] Updated weights for policy 1, policy_version 75960 (0.0008) -[2023-10-09 03:10:23,974][87372] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 155516928. Throughput: 0: 1691.2, 1: 1707.7. Samples: 38878938. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-09 03:10:23,975][87372] Avg episode reward: [(0, '7.630'), (1, '8.120')] -[2023-10-09 03:10:26,017][88326] Updated weights for policy 0, policy_version 75912 (0.0008) -[2023-10-09 03:10:26,387][88326] Updated weights for policy 0, policy_version 75922 (0.0009) -[2023-10-09 03:10:26,766][88326] Updated weights for policy 0, policy_version 75932 (0.0010) -[2023-10-09 03:10:27,413][88327] Updated weights for policy 1, policy_version 75970 (0.0009) -[2023-10-09 03:10:27,778][88327] Updated weights for policy 1, policy_version 75980 (0.0007) -[2023-10-09 03:10:28,133][88327] Updated weights for policy 1, policy_version 75990 (0.0011) -[2023-10-09 03:10:28,499][88327] Updated weights for policy 1, policy_version 76000 (0.0008) -[2023-10-09 03:10:28,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 155582464. Throughput: 0: 1672.5, 1: 1715.5. Samples: 38899158. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-09 03:10:28,975][87372] Avg episode reward: [(0, '8.110'), (1, '7.900')] -[2023-10-09 03:10:30,840][88326] Updated weights for policy 0, policy_version 75942 (0.0008) -[2023-10-09 03:10:31,206][88326] Updated weights for policy 0, policy_version 75952 (0.0009) -[2023-10-09 03:10:31,573][88326] Updated weights for policy 0, policy_version 75962 (0.0009) -[2023-10-09 03:10:32,555][88327] Updated weights for policy 1, policy_version 76010 (0.0009) -[2023-10-09 03:10:32,919][88327] Updated weights for policy 1, policy_version 76020 (0.0009) -[2023-10-09 03:10:33,277][88327] Updated weights for policy 1, policy_version 76030 (0.0008) -[2023-10-09 03:10:33,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 155648000. Throughput: 0: 1708.9, 1: 1692.3. Samples: 38919428. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-09 03:10:33,975][87372] Avg episode reward: [(0, '7.150'), (1, '7.110')] -[2023-10-09 03:10:33,987][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000076032_77856768.pth... -[2023-10-09 03:10:33,987][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000075968_77791232.pth... -[2023-10-09 03:10:34,023][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000074432_76218368.pth -[2023-10-09 03:10:34,023][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000074400_76185600.pth -[2023-10-09 03:10:35,610][88326] Updated weights for policy 0, policy_version 75972 (0.0008) -[2023-10-09 03:10:35,985][88326] Updated weights for policy 0, policy_version 75982 (0.0011) -[2023-10-09 03:10:36,340][88326] Updated weights for policy 0, policy_version 75992 (0.0011) -[2023-10-09 03:10:37,278][88327] Updated weights for policy 1, policy_version 76040 (0.0007) -[2023-10-09 03:10:37,647][88327] Updated weights for policy 1, policy_version 76050 (0.0008) -[2023-10-09 03:10:38,010][88327] Updated weights for policy 1, policy_version 76060 (0.0008) -[2023-10-09 03:10:38,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 155713536. Throughput: 0: 1690.2, 1: 1717.1. Samples: 38929964. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-09 03:10:38,975][87372] Avg episode reward: [(0, '6.330'), (1, '7.090')] -[2023-10-09 03:10:40,353][88326] Updated weights for policy 0, policy_version 76002 (0.0009) -[2023-10-09 03:10:40,719][88326] Updated weights for policy 0, policy_version 76012 (0.0009) -[2023-10-09 03:10:41,091][88326] Updated weights for policy 0, policy_version 76022 (0.0010) -[2023-10-09 03:10:41,455][88326] Updated weights for policy 0, policy_version 76032 (0.0008) -[2023-10-09 03:10:41,905][88327] Updated weights for policy 1, policy_version 76070 (0.0010) -[2023-10-09 03:10:42,266][88327] Updated weights for policy 1, policy_version 76080 (0.0008) -[2023-10-09 03:10:42,626][88327] Updated weights for policy 1, policy_version 76090 (0.0009) -[2023-10-09 03:10:43,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 155779072. Throughput: 0: 1690.4, 1: 1706.4. Samples: 38949792. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-09 03:10:43,975][87372] Avg episode reward: [(0, '6.850'), (1, '7.450')] -[2023-10-09 03:10:45,472][88326] Updated weights for policy 0, policy_version 76042 (0.0010) -[2023-10-09 03:10:45,831][88326] Updated weights for policy 0, policy_version 76052 (0.0007) -[2023-10-09 03:10:46,207][88326] Updated weights for policy 0, policy_version 76062 (0.0007) -[2023-10-09 03:10:46,645][88327] Updated weights for policy 1, policy_version 76100 (0.0009) -[2023-10-09 03:10:47,010][88327] Updated weights for policy 1, policy_version 76110 (0.0010) -[2023-10-09 03:10:47,376][88327] Updated weights for policy 1, policy_version 76120 (0.0011) -[2023-10-09 03:10:48,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 155844608. Throughput: 0: 1708.1, 1: 1683.1. Samples: 38969956. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-09 03:10:48,975][87372] Avg episode reward: [(0, '6.220'), (1, '7.330')] -[2023-10-09 03:10:50,309][88326] Updated weights for policy 0, policy_version 76072 (0.0011) -[2023-10-09 03:10:50,679][88326] Updated weights for policy 0, policy_version 76082 (0.0008) -[2023-10-09 03:10:51,042][88326] Updated weights for policy 0, policy_version 76092 (0.0008) -[2023-10-09 03:10:51,493][88327] Updated weights for policy 1, policy_version 76130 (0.0008) -[2023-10-09 03:10:51,910][88327] Updated weights for policy 1, policy_version 76140 (0.0009) -[2023-10-09 03:10:52,280][88327] Updated weights for policy 1, policy_version 76150 (0.0009) -[2023-10-09 03:10:52,647][88327] Updated weights for policy 1, policy_version 76160 (0.0009) -[2023-10-09 03:10:53,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 155910144. Throughput: 0: 1677.2, 1: 1715.5. Samples: 38980370. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-09 03:10:53,975][87372] Avg episode reward: [(0, '6.190'), (1, '7.420')] -[2023-10-09 03:10:55,128][88326] Updated weights for policy 0, policy_version 76102 (0.0008) -[2023-10-09 03:10:55,489][88326] Updated weights for policy 0, policy_version 76112 (0.0009) -[2023-10-09 03:10:55,870][88326] Updated weights for policy 0, policy_version 76122 (0.0010) -[2023-10-09 03:10:56,642][88327] Updated weights for policy 1, policy_version 76170 (0.0009) -[2023-10-09 03:10:57,002][88327] Updated weights for policy 1, policy_version 76180 (0.0009) -[2023-10-09 03:10:57,373][88327] Updated weights for policy 1, policy_version 76190 (0.0008) -[2023-10-09 03:10:58,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 155975680. Throughput: 0: 1699.2, 1: 1683.5. Samples: 39000084. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-09 03:10:58,975][87372] Avg episode reward: [(0, '6.790'), (1, '7.390')] -[2023-10-09 03:10:59,926][88326] Updated weights for policy 0, policy_version 76132 (0.0009) -[2023-10-09 03:11:00,286][88326] Updated weights for policy 0, policy_version 76142 (0.0008) -[2023-10-09 03:11:00,667][88326] Updated weights for policy 0, policy_version 76152 (0.0009) -[2023-10-09 03:11:01,529][88327] Updated weights for policy 1, policy_version 76200 (0.0010) -[2023-10-09 03:11:01,898][88327] Updated weights for policy 1, policy_version 76210 (0.0009) -[2023-10-09 03:11:02,261][88327] Updated weights for policy 1, policy_version 76220 (0.0009) -[2023-10-09 03:11:03,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 156041216. Throughput: 0: 1701.2, 1: 1680.5. Samples: 39020598. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-09 03:11:03,975][87372] Avg episode reward: [(0, '6.610'), (1, '7.710')] -[2023-10-09 03:11:04,705][88326] Updated weights for policy 0, policy_version 76162 (0.0008) -[2023-10-09 03:11:05,090][88326] Updated weights for policy 0, policy_version 76172 (0.0007) -[2023-10-09 03:11:05,465][88326] Updated weights for policy 0, policy_version 76182 (0.0007) -[2023-10-09 03:11:05,828][88326] Updated weights for policy 0, policy_version 76192 (0.0010) -[2023-10-09 03:11:06,255][88327] Updated weights for policy 1, policy_version 76230 (0.0008) -[2023-10-09 03:11:06,613][88327] Updated weights for policy 1, policy_version 76240 (0.0010) -[2023-10-09 03:11:06,987][88327] Updated weights for policy 1, policy_version 76250 (0.0008) -[2023-10-09 03:11:08,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 156106752. Throughput: 0: 1680.5, 1: 1698.8. Samples: 39031004. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-09 03:11:08,975][87372] Avg episode reward: [(0, '6.540'), (1, '7.450')] -[2023-10-09 03:11:10,031][88326] Updated weights for policy 0, policy_version 76202 (0.0008) -[2023-10-09 03:11:10,402][88326] Updated weights for policy 0, policy_version 76212 (0.0010) -[2023-10-09 03:11:10,763][88326] Updated weights for policy 0, policy_version 76222 (0.0011) -[2023-10-09 03:11:11,015][88327] Updated weights for policy 1, policy_version 76260 (0.0009) -[2023-10-09 03:11:11,376][88327] Updated weights for policy 1, policy_version 76270 (0.0010) -[2023-10-09 03:11:11,753][88327] Updated weights for policy 1, policy_version 76280 (0.0009) -[2023-10-09 03:11:13,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 156172288. Throughput: 0: 1697.8, 1: 1666.8. Samples: 39050566. Policy #0 lag: (min: 8.0, avg: 22.1, max: 40.0) -[2023-10-09 03:11:13,975][87372] Avg episode reward: [(0, '6.440'), (1, '6.880')] -[2023-10-09 03:11:14,801][88326] Updated weights for policy 0, policy_version 76232 (0.0012) -[2023-10-09 03:11:15,166][88326] Updated weights for policy 0, policy_version 76242 (0.0010) -[2023-10-09 03:11:15,532][88326] Updated weights for policy 0, policy_version 76252 (0.0009) -[2023-10-09 03:11:15,793][88327] Updated weights for policy 1, policy_version 76290 (0.0007) -[2023-10-09 03:11:16,155][88327] Updated weights for policy 1, policy_version 76300 (0.0008) -[2023-10-09 03:11:16,525][88327] Updated weights for policy 1, policy_version 76310 (0.0009) -[2023-10-09 03:11:16,895][88327] Updated weights for policy 1, policy_version 76320 (0.0008) -[2023-10-09 03:11:18,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 156237824. Throughput: 0: 1694.4, 1: 1689.5. Samples: 39071702. Policy #0 lag: (min: 8.0, avg: 22.1, max: 40.0) -[2023-10-09 03:11:18,975][87372] Avg episode reward: [(0, '6.710'), (1, '7.040')] -[2023-10-09 03:11:19,443][88326] Updated weights for policy 0, policy_version 76262 (0.0009) -[2023-10-09 03:11:19,816][88326] Updated weights for policy 0, policy_version 76272 (0.0009) -[2023-10-09 03:11:20,175][88326] Updated weights for policy 0, policy_version 76282 (0.0010) -[2023-10-09 03:11:20,770][88327] Updated weights for policy 1, policy_version 76330 (0.0008) -[2023-10-09 03:11:21,136][88327] Updated weights for policy 1, policy_version 76340 (0.0008) -[2023-10-09 03:11:21,497][88327] Updated weights for policy 1, policy_version 76350 (0.0007) -[2023-10-09 03:11:23,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 156303360. Throughput: 0: 1685.1, 1: 1682.8. Samples: 39081516. Policy #0 lag: (min: 8.0, avg: 22.1, max: 40.0) -[2023-10-09 03:11:23,974][87372] Avg episode reward: [(0, '6.870'), (1, '7.920')] -[2023-10-09 03:11:24,185][88326] Updated weights for policy 0, policy_version 76292 (0.0011) -[2023-10-09 03:11:24,559][88326] Updated weights for policy 0, policy_version 76302 (0.0009) -[2023-10-09 03:11:24,925][88326] Updated weights for policy 0, policy_version 76312 (0.0010) -[2023-10-09 03:11:25,443][88327] Updated weights for policy 1, policy_version 76360 (0.0009) -[2023-10-09 03:11:25,800][88327] Updated weights for policy 1, policy_version 76370 (0.0009) -[2023-10-09 03:11:26,159][88327] Updated weights for policy 1, policy_version 76380 (0.0012) -[2023-10-09 03:11:28,921][88326] Updated weights for policy 0, policy_version 76322 (0.0008) -[2023-10-09 03:11:28,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 156368896. Throughput: 0: 1696.5, 1: 1682.9. Samples: 39101862. Policy #0 lag: (min: 8.0, avg: 22.1, max: 40.0) -[2023-10-09 03:11:28,975][87372] Avg episode reward: [(0, '7.280'), (1, '7.310')] -[2023-10-09 03:11:29,297][88326] Updated weights for policy 0, policy_version 76332 (0.0010) -[2023-10-09 03:11:29,669][88326] Updated weights for policy 0, policy_version 76342 (0.0008) -[2023-10-09 03:11:30,035][88326] Updated weights for policy 0, policy_version 76352 (0.0009) -[2023-10-09 03:11:30,157][88327] Updated weights for policy 1, policy_version 76390 (0.0009) -[2023-10-09 03:11:30,529][88327] Updated weights for policy 1, policy_version 76400 (0.0008) -[2023-10-09 03:11:30,891][88327] Updated weights for policy 1, policy_version 76410 (0.0007) -[2023-10-09 03:11:33,881][88326] Updated weights for policy 0, policy_version 76362 (0.0008) -[2023-10-09 03:11:33,974][87372] Fps is (10 sec: 13106.8, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 156434432. Throughput: 0: 1695.0, 1: 1703.4. Samples: 39122882. Policy #0 lag: (min: 8.0, avg: 22.1, max: 40.0) -[2023-10-09 03:11:33,975][87372] Avg episode reward: [(0, '7.230'), (1, '7.360')] -[2023-10-09 03:11:34,259][88326] Updated weights for policy 0, policy_version 76372 (0.0007) -[2023-10-09 03:11:34,620][88326] Updated weights for policy 0, policy_version 76382 (0.0008) -[2023-10-09 03:11:34,892][88327] Updated weights for policy 1, policy_version 76420 (0.0007) -[2023-10-09 03:11:35,254][88327] Updated weights for policy 1, policy_version 76430 (0.0008) -[2023-10-09 03:11:35,613][88327] Updated weights for policy 1, policy_version 76440 (0.0009) -[2023-10-09 03:11:38,693][88326] Updated weights for policy 0, policy_version 76392 (0.0008) -[2023-10-09 03:11:38,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 156499968. Throughput: 0: 1697.7, 1: 1674.2. Samples: 39132106. Policy #0 lag: (min: 8.0, avg: 22.1, max: 40.0) -[2023-10-09 03:11:38,975][87372] Avg episode reward: [(0, '7.370'), (1, '7.390')] -[2023-10-09 03:11:39,059][88326] Updated weights for policy 0, policy_version 76402 (0.0010) -[2023-10-09 03:11:39,437][88326] Updated weights for policy 0, policy_version 76412 (0.0009) -[2023-10-09 03:11:39,642][88327] Updated weights for policy 1, policy_version 76450 (0.0008) -[2023-10-09 03:11:40,006][88327] Updated weights for policy 1, policy_version 76460 (0.0011) -[2023-10-09 03:11:40,365][88327] Updated weights for policy 1, policy_version 76470 (0.0009) -[2023-10-09 03:11:40,735][88327] Updated weights for policy 1, policy_version 76480 (0.0008) -[2023-10-09 03:11:43,580][88326] Updated weights for policy 0, policy_version 76422 (0.0009) -[2023-10-09 03:11:43,945][88326] Updated weights for policy 0, policy_version 76432 (0.0010) -[2023-10-09 03:11:43,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.3, 300 sec: 13440.4). Total num frames: 156565504. Throughput: 0: 1695.7, 1: 1702.1. Samples: 39152984. Policy #0 lag: (min: 8.0, avg: 22.1, max: 40.0) -[2023-10-09 03:11:43,975][87372] Avg episode reward: [(0, '7.350'), (1, '7.510')] -[2023-10-09 03:11:44,309][88326] Updated weights for policy 0, policy_version 76442 (0.0010) -[2023-10-09 03:11:44,945][88327] Updated weights for policy 1, policy_version 76490 (0.0009) -[2023-10-09 03:11:45,322][88327] Updated weights for policy 1, policy_version 76500 (0.0007) -[2023-10-09 03:11:45,677][88327] Updated weights for policy 1, policy_version 76510 (0.0010) -[2023-10-09 03:11:48,350][88326] Updated weights for policy 0, policy_version 76452 (0.0008) -[2023-10-09 03:11:48,716][88326] Updated weights for policy 0, policy_version 76462 (0.0008) -[2023-10-09 03:11:48,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 156631040. Throughput: 0: 1696.4, 1: 1704.5. Samples: 39173638. Policy #0 lag: (min: 8.0, avg: 22.1, max: 40.0) -[2023-10-09 03:11:48,975][87372] Avg episode reward: [(0, '7.780'), (1, '7.070')] -[2023-10-09 03:11:49,084][88326] Updated weights for policy 0, policy_version 76472 (0.0008) -[2023-10-09 03:11:49,829][88327] Updated weights for policy 1, policy_version 76520 (0.0008) -[2023-10-09 03:11:50,194][88327] Updated weights for policy 1, policy_version 76530 (0.0008) -[2023-10-09 03:11:50,563][88327] Updated weights for policy 1, policy_version 76540 (0.0009) -[2023-10-09 03:11:53,096][88326] Updated weights for policy 0, policy_version 76482 (0.0007) -[2023-10-09 03:11:53,486][88326] Updated weights for policy 0, policy_version 76492 (0.0008) -[2023-10-09 03:11:53,846][88326] Updated weights for policy 0, policy_version 76502 (0.0009) -[2023-10-09 03:11:53,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 156696576. Throughput: 0: 1699.5, 1: 1674.5. Samples: 39182836. Policy #0 lag: (min: 8.0, avg: 22.1, max: 40.0) -[2023-10-09 03:11:53,975][87372] Avg episode reward: [(0, '7.060'), (1, '7.540')] -[2023-10-09 03:11:54,210][88326] Updated weights for policy 0, policy_version 76512 (0.0011) -[2023-10-09 03:11:54,702][88327] Updated weights for policy 1, policy_version 76550 (0.0008) -[2023-10-09 03:11:55,063][88327] Updated weights for policy 1, policy_version 76560 (0.0007) -[2023-10-09 03:11:55,432][88327] Updated weights for policy 1, policy_version 76570 (0.0010) -[2023-10-09 03:11:58,229][88326] Updated weights for policy 0, policy_version 76522 (0.0012) -[2023-10-09 03:11:58,591][88326] Updated weights for policy 0, policy_version 76532 (0.0011) -[2023-10-09 03:11:58,955][88326] Updated weights for policy 0, policy_version 76542 (0.0011) -[2023-10-09 03:11:58,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 156762112. Throughput: 0: 1700.7, 1: 1698.7. Samples: 39203538. Policy #0 lag: (min: 8.0, avg: 22.1, max: 40.0) -[2023-10-09 03:11:58,975][87372] Avg episode reward: [(0, '7.340'), (1, '7.160')] -[2023-10-09 03:11:59,393][88327] Updated weights for policy 1, policy_version 76580 (0.0007) -[2023-10-09 03:11:59,757][88327] Updated weights for policy 1, policy_version 76590 (0.0009) -[2023-10-09 03:12:00,122][88327] Updated weights for policy 1, policy_version 76600 (0.0008) -[2023-10-09 03:12:02,989][88326] Updated weights for policy 0, policy_version 76552 (0.0010) -[2023-10-09 03:12:03,361][88326] Updated weights for policy 0, policy_version 76562 (0.0007) -[2023-10-09 03:12:03,728][88326] Updated weights for policy 0, policy_version 76572 (0.0008) -[2023-10-09 03:12:03,974][87372] Fps is (10 sec: 16384.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 156860416. Throughput: 0: 1681.6, 1: 1701.6. Samples: 39223944. Policy #0 lag: (min: 17.0, avg: 20.4, max: 49.0) -[2023-10-09 03:12:03,975][87372] Avg episode reward: [(0, '7.000'), (1, '7.150')] -[2023-10-09 03:12:04,235][88327] Updated weights for policy 1, policy_version 76610 (0.0011) -[2023-10-09 03:12:04,593][88327] Updated weights for policy 1, policy_version 76620 (0.0009) -[2023-10-09 03:12:04,957][88327] Updated weights for policy 1, policy_version 76630 (0.0007) -[2023-10-09 03:12:05,318][88327] Updated weights for policy 1, policy_version 76640 (0.0008) -[2023-10-09 03:12:07,750][88326] Updated weights for policy 0, policy_version 76582 (0.0008) -[2023-10-09 03:12:08,113][88326] Updated weights for policy 0, policy_version 76592 (0.0008) -[2023-10-09 03:12:08,480][88326] Updated weights for policy 0, policy_version 76602 (0.0007) -[2023-10-09 03:12:08,974][87372] Fps is (10 sec: 16383.8, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 156925952. Throughput: 0: 1694.1, 1: 1689.4. Samples: 39233774. Policy #0 lag: (min: 17.0, avg: 20.4, max: 49.0) -[2023-10-09 03:12:08,975][87372] Avg episode reward: [(0, '6.900'), (1, '7.210')] -[2023-10-09 03:12:09,106][88327] Updated weights for policy 1, policy_version 76650 (0.0011) -[2023-10-09 03:12:09,476][88327] Updated weights for policy 1, policy_version 76660 (0.0009) -[2023-10-09 03:12:09,846][88327] Updated weights for policy 1, policy_version 76670 (0.0008) -[2023-10-09 03:12:12,553][88326] Updated weights for policy 0, policy_version 76612 (0.0008) -[2023-10-09 03:12:12,926][88326] Updated weights for policy 0, policy_version 76622 (0.0009) -[2023-10-09 03:12:13,288][88326] Updated weights for policy 0, policy_version 76632 (0.0009) -[2023-10-09 03:12:13,839][88327] Updated weights for policy 1, policy_version 76680 (0.0009) -[2023-10-09 03:12:13,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 156991488. Throughput: 0: 1701.6, 1: 1703.7. Samples: 39255100. Policy #0 lag: (min: 17.0, avg: 20.4, max: 49.0) -[2023-10-09 03:12:13,975][87372] Avg episode reward: [(0, '6.390'), (1, '7.580')] -[2023-10-09 03:12:14,206][88327] Updated weights for policy 1, policy_version 76690 (0.0008) -[2023-10-09 03:12:14,579][88327] Updated weights for policy 1, policy_version 76700 (0.0007) -[2023-10-09 03:12:17,223][88326] Updated weights for policy 0, policy_version 76642 (0.0007) -[2023-10-09 03:12:17,599][88326] Updated weights for policy 0, policy_version 76652 (0.0007) -[2023-10-09 03:12:17,968][88326] Updated weights for policy 0, policy_version 76662 (0.0007) -[2023-10-09 03:12:18,336][88326] Updated weights for policy 0, policy_version 76672 (0.0007) -[2023-10-09 03:12:18,615][88327] Updated weights for policy 1, policy_version 76710 (0.0009) -[2023-10-09 03:12:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 157057024. Throughput: 0: 1675.9, 1: 1700.9. Samples: 39274838. Policy #0 lag: (min: 17.0, avg: 20.4, max: 49.0) -[2023-10-09 03:12:18,975][87372] Avg episode reward: [(0, '7.170'), (1, '6.980')] -[2023-10-09 03:12:18,977][88327] Updated weights for policy 1, policy_version 76720 (0.0010) -[2023-10-09 03:12:19,351][88327] Updated weights for policy 1, policy_version 76730 (0.0010) -[2023-10-09 03:12:22,175][88326] Updated weights for policy 0, policy_version 76682 (0.0009) -[2023-10-09 03:12:22,540][88326] Updated weights for policy 0, policy_version 76692 (0.0009) -[2023-10-09 03:12:22,898][88326] Updated weights for policy 0, policy_version 76702 (0.0007) -[2023-10-09 03:12:23,536][88327] Updated weights for policy 1, policy_version 76740 (0.0008) -[2023-10-09 03:12:23,896][88327] Updated weights for policy 1, policy_version 76750 (0.0011) -[2023-10-09 03:12:23,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 157122560. Throughput: 0: 1705.7, 1: 1695.2. Samples: 39285150. Policy #0 lag: (min: 17.0, avg: 20.4, max: 49.0) -[2023-10-09 03:12:23,974][87372] Avg episode reward: [(0, '7.300'), (1, '7.320')] -[2023-10-09 03:12:24,262][88327] Updated weights for policy 1, policy_version 76760 (0.0007) -[2023-10-09 03:12:26,980][88326] Updated weights for policy 0, policy_version 76712 (0.0008) -[2023-10-09 03:12:27,350][88326] Updated weights for policy 0, policy_version 76722 (0.0008) -[2023-10-09 03:12:27,715][88326] Updated weights for policy 0, policy_version 76732 (0.0009) -[2023-10-09 03:12:28,057][88327] Updated weights for policy 1, policy_version 76770 (0.0009) -[2023-10-09 03:12:28,416][88327] Updated weights for policy 1, policy_version 76780 (0.0010) -[2023-10-09 03:12:28,794][88327] Updated weights for policy 1, policy_version 76790 (0.0010) -[2023-10-09 03:12:28,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 157188096. Throughput: 0: 1691.3, 1: 1699.2. Samples: 39305556. Policy #0 lag: (min: 17.0, avg: 20.4, max: 49.0) -[2023-10-09 03:12:28,975][87372] Avg episode reward: [(0, '7.390'), (1, '7.770')] -[2023-10-09 03:12:29,158][88327] Updated weights for policy 1, policy_version 76800 (0.0009) -[2023-10-09 03:12:31,786][88326] Updated weights for policy 0, policy_version 76742 (0.0009) -[2023-10-09 03:12:32,150][88326] Updated weights for policy 0, policy_version 76752 (0.0009) -[2023-10-09 03:12:32,520][88326] Updated weights for policy 0, policy_version 76762 (0.0007) -[2023-10-09 03:12:33,317][88327] Updated weights for policy 1, policy_version 76810 (0.0008) -[2023-10-09 03:12:33,693][88327] Updated weights for policy 1, policy_version 76820 (0.0007) -[2023-10-09 03:12:33,974][87372] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 157253632. Throughput: 0: 1676.4, 1: 1696.4. Samples: 39325412. Policy #0 lag: (min: 17.0, avg: 20.4, max: 49.0) -[2023-10-09 03:12:33,975][87372] Avg episode reward: [(0, '7.290'), (1, '7.780')] -[2023-10-09 03:12:33,985][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000076768_78610432.pth... -[2023-10-09 03:12:34,022][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000075168_76972032.pth -[2023-10-09 03:12:34,049][88327] Updated weights for policy 1, policy_version 76830 (0.0008) -[2023-10-09 03:12:34,118][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000076832_78675968.pth... -[2023-10-09 03:12:34,158][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000075232_77037568.pth -[2023-10-09 03:12:36,675][88326] Updated weights for policy 0, policy_version 76772 (0.0007) -[2023-10-09 03:12:37,052][88326] Updated weights for policy 0, policy_version 76782 (0.0008) -[2023-10-09 03:12:37,421][88326] Updated weights for policy 0, policy_version 76792 (0.0007) -[2023-10-09 03:12:38,133][88327] Updated weights for policy 1, policy_version 76840 (0.0008) -[2023-10-09 03:12:38,495][88327] Updated weights for policy 1, policy_version 76850 (0.0009) -[2023-10-09 03:12:38,862][88327] Updated weights for policy 1, policy_version 76860 (0.0008) -[2023-10-09 03:12:38,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 157319168. Throughput: 0: 1702.2, 1: 1698.6. Samples: 39335872. Policy #0 lag: (min: 17.0, avg: 20.4, max: 49.0) -[2023-10-09 03:12:38,975][87372] Avg episode reward: [(0, '6.560'), (1, '6.790')] -[2023-10-09 03:12:41,209][88326] Updated weights for policy 0, policy_version 76802 (0.0007) -[2023-10-09 03:12:41,569][88326] Updated weights for policy 0, policy_version 76812 (0.0008) -[2023-10-09 03:12:41,933][88326] Updated weights for policy 0, policy_version 76822 (0.0010) -[2023-10-09 03:12:42,301][88326] Updated weights for policy 0, policy_version 76832 (0.0007) -[2023-10-09 03:12:42,970][88327] Updated weights for policy 1, policy_version 76870 (0.0009) -[2023-10-09 03:12:43,330][88327] Updated weights for policy 1, policy_version 76880 (0.0008) -[2023-10-09 03:12:43,694][88327] Updated weights for policy 1, policy_version 76890 (0.0009) -[2023-10-09 03:12:43,974][87372] Fps is (10 sec: 16384.1, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 157417472. Throughput: 0: 1681.7, 1: 1703.9. Samples: 39355888. Policy #0 lag: (min: 17.0, avg: 20.4, max: 49.0) -[2023-10-09 03:12:43,975][87372] Avg episode reward: [(0, '6.820'), (1, '7.220')] -[2023-10-09 03:12:46,556][88326] Updated weights for policy 0, policy_version 76842 (0.0007) -[2023-10-09 03:12:46,925][88326] Updated weights for policy 0, policy_version 76852 (0.0007) -[2023-10-09 03:12:47,296][88326] Updated weights for policy 0, policy_version 76862 (0.0007) -[2023-10-09 03:12:47,777][88327] Updated weights for policy 1, policy_version 76900 (0.0009) -[2023-10-09 03:12:48,145][88327] Updated weights for policy 1, policy_version 76910 (0.0010) -[2023-10-09 03:12:48,504][88327] Updated weights for policy 1, policy_version 76920 (0.0010) -[2023-10-09 03:12:48,974][87372] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 157483008. Throughput: 0: 1685.9, 1: 1693.7. Samples: 39376026. Policy #0 lag: (min: 31.0, avg: 44.1, max: 63.0) -[2023-10-09 03:12:48,975][87372] Avg episode reward: [(0, '6.660'), (1, '7.150')] -[2023-10-09 03:12:51,480][88326] Updated weights for policy 0, policy_version 76872 (0.0008) -[2023-10-09 03:12:51,863][88326] Updated weights for policy 0, policy_version 76882 (0.0008) -[2023-10-09 03:12:52,238][88326] Updated weights for policy 0, policy_version 76892 (0.0009) -[2023-10-09 03:12:52,636][88327] Updated weights for policy 1, policy_version 76930 (0.0010) -[2023-10-09 03:12:53,000][88327] Updated weights for policy 1, policy_version 76940 (0.0009) -[2023-10-09 03:12:53,366][88327] Updated weights for policy 1, policy_version 76950 (0.0007) -[2023-10-09 03:12:53,722][88327] Updated weights for policy 1, policy_version 76960 (0.0008) -[2023-10-09 03:12:53,974][87372] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 157548544. Throughput: 0: 1698.7, 1: 1700.8. Samples: 39386750. Policy #0 lag: (min: 31.0, avg: 44.1, max: 63.0) -[2023-10-09 03:12:53,975][87372] Avg episode reward: [(0, '6.610'), (1, '7.310')] -[2023-10-09 03:12:56,224][88326] Updated weights for policy 0, policy_version 76902 (0.0009) -[2023-10-09 03:12:56,591][88326] Updated weights for policy 0, policy_version 76912 (0.0008) -[2023-10-09 03:12:56,962][88326] Updated weights for policy 0, policy_version 76922 (0.0009) -[2023-10-09 03:12:57,596][88327] Updated weights for policy 1, policy_version 76970 (0.0007) -[2023-10-09 03:12:57,968][88327] Updated weights for policy 1, policy_version 76980 (0.0007) -[2023-10-09 03:12:58,329][88327] Updated weights for policy 1, policy_version 76990 (0.0008) -[2023-10-09 03:12:58,974][87372] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 157614080. Throughput: 0: 1664.3, 1: 1702.7. Samples: 39406618. Policy #0 lag: (min: 31.0, avg: 44.1, max: 63.0) -[2023-10-09 03:12:58,975][87372] Avg episode reward: [(0, '6.750'), (1, '7.170')] -[2023-10-09 03:13:01,017][88326] Updated weights for policy 0, policy_version 76932 (0.0009) -[2023-10-09 03:13:01,385][88326] Updated weights for policy 0, policy_version 76942 (0.0008) -[2023-10-09 03:13:01,758][88326] Updated weights for policy 0, policy_version 76952 (0.0008) -[2023-10-09 03:13:02,359][88327] Updated weights for policy 1, policy_version 77000 (0.0008) -[2023-10-09 03:13:02,723][88327] Updated weights for policy 1, policy_version 77010 (0.0009) -[2023-10-09 03:13:03,096][88327] Updated weights for policy 1, policy_version 77020 (0.0008) -[2023-10-09 03:13:03,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 157679616. Throughput: 0: 1688.0, 1: 1681.1. Samples: 39426444. Policy #0 lag: (min: 31.0, avg: 44.1, max: 63.0) -[2023-10-09 03:13:03,975][87372] Avg episode reward: [(0, '6.810'), (1, '7.070')] -[2023-10-09 03:13:05,837][88326] Updated weights for policy 0, policy_version 76962 (0.0010) -[2023-10-09 03:13:06,201][88326] Updated weights for policy 0, policy_version 76972 (0.0011) -[2023-10-09 03:13:06,565][88326] Updated weights for policy 0, policy_version 76982 (0.0011) -[2023-10-09 03:13:06,926][88326] Updated weights for policy 0, policy_version 76992 (0.0009) -[2023-10-09 03:13:06,957][88327] Updated weights for policy 1, policy_version 77030 (0.0008) -[2023-10-09 03:13:07,317][88327] Updated weights for policy 1, policy_version 77040 (0.0010) -[2023-10-09 03:13:07,679][88327] Updated weights for policy 1, policy_version 77050 (0.0007) -[2023-10-09 03:13:08,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 157745152. Throughput: 0: 1674.2, 1: 1711.7. Samples: 39437516. Policy #0 lag: (min: 31.0, avg: 44.1, max: 63.0) -[2023-10-09 03:13:08,975][87372] Avg episode reward: [(0, '7.210'), (1, '7.880')] -[2023-10-09 03:13:11,055][88326] Updated weights for policy 0, policy_version 77002 (0.0011) -[2023-10-09 03:13:11,430][88326] Updated weights for policy 0, policy_version 77012 (0.0008) -[2023-10-09 03:13:11,782][88327] Updated weights for policy 1, policy_version 77060 (0.0008) -[2023-10-09 03:13:11,799][88326] Updated weights for policy 0, policy_version 77022 (0.0008) -[2023-10-09 03:13:12,144][88327] Updated weights for policy 1, policy_version 77070 (0.0009) -[2023-10-09 03:13:12,509][88327] Updated weights for policy 1, policy_version 77080 (0.0009) -[2023-10-09 03:13:13,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 157810688. Throughput: 0: 1668.4, 1: 1695.5. Samples: 39456930. Policy #0 lag: (min: 31.0, avg: 44.1, max: 63.0) -[2023-10-09 03:13:13,975][87372] Avg episode reward: [(0, '7.110'), (1, '7.440')] -[2023-10-09 03:13:15,886][88326] Updated weights for policy 0, policy_version 77032 (0.0007) -[2023-10-09 03:13:16,256][88326] Updated weights for policy 0, policy_version 77042 (0.0008) -[2023-10-09 03:13:16,558][88327] Updated weights for policy 1, policy_version 77090 (0.0010) -[2023-10-09 03:13:16,619][88326] Updated weights for policy 0, policy_version 77052 (0.0009) -[2023-10-09 03:13:16,924][88327] Updated weights for policy 1, policy_version 77100 (0.0010) -[2023-10-09 03:13:17,294][88327] Updated weights for policy 1, policy_version 77110 (0.0008) -[2023-10-09 03:13:17,666][88327] Updated weights for policy 1, policy_version 77120 (0.0007) -[2023-10-09 03:13:18,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 157876224. Throughput: 0: 1690.5, 1: 1681.8. Samples: 39477168. Policy #0 lag: (min: 31.0, avg: 44.1, max: 63.0) -[2023-10-09 03:13:18,975][87372] Avg episode reward: [(0, '6.930'), (1, '7.250')] -[2023-10-09 03:13:20,703][88326] Updated weights for policy 0, policy_version 77062 (0.0008) -[2023-10-09 03:13:21,073][88326] Updated weights for policy 0, policy_version 77072 (0.0007) -[2023-10-09 03:13:21,436][88326] Updated weights for policy 0, policy_version 77082 (0.0007) -[2023-10-09 03:13:21,833][88327] Updated weights for policy 1, policy_version 77130 (0.0008) -[2023-10-09 03:13:22,208][88327] Updated weights for policy 1, policy_version 77140 (0.0007) -[2023-10-09 03:13:22,584][88327] Updated weights for policy 1, policy_version 77150 (0.0007) -[2023-10-09 03:13:23,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 157941760. Throughput: 0: 1670.9, 1: 1705.8. Samples: 39487824. Policy #0 lag: (min: 31.0, avg: 44.1, max: 63.0) -[2023-10-09 03:13:23,975][87372] Avg episode reward: [(0, '6.640'), (1, '7.220')] -[2023-10-09 03:13:25,497][88326] Updated weights for policy 0, policy_version 77092 (0.0008) -[2023-10-09 03:13:25,863][88326] Updated weights for policy 0, policy_version 77102 (0.0007) -[2023-10-09 03:13:26,225][88326] Updated weights for policy 0, policy_version 77112 (0.0007) -[2023-10-09 03:13:26,695][88327] Updated weights for policy 1, policy_version 77160 (0.0008) -[2023-10-09 03:13:27,063][88327] Updated weights for policy 1, policy_version 77170 (0.0010) -[2023-10-09 03:13:27,428][88327] Updated weights for policy 1, policy_version 77180 (0.0008) -[2023-10-09 03:13:28,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 158007296. Throughput: 0: 1679.2, 1: 1683.2. Samples: 39507200. Policy #0 lag: (min: 31.0, avg: 44.1, max: 63.0) -[2023-10-09 03:13:28,975][87372] Avg episode reward: [(0, '7.310'), (1, '7.410')] -[2023-10-09 03:13:30,206][88326] Updated weights for policy 0, policy_version 77122 (0.0009) -[2023-10-09 03:13:30,567][88326] Updated weights for policy 0, policy_version 77132 (0.0007) -[2023-10-09 03:13:30,928][88326] Updated weights for policy 0, policy_version 77142 (0.0011) -[2023-10-09 03:13:31,303][88326] Updated weights for policy 0, policy_version 77152 (0.0010) -[2023-10-09 03:13:31,431][88327] Updated weights for policy 1, policy_version 77190 (0.0007) -[2023-10-09 03:13:31,793][88327] Updated weights for policy 1, policy_version 77200 (0.0007) -[2023-10-09 03:13:32,157][88327] Updated weights for policy 1, policy_version 77210 (0.0011) -[2023-10-09 03:13:33,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 158072832. Throughput: 0: 1686.2, 1: 1683.3. Samples: 39527650. Policy #0 lag: (min: 31.0, avg: 44.1, max: 63.0) -[2023-10-09 03:13:33,975][87372] Avg episode reward: [(0, '6.980'), (1, '6.790')] -[2023-10-09 03:13:35,456][88326] Updated weights for policy 0, policy_version 77162 (0.0009) -[2023-10-09 03:13:35,826][88326] Updated weights for policy 0, policy_version 77172 (0.0011) -[2023-10-09 03:13:36,159][88327] Updated weights for policy 1, policy_version 77220 (0.0008) -[2023-10-09 03:13:36,189][88326] Updated weights for policy 0, policy_version 77182 (0.0010) -[2023-10-09 03:13:36,522][88327] Updated weights for policy 1, policy_version 77230 (0.0009) -[2023-10-09 03:13:36,882][88327] Updated weights for policy 1, policy_version 77240 (0.0008) -[2023-10-09 03:13:38,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 158138368. Throughput: 0: 1661.4, 1: 1700.1. Samples: 39538016. Policy #0 lag: (min: 4.0, avg: 9.9, max: 36.0) -[2023-10-09 03:13:38,975][87372] Avg episode reward: [(0, '7.220'), (1, '7.550')] -[2023-10-09 03:13:40,064][88326] Updated weights for policy 0, policy_version 77192 (0.0007) -[2023-10-09 03:13:40,431][88326] Updated weights for policy 0, policy_version 77202 (0.0008) -[2023-10-09 03:13:40,795][88326] Updated weights for policy 0, policy_version 77212 (0.0007) -[2023-10-09 03:13:41,077][88327] Updated weights for policy 1, policy_version 77250 (0.0008) -[2023-10-09 03:13:41,441][88327] Updated weights for policy 1, policy_version 77260 (0.0009) -[2023-10-09 03:13:41,797][88327] Updated weights for policy 1, policy_version 77270 (0.0009) -[2023-10-09 03:13:42,160][88327] Updated weights for policy 1, policy_version 77280 (0.0008) -[2023-10-09 03:13:43,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 158203904. Throughput: 0: 1695.5, 1: 1669.8. Samples: 39558056. Policy #0 lag: (min: 4.0, avg: 9.9, max: 36.0) -[2023-10-09 03:13:43,975][87372] Avg episode reward: [(0, '7.560'), (1, '7.540')] -[2023-10-09 03:13:44,654][88326] Updated weights for policy 0, policy_version 77222 (0.0008) -[2023-10-09 03:13:45,018][88326] Updated weights for policy 0, policy_version 77232 (0.0007) -[2023-10-09 03:13:45,389][88326] Updated weights for policy 0, policy_version 77242 (0.0008) -[2023-10-09 03:13:46,033][88327] Updated weights for policy 1, policy_version 77290 (0.0011) -[2023-10-09 03:13:46,393][88327] Updated weights for policy 1, policy_version 77300 (0.0009) -[2023-10-09 03:13:46,754][88327] Updated weights for policy 1, policy_version 77310 (0.0008) -[2023-10-09 03:13:48,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 158269440. Throughput: 0: 1695.6, 1: 1693.0. Samples: 39578934. Policy #0 lag: (min: 4.0, avg: 9.9, max: 36.0) -[2023-10-09 03:13:48,975][87372] Avg episode reward: [(0, '6.950'), (1, '8.090')] -[2023-10-09 03:13:49,537][88326] Updated weights for policy 0, policy_version 77252 (0.0010) -[2023-10-09 03:13:49,902][88326] Updated weights for policy 0, policy_version 77262 (0.0009) -[2023-10-09 03:13:50,268][88326] Updated weights for policy 0, policy_version 77272 (0.0009) -[2023-10-09 03:13:50,737][88327] Updated weights for policy 1, policy_version 77320 (0.0007) -[2023-10-09 03:13:51,093][88327] Updated weights for policy 1, policy_version 77330 (0.0007) -[2023-10-09 03:13:51,462][88327] Updated weights for policy 1, policy_version 77340 (0.0008) -[2023-10-09 03:13:53,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 158334976. Throughput: 0: 1679.6, 1: 1679.3. Samples: 39588668. Policy #0 lag: (min: 4.0, avg: 9.9, max: 36.0) -[2023-10-09 03:13:53,975][87372] Avg episode reward: [(0, '7.190'), (1, '7.090')] -[2023-10-09 03:13:54,302][88326] Updated weights for policy 0, policy_version 77282 (0.0008) -[2023-10-09 03:13:54,676][88326] Updated weights for policy 0, policy_version 77292 (0.0008) -[2023-10-09 03:13:55,046][88326] Updated weights for policy 0, policy_version 77302 (0.0007) -[2023-10-09 03:13:55,343][88327] Updated weights for policy 1, policy_version 77350 (0.0008) -[2023-10-09 03:13:55,413][88326] Updated weights for policy 0, policy_version 77312 (0.0008) -[2023-10-09 03:13:55,714][88327] Updated weights for policy 1, policy_version 77360 (0.0008) -[2023-10-09 03:13:56,084][88327] Updated weights for policy 1, policy_version 77370 (0.0008) -[2023-10-09 03:13:58,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 158400512. Throughput: 0: 1703.2, 1: 1681.6. Samples: 39609246. Policy #0 lag: (min: 4.0, avg: 9.9, max: 36.0) -[2023-10-09 03:13:58,975][87372] Avg episode reward: [(0, '6.790'), (1, '7.110')] -[2023-10-09 03:13:59,503][88326] Updated weights for policy 0, policy_version 77322 (0.0007) -[2023-10-09 03:13:59,866][88326] Updated weights for policy 0, policy_version 77332 (0.0008) -[2023-10-09 03:14:00,055][88327] Updated weights for policy 1, policy_version 77380 (0.0010) -[2023-10-09 03:14:00,230][88326] Updated weights for policy 0, policy_version 77342 (0.0008) -[2023-10-09 03:14:00,421][88327] Updated weights for policy 1, policy_version 77390 (0.0010) -[2023-10-09 03:14:00,790][88327] Updated weights for policy 1, policy_version 77400 (0.0008) -[2023-10-09 03:14:03,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 158466048. Throughput: 0: 1694.8, 1: 1700.1. Samples: 39629938. Policy #0 lag: (min: 4.0, avg: 9.9, max: 36.0) -[2023-10-09 03:14:03,974][87372] Avg episode reward: [(0, '7.330'), (1, '6.900')] -[2023-10-09 03:14:04,232][88326] Updated weights for policy 0, policy_version 77352 (0.0009) -[2023-10-09 03:14:04,603][88326] Updated weights for policy 0, policy_version 77362 (0.0009) -[2023-10-09 03:14:04,902][88327] Updated weights for policy 1, policy_version 77410 (0.0007) -[2023-10-09 03:14:04,971][88326] Updated weights for policy 0, policy_version 77372 (0.0009) -[2023-10-09 03:14:05,260][88327] Updated weights for policy 1, policy_version 77420 (0.0009) -[2023-10-09 03:14:05,622][88327] Updated weights for policy 1, policy_version 77430 (0.0009) -[2023-10-09 03:14:05,987][88327] Updated weights for policy 1, policy_version 77440 (0.0009) -[2023-10-09 03:14:08,954][88326] Updated weights for policy 0, policy_version 77382 (0.0009) -[2023-10-09 03:14:08,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 158531584. Throughput: 0: 1690.0, 1: 1672.1. Samples: 39639116. Policy #0 lag: (min: 4.0, avg: 9.9, max: 36.0) -[2023-10-09 03:14:08,975][87372] Avg episode reward: [(0, '7.090'), (1, '6.500')] -[2023-10-09 03:14:09,316][88326] Updated weights for policy 0, policy_version 77392 (0.0008) -[2023-10-09 03:14:09,679][88326] Updated weights for policy 0, policy_version 77402 (0.0009) -[2023-10-09 03:14:10,066][88327] Updated weights for policy 1, policy_version 77450 (0.0009) -[2023-10-09 03:14:10,425][88327] Updated weights for policy 1, policy_version 77460 (0.0008) -[2023-10-09 03:14:10,787][88327] Updated weights for policy 1, policy_version 77470 (0.0008) -[2023-10-09 03:14:13,617][88326] Updated weights for policy 0, policy_version 77412 (0.0009) -[2023-10-09 03:14:13,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 158597120. Throughput: 0: 1708.5, 1: 1698.9. Samples: 39660534. Policy #0 lag: (min: 4.0, avg: 9.9, max: 36.0) -[2023-10-09 03:14:13,975][87372] Avg episode reward: [(0, '7.040'), (1, '6.550')] -[2023-10-09 03:14:13,978][88326] Updated weights for policy 0, policy_version 77422 (0.0007) -[2023-10-09 03:14:14,353][88326] Updated weights for policy 0, policy_version 77432 (0.0007) -[2023-10-09 03:14:14,675][88327] Updated weights for policy 1, policy_version 77480 (0.0010) -[2023-10-09 03:14:15,041][88327] Updated weights for policy 1, policy_version 77490 (0.0010) -[2023-10-09 03:14:15,400][88327] Updated weights for policy 1, policy_version 77500 (0.0011) -[2023-10-09 03:14:18,342][88326] Updated weights for policy 0, policy_version 77442 (0.0007) -[2023-10-09 03:14:18,709][88326] Updated weights for policy 0, policy_version 77452 (0.0010) -[2023-10-09 03:14:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 158662656. Throughput: 0: 1711.3, 1: 1710.7. Samples: 39681640. Policy #0 lag: (min: 4.0, avg: 9.9, max: 36.0) -[2023-10-09 03:14:18,975][87372] Avg episode reward: [(0, '7.340'), (1, '7.340')] -[2023-10-09 03:14:19,075][88326] Updated weights for policy 0, policy_version 77462 (0.0010) -[2023-10-09 03:14:19,405][88327] Updated weights for policy 1, policy_version 77510 (0.0010) -[2023-10-09 03:14:19,452][88326] Updated weights for policy 0, policy_version 77472 (0.0008) -[2023-10-09 03:14:19,767][88327] Updated weights for policy 1, policy_version 77520 (0.0008) -[2023-10-09 03:14:20,133][88327] Updated weights for policy 1, policy_version 77530 (0.0008) -[2023-10-09 03:14:23,617][88326] Updated weights for policy 0, policy_version 77482 (0.0008) -[2023-10-09 03:14:23,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 158728192. Throughput: 0: 1709.6, 1: 1682.1. Samples: 39690644. Policy #0 lag: (min: 4.0, avg: 9.9, max: 36.0) -[2023-10-09 03:14:23,975][87372] Avg episode reward: [(0, '7.550'), (1, '7.260')] -[2023-10-09 03:14:23,982][88326] Updated weights for policy 0, policy_version 77492 (0.0008) -[2023-10-09 03:14:24,298][88327] Updated weights for policy 1, policy_version 77540 (0.0008) -[2023-10-09 03:14:24,354][88326] Updated weights for policy 0, policy_version 77502 (0.0007) -[2023-10-09 03:14:24,655][88327] Updated weights for policy 1, policy_version 77550 (0.0009) -[2023-10-09 03:14:25,018][88327] Updated weights for policy 1, policy_version 77560 (0.0009) -[2023-10-09 03:14:28,359][88326] Updated weights for policy 0, policy_version 77512 (0.0009) -[2023-10-09 03:14:28,733][88326] Updated weights for policy 0, policy_version 77522 (0.0011) -[2023-10-09 03:14:28,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 158793728. Throughput: 0: 1704.4, 1: 1703.4. Samples: 39711406. Policy #0 lag: (min: 18.0, avg: 43.5, max: 48.0) -[2023-10-09 03:14:28,974][87372] Avg episode reward: [(0, '7.130'), (1, '7.760')] -[2023-10-09 03:14:28,975][88327] Updated weights for policy 1, policy_version 77570 (0.0009) -[2023-10-09 03:14:29,100][88326] Updated weights for policy 0, policy_version 77532 (0.0007) -[2023-10-09 03:14:29,336][88327] Updated weights for policy 1, policy_version 77580 (0.0009) -[2023-10-09 03:14:29,714][88327] Updated weights for policy 1, policy_version 77590 (0.0008) -[2023-10-09 03:14:30,081][88327] Updated weights for policy 1, policy_version 77600 (0.0008) -[2023-10-09 03:14:33,074][88326] Updated weights for policy 0, policy_version 77542 (0.0009) -[2023-10-09 03:14:33,449][88326] Updated weights for policy 0, policy_version 77552 (0.0010) -[2023-10-09 03:14:33,820][88326] Updated weights for policy 0, policy_version 77562 (0.0010) -[2023-10-09 03:14:33,975][87372] Fps is (10 sec: 13106.7, 60 sec: 13107.1, 300 sec: 13440.4). Total num frames: 158859264. Throughput: 0: 1695.2, 1: 1703.6. Samples: 39731882. Policy #0 lag: (min: 18.0, avg: 43.5, max: 48.0) -[2023-10-09 03:14:33,976][87372] Avg episode reward: [(0, '6.840'), (1, '7.640')] -[2023-10-09 03:14:34,034][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000077568_79429632.pth... -[2023-10-09 03:14:34,074][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000075968_77791232.pth -[2023-10-09 03:14:34,386][88327] Updated weights for policy 1, policy_version 77610 (0.0011) -[2023-10-09 03:14:34,757][88327] Updated weights for policy 1, policy_version 77620 (0.0008) -[2023-10-09 03:14:35,115][88327] Updated weights for policy 1, policy_version 77630 (0.0011) -[2023-10-09 03:14:35,186][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000077632_79495168.pth... -[2023-10-09 03:14:35,223][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000076032_77856768.pth -[2023-10-09 03:14:37,937][88326] Updated weights for policy 0, policy_version 77572 (0.0007) -[2023-10-09 03:14:38,308][88326] Updated weights for policy 0, policy_version 77582 (0.0009) -[2023-10-09 03:14:38,676][88326] Updated weights for policy 0, policy_version 77592 (0.0007) -[2023-10-09 03:14:38,974][87372] Fps is (10 sec: 16383.9, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 158957568. Throughput: 0: 1703.3, 1: 1689.5. Samples: 39741346. Policy #0 lag: (min: 18.0, avg: 43.5, max: 48.0) -[2023-10-09 03:14:38,975][87372] Avg episode reward: [(0, '7.200'), (1, '8.000')] -[2023-10-09 03:14:39,317][88327] Updated weights for policy 1, policy_version 77640 (0.0009) -[2023-10-09 03:14:39,681][88327] Updated weights for policy 1, policy_version 77650 (0.0010) -[2023-10-09 03:14:40,038][88327] Updated weights for policy 1, policy_version 77660 (0.0008) -[2023-10-09 03:14:42,665][88326] Updated weights for policy 0, policy_version 77602 (0.0008) -[2023-10-09 03:14:43,036][88326] Updated weights for policy 0, policy_version 77612 (0.0007) -[2023-10-09 03:14:43,399][88326] Updated weights for policy 0, policy_version 77622 (0.0007) -[2023-10-09 03:14:43,765][88326] Updated weights for policy 0, policy_version 77632 (0.0009) -[2023-10-09 03:14:43,974][87372] Fps is (10 sec: 16384.7, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 159023104. Throughput: 0: 1699.0, 1: 1695.0. Samples: 39761976. Policy #0 lag: (min: 18.0, avg: 43.5, max: 48.0) -[2023-10-09 03:14:43,975][87372] Avg episode reward: [(0, '6.240'), (1, '7.930')] -[2023-10-09 03:14:44,080][88327] Updated weights for policy 1, policy_version 77670 (0.0009) -[2023-10-09 03:14:44,439][88327] Updated weights for policy 1, policy_version 77680 (0.0011) -[2023-10-09 03:14:44,804][88327] Updated weights for policy 1, policy_version 77690 (0.0010) -[2023-10-09 03:14:47,917][88326] Updated weights for policy 0, policy_version 77642 (0.0008) -[2023-10-09 03:14:48,281][88326] Updated weights for policy 0, policy_version 77652 (0.0009) -[2023-10-09 03:14:48,653][88326] Updated weights for policy 0, policy_version 77662 (0.0007) -[2023-10-09 03:14:48,745][88327] Updated weights for policy 1, policy_version 77700 (0.0009) -[2023-10-09 03:14:48,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 159088640. Throughput: 0: 1687.6, 1: 1701.7. Samples: 39782458. Policy #0 lag: (min: 18.0, avg: 43.5, max: 48.0) -[2023-10-09 03:14:48,975][87372] Avg episode reward: [(0, '6.230'), (1, '7.360')] -[2023-10-09 03:14:49,104][88327] Updated weights for policy 1, policy_version 77710 (0.0008) -[2023-10-09 03:14:49,478][88327] Updated weights for policy 1, policy_version 77720 (0.0011) -[2023-10-09 03:14:52,682][88326] Updated weights for policy 0, policy_version 77672 (0.0009) -[2023-10-09 03:14:53,048][88326] Updated weights for policy 0, policy_version 77682 (0.0010) -[2023-10-09 03:14:53,412][88326] Updated weights for policy 0, policy_version 77692 (0.0008) -[2023-10-09 03:14:53,417][88327] Updated weights for policy 1, policy_version 77730 (0.0009) -[2023-10-09 03:14:53,778][88327] Updated weights for policy 1, policy_version 77740 (0.0007) -[2023-10-09 03:14:53,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 159154176. Throughput: 0: 1699.5, 1: 1705.5. Samples: 39792338. Policy #0 lag: (min: 18.0, avg: 43.5, max: 48.0) -[2023-10-09 03:14:53,975][87372] Avg episode reward: [(0, '7.010'), (1, '7.300')] -[2023-10-09 03:14:54,145][88327] Updated weights for policy 1, policy_version 77750 (0.0007) -[2023-10-09 03:14:54,515][88327] Updated weights for policy 1, policy_version 77760 (0.0007) -[2023-10-09 03:14:57,497][88326] Updated weights for policy 0, policy_version 77702 (0.0007) -[2023-10-09 03:14:57,849][88326] Updated weights for policy 0, policy_version 77712 (0.0008) -[2023-10-09 03:14:58,211][88326] Updated weights for policy 0, policy_version 77722 (0.0008) -[2023-10-09 03:14:58,547][88327] Updated weights for policy 1, policy_version 77770 (0.0007) -[2023-10-09 03:14:58,915][88327] Updated weights for policy 1, policy_version 77780 (0.0007) -[2023-10-09 03:14:58,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 159219712. Throughput: 0: 1694.3, 1: 1699.4. Samples: 39813250. Policy #0 lag: (min: 18.0, avg: 43.5, max: 48.0) -[2023-10-09 03:14:58,975][87372] Avg episode reward: [(0, '6.470'), (1, '7.580')] -[2023-10-09 03:14:59,274][88327] Updated weights for policy 1, policy_version 77790 (0.0009) -[2023-10-09 03:15:02,301][88326] Updated weights for policy 0, policy_version 77732 (0.0009) -[2023-10-09 03:15:02,673][88326] Updated weights for policy 0, policy_version 77742 (0.0009) -[2023-10-09 03:15:03,040][88326] Updated weights for policy 0, policy_version 77752 (0.0008) -[2023-10-09 03:15:03,307][88327] Updated weights for policy 1, policy_version 77800 (0.0009) -[2023-10-09 03:15:03,676][88327] Updated weights for policy 1, policy_version 77810 (0.0007) -[2023-10-09 03:15:03,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 159285248. Throughput: 0: 1668.7, 1: 1695.5. Samples: 39833032. Policy #0 lag: (min: 18.0, avg: 43.5, max: 48.0) -[2023-10-09 03:15:03,975][87372] Avg episode reward: [(0, '6.510'), (1, '6.840')] -[2023-10-09 03:15:04,050][88327] Updated weights for policy 1, policy_version 77820 (0.0007) -[2023-10-09 03:15:06,844][88326] Updated weights for policy 0, policy_version 77762 (0.0009) -[2023-10-09 03:15:07,222][88326] Updated weights for policy 0, policy_version 77772 (0.0007) -[2023-10-09 03:15:07,595][88326] Updated weights for policy 0, policy_version 77782 (0.0009) -[2023-10-09 03:15:07,952][88326] Updated weights for policy 0, policy_version 77792 (0.0009) -[2023-10-09 03:15:08,027][88327] Updated weights for policy 1, policy_version 77830 (0.0008) -[2023-10-09 03:15:08,391][88327] Updated weights for policy 1, policy_version 77840 (0.0009) -[2023-10-09 03:15:08,763][88327] Updated weights for policy 1, policy_version 77850 (0.0008) -[2023-10-09 03:15:08,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 159350784. Throughput: 0: 1696.9, 1: 1700.0. Samples: 39843500. Policy #0 lag: (min: 18.0, avg: 43.5, max: 48.0) -[2023-10-09 03:15:08,975][87372] Avg episode reward: [(0, '7.110'), (1, '6.980')] -[2023-10-09 03:15:12,108][88326] Updated weights for policy 0, policy_version 77802 (0.0011) -[2023-10-09 03:15:12,468][88326] Updated weights for policy 0, policy_version 77812 (0.0009) -[2023-10-09 03:15:12,848][88326] Updated weights for policy 0, policy_version 77822 (0.0008) -[2023-10-09 03:15:12,878][88327] Updated weights for policy 1, policy_version 77860 (0.0008) -[2023-10-09 03:15:13,243][88327] Updated weights for policy 1, policy_version 77870 (0.0009) -[2023-10-09 03:15:13,610][88327] Updated weights for policy 1, policy_version 77880 (0.0007) -[2023-10-09 03:15:13,974][87372] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 159449088. Throughput: 0: 1684.3, 1: 1697.6. Samples: 39863596. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:15:13,975][87372] Avg episode reward: [(0, '6.350'), (1, '7.230')] -[2023-10-09 03:15:16,782][88326] Updated weights for policy 0, policy_version 77832 (0.0007) -[2023-10-09 03:15:17,157][88326] Updated weights for policy 0, policy_version 77842 (0.0008) -[2023-10-09 03:15:17,532][88326] Updated weights for policy 0, policy_version 77852 (0.0009) -[2023-10-09 03:15:17,611][88327] Updated weights for policy 1, policy_version 77890 (0.0009) -[2023-10-09 03:15:17,978][88327] Updated weights for policy 1, policy_version 77900 (0.0007) -[2023-10-09 03:15:18,343][88327] Updated weights for policy 1, policy_version 77910 (0.0007) -[2023-10-09 03:15:18,704][88327] Updated weights for policy 1, policy_version 77920 (0.0007) -[2023-10-09 03:15:18,974][87372] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 159514624. Throughput: 0: 1683.0, 1: 1691.7. Samples: 39883744. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:15:18,975][87372] Avg episode reward: [(0, '6.310'), (1, '6.480')] -[2023-10-09 03:15:21,587][88326] Updated weights for policy 0, policy_version 77862 (0.0009) -[2023-10-09 03:15:21,957][88326] Updated weights for policy 0, policy_version 77872 (0.0007) -[2023-10-09 03:15:22,325][88326] Updated weights for policy 0, policy_version 77882 (0.0007) -[2023-10-09 03:15:22,804][88327] Updated weights for policy 1, policy_version 77930 (0.0008) -[2023-10-09 03:15:23,169][88327] Updated weights for policy 1, policy_version 77940 (0.0007) -[2023-10-09 03:15:23,524][88327] Updated weights for policy 1, policy_version 77950 (0.0009) -[2023-10-09 03:15:23,974][87372] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 159580160. Throughput: 0: 1704.8, 1: 1704.5. Samples: 39894764. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:15:23,975][87372] Avg episode reward: [(0, '6.680'), (1, '6.500')] -[2023-10-09 03:15:26,224][88326] Updated weights for policy 0, policy_version 77892 (0.0009) -[2023-10-09 03:15:26,602][88326] Updated weights for policy 0, policy_version 77902 (0.0010) -[2023-10-09 03:15:26,965][88326] Updated weights for policy 0, policy_version 77912 (0.0009) -[2023-10-09 03:15:27,455][88327] Updated weights for policy 1, policy_version 77960 (0.0010) -[2023-10-09 03:15:27,819][88327] Updated weights for policy 1, policy_version 77970 (0.0009) -[2023-10-09 03:15:28,190][88327] Updated weights for policy 1, policy_version 77980 (0.0007) -[2023-10-09 03:15:28,974][87372] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 159645696. Throughput: 0: 1678.6, 1: 1711.6. Samples: 39914534. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:15:28,975][87372] Avg episode reward: [(0, '7.300'), (1, '7.480')] -[2023-10-09 03:15:31,041][88326] Updated weights for policy 0, policy_version 77922 (0.0007) -[2023-10-09 03:15:31,413][88326] Updated weights for policy 0, policy_version 77932 (0.0008) -[2023-10-09 03:15:31,787][88326] Updated weights for policy 0, policy_version 77942 (0.0008) -[2023-10-09 03:15:32,148][88326] Updated weights for policy 0, policy_version 77952 (0.0008) -[2023-10-09 03:15:32,248][88327] Updated weights for policy 1, policy_version 77990 (0.0009) -[2023-10-09 03:15:32,623][88327] Updated weights for policy 1, policy_version 78000 (0.0010) -[2023-10-09 03:15:32,985][88327] Updated weights for policy 1, policy_version 78010 (0.0008) -[2023-10-09 03:15:33,974][87372] Fps is (10 sec: 13107.1, 60 sec: 14199.6, 300 sec: 13551.5). Total num frames: 159711232. Throughput: 0: 1693.3, 1: 1683.0. Samples: 39934392. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:15:33,975][87372] Avg episode reward: [(0, '7.400'), (1, '7.950')] -[2023-10-09 03:15:36,082][88326] Updated weights for policy 0, policy_version 77962 (0.0007) -[2023-10-09 03:15:36,454][88326] Updated weights for policy 0, policy_version 77972 (0.0007) -[2023-10-09 03:15:36,823][88326] Updated weights for policy 0, policy_version 77982 (0.0009) -[2023-10-09 03:15:37,024][88327] Updated weights for policy 1, policy_version 78020 (0.0008) -[2023-10-09 03:15:37,390][88327] Updated weights for policy 1, policy_version 78030 (0.0008) -[2023-10-09 03:15:37,747][88327] Updated weights for policy 1, policy_version 78040 (0.0008) -[2023-10-09 03:15:38,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 159776768. Throughput: 0: 1694.1, 1: 1708.0. Samples: 39945432. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:15:38,975][87372] Avg episode reward: [(0, '7.100'), (1, '7.480')] -[2023-10-09 03:15:40,868][88326] Updated weights for policy 0, policy_version 77992 (0.0008) -[2023-10-09 03:15:41,233][88326] Updated weights for policy 0, policy_version 78002 (0.0011) -[2023-10-09 03:15:41,595][88326] Updated weights for policy 0, policy_version 78012 (0.0009) -[2023-10-09 03:15:41,790][88327] Updated weights for policy 1, policy_version 78050 (0.0009) -[2023-10-09 03:15:42,156][88327] Updated weights for policy 1, policy_version 78060 (0.0008) -[2023-10-09 03:15:42,520][88327] Updated weights for policy 1, policy_version 78070 (0.0008) -[2023-10-09 03:15:42,892][88327] Updated weights for policy 1, policy_version 78080 (0.0009) -[2023-10-09 03:15:43,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 159842304. Throughput: 0: 1673.1, 1: 1696.0. Samples: 39964860. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:15:43,975][87372] Avg episode reward: [(0, '6.670'), (1, '7.560')] -[2023-10-09 03:15:45,699][88326] Updated weights for policy 0, policy_version 78022 (0.0007) -[2023-10-09 03:15:46,071][88326] Updated weights for policy 0, policy_version 78032 (0.0007) -[2023-10-09 03:15:46,438][88326] Updated weights for policy 0, policy_version 78042 (0.0007) -[2023-10-09 03:15:47,027][88327] Updated weights for policy 1, policy_version 78090 (0.0009) -[2023-10-09 03:15:47,387][88327] Updated weights for policy 1, policy_version 78100 (0.0010) -[2023-10-09 03:15:47,760][88327] Updated weights for policy 1, policy_version 78110 (0.0008) -[2023-10-09 03:15:48,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 159907840. Throughput: 0: 1699.2, 1: 1671.8. Samples: 39984730. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:15:48,975][87372] Avg episode reward: [(0, '6.870'), (1, '7.380')] -[2023-10-09 03:15:50,343][88326] Updated weights for policy 0, policy_version 78052 (0.0007) -[2023-10-09 03:15:50,719][88326] Updated weights for policy 0, policy_version 78062 (0.0010) -[2023-10-09 03:15:51,083][88326] Updated weights for policy 0, policy_version 78072 (0.0010) -[2023-10-09 03:15:51,774][88327] Updated weights for policy 1, policy_version 78120 (0.0009) -[2023-10-09 03:15:52,149][88327] Updated weights for policy 1, policy_version 78130 (0.0007) -[2023-10-09 03:15:52,514][88327] Updated weights for policy 1, policy_version 78140 (0.0008) -[2023-10-09 03:15:53,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 159973376. Throughput: 0: 1679.0, 1: 1697.7. Samples: 39995450. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:15:53,975][87372] Avg episode reward: [(0, '7.130'), (1, '7.220')] -[2023-10-09 03:15:55,130][88326] Updated weights for policy 0, policy_version 78082 (0.0011) -[2023-10-09 03:15:55,496][88326] Updated weights for policy 0, policy_version 78092 (0.0010) -[2023-10-09 03:15:55,867][88326] Updated weights for policy 0, policy_version 78102 (0.0010) -[2023-10-09 03:15:56,238][88326] Updated weights for policy 0, policy_version 78112 (0.0010) -[2023-10-09 03:15:56,440][88327] Updated weights for policy 1, policy_version 78150 (0.0008) -[2023-10-09 03:15:56,804][88327] Updated weights for policy 1, policy_version 78160 (0.0010) -[2023-10-09 03:15:57,174][88327] Updated weights for policy 1, policy_version 78170 (0.0009) -[2023-10-09 03:15:58,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 160038912. Throughput: 0: 1690.9, 1: 1688.3. Samples: 40015658. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:15:58,975][87372] Avg episode reward: [(0, '6.560'), (1, '6.980')] -[2023-10-09 03:16:00,313][88326] Updated weights for policy 0, policy_version 78122 (0.0009) -[2023-10-09 03:16:00,678][88326] Updated weights for policy 0, policy_version 78132 (0.0009) -[2023-10-09 03:16:01,048][88326] Updated weights for policy 0, policy_version 78142 (0.0008) -[2023-10-09 03:16:01,222][88327] Updated weights for policy 1, policy_version 78180 (0.0009) -[2023-10-09 03:16:01,582][88327] Updated weights for policy 1, policy_version 78190 (0.0009) -[2023-10-09 03:16:01,948][88327] Updated weights for policy 1, policy_version 78200 (0.0009) -[2023-10-09 03:16:03,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 160104448. Throughput: 0: 1697.2, 1: 1687.9. Samples: 40036070. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:16:03,974][87372] Avg episode reward: [(0, '7.160'), (1, '7.430')] -[2023-10-09 03:16:05,118][88326] Updated weights for policy 0, policy_version 78152 (0.0007) -[2023-10-09 03:16:05,477][88326] Updated weights for policy 0, policy_version 78162 (0.0009) -[2023-10-09 03:16:05,850][88326] Updated weights for policy 0, policy_version 78172 (0.0009) -[2023-10-09 03:16:06,024][88327] Updated weights for policy 1, policy_version 78210 (0.0010) -[2023-10-09 03:16:06,385][88327] Updated weights for policy 1, policy_version 78220 (0.0007) -[2023-10-09 03:16:06,759][88327] Updated weights for policy 1, policy_version 78230 (0.0007) -[2023-10-09 03:16:07,117][88327] Updated weights for policy 1, policy_version 78240 (0.0008) -[2023-10-09 03:16:08,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 160169984. Throughput: 0: 1666.6, 1: 1699.5. Samples: 40046240. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-09 03:16:08,974][87372] Avg episode reward: [(0, '6.910'), (1, '7.050')] -[2023-10-09 03:16:09,915][88326] Updated weights for policy 0, policy_version 78182 (0.0009) -[2023-10-09 03:16:10,279][88326] Updated weights for policy 0, policy_version 78192 (0.0009) -[2023-10-09 03:16:10,652][88326] Updated weights for policy 0, policy_version 78202 (0.0008) -[2023-10-09 03:16:11,117][88327] Updated weights for policy 1, policy_version 78250 (0.0007) -[2023-10-09 03:16:11,476][88327] Updated weights for policy 1, policy_version 78260 (0.0007) -[2023-10-09 03:16:11,848][88327] Updated weights for policy 1, policy_version 78270 (0.0008) -[2023-10-09 03:16:13,974][87372] Fps is (10 sec: 13106.8, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 160235520. Throughput: 0: 1695.1, 1: 1668.8. Samples: 40065908. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-09 03:16:13,975][87372] Avg episode reward: [(0, '6.480'), (1, '7.610')] -[2023-10-09 03:16:14,872][88326] Updated weights for policy 0, policy_version 78212 (0.0009) -[2023-10-09 03:16:15,243][88326] Updated weights for policy 0, policy_version 78222 (0.0010) -[2023-10-09 03:16:15,606][88326] Updated weights for policy 0, policy_version 78232 (0.0010) -[2023-10-09 03:16:15,928][88327] Updated weights for policy 1, policy_version 78280 (0.0009) -[2023-10-09 03:16:16,293][88327] Updated weights for policy 1, policy_version 78290 (0.0011) -[2023-10-09 03:16:16,665][88327] Updated weights for policy 1, policy_version 78300 (0.0011) -[2023-10-09 03:16:18,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 160301056. Throughput: 0: 1696.4, 1: 1697.2. Samples: 40087104. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-09 03:16:18,975][87372] Avg episode reward: [(0, '6.930'), (1, '6.870')] -[2023-10-09 03:16:19,498][88326] Updated weights for policy 0, policy_version 78242 (0.0009) -[2023-10-09 03:16:19,864][88326] Updated weights for policy 0, policy_version 78252 (0.0009) -[2023-10-09 03:16:20,226][88326] Updated weights for policy 0, policy_version 78262 (0.0008) -[2023-10-09 03:16:20,525][88327] Updated weights for policy 1, policy_version 78310 (0.0008) -[2023-10-09 03:16:20,593][88326] Updated weights for policy 0, policy_version 78272 (0.0009) -[2023-10-09 03:16:20,882][88327] Updated weights for policy 1, policy_version 78320 (0.0008) -[2023-10-09 03:16:21,250][88327] Updated weights for policy 1, policy_version 78330 (0.0009) -[2023-10-09 03:16:23,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 160366592. Throughput: 0: 1680.4, 1: 1686.3. Samples: 40096934. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-09 03:16:23,975][87372] Avg episode reward: [(0, '6.810'), (1, '6.960')] -[2023-10-09 03:16:24,595][88326] Updated weights for policy 0, policy_version 78282 (0.0011) -[2023-10-09 03:16:24,957][88326] Updated weights for policy 0, policy_version 78292 (0.0009) -[2023-10-09 03:16:25,331][88326] Updated weights for policy 0, policy_version 78302 (0.0009) -[2023-10-09 03:16:25,339][88327] Updated weights for policy 1, policy_version 78340 (0.0010) -[2023-10-09 03:16:25,699][88327] Updated weights for policy 1, policy_version 78350 (0.0011) -[2023-10-09 03:16:26,067][88327] Updated weights for policy 1, policy_version 78360 (0.0007) -[2023-10-09 03:16:28,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 160432128. Throughput: 0: 1701.8, 1: 1684.5. Samples: 40117242. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-09 03:16:28,975][87372] Avg episode reward: [(0, '6.730'), (1, '7.560')] -[2023-10-09 03:16:29,343][88326] Updated weights for policy 0, policy_version 78312 (0.0009) -[2023-10-09 03:16:29,722][88326] Updated weights for policy 0, policy_version 78322 (0.0008) -[2023-10-09 03:16:30,093][88326] Updated weights for policy 0, policy_version 78332 (0.0008) -[2023-10-09 03:16:30,094][88327] Updated weights for policy 1, policy_version 78370 (0.0008) -[2023-10-09 03:16:30,453][88327] Updated weights for policy 1, policy_version 78380 (0.0009) -[2023-10-09 03:16:30,829][88327] Updated weights for policy 1, policy_version 78390 (0.0008) -[2023-10-09 03:16:31,189][88327] Updated weights for policy 1, policy_version 78400 (0.0008) -[2023-10-09 03:16:33,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 160497664. Throughput: 0: 1701.5, 1: 1708.1. Samples: 40138162. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-09 03:16:33,975][87372] Avg episode reward: [(0, '6.780'), (1, '7.660')] -[2023-10-09 03:16:33,983][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000078400_80281600.pth... -[2023-10-09 03:16:34,019][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000076832_78675968.pth -[2023-10-09 03:16:34,132][88326] Updated weights for policy 0, policy_version 78342 (0.0009) -[2023-10-09 03:16:34,504][88326] Updated weights for policy 0, policy_version 78352 (0.0009) -[2023-10-09 03:16:34,886][88326] Updated weights for policy 0, policy_version 78362 (0.0008) -[2023-10-09 03:16:35,000][88327] Updated weights for policy 1, policy_version 78410 (0.0009) -[2023-10-09 03:16:35,096][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000078368_80248832.pth... -[2023-10-09 03:16:35,128][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000076768_78610432.pth -[2023-10-09 03:16:35,362][88327] Updated weights for policy 1, policy_version 78420 (0.0009) -[2023-10-09 03:16:35,733][88327] Updated weights for policy 1, policy_version 78430 (0.0009) -[2023-10-09 03:16:38,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 160563200. Throughput: 0: 1693.0, 1: 1684.9. Samples: 40147454. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-09 03:16:38,974][87372] Avg episode reward: [(0, '6.670'), (1, '7.250')] -[2023-10-09 03:16:39,036][88326] Updated weights for policy 0, policy_version 78372 (0.0009) -[2023-10-09 03:16:39,391][88326] Updated weights for policy 0, policy_version 78382 (0.0007) -[2023-10-09 03:16:39,755][88326] Updated weights for policy 0, policy_version 78392 (0.0007) -[2023-10-09 03:16:39,783][88327] Updated weights for policy 1, policy_version 78440 (0.0008) -[2023-10-09 03:16:40,147][88327] Updated weights for policy 1, policy_version 78450 (0.0007) -[2023-10-09 03:16:40,509][88327] Updated weights for policy 1, policy_version 78460 (0.0008) -[2023-10-09 03:16:43,730][88326] Updated weights for policy 0, policy_version 78402 (0.0007) -[2023-10-09 03:16:43,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 160628736. Throughput: 0: 1692.2, 1: 1703.7. Samples: 40168476. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-09 03:16:43,975][87372] Avg episode reward: [(0, '7.230'), (1, '7.600')] -[2023-10-09 03:16:44,101][88326] Updated weights for policy 0, policy_version 78412 (0.0009) -[2023-10-09 03:16:44,478][88326] Updated weights for policy 0, policy_version 78422 (0.0009) -[2023-10-09 03:16:44,674][88327] Updated weights for policy 1, policy_version 78470 (0.0007) -[2023-10-09 03:16:44,833][88326] Updated weights for policy 0, policy_version 78432 (0.0008) -[2023-10-09 03:16:45,067][88327] Updated weights for policy 1, policy_version 78480 (0.0008) -[2023-10-09 03:16:45,423][88327] Updated weights for policy 1, policy_version 78490 (0.0009) -[2023-10-09 03:16:48,856][88326] Updated weights for policy 0, policy_version 78442 (0.0008) -[2023-10-09 03:16:48,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 160694272. Throughput: 0: 1701.2, 1: 1709.2. Samples: 40189538. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-09 03:16:48,974][87372] Avg episode reward: [(0, '6.940'), (1, '7.310')] -[2023-10-09 03:16:49,218][88326] Updated weights for policy 0, policy_version 78452 (0.0009) -[2023-10-09 03:16:49,416][88327] Updated weights for policy 1, policy_version 78500 (0.0008) -[2023-10-09 03:16:49,583][88326] Updated weights for policy 0, policy_version 78462 (0.0007) -[2023-10-09 03:16:49,786][88327] Updated weights for policy 1, policy_version 78510 (0.0007) -[2023-10-09 03:16:50,142][88327] Updated weights for policy 1, policy_version 78520 (0.0008) -[2023-10-09 03:16:53,478][88326] Updated weights for policy 0, policy_version 78472 (0.0008) -[2023-10-09 03:16:53,849][88326] Updated weights for policy 0, policy_version 78482 (0.0009) -[2023-10-09 03:16:53,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 160759808. Throughput: 0: 1698.1, 1: 1685.1. Samples: 40198488. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-09 03:16:53,976][87372] Avg episode reward: [(0, '6.650'), (1, '6.700')] -[2023-10-09 03:16:54,219][88326] Updated weights for policy 0, policy_version 78492 (0.0008) -[2023-10-09 03:16:54,239][88327] Updated weights for policy 1, policy_version 78530 (0.0009) -[2023-10-09 03:16:54,599][88327] Updated weights for policy 1, policy_version 78540 (0.0007) -[2023-10-09 03:16:54,959][88327] Updated weights for policy 1, policy_version 78550 (0.0007) -[2023-10-09 03:16:55,330][88327] Updated weights for policy 1, policy_version 78560 (0.0007) -[2023-10-09 03:16:58,345][88326] Updated weights for policy 0, policy_version 78502 (0.0007) -[2023-10-09 03:16:58,709][88326] Updated weights for policy 0, policy_version 78512 (0.0007) -[2023-10-09 03:16:58,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 160825344. Throughput: 0: 1697.3, 1: 1714.5. Samples: 40219438. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-09 03:16:58,975][87372] Avg episode reward: [(0, '6.660'), (1, '6.790')] -[2023-10-09 03:16:59,077][88326] Updated weights for policy 0, policy_version 78522 (0.0008) -[2023-10-09 03:16:59,195][88327] Updated weights for policy 1, policy_version 78570 (0.0009) -[2023-10-09 03:16:59,558][88327] Updated weights for policy 1, policy_version 78580 (0.0009) -[2023-10-09 03:16:59,928][88327] Updated weights for policy 1, policy_version 78590 (0.0010) -[2023-10-09 03:17:03,091][88326] Updated weights for policy 0, policy_version 78532 (0.0008) -[2023-10-09 03:17:03,464][88326] Updated weights for policy 0, policy_version 78542 (0.0007) -[2023-10-09 03:17:03,831][88326] Updated weights for policy 0, policy_version 78552 (0.0007) -[2023-10-09 03:17:03,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 160890880. Throughput: 0: 1694.0, 1: 1711.6. Samples: 40240356. Policy #0 lag: (min: 31.0, avg: 35.8, max: 63.0) -[2023-10-09 03:17:03,975][87372] Avg episode reward: [(0, '6.840'), (1, '7.060')] -[2023-10-09 03:17:04,028][88327] Updated weights for policy 1, policy_version 78600 (0.0009) -[2023-10-09 03:17:04,397][88327] Updated weights for policy 1, policy_version 78610 (0.0009) -[2023-10-09 03:17:04,758][88327] Updated weights for policy 1, policy_version 78620 (0.0008) -[2023-10-09 03:17:07,804][88326] Updated weights for policy 0, policy_version 78562 (0.0008) -[2023-10-09 03:17:08,172][88326] Updated weights for policy 0, policy_version 78572 (0.0008) -[2023-10-09 03:17:08,543][88326] Updated weights for policy 0, policy_version 78582 (0.0008) -[2023-10-09 03:17:08,834][88327] Updated weights for policy 1, policy_version 78630 (0.0009) -[2023-10-09 03:17:08,917][88326] Updated weights for policy 0, policy_version 78592 (0.0008) -[2023-10-09 03:17:08,974][87372] Fps is (10 sec: 16383.8, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 160989184. Throughput: 0: 1701.1, 1: 1695.3. Samples: 40249770. Policy #0 lag: (min: 31.0, avg: 35.8, max: 63.0) -[2023-10-09 03:17:08,975][87372] Avg episode reward: [(0, '7.110'), (1, '7.050')] -[2023-10-09 03:17:09,197][88327] Updated weights for policy 1, policy_version 78640 (0.0008) -[2023-10-09 03:17:09,559][88327] Updated weights for policy 1, policy_version 78650 (0.0011) -[2023-10-09 03:17:12,982][88326] Updated weights for policy 0, policy_version 78602 (0.0008) -[2023-10-09 03:17:13,362][88326] Updated weights for policy 0, policy_version 78612 (0.0008) -[2023-10-09 03:17:13,565][88327] Updated weights for policy 1, policy_version 78660 (0.0008) -[2023-10-09 03:17:13,729][88326] Updated weights for policy 0, policy_version 78622 (0.0010) -[2023-10-09 03:17:13,928][88327] Updated weights for policy 1, policy_version 78670 (0.0008) -[2023-10-09 03:17:13,974][87372] Fps is (10 sec: 16383.5, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 161054720. Throughput: 0: 1698.1, 1: 1705.1. Samples: 40270388. Policy #0 lag: (min: 31.0, avg: 35.8, max: 63.0) -[2023-10-09 03:17:13,976][87372] Avg episode reward: [(0, '7.520'), (1, '7.400')] -[2023-10-09 03:17:14,291][88327] Updated weights for policy 1, policy_version 78680 (0.0008) -[2023-10-09 03:17:17,911][88326] Updated weights for policy 0, policy_version 78632 (0.0009) -[2023-10-09 03:17:18,200][88327] Updated weights for policy 1, policy_version 78690 (0.0007) -[2023-10-09 03:17:18,274][88326] Updated weights for policy 0, policy_version 78642 (0.0007) -[2023-10-09 03:17:18,570][88327] Updated weights for policy 1, policy_version 78700 (0.0008) -[2023-10-09 03:17:18,638][88326] Updated weights for policy 0, policy_version 78652 (0.0007) -[2023-10-09 03:17:18,926][88327] Updated weights for policy 1, policy_version 78710 (0.0008) -[2023-10-09 03:17:18,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 161120256. Throughput: 0: 1681.0, 1: 1709.8. Samples: 40290746. Policy #0 lag: (min: 31.0, avg: 35.8, max: 63.0) -[2023-10-09 03:17:18,974][87372] Avg episode reward: [(0, '6.960'), (1, '7.130')] -[2023-10-09 03:17:19,295][88327] Updated weights for policy 1, policy_version 78720 (0.0008) -[2023-10-09 03:17:22,775][88326] Updated weights for policy 0, policy_version 78662 (0.0007) -[2023-10-09 03:17:23,157][88326] Updated weights for policy 0, policy_version 78672 (0.0008) -[2023-10-09 03:17:23,378][88327] Updated weights for policy 1, policy_version 78730 (0.0007) -[2023-10-09 03:17:23,525][88326] Updated weights for policy 0, policy_version 78682 (0.0008) -[2023-10-09 03:17:23,743][88327] Updated weights for policy 1, policy_version 78740 (0.0008) -[2023-10-09 03:17:23,974][87372] Fps is (10 sec: 13107.6, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 161185792. Throughput: 0: 1694.6, 1: 1703.3. Samples: 40300360. Policy #0 lag: (min: 31.0, avg: 35.8, max: 63.0) -[2023-10-09 03:17:23,975][87372] Avg episode reward: [(0, '6.750'), (1, '6.980')] -[2023-10-09 03:17:24,105][88327] Updated weights for policy 1, policy_version 78750 (0.0007) -[2023-10-09 03:17:27,786][88326] Updated weights for policy 0, policy_version 78692 (0.0008) -[2023-10-09 03:17:28,047][88327] Updated weights for policy 1, policy_version 78760 (0.0009) -[2023-10-09 03:17:28,145][88326] Updated weights for policy 0, policy_version 78702 (0.0007) -[2023-10-09 03:17:28,403][88327] Updated weights for policy 1, policy_version 78770 (0.0007) -[2023-10-09 03:17:28,514][88326] Updated weights for policy 0, policy_version 78712 (0.0009) -[2023-10-09 03:17:28,764][88327] Updated weights for policy 1, policy_version 78780 (0.0009) -[2023-10-09 03:17:28,974][87372] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 161284096. Throughput: 0: 1691.2, 1: 1698.5. Samples: 40321010. Policy #0 lag: (min: 31.0, avg: 35.8, max: 63.0) -[2023-10-09 03:17:28,975][87372] Avg episode reward: [(0, '6.830'), (1, '7.350')] -[2023-10-09 03:17:32,745][88326] Updated weights for policy 0, policy_version 78722 (0.0008) -[2023-10-09 03:17:33,048][88327] Updated weights for policy 1, policy_version 78790 (0.0008) -[2023-10-09 03:17:33,104][88326] Updated weights for policy 0, policy_version 78732 (0.0008) -[2023-10-09 03:17:33,438][88327] Updated weights for policy 1, policy_version 78800 (0.0009) -[2023-10-09 03:17:33,474][88326] Updated weights for policy 0, policy_version 78742 (0.0008) -[2023-10-09 03:17:33,792][88327] Updated weights for policy 1, policy_version 78810 (0.0008) -[2023-10-09 03:17:33,842][88326] Updated weights for policy 0, policy_version 78752 (0.0008) -[2023-10-09 03:17:33,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 161316864. Throughput: 0: 1668.6, 1: 1686.7. Samples: 40340524. Policy #0 lag: (min: 31.0, avg: 35.8, max: 63.0) -[2023-10-09 03:17:33,975][87372] Avg episode reward: [(0, '6.580'), (1, '7.170')] -[2023-10-09 03:17:37,808][88327] Updated weights for policy 1, policy_version 78820 (0.0008) -[2023-10-09 03:17:37,887][88326] Updated weights for policy 0, policy_version 78762 (0.0008) -[2023-10-09 03:17:38,181][88327] Updated weights for policy 1, policy_version 78830 (0.0007) -[2023-10-09 03:17:38,257][88326] Updated weights for policy 0, policy_version 78772 (0.0008) -[2023-10-09 03:17:38,538][88327] Updated weights for policy 1, policy_version 78840 (0.0007) -[2023-10-09 03:17:38,623][88326] Updated weights for policy 0, policy_version 78782 (0.0008) -[2023-10-09 03:17:38,974][87372] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 161415168. Throughput: 0: 1686.0, 1: 1694.8. Samples: 40350624. Policy #0 lag: (min: 31.0, avg: 35.8, max: 63.0) -[2023-10-09 03:17:38,975][87372] Avg episode reward: [(0, '6.690'), (1, '7.110')] -[2023-10-09 03:17:42,684][88326] Updated weights for policy 0, policy_version 78792 (0.0008) -[2023-10-09 03:17:42,710][88327] Updated weights for policy 1, policy_version 78850 (0.0008) -[2023-10-09 03:17:43,060][88326] Updated weights for policy 0, policy_version 78802 (0.0007) -[2023-10-09 03:17:43,074][88327] Updated weights for policy 1, policy_version 78860 (0.0007) -[2023-10-09 03:17:43,429][88326] Updated weights for policy 0, policy_version 78812 (0.0007) -[2023-10-09 03:17:43,441][88327] Updated weights for policy 1, policy_version 78870 (0.0009) -[2023-10-09 03:17:43,812][88327] Updated weights for policy 1, policy_version 78880 (0.0007) -[2023-10-09 03:17:43,974][87372] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 161480704. Throughput: 0: 1680.6, 1: 1689.7. Samples: 40371102. Policy #0 lag: (min: 31.0, avg: 35.8, max: 63.0) -[2023-10-09 03:17:43,975][87372] Avg episode reward: [(0, '7.520'), (1, '7.230')] -[2023-10-09 03:17:47,447][88326] Updated weights for policy 0, policy_version 78822 (0.0008) -[2023-10-09 03:17:47,815][88326] Updated weights for policy 0, policy_version 78832 (0.0008) -[2023-10-09 03:17:48,038][88327] Updated weights for policy 1, policy_version 78890 (0.0007) -[2023-10-09 03:17:48,188][88326] Updated weights for policy 0, policy_version 78842 (0.0007) -[2023-10-09 03:17:48,393][88327] Updated weights for policy 1, policy_version 78900 (0.0009) -[2023-10-09 03:17:48,764][88327] Updated weights for policy 1, policy_version 78910 (0.0008) -[2023-10-09 03:17:48,974][87372] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 161546240. Throughput: 0: 1657.7, 1: 1674.9. Samples: 40390324. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:17:48,975][87372] Avg episode reward: [(0, '7.110'), (1, '7.880')] -[2023-10-09 03:17:52,216][88326] Updated weights for policy 0, policy_version 78852 (0.0009) -[2023-10-09 03:17:52,585][88326] Updated weights for policy 0, policy_version 78862 (0.0009) -[2023-10-09 03:17:52,715][88327] Updated weights for policy 1, policy_version 78920 (0.0007) -[2023-10-09 03:17:52,959][88326] Updated weights for policy 0, policy_version 78872 (0.0008) -[2023-10-09 03:17:53,087][88327] Updated weights for policy 1, policy_version 78930 (0.0009) -[2023-10-09 03:17:53,445][88327] Updated weights for policy 1, policy_version 78940 (0.0009) -[2023-10-09 03:17:53,974][87372] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 161611776. Throughput: 0: 1674.1, 1: 1686.3. Samples: 40400986. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:17:53,975][87372] Avg episode reward: [(0, '7.140'), (1, '7.980')] -[2023-10-09 03:17:57,031][88326] Updated weights for policy 0, policy_version 78882 (0.0010) -[2023-10-09 03:17:57,398][88326] Updated weights for policy 0, policy_version 78892 (0.0010) -[2023-10-09 03:17:57,498][88327] Updated weights for policy 1, policy_version 78950 (0.0008) -[2023-10-09 03:17:57,764][88326] Updated weights for policy 0, policy_version 78902 (0.0008) -[2023-10-09 03:17:57,862][88327] Updated weights for policy 1, policy_version 78960 (0.0008) -[2023-10-09 03:17:58,125][88326] Updated weights for policy 0, policy_version 78912 (0.0008) -[2023-10-09 03:17:58,233][88327] Updated weights for policy 1, policy_version 78970 (0.0008) -[2023-10-09 03:17:58,974][87372] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 161677312. Throughput: 0: 1666.4, 1: 1687.2. Samples: 40421296. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:17:58,975][87372] Avg episode reward: [(0, '6.820'), (1, '7.080')] -[2023-10-09 03:18:02,091][88327] Updated weights for policy 1, policy_version 78980 (0.0009) -[2023-10-09 03:18:02,361][88326] Updated weights for policy 0, policy_version 78922 (0.0008) -[2023-10-09 03:18:02,455][88327] Updated weights for policy 1, policy_version 78990 (0.0007) -[2023-10-09 03:18:02,722][88326] Updated weights for policy 0, policy_version 78932 (0.0009) -[2023-10-09 03:18:02,810][88327] Updated weights for policy 1, policy_version 79000 (0.0010) -[2023-10-09 03:18:03,088][88326] Updated weights for policy 0, policy_version 78942 (0.0008) -[2023-10-09 03:18:03,974][87372] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 161742848. Throughput: 0: 1656.1, 1: 1660.0. Samples: 40439968. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:18:03,975][87372] Avg episode reward: [(0, '6.850'), (1, '7.480')] -[2023-10-09 03:18:06,999][88327] Updated weights for policy 1, policy_version 79010 (0.0010) -[2023-10-09 03:18:07,129][88326] Updated weights for policy 0, policy_version 78952 (0.0007) -[2023-10-09 03:18:07,358][88327] Updated weights for policy 1, policy_version 79020 (0.0010) -[2023-10-09 03:18:07,502][88326] Updated weights for policy 0, policy_version 78962 (0.0008) -[2023-10-09 03:18:07,715][88327] Updated weights for policy 1, policy_version 79030 (0.0008) -[2023-10-09 03:18:07,869][88326] Updated weights for policy 0, policy_version 78972 (0.0007) -[2023-10-09 03:18:08,080][88327] Updated weights for policy 1, policy_version 79040 (0.0009) -[2023-10-09 03:18:08,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 161808384. Throughput: 0: 1672.7, 1: 1688.3. Samples: 40451602. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:18:08,975][87372] Avg episode reward: [(0, '6.800'), (1, '7.910')] -[2023-10-09 03:18:11,863][88326] Updated weights for policy 0, policy_version 78982 (0.0009) -[2023-10-09 03:18:12,169][88327] Updated weights for policy 1, policy_version 79050 (0.0010) -[2023-10-09 03:18:12,236][88326] Updated weights for policy 0, policy_version 78992 (0.0008) -[2023-10-09 03:18:12,529][88327] Updated weights for policy 1, policy_version 79060 (0.0009) -[2023-10-09 03:18:12,604][88326] Updated weights for policy 0, policy_version 79002 (0.0007) -[2023-10-09 03:18:12,897][88327] Updated weights for policy 1, policy_version 79070 (0.0008) -[2023-10-09 03:18:13,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 161873920. Throughput: 0: 1661.7, 1: 1681.0. Samples: 40471434. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:18:13,975][87372] Avg episode reward: [(0, '6.820'), (1, '7.300')] -[2023-10-09 03:18:16,705][88326] Updated weights for policy 0, policy_version 79012 (0.0009) -[2023-10-09 03:18:17,000][88327] Updated weights for policy 1, policy_version 79080 (0.0008) -[2023-10-09 03:18:17,073][88326] Updated weights for policy 0, policy_version 79022 (0.0007) -[2023-10-09 03:18:17,369][88327] Updated weights for policy 1, policy_version 79090 (0.0008) -[2023-10-09 03:18:17,437][88326] Updated weights for policy 0, policy_version 79032 (0.0007) -[2023-10-09 03:18:17,730][88327] Updated weights for policy 1, policy_version 79100 (0.0007) -[2023-10-09 03:18:18,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 161939456. Throughput: 0: 1666.3, 1: 1671.3. Samples: 40490714. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:18:18,975][87372] Avg episode reward: [(0, '7.130'), (1, '7.640')] -[2023-10-09 03:18:21,577][88326] Updated weights for policy 0, policy_version 79042 (0.0008) -[2023-10-09 03:18:21,765][88327] Updated weights for policy 1, policy_version 79110 (0.0009) -[2023-10-09 03:18:21,936][88326] Updated weights for policy 0, policy_version 79052 (0.0008) -[2023-10-09 03:18:22,146][88327] Updated weights for policy 1, policy_version 79120 (0.0007) -[2023-10-09 03:18:22,308][88326] Updated weights for policy 0, policy_version 79062 (0.0007) -[2023-10-09 03:18:22,516][88327] Updated weights for policy 1, policy_version 79130 (0.0007) -[2023-10-09 03:18:22,678][88326] Updated weights for policy 0, policy_version 79072 (0.0007) -[2023-10-09 03:18:23,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 162004992. Throughput: 0: 1678.8, 1: 1692.3. Samples: 40502324. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:18:23,975][87372] Avg episode reward: [(0, '7.140'), (1, '7.630')] -[2023-10-09 03:18:26,637][88327] Updated weights for policy 1, policy_version 79140 (0.0009) -[2023-10-09 03:18:26,747][88326] Updated weights for policy 0, policy_version 79082 (0.0008) -[2023-10-09 03:18:26,999][88327] Updated weights for policy 1, policy_version 79150 (0.0009) -[2023-10-09 03:18:27,111][88326] Updated weights for policy 0, policy_version 79092 (0.0008) -[2023-10-09 03:18:27,352][88327] Updated weights for policy 1, policy_version 79160 (0.0008) -[2023-10-09 03:18:27,474][88326] Updated weights for policy 0, policy_version 79102 (0.0010) -[2023-10-09 03:18:28,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 162070528. Throughput: 0: 1662.0, 1: 1674.5. Samples: 40521240. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:18:28,974][87372] Avg episode reward: [(0, '6.250'), (1, '7.750')] -[2023-10-09 03:18:31,358][88327] Updated weights for policy 1, policy_version 79170 (0.0009) -[2023-10-09 03:18:31,608][88326] Updated weights for policy 0, policy_version 79112 (0.0007) -[2023-10-09 03:18:31,717][88327] Updated weights for policy 1, policy_version 79180 (0.0009) -[2023-10-09 03:18:31,978][88326] Updated weights for policy 0, policy_version 79122 (0.0007) -[2023-10-09 03:18:32,078][88327] Updated weights for policy 1, policy_version 79190 (0.0007) -[2023-10-09 03:18:32,342][88326] Updated weights for policy 0, policy_version 79132 (0.0008) -[2023-10-09 03:18:32,442][88327] Updated weights for policy 1, policy_version 79200 (0.0007) -[2023-10-09 03:18:33,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 162136064. Throughput: 0: 1674.5, 1: 1671.4. Samples: 40540892. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:18:33,975][87372] Avg episode reward: [(0, '6.700'), (1, '7.000')] -[2023-10-09 03:18:33,983][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000079136_81035264.pth... -[2023-10-09 03:18:33,983][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000079200_81100800.pth... -[2023-10-09 03:18:34,013][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000077632_79495168.pth -[2023-10-09 03:18:34,017][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000077568_79429632.pth -[2023-10-09 03:18:34,017][88168] Saving a milestone ./train_atari/atari_battlezone_APPO/checkpoint_p1/milestones/checkpoint_000079200_81100800.pth -[2023-10-09 03:18:34,021][88088] Saving a milestone ./train_atari/atari_battlezone_APPO/checkpoint_p0/milestones/checkpoint_000079136_81035264.pth -[2023-10-09 03:18:36,187][88326] Updated weights for policy 0, policy_version 79142 (0.0008) -[2023-10-09 03:18:36,469][88327] Updated weights for policy 1, policy_version 79210 (0.0008) -[2023-10-09 03:18:36,554][88326] Updated weights for policy 0, policy_version 79152 (0.0009) -[2023-10-09 03:18:36,836][88327] Updated weights for policy 1, policy_version 79220 (0.0008) -[2023-10-09 03:18:36,924][88326] Updated weights for policy 0, policy_version 79162 (0.0009) -[2023-10-09 03:18:37,201][88327] Updated weights for policy 1, policy_version 79230 (0.0007) -[2023-10-09 03:18:38,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 162201600. Throughput: 0: 1676.3, 1: 1690.0. Samples: 40552468. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:18:38,975][87372] Avg episode reward: [(0, '6.310'), (1, '6.750')] -[2023-10-09 03:18:40,945][88326] Updated weights for policy 0, policy_version 79172 (0.0008) -[2023-10-09 03:18:41,319][88326] Updated weights for policy 0, policy_version 79182 (0.0007) -[2023-10-09 03:18:41,365][88327] Updated weights for policy 1, policy_version 79240 (0.0007) -[2023-10-09 03:18:41,693][88326] Updated weights for policy 0, policy_version 79192 (0.0007) -[2023-10-09 03:18:41,726][88327] Updated weights for policy 1, policy_version 79250 (0.0008) -[2023-10-09 03:18:42,089][88327] Updated weights for policy 1, policy_version 79260 (0.0008) -[2023-10-09 03:18:43,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 162267136. Throughput: 0: 1662.6, 1: 1670.2. Samples: 40571270. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:18:43,974][87372] Avg episode reward: [(0, '6.790'), (1, '6.930')] -[2023-10-09 03:18:45,734][88326] Updated weights for policy 0, policy_version 79202 (0.0009) -[2023-10-09 03:18:46,100][88326] Updated weights for policy 0, policy_version 79212 (0.0007) -[2023-10-09 03:18:46,172][88327] Updated weights for policy 1, policy_version 79270 (0.0008) -[2023-10-09 03:18:46,472][88326] Updated weights for policy 0, policy_version 79222 (0.0010) -[2023-10-09 03:18:46,523][88327] Updated weights for policy 1, policy_version 79280 (0.0008) -[2023-10-09 03:18:46,836][88326] Updated weights for policy 0, policy_version 79232 (0.0009) -[2023-10-09 03:18:46,892][88327] Updated weights for policy 1, policy_version 79290 (0.0008) -[2023-10-09 03:18:48,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 162332672. Throughput: 0: 1685.5, 1: 1685.4. Samples: 40591656. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:18:48,974][87372] Avg episode reward: [(0, '7.320'), (1, '6.940')] -[2023-10-09 03:18:50,899][88326] Updated weights for policy 0, policy_version 79242 (0.0009) -[2023-10-09 03:18:51,030][88327] Updated weights for policy 1, policy_version 79300 (0.0008) -[2023-10-09 03:18:51,261][88326] Updated weights for policy 0, policy_version 79252 (0.0008) -[2023-10-09 03:18:51,390][88327] Updated weights for policy 1, policy_version 79310 (0.0008) -[2023-10-09 03:18:51,637][88326] Updated weights for policy 0, policy_version 79262 (0.0007) -[2023-10-09 03:18:51,762][88327] Updated weights for policy 1, policy_version 79320 (0.0009) -[2023-10-09 03:18:53,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 162398208. Throughput: 0: 1670.2, 1: 1683.6. Samples: 40602522. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:18:53,975][87372] Avg episode reward: [(0, '7.620'), (1, '7.190')] -[2023-10-09 03:18:55,689][88327] Updated weights for policy 1, policy_version 79330 (0.0009) -[2023-10-09 03:18:55,715][88326] Updated weights for policy 0, policy_version 79272 (0.0010) -[2023-10-09 03:18:56,051][88327] Updated weights for policy 1, policy_version 79340 (0.0008) -[2023-10-09 03:18:56,085][88326] Updated weights for policy 0, policy_version 79282 (0.0008) -[2023-10-09 03:18:56,421][88327] Updated weights for policy 1, policy_version 79350 (0.0008) -[2023-10-09 03:18:56,448][88326] Updated weights for policy 0, policy_version 79292 (0.0007) -[2023-10-09 03:18:56,778][88327] Updated weights for policy 1, policy_version 79360 (0.0007) -[2023-10-09 03:18:58,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 162463744. Throughput: 0: 1672.0, 1: 1671.7. Samples: 40621900. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:18:58,975][87372] Avg episode reward: [(0, '7.080'), (1, '7.210')] -[2023-10-09 03:19:00,655][88326] Updated weights for policy 0, policy_version 79302 (0.0009) -[2023-10-09 03:19:00,790][88327] Updated weights for policy 1, policy_version 79370 (0.0007) -[2023-10-09 03:19:01,019][88326] Updated weights for policy 0, policy_version 79312 (0.0008) -[2023-10-09 03:19:01,149][88327] Updated weights for policy 1, policy_version 79380 (0.0008) -[2023-10-09 03:19:01,394][88326] Updated weights for policy 0, policy_version 79322 (0.0008) -[2023-10-09 03:19:01,517][88327] Updated weights for policy 1, policy_version 79390 (0.0009) -[2023-10-09 03:19:03,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 162529280. Throughput: 0: 1685.7, 1: 1694.9. Samples: 40642840. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:19:03,975][87372] Avg episode reward: [(0, '6.580'), (1, '7.240')] -[2023-10-09 03:19:05,361][88326] Updated weights for policy 0, policy_version 79332 (0.0008) -[2023-10-09 03:19:05,421][88327] Updated weights for policy 1, policy_version 79400 (0.0007) -[2023-10-09 03:19:05,732][88326] Updated weights for policy 0, policy_version 79342 (0.0007) -[2023-10-09 03:19:05,788][88327] Updated weights for policy 1, policy_version 79410 (0.0008) -[2023-10-09 03:19:06,095][88326] Updated weights for policy 0, policy_version 79352 (0.0007) -[2023-10-09 03:19:06,154][88327] Updated weights for policy 1, policy_version 79420 (0.0008) -[2023-10-09 03:19:08,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 162594816. Throughput: 0: 1664.6, 1: 1672.5. Samples: 40652494. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:19:08,975][87372] Avg episode reward: [(0, '6.700'), (1, '7.860')] -[2023-10-09 03:19:10,246][88327] Updated weights for policy 1, policy_version 79430 (0.0007) -[2023-10-09 03:19:10,318][88326] Updated weights for policy 0, policy_version 79362 (0.0008) -[2023-10-09 03:19:10,610][88327] Updated weights for policy 1, policy_version 79440 (0.0007) -[2023-10-09 03:19:10,692][88326] Updated weights for policy 0, policy_version 79372 (0.0008) -[2023-10-09 03:19:10,973][88327] Updated weights for policy 1, policy_version 79450 (0.0008) -[2023-10-09 03:19:11,053][88326] Updated weights for policy 0, policy_version 79382 (0.0009) -[2023-10-09 03:19:11,417][88326] Updated weights for policy 0, policy_version 79392 (0.0008) -[2023-10-09 03:19:13,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 162660352. Throughput: 0: 1676.8, 1: 1689.1. Samples: 40672710. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:19:13,975][87372] Avg episode reward: [(0, '6.900'), (1, '7.690')] -[2023-10-09 03:19:15,096][88327] Updated weights for policy 1, policy_version 79460 (0.0008) -[2023-10-09 03:19:15,485][88327] Updated weights for policy 1, policy_version 79470 (0.0009) -[2023-10-09 03:19:15,602][88326] Updated weights for policy 0, policy_version 79402 (0.0008) -[2023-10-09 03:19:15,845][88327] Updated weights for policy 1, policy_version 79480 (0.0009) -[2023-10-09 03:19:15,972][88326] Updated weights for policy 0, policy_version 79412 (0.0009) -[2023-10-09 03:19:16,339][88326] Updated weights for policy 0, policy_version 79422 (0.0007) -[2023-10-09 03:19:18,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 162725888. Throughput: 0: 1685.8, 1: 1703.2. Samples: 40693394. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:19:18,975][87372] Avg episode reward: [(0, '7.000'), (1, '7.210')] -[2023-10-09 03:19:19,756][88327] Updated weights for policy 1, policy_version 79490 (0.0008) -[2023-10-09 03:19:20,119][88327] Updated weights for policy 1, policy_version 79500 (0.0010) -[2023-10-09 03:19:20,420][88326] Updated weights for policy 0, policy_version 79432 (0.0008) -[2023-10-09 03:19:20,476][88327] Updated weights for policy 1, policy_version 79510 (0.0009) -[2023-10-09 03:19:20,797][88326] Updated weights for policy 0, policy_version 79442 (0.0009) -[2023-10-09 03:19:20,840][88327] Updated weights for policy 1, policy_version 79520 (0.0008) -[2023-10-09 03:19:21,164][88326] Updated weights for policy 0, policy_version 79452 (0.0009) -[2023-10-09 03:19:23,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 162791424. Throughput: 0: 1663.9, 1: 1675.7. Samples: 40702748. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:19:23,975][87372] Avg episode reward: [(0, '7.050'), (1, '7.140')] -[2023-10-09 03:19:24,875][88327] Updated weights for policy 1, policy_version 79530 (0.0007) -[2023-10-09 03:19:25,218][88326] Updated weights for policy 0, policy_version 79462 (0.0008) -[2023-10-09 03:19:25,245][88327] Updated weights for policy 1, policy_version 79540 (0.0007) -[2023-10-09 03:19:25,590][88326] Updated weights for policy 0, policy_version 79472 (0.0009) -[2023-10-09 03:19:25,599][88327] Updated weights for policy 1, policy_version 79550 (0.0008) -[2023-10-09 03:19:25,953][88326] Updated weights for policy 0, policy_version 79482 (0.0007) -[2023-10-09 03:19:28,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 162856960. Throughput: 0: 1683.1, 1: 1707.6. Samples: 40723852. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:19:28,975][87372] Avg episode reward: [(0, '6.660'), (1, '7.200')] -[2023-10-09 03:19:29,536][88327] Updated weights for policy 1, policy_version 79560 (0.0007) -[2023-10-09 03:19:29,878][88326] Updated weights for policy 0, policy_version 79492 (0.0007) -[2023-10-09 03:19:29,899][88327] Updated weights for policy 1, policy_version 79570 (0.0007) -[2023-10-09 03:19:30,238][88326] Updated weights for policy 0, policy_version 79502 (0.0008) -[2023-10-09 03:19:30,264][88327] Updated weights for policy 1, policy_version 79580 (0.0008) -[2023-10-09 03:19:30,605][88326] Updated weights for policy 0, policy_version 79512 (0.0010) -[2023-10-09 03:19:33,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 162922496. Throughput: 0: 1685.7, 1: 1718.2. Samples: 40744832. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:19:33,975][87372] Avg episode reward: [(0, '6.500'), (1, '6.940')] -[2023-10-09 03:19:34,162][88327] Updated weights for policy 1, policy_version 79590 (0.0007) -[2023-10-09 03:19:34,525][88327] Updated weights for policy 1, policy_version 79600 (0.0009) -[2023-10-09 03:19:34,706][88326] Updated weights for policy 0, policy_version 79522 (0.0010) -[2023-10-09 03:19:34,894][88327] Updated weights for policy 1, policy_version 79610 (0.0007) -[2023-10-09 03:19:35,078][88326] Updated weights for policy 0, policy_version 79532 (0.0009) -[2023-10-09 03:19:35,457][88326] Updated weights for policy 0, policy_version 79542 (0.0010) -[2023-10-09 03:19:35,821][88326] Updated weights for policy 0, policy_version 79552 (0.0010) -[2023-10-09 03:19:38,917][88327] Updated weights for policy 1, policy_version 79620 (0.0007) -[2023-10-09 03:19:38,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 162988032. Throughput: 0: 1671.6, 1: 1694.6. Samples: 40754000. Policy #0 lag: (min: 8.0, avg: 23.4, max: 40.0) -[2023-10-09 03:19:38,975][87372] Avg episode reward: [(0, '7.040'), (1, '7.010')] -[2023-10-09 03:19:39,277][88327] Updated weights for policy 1, policy_version 79630 (0.0008) -[2023-10-09 03:19:39,645][88327] Updated weights for policy 1, policy_version 79640 (0.0007) -[2023-10-09 03:19:39,860][88326] Updated weights for policy 0, policy_version 79562 (0.0008) -[2023-10-09 03:19:40,233][88326] Updated weights for policy 0, policy_version 79572 (0.0010) -[2023-10-09 03:19:40,588][88326] Updated weights for policy 0, policy_version 79582 (0.0008) -[2023-10-09 03:19:43,707][88327] Updated weights for policy 1, policy_version 79650 (0.0008) -[2023-10-09 03:19:43,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 163053568. Throughput: 0: 1685.7, 1: 1711.4. Samples: 40774770. Policy #0 lag: (min: 8.0, avg: 23.4, max: 40.0) -[2023-10-09 03:19:43,975][87372] Avg episode reward: [(0, '6.920'), (1, '7.370')] -[2023-10-09 03:19:44,073][88327] Updated weights for policy 1, policy_version 79660 (0.0010) -[2023-10-09 03:19:44,427][88327] Updated weights for policy 1, policy_version 79670 (0.0010) -[2023-10-09 03:19:44,597][88326] Updated weights for policy 0, policy_version 79592 (0.0008) -[2023-10-09 03:19:44,791][88327] Updated weights for policy 1, policy_version 79680 (0.0009) -[2023-10-09 03:19:44,966][88326] Updated weights for policy 0, policy_version 79602 (0.0007) -[2023-10-09 03:19:45,343][88326] Updated weights for policy 0, policy_version 79612 (0.0008) -[2023-10-09 03:19:48,687][88327] Updated weights for policy 1, policy_version 79690 (0.0007) -[2023-10-09 03:19:48,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 163119104. Throughput: 0: 1685.0, 1: 1716.0. Samples: 40795884. Policy #0 lag: (min: 8.0, avg: 23.4, max: 40.0) -[2023-10-09 03:19:48,975][87372] Avg episode reward: [(0, '6.980'), (1, '6.810')] -[2023-10-09 03:19:49,054][88327] Updated weights for policy 1, policy_version 79700 (0.0007) -[2023-10-09 03:19:49,417][88326] Updated weights for policy 0, policy_version 79622 (0.0008) -[2023-10-09 03:19:49,423][88327] Updated weights for policy 1, policy_version 79710 (0.0007) -[2023-10-09 03:19:49,790][88326] Updated weights for policy 0, policy_version 79632 (0.0010) -[2023-10-09 03:19:50,153][88326] Updated weights for policy 0, policy_version 79642 (0.0008) -[2023-10-09 03:19:53,476][88327] Updated weights for policy 1, policy_version 79720 (0.0010) -[2023-10-09 03:19:53,845][88327] Updated weights for policy 1, policy_version 79730 (0.0010) -[2023-10-09 03:19:53,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 163184640. Throughput: 0: 1678.3, 1: 1710.5. Samples: 40804992. Policy #0 lag: (min: 8.0, avg: 23.4, max: 40.0) -[2023-10-09 03:19:53,975][87372] Avg episode reward: [(0, '7.010'), (1, '6.760')] -[2023-10-09 03:19:54,212][88327] Updated weights for policy 1, policy_version 79740 (0.0010) -[2023-10-09 03:19:54,233][88326] Updated weights for policy 0, policy_version 79652 (0.0009) -[2023-10-09 03:19:54,596][88326] Updated weights for policy 0, policy_version 79662 (0.0007) -[2023-10-09 03:19:54,972][88326] Updated weights for policy 0, policy_version 79672 (0.0007) -[2023-10-09 03:19:58,267][88327] Updated weights for policy 1, policy_version 79750 (0.0008) -[2023-10-09 03:19:58,625][88327] Updated weights for policy 1, policy_version 79760 (0.0009) -[2023-10-09 03:19:58,826][88326] Updated weights for policy 0, policy_version 79682 (0.0008) -[2023-10-09 03:19:58,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 163250176. Throughput: 0: 1694.3, 1: 1718.7. Samples: 40826294. Policy #0 lag: (min: 8.0, avg: 23.4, max: 40.0) -[2023-10-09 03:19:58,975][87372] Avg episode reward: [(0, '6.930'), (1, '7.140')] -[2023-10-09 03:19:58,989][88327] Updated weights for policy 1, policy_version 79770 (0.0008) -[2023-10-09 03:19:59,196][88326] Updated weights for policy 0, policy_version 79692 (0.0008) -[2023-10-09 03:19:59,567][88326] Updated weights for policy 0, policy_version 79702 (0.0011) -[2023-10-09 03:19:59,930][88326] Updated weights for policy 0, policy_version 79712 (0.0010) -[2023-10-09 03:20:03,131][88327] Updated weights for policy 1, policy_version 79780 (0.0008) -[2023-10-09 03:20:03,534][88327] Updated weights for policy 1, policy_version 79790 (0.0011) -[2023-10-09 03:20:03,892][88327] Updated weights for policy 1, policy_version 79800 (0.0009) -[2023-10-09 03:20:03,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 163315712. Throughput: 0: 1693.6, 1: 1710.3. Samples: 40846572. Policy #0 lag: (min: 8.0, avg: 23.4, max: 40.0) -[2023-10-09 03:20:03,975][87372] Avg episode reward: [(0, '7.400'), (1, '7.690')] -[2023-10-09 03:20:04,150][88326] Updated weights for policy 0, policy_version 79722 (0.0008) -[2023-10-09 03:20:04,528][88326] Updated weights for policy 0, policy_version 79732 (0.0008) -[2023-10-09 03:20:04,897][88326] Updated weights for policy 0, policy_version 79742 (0.0007) -[2023-10-09 03:20:07,796][88327] Updated weights for policy 1, policy_version 79810 (0.0009) -[2023-10-09 03:20:08,164][88327] Updated weights for policy 1, policy_version 79820 (0.0010) -[2023-10-09 03:20:08,533][88327] Updated weights for policy 1, policy_version 79830 (0.0007) -[2023-10-09 03:20:08,813][88326] Updated weights for policy 0, policy_version 79752 (0.0007) -[2023-10-09 03:20:08,900][88327] Updated weights for policy 1, policy_version 79840 (0.0007) -[2023-10-09 03:20:08,974][87372] Fps is (10 sec: 16384.0, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 163414016. Throughput: 0: 1690.2, 1: 1711.1. Samples: 40855804. Policy #0 lag: (min: 8.0, avg: 23.4, max: 40.0) -[2023-10-09 03:20:08,975][87372] Avg episode reward: [(0, '7.560'), (1, '7.780')] -[2023-10-09 03:20:09,184][88326] Updated weights for policy 0, policy_version 79762 (0.0008) -[2023-10-09 03:20:09,554][88326] Updated weights for policy 0, policy_version 79772 (0.0008) -[2023-10-09 03:20:13,030][88327] Updated weights for policy 1, policy_version 79850 (0.0008) -[2023-10-09 03:20:13,393][88327] Updated weights for policy 1, policy_version 79860 (0.0010) -[2023-10-09 03:20:13,588][88326] Updated weights for policy 0, policy_version 79782 (0.0008) -[2023-10-09 03:20:13,761][88327] Updated weights for policy 1, policy_version 79870 (0.0007) -[2023-10-09 03:20:13,952][88326] Updated weights for policy 0, policy_version 79792 (0.0009) -[2023-10-09 03:20:13,974][87372] Fps is (10 sec: 16384.2, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 163479552. Throughput: 0: 1694.5, 1: 1700.4. Samples: 40876624. Policy #0 lag: (min: 8.0, avg: 23.4, max: 40.0) -[2023-10-09 03:20:13,974][87372] Avg episode reward: [(0, '7.510'), (1, '7.170')] -[2023-10-09 03:20:14,318][88326] Updated weights for policy 0, policy_version 79802 (0.0007) -[2023-10-09 03:20:17,861][88327] Updated weights for policy 1, policy_version 79880 (0.0007) -[2023-10-09 03:20:18,217][88327] Updated weights for policy 1, policy_version 79890 (0.0009) -[2023-10-09 03:20:18,382][88326] Updated weights for policy 0, policy_version 79812 (0.0009) -[2023-10-09 03:20:18,588][88327] Updated weights for policy 1, policy_version 79900 (0.0007) -[2023-10-09 03:20:18,745][88326] Updated weights for policy 0, policy_version 79822 (0.0010) -[2023-10-09 03:20:18,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 163545088. Throughput: 0: 1699.1, 1: 1686.9. Samples: 40897200. Policy #0 lag: (min: 8.0, avg: 23.4, max: 40.0) -[2023-10-09 03:20:18,975][87372] Avg episode reward: [(0, '7.690'), (1, '7.230')] -[2023-10-09 03:20:19,104][88326] Updated weights for policy 0, policy_version 79832 (0.0008) -[2023-10-09 03:20:22,644][88327] Updated weights for policy 1, policy_version 79910 (0.0007) -[2023-10-09 03:20:23,016][88327] Updated weights for policy 1, policy_version 79920 (0.0008) -[2023-10-09 03:20:23,064][88326] Updated weights for policy 0, policy_version 79842 (0.0007) -[2023-10-09 03:20:23,375][88327] Updated weights for policy 1, policy_version 79930 (0.0007) -[2023-10-09 03:20:23,429][88326] Updated weights for policy 0, policy_version 79852 (0.0008) -[2023-10-09 03:20:23,788][88326] Updated weights for policy 0, policy_version 79862 (0.0010) -[2023-10-09 03:20:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 163610624. Throughput: 0: 1702.6, 1: 1695.8. Samples: 40906926. Policy #0 lag: (min: 8.0, avg: 23.4, max: 40.0) -[2023-10-09 03:20:23,974][87372] Avg episode reward: [(0, '7.870'), (1, '7.640')] -[2023-10-09 03:20:24,161][88326] Updated weights for policy 0, policy_version 79872 (0.0008) -[2023-10-09 03:20:27,185][88327] Updated weights for policy 1, policy_version 79940 (0.0009) -[2023-10-09 03:20:27,547][88327] Updated weights for policy 1, policy_version 79950 (0.0009) -[2023-10-09 03:20:27,914][88327] Updated weights for policy 1, policy_version 79960 (0.0009) -[2023-10-09 03:20:28,120][88326] Updated weights for policy 0, policy_version 79882 (0.0008) -[2023-10-09 03:20:28,490][88326] Updated weights for policy 0, policy_version 79892 (0.0010) -[2023-10-09 03:20:28,867][88326] Updated weights for policy 0, policy_version 79902 (0.0010) -[2023-10-09 03:20:28,974][87372] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 163708928. Throughput: 0: 1706.6, 1: 1698.2. Samples: 40927986. Policy #0 lag: (min: 18.0, avg: 27.4, max: 50.0) -[2023-10-09 03:20:28,975][87372] Avg episode reward: [(0, '7.270'), (1, '7.080')] -[2023-10-09 03:20:32,037][88327] Updated weights for policy 1, policy_version 79970 (0.0010) -[2023-10-09 03:20:32,407][88327] Updated weights for policy 1, policy_version 79980 (0.0007) -[2023-10-09 03:20:32,769][88327] Updated weights for policy 1, policy_version 79990 (0.0009) -[2023-10-09 03:20:33,029][88326] Updated weights for policy 0, policy_version 79912 (0.0009) -[2023-10-09 03:20:33,131][88327] Updated weights for policy 1, policy_version 80000 (0.0007) -[2023-10-09 03:20:33,401][88326] Updated weights for policy 0, policy_version 79922 (0.0010) -[2023-10-09 03:20:33,770][88326] Updated weights for policy 0, policy_version 79932 (0.0009) -[2023-10-09 03:20:33,974][87372] Fps is (10 sec: 16383.5, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 163774464. Throughput: 0: 1692.7, 1: 1670.1. Samples: 40947214. Policy #0 lag: (min: 18.0, avg: 27.4, max: 50.0) -[2023-10-09 03:20:33,975][87372] Avg episode reward: [(0, '7.130'), (1, '6.850')] -[2023-10-09 03:20:33,985][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000079936_81854464.pth... -[2023-10-09 03:20:33,986][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000080000_81920000.pth... -[2023-10-09 03:20:34,017][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000078400_80281600.pth -[2023-10-09 03:20:34,023][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000078368_80248832.pth -[2023-10-09 03:20:37,204][88327] Updated weights for policy 1, policy_version 80010 (0.0007) -[2023-10-09 03:20:37,564][88327] Updated weights for policy 1, policy_version 80020 (0.0008) -[2023-10-09 03:20:37,834][88326] Updated weights for policy 0, policy_version 79942 (0.0008) -[2023-10-09 03:20:37,932][88327] Updated weights for policy 1, policy_version 80030 (0.0007) -[2023-10-09 03:20:38,199][88326] Updated weights for policy 0, policy_version 79952 (0.0008) -[2023-10-09 03:20:38,579][88326] Updated weights for policy 0, policy_version 79962 (0.0007) -[2023-10-09 03:20:38,974][87372] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 163840000. Throughput: 0: 1702.0, 1: 1696.5. Samples: 40957922. Policy #0 lag: (min: 18.0, avg: 27.4, max: 50.0) -[2023-10-09 03:20:38,975][87372] Avg episode reward: [(0, '7.040'), (1, '7.690')] -[2023-10-09 03:20:41,937][88327] Updated weights for policy 1, policy_version 80040 (0.0010) -[2023-10-09 03:20:42,296][88327] Updated weights for policy 1, policy_version 80050 (0.0010) -[2023-10-09 03:20:42,668][88327] Updated weights for policy 1, policy_version 80060 (0.0010) -[2023-10-09 03:20:42,807][88326] Updated weights for policy 0, policy_version 79972 (0.0008) -[2023-10-09 03:20:43,179][88326] Updated weights for policy 0, policy_version 79982 (0.0008) -[2023-10-09 03:20:43,552][88326] Updated weights for policy 0, policy_version 79992 (0.0008) -[2023-10-09 03:20:43,974][87372] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 163905536. Throughput: 0: 1691.2, 1: 1680.0. Samples: 40977994. Policy #0 lag: (min: 18.0, avg: 27.4, max: 50.0) -[2023-10-09 03:20:43,975][87372] Avg episode reward: [(0, '6.960'), (1, '7.460')] -[2023-10-09 03:20:46,890][88327] Updated weights for policy 1, policy_version 80070 (0.0008) -[2023-10-09 03:20:47,251][88327] Updated weights for policy 1, policy_version 80080 (0.0007) -[2023-10-09 03:20:47,518][88326] Updated weights for policy 0, policy_version 80002 (0.0008) -[2023-10-09 03:20:47,607][88327] Updated weights for policy 1, policy_version 80090 (0.0010) -[2023-10-09 03:20:47,891][88326] Updated weights for policy 0, policy_version 80012 (0.0009) -[2023-10-09 03:20:48,259][88326] Updated weights for policy 0, policy_version 80022 (0.0011) -[2023-10-09 03:20:48,627][88326] Updated weights for policy 0, policy_version 80032 (0.0010) -[2023-10-09 03:20:48,974][87372] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 163971072. Throughput: 0: 1679.1, 1: 1673.8. Samples: 40997452. Policy #0 lag: (min: 18.0, avg: 27.4, max: 50.0) -[2023-10-09 03:20:48,975][87372] Avg episode reward: [(0, '6.330'), (1, '7.620')] -[2023-10-09 03:20:51,608][88327] Updated weights for policy 1, policy_version 80100 (0.0009) -[2023-10-09 03:20:51,987][88327] Updated weights for policy 1, policy_version 80110 (0.0008) -[2023-10-09 03:20:52,343][88327] Updated weights for policy 1, policy_version 80120 (0.0009) -[2023-10-09 03:20:52,768][88326] Updated weights for policy 0, policy_version 80042 (0.0008) -[2023-10-09 03:20:53,135][88326] Updated weights for policy 0, policy_version 80052 (0.0007) -[2023-10-09 03:20:53,510][88326] Updated weights for policy 0, policy_version 80062 (0.0007) -[2023-10-09 03:20:53,974][87372] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 164036608. Throughput: 0: 1692.8, 1: 1701.2. Samples: 41008536. Policy #0 lag: (min: 18.0, avg: 27.4, max: 50.0) -[2023-10-09 03:20:53,975][87372] Avg episode reward: [(0, '6.710'), (1, '7.590')] -[2023-10-09 03:20:56,511][88327] Updated weights for policy 1, policy_version 80130 (0.0009) -[2023-10-09 03:20:56,869][88327] Updated weights for policy 1, policy_version 80140 (0.0008) -[2023-10-09 03:20:57,232][88327] Updated weights for policy 1, policy_version 80150 (0.0008) -[2023-10-09 03:20:57,556][88326] Updated weights for policy 0, policy_version 80072 (0.0009) -[2023-10-09 03:20:57,589][88327] Updated weights for policy 1, policy_version 80160 (0.0009) -[2023-10-09 03:20:57,911][88326] Updated weights for policy 0, policy_version 80082 (0.0010) -[2023-10-09 03:20:58,281][88326] Updated weights for policy 0, policy_version 80092 (0.0008) -[2023-10-09 03:20:58,974][87372] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 164102144. Throughput: 0: 1693.1, 1: 1681.5. Samples: 41028484. Policy #0 lag: (min: 18.0, avg: 27.4, max: 50.0) -[2023-10-09 03:20:58,975][87372] Avg episode reward: [(0, '6.860'), (1, '7.830')] -[2023-10-09 03:21:01,582][88327] Updated weights for policy 1, policy_version 80170 (0.0009) -[2023-10-09 03:21:01,951][88327] Updated weights for policy 1, policy_version 80180 (0.0007) -[2023-10-09 03:21:02,320][88327] Updated weights for policy 1, policy_version 80190 (0.0007) -[2023-10-09 03:21:02,446][88326] Updated weights for policy 0, policy_version 80102 (0.0007) -[2023-10-09 03:21:02,814][88326] Updated weights for policy 0, policy_version 80112 (0.0008) -[2023-10-09 03:21:03,174][88326] Updated weights for policy 0, policy_version 80122 (0.0007) -[2023-10-09 03:21:03,974][87372] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 164167680. Throughput: 0: 1664.0, 1: 1677.2. Samples: 41047552. Policy #0 lag: (min: 18.0, avg: 27.4, max: 50.0) -[2023-10-09 03:21:03,975][87372] Avg episode reward: [(0, '6.310'), (1, '7.680')] -[2023-10-09 03:21:06,335][88327] Updated weights for policy 1, policy_version 80200 (0.0009) -[2023-10-09 03:21:06,703][88327] Updated weights for policy 1, policy_version 80210 (0.0009) -[2023-10-09 03:21:07,068][88327] Updated weights for policy 1, policy_version 80220 (0.0009) -[2023-10-09 03:21:07,097][88326] Updated weights for policy 0, policy_version 80132 (0.0008) -[2023-10-09 03:21:07,467][88326] Updated weights for policy 0, policy_version 80142 (0.0007) -[2023-10-09 03:21:07,824][88326] Updated weights for policy 0, policy_version 80152 (0.0007) -[2023-10-09 03:21:08,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 164233216. Throughput: 0: 1687.8, 1: 1691.4. Samples: 41058992. Policy #0 lag: (min: 18.0, avg: 27.4, max: 50.0) -[2023-10-09 03:21:08,975][87372] Avg episode reward: [(0, '7.110'), (1, '7.900')] -[2023-10-09 03:21:11,274][88327] Updated weights for policy 1, policy_version 80230 (0.0009) -[2023-10-09 03:21:11,639][88327] Updated weights for policy 1, policy_version 80240 (0.0010) -[2023-10-09 03:21:11,967][88326] Updated weights for policy 0, policy_version 80162 (0.0009) -[2023-10-09 03:21:12,008][88327] Updated weights for policy 1, policy_version 80250 (0.0008) -[2023-10-09 03:21:12,343][88326] Updated weights for policy 0, policy_version 80172 (0.0008) -[2023-10-09 03:21:12,704][88326] Updated weights for policy 0, policy_version 80182 (0.0010) -[2023-10-09 03:21:13,076][88326] Updated weights for policy 0, policy_version 80192 (0.0008) -[2023-10-09 03:21:13,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 164298752. Throughput: 0: 1675.6, 1: 1665.1. Samples: 41078314. Policy #0 lag: (min: 18.0, avg: 27.4, max: 50.0) -[2023-10-09 03:21:13,975][87372] Avg episode reward: [(0, '6.810'), (1, '7.410')] -[2023-10-09 03:21:15,933][88327] Updated weights for policy 1, policy_version 80260 (0.0010) -[2023-10-09 03:21:16,297][88327] Updated weights for policy 1, policy_version 80270 (0.0009) -[2023-10-09 03:21:16,657][88327] Updated weights for policy 1, policy_version 80280 (0.0008) -[2023-10-09 03:21:17,187][88326] Updated weights for policy 0, policy_version 80202 (0.0009) -[2023-10-09 03:21:17,554][88326] Updated weights for policy 0, policy_version 80212 (0.0009) -[2023-10-09 03:21:17,931][88326] Updated weights for policy 0, policy_version 80222 (0.0010) -[2023-10-09 03:21:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 164364288. Throughput: 0: 1663.2, 1: 1686.4. Samples: 41097942. Policy #0 lag: (min: 18.0, avg: 27.4, max: 50.0) -[2023-10-09 03:21:18,975][87372] Avg episode reward: [(0, '6.980'), (1, '7.680')] -[2023-10-09 03:21:20,732][88327] Updated weights for policy 1, policy_version 80290 (0.0009) -[2023-10-09 03:21:21,099][88327] Updated weights for policy 1, policy_version 80300 (0.0007) -[2023-10-09 03:21:21,470][88327] Updated weights for policy 1, policy_version 80310 (0.0008) -[2023-10-09 03:21:21,833][88327] Updated weights for policy 1, policy_version 80320 (0.0007) -[2023-10-09 03:21:21,957][88326] Updated weights for policy 0, policy_version 80232 (0.0009) -[2023-10-09 03:21:22,335][88326] Updated weights for policy 0, policy_version 80242 (0.0007) -[2023-10-09 03:21:22,701][88326] Updated weights for policy 0, policy_version 80252 (0.0007) -[2023-10-09 03:21:23,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 164429824. Throughput: 0: 1684.4, 1: 1678.1. Samples: 41109236. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) -[2023-10-09 03:21:23,974][87372] Avg episode reward: [(0, '7.290'), (1, '7.550')] -[2023-10-09 03:21:25,749][88327] Updated weights for policy 1, policy_version 80330 (0.0010) -[2023-10-09 03:21:26,105][88327] Updated weights for policy 1, policy_version 80340 (0.0010) -[2023-10-09 03:21:26,473][88327] Updated weights for policy 1, policy_version 80350 (0.0009) -[2023-10-09 03:21:26,674][88326] Updated weights for policy 0, policy_version 80262 (0.0008) -[2023-10-09 03:21:27,053][88326] Updated weights for policy 0, policy_version 80272 (0.0008) -[2023-10-09 03:21:27,425][88326] Updated weights for policy 0, policy_version 80282 (0.0007) -[2023-10-09 03:21:28,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 164495360. Throughput: 0: 1675.4, 1: 1681.8. Samples: 41129068. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) -[2023-10-09 03:21:28,974][87372] Avg episode reward: [(0, '7.840'), (1, '7.330')] -[2023-10-09 03:21:30,558][88327] Updated weights for policy 1, policy_version 80360 (0.0010) -[2023-10-09 03:21:30,928][88327] Updated weights for policy 1, policy_version 80370 (0.0011) -[2023-10-09 03:21:31,277][88326] Updated weights for policy 0, policy_version 80292 (0.0009) -[2023-10-09 03:21:31,303][88327] Updated weights for policy 1, policy_version 80380 (0.0010) -[2023-10-09 03:21:31,647][88326] Updated weights for policy 0, policy_version 80302 (0.0010) -[2023-10-09 03:21:32,020][88326] Updated weights for policy 0, policy_version 80312 (0.0009) -[2023-10-09 03:21:33,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 164560896. Throughput: 0: 1676.5, 1: 1700.1. Samples: 41149398. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) -[2023-10-09 03:21:33,975][87372] Avg episode reward: [(0, '7.560'), (1, '7.730')] -[2023-10-09 03:21:35,292][88327] Updated weights for policy 1, policy_version 80390 (0.0010) -[2023-10-09 03:21:35,653][88327] Updated weights for policy 1, policy_version 80400 (0.0010) -[2023-10-09 03:21:36,011][88327] Updated weights for policy 1, policy_version 80410 (0.0008) -[2023-10-09 03:21:36,036][88326] Updated weights for policy 0, policy_version 80322 (0.0010) -[2023-10-09 03:21:36,395][88326] Updated weights for policy 0, policy_version 80332 (0.0009) -[2023-10-09 03:21:36,766][88326] Updated weights for policy 0, policy_version 80342 (0.0007) -[2023-10-09 03:21:37,136][88326] Updated weights for policy 0, policy_version 80352 (0.0008) -[2023-10-09 03:21:38,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 164626432. Throughput: 0: 1685.0, 1: 1674.4. Samples: 41159710. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) -[2023-10-09 03:21:38,974][87372] Avg episode reward: [(0, '7.730'), (1, '7.040')] -[2023-10-09 03:21:40,002][88327] Updated weights for policy 1, policy_version 80420 (0.0009) -[2023-10-09 03:21:40,365][88327] Updated weights for policy 1, policy_version 80430 (0.0010) -[2023-10-09 03:21:40,729][88327] Updated weights for policy 1, policy_version 80440 (0.0007) -[2023-10-09 03:21:41,158][88326] Updated weights for policy 0, policy_version 80362 (0.0008) -[2023-10-09 03:21:41,532][88326] Updated weights for policy 0, policy_version 80372 (0.0008) -[2023-10-09 03:21:41,893][88326] Updated weights for policy 0, policy_version 80382 (0.0010) -[2023-10-09 03:21:43,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 164691968. Throughput: 0: 1660.8, 1: 1696.5. Samples: 41179562. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) -[2023-10-09 03:21:43,975][87372] Avg episode reward: [(0, '7.530'), (1, '7.490')] -[2023-10-09 03:21:44,718][88327] Updated weights for policy 1, policy_version 80450 (0.0007) -[2023-10-09 03:21:45,125][88327] Updated weights for policy 1, policy_version 80460 (0.0009) -[2023-10-09 03:21:45,478][88327] Updated weights for policy 1, policy_version 80470 (0.0010) -[2023-10-09 03:21:45,847][88327] Updated weights for policy 1, policy_version 80480 (0.0011) -[2023-10-09 03:21:46,056][88326] Updated weights for policy 0, policy_version 80392 (0.0009) -[2023-10-09 03:21:46,432][88326] Updated weights for policy 0, policy_version 80402 (0.0007) -[2023-10-09 03:21:46,800][88326] Updated weights for policy 0, policy_version 80412 (0.0010) -[2023-10-09 03:21:48,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 164757504. Throughput: 0: 1680.6, 1: 1709.9. Samples: 41200126. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) -[2023-10-09 03:21:48,975][87372] Avg episode reward: [(0, '7.140'), (1, '7.350')] -[2023-10-09 03:21:49,920][88327] Updated weights for policy 1, policy_version 80490 (0.0008) -[2023-10-09 03:21:50,290][88327] Updated weights for policy 1, policy_version 80500 (0.0007) -[2023-10-09 03:21:50,648][88327] Updated weights for policy 1, policy_version 80510 (0.0011) -[2023-10-09 03:21:50,829][88326] Updated weights for policy 0, policy_version 80422 (0.0010) -[2023-10-09 03:21:51,195][88326] Updated weights for policy 0, policy_version 80432 (0.0011) -[2023-10-09 03:21:51,570][88326] Updated weights for policy 0, policy_version 80442 (0.0008) -[2023-10-09 03:21:53,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 164823040. Throughput: 0: 1669.2, 1: 1685.0. Samples: 41209930. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) -[2023-10-09 03:21:53,975][87372] Avg episode reward: [(0, '6.610'), (1, '7.700')] -[2023-10-09 03:21:54,762][88327] Updated weights for policy 1, policy_version 80520 (0.0009) -[2023-10-09 03:21:55,122][88327] Updated weights for policy 1, policy_version 80530 (0.0011) -[2023-10-09 03:21:55,493][88327] Updated weights for policy 1, policy_version 80540 (0.0009) -[2023-10-09 03:21:55,785][88326] Updated weights for policy 0, policy_version 80452 (0.0009) -[2023-10-09 03:21:56,154][88326] Updated weights for policy 0, policy_version 80462 (0.0009) -[2023-10-09 03:21:56,518][88326] Updated weights for policy 0, policy_version 80472 (0.0007) -[2023-10-09 03:21:58,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 164888576. Throughput: 0: 1655.6, 1: 1711.4. Samples: 41229828. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) -[2023-10-09 03:21:58,975][87372] Avg episode reward: [(0, '6.950'), (1, '7.650')] -[2023-10-09 03:21:59,392][88327] Updated weights for policy 1, policy_version 80550 (0.0008) -[2023-10-09 03:21:59,755][88327] Updated weights for policy 1, policy_version 80560 (0.0008) -[2023-10-09 03:22:00,114][88327] Updated weights for policy 1, policy_version 80570 (0.0008) -[2023-10-09 03:22:00,638][88326] Updated weights for policy 0, policy_version 80482 (0.0008) -[2023-10-09 03:22:01,008][88326] Updated weights for policy 0, policy_version 80492 (0.0008) -[2023-10-09 03:22:01,382][88326] Updated weights for policy 0, policy_version 80502 (0.0008) -[2023-10-09 03:22:01,753][88326] Updated weights for policy 0, policy_version 80512 (0.0009) -[2023-10-09 03:22:03,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 164954112. Throughput: 0: 1683.3, 1: 1715.7. Samples: 41250896. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) -[2023-10-09 03:22:03,975][87372] Avg episode reward: [(0, '7.160'), (1, '7.750')] -[2023-10-09 03:22:04,120][88327] Updated weights for policy 1, policy_version 80580 (0.0009) -[2023-10-09 03:22:04,481][88327] Updated weights for policy 1, policy_version 80590 (0.0008) -[2023-10-09 03:22:04,852][88327] Updated weights for policy 1, policy_version 80600 (0.0008) -[2023-10-09 03:22:05,779][88326] Updated weights for policy 0, policy_version 80522 (0.0008) -[2023-10-09 03:22:06,139][88326] Updated weights for policy 0, policy_version 80532 (0.0008) -[2023-10-09 03:22:06,510][88326] Updated weights for policy 0, policy_version 80542 (0.0007) -[2023-10-09 03:22:08,883][88327] Updated weights for policy 1, policy_version 80610 (0.0008) -[2023-10-09 03:22:08,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 165019648. Throughput: 0: 1665.7, 1: 1696.8. Samples: 41260552. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) -[2023-10-09 03:22:08,975][87372] Avg episode reward: [(0, '6.930'), (1, '7.280')] -[2023-10-09 03:22:09,252][88327] Updated weights for policy 1, policy_version 80620 (0.0009) -[2023-10-09 03:22:09,620][88327] Updated weights for policy 1, policy_version 80630 (0.0010) -[2023-10-09 03:22:09,986][88327] Updated weights for policy 1, policy_version 80640 (0.0009) -[2023-10-09 03:22:10,514][88326] Updated weights for policy 0, policy_version 80552 (0.0009) -[2023-10-09 03:22:10,888][88326] Updated weights for policy 0, policy_version 80562 (0.0010) -[2023-10-09 03:22:11,253][88326] Updated weights for policy 0, policy_version 80572 (0.0010) -[2023-10-09 03:22:13,974][87372] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 165085184. Throughput: 0: 1671.5, 1: 1706.8. Samples: 41281092. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) -[2023-10-09 03:22:13,974][87372] Avg episode reward: [(0, '7.110'), (1, '7.110')] -[2023-10-09 03:22:13,979][88327] Updated weights for policy 1, policy_version 80650 (0.0008) -[2023-10-09 03:22:14,342][88327] Updated weights for policy 1, policy_version 80660 (0.0008) -[2023-10-09 03:22:14,700][88327] Updated weights for policy 1, policy_version 80670 (0.0008) -[2023-10-09 03:22:15,281][88326] Updated weights for policy 0, policy_version 80582 (0.0008) -[2023-10-09 03:22:15,646][88326] Updated weights for policy 0, policy_version 80592 (0.0008) -[2023-10-09 03:22:16,022][88326] Updated weights for policy 0, policy_version 80602 (0.0009) -[2023-10-09 03:22:18,831][88327] Updated weights for policy 1, policy_version 80680 (0.0007) -[2023-10-09 03:22:18,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 165150720. Throughput: 0: 1688.3, 1: 1706.6. Samples: 41302166. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:22:18,975][87372] Avg episode reward: [(0, '7.090'), (1, '7.660')] -[2023-10-09 03:22:19,197][88327] Updated weights for policy 1, policy_version 80690 (0.0010) -[2023-10-09 03:22:19,575][88327] Updated weights for policy 1, policy_version 80700 (0.0008) -[2023-10-09 03:22:20,034][88326] Updated weights for policy 0, policy_version 80612 (0.0007) -[2023-10-09 03:22:20,403][88326] Updated weights for policy 0, policy_version 80622 (0.0008) -[2023-10-09 03:22:20,769][88326] Updated weights for policy 0, policy_version 80632 (0.0009) -[2023-10-09 03:22:23,534][88327] Updated weights for policy 1, policy_version 80710 (0.0009) -[2023-10-09 03:22:23,893][88327] Updated weights for policy 1, policy_version 80720 (0.0008) -[2023-10-09 03:22:23,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13329.3). Total num frames: 165216256. Throughput: 0: 1666.8, 1: 1703.8. Samples: 41311386. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:22:23,975][87372] Avg episode reward: [(0, '7.210'), (1, '8.040')] -[2023-10-09 03:22:24,260][88327] Updated weights for policy 1, policy_version 80730 (0.0009) -[2023-10-09 03:22:24,712][88326] Updated weights for policy 0, policy_version 80642 (0.0008) -[2023-10-09 03:22:25,069][88326] Updated weights for policy 0, policy_version 80652 (0.0007) -[2023-10-09 03:22:25,435][88326] Updated weights for policy 0, policy_version 80662 (0.0007) -[2023-10-09 03:22:25,799][88326] Updated weights for policy 0, policy_version 80672 (0.0010) -[2023-10-09 03:22:28,299][88327] Updated weights for policy 1, policy_version 80740 (0.0008) -[2023-10-09 03:22:28,668][88327] Updated weights for policy 1, policy_version 80750 (0.0007) -[2023-10-09 03:22:28,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 165281792. Throughput: 0: 1694.7, 1: 1704.2. Samples: 41332512. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:22:28,975][87372] Avg episode reward: [(0, '6.310'), (1, '7.570')] -[2023-10-09 03:22:29,034][88327] Updated weights for policy 1, policy_version 80760 (0.0008) -[2023-10-09 03:22:29,925][88326] Updated weights for policy 0, policy_version 80682 (0.0010) -[2023-10-09 03:22:30,287][88326] Updated weights for policy 0, policy_version 80692 (0.0011) -[2023-10-09 03:22:30,660][88326] Updated weights for policy 0, policy_version 80702 (0.0010) -[2023-10-09 03:22:33,148][88327] Updated weights for policy 1, policy_version 80770 (0.0009) -[2023-10-09 03:22:33,571][88327] Updated weights for policy 1, policy_version 80780 (0.0008) -[2023-10-09 03:22:33,937][88327] Updated weights for policy 1, policy_version 80790 (0.0008) -[2023-10-09 03:22:33,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13329.3). Total num frames: 165347328. Throughput: 0: 1697.0, 1: 1698.6. Samples: 41352928. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:22:33,975][87372] Avg episode reward: [(0, '7.020'), (1, '7.600')] -[2023-10-09 03:22:33,985][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000080704_82640896.pth... -[2023-10-09 03:22:34,023][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000079136_81035264.pth -[2023-10-09 03:22:34,301][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000080800_82739200.pth... -[2023-10-09 03:22:34,305][88327] Updated weights for policy 1, policy_version 80800 (0.0008) -[2023-10-09 03:22:34,330][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000079200_81100800.pth -[2023-10-09 03:22:34,791][88326] Updated weights for policy 0, policy_version 80712 (0.0009) -[2023-10-09 03:22:35,160][88326] Updated weights for policy 0, policy_version 80722 (0.0009) -[2023-10-09 03:22:35,527][88326] Updated weights for policy 0, policy_version 80732 (0.0011) -[2023-10-09 03:22:38,318][88327] Updated weights for policy 1, policy_version 80810 (0.0008) -[2023-10-09 03:22:38,681][88327] Updated weights for policy 1, policy_version 80820 (0.0009) -[2023-10-09 03:22:38,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 165412864. Throughput: 0: 1681.4, 1: 1697.2. Samples: 41361968. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:22:38,975][87372] Avg episode reward: [(0, '6.780'), (1, '7.540')] -[2023-10-09 03:22:39,050][88327] Updated weights for policy 1, policy_version 80830 (0.0007) -[2023-10-09 03:22:39,664][88326] Updated weights for policy 0, policy_version 80742 (0.0010) -[2023-10-09 03:22:40,035][88326] Updated weights for policy 0, policy_version 80752 (0.0010) -[2023-10-09 03:22:40,405][88326] Updated weights for policy 0, policy_version 80762 (0.0009) -[2023-10-09 03:22:42,934][88327] Updated weights for policy 1, policy_version 80840 (0.0009) -[2023-10-09 03:22:43,295][88327] Updated weights for policy 1, policy_version 80850 (0.0010) -[2023-10-09 03:22:43,657][88327] Updated weights for policy 1, policy_version 80860 (0.0009) -[2023-10-09 03:22:43,974][87372] Fps is (10 sec: 16384.3, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 165511168. Throughput: 0: 1701.1, 1: 1698.4. Samples: 41382804. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:22:43,975][87372] Avg episode reward: [(0, '6.260'), (1, '6.780')] -[2023-10-09 03:22:44,476][88326] Updated weights for policy 0, policy_version 80772 (0.0008) -[2023-10-09 03:22:44,842][88326] Updated weights for policy 0, policy_version 80782 (0.0009) -[2023-10-09 03:22:45,218][88326] Updated weights for policy 0, policy_version 80792 (0.0010) -[2023-10-09 03:22:47,731][88327] Updated weights for policy 1, policy_version 80870 (0.0009) -[2023-10-09 03:22:48,092][88327] Updated weights for policy 1, policy_version 80880 (0.0010) -[2023-10-09 03:22:48,463][88327] Updated weights for policy 1, policy_version 80890 (0.0009) -[2023-10-09 03:22:48,974][87372] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 165576704. Throughput: 0: 1703.8, 1: 1681.6. Samples: 41403240. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:22:48,975][87372] Avg episode reward: [(0, '6.590'), (1, '7.260')] -[2023-10-09 03:22:49,139][88326] Updated weights for policy 0, policy_version 80802 (0.0008) -[2023-10-09 03:22:49,506][88326] Updated weights for policy 0, policy_version 80812 (0.0010) -[2023-10-09 03:22:49,879][88326] Updated weights for policy 0, policy_version 80822 (0.0010) -[2023-10-09 03:22:50,250][88326] Updated weights for policy 0, policy_version 80832 (0.0009) -[2023-10-09 03:22:52,702][88327] Updated weights for policy 1, policy_version 80900 (0.0008) -[2023-10-09 03:22:53,063][88327] Updated weights for policy 1, policy_version 80910 (0.0010) -[2023-10-09 03:22:53,431][88327] Updated weights for policy 1, policy_version 80920 (0.0011) -[2023-10-09 03:22:53,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 165642240. Throughput: 0: 1689.7, 1: 1694.4. Samples: 41412838. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:22:53,975][87372] Avg episode reward: [(0, '7.030'), (1, '7.020')] -[2023-10-09 03:22:54,330][88326] Updated weights for policy 0, policy_version 80842 (0.0007) -[2023-10-09 03:22:54,689][88326] Updated weights for policy 0, policy_version 80852 (0.0007) -[2023-10-09 03:22:55,062][88326] Updated weights for policy 0, policy_version 80862 (0.0007) -[2023-10-09 03:22:57,323][88327] Updated weights for policy 1, policy_version 80930 (0.0010) -[2023-10-09 03:22:57,690][88327] Updated weights for policy 1, policy_version 80940 (0.0011) -[2023-10-09 03:22:58,053][88327] Updated weights for policy 1, policy_version 80950 (0.0009) -[2023-10-09 03:22:58,418][88327] Updated weights for policy 1, policy_version 80960 (0.0007) -[2023-10-09 03:22:58,947][88326] Updated weights for policy 0, policy_version 80872 (0.0009) -[2023-10-09 03:22:58,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 165707776. Throughput: 0: 1701.0, 1: 1696.6. Samples: 41433984. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:22:58,974][87372] Avg episode reward: [(0, '6.510'), (1, '7.330')] -[2023-10-09 03:22:59,307][88326] Updated weights for policy 0, policy_version 80882 (0.0007) -[2023-10-09 03:22:59,677][88326] Updated weights for policy 0, policy_version 80892 (0.0008) -[2023-10-09 03:23:02,500][88327] Updated weights for policy 1, policy_version 80970 (0.0009) -[2023-10-09 03:23:02,863][88327] Updated weights for policy 1, policy_version 80980 (0.0009) -[2023-10-09 03:23:03,227][88327] Updated weights for policy 1, policy_version 80990 (0.0009) -[2023-10-09 03:23:03,692][88326] Updated weights for policy 0, policy_version 80902 (0.0008) -[2023-10-09 03:23:03,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 165773312. Throughput: 0: 1703.0, 1: 1672.6. Samples: 41454068. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:23:03,975][87372] Avg episode reward: [(0, '7.010'), (1, '7.650')] -[2023-10-09 03:23:04,055][88326] Updated weights for policy 0, policy_version 80912 (0.0009) -[2023-10-09 03:23:04,429][88326] Updated weights for policy 0, policy_version 80922 (0.0009) -[2023-10-09 03:23:07,177][88327] Updated weights for policy 1, policy_version 81000 (0.0007) -[2023-10-09 03:23:07,534][88327] Updated weights for policy 1, policy_version 81010 (0.0008) -[2023-10-09 03:23:07,904][88327] Updated weights for policy 1, policy_version 81020 (0.0008) -[2023-10-09 03:23:08,554][88326] Updated weights for policy 0, policy_version 80932 (0.0010) -[2023-10-09 03:23:08,920][88326] Updated weights for policy 0, policy_version 80942 (0.0008) -[2023-10-09 03:23:08,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 165838848. Throughput: 0: 1699.1, 1: 1696.9. Samples: 41464206. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:23:08,975][87372] Avg episode reward: [(0, '6.920'), (1, '7.510')] -[2023-10-09 03:23:09,287][88326] Updated weights for policy 0, policy_version 80952 (0.0008) -[2023-10-09 03:23:11,857][88327] Updated weights for policy 1, policy_version 81030 (0.0009) -[2023-10-09 03:23:12,213][88327] Updated weights for policy 1, policy_version 81040 (0.0008) -[2023-10-09 03:23:12,576][88327] Updated weights for policy 1, policy_version 81050 (0.0007) -[2023-10-09 03:23:13,345][88326] Updated weights for policy 0, policy_version 80962 (0.0007) -[2023-10-09 03:23:13,708][88326] Updated weights for policy 0, policy_version 80972 (0.0009) -[2023-10-09 03:23:13,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 165904384. Throughput: 0: 1693.6, 1: 1686.7. Samples: 41484628. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-10-09 03:23:13,975][87372] Avg episode reward: [(0, '6.490'), (1, '7.530')] -[2023-10-09 03:23:14,080][88326] Updated weights for policy 0, policy_version 80982 (0.0009) -[2023-10-09 03:23:14,449][88326] Updated weights for policy 0, policy_version 80992 (0.0009) -[2023-10-09 03:23:16,519][88327] Updated weights for policy 1, policy_version 81060 (0.0007) -[2023-10-09 03:23:16,892][88327] Updated weights for policy 1, policy_version 81070 (0.0009) -[2023-10-09 03:23:17,254][88327] Updated weights for policy 1, policy_version 81080 (0.0011) -[2023-10-09 03:23:18,438][88326] Updated weights for policy 0, policy_version 81002 (0.0007) -[2023-10-09 03:23:18,814][88326] Updated weights for policy 0, policy_version 81012 (0.0009) -[2023-10-09 03:23:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 165969920. Throughput: 0: 1698.5, 1: 1680.3. Samples: 41504972. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-10-09 03:23:18,975][87372] Avg episode reward: [(0, '6.510'), (1, '7.880')] -[2023-10-09 03:23:19,194][88326] Updated weights for policy 0, policy_version 81022 (0.0008) -[2023-10-09 03:23:21,406][88327] Updated weights for policy 1, policy_version 81090 (0.0010) -[2023-10-09 03:23:21,819][88327] Updated weights for policy 1, policy_version 81100 (0.0008) -[2023-10-09 03:23:22,178][88327] Updated weights for policy 1, policy_version 81110 (0.0009) -[2023-10-09 03:23:22,545][88327] Updated weights for policy 1, policy_version 81120 (0.0008) -[2023-10-09 03:23:23,195][88326] Updated weights for policy 0, policy_version 81032 (0.0010) -[2023-10-09 03:23:23,566][88326] Updated weights for policy 0, policy_version 81042 (0.0009) -[2023-10-09 03:23:23,931][88326] Updated weights for policy 0, policy_version 81052 (0.0008) -[2023-10-09 03:23:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 166035456. Throughput: 0: 1702.4, 1: 1708.8. Samples: 41515470. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-10-09 03:23:23,975][87372] Avg episode reward: [(0, '7.150'), (1, '7.490')] -[2023-10-09 03:23:26,508][88327] Updated weights for policy 1, policy_version 81130 (0.0007) -[2023-10-09 03:23:26,864][88327] Updated weights for policy 1, policy_version 81140 (0.0007) -[2023-10-09 03:23:27,231][88327] Updated weights for policy 1, policy_version 81150 (0.0007) -[2023-10-09 03:23:27,918][88326] Updated weights for policy 0, policy_version 81062 (0.0009) -[2023-10-09 03:23:28,291][88326] Updated weights for policy 0, policy_version 81072 (0.0009) -[2023-10-09 03:23:28,670][88326] Updated weights for policy 0, policy_version 81082 (0.0007) -[2023-10-09 03:23:28,974][87372] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 166133760. Throughput: 0: 1708.4, 1: 1687.7. Samples: 41535628. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-10-09 03:23:28,974][87372] Avg episode reward: [(0, '7.320'), (1, '7.350')] -[2023-10-09 03:23:31,189][88327] Updated weights for policy 1, policy_version 81160 (0.0009) -[2023-10-09 03:23:31,551][88327] Updated weights for policy 1, policy_version 81170 (0.0009) -[2023-10-09 03:23:31,913][88327] Updated weights for policy 1, policy_version 81180 (0.0009) -[2023-10-09 03:23:32,687][88326] Updated weights for policy 0, policy_version 81092 (0.0007) -[2023-10-09 03:23:33,055][88326] Updated weights for policy 0, policy_version 81102 (0.0009) -[2023-10-09 03:23:33,426][88326] Updated weights for policy 0, policy_version 81112 (0.0007) -[2023-10-09 03:23:33,974][87372] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 166199296. Throughput: 0: 1691.8, 1: 1702.0. Samples: 41555962. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-10-09 03:23:33,975][87372] Avg episode reward: [(0, '7.410'), (1, '7.600')] -[2023-10-09 03:23:35,882][88327] Updated weights for policy 1, policy_version 81190 (0.0009) -[2023-10-09 03:23:36,258][88327] Updated weights for policy 1, policy_version 81200 (0.0007) -[2023-10-09 03:23:36,614][88327] Updated weights for policy 1, policy_version 81210 (0.0010) -[2023-10-09 03:23:37,498][88326] Updated weights for policy 0, policy_version 81122 (0.0008) -[2023-10-09 03:23:37,877][88326] Updated weights for policy 0, policy_version 81132 (0.0010) -[2023-10-09 03:23:38,242][88326] Updated weights for policy 0, policy_version 81142 (0.0008) -[2023-10-09 03:23:38,608][88326] Updated weights for policy 0, policy_version 81152 (0.0008) -[2023-10-09 03:23:38,974][87372] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 166264832. Throughput: 0: 1709.2, 1: 1705.3. Samples: 41566490. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-10-09 03:23:38,975][87372] Avg episode reward: [(0, '7.040'), (1, '7.970')] -[2023-10-09 03:23:40,790][88327] Updated weights for policy 1, policy_version 81220 (0.0009) -[2023-10-09 03:23:41,154][88327] Updated weights for policy 1, policy_version 81230 (0.0007) -[2023-10-09 03:23:41,521][88327] Updated weights for policy 1, policy_version 81240 (0.0007) -[2023-10-09 03:23:42,591][88326] Updated weights for policy 0, policy_version 81162 (0.0008) -[2023-10-09 03:23:42,964][88326] Updated weights for policy 0, policy_version 81172 (0.0010) -[2023-10-09 03:23:43,324][88326] Updated weights for policy 0, policy_version 81182 (0.0009) -[2023-10-09 03:23:43,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 166330368. Throughput: 0: 1708.1, 1: 1683.3. Samples: 41586600. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-10-09 03:23:43,975][87372] Avg episode reward: [(0, '7.040'), (1, '7.250')] -[2023-10-09 03:23:45,494][88327] Updated weights for policy 1, policy_version 81250 (0.0008) -[2023-10-09 03:23:45,858][88327] Updated weights for policy 1, policy_version 81260 (0.0009) -[2023-10-09 03:23:46,228][88327] Updated weights for policy 1, policy_version 81270 (0.0008) -[2023-10-09 03:23:46,594][88327] Updated weights for policy 1, policy_version 81280 (0.0009) -[2023-10-09 03:23:47,375][88326] Updated weights for policy 0, policy_version 81192 (0.0009) -[2023-10-09 03:23:47,742][88326] Updated weights for policy 0, policy_version 81202 (0.0009) -[2023-10-09 03:23:48,123][88326] Updated weights for policy 0, policy_version 81212 (0.0009) -[2023-10-09 03:23:48,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 166395904. Throughput: 0: 1678.0, 1: 1704.9. Samples: 41606300. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-10-09 03:23:48,975][87372] Avg episode reward: [(0, '7.100'), (1, '7.510')] -[2023-10-09 03:23:50,728][88327] Updated weights for policy 1, policy_version 81290 (0.0011) -[2023-10-09 03:23:51,090][88327] Updated weights for policy 1, policy_version 81300 (0.0009) -[2023-10-09 03:23:51,460][88327] Updated weights for policy 1, policy_version 81310 (0.0010) -[2023-10-09 03:23:51,991][88326] Updated weights for policy 0, policy_version 81222 (0.0009) -[2023-10-09 03:23:52,356][88326] Updated weights for policy 0, policy_version 81232 (0.0007) -[2023-10-09 03:23:52,726][88326] Updated weights for policy 0, policy_version 81242 (0.0008) -[2023-10-09 03:23:53,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 166461440. Throughput: 0: 1710.6, 1: 1688.3. Samples: 41617156. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-10-09 03:23:53,975][87372] Avg episode reward: [(0, '7.360'), (1, '7.000')] -[2023-10-09 03:23:55,421][88327] Updated weights for policy 1, policy_version 81320 (0.0010) -[2023-10-09 03:23:55,777][88327] Updated weights for policy 1, policy_version 81330 (0.0010) -[2023-10-09 03:23:56,149][88327] Updated weights for policy 1, policy_version 81340 (0.0009) -[2023-10-09 03:23:56,896][88326] Updated weights for policy 0, policy_version 81252 (0.0008) -[2023-10-09 03:23:57,273][88326] Updated weights for policy 0, policy_version 81262 (0.0008) -[2023-10-09 03:23:57,650][88326] Updated weights for policy 0, policy_version 81272 (0.0009) -[2023-10-09 03:23:58,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 166526976. Throughput: 0: 1700.4, 1: 1687.3. Samples: 41637074. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-10-09 03:23:58,975][87372] Avg episode reward: [(0, '7.300'), (1, '7.170')] -[2023-10-09 03:24:00,089][88327] Updated weights for policy 1, policy_version 81350 (0.0009) -[2023-10-09 03:24:00,460][88327] Updated weights for policy 1, policy_version 81360 (0.0010) -[2023-10-09 03:24:00,829][88327] Updated weights for policy 1, policy_version 81370 (0.0008) -[2023-10-09 03:24:01,679][88326] Updated weights for policy 0, policy_version 81282 (0.0009) -[2023-10-09 03:24:02,038][88326] Updated weights for policy 0, policy_version 81292 (0.0008) -[2023-10-09 03:24:02,408][88326] Updated weights for policy 0, policy_version 81302 (0.0007) -[2023-10-09 03:24:02,776][88326] Updated weights for policy 0, policy_version 81312 (0.0009) -[2023-10-09 03:24:03,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 166592512. Throughput: 0: 1677.4, 1: 1704.4. Samples: 41657152. Policy #0 lag: (min: 25.0, avg: 26.8, max: 50.0) -[2023-10-09 03:24:03,975][87372] Avg episode reward: [(0, '7.650'), (1, '7.490')] -[2023-10-09 03:24:04,748][88327] Updated weights for policy 1, policy_version 81380 (0.0008) -[2023-10-09 03:24:05,103][88327] Updated weights for policy 1, policy_version 81390 (0.0009) -[2023-10-09 03:24:05,471][88327] Updated weights for policy 1, policy_version 81400 (0.0008) -[2023-10-09 03:24:06,816][88326] Updated weights for policy 0, policy_version 81322 (0.0010) -[2023-10-09 03:24:07,179][88326] Updated weights for policy 0, policy_version 81332 (0.0009) -[2023-10-09 03:24:07,555][88326] Updated weights for policy 0, policy_version 81342 (0.0010) -[2023-10-09 03:24:08,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 166658048. Throughput: 0: 1702.2, 1: 1676.8. Samples: 41667524. Policy #0 lag: (min: 25.0, avg: 26.8, max: 50.0) -[2023-10-09 03:24:08,975][87372] Avg episode reward: [(0, '7.600'), (1, '7.920')] -[2023-10-09 03:24:09,538][88327] Updated weights for policy 1, policy_version 81410 (0.0008) -[2023-10-09 03:24:09,899][88327] Updated weights for policy 1, policy_version 81420 (0.0012) -[2023-10-09 03:24:10,262][88327] Updated weights for policy 1, policy_version 81430 (0.0011) -[2023-10-09 03:24:10,627][88327] Updated weights for policy 1, policy_version 81440 (0.0011) -[2023-10-09 03:24:11,757][88326] Updated weights for policy 0, policy_version 81352 (0.0010) -[2023-10-09 03:24:12,121][88326] Updated weights for policy 0, policy_version 81362 (0.0008) -[2023-10-09 03:24:12,492][88326] Updated weights for policy 0, policy_version 81372 (0.0007) -[2023-10-09 03:24:13,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 166723584. Throughput: 0: 1676.8, 1: 1702.0. Samples: 41687672. Policy #0 lag: (min: 25.0, avg: 26.8, max: 50.0) -[2023-10-09 03:24:13,975][87372] Avg episode reward: [(0, '6.700'), (1, '7.850')] -[2023-10-09 03:24:14,677][88327] Updated weights for policy 1, policy_version 81450 (0.0011) -[2023-10-09 03:24:15,039][88327] Updated weights for policy 1, policy_version 81460 (0.0007) -[2023-10-09 03:24:15,407][88327] Updated weights for policy 1, policy_version 81470 (0.0009) -[2023-10-09 03:24:16,497][88326] Updated weights for policy 0, policy_version 81382 (0.0008) -[2023-10-09 03:24:16,866][88326] Updated weights for policy 0, policy_version 81392 (0.0009) -[2023-10-09 03:24:17,227][88326] Updated weights for policy 0, policy_version 81402 (0.0007) -[2023-10-09 03:24:18,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 166789120. Throughput: 0: 1676.8, 1: 1702.1. Samples: 41708012. Policy #0 lag: (min: 25.0, avg: 26.8, max: 50.0) -[2023-10-09 03:24:18,975][87372] Avg episode reward: [(0, '6.700'), (1, '7.050')] -[2023-10-09 03:24:19,425][88327] Updated weights for policy 1, policy_version 81480 (0.0009) -[2023-10-09 03:24:19,784][88327] Updated weights for policy 1, policy_version 81490 (0.0008) -[2023-10-09 03:24:20,154][88327] Updated weights for policy 1, policy_version 81500 (0.0009) -[2023-10-09 03:24:21,282][88326] Updated weights for policy 0, policy_version 81412 (0.0007) -[2023-10-09 03:24:21,651][88326] Updated weights for policy 0, policy_version 81422 (0.0008) -[2023-10-09 03:24:22,016][88326] Updated weights for policy 0, policy_version 81432 (0.0010) -[2023-10-09 03:24:23,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 166854656. Throughput: 0: 1687.1, 1: 1683.8. Samples: 41718182. Policy #0 lag: (min: 25.0, avg: 26.8, max: 50.0) -[2023-10-09 03:24:23,974][87372] Avg episode reward: [(0, '7.170'), (1, '7.100')] -[2023-10-09 03:24:24,149][88327] Updated weights for policy 1, policy_version 81510 (0.0010) -[2023-10-09 03:24:24,517][88327] Updated weights for policy 1, policy_version 81520 (0.0009) -[2023-10-09 03:24:24,886][88327] Updated weights for policy 1, policy_version 81530 (0.0008) -[2023-10-09 03:24:26,028][88326] Updated weights for policy 0, policy_version 81442 (0.0009) -[2023-10-09 03:24:26,402][88326] Updated weights for policy 0, policy_version 81452 (0.0007) -[2023-10-09 03:24:26,774][88326] Updated weights for policy 0, policy_version 81462 (0.0010) -[2023-10-09 03:24:27,134][88326] Updated weights for policy 0, policy_version 81472 (0.0009) -[2023-10-09 03:24:28,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 166920192. Throughput: 0: 1658.2, 1: 1705.5. Samples: 41737968. Policy #0 lag: (min: 25.0, avg: 26.8, max: 50.0) -[2023-10-09 03:24:28,974][87372] Avg episode reward: [(0, '7.090'), (1, '7.190')] -[2023-10-09 03:24:29,048][88327] Updated weights for policy 1, policy_version 81540 (0.0007) -[2023-10-09 03:24:29,407][88327] Updated weights for policy 1, policy_version 81550 (0.0007) -[2023-10-09 03:24:29,770][88327] Updated weights for policy 1, policy_version 81560 (0.0008) -[2023-10-09 03:24:31,276][88326] Updated weights for policy 0, policy_version 81482 (0.0009) -[2023-10-09 03:24:31,647][88326] Updated weights for policy 0, policy_version 81492 (0.0007) -[2023-10-09 03:24:32,019][88326] Updated weights for policy 0, policy_version 81502 (0.0007) -[2023-10-09 03:24:33,731][88327] Updated weights for policy 1, policy_version 81570 (0.0010) -[2023-10-09 03:24:33,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 166985728. Throughput: 0: 1681.9, 1: 1706.8. Samples: 41758792. Policy #0 lag: (min: 25.0, avg: 26.8, max: 50.0) -[2023-10-09 03:24:33,975][87372] Avg episode reward: [(0, '6.950'), (1, '6.810')] -[2023-10-09 03:24:33,984][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000081504_83460096.pth... -[2023-10-09 03:24:34,017][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000079936_81854464.pth -[2023-10-09 03:24:34,101][88327] Updated weights for policy 1, policy_version 81580 (0.0008) -[2023-10-09 03:24:34,468][88327] Updated weights for policy 1, policy_version 81590 (0.0010) -[2023-10-09 03:24:34,831][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000081600_83558400.pth... -[2023-10-09 03:24:34,836][88327] Updated weights for policy 1, policy_version 81600 (0.0008) -[2023-10-09 03:24:34,860][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000080000_81920000.pth -[2023-10-09 03:24:35,987][88326] Updated weights for policy 0, policy_version 81512 (0.0007) -[2023-10-09 03:24:36,363][88326] Updated weights for policy 0, policy_version 81522 (0.0009) -[2023-10-09 03:24:36,735][88326] Updated weights for policy 0, policy_version 81532 (0.0009) -[2023-10-09 03:24:38,827][88327] Updated weights for policy 1, policy_version 81610 (0.0009) -[2023-10-09 03:24:38,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 167051264. Throughput: 0: 1668.9, 1: 1697.0. Samples: 41768622. Policy #0 lag: (min: 25.0, avg: 26.8, max: 50.0) -[2023-10-09 03:24:38,975][87372] Avg episode reward: [(0, '7.040'), (1, '6.980')] -[2023-10-09 03:24:39,205][88327] Updated weights for policy 1, policy_version 81620 (0.0009) -[2023-10-09 03:24:39,573][88327] Updated weights for policy 1, policy_version 81630 (0.0008) -[2023-10-09 03:24:40,719][88326] Updated weights for policy 0, policy_version 81542 (0.0008) -[2023-10-09 03:24:41,087][88326] Updated weights for policy 0, policy_version 81552 (0.0009) -[2023-10-09 03:24:41,458][88326] Updated weights for policy 0, policy_version 81562 (0.0007) -[2023-10-09 03:24:43,711][88327] Updated weights for policy 1, policy_version 81640 (0.0008) -[2023-10-09 03:24:43,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 167116800. Throughput: 0: 1663.1, 1: 1711.3. Samples: 41788920. Policy #0 lag: (min: 25.0, avg: 26.8, max: 50.0) -[2023-10-09 03:24:43,975][87372] Avg episode reward: [(0, '6.980'), (1, '7.300')] -[2023-10-09 03:24:44,080][88327] Updated weights for policy 1, policy_version 81650 (0.0007) -[2023-10-09 03:24:44,438][88327] Updated weights for policy 1, policy_version 81660 (0.0009) -[2023-10-09 03:24:45,560][88326] Updated weights for policy 0, policy_version 81572 (0.0008) -[2023-10-09 03:24:45,932][88326] Updated weights for policy 0, policy_version 81582 (0.0008) -[2023-10-09 03:24:46,300][88326] Updated weights for policy 0, policy_version 81592 (0.0007) -[2023-10-09 03:24:48,651][88327] Updated weights for policy 1, policy_version 81670 (0.0007) -[2023-10-09 03:24:48,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 167182336. Throughput: 0: 1685.5, 1: 1706.0. Samples: 41809770. Policy #0 lag: (min: 25.0, avg: 26.8, max: 50.0) -[2023-10-09 03:24:48,975][87372] Avg episode reward: [(0, '6.850'), (1, '7.500')] -[2023-10-09 03:24:49,018][88327] Updated weights for policy 1, policy_version 81680 (0.0008) -[2023-10-09 03:24:49,375][88327] Updated weights for policy 1, policy_version 81690 (0.0009) -[2023-10-09 03:24:50,384][88326] Updated weights for policy 0, policy_version 81602 (0.0009) -[2023-10-09 03:24:50,752][88326] Updated weights for policy 0, policy_version 81612 (0.0010) -[2023-10-09 03:24:51,128][88326] Updated weights for policy 0, policy_version 81622 (0.0009) -[2023-10-09 03:24:51,489][88326] Updated weights for policy 0, policy_version 81632 (0.0007) -[2023-10-09 03:24:53,272][88327] Updated weights for policy 1, policy_version 81700 (0.0008) -[2023-10-09 03:24:53,634][88327] Updated weights for policy 1, policy_version 81710 (0.0007) -[2023-10-09 03:24:53,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 167247872. Throughput: 0: 1664.3, 1: 1707.9. Samples: 41819274. Policy #0 lag: (min: 25.0, avg: 26.8, max: 50.0) -[2023-10-09 03:24:53,975][87372] Avg episode reward: [(0, '6.800'), (1, '7.010')] -[2023-10-09 03:24:53,999][88327] Updated weights for policy 1, policy_version 81720 (0.0010) -[2023-10-09 03:24:55,551][88326] Updated weights for policy 0, policy_version 81642 (0.0012) -[2023-10-09 03:24:55,921][88326] Updated weights for policy 0, policy_version 81652 (0.0009) -[2023-10-09 03:24:56,283][88326] Updated weights for policy 0, policy_version 81662 (0.0007) -[2023-10-09 03:24:58,002][88327] Updated weights for policy 1, policy_version 81730 (0.0007) -[2023-10-09 03:24:58,370][88327] Updated weights for policy 1, policy_version 81740 (0.0007) -[2023-10-09 03:24:58,730][88327] Updated weights for policy 1, policy_version 81750 (0.0008) -[2023-10-09 03:24:58,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 167313408. Throughput: 0: 1681.9, 1: 1707.9. Samples: 41840210. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-09 03:24:58,974][87372] Avg episode reward: [(0, '7.430'), (1, '7.480')] -[2023-10-09 03:24:59,098][88327] Updated weights for policy 1, policy_version 81760 (0.0007) -[2023-10-09 03:25:00,229][88326] Updated weights for policy 0, policy_version 81672 (0.0009) -[2023-10-09 03:25:00,609][88326] Updated weights for policy 0, policy_version 81682 (0.0008) -[2023-10-09 03:25:00,981][88326] Updated weights for policy 0, policy_version 81692 (0.0008) -[2023-10-09 03:25:03,136][88327] Updated weights for policy 1, policy_version 81770 (0.0008) -[2023-10-09 03:25:03,517][88327] Updated weights for policy 1, policy_version 81780 (0.0009) -[2023-10-09 03:25:03,881][88327] Updated weights for policy 1, policy_version 81790 (0.0009) -[2023-10-09 03:25:03,974][87372] Fps is (10 sec: 16383.8, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 167411712. Throughput: 0: 1693.1, 1: 1696.1. Samples: 41860524. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-09 03:25:03,975][87372] Avg episode reward: [(0, '7.550'), (1, '6.910')] -[2023-10-09 03:25:05,025][88326] Updated weights for policy 0, policy_version 81702 (0.0010) -[2023-10-09 03:25:05,393][88326] Updated weights for policy 0, policy_version 81712 (0.0007) -[2023-10-09 03:25:05,754][88326] Updated weights for policy 0, policy_version 81722 (0.0009) -[2023-10-09 03:25:07,993][88327] Updated weights for policy 1, policy_version 81800 (0.0009) -[2023-10-09 03:25:08,351][88327] Updated weights for policy 1, policy_version 81810 (0.0009) -[2023-10-09 03:25:08,724][88327] Updated weights for policy 1, policy_version 81820 (0.0008) -[2023-10-09 03:25:08,974][87372] Fps is (10 sec: 16383.8, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 167477248. Throughput: 0: 1667.8, 1: 1706.1. Samples: 41870006. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-09 03:25:08,975][87372] Avg episode reward: [(0, '8.230'), (1, '7.600')] -[2023-10-09 03:25:09,847][88326] Updated weights for policy 0, policy_version 81732 (0.0007) -[2023-10-09 03:25:10,205][88326] Updated weights for policy 0, policy_version 81742 (0.0009) -[2023-10-09 03:25:10,576][88326] Updated weights for policy 0, policy_version 81752 (0.0007) -[2023-10-09 03:25:12,670][88327] Updated weights for policy 1, policy_version 81830 (0.0007) -[2023-10-09 03:25:13,034][88327] Updated weights for policy 1, policy_version 81840 (0.0009) -[2023-10-09 03:25:13,394][88327] Updated weights for policy 1, policy_version 81850 (0.0008) -[2023-10-09 03:25:13,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 167542784. Throughput: 0: 1694.0, 1: 1705.4. Samples: 41890940. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-09 03:25:13,975][87372] Avg episode reward: [(0, '7.990'), (1, '7.160')] -[2023-10-09 03:25:14,708][88326] Updated weights for policy 0, policy_version 81762 (0.0007) -[2023-10-09 03:25:15,072][88326] Updated weights for policy 0, policy_version 81772 (0.0008) -[2023-10-09 03:25:15,455][88326] Updated weights for policy 0, policy_version 81782 (0.0009) -[2023-10-09 03:25:15,821][88326] Updated weights for policy 0, policy_version 81792 (0.0007) -[2023-10-09 03:25:17,403][88327] Updated weights for policy 1, policy_version 81860 (0.0008) -[2023-10-09 03:25:17,769][88327] Updated weights for policy 1, policy_version 81870 (0.0008) -[2023-10-09 03:25:18,122][88327] Updated weights for policy 1, policy_version 81880 (0.0010) -[2023-10-09 03:25:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 167608320. Throughput: 0: 1702.9, 1: 1686.4. Samples: 41911310. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-09 03:25:18,975][87372] Avg episode reward: [(0, '8.000'), (1, '7.080')] -[2023-10-09 03:25:19,740][88326] Updated weights for policy 0, policy_version 81802 (0.0008) -[2023-10-09 03:25:20,111][88326] Updated weights for policy 0, policy_version 81812 (0.0009) -[2023-10-09 03:25:20,479][88326] Updated weights for policy 0, policy_version 81822 (0.0008) -[2023-10-09 03:25:22,151][88327] Updated weights for policy 1, policy_version 81890 (0.0010) -[2023-10-09 03:25:22,509][88327] Updated weights for policy 1, policy_version 81900 (0.0008) -[2023-10-09 03:25:22,882][88327] Updated weights for policy 1, policy_version 81910 (0.0010) -[2023-10-09 03:25:23,242][88327] Updated weights for policy 1, policy_version 81920 (0.0007) -[2023-10-09 03:25:23,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 167673856. Throughput: 0: 1686.4, 1: 1710.0. Samples: 41921456. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-09 03:25:23,975][87372] Avg episode reward: [(0, '8.290'), (1, '7.340')] -[2023-10-09 03:25:23,976][88088] Saving new best policy, reward=8.290! -[2023-10-09 03:25:24,439][88326] Updated weights for policy 0, policy_version 81832 (0.0008) -[2023-10-09 03:25:24,814][88326] Updated weights for policy 0, policy_version 81842 (0.0008) -[2023-10-09 03:25:25,185][88326] Updated weights for policy 0, policy_version 81852 (0.0010) -[2023-10-09 03:25:27,197][88327] Updated weights for policy 1, policy_version 81930 (0.0008) -[2023-10-09 03:25:27,565][88327] Updated weights for policy 1, policy_version 81940 (0.0009) -[2023-10-09 03:25:27,926][88327] Updated weights for policy 1, policy_version 81950 (0.0008) -[2023-10-09 03:25:28,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 167739392. Throughput: 0: 1706.7, 1: 1699.8. Samples: 41942214. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-09 03:25:28,975][87372] Avg episode reward: [(0, '7.520'), (1, '7.300')] -[2023-10-09 03:25:29,131][88326] Updated weights for policy 0, policy_version 81862 (0.0009) -[2023-10-09 03:25:29,503][88326] Updated weights for policy 0, policy_version 81872 (0.0007) -[2023-10-09 03:25:29,891][88326] Updated weights for policy 0, policy_version 81882 (0.0009) -[2023-10-09 03:25:31,883][88327] Updated weights for policy 1, policy_version 81960 (0.0009) -[2023-10-09 03:25:32,260][88327] Updated weights for policy 1, policy_version 81970 (0.0009) -[2023-10-09 03:25:32,632][88327] Updated weights for policy 1, policy_version 81980 (0.0009) -[2023-10-09 03:25:33,939][88326] Updated weights for policy 0, policy_version 81892 (0.0009) -[2023-10-09 03:25:33,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 167804928. Throughput: 0: 1706.2, 1: 1678.3. Samples: 41962072. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-09 03:25:33,975][87372] Avg episode reward: [(0, '6.830'), (1, '7.660')] -[2023-10-09 03:25:34,319][88326] Updated weights for policy 0, policy_version 81902 (0.0009) -[2023-10-09 03:25:34,678][88326] Updated weights for policy 0, policy_version 81912 (0.0007) -[2023-10-09 03:25:36,709][88327] Updated weights for policy 1, policy_version 81990 (0.0009) -[2023-10-09 03:25:37,076][88327] Updated weights for policy 1, policy_version 82000 (0.0011) -[2023-10-09 03:25:37,448][88327] Updated weights for policy 1, policy_version 82010 (0.0010) -[2023-10-09 03:25:38,597][88326] Updated weights for policy 0, policy_version 81922 (0.0008) -[2023-10-09 03:25:38,970][88326] Updated weights for policy 0, policy_version 81932 (0.0010) -[2023-10-09 03:25:38,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 167870464. Throughput: 0: 1700.6, 1: 1705.9. Samples: 41972568. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-09 03:25:38,974][87372] Avg episode reward: [(0, '6.750'), (1, '8.050')] -[2023-10-09 03:25:39,336][88326] Updated weights for policy 0, policy_version 81942 (0.0010) -[2023-10-09 03:25:39,702][88326] Updated weights for policy 0, policy_version 81952 (0.0007) -[2023-10-09 03:25:41,642][88327] Updated weights for policy 1, policy_version 82020 (0.0009) -[2023-10-09 03:25:42,008][88327] Updated weights for policy 1, policy_version 82030 (0.0010) -[2023-10-09 03:25:42,375][88327] Updated weights for policy 1, policy_version 82040 (0.0010) -[2023-10-09 03:25:43,811][88326] Updated weights for policy 0, policy_version 81962 (0.0010) -[2023-10-09 03:25:43,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 167936000. Throughput: 0: 1706.4, 1: 1683.9. Samples: 41992772. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-09 03:25:43,975][87372] Avg episode reward: [(0, '7.050'), (1, '7.910')] -[2023-10-09 03:25:44,182][88326] Updated weights for policy 0, policy_version 81972 (0.0009) -[2023-10-09 03:25:44,557][88326] Updated weights for policy 0, policy_version 81982 (0.0008) -[2023-10-09 03:25:46,523][88327] Updated weights for policy 1, policy_version 82050 (0.0010) -[2023-10-09 03:25:46,885][88327] Updated weights for policy 1, policy_version 82060 (0.0009) -[2023-10-09 03:25:47,254][88327] Updated weights for policy 1, policy_version 82070 (0.0008) -[2023-10-09 03:25:47,621][88327] Updated weights for policy 1, policy_version 82080 (0.0007) -[2023-10-09 03:25:48,687][88326] Updated weights for policy 0, policy_version 81992 (0.0008) -[2023-10-09 03:25:48,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 168001536. Throughput: 0: 1704.6, 1: 1677.6. Samples: 42012724. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-09 03:25:48,975][87372] Avg episode reward: [(0, '6.740'), (1, '7.380')] -[2023-10-09 03:25:49,057][88326] Updated weights for policy 0, policy_version 82002 (0.0009) -[2023-10-09 03:25:49,423][88326] Updated weights for policy 0, policy_version 82012 (0.0008) -[2023-10-09 03:25:51,635][88327] Updated weights for policy 1, policy_version 82090 (0.0009) -[2023-10-09 03:25:52,010][88327] Updated weights for policy 1, policy_version 82100 (0.0009) -[2023-10-09 03:25:52,370][88327] Updated weights for policy 1, policy_version 82110 (0.0007) -[2023-10-09 03:25:53,470][88326] Updated weights for policy 0, policy_version 82022 (0.0010) -[2023-10-09 03:25:53,836][88326] Updated weights for policy 0, policy_version 82032 (0.0009) -[2023-10-09 03:25:53,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 168067072. Throughput: 0: 1701.5, 1: 1699.8. Samples: 42023064. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:25:53,975][87372] Avg episode reward: [(0, '6.900'), (1, '7.250')] -[2023-10-09 03:25:54,211][88326] Updated weights for policy 0, policy_version 82042 (0.0009) -[2023-10-09 03:25:56,274][88327] Updated weights for policy 1, policy_version 82120 (0.0008) -[2023-10-09 03:25:56,635][88327] Updated weights for policy 1, policy_version 82130 (0.0007) -[2023-10-09 03:25:57,000][88327] Updated weights for policy 1, policy_version 82140 (0.0008) -[2023-10-09 03:25:58,177][88326] Updated weights for policy 0, policy_version 82052 (0.0010) -[2023-10-09 03:25:58,553][88326] Updated weights for policy 0, policy_version 82062 (0.0007) -[2023-10-09 03:25:58,918][88326] Updated weights for policy 0, policy_version 82072 (0.0009) -[2023-10-09 03:25:58,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 168132608. Throughput: 0: 1703.8, 1: 1673.4. Samples: 42042914. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:25:58,974][87372] Avg episode reward: [(0, '7.600'), (1, '6.920')] -[2023-10-09 03:26:00,841][88327] Updated weights for policy 1, policy_version 82150 (0.0008) -[2023-10-09 03:26:01,210][88327] Updated weights for policy 1, policy_version 82160 (0.0008) -[2023-10-09 03:26:01,580][88327] Updated weights for policy 1, policy_version 82170 (0.0008) -[2023-10-09 03:26:02,981][88326] Updated weights for policy 0, policy_version 82082 (0.0009) -[2023-10-09 03:26:03,362][88326] Updated weights for policy 0, policy_version 82092 (0.0008) -[2023-10-09 03:26:03,729][88326] Updated weights for policy 0, policy_version 82102 (0.0008) -[2023-10-09 03:26:03,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 168198144. Throughput: 0: 1687.8, 1: 1693.5. Samples: 42063470. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:26:03,974][87372] Avg episode reward: [(0, '7.220'), (1, '7.200')] -[2023-10-09 03:26:04,096][88326] Updated weights for policy 0, policy_version 82112 (0.0011) -[2023-10-09 03:26:05,709][88327] Updated weights for policy 1, policy_version 82180 (0.0008) -[2023-10-09 03:26:06,073][88327] Updated weights for policy 1, policy_version 82190 (0.0009) -[2023-10-09 03:26:06,441][88327] Updated weights for policy 1, policy_version 82200 (0.0010) -[2023-10-09 03:26:08,125][88326] Updated weights for policy 0, policy_version 82122 (0.0008) -[2023-10-09 03:26:08,495][88326] Updated weights for policy 0, policy_version 82132 (0.0009) -[2023-10-09 03:26:08,860][88326] Updated weights for policy 0, policy_version 82142 (0.0007) -[2023-10-09 03:26:08,974][87372] Fps is (10 sec: 16384.0, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 168296448. Throughput: 0: 1694.8, 1: 1685.2. Samples: 42073556. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:26:08,974][87372] Avg episode reward: [(0, '7.180'), (1, '7.440')] -[2023-10-09 03:26:10,599][88327] Updated weights for policy 1, policy_version 82210 (0.0008) -[2023-10-09 03:26:10,965][88327] Updated weights for policy 1, policy_version 82220 (0.0008) -[2023-10-09 03:26:11,336][88327] Updated weights for policy 1, policy_version 82230 (0.0007) -[2023-10-09 03:26:11,707][88327] Updated weights for policy 1, policy_version 82240 (0.0009) -[2023-10-09 03:26:12,709][88326] Updated weights for policy 0, policy_version 82152 (0.0009) -[2023-10-09 03:26:13,077][88326] Updated weights for policy 0, policy_version 82162 (0.0009) -[2023-10-09 03:26:13,446][88326] Updated weights for policy 0, policy_version 82172 (0.0008) -[2023-10-09 03:26:13,974][87372] Fps is (10 sec: 16383.6, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 168361984. Throughput: 0: 1696.7, 1: 1669.2. Samples: 42093682. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:26:13,975][87372] Avg episode reward: [(0, '7.620'), (1, '8.060')] -[2023-10-09 03:26:15,730][88327] Updated weights for policy 1, policy_version 82250 (0.0008) -[2023-10-09 03:26:16,094][88327] Updated weights for policy 1, policy_version 82260 (0.0008) -[2023-10-09 03:26:16,456][88327] Updated weights for policy 1, policy_version 82270 (0.0007) -[2023-10-09 03:26:17,529][88326] Updated weights for policy 0, policy_version 82182 (0.0007) -[2023-10-09 03:26:17,894][88326] Updated weights for policy 0, policy_version 82192 (0.0007) -[2023-10-09 03:26:18,267][88326] Updated weights for policy 0, policy_version 82202 (0.0007) -[2023-10-09 03:26:18,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 168427520. Throughput: 0: 1675.0, 1: 1701.9. Samples: 42114030. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:26:18,975][87372] Avg episode reward: [(0, '7.650'), (1, '7.850')] -[2023-10-09 03:26:20,473][88327] Updated weights for policy 1, policy_version 82280 (0.0010) -[2023-10-09 03:26:20,831][88327] Updated weights for policy 1, policy_version 82290 (0.0008) -[2023-10-09 03:26:21,198][88327] Updated weights for policy 1, policy_version 82300 (0.0007) -[2023-10-09 03:26:22,293][88326] Updated weights for policy 0, policy_version 82212 (0.0008) -[2023-10-09 03:26:22,662][88326] Updated weights for policy 0, policy_version 82222 (0.0008) -[2023-10-09 03:26:23,035][88326] Updated weights for policy 0, policy_version 82232 (0.0009) -[2023-10-09 03:26:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 168493056. Throughput: 0: 1696.1, 1: 1677.1. Samples: 42124366. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:26:23,975][87372] Avg episode reward: [(0, '7.410'), (1, '8.290')] -[2023-10-09 03:26:25,215][88327] Updated weights for policy 1, policy_version 82310 (0.0008) -[2023-10-09 03:26:25,577][88327] Updated weights for policy 1, policy_version 82320 (0.0009) -[2023-10-09 03:26:25,951][88327] Updated weights for policy 1, policy_version 82330 (0.0008) -[2023-10-09 03:26:26,968][88326] Updated weights for policy 0, policy_version 82242 (0.0009) -[2023-10-09 03:26:27,331][88326] Updated weights for policy 0, policy_version 82252 (0.0007) -[2023-10-09 03:26:27,703][88326] Updated weights for policy 0, policy_version 82262 (0.0007) -[2023-10-09 03:26:28,068][88326] Updated weights for policy 0, policy_version 82272 (0.0008) -[2023-10-09 03:26:28,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 168558592. Throughput: 0: 1689.1, 1: 1689.4. Samples: 42144804. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:26:28,975][87372] Avg episode reward: [(0, '7.160'), (1, '8.350')] -[2023-10-09 03:26:29,984][88327] Updated weights for policy 1, policy_version 82340 (0.0008) -[2023-10-09 03:26:30,357][88327] Updated weights for policy 1, policy_version 82350 (0.0010) -[2023-10-09 03:26:30,725][88327] Updated weights for policy 1, policy_version 82360 (0.0009) -[2023-10-09 03:26:31,953][88326] Updated weights for policy 0, policy_version 82282 (0.0010) -[2023-10-09 03:26:32,319][88326] Updated weights for policy 0, policy_version 82292 (0.0010) -[2023-10-09 03:26:32,697][88326] Updated weights for policy 0, policy_version 82302 (0.0007) -[2023-10-09 03:26:33,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 168624128. Throughput: 0: 1673.7, 1: 1710.1. Samples: 42164994. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:26:33,975][87372] Avg episode reward: [(0, '7.660'), (1, '8.210')] -[2023-10-09 03:26:33,986][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000082304_84279296.pth... -[2023-10-09 03:26:33,987][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000082368_84344832.pth... -[2023-10-09 03:26:34,022][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000080800_82739200.pth -[2023-10-09 03:26:34,030][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000080704_82640896.pth -[2023-10-09 03:26:34,642][88327] Updated weights for policy 1, policy_version 82370 (0.0011) -[2023-10-09 03:26:35,014][88327] Updated weights for policy 1, policy_version 82380 (0.0008) -[2023-10-09 03:26:35,376][88327] Updated weights for policy 1, policy_version 82390 (0.0009) -[2023-10-09 03:26:35,748][88327] Updated weights for policy 1, policy_version 82400 (0.0009) -[2023-10-09 03:26:36,907][88326] Updated weights for policy 0, policy_version 82312 (0.0008) -[2023-10-09 03:26:37,285][88326] Updated weights for policy 0, policy_version 82322 (0.0009) -[2023-10-09 03:26:37,652][88326] Updated weights for policy 0, policy_version 82332 (0.0009) -[2023-10-09 03:26:38,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 168689664. Throughput: 0: 1702.8, 1: 1678.7. Samples: 42175228. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:26:38,974][87372] Avg episode reward: [(0, '7.500'), (1, '7.330')] -[2023-10-09 03:26:39,927][88327] Updated weights for policy 1, policy_version 82410 (0.0009) -[2023-10-09 03:26:40,283][88327] Updated weights for policy 1, policy_version 82420 (0.0007) -[2023-10-09 03:26:40,653][88327] Updated weights for policy 1, policy_version 82430 (0.0008) -[2023-10-09 03:26:41,800][88326] Updated weights for policy 0, policy_version 82342 (0.0010) -[2023-10-09 03:26:42,169][88326] Updated weights for policy 0, policy_version 82352 (0.0009) -[2023-10-09 03:26:42,533][88326] Updated weights for policy 0, policy_version 82362 (0.0008) -[2023-10-09 03:26:43,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 168755200. Throughput: 0: 1685.5, 1: 1702.4. Samples: 42195372. Policy #0 lag: (min: 26.0, avg: 37.9, max: 58.0) -[2023-10-09 03:26:43,975][87372] Avg episode reward: [(0, '7.520'), (1, '7.110')] -[2023-10-09 03:26:44,728][88327] Updated weights for policy 1, policy_version 82440 (0.0009) -[2023-10-09 03:26:45,095][88327] Updated weights for policy 1, policy_version 82450 (0.0008) -[2023-10-09 03:26:45,450][88327] Updated weights for policy 1, policy_version 82460 (0.0009) -[2023-10-09 03:26:46,720][88326] Updated weights for policy 0, policy_version 82372 (0.0008) -[2023-10-09 03:26:47,086][88326] Updated weights for policy 0, policy_version 82382 (0.0008) -[2023-10-09 03:26:47,455][88326] Updated weights for policy 0, policy_version 82392 (0.0010) -[2023-10-09 03:26:48,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 168820736. Throughput: 0: 1677.2, 1: 1702.0. Samples: 42215536. Policy #0 lag: (min: 26.0, avg: 37.9, max: 58.0) -[2023-10-09 03:26:48,975][87372] Avg episode reward: [(0, '7.460'), (1, '7.520')] -[2023-10-09 03:26:49,419][88327] Updated weights for policy 1, policy_version 82470 (0.0009) -[2023-10-09 03:26:49,783][88327] Updated weights for policy 1, policy_version 82480 (0.0009) -[2023-10-09 03:26:50,157][88327] Updated weights for policy 1, policy_version 82490 (0.0009) -[2023-10-09 03:26:51,652][88326] Updated weights for policy 0, policy_version 82402 (0.0010) -[2023-10-09 03:26:52,015][88326] Updated weights for policy 0, policy_version 82412 (0.0011) -[2023-10-09 03:26:52,377][88326] Updated weights for policy 0, policy_version 82422 (0.0008) -[2023-10-09 03:26:52,744][88326] Updated weights for policy 0, policy_version 82432 (0.0008) -[2023-10-09 03:26:53,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 168886272. Throughput: 0: 1700.6, 1: 1684.1. Samples: 42225868. Policy #0 lag: (min: 26.0, avg: 37.9, max: 58.0) -[2023-10-09 03:26:53,975][87372] Avg episode reward: [(0, '6.790'), (1, '7.170')] -[2023-10-09 03:26:54,173][88327] Updated weights for policy 1, policy_version 82500 (0.0007) -[2023-10-09 03:26:54,536][88327] Updated weights for policy 1, policy_version 82510 (0.0009) -[2023-10-09 03:26:54,908][88327] Updated weights for policy 1, policy_version 82520 (0.0008) -[2023-10-09 03:26:56,610][88326] Updated weights for policy 0, policy_version 82442 (0.0007) -[2023-10-09 03:26:56,979][88326] Updated weights for policy 0, policy_version 82452 (0.0008) -[2023-10-09 03:26:57,345][88326] Updated weights for policy 0, policy_version 82462 (0.0009) -[2023-10-09 03:26:58,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 168951808. Throughput: 0: 1674.0, 1: 1706.8. Samples: 42245820. Policy #0 lag: (min: 26.0, avg: 37.9, max: 58.0) -[2023-10-09 03:26:58,975][87372] Avg episode reward: [(0, '6.770'), (1, '7.420')] -[2023-10-09 03:26:59,042][88327] Updated weights for policy 1, policy_version 82530 (0.0009) -[2023-10-09 03:26:59,411][88327] Updated weights for policy 1, policy_version 82540 (0.0008) -[2023-10-09 03:26:59,774][88327] Updated weights for policy 1, policy_version 82550 (0.0007) -[2023-10-09 03:27:00,140][88327] Updated weights for policy 1, policy_version 82560 (0.0008) -[2023-10-09 03:27:01,474][88326] Updated weights for policy 0, policy_version 82472 (0.0009) -[2023-10-09 03:27:01,848][88326] Updated weights for policy 0, policy_version 82482 (0.0008) -[2023-10-09 03:27:02,221][88326] Updated weights for policy 0, policy_version 82492 (0.0009) -[2023-10-09 03:27:03,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 169017344. Throughput: 0: 1688.9, 1: 1695.2. Samples: 42266312. Policy #0 lag: (min: 26.0, avg: 37.9, max: 58.0) -[2023-10-09 03:27:03,974][87372] Avg episode reward: [(0, '6.970'), (1, '7.940')] -[2023-10-09 03:27:04,187][88327] Updated weights for policy 1, policy_version 82570 (0.0010) -[2023-10-09 03:27:04,566][88327] Updated weights for policy 1, policy_version 82580 (0.0011) -[2023-10-09 03:27:04,932][88327] Updated weights for policy 1, policy_version 82590 (0.0008) -[2023-10-09 03:27:06,114][88326] Updated weights for policy 0, policy_version 82502 (0.0007) -[2023-10-09 03:27:06,474][88326] Updated weights for policy 0, policy_version 82512 (0.0008) -[2023-10-09 03:27:06,843][88326] Updated weights for policy 0, policy_version 82522 (0.0007) -[2023-10-09 03:27:08,957][88327] Updated weights for policy 1, policy_version 82600 (0.0008) -[2023-10-09 03:27:08,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 169082880. Throughput: 0: 1689.4, 1: 1689.5. Samples: 42276414. Policy #0 lag: (min: 26.0, avg: 37.9, max: 58.0) -[2023-10-09 03:27:08,974][87372] Avg episode reward: [(0, '6.520'), (1, '7.340')] -[2023-10-09 03:27:09,330][88327] Updated weights for policy 1, policy_version 82610 (0.0010) -[2023-10-09 03:27:09,698][88327] Updated weights for policy 1, policy_version 82620 (0.0008) -[2023-10-09 03:27:10,853][88326] Updated weights for policy 0, policy_version 82532 (0.0008) -[2023-10-09 03:27:11,210][88326] Updated weights for policy 0, policy_version 82542 (0.0009) -[2023-10-09 03:27:11,584][88326] Updated weights for policy 0, policy_version 82552 (0.0009) -[2023-10-09 03:27:13,585][88327] Updated weights for policy 1, policy_version 82630 (0.0010) -[2023-10-09 03:27:13,948][88327] Updated weights for policy 1, policy_version 82640 (0.0009) -[2023-10-09 03:27:13,974][87372] Fps is (10 sec: 13106.8, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 169148416. Throughput: 0: 1672.7, 1: 1694.8. Samples: 42296344. Policy #0 lag: (min: 26.0, avg: 37.9, max: 58.0) -[2023-10-09 03:27:13,975][87372] Avg episode reward: [(0, '6.340'), (1, '7.420')] -[2023-10-09 03:27:14,309][88327] Updated weights for policy 1, policy_version 82650 (0.0008) -[2023-10-09 03:27:15,655][88326] Updated weights for policy 0, policy_version 82562 (0.0008) -[2023-10-09 03:27:16,025][88326] Updated weights for policy 0, policy_version 82572 (0.0007) -[2023-10-09 03:27:16,385][88326] Updated weights for policy 0, policy_version 82582 (0.0009) -[2023-10-09 03:27:16,753][88326] Updated weights for policy 0, policy_version 82592 (0.0008) -[2023-10-09 03:27:18,475][88327] Updated weights for policy 1, policy_version 82660 (0.0009) -[2023-10-09 03:27:18,841][88327] Updated weights for policy 1, policy_version 82670 (0.0008) -[2023-10-09 03:27:18,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 169213952. Throughput: 0: 1691.1, 1: 1693.9. Samples: 42317318. Policy #0 lag: (min: 26.0, avg: 37.9, max: 58.0) -[2023-10-09 03:27:18,975][87372] Avg episode reward: [(0, '6.010'), (1, '8.160')] -[2023-10-09 03:27:19,204][88327] Updated weights for policy 1, policy_version 82680 (0.0008) -[2023-10-09 03:27:20,869][88326] Updated weights for policy 0, policy_version 82602 (0.0009) -[2023-10-09 03:27:21,231][88326] Updated weights for policy 0, policy_version 82612 (0.0007) -[2023-10-09 03:27:21,600][88326] Updated weights for policy 0, policy_version 82622 (0.0008) -[2023-10-09 03:27:23,165][88327] Updated weights for policy 1, policy_version 82690 (0.0007) -[2023-10-09 03:27:23,520][88327] Updated weights for policy 1, policy_version 82700 (0.0007) -[2023-10-09 03:27:23,880][88327] Updated weights for policy 1, policy_version 82710 (0.0008) -[2023-10-09 03:27:23,974][87372] Fps is (10 sec: 13107.6, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 169279488. Throughput: 0: 1676.5, 1: 1695.5. Samples: 42326968. Policy #0 lag: (min: 26.0, avg: 37.9, max: 58.0) -[2023-10-09 03:27:23,974][87372] Avg episode reward: [(0, '6.060'), (1, '7.900')] -[2023-10-09 03:27:24,242][88327] Updated weights for policy 1, policy_version 82720 (0.0007) -[2023-10-09 03:27:25,728][88326] Updated weights for policy 0, policy_version 82632 (0.0009) -[2023-10-09 03:27:26,099][88326] Updated weights for policy 0, policy_version 82642 (0.0008) -[2023-10-09 03:27:26,475][88326] Updated weights for policy 0, policy_version 82652 (0.0009) -[2023-10-09 03:27:28,402][88327] Updated weights for policy 1, policy_version 82730 (0.0010) -[2023-10-09 03:27:28,768][88327] Updated weights for policy 1, policy_version 82740 (0.0010) -[2023-10-09 03:27:28,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 169345024. Throughput: 0: 1679.8, 1: 1698.0. Samples: 42347370. Policy #0 lag: (min: 26.0, avg: 37.9, max: 58.0) -[2023-10-09 03:27:28,974][87372] Avg episode reward: [(0, '6.740'), (1, '7.200')] -[2023-10-09 03:27:29,125][88327] Updated weights for policy 1, policy_version 82750 (0.0009) -[2023-10-09 03:27:30,511][88326] Updated weights for policy 0, policy_version 82662 (0.0008) -[2023-10-09 03:27:30,881][88326] Updated weights for policy 0, policy_version 82672 (0.0009) -[2023-10-09 03:27:31,244][88326] Updated weights for policy 0, policy_version 82682 (0.0010) -[2023-10-09 03:27:33,083][88327] Updated weights for policy 1, policy_version 82760 (0.0008) -[2023-10-09 03:27:33,461][88327] Updated weights for policy 1, policy_version 82770 (0.0007) -[2023-10-09 03:27:33,826][88327] Updated weights for policy 1, policy_version 82780 (0.0010) -[2023-10-09 03:27:33,974][87372] Fps is (10 sec: 16383.8, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 169443328. Throughput: 0: 1697.6, 1: 1686.7. Samples: 42367832. Policy #0 lag: (min: 26.0, avg: 37.9, max: 58.0) -[2023-10-09 03:27:33,975][87372] Avg episode reward: [(0, '7.040'), (1, '7.630')] -[2023-10-09 03:27:35,168][88326] Updated weights for policy 0, policy_version 82692 (0.0010) -[2023-10-09 03:27:35,531][88326] Updated weights for policy 0, policy_version 82702 (0.0009) -[2023-10-09 03:27:35,904][88326] Updated weights for policy 0, policy_version 82712 (0.0008) -[2023-10-09 03:27:37,908][88327] Updated weights for policy 1, policy_version 82790 (0.0008) -[2023-10-09 03:27:38,272][88327] Updated weights for policy 1, policy_version 82800 (0.0008) -[2023-10-09 03:27:38,638][88327] Updated weights for policy 1, policy_version 82810 (0.0007) -[2023-10-09 03:27:38,974][87372] Fps is (10 sec: 16383.7, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 169508864. Throughput: 0: 1673.1, 1: 1698.1. Samples: 42377570. Policy #0 lag: (min: 0.0, avg: 23.1, max: 32.0) -[2023-10-09 03:27:38,975][87372] Avg episode reward: [(0, '7.330'), (1, '7.530')] -[2023-10-09 03:27:39,872][88326] Updated weights for policy 0, policy_version 82722 (0.0008) -[2023-10-09 03:27:40,249][88326] Updated weights for policy 0, policy_version 82732 (0.0010) -[2023-10-09 03:27:40,614][88326] Updated weights for policy 0, policy_version 82742 (0.0008) -[2023-10-09 03:27:40,982][88326] Updated weights for policy 0, policy_version 82752 (0.0008) -[2023-10-09 03:27:42,509][88327] Updated weights for policy 1, policy_version 82820 (0.0007) -[2023-10-09 03:27:42,867][88327] Updated weights for policy 1, policy_version 82830 (0.0009) -[2023-10-09 03:27:43,229][88327] Updated weights for policy 1, policy_version 82840 (0.0009) -[2023-10-09 03:27:43,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 169574400. Throughput: 0: 1696.8, 1: 1697.3. Samples: 42398552. Policy #0 lag: (min: 0.0, avg: 23.1, max: 32.0) -[2023-10-09 03:27:43,975][87372] Avg episode reward: [(0, '7.130'), (1, '6.930')] -[2023-10-09 03:27:44,837][88326] Updated weights for policy 0, policy_version 82762 (0.0009) -[2023-10-09 03:27:45,206][88326] Updated weights for policy 0, policy_version 82772 (0.0009) -[2023-10-09 03:27:45,570][88326] Updated weights for policy 0, policy_version 82782 (0.0007) -[2023-10-09 03:27:47,385][88327] Updated weights for policy 1, policy_version 82850 (0.0008) -[2023-10-09 03:27:47,748][88327] Updated weights for policy 1, policy_version 82860 (0.0011) -[2023-10-09 03:27:48,113][88327] Updated weights for policy 1, policy_version 82870 (0.0009) -[2023-10-09 03:27:48,479][88327] Updated weights for policy 1, policy_version 82880 (0.0010) -[2023-10-09 03:27:48,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 169639936. Throughput: 0: 1709.3, 1: 1677.0. Samples: 42418696. Policy #0 lag: (min: 0.0, avg: 23.1, max: 32.0) -[2023-10-09 03:27:48,975][87372] Avg episode reward: [(0, '6.770'), (1, '6.400')] -[2023-10-09 03:27:49,493][88326] Updated weights for policy 0, policy_version 82792 (0.0007) -[2023-10-09 03:27:49,862][88326] Updated weights for policy 0, policy_version 82802 (0.0007) -[2023-10-09 03:27:50,225][88326] Updated weights for policy 0, policy_version 82812 (0.0007) -[2023-10-09 03:27:52,674][88327] Updated weights for policy 1, policy_version 82890 (0.0008) -[2023-10-09 03:27:53,034][88327] Updated weights for policy 1, policy_version 82900 (0.0009) -[2023-10-09 03:27:53,402][88327] Updated weights for policy 1, policy_version 82910 (0.0008) -[2023-10-09 03:27:53,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 169705472. Throughput: 0: 1688.2, 1: 1694.5. Samples: 42428638. Policy #0 lag: (min: 0.0, avg: 23.1, max: 32.0) -[2023-10-09 03:27:53,975][87372] Avg episode reward: [(0, '7.360'), (1, '7.660')] -[2023-10-09 03:27:54,072][88326] Updated weights for policy 0, policy_version 82822 (0.0007) -[2023-10-09 03:27:54,440][88326] Updated weights for policy 0, policy_version 82832 (0.0008) -[2023-10-09 03:27:54,815][88326] Updated weights for policy 0, policy_version 82842 (0.0009) -[2023-10-09 03:27:57,460][88327] Updated weights for policy 1, policy_version 82920 (0.0010) -[2023-10-09 03:27:57,832][88327] Updated weights for policy 1, policy_version 82930 (0.0009) -[2023-10-09 03:27:58,202][88327] Updated weights for policy 1, policy_version 82940 (0.0007) -[2023-10-09 03:27:58,812][88326] Updated weights for policy 0, policy_version 82852 (0.0009) -[2023-10-09 03:27:58,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 169771008. Throughput: 0: 1712.0, 1: 1693.2. Samples: 42449576. Policy #0 lag: (min: 0.0, avg: 23.1, max: 32.0) -[2023-10-09 03:27:58,974][87372] Avg episode reward: [(0, '7.780'), (1, '7.310')] -[2023-10-09 03:27:59,170][88326] Updated weights for policy 0, policy_version 82862 (0.0011) -[2023-10-09 03:27:59,541][88326] Updated weights for policy 0, policy_version 82872 (0.0010) -[2023-10-09 03:28:02,326][88327] Updated weights for policy 1, policy_version 82950 (0.0008) -[2023-10-09 03:28:02,696][88327] Updated weights for policy 1, policy_version 82960 (0.0009) -[2023-10-09 03:28:03,057][88327] Updated weights for policy 1, policy_version 82970 (0.0009) -[2023-10-09 03:28:03,805][88326] Updated weights for policy 0, policy_version 82882 (0.0009) -[2023-10-09 03:28:03,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 169836544. Throughput: 0: 1709.5, 1: 1668.0. Samples: 42469302. Policy #0 lag: (min: 0.0, avg: 23.1, max: 32.0) -[2023-10-09 03:28:03,975][87372] Avg episode reward: [(0, '7.400'), (1, '7.310')] -[2023-10-09 03:28:04,168][88326] Updated weights for policy 0, policy_version 82892 (0.0008) -[2023-10-09 03:28:04,544][88326] Updated weights for policy 0, policy_version 82902 (0.0007) -[2023-10-09 03:28:04,918][88326] Updated weights for policy 0, policy_version 82912 (0.0008) -[2023-10-09 03:28:07,027][88327] Updated weights for policy 1, policy_version 82980 (0.0009) -[2023-10-09 03:28:07,393][88327] Updated weights for policy 1, policy_version 82990 (0.0008) -[2023-10-09 03:28:07,767][88327] Updated weights for policy 1, policy_version 83000 (0.0007) -[2023-10-09 03:28:08,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 169902080. Throughput: 0: 1698.7, 1: 1692.4. Samples: 42479570. Policy #0 lag: (min: 0.0, avg: 23.1, max: 32.0) -[2023-10-09 03:28:08,975][87372] Avg episode reward: [(0, '7.140'), (1, '7.340')] -[2023-10-09 03:28:09,036][88326] Updated weights for policy 0, policy_version 82922 (0.0010) -[2023-10-09 03:28:09,392][88326] Updated weights for policy 0, policy_version 82932 (0.0009) -[2023-10-09 03:28:09,773][88326] Updated weights for policy 0, policy_version 82942 (0.0011) -[2023-10-09 03:28:11,699][88327] Updated weights for policy 1, policy_version 83010 (0.0009) -[2023-10-09 03:28:12,057][88327] Updated weights for policy 1, policy_version 83020 (0.0010) -[2023-10-09 03:28:12,419][88327] Updated weights for policy 1, policy_version 83030 (0.0009) -[2023-10-09 03:28:12,786][88327] Updated weights for policy 1, policy_version 83040 (0.0008) -[2023-10-09 03:28:13,807][88326] Updated weights for policy 0, policy_version 82952 (0.0008) -[2023-10-09 03:28:13,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 169967616. Throughput: 0: 1711.5, 1: 1680.1. Samples: 42499992. Policy #0 lag: (min: 0.0, avg: 23.1, max: 32.0) -[2023-10-09 03:28:13,975][87372] Avg episode reward: [(0, '7.810'), (1, '7.300')] -[2023-10-09 03:28:14,186][88326] Updated weights for policy 0, policy_version 82962 (0.0008) -[2023-10-09 03:28:14,554][88326] Updated weights for policy 0, policy_version 82972 (0.0009) -[2023-10-09 03:28:16,916][88327] Updated weights for policy 1, policy_version 83050 (0.0009) -[2023-10-09 03:28:17,276][88327] Updated weights for policy 1, policy_version 83060 (0.0007) -[2023-10-09 03:28:17,643][88327] Updated weights for policy 1, policy_version 83070 (0.0008) -[2023-10-09 03:28:18,609][88326] Updated weights for policy 0, policy_version 82982 (0.0008) -[2023-10-09 03:28:18,974][88326] Updated weights for policy 0, policy_version 82992 (0.0007) -[2023-10-09 03:28:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 170033152. Throughput: 0: 1706.8, 1: 1675.1. Samples: 42520016. Policy #0 lag: (min: 0.0, avg: 23.1, max: 32.0) -[2023-10-09 03:28:18,975][87372] Avg episode reward: [(0, '7.340'), (1, '7.430')] -[2023-10-09 03:28:19,342][88326] Updated weights for policy 0, policy_version 83002 (0.0008) -[2023-10-09 03:28:21,836][88327] Updated weights for policy 1, policy_version 83080 (0.0010) -[2023-10-09 03:28:22,213][88327] Updated weights for policy 1, policy_version 83090 (0.0011) -[2023-10-09 03:28:22,573][88327] Updated weights for policy 1, policy_version 83100 (0.0009) -[2023-10-09 03:28:23,394][88326] Updated weights for policy 0, policy_version 83012 (0.0009) -[2023-10-09 03:28:23,766][88326] Updated weights for policy 0, policy_version 83022 (0.0009) -[2023-10-09 03:28:23,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 170098688. Throughput: 0: 1701.8, 1: 1698.0. Samples: 42530558. Policy #0 lag: (min: 0.0, avg: 23.1, max: 32.0) -[2023-10-09 03:28:23,975][87372] Avg episode reward: [(0, '6.960'), (1, '7.900')] -[2023-10-09 03:28:24,137][88326] Updated weights for policy 0, policy_version 83032 (0.0009) -[2023-10-09 03:28:26,605][88327] Updated weights for policy 1, policy_version 83110 (0.0009) -[2023-10-09 03:28:26,964][88327] Updated weights for policy 1, policy_version 83120 (0.0008) -[2023-10-09 03:28:27,334][88327] Updated weights for policy 1, policy_version 83130 (0.0007) -[2023-10-09 03:28:28,386][88326] Updated weights for policy 0, policy_version 83042 (0.0008) -[2023-10-09 03:28:28,762][88326] Updated weights for policy 0, policy_version 83052 (0.0007) -[2023-10-09 03:28:28,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 170164224. Throughput: 0: 1697.7, 1: 1672.7. Samples: 42550220. Policy #0 lag: (min: 0.0, avg: 23.1, max: 32.0) -[2023-10-09 03:28:28,975][87372] Avg episode reward: [(0, '7.280'), (1, '7.590')] -[2023-10-09 03:28:29,127][88326] Updated weights for policy 0, policy_version 83062 (0.0007) -[2023-10-09 03:28:29,500][88326] Updated weights for policy 0, policy_version 83072 (0.0008) -[2023-10-09 03:28:31,307][88327] Updated weights for policy 1, policy_version 83140 (0.0008) -[2023-10-09 03:28:31,660][88327] Updated weights for policy 1, policy_version 83150 (0.0009) -[2023-10-09 03:28:32,022][88327] Updated weights for policy 1, policy_version 83160 (0.0008) -[2023-10-09 03:28:33,466][88326] Updated weights for policy 0, policy_version 83082 (0.0011) -[2023-10-09 03:28:33,835][88326] Updated weights for policy 0, policy_version 83092 (0.0010) -[2023-10-09 03:28:33,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 170229760. Throughput: 0: 1693.2, 1: 1686.2. Samples: 42570772. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-09 03:28:33,975][87372] Avg episode reward: [(0, '6.420'), (1, '7.470')] -[2023-10-09 03:28:33,989][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000083168_85164032.pth... -[2023-10-09 03:28:34,024][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000081600_83558400.pth -[2023-10-09 03:28:34,201][88326] Updated weights for policy 0, policy_version 83102 (0.0009) -[2023-10-09 03:28:34,272][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000083104_85098496.pth... -[2023-10-09 03:28:34,314][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000081504_83460096.pth -[2023-10-09 03:28:36,130][88327] Updated weights for policy 1, policy_version 83170 (0.0010) -[2023-10-09 03:28:36,490][88327] Updated weights for policy 1, policy_version 83180 (0.0011) -[2023-10-09 03:28:36,851][88327] Updated weights for policy 1, policy_version 83190 (0.0010) -[2023-10-09 03:28:37,212][88327] Updated weights for policy 1, policy_version 83200 (0.0009) -[2023-10-09 03:28:38,161][88326] Updated weights for policy 0, policy_version 83112 (0.0010) -[2023-10-09 03:28:38,530][88326] Updated weights for policy 0, policy_version 83122 (0.0009) -[2023-10-09 03:28:38,901][88326] Updated weights for policy 0, policy_version 83132 (0.0008) -[2023-10-09 03:28:38,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 170295296. Throughput: 0: 1693.8, 1: 1695.8. Samples: 42581172. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-09 03:28:38,975][87372] Avg episode reward: [(0, '6.520'), (1, '7.500')] -[2023-10-09 03:28:41,381][88327] Updated weights for policy 1, policy_version 83210 (0.0009) -[2023-10-09 03:28:41,742][88327] Updated weights for policy 1, policy_version 83220 (0.0007) -[2023-10-09 03:28:42,101][88327] Updated weights for policy 1, policy_version 83230 (0.0009) -[2023-10-09 03:28:42,934][88326] Updated weights for policy 0, policy_version 83142 (0.0008) -[2023-10-09 03:28:43,301][88326] Updated weights for policy 0, policy_version 83152 (0.0010) -[2023-10-09 03:28:43,674][88326] Updated weights for policy 0, policy_version 83162 (0.0011) -[2023-10-09 03:28:43,974][87372] Fps is (10 sec: 16384.5, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 170393600. Throughput: 0: 1694.6, 1: 1671.6. Samples: 42601054. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-09 03:28:43,975][87372] Avg episode reward: [(0, '6.640'), (1, '7.020')] -[2023-10-09 03:28:46,027][88327] Updated weights for policy 1, policy_version 83240 (0.0007) -[2023-10-09 03:28:46,402][88327] Updated weights for policy 1, policy_version 83250 (0.0011) -[2023-10-09 03:28:46,765][88327] Updated weights for policy 1, policy_version 83260 (0.0010) -[2023-10-09 03:28:47,637][88326] Updated weights for policy 0, policy_version 83172 (0.0007) -[2023-10-09 03:28:48,002][88326] Updated weights for policy 0, policy_version 83182 (0.0007) -[2023-10-09 03:28:48,375][88326] Updated weights for policy 0, policy_version 83192 (0.0008) -[2023-10-09 03:28:48,974][87372] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 170459136. Throughput: 0: 1682.7, 1: 1689.6. Samples: 42621056. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-09 03:28:48,975][87372] Avg episode reward: [(0, '6.930'), (1, '7.160')] -[2023-10-09 03:28:50,764][88327] Updated weights for policy 1, policy_version 83270 (0.0009) -[2023-10-09 03:28:51,133][88327] Updated weights for policy 1, policy_version 83280 (0.0008) -[2023-10-09 03:28:51,499][88327] Updated weights for policy 1, policy_version 83290 (0.0008) -[2023-10-09 03:28:52,497][88326] Updated weights for policy 0, policy_version 83202 (0.0009) -[2023-10-09 03:28:52,866][88326] Updated weights for policy 0, policy_version 83212 (0.0008) -[2023-10-09 03:28:53,228][88326] Updated weights for policy 0, policy_version 83222 (0.0008) -[2023-10-09 03:28:53,596][88326] Updated weights for policy 0, policy_version 83232 (0.0009) -[2023-10-09 03:28:53,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 170524672. Throughput: 0: 1698.8, 1: 1683.8. Samples: 42631786. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-09 03:28:53,974][87372] Avg episode reward: [(0, '7.380'), (1, '6.930')] -[2023-10-09 03:28:55,347][88327] Updated weights for policy 1, policy_version 83300 (0.0009) -[2023-10-09 03:28:55,699][88327] Updated weights for policy 1, policy_version 83310 (0.0009) -[2023-10-09 03:28:56,063][88327] Updated weights for policy 1, policy_version 83320 (0.0007) -[2023-10-09 03:28:57,706][88326] Updated weights for policy 0, policy_version 83242 (0.0009) -[2023-10-09 03:28:58,070][88326] Updated weights for policy 0, policy_version 83252 (0.0009) -[2023-10-09 03:28:58,441][88326] Updated weights for policy 0, policy_version 83262 (0.0010) -[2023-10-09 03:28:58,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 170590208. Throughput: 0: 1696.0, 1: 1680.8. Samples: 42651950. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-09 03:28:58,975][87372] Avg episode reward: [(0, '7.220'), (1, '7.530')] -[2023-10-09 03:28:59,984][88327] Updated weights for policy 1, policy_version 83330 (0.0008) -[2023-10-09 03:29:00,346][88327] Updated weights for policy 1, policy_version 83340 (0.0009) -[2023-10-09 03:29:00,712][88327] Updated weights for policy 1, policy_version 83350 (0.0008) -[2023-10-09 03:29:01,086][88327] Updated weights for policy 1, policy_version 83360 (0.0009) -[2023-10-09 03:29:02,515][88326] Updated weights for policy 0, policy_version 83272 (0.0007) -[2023-10-09 03:29:02,886][88326] Updated weights for policy 0, policy_version 83282 (0.0007) -[2023-10-09 03:29:03,262][88326] Updated weights for policy 0, policy_version 83292 (0.0009) -[2023-10-09 03:29:03,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 170655744. Throughput: 0: 1674.5, 1: 1701.9. Samples: 42671958. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-09 03:29:03,975][87372] Avg episode reward: [(0, '7.620'), (1, '7.300')] -[2023-10-09 03:29:05,193][88327] Updated weights for policy 1, policy_version 83370 (0.0007) -[2023-10-09 03:29:05,556][88327] Updated weights for policy 1, policy_version 83380 (0.0008) -[2023-10-09 03:29:05,929][88327] Updated weights for policy 1, policy_version 83390 (0.0008) -[2023-10-09 03:29:07,283][88326] Updated weights for policy 0, policy_version 83302 (0.0009) -[2023-10-09 03:29:07,659][88326] Updated weights for policy 0, policy_version 83312 (0.0008) -[2023-10-09 03:29:08,041][88326] Updated weights for policy 0, policy_version 83322 (0.0007) -[2023-10-09 03:29:08,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 170721280. Throughput: 0: 1693.7, 1: 1671.9. Samples: 42682012. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-09 03:29:08,974][87372] Avg episode reward: [(0, '7.990'), (1, '7.040')] -[2023-10-09 03:29:10,075][88327] Updated weights for policy 1, policy_version 83400 (0.0009) -[2023-10-09 03:29:10,432][88327] Updated weights for policy 1, policy_version 83410 (0.0008) -[2023-10-09 03:29:10,799][88327] Updated weights for policy 1, policy_version 83420 (0.0009) -[2023-10-09 03:29:11,928][88326] Updated weights for policy 0, policy_version 83332 (0.0008) -[2023-10-09 03:29:12,291][88326] Updated weights for policy 0, policy_version 83342 (0.0007) -[2023-10-09 03:29:12,658][88326] Updated weights for policy 0, policy_version 83352 (0.0009) -[2023-10-09 03:29:13,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 170786816. Throughput: 0: 1686.8, 1: 1698.4. Samples: 42702558. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-09 03:29:13,975][87372] Avg episode reward: [(0, '7.550'), (1, '7.260')] -[2023-10-09 03:29:14,793][88327] Updated weights for policy 1, policy_version 83430 (0.0008) -[2023-10-09 03:29:15,185][88327] Updated weights for policy 1, policy_version 83440 (0.0007) -[2023-10-09 03:29:15,558][88327] Updated weights for policy 1, policy_version 83450 (0.0009) -[2023-10-09 03:29:16,836][88326] Updated weights for policy 0, policy_version 83362 (0.0008) -[2023-10-09 03:29:17,205][88326] Updated weights for policy 0, policy_version 83372 (0.0008) -[2023-10-09 03:29:17,580][88326] Updated weights for policy 0, policy_version 83382 (0.0009) -[2023-10-09 03:29:17,951][88326] Updated weights for policy 0, policy_version 83392 (0.0009) -[2023-10-09 03:29:18,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 170852352. Throughput: 0: 1665.1, 1: 1707.2. Samples: 42722524. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-09 03:29:18,975][87372] Avg episode reward: [(0, '7.580'), (1, '7.880')] -[2023-10-09 03:29:19,528][88327] Updated weights for policy 1, policy_version 83460 (0.0008) -[2023-10-09 03:29:19,903][88327] Updated weights for policy 1, policy_version 83470 (0.0009) -[2023-10-09 03:29:20,261][88327] Updated weights for policy 1, policy_version 83480 (0.0010) -[2023-10-09 03:29:22,044][88326] Updated weights for policy 0, policy_version 83402 (0.0011) -[2023-10-09 03:29:22,410][88326] Updated weights for policy 0, policy_version 83412 (0.0010) -[2023-10-09 03:29:22,781][88326] Updated weights for policy 0, policy_version 83422 (0.0009) -[2023-10-09 03:29:23,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 170917888. Throughput: 0: 1691.6, 1: 1680.8. Samples: 42732932. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-09 03:29:23,975][87372] Avg episode reward: [(0, '7.180'), (1, '7.900')] -[2023-10-09 03:29:23,999][88327] Updated weights for policy 1, policy_version 83490 (0.0007) -[2023-10-09 03:29:24,360][88327] Updated weights for policy 1, policy_version 83500 (0.0008) -[2023-10-09 03:29:24,727][88327] Updated weights for policy 1, policy_version 83510 (0.0009) -[2023-10-09 03:29:25,097][88327] Updated weights for policy 1, policy_version 83520 (0.0008) -[2023-10-09 03:29:26,947][88326] Updated weights for policy 0, policy_version 83432 (0.0007) -[2023-10-09 03:29:27,313][88326] Updated weights for policy 0, policy_version 83442 (0.0007) -[2023-10-09 03:29:27,673][88326] Updated weights for policy 0, policy_version 83452 (0.0008) -[2023-10-09 03:29:28,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 170983424. Throughput: 0: 1669.9, 1: 1709.4. Samples: 42753126. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-09 03:29:28,975][87372] Avg episode reward: [(0, '7.040'), (1, '7.710')] -[2023-10-09 03:29:29,293][88327] Updated weights for policy 1, policy_version 83530 (0.0008) -[2023-10-09 03:29:29,648][88327] Updated weights for policy 1, policy_version 83540 (0.0007) -[2023-10-09 03:29:30,015][88327] Updated weights for policy 1, policy_version 83550 (0.0008) -[2023-10-09 03:29:31,710][88326] Updated weights for policy 0, policy_version 83462 (0.0007) -[2023-10-09 03:29:32,072][88326] Updated weights for policy 0, policy_version 83472 (0.0008) -[2023-10-09 03:29:32,438][88326] Updated weights for policy 0, policy_version 83482 (0.0009) -[2023-10-09 03:29:33,974][87372] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 171048960. Throughput: 0: 1670.7, 1: 1718.1. Samples: 42773554. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-09 03:29:33,975][87372] Avg episode reward: [(0, '6.860'), (1, '6.670')] -[2023-10-09 03:29:34,030][88327] Updated weights for policy 1, policy_version 83560 (0.0007) -[2023-10-09 03:29:34,399][88327] Updated weights for policy 1, policy_version 83570 (0.0007) -[2023-10-09 03:29:34,770][88327] Updated weights for policy 1, policy_version 83580 (0.0008) -[2023-10-09 03:29:36,444][88326] Updated weights for policy 0, policy_version 83492 (0.0009) -[2023-10-09 03:29:36,814][88326] Updated weights for policy 0, policy_version 83502 (0.0010) -[2023-10-09 03:29:37,178][88326] Updated weights for policy 0, policy_version 83512 (0.0009) -[2023-10-09 03:29:38,916][88327] Updated weights for policy 1, policy_version 83590 (0.0008) -[2023-10-09 03:29:38,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 171114496. Throughput: 0: 1685.4, 1: 1701.4. Samples: 42784192. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-09 03:29:38,974][87372] Avg episode reward: [(0, '5.940'), (1, '7.000')] -[2023-10-09 03:29:39,284][88327] Updated weights for policy 1, policy_version 83600 (0.0008) -[2023-10-09 03:29:39,661][88327] Updated weights for policy 1, policy_version 83610 (0.0010) -[2023-10-09 03:29:41,320][88326] Updated weights for policy 0, policy_version 83522 (0.0008) -[2023-10-09 03:29:41,688][88326] Updated weights for policy 0, policy_version 83532 (0.0008) -[2023-10-09 03:29:42,061][88326] Updated weights for policy 0, policy_version 83542 (0.0009) -[2023-10-09 03:29:42,431][88326] Updated weights for policy 0, policy_version 83552 (0.0007) -[2023-10-09 03:29:43,669][88327] Updated weights for policy 1, policy_version 83620 (0.0008) -[2023-10-09 03:29:43,974][87372] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 171180032. Throughput: 0: 1664.6, 1: 1714.1. Samples: 42803992. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-09 03:29:43,975][87372] Avg episode reward: [(0, '6.920'), (1, '7.240')] -[2023-10-09 03:29:44,035][88327] Updated weights for policy 1, policy_version 83630 (0.0007) -[2023-10-09 03:29:44,393][88327] Updated weights for policy 1, policy_version 83640 (0.0007) -[2023-10-09 03:29:46,429][88326] Updated weights for policy 0, policy_version 83562 (0.0009) -[2023-10-09 03:29:46,796][88326] Updated weights for policy 0, policy_version 83572 (0.0007) -[2023-10-09 03:29:47,165][88326] Updated weights for policy 0, policy_version 83582 (0.0007) -[2023-10-09 03:29:48,459][88327] Updated weights for policy 1, policy_version 83650 (0.0007) -[2023-10-09 03:29:48,824][88327] Updated weights for policy 1, policy_version 83660 (0.0009) -[2023-10-09 03:29:48,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 171245568. Throughput: 0: 1680.9, 1: 1704.4. Samples: 42824294. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-09 03:29:48,974][87372] Avg episode reward: [(0, '7.280'), (1, '7.410')] -[2023-10-09 03:29:49,193][88327] Updated weights for policy 1, policy_version 83670 (0.0008) -[2023-10-09 03:29:49,553][88327] Updated weights for policy 1, policy_version 83680 (0.0008) -[2023-10-09 03:29:51,238][88326] Updated weights for policy 0, policy_version 83592 (0.0007) -[2023-10-09 03:29:51,613][88326] Updated weights for policy 0, policy_version 83602 (0.0007) -[2023-10-09 03:29:51,987][88326] Updated weights for policy 0, policy_version 83612 (0.0007) -[2023-10-09 03:29:53,460][88327] Updated weights for policy 1, policy_version 83690 (0.0008) -[2023-10-09 03:29:53,828][88327] Updated weights for policy 1, policy_version 83700 (0.0009) -[2023-10-09 03:29:53,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 171311104. Throughput: 0: 1682.8, 1: 1703.9. Samples: 42834416. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-09 03:29:53,975][87372] Avg episode reward: [(0, '6.940'), (1, '7.470')] -[2023-10-09 03:29:54,183][88327] Updated weights for policy 1, policy_version 83710 (0.0007) -[2023-10-09 03:29:56,008][88326] Updated weights for policy 0, policy_version 83622 (0.0009) -[2023-10-09 03:29:56,377][88326] Updated weights for policy 0, policy_version 83632 (0.0009) -[2023-10-09 03:29:56,760][88326] Updated weights for policy 0, policy_version 83642 (0.0010) -[2023-10-09 03:29:58,284][88327] Updated weights for policy 1, policy_version 83720 (0.0009) -[2023-10-09 03:29:58,655][88327] Updated weights for policy 1, policy_version 83730 (0.0009) -[2023-10-09 03:29:58,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 171376640. Throughput: 0: 1667.7, 1: 1701.7. Samples: 42854182. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-09 03:29:58,975][87372] Avg episode reward: [(0, '7.530'), (1, '8.830')] -[2023-10-09 03:29:59,023][88327] Updated weights for policy 1, policy_version 83740 (0.0008) -[2023-10-09 03:29:59,166][88168] Saving new best policy, reward=8.830! -[2023-10-09 03:30:00,767][88326] Updated weights for policy 0, policy_version 83652 (0.0009) -[2023-10-09 03:30:01,138][88326] Updated weights for policy 0, policy_version 83662 (0.0009) -[2023-10-09 03:30:01,512][88326] Updated weights for policy 0, policy_version 83672 (0.0007) -[2023-10-09 03:30:03,215][88327] Updated weights for policy 1, policy_version 83750 (0.0009) -[2023-10-09 03:30:03,600][88327] Updated weights for policy 1, policy_version 83760 (0.0010) -[2023-10-09 03:30:03,963][88327] Updated weights for policy 1, policy_version 83770 (0.0007) -[2023-10-09 03:30:03,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 171442176. Throughput: 0: 1686.3, 1: 1698.2. Samples: 42874828. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-09 03:30:03,975][87372] Avg episode reward: [(0, '7.430'), (1, '7.820')] -[2023-10-09 03:30:05,580][88326] Updated weights for policy 0, policy_version 83682 (0.0010) -[2023-10-09 03:30:05,945][88326] Updated weights for policy 0, policy_version 83692 (0.0008) -[2023-10-09 03:30:06,315][88326] Updated weights for policy 0, policy_version 83702 (0.0009) -[2023-10-09 03:30:06,677][88326] Updated weights for policy 0, policy_version 83712 (0.0008) -[2023-10-09 03:30:07,916][88327] Updated weights for policy 1, policy_version 83780 (0.0007) -[2023-10-09 03:30:08,283][88327] Updated weights for policy 1, policy_version 83790 (0.0009) -[2023-10-09 03:30:08,642][88327] Updated weights for policy 1, policy_version 83800 (0.0009) -[2023-10-09 03:30:08,974][87372] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 171540480. Throughput: 0: 1670.8, 1: 1700.9. Samples: 42884662. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-09 03:30:08,975][87372] Avg episode reward: [(0, '7.130'), (1, '8.040')] -[2023-10-09 03:30:10,716][88326] Updated weights for policy 0, policy_version 83722 (0.0010) -[2023-10-09 03:30:11,087][88326] Updated weights for policy 0, policy_version 83732 (0.0010) -[2023-10-09 03:30:11,459][88326] Updated weights for policy 0, policy_version 83742 (0.0011) -[2023-10-09 03:30:12,762][88327] Updated weights for policy 1, policy_version 83810 (0.0009) -[2023-10-09 03:30:13,128][88327] Updated weights for policy 1, policy_version 83820 (0.0008) -[2023-10-09 03:30:13,495][88327] Updated weights for policy 1, policy_version 83830 (0.0010) -[2023-10-09 03:30:13,860][88327] Updated weights for policy 1, policy_version 83840 (0.0010) -[2023-10-09 03:30:13,974][87372] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 171606016. Throughput: 0: 1677.1, 1: 1701.0. Samples: 42905140. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-09 03:30:13,975][87372] Avg episode reward: [(0, '7.280'), (1, '7.450')] -[2023-10-09 03:30:15,594][88326] Updated weights for policy 0, policy_version 83752 (0.0007) -[2023-10-09 03:30:15,966][88326] Updated weights for policy 0, policy_version 83762 (0.0009) -[2023-10-09 03:30:16,341][88326] Updated weights for policy 0, policy_version 83772 (0.0009) -[2023-10-09 03:30:17,773][88327] Updated weights for policy 1, policy_version 83850 (0.0007) -[2023-10-09 03:30:18,145][88327] Updated weights for policy 1, policy_version 83860 (0.0009) -[2023-10-09 03:30:18,508][88327] Updated weights for policy 1, policy_version 83870 (0.0007) -[2023-10-09 03:30:18,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 171671552. Throughput: 0: 1691.2, 1: 1682.1. Samples: 42925348. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-09 03:30:18,975][87372] Avg episode reward: [(0, '7.320'), (1, '7.390')] -[2023-10-09 03:30:20,285][88326] Updated weights for policy 0, policy_version 83782 (0.0007) -[2023-10-09 03:30:20,654][88326] Updated weights for policy 0, policy_version 83792 (0.0008) -[2023-10-09 03:30:21,028][88326] Updated weights for policy 0, policy_version 83802 (0.0008) -[2023-10-09 03:30:22,550][88327] Updated weights for policy 1, policy_version 83880 (0.0008) -[2023-10-09 03:30:22,915][88327] Updated weights for policy 1, policy_version 83890 (0.0009) -[2023-10-09 03:30:23,270][88327] Updated weights for policy 1, policy_version 83900 (0.0009) -[2023-10-09 03:30:23,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 171737088. Throughput: 0: 1663.1, 1: 1697.4. Samples: 42935414. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-09 03:30:23,975][87372] Avg episode reward: [(0, '7.390'), (1, '7.340')] -[2023-10-09 03:30:25,076][88326] Updated weights for policy 0, policy_version 83812 (0.0009) -[2023-10-09 03:30:25,431][88326] Updated weights for policy 0, policy_version 83822 (0.0008) -[2023-10-09 03:30:25,801][88326] Updated weights for policy 0, policy_version 83832 (0.0009) -[2023-10-09 03:30:27,277][88327] Updated weights for policy 1, policy_version 83910 (0.0007) -[2023-10-09 03:30:27,647][88327] Updated weights for policy 1, policy_version 83920 (0.0008) -[2023-10-09 03:30:28,018][88327] Updated weights for policy 1, policy_version 83930 (0.0009) -[2023-10-09 03:30:28,974][87372] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 171802624. Throughput: 0: 1687.8, 1: 1696.6. Samples: 42956288. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-09 03:30:28,975][87372] Avg episode reward: [(0, '7.440'), (1, '7.680')] -[2023-10-09 03:30:29,631][88326] Updated weights for policy 0, policy_version 83842 (0.0008) -[2023-10-09 03:30:30,002][88326] Updated weights for policy 0, policy_version 83852 (0.0008) -[2023-10-09 03:30:30,373][88326] Updated weights for policy 0, policy_version 83862 (0.0007) -[2023-10-09 03:30:30,740][88326] Updated weights for policy 0, policy_version 83872 (0.0009) -[2023-10-09 03:30:32,027][88327] Updated weights for policy 1, policy_version 83940 (0.0009) -[2023-10-09 03:30:32,389][88327] Updated weights for policy 1, policy_version 83950 (0.0011) -[2023-10-09 03:30:32,756][88327] Updated weights for policy 1, policy_version 83960 (0.0009) -[2023-10-09 03:30:33,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 171868160. Throughput: 0: 1699.1, 1: 1675.6. Samples: 42976154. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-09 03:30:33,975][87372] Avg episode reward: [(0, '7.990'), (1, '7.360')] -[2023-10-09 03:30:33,985][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000083968_85983232.pth... -[2023-10-09 03:30:33,985][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000083872_85884928.pth... -[2023-10-09 03:30:34,022][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000082304_84279296.pth -[2023-10-09 03:30:34,027][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000082368_84344832.pth -[2023-10-09 03:30:34,757][88326] Updated weights for policy 0, policy_version 83882 (0.0009) -[2023-10-09 03:30:35,123][88326] Updated weights for policy 0, policy_version 83892 (0.0007) -[2023-10-09 03:30:35,498][88326] Updated weights for policy 0, policy_version 83902 (0.0008) -[2023-10-09 03:30:36,822][88327] Updated weights for policy 1, policy_version 83970 (0.0008) -[2023-10-09 03:30:37,199][88327] Updated weights for policy 1, policy_version 83980 (0.0009) -[2023-10-09 03:30:37,566][88327] Updated weights for policy 1, policy_version 83990 (0.0010) -[2023-10-09 03:30:37,939][88327] Updated weights for policy 1, policy_version 84000 (0.0008) -[2023-10-09 03:30:38,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 171933696. Throughput: 0: 1676.0, 1: 1704.2. Samples: 42986528. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-09 03:30:38,975][87372] Avg episode reward: [(0, '7.230'), (1, '6.980')] -[2023-10-09 03:30:39,622][88326] Updated weights for policy 0, policy_version 83912 (0.0010) -[2023-10-09 03:30:39,986][88326] Updated weights for policy 0, policy_version 83922 (0.0007) -[2023-10-09 03:30:40,345][88326] Updated weights for policy 0, policy_version 83932 (0.0009) -[2023-10-09 03:30:41,921][88327] Updated weights for policy 1, policy_version 84010 (0.0007) -[2023-10-09 03:30:42,282][88327] Updated weights for policy 1, policy_version 84020 (0.0007) -[2023-10-09 03:30:42,650][88327] Updated weights for policy 1, policy_version 84030 (0.0009) -[2023-10-09 03:30:43,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 171999232. Throughput: 0: 1698.1, 1: 1692.2. Samples: 43006748. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-09 03:30:43,975][87372] Avg episode reward: [(0, '7.050'), (1, '6.930')] -[2023-10-09 03:30:44,497][88326] Updated weights for policy 0, policy_version 83942 (0.0010) -[2023-10-09 03:30:44,857][88326] Updated weights for policy 0, policy_version 83952 (0.0009) -[2023-10-09 03:30:45,229][88326] Updated weights for policy 0, policy_version 83962 (0.0009) -[2023-10-09 03:30:46,637][88327] Updated weights for policy 1, policy_version 84040 (0.0008) -[2023-10-09 03:30:46,998][88327] Updated weights for policy 1, policy_version 84050 (0.0008) -[2023-10-09 03:30:47,373][88327] Updated weights for policy 1, policy_version 84060 (0.0008) -[2023-10-09 03:30:48,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 172064768. Throughput: 0: 1698.0, 1: 1681.0. Samples: 43026886. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-09 03:30:48,975][87372] Avg episode reward: [(0, '7.150'), (1, '7.090')] -[2023-10-09 03:30:49,169][88326] Updated weights for policy 0, policy_version 83972 (0.0009) -[2023-10-09 03:30:49,544][88326] Updated weights for policy 0, policy_version 83982 (0.0007) -[2023-10-09 03:30:49,916][88326] Updated weights for policy 0, policy_version 83992 (0.0008) -[2023-10-09 03:30:51,513][88327] Updated weights for policy 1, policy_version 84070 (0.0008) -[2023-10-09 03:30:51,883][88327] Updated weights for policy 1, policy_version 84080 (0.0008) -[2023-10-09 03:30:52,245][88327] Updated weights for policy 1, policy_version 84090 (0.0009) -[2023-10-09 03:30:53,843][88326] Updated weights for policy 0, policy_version 84002 (0.0007) -[2023-10-09 03:30:53,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 172130304. Throughput: 0: 1685.4, 1: 1707.0. Samples: 43037318. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-09 03:30:53,975][87372] Avg episode reward: [(0, '6.710'), (1, '6.920')] -[2023-10-09 03:30:54,204][88326] Updated weights for policy 0, policy_version 84012 (0.0009) -[2023-10-09 03:30:54,570][88326] Updated weights for policy 0, policy_version 84022 (0.0007) -[2023-10-09 03:30:54,934][88326] Updated weights for policy 0, policy_version 84032 (0.0007) -[2023-10-09 03:30:56,071][88327] Updated weights for policy 1, policy_version 84100 (0.0008) -[2023-10-09 03:30:56,433][88327] Updated weights for policy 1, policy_version 84110 (0.0009) -[2023-10-09 03:30:56,799][88327] Updated weights for policy 1, policy_version 84120 (0.0010) -[2023-10-09 03:30:58,970][88326] Updated weights for policy 0, policy_version 84042 (0.0009) -[2023-10-09 03:30:58,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 172195840. Throughput: 0: 1703.7, 1: 1675.4. Samples: 43057200. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-09 03:30:58,975][87372] Avg episode reward: [(0, '6.990'), (1, '7.140')] -[2023-10-09 03:30:59,340][88326] Updated weights for policy 0, policy_version 84052 (0.0008) -[2023-10-09 03:30:59,708][88326] Updated weights for policy 0, policy_version 84062 (0.0007) -[2023-10-09 03:31:00,922][88327] Updated weights for policy 1, policy_version 84130 (0.0010) -[2023-10-09 03:31:01,291][88327] Updated weights for policy 1, policy_version 84140 (0.0010) -[2023-10-09 03:31:01,654][88327] Updated weights for policy 1, policy_version 84150 (0.0009) -[2023-10-09 03:31:02,024][88327] Updated weights for policy 1, policy_version 84160 (0.0009) -[2023-10-09 03:31:03,685][88326] Updated weights for policy 0, policy_version 84072 (0.0008) -[2023-10-09 03:31:03,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 172261376. Throughput: 0: 1704.5, 1: 1688.0. Samples: 43078012. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-09 03:31:03,975][87372] Avg episode reward: [(0, '7.370'), (1, '7.190')] -[2023-10-09 03:31:04,070][88326] Updated weights for policy 0, policy_version 84082 (0.0008) -[2023-10-09 03:31:04,433][88326] Updated weights for policy 0, policy_version 84092 (0.0008) -[2023-10-09 03:31:06,002][88327] Updated weights for policy 1, policy_version 84170 (0.0011) -[2023-10-09 03:31:06,373][88327] Updated weights for policy 1, policy_version 84180 (0.0009) -[2023-10-09 03:31:06,730][88327] Updated weights for policy 1, policy_version 84190 (0.0009) -[2023-10-09 03:31:08,698][88326] Updated weights for policy 0, policy_version 84102 (0.0007) -[2023-10-09 03:31:08,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 172326912. Throughput: 0: 1697.4, 1: 1689.3. Samples: 43087818. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-09 03:31:08,975][87372] Avg episode reward: [(0, '7.200'), (1, '7.090')] -[2023-10-09 03:31:09,063][88326] Updated weights for policy 0, policy_version 84112 (0.0009) -[2023-10-09 03:31:09,426][88326] Updated weights for policy 0, policy_version 84122 (0.0008) -[2023-10-09 03:31:10,792][88327] Updated weights for policy 1, policy_version 84200 (0.0009) -[2023-10-09 03:31:11,159][88327] Updated weights for policy 1, policy_version 84210 (0.0007) -[2023-10-09 03:31:11,528][88327] Updated weights for policy 1, policy_version 84220 (0.0007) -[2023-10-09 03:31:13,421][88326] Updated weights for policy 0, policy_version 84132 (0.0009) -[2023-10-09 03:31:13,787][88326] Updated weights for policy 0, policy_version 84142 (0.0008) -[2023-10-09 03:31:13,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 172392448. Throughput: 0: 1699.7, 1: 1675.3. Samples: 43108164. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:31:13,975][87372] Avg episode reward: [(0, '7.300'), (1, '7.710')] -[2023-10-09 03:31:14,155][88326] Updated weights for policy 0, policy_version 84152 (0.0007) -[2023-10-09 03:31:15,435][88327] Updated weights for policy 1, policy_version 84230 (0.0008) -[2023-10-09 03:31:15,807][88327] Updated weights for policy 1, policy_version 84240 (0.0007) -[2023-10-09 03:31:16,169][88327] Updated weights for policy 1, policy_version 84250 (0.0008) -[2023-10-09 03:31:18,099][88326] Updated weights for policy 0, policy_version 84162 (0.0008) -[2023-10-09 03:31:18,468][88326] Updated weights for policy 0, policy_version 84172 (0.0009) -[2023-10-09 03:31:18,827][88326] Updated weights for policy 0, policy_version 84182 (0.0008) -[2023-10-09 03:31:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 172457984. Throughput: 0: 1692.2, 1: 1699.4. Samples: 43128776. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:31:18,975][87372] Avg episode reward: [(0, '6.900'), (1, '7.920')] -[2023-10-09 03:31:19,194][88326] Updated weights for policy 0, policy_version 84192 (0.0010) -[2023-10-09 03:31:20,394][88327] Updated weights for policy 1, policy_version 84260 (0.0008) -[2023-10-09 03:31:20,758][88327] Updated weights for policy 1, policy_version 84270 (0.0009) -[2023-10-09 03:31:21,126][88327] Updated weights for policy 1, policy_version 84280 (0.0008) -[2023-10-09 03:31:23,291][88326] Updated weights for policy 0, policy_version 84202 (0.0007) -[2023-10-09 03:31:23,661][88326] Updated weights for policy 0, policy_version 84212 (0.0009) -[2023-10-09 03:31:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 172523520. Throughput: 0: 1697.4, 1: 1678.6. Samples: 43138448. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:31:23,974][87372] Avg episode reward: [(0, '6.420'), (1, '7.940')] -[2023-10-09 03:31:24,029][88326] Updated weights for policy 0, policy_version 84222 (0.0010) -[2023-10-09 03:31:25,277][88327] Updated weights for policy 1, policy_version 84290 (0.0010) -[2023-10-09 03:31:25,644][88327] Updated weights for policy 1, policy_version 84300 (0.0008) -[2023-10-09 03:31:26,009][88327] Updated weights for policy 1, policy_version 84310 (0.0010) -[2023-10-09 03:31:26,366][88327] Updated weights for policy 1, policy_version 84320 (0.0008) -[2023-10-09 03:31:28,150][88326] Updated weights for policy 0, policy_version 84232 (0.0009) -[2023-10-09 03:31:28,521][88326] Updated weights for policy 0, policy_version 84242 (0.0010) -[2023-10-09 03:31:28,886][88326] Updated weights for policy 0, policy_version 84252 (0.0010) -[2023-10-09 03:31:28,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 172589056. Throughput: 0: 1698.8, 1: 1685.2. Samples: 43159032. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:31:28,975][87372] Avg episode reward: [(0, '6.460'), (1, '8.620')] -[2023-10-09 03:31:30,474][88327] Updated weights for policy 1, policy_version 84330 (0.0009) -[2023-10-09 03:31:30,838][88327] Updated weights for policy 1, policy_version 84340 (0.0008) -[2023-10-09 03:31:31,202][88327] Updated weights for policy 1, policy_version 84350 (0.0008) -[2023-10-09 03:31:32,878][88326] Updated weights for policy 0, policy_version 84262 (0.0008) -[2023-10-09 03:31:33,240][88326] Updated weights for policy 0, policy_version 84272 (0.0007) -[2023-10-09 03:31:33,601][88326] Updated weights for policy 0, policy_version 84282 (0.0008) -[2023-10-09 03:31:33,974][87372] Fps is (10 sec: 16384.0, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 172687360. Throughput: 0: 1687.1, 1: 1698.1. Samples: 43179218. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:31:33,975][87372] Avg episode reward: [(0, '7.180'), (1, '7.440')] -[2023-10-09 03:31:35,157][88327] Updated weights for policy 1, policy_version 84360 (0.0009) -[2023-10-09 03:31:35,531][88327] Updated weights for policy 1, policy_version 84370 (0.0010) -[2023-10-09 03:31:35,897][88327] Updated weights for policy 1, policy_version 84380 (0.0007) -[2023-10-09 03:31:37,579][88326] Updated weights for policy 0, policy_version 84292 (0.0008) -[2023-10-09 03:31:37,940][88326] Updated weights for policy 0, policy_version 84302 (0.0008) -[2023-10-09 03:31:38,317][88326] Updated weights for policy 0, policy_version 84312 (0.0008) -[2023-10-09 03:31:38,974][87372] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 172752896. Throughput: 0: 1702.8, 1: 1671.6. Samples: 43189166. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:31:38,975][87372] Avg episode reward: [(0, '7.240'), (1, '7.390')] -[2023-10-09 03:31:39,805][88327] Updated weights for policy 1, policy_version 84390 (0.0008) -[2023-10-09 03:31:40,168][88327] Updated weights for policy 1, policy_version 84400 (0.0007) -[2023-10-09 03:31:40,530][88327] Updated weights for policy 1, policy_version 84410 (0.0008) -[2023-10-09 03:31:42,237][88326] Updated weights for policy 0, policy_version 84322 (0.0008) -[2023-10-09 03:31:42,606][88326] Updated weights for policy 0, policy_version 84332 (0.0010) -[2023-10-09 03:31:42,979][88326] Updated weights for policy 0, policy_version 84342 (0.0008) -[2023-10-09 03:31:43,342][88326] Updated weights for policy 0, policy_version 84352 (0.0007) -[2023-10-09 03:31:43,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 172818432. Throughput: 0: 1698.0, 1: 1703.3. Samples: 43210258. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:31:43,975][87372] Avg episode reward: [(0, '7.150'), (1, '7.220')] -[2023-10-09 03:31:44,676][88327] Updated weights for policy 1, policy_version 84420 (0.0010) -[2023-10-09 03:31:45,048][88327] Updated weights for policy 1, policy_version 84430 (0.0010) -[2023-10-09 03:31:45,407][88327] Updated weights for policy 1, policy_version 84440 (0.0011) -[2023-10-09 03:31:47,191][88326] Updated weights for policy 0, policy_version 84362 (0.0011) -[2023-10-09 03:31:47,563][88326] Updated weights for policy 0, policy_version 84372 (0.0009) -[2023-10-09 03:31:47,928][88326] Updated weights for policy 0, policy_version 84382 (0.0009) -[2023-10-09 03:31:48,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 172883968. Throughput: 0: 1673.6, 1: 1707.7. Samples: 43230172. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:31:48,975][87372] Avg episode reward: [(0, '8.060'), (1, '6.420')] -[2023-10-09 03:31:49,328][88327] Updated weights for policy 1, policy_version 84450 (0.0010) -[2023-10-09 03:31:49,699][88327] Updated weights for policy 1, policy_version 84460 (0.0008) -[2023-10-09 03:31:50,064][88327] Updated weights for policy 1, policy_version 84470 (0.0008) -[2023-10-09 03:31:50,424][88327] Updated weights for policy 1, policy_version 84480 (0.0009) -[2023-10-09 03:31:52,082][88326] Updated weights for policy 0, policy_version 84392 (0.0008) -[2023-10-09 03:31:52,448][88326] Updated weights for policy 0, policy_version 84402 (0.0007) -[2023-10-09 03:31:52,821][88326] Updated weights for policy 0, policy_version 84412 (0.0009) -[2023-10-09 03:31:53,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 172949504. Throughput: 0: 1705.4, 1: 1686.4. Samples: 43240448. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:31:53,975][87372] Avg episode reward: [(0, '7.390'), (1, '6.920')] -[2023-10-09 03:31:54,432][88327] Updated weights for policy 1, policy_version 84490 (0.0009) -[2023-10-09 03:31:54,794][88327] Updated weights for policy 1, policy_version 84500 (0.0008) -[2023-10-09 03:31:55,171][88327] Updated weights for policy 1, policy_version 84510 (0.0008) -[2023-10-09 03:31:56,794][88326] Updated weights for policy 0, policy_version 84422 (0.0009) -[2023-10-09 03:31:57,171][88326] Updated weights for policy 0, policy_version 84432 (0.0007) -[2023-10-09 03:31:57,538][88326] Updated weights for policy 0, policy_version 84442 (0.0008) -[2023-10-09 03:31:58,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 173015040. Throughput: 0: 1691.2, 1: 1703.3. Samples: 43260920. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:31:58,975][87372] Avg episode reward: [(0, '6.590'), (1, '7.260')] -[2023-10-09 03:31:59,161][88327] Updated weights for policy 1, policy_version 84520 (0.0010) -[2023-10-09 03:31:59,527][88327] Updated weights for policy 1, policy_version 84530 (0.0008) -[2023-10-09 03:31:59,885][88327] Updated weights for policy 1, policy_version 84540 (0.0009) -[2023-10-09 03:32:01,654][88326] Updated weights for policy 0, policy_version 84452 (0.0008) -[2023-10-09 03:32:02,018][88326] Updated weights for policy 0, policy_version 84462 (0.0009) -[2023-10-09 03:32:02,395][88326] Updated weights for policy 0, policy_version 84472 (0.0007) -[2023-10-09 03:32:03,967][88327] Updated weights for policy 1, policy_version 84550 (0.0008) -[2023-10-09 03:32:03,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 173080576. Throughput: 0: 1680.0, 1: 1704.9. Samples: 43281096. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-09 03:32:03,975][87372] Avg episode reward: [(0, '7.540'), (1, '7.960')] -[2023-10-09 03:32:04,328][88327] Updated weights for policy 1, policy_version 84560 (0.0009) -[2023-10-09 03:32:04,691][88327] Updated weights for policy 1, policy_version 84570 (0.0010) -[2023-10-09 03:32:06,653][88326] Updated weights for policy 0, policy_version 84482 (0.0008) -[2023-10-09 03:32:07,024][88326] Updated weights for policy 0, policy_version 84492 (0.0009) -[2023-10-09 03:32:07,383][88326] Updated weights for policy 0, policy_version 84502 (0.0008) -[2023-10-09 03:32:07,749][88326] Updated weights for policy 0, policy_version 84512 (0.0008) -[2023-10-09 03:32:08,607][88327] Updated weights for policy 1, policy_version 84580 (0.0009) -[2023-10-09 03:32:08,965][88327] Updated weights for policy 1, policy_version 84590 (0.0008) -[2023-10-09 03:32:08,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 173146112. Throughput: 0: 1708.4, 1: 1694.2. Samples: 43291566. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-09 03:32:08,976][87372] Avg episode reward: [(0, '7.770'), (1, '7.540')] -[2023-10-09 03:32:09,327][88327] Updated weights for policy 1, policy_version 84600 (0.0007) -[2023-10-09 03:32:11,674][88326] Updated weights for policy 0, policy_version 84522 (0.0007) -[2023-10-09 03:32:12,032][88326] Updated weights for policy 0, policy_version 84532 (0.0010) -[2023-10-09 03:32:12,408][88326] Updated weights for policy 0, policy_version 84542 (0.0007) -[2023-10-09 03:32:13,441][88327] Updated weights for policy 1, policy_version 84610 (0.0007) -[2023-10-09 03:32:13,808][88327] Updated weights for policy 1, policy_version 84620 (0.0008) -[2023-10-09 03:32:13,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 173211648. Throughput: 0: 1685.4, 1: 1707.2. Samples: 43311698. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-09 03:32:13,975][87372] Avg episode reward: [(0, '7.160'), (1, '7.210')] -[2023-10-09 03:32:14,172][88327] Updated weights for policy 1, policy_version 84630 (0.0007) -[2023-10-09 03:32:14,535][88327] Updated weights for policy 1, policy_version 84640 (0.0009) -[2023-10-09 03:32:16,507][88326] Updated weights for policy 0, policy_version 84552 (0.0007) -[2023-10-09 03:32:16,890][88326] Updated weights for policy 0, policy_version 84562 (0.0007) -[2023-10-09 03:32:17,265][88326] Updated weights for policy 0, policy_version 84572 (0.0007) -[2023-10-09 03:32:18,607][88327] Updated weights for policy 1, policy_version 84650 (0.0008) -[2023-10-09 03:32:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 173277184. Throughput: 0: 1691.2, 1: 1711.1. Samples: 43332326. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-09 03:32:18,975][87372] Avg episode reward: [(0, '6.970'), (1, '6.920')] -[2023-10-09 03:32:18,977][88327] Updated weights for policy 1, policy_version 84660 (0.0009) -[2023-10-09 03:32:19,337][88327] Updated weights for policy 1, policy_version 84670 (0.0007) -[2023-10-09 03:32:21,320][88326] Updated weights for policy 0, policy_version 84582 (0.0009) -[2023-10-09 03:32:21,680][88326] Updated weights for policy 0, policy_version 84592 (0.0009) -[2023-10-09 03:32:22,050][88326] Updated weights for policy 0, policy_version 84602 (0.0010) -[2023-10-09 03:32:23,265][88327] Updated weights for policy 1, policy_version 84680 (0.0007) -[2023-10-09 03:32:23,628][88327] Updated weights for policy 1, policy_version 84690 (0.0007) -[2023-10-09 03:32:23,974][87372] Fps is (10 sec: 13107.6, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 173342720. Throughput: 0: 1698.8, 1: 1709.9. Samples: 43342560. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-09 03:32:23,974][87372] Avg episode reward: [(0, '6.950'), (1, '7.100')] -[2023-10-09 03:32:23,995][88327] Updated weights for policy 1, policy_version 84700 (0.0010) -[2023-10-09 03:32:25,956][88326] Updated weights for policy 0, policy_version 84612 (0.0008) -[2023-10-09 03:32:26,323][88326] Updated weights for policy 0, policy_version 84622 (0.0007) -[2023-10-09 03:32:26,691][88326] Updated weights for policy 0, policy_version 84632 (0.0008) -[2023-10-09 03:32:28,139][88327] Updated weights for policy 1, policy_version 84710 (0.0008) -[2023-10-09 03:32:28,493][88327] Updated weights for policy 1, policy_version 84720 (0.0009) -[2023-10-09 03:32:28,860][88327] Updated weights for policy 1, policy_version 84730 (0.0007) -[2023-10-09 03:32:28,974][87372] Fps is (10 sec: 13107.6, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 173408256. Throughput: 0: 1674.9, 1: 1709.3. Samples: 43362546. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-09 03:32:28,974][87372] Avg episode reward: [(0, '7.070'), (1, '7.300')] -[2023-10-09 03:32:30,789][88326] Updated weights for policy 0, policy_version 84642 (0.0010) -[2023-10-09 03:32:31,152][88326] Updated weights for policy 0, policy_version 84652 (0.0011) -[2023-10-09 03:32:31,521][88326] Updated weights for policy 0, policy_version 84662 (0.0007) -[2023-10-09 03:32:31,896][88326] Updated weights for policy 0, policy_version 84672 (0.0007) -[2023-10-09 03:32:32,973][88327] Updated weights for policy 1, policy_version 84740 (0.0008) -[2023-10-09 03:32:33,372][88327] Updated weights for policy 1, policy_version 84750 (0.0008) -[2023-10-09 03:32:33,740][88327] Updated weights for policy 1, policy_version 84760 (0.0007) -[2023-10-09 03:32:33,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 173473792. Throughput: 0: 1698.2, 1: 1696.4. Samples: 43382930. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-09 03:32:33,975][87372] Avg episode reward: [(0, '6.980'), (1, '6.630')] -[2023-10-09 03:32:33,982][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000084672_86704128.pth... -[2023-10-09 03:32:34,022][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000083104_85098496.pth -[2023-10-09 03:32:34,032][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000084768_86802432.pth... -[2023-10-09 03:32:34,071][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000083168_85164032.pth -[2023-10-09 03:32:35,851][88326] Updated weights for policy 0, policy_version 84682 (0.0010) -[2023-10-09 03:32:36,228][88326] Updated weights for policy 0, policy_version 84692 (0.0010) -[2023-10-09 03:32:36,588][88326] Updated weights for policy 0, policy_version 84702 (0.0008) -[2023-10-09 03:32:37,571][88327] Updated weights for policy 1, policy_version 84770 (0.0009) -[2023-10-09 03:32:37,935][88327] Updated weights for policy 1, policy_version 84780 (0.0010) -[2023-10-09 03:32:38,295][88327] Updated weights for policy 1, policy_version 84790 (0.0009) -[2023-10-09 03:32:38,657][88327] Updated weights for policy 1, policy_version 84800 (0.0009) -[2023-10-09 03:32:38,974][87372] Fps is (10 sec: 16384.0, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 173572096. Throughput: 0: 1683.4, 1: 1707.4. Samples: 43393032. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-09 03:32:38,974][87372] Avg episode reward: [(0, '6.840'), (1, '7.030')] -[2023-10-09 03:32:40,588][88326] Updated weights for policy 0, policy_version 84712 (0.0007) -[2023-10-09 03:32:40,954][88326] Updated weights for policy 0, policy_version 84722 (0.0010) -[2023-10-09 03:32:41,322][88326] Updated weights for policy 0, policy_version 84732 (0.0008) -[2023-10-09 03:32:42,543][88327] Updated weights for policy 1, policy_version 84810 (0.0010) -[2023-10-09 03:32:42,903][88327] Updated weights for policy 1, policy_version 84820 (0.0010) -[2023-10-09 03:32:43,263][88327] Updated weights for policy 1, policy_version 84830 (0.0008) -[2023-10-09 03:32:43,974][87372] Fps is (10 sec: 16383.7, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 173637632. Throughput: 0: 1682.5, 1: 1709.8. Samples: 43413572. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-09 03:32:43,975][87372] Avg episode reward: [(0, '7.490'), (1, '6.930')] -[2023-10-09 03:32:45,524][88326] Updated weights for policy 0, policy_version 84742 (0.0008) -[2023-10-09 03:32:45,891][88326] Updated weights for policy 0, policy_version 84752 (0.0010) -[2023-10-09 03:32:46,256][88326] Updated weights for policy 0, policy_version 84762 (0.0008) -[2023-10-09 03:32:47,253][88327] Updated weights for policy 1, policy_version 84840 (0.0010) -[2023-10-09 03:32:47,620][88327] Updated weights for policy 1, policy_version 84850 (0.0009) -[2023-10-09 03:32:47,988][88327] Updated weights for policy 1, policy_version 84860 (0.0009) -[2023-10-09 03:32:48,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 173703168. Throughput: 0: 1697.0, 1: 1686.7. Samples: 43433360. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-09 03:32:48,974][87372] Avg episode reward: [(0, '7.520'), (1, '6.600')] -[2023-10-09 03:32:50,363][88326] Updated weights for policy 0, policy_version 84772 (0.0009) -[2023-10-09 03:32:50,735][88326] Updated weights for policy 0, policy_version 84782 (0.0008) -[2023-10-09 03:32:51,102][88326] Updated weights for policy 0, policy_version 84792 (0.0007) -[2023-10-09 03:32:52,052][88327] Updated weights for policy 1, policy_version 84870 (0.0009) -[2023-10-09 03:32:52,409][88327] Updated weights for policy 1, policy_version 84880 (0.0007) -[2023-10-09 03:32:52,780][88327] Updated weights for policy 1, policy_version 84890 (0.0009) -[2023-10-09 03:32:53,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 173768704. Throughput: 0: 1670.5, 1: 1718.1. Samples: 43444048. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-10-09 03:32:53,975][87372] Avg episode reward: [(0, '6.690'), (1, '7.050')] -[2023-10-09 03:32:54,996][88326] Updated weights for policy 0, policy_version 84802 (0.0008) -[2023-10-09 03:32:55,364][88326] Updated weights for policy 0, policy_version 84812 (0.0008) -[2023-10-09 03:32:55,733][88326] Updated weights for policy 0, policy_version 84822 (0.0010) -[2023-10-09 03:32:56,112][88326] Updated weights for policy 0, policy_version 84832 (0.0010) -[2023-10-09 03:32:56,798][88327] Updated weights for policy 1, policy_version 84900 (0.0011) -[2023-10-09 03:32:57,172][88327] Updated weights for policy 1, policy_version 84910 (0.0011) -[2023-10-09 03:32:57,529][88327] Updated weights for policy 1, policy_version 84920 (0.0009) -[2023-10-09 03:32:58,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 173834240. Throughput: 0: 1693.7, 1: 1698.3. Samples: 43464336. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-09 03:32:58,975][87372] Avg episode reward: [(0, '7.210'), (1, '7.260')] -[2023-10-09 03:33:00,051][88326] Updated weights for policy 0, policy_version 84842 (0.0010) -[2023-10-09 03:33:00,429][88326] Updated weights for policy 0, policy_version 84852 (0.0009) -[2023-10-09 03:33:00,787][88326] Updated weights for policy 0, policy_version 84862 (0.0009) -[2023-10-09 03:33:01,708][88327] Updated weights for policy 1, policy_version 84930 (0.0008) -[2023-10-09 03:33:02,076][88327] Updated weights for policy 1, policy_version 84940 (0.0010) -[2023-10-09 03:33:02,445][88327] Updated weights for policy 1, policy_version 84950 (0.0009) -[2023-10-09 03:33:02,797][88327] Updated weights for policy 1, policy_version 84960 (0.0007) -[2023-10-09 03:33:03,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 173899776. Throughput: 0: 1707.6, 1: 1677.6. Samples: 43484660. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-09 03:33:03,975][87372] Avg episode reward: [(0, '7.350'), (1, '6.920')] -[2023-10-09 03:33:04,821][88326] Updated weights for policy 0, policy_version 84872 (0.0008) -[2023-10-09 03:33:05,190][88326] Updated weights for policy 0, policy_version 84882 (0.0007) -[2023-10-09 03:33:05,567][88326] Updated weights for policy 0, policy_version 84892 (0.0008) -[2023-10-09 03:33:06,869][88327] Updated weights for policy 1, policy_version 84970 (0.0009) -[2023-10-09 03:33:07,225][88327] Updated weights for policy 1, policy_version 84980 (0.0008) -[2023-10-09 03:33:07,594][88327] Updated weights for policy 1, policy_version 84990 (0.0007) -[2023-10-09 03:33:08,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 173965312. Throughput: 0: 1680.8, 1: 1708.3. Samples: 43495068. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-09 03:33:08,975][87372] Avg episode reward: [(0, '6.370'), (1, '8.150')] -[2023-10-09 03:33:09,439][88326] Updated weights for policy 0, policy_version 84902 (0.0008) -[2023-10-09 03:33:09,815][88326] Updated weights for policy 0, policy_version 84912 (0.0008) -[2023-10-09 03:33:10,182][88326] Updated weights for policy 0, policy_version 84922 (0.0009) -[2023-10-09 03:33:11,481][88327] Updated weights for policy 1, policy_version 85000 (0.0009) -[2023-10-09 03:33:11,845][88327] Updated weights for policy 1, policy_version 85010 (0.0010) -[2023-10-09 03:33:12,207][88327] Updated weights for policy 1, policy_version 85020 (0.0007) -[2023-10-09 03:33:13,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 174030848. Throughput: 0: 1711.2, 1: 1684.8. Samples: 43515368. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-09 03:33:13,975][87372] Avg episode reward: [(0, '6.880'), (1, '7.340')] -[2023-10-09 03:33:14,073][88326] Updated weights for policy 0, policy_version 84932 (0.0009) -[2023-10-09 03:33:14,442][88326] Updated weights for policy 0, policy_version 84942 (0.0007) -[2023-10-09 03:33:14,816][88326] Updated weights for policy 0, policy_version 84952 (0.0009) -[2023-10-09 03:33:16,298][88327] Updated weights for policy 1, policy_version 85030 (0.0009) -[2023-10-09 03:33:16,659][88327] Updated weights for policy 1, policy_version 85040 (0.0010) -[2023-10-09 03:33:17,026][88327] Updated weights for policy 1, policy_version 85050 (0.0010) -[2023-10-09 03:33:18,828][88326] Updated weights for policy 0, policy_version 84962 (0.0009) -[2023-10-09 03:33:18,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 174096384. Throughput: 0: 1713.9, 1: 1689.2. Samples: 43536070. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-09 03:33:18,975][87372] Avg episode reward: [(0, '6.800'), (1, '7.230')] -[2023-10-09 03:33:19,191][88326] Updated weights for policy 0, policy_version 84972 (0.0010) -[2023-10-09 03:33:19,559][88326] Updated weights for policy 0, policy_version 84982 (0.0011) -[2023-10-09 03:33:19,930][88326] Updated weights for policy 0, policy_version 84992 (0.0010) -[2023-10-09 03:33:21,077][88327] Updated weights for policy 1, policy_version 85060 (0.0009) -[2023-10-09 03:33:21,435][88327] Updated weights for policy 1, policy_version 85070 (0.0007) -[2023-10-09 03:33:21,807][88327] Updated weights for policy 1, policy_version 85080 (0.0008) -[2023-10-09 03:33:23,927][88326] Updated weights for policy 0, policy_version 85002 (0.0007) -[2023-10-09 03:33:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 174161920. Throughput: 0: 1699.9, 1: 1703.5. Samples: 43546184. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-09 03:33:23,975][87372] Avg episode reward: [(0, '7.370'), (1, '7.860')] -[2023-10-09 03:33:24,295][88326] Updated weights for policy 0, policy_version 85012 (0.0009) -[2023-10-09 03:33:24,661][88326] Updated weights for policy 0, policy_version 85022 (0.0011) -[2023-10-09 03:33:25,784][88327] Updated weights for policy 1, policy_version 85090 (0.0007) -[2023-10-09 03:33:26,157][88327] Updated weights for policy 1, policy_version 85100 (0.0008) -[2023-10-09 03:33:26,525][88327] Updated weights for policy 1, policy_version 85110 (0.0007) -[2023-10-09 03:33:26,884][88327] Updated weights for policy 1, policy_version 85120 (0.0009) -[2023-10-09 03:33:28,783][88326] Updated weights for policy 0, policy_version 85032 (0.0008) -[2023-10-09 03:33:28,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 174227456. Throughput: 0: 1716.5, 1: 1675.7. Samples: 43566220. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-09 03:33:28,975][87372] Avg episode reward: [(0, '7.770'), (1, '8.020')] -[2023-10-09 03:33:29,158][88326] Updated weights for policy 0, policy_version 85042 (0.0009) -[2023-10-09 03:33:29,522][88326] Updated weights for policy 0, policy_version 85052 (0.0007) -[2023-10-09 03:33:31,042][88327] Updated weights for policy 1, policy_version 85130 (0.0008) -[2023-10-09 03:33:31,403][88327] Updated weights for policy 1, policy_version 85140 (0.0010) -[2023-10-09 03:33:31,768][88327] Updated weights for policy 1, policy_version 85150 (0.0009) -[2023-10-09 03:33:33,300][88326] Updated weights for policy 0, policy_version 85062 (0.0007) -[2023-10-09 03:33:33,671][88326] Updated weights for policy 0, policy_version 85072 (0.0008) -[2023-10-09 03:33:33,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 174292992. Throughput: 0: 1719.9, 1: 1696.9. Samples: 43587114. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-09 03:33:33,975][87372] Avg episode reward: [(0, '7.790'), (1, '7.720')] -[2023-10-09 03:33:34,042][88326] Updated weights for policy 0, policy_version 85082 (0.0007) -[2023-10-09 03:33:35,976][88327] Updated weights for policy 1, policy_version 85160 (0.0008) -[2023-10-09 03:33:36,334][88327] Updated weights for policy 1, policy_version 85170 (0.0009) -[2023-10-09 03:33:36,699][88327] Updated weights for policy 1, policy_version 85180 (0.0008) -[2023-10-09 03:33:37,939][88326] Updated weights for policy 0, policy_version 85092 (0.0009) -[2023-10-09 03:33:38,303][88326] Updated weights for policy 0, policy_version 85102 (0.0009) -[2023-10-09 03:33:38,670][88326] Updated weights for policy 0, policy_version 85112 (0.0008) -[2023-10-09 03:33:38,974][87372] Fps is (10 sec: 16384.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 174391296. Throughput: 0: 1717.4, 1: 1686.1. Samples: 43597208. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-09 03:33:38,975][87372] Avg episode reward: [(0, '7.910'), (1, '7.580')] -[2023-10-09 03:33:40,601][88327] Updated weights for policy 1, policy_version 85190 (0.0008) -[2023-10-09 03:33:40,971][88327] Updated weights for policy 1, policy_version 85200 (0.0009) -[2023-10-09 03:33:41,335][88327] Updated weights for policy 1, policy_version 85210 (0.0010) -[2023-10-09 03:33:42,862][88326] Updated weights for policy 0, policy_version 85122 (0.0007) -[2023-10-09 03:33:43,224][88326] Updated weights for policy 0, policy_version 85132 (0.0009) -[2023-10-09 03:33:43,598][88326] Updated weights for policy 0, policy_version 85142 (0.0009) -[2023-10-09 03:33:43,972][88326] Updated weights for policy 0, policy_version 85152 (0.0010) -[2023-10-09 03:33:43,974][87372] Fps is (10 sec: 16384.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 174456832. Throughput: 0: 1720.4, 1: 1685.2. Samples: 43617586. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-09 03:33:43,975][87372] Avg episode reward: [(0, '6.790'), (1, '7.140')] -[2023-10-09 03:33:45,143][88327] Updated weights for policy 1, policy_version 85220 (0.0008) -[2023-10-09 03:33:45,504][88327] Updated weights for policy 1, policy_version 85230 (0.0007) -[2023-10-09 03:33:45,862][88327] Updated weights for policy 1, policy_version 85240 (0.0007) -[2023-10-09 03:33:47,843][88326] Updated weights for policy 0, policy_version 85162 (0.0008) -[2023-10-09 03:33:48,214][88326] Updated weights for policy 0, policy_version 85172 (0.0007) -[2023-10-09 03:33:48,581][88326] Updated weights for policy 0, policy_version 85182 (0.0007) -[2023-10-09 03:33:48,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 174522368. Throughput: 0: 1698.7, 1: 1702.0. Samples: 43637690. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-09 03:33:48,974][87372] Avg episode reward: [(0, '7.340'), (1, '8.010')] -[2023-10-09 03:33:49,903][88327] Updated weights for policy 1, policy_version 85250 (0.0008) -[2023-10-09 03:33:50,266][88327] Updated weights for policy 1, policy_version 85260 (0.0007) -[2023-10-09 03:33:50,640][88327] Updated weights for policy 1, policy_version 85270 (0.0009) -[2023-10-09 03:33:50,997][88327] Updated weights for policy 1, policy_version 85280 (0.0009) -[2023-10-09 03:33:52,667][88326] Updated weights for policy 0, policy_version 85192 (0.0007) -[2023-10-09 03:33:53,042][88326] Updated weights for policy 0, policy_version 85202 (0.0007) -[2023-10-09 03:33:53,406][88326] Updated weights for policy 0, policy_version 85212 (0.0008) -[2023-10-09 03:33:53,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 174587904. Throughput: 0: 1720.3, 1: 1671.8. Samples: 43647712. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-09 03:33:53,975][87372] Avg episode reward: [(0, '7.200'), (1, '7.900')] -[2023-10-09 03:33:54,988][88327] Updated weights for policy 1, policy_version 85290 (0.0009) -[2023-10-09 03:33:55,342][88327] Updated weights for policy 1, policy_version 85300 (0.0008) -[2023-10-09 03:33:55,708][88327] Updated weights for policy 1, policy_version 85310 (0.0008) -[2023-10-09 03:33:57,408][88326] Updated weights for policy 0, policy_version 85222 (0.0009) -[2023-10-09 03:33:57,785][88326] Updated weights for policy 0, policy_version 85232 (0.0011) -[2023-10-09 03:33:58,143][88326] Updated weights for policy 0, policy_version 85242 (0.0010) -[2023-10-09 03:33:58,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 174653440. Throughput: 0: 1710.9, 1: 1694.2. Samples: 43668598. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-09 03:33:58,975][87372] Avg episode reward: [(0, '6.630'), (1, '7.920')] -[2023-10-09 03:33:59,758][88327] Updated weights for policy 1, policy_version 85320 (0.0007) -[2023-10-09 03:34:00,130][88327] Updated weights for policy 1, policy_version 85330 (0.0009) -[2023-10-09 03:34:00,485][88327] Updated weights for policy 1, policy_version 85340 (0.0009) -[2023-10-09 03:34:02,254][88326] Updated weights for policy 0, policy_version 85252 (0.0010) -[2023-10-09 03:34:02,610][88326] Updated weights for policy 0, policy_version 85262 (0.0010) -[2023-10-09 03:34:02,974][88326] Updated weights for policy 0, policy_version 85272 (0.0010) -[2023-10-09 03:34:03,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 174718976. Throughput: 0: 1681.1, 1: 1702.0. Samples: 43688314. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-09 03:34:03,975][87372] Avg episode reward: [(0, '7.190'), (1, '7.250')] -[2023-10-09 03:34:04,760][88327] Updated weights for policy 1, policy_version 85350 (0.0008) -[2023-10-09 03:34:05,126][88327] Updated weights for policy 1, policy_version 85360 (0.0011) -[2023-10-09 03:34:05,487][88327] Updated weights for policy 1, policy_version 85370 (0.0011) -[2023-10-09 03:34:07,091][88326] Updated weights for policy 0, policy_version 85282 (0.0009) -[2023-10-09 03:34:07,456][88326] Updated weights for policy 0, policy_version 85292 (0.0008) -[2023-10-09 03:34:07,826][88326] Updated weights for policy 0, policy_version 85302 (0.0009) -[2023-10-09 03:34:08,192][88326] Updated weights for policy 0, policy_version 85312 (0.0008) -[2023-10-09 03:34:08,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 174784512. Throughput: 0: 1708.8, 1: 1680.0. Samples: 43698680. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-09 03:34:08,975][87372] Avg episode reward: [(0, '6.850'), (1, '7.810')] -[2023-10-09 03:34:09,613][88327] Updated weights for policy 1, policy_version 85380 (0.0009) -[2023-10-09 03:34:09,975][88327] Updated weights for policy 1, policy_version 85390 (0.0009) -[2023-10-09 03:34:10,332][88327] Updated weights for policy 1, policy_version 85400 (0.0010) -[2023-10-09 03:34:12,164][88326] Updated weights for policy 0, policy_version 85322 (0.0007) -[2023-10-09 03:34:12,535][88326] Updated weights for policy 0, policy_version 85332 (0.0010) -[2023-10-09 03:34:12,901][88326] Updated weights for policy 0, policy_version 85342 (0.0010) -[2023-10-09 03:34:13,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 174850048. Throughput: 0: 1696.8, 1: 1702.6. Samples: 43719194. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-09 03:34:13,975][87372] Avg episode reward: [(0, '6.820'), (1, '6.880')] -[2023-10-09 03:34:14,408][88327] Updated weights for policy 1, policy_version 85410 (0.0010) -[2023-10-09 03:34:14,773][88327] Updated weights for policy 1, policy_version 85420 (0.0010) -[2023-10-09 03:34:15,142][88327] Updated weights for policy 1, policy_version 85430 (0.0010) -[2023-10-09 03:34:15,498][88327] Updated weights for policy 1, policy_version 85440 (0.0011) -[2023-10-09 03:34:16,823][88326] Updated weights for policy 0, policy_version 85352 (0.0009) -[2023-10-09 03:34:17,198][88326] Updated weights for policy 0, policy_version 85362 (0.0009) -[2023-10-09 03:34:17,580][88326] Updated weights for policy 0, policy_version 85372 (0.0008) -[2023-10-09 03:34:18,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 174915584. Throughput: 0: 1675.2, 1: 1703.8. Samples: 43739168. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-09 03:34:18,975][87372] Avg episode reward: [(0, '7.050'), (1, '7.140')] -[2023-10-09 03:34:19,539][88327] Updated weights for policy 1, policy_version 85450 (0.0009) -[2023-10-09 03:34:19,908][88327] Updated weights for policy 1, policy_version 85460 (0.0007) -[2023-10-09 03:34:20,272][88327] Updated weights for policy 1, policy_version 85470 (0.0007) -[2023-10-09 03:34:21,662][88326] Updated weights for policy 0, policy_version 85382 (0.0008) -[2023-10-09 03:34:22,028][88326] Updated weights for policy 0, policy_version 85392 (0.0009) -[2023-10-09 03:34:22,399][88326] Updated weights for policy 0, policy_version 85402 (0.0009) -[2023-10-09 03:34:23,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 174981120. Throughput: 0: 1700.8, 1: 1683.9. Samples: 43749520. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-09 03:34:23,975][87372] Avg episode reward: [(0, '6.510'), (1, '7.260')] -[2023-10-09 03:34:24,092][88327] Updated weights for policy 1, policy_version 85480 (0.0011) -[2023-10-09 03:34:24,455][88327] Updated weights for policy 1, policy_version 85490 (0.0011) -[2023-10-09 03:34:24,815][88327] Updated weights for policy 1, policy_version 85500 (0.0009) -[2023-10-09 03:34:26,443][88326] Updated weights for policy 0, policy_version 85412 (0.0007) -[2023-10-09 03:34:26,801][88326] Updated weights for policy 0, policy_version 85422 (0.0009) -[2023-10-09 03:34:27,171][88326] Updated weights for policy 0, policy_version 85432 (0.0007) -[2023-10-09 03:34:28,804][88327] Updated weights for policy 1, policy_version 85510 (0.0007) -[2023-10-09 03:34:28,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 175046656. Throughput: 0: 1678.0, 1: 1702.3. Samples: 43769696. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-09 03:34:28,974][87372] Avg episode reward: [(0, '6.890'), (1, '7.440')] -[2023-10-09 03:34:29,176][88327] Updated weights for policy 1, policy_version 85520 (0.0010) -[2023-10-09 03:34:29,549][88327] Updated weights for policy 1, policy_version 85530 (0.0010) -[2023-10-09 03:34:31,248][88326] Updated weights for policy 0, policy_version 85442 (0.0008) -[2023-10-09 03:34:31,628][88326] Updated weights for policy 0, policy_version 85452 (0.0009) -[2023-10-09 03:34:31,998][88326] Updated weights for policy 0, policy_version 85462 (0.0007) -[2023-10-09 03:34:32,375][88326] Updated weights for policy 0, policy_version 85472 (0.0008) -[2023-10-09 03:34:33,533][88327] Updated weights for policy 1, policy_version 85540 (0.0010) -[2023-10-09 03:34:33,902][88327] Updated weights for policy 1, policy_version 85550 (0.0007) -[2023-10-09 03:34:33,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 175112192. Throughput: 0: 1684.2, 1: 1703.2. Samples: 43790126. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-09 03:34:33,975][87372] Avg episode reward: [(0, '7.340'), (1, '8.420')] -[2023-10-09 03:34:33,987][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000085472_87523328.pth... -[2023-10-09 03:34:34,017][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000083872_85884928.pth -[2023-10-09 03:34:34,266][88327] Updated weights for policy 1, policy_version 85560 (0.0009) -[2023-10-09 03:34:34,559][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000085568_87621632.pth... -[2023-10-09 03:34:34,598][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000083968_85983232.pth -[2023-10-09 03:34:36,376][88326] Updated weights for policy 0, policy_version 85482 (0.0007) -[2023-10-09 03:34:36,750][88326] Updated weights for policy 0, policy_version 85492 (0.0007) -[2023-10-09 03:34:37,120][88326] Updated weights for policy 0, policy_version 85502 (0.0008) -[2023-10-09 03:34:38,421][88327] Updated weights for policy 1, policy_version 85570 (0.0008) -[2023-10-09 03:34:38,781][88327] Updated weights for policy 1, policy_version 85580 (0.0008) -[2023-10-09 03:34:38,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 175177728. Throughput: 0: 1691.8, 1: 1700.5. Samples: 43800366. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-09 03:34:38,975][87372] Avg episode reward: [(0, '7.620'), (1, '7.350')] -[2023-10-09 03:34:39,156][88327] Updated weights for policy 1, policy_version 85590 (0.0008) -[2023-10-09 03:34:39,523][88327] Updated weights for policy 1, policy_version 85600 (0.0008) -[2023-10-09 03:34:41,130][88326] Updated weights for policy 0, policy_version 85512 (0.0009) -[2023-10-09 03:34:41,503][88326] Updated weights for policy 0, policy_version 85522 (0.0009) -[2023-10-09 03:34:41,863][88326] Updated weights for policy 0, policy_version 85532 (0.0009) -[2023-10-09 03:34:43,466][88327] Updated weights for policy 1, policy_version 85610 (0.0009) -[2023-10-09 03:34:43,828][88327] Updated weights for policy 1, policy_version 85620 (0.0011) -[2023-10-09 03:34:43,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 175243264. Throughput: 0: 1666.6, 1: 1702.3. Samples: 43820202. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-09 03:34:43,975][87372] Avg episode reward: [(0, '7.170'), (1, '7.460')] -[2023-10-09 03:34:44,189][88327] Updated weights for policy 1, policy_version 85630 (0.0008) -[2023-10-09 03:34:46,172][88326] Updated weights for policy 0, policy_version 85542 (0.0010) -[2023-10-09 03:34:46,554][88326] Updated weights for policy 0, policy_version 85552 (0.0008) -[2023-10-09 03:34:46,917][88326] Updated weights for policy 0, policy_version 85562 (0.0009) -[2023-10-09 03:34:48,110][88327] Updated weights for policy 1, policy_version 85640 (0.0009) -[2023-10-09 03:34:48,474][88327] Updated weights for policy 1, policy_version 85650 (0.0008) -[2023-10-09 03:34:48,839][88327] Updated weights for policy 1, policy_version 85660 (0.0008) -[2023-10-09 03:34:48,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 175308800. Throughput: 0: 1693.9, 1: 1698.9. Samples: 43840990. Policy #0 lag: (min: 17.0, avg: 20.2, max: 49.0) -[2023-10-09 03:34:48,974][87372] Avg episode reward: [(0, '7.770'), (1, '7.730')] -[2023-10-09 03:34:50,948][88326] Updated weights for policy 0, policy_version 85572 (0.0007) -[2023-10-09 03:34:51,323][88326] Updated weights for policy 0, policy_version 85582 (0.0007) -[2023-10-09 03:34:51,687][88326] Updated weights for policy 0, policy_version 85592 (0.0009) -[2023-10-09 03:34:52,849][88327] Updated weights for policy 1, policy_version 85670 (0.0007) -[2023-10-09 03:34:53,219][88327] Updated weights for policy 1, policy_version 85680 (0.0008) -[2023-10-09 03:34:53,577][88327] Updated weights for policy 1, policy_version 85690 (0.0009) -[2023-10-09 03:34:53,974][87372] Fps is (10 sec: 16384.3, 60 sec: 13653.4, 300 sec: 13662.6). Total num frames: 175407104. Throughput: 0: 1689.3, 1: 1707.7. Samples: 43851544. Policy #0 lag: (min: 17.0, avg: 20.2, max: 49.0) -[2023-10-09 03:34:53,975][87372] Avg episode reward: [(0, '7.550'), (1, '8.610')] -[2023-10-09 03:34:55,735][88326] Updated weights for policy 0, policy_version 85602 (0.0010) -[2023-10-09 03:34:56,105][88326] Updated weights for policy 0, policy_version 85612 (0.0010) -[2023-10-09 03:34:56,476][88326] Updated weights for policy 0, policy_version 85622 (0.0009) -[2023-10-09 03:34:56,844][88326] Updated weights for policy 0, policy_version 85632 (0.0007) -[2023-10-09 03:34:57,608][88327] Updated weights for policy 1, policy_version 85700 (0.0008) -[2023-10-09 03:34:57,969][88327] Updated weights for policy 1, policy_version 85710 (0.0009) -[2023-10-09 03:34:58,327][88327] Updated weights for policy 1, policy_version 85720 (0.0007) -[2023-10-09 03:34:58,974][87372] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 175472640. Throughput: 0: 1675.5, 1: 1711.6. Samples: 43871612. Policy #0 lag: (min: 17.0, avg: 20.2, max: 49.0) -[2023-10-09 03:34:58,975][87372] Avg episode reward: [(0, '7.870'), (1, '7.550')] -[2023-10-09 03:35:00,773][88326] Updated weights for policy 0, policy_version 85642 (0.0008) -[2023-10-09 03:35:01,153][88326] Updated weights for policy 0, policy_version 85652 (0.0010) -[2023-10-09 03:35:01,517][88326] Updated weights for policy 0, policy_version 85662 (0.0008) -[2023-10-09 03:35:02,254][88327] Updated weights for policy 1, policy_version 85730 (0.0009) -[2023-10-09 03:35:02,622][88327] Updated weights for policy 1, policy_version 85740 (0.0007) -[2023-10-09 03:35:02,986][88327] Updated weights for policy 1, policy_version 85750 (0.0007) -[2023-10-09 03:35:03,347][88327] Updated weights for policy 1, policy_version 85760 (0.0009) -[2023-10-09 03:35:03,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 175538176. Throughput: 0: 1700.4, 1: 1690.4. Samples: 43891756. Policy #0 lag: (min: 17.0, avg: 20.2, max: 49.0) -[2023-10-09 03:35:03,975][87372] Avg episode reward: [(0, '7.440'), (1, '7.280')] -[2023-10-09 03:35:05,597][88326] Updated weights for policy 0, policy_version 85672 (0.0009) -[2023-10-09 03:35:05,964][88326] Updated weights for policy 0, policy_version 85682 (0.0010) -[2023-10-09 03:35:06,344][88326] Updated weights for policy 0, policy_version 85692 (0.0007) -[2023-10-09 03:35:07,493][88327] Updated weights for policy 1, policy_version 85770 (0.0010) -[2023-10-09 03:35:07,852][88327] Updated weights for policy 1, policy_version 85780 (0.0010) -[2023-10-09 03:35:08,209][88327] Updated weights for policy 1, policy_version 85790 (0.0011) -[2023-10-09 03:35:08,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 175603712. Throughput: 0: 1678.6, 1: 1715.7. Samples: 43902262. Policy #0 lag: (min: 17.0, avg: 20.2, max: 49.0) -[2023-10-09 03:35:08,975][87372] Avg episode reward: [(0, '8.080'), (1, '7.250')] -[2023-10-09 03:35:10,339][88326] Updated weights for policy 0, policy_version 85702 (0.0009) -[2023-10-09 03:35:10,704][88326] Updated weights for policy 0, policy_version 85712 (0.0008) -[2023-10-09 03:35:11,071][88326] Updated weights for policy 0, policy_version 85722 (0.0007) -[2023-10-09 03:35:12,522][88327] Updated weights for policy 1, policy_version 85800 (0.0008) -[2023-10-09 03:35:12,877][88327] Updated weights for policy 1, policy_version 85810 (0.0008) -[2023-10-09 03:35:13,242][88327] Updated weights for policy 1, policy_version 85820 (0.0008) -[2023-10-09 03:35:13,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 175669248. Throughput: 0: 1692.2, 1: 1707.5. Samples: 43922680. Policy #0 lag: (min: 17.0, avg: 20.2, max: 49.0) -[2023-10-09 03:35:13,975][87372] Avg episode reward: [(0, '7.500'), (1, '7.730')] -[2023-10-09 03:35:15,197][88326] Updated weights for policy 0, policy_version 85732 (0.0009) -[2023-10-09 03:35:15,569][88326] Updated weights for policy 0, policy_version 85742 (0.0011) -[2023-10-09 03:35:15,950][88326] Updated weights for policy 0, policy_version 85752 (0.0009) -[2023-10-09 03:35:17,257][88327] Updated weights for policy 1, policy_version 85830 (0.0008) -[2023-10-09 03:35:17,616][88327] Updated weights for policy 1, policy_version 85840 (0.0010) -[2023-10-09 03:35:17,983][88327] Updated weights for policy 1, policy_version 85850 (0.0009) -[2023-10-09 03:35:18,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 175734784. Throughput: 0: 1701.0, 1: 1682.8. Samples: 43942398. Policy #0 lag: (min: 17.0, avg: 20.2, max: 49.0) -[2023-10-09 03:35:18,975][87372] Avg episode reward: [(0, '7.390'), (1, '7.620')] -[2023-10-09 03:35:19,825][88326] Updated weights for policy 0, policy_version 85762 (0.0007) -[2023-10-09 03:35:20,185][88326] Updated weights for policy 0, policy_version 85772 (0.0008) -[2023-10-09 03:35:20,555][88326] Updated weights for policy 0, policy_version 85782 (0.0009) -[2023-10-09 03:35:20,929][88326] Updated weights for policy 0, policy_version 85792 (0.0009) -[2023-10-09 03:35:22,032][88327] Updated weights for policy 1, policy_version 85860 (0.0010) -[2023-10-09 03:35:22,396][88327] Updated weights for policy 1, policy_version 85870 (0.0008) -[2023-10-09 03:35:22,754][88327] Updated weights for policy 1, policy_version 85880 (0.0007) -[2023-10-09 03:35:23,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 175800320. Throughput: 0: 1673.0, 1: 1709.4. Samples: 43952576. Policy #0 lag: (min: 17.0, avg: 20.2, max: 49.0) -[2023-10-09 03:35:23,975][87372] Avg episode reward: [(0, '7.050'), (1, '7.700')] -[2023-10-09 03:35:24,956][88326] Updated weights for policy 0, policy_version 85802 (0.0008) -[2023-10-09 03:35:25,319][88326] Updated weights for policy 0, policy_version 85812 (0.0009) -[2023-10-09 03:35:25,701][88326] Updated weights for policy 0, policy_version 85822 (0.0008) -[2023-10-09 03:35:26,602][88327] Updated weights for policy 1, policy_version 85890 (0.0008) -[2023-10-09 03:35:26,973][88327] Updated weights for policy 1, policy_version 85900 (0.0007) -[2023-10-09 03:35:27,332][88327] Updated weights for policy 1, policy_version 85910 (0.0007) -[2023-10-09 03:35:27,699][88327] Updated weights for policy 1, policy_version 85920 (0.0009) -[2023-10-09 03:35:28,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 175865856. Throughput: 0: 1701.0, 1: 1692.4. Samples: 43972904. Policy #0 lag: (min: 17.0, avg: 20.2, max: 49.0) -[2023-10-09 03:35:28,975][87372] Avg episode reward: [(0, '7.140'), (1, '8.060')] -[2023-10-09 03:35:29,734][88326] Updated weights for policy 0, policy_version 85832 (0.0007) -[2023-10-09 03:35:30,105][88326] Updated weights for policy 0, policy_version 85842 (0.0007) -[2023-10-09 03:35:30,476][88326] Updated weights for policy 0, policy_version 85852 (0.0011) -[2023-10-09 03:35:31,802][88327] Updated weights for policy 1, policy_version 85930 (0.0009) -[2023-10-09 03:35:32,165][88327] Updated weights for policy 1, policy_version 85940 (0.0009) -[2023-10-09 03:35:32,531][88327] Updated weights for policy 1, policy_version 85950 (0.0010) -[2023-10-09 03:35:33,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 175931392. Throughput: 0: 1701.2, 1: 1682.3. Samples: 43993250. Policy #0 lag: (min: 17.0, avg: 20.2, max: 49.0) -[2023-10-09 03:35:33,975][87372] Avg episode reward: [(0, '7.180'), (1, '7.470')] -[2023-10-09 03:35:34,664][88326] Updated weights for policy 0, policy_version 85862 (0.0008) -[2023-10-09 03:35:35,044][88326] Updated weights for policy 0, policy_version 85872 (0.0008) -[2023-10-09 03:35:35,425][88326] Updated weights for policy 0, policy_version 85882 (0.0010) -[2023-10-09 03:35:36,669][88327] Updated weights for policy 1, policy_version 85960 (0.0007) -[2023-10-09 03:35:37,031][88327] Updated weights for policy 1, policy_version 85970 (0.0008) -[2023-10-09 03:35:37,397][88327] Updated weights for policy 1, policy_version 85980 (0.0007) -[2023-10-09 03:35:38,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 175996928. Throughput: 0: 1674.0, 1: 1701.2. Samples: 44003428. Policy #0 lag: (min: 17.0, avg: 20.2, max: 49.0) -[2023-10-09 03:35:38,975][87372] Avg episode reward: [(0, '7.650'), (1, '6.870')] -[2023-10-09 03:35:39,457][88326] Updated weights for policy 0, policy_version 85892 (0.0008) -[2023-10-09 03:35:39,835][88326] Updated weights for policy 0, policy_version 85902 (0.0009) -[2023-10-09 03:35:40,200][88326] Updated weights for policy 0, policy_version 85912 (0.0009) -[2023-10-09 03:35:41,378][88327] Updated weights for policy 1, policy_version 85990 (0.0008) -[2023-10-09 03:35:41,742][88327] Updated weights for policy 1, policy_version 86000 (0.0008) -[2023-10-09 03:35:42,111][88327] Updated weights for policy 1, policy_version 86010 (0.0009) -[2023-10-09 03:35:43,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 176062464. Throughput: 0: 1691.3, 1: 1678.2. Samples: 44023240. Policy #0 lag: (min: 10.0, avg: 10.1, max: 16.0) -[2023-10-09 03:35:43,975][87372] Avg episode reward: [(0, '7.720'), (1, '6.530')] -[2023-10-09 03:35:44,218][88326] Updated weights for policy 0, policy_version 85922 (0.0010) -[2023-10-09 03:35:44,585][88326] Updated weights for policy 0, policy_version 85932 (0.0009) -[2023-10-09 03:35:44,948][88326] Updated weights for policy 0, policy_version 85942 (0.0008) -[2023-10-09 03:35:45,309][88326] Updated weights for policy 0, policy_version 85952 (0.0009) -[2023-10-09 03:35:46,181][88327] Updated weights for policy 1, policy_version 86020 (0.0009) -[2023-10-09 03:35:46,585][88327] Updated weights for policy 1, policy_version 86030 (0.0007) -[2023-10-09 03:35:46,951][88327] Updated weights for policy 1, policy_version 86040 (0.0007) -[2023-10-09 03:35:48,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 176128000. Throughput: 0: 1693.2, 1: 1690.7. Samples: 44044028. Policy #0 lag: (min: 10.0, avg: 10.1, max: 16.0) -[2023-10-09 03:35:48,975][87372] Avg episode reward: [(0, '7.120'), (1, '6.840')] -[2023-10-09 03:35:49,287][88326] Updated weights for policy 0, policy_version 85962 (0.0009) -[2023-10-09 03:35:49,660][88326] Updated weights for policy 0, policy_version 85972 (0.0009) -[2023-10-09 03:35:50,027][88326] Updated weights for policy 0, policy_version 85982 (0.0008) -[2023-10-09 03:35:50,828][88327] Updated weights for policy 1, policy_version 86050 (0.0009) -[2023-10-09 03:35:51,195][88327] Updated weights for policy 1, policy_version 86060 (0.0010) -[2023-10-09 03:35:51,569][88327] Updated weights for policy 1, policy_version 86070 (0.0009) -[2023-10-09 03:35:51,930][88327] Updated weights for policy 1, policy_version 86080 (0.0008) -[2023-10-09 03:35:53,929][88326] Updated weights for policy 0, policy_version 85992 (0.0009) -[2023-10-09 03:35:53,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 176193536. Throughput: 0: 1686.4, 1: 1689.5. Samples: 44054178. Policy #0 lag: (min: 10.0, avg: 10.1, max: 16.0) -[2023-10-09 03:35:53,974][87372] Avg episode reward: [(0, '7.420'), (1, '6.670')] -[2023-10-09 03:35:54,298][88326] Updated weights for policy 0, policy_version 86002 (0.0008) -[2023-10-09 03:35:54,674][88326] Updated weights for policy 0, policy_version 86012 (0.0007) -[2023-10-09 03:35:56,055][88327] Updated weights for policy 1, policy_version 86090 (0.0007) -[2023-10-09 03:35:56,424][88327] Updated weights for policy 1, policy_version 86100 (0.0008) -[2023-10-09 03:35:56,790][88327] Updated weights for policy 1, policy_version 86110 (0.0009) -[2023-10-09 03:35:58,518][88326] Updated weights for policy 0, policy_version 86022 (0.0007) -[2023-10-09 03:35:58,894][88326] Updated weights for policy 0, policy_version 86032 (0.0008) -[2023-10-09 03:35:58,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 176259072. Throughput: 0: 1701.2, 1: 1672.2. Samples: 44074482. Policy #0 lag: (min: 10.0, avg: 10.1, max: 16.0) -[2023-10-09 03:35:58,975][87372] Avg episode reward: [(0, '6.740'), (1, '7.240')] -[2023-10-09 03:35:59,256][88326] Updated weights for policy 0, policy_version 86042 (0.0009) -[2023-10-09 03:36:00,709][88327] Updated weights for policy 1, policy_version 86120 (0.0008) -[2023-10-09 03:36:01,069][88327] Updated weights for policy 1, policy_version 86130 (0.0007) -[2023-10-09 03:36:01,420][88327] Updated weights for policy 1, policy_version 86140 (0.0007) -[2023-10-09 03:36:03,245][88326] Updated weights for policy 0, policy_version 86052 (0.0009) -[2023-10-09 03:36:03,615][88326] Updated weights for policy 0, policy_version 86062 (0.0007) -[2023-10-09 03:36:03,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 176324608. Throughput: 0: 1702.7, 1: 1700.3. Samples: 44095532. Policy #0 lag: (min: 10.0, avg: 10.1, max: 16.0) -[2023-10-09 03:36:03,975][87372] Avg episode reward: [(0, '6.370'), (1, '7.530')] -[2023-10-09 03:36:03,989][88326] Updated weights for policy 0, policy_version 86072 (0.0007) -[2023-10-09 03:36:05,462][88327] Updated weights for policy 1, policy_version 86150 (0.0010) -[2023-10-09 03:36:05,829][88327] Updated weights for policy 1, policy_version 86160 (0.0011) -[2023-10-09 03:36:06,201][88327] Updated weights for policy 1, policy_version 86170 (0.0007) -[2023-10-09 03:36:08,114][88326] Updated weights for policy 0, policy_version 86082 (0.0009) -[2023-10-09 03:36:08,488][88326] Updated weights for policy 0, policy_version 86092 (0.0008) -[2023-10-09 03:36:08,861][88326] Updated weights for policy 0, policy_version 86102 (0.0009) -[2023-10-09 03:36:08,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 176390144. Throughput: 0: 1706.4, 1: 1683.4. Samples: 44105118. Policy #0 lag: (min: 10.0, avg: 10.1, max: 16.0) -[2023-10-09 03:36:08,975][87372] Avg episode reward: [(0, '6.670'), (1, '7.980')] -[2023-10-09 03:36:09,219][88326] Updated weights for policy 0, policy_version 86112 (0.0010) -[2023-10-09 03:36:10,216][88327] Updated weights for policy 1, policy_version 86180 (0.0008) -[2023-10-09 03:36:10,578][88327] Updated weights for policy 1, policy_version 86190 (0.0008) -[2023-10-09 03:36:10,938][88327] Updated weights for policy 1, policy_version 86200 (0.0010) -[2023-10-09 03:36:13,437][88326] Updated weights for policy 0, policy_version 86122 (0.0009) -[2023-10-09 03:36:13,806][88326] Updated weights for policy 0, policy_version 86132 (0.0009) -[2023-10-09 03:36:13,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 176455680. Throughput: 0: 1703.6, 1: 1694.4. Samples: 44125814. Policy #0 lag: (min: 10.0, avg: 10.1, max: 16.0) -[2023-10-09 03:36:13,974][87372] Avg episode reward: [(0, '6.910'), (1, '7.510')] -[2023-10-09 03:36:14,182][88326] Updated weights for policy 0, policy_version 86142 (0.0009) -[2023-10-09 03:36:14,841][88327] Updated weights for policy 1, policy_version 86210 (0.0008) -[2023-10-09 03:36:15,200][88327] Updated weights for policy 1, policy_version 86220 (0.0008) -[2023-10-09 03:36:15,566][88327] Updated weights for policy 1, policy_version 86230 (0.0010) -[2023-10-09 03:36:15,928][88327] Updated weights for policy 1, policy_version 86240 (0.0009) -[2023-10-09 03:36:18,170][88326] Updated weights for policy 0, policy_version 86152 (0.0007) -[2023-10-09 03:36:18,541][88326] Updated weights for policy 0, policy_version 86162 (0.0007) -[2023-10-09 03:36:18,905][88326] Updated weights for policy 0, policy_version 86172 (0.0011) -[2023-10-09 03:36:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 176521216. Throughput: 0: 1692.0, 1: 1716.4. Samples: 44146628. Policy #0 lag: (min: 10.0, avg: 10.1, max: 16.0) -[2023-10-09 03:36:18,975][87372] Avg episode reward: [(0, '7.320'), (1, '7.420')] -[2023-10-09 03:36:19,639][88327] Updated weights for policy 1, policy_version 86250 (0.0009) -[2023-10-09 03:36:20,015][88327] Updated weights for policy 1, policy_version 86260 (0.0009) -[2023-10-09 03:36:20,378][88327] Updated weights for policy 1, policy_version 86270 (0.0008) -[2023-10-09 03:36:23,096][88326] Updated weights for policy 0, policy_version 86182 (0.0008) -[2023-10-09 03:36:23,479][88326] Updated weights for policy 0, policy_version 86192 (0.0008) -[2023-10-09 03:36:23,854][88326] Updated weights for policy 0, policy_version 86202 (0.0007) -[2023-10-09 03:36:23,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 176586752. Throughput: 0: 1706.7, 1: 1688.7. Samples: 44156220. Policy #0 lag: (min: 10.0, avg: 10.1, max: 16.0) -[2023-10-09 03:36:23,975][87372] Avg episode reward: [(0, '7.930'), (1, '8.260')] -[2023-10-09 03:36:24,400][88327] Updated weights for policy 1, policy_version 86280 (0.0008) -[2023-10-09 03:36:24,756][88327] Updated weights for policy 1, policy_version 86290 (0.0008) -[2023-10-09 03:36:25,131][88327] Updated weights for policy 1, policy_version 86300 (0.0008) -[2023-10-09 03:36:27,795][88326] Updated weights for policy 0, policy_version 86212 (0.0008) -[2023-10-09 03:36:28,153][88326] Updated weights for policy 0, policy_version 86222 (0.0012) -[2023-10-09 03:36:28,520][88326] Updated weights for policy 0, policy_version 86232 (0.0010) -[2023-10-09 03:36:28,974][87372] Fps is (10 sec: 16383.7, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 176685056. Throughput: 0: 1707.2, 1: 1711.9. Samples: 44177100. Policy #0 lag: (min: 10.0, avg: 10.1, max: 16.0) -[2023-10-09 03:36:28,975][87372] Avg episode reward: [(0, '8.610'), (1, '7.490')] -[2023-10-09 03:36:28,977][88088] Saving new best policy, reward=8.610! -[2023-10-09 03:36:29,324][88327] Updated weights for policy 1, policy_version 86310 (0.0009) -[2023-10-09 03:36:29,699][88327] Updated weights for policy 1, policy_version 86320 (0.0008) -[2023-10-09 03:36:30,056][88327] Updated weights for policy 1, policy_version 86330 (0.0007) -[2023-10-09 03:36:32,576][88326] Updated weights for policy 0, policy_version 86242 (0.0008) -[2023-10-09 03:36:32,947][88326] Updated weights for policy 0, policy_version 86252 (0.0010) -[2023-10-09 03:36:33,326][88326] Updated weights for policy 0, policy_version 86262 (0.0010) -[2023-10-09 03:36:33,700][88326] Updated weights for policy 0, policy_version 86272 (0.0009) -[2023-10-09 03:36:33,974][87372] Fps is (10 sec: 16384.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 176750592. Throughput: 0: 1684.4, 1: 1717.0. Samples: 44197092. Policy #0 lag: (min: 13.0, avg: 15.8, max: 43.0) -[2023-10-09 03:36:33,975][87372] Avg episode reward: [(0, '7.880'), (1, '7.250')] -[2023-10-09 03:36:33,982][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000086272_88342528.pth... -[2023-10-09 03:36:34,018][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000084672_86704128.pth -[2023-10-09 03:36:34,053][88327] Updated weights for policy 1, policy_version 86340 (0.0009) -[2023-10-09 03:36:34,456][88327] Updated weights for policy 1, policy_version 86350 (0.0007) -[2023-10-09 03:36:34,825][88327] Updated weights for policy 1, policy_version 86360 (0.0007) -[2023-10-09 03:36:35,115][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000086368_88440832.pth... -[2023-10-09 03:36:35,153][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000084768_86802432.pth -[2023-10-09 03:36:37,678][88326] Updated weights for policy 0, policy_version 86282 (0.0008) -[2023-10-09 03:36:38,038][88326] Updated weights for policy 0, policy_version 86292 (0.0007) -[2023-10-09 03:36:38,412][88326] Updated weights for policy 0, policy_version 86302 (0.0007) -[2023-10-09 03:36:38,947][88327] Updated weights for policy 1, policy_version 86370 (0.0008) -[2023-10-09 03:36:38,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 176816128. Throughput: 0: 1698.3, 1: 1690.5. Samples: 44206672. Policy #0 lag: (min: 13.0, avg: 15.8, max: 43.0) -[2023-10-09 03:36:38,974][87372] Avg episode reward: [(0, '7.890'), (1, '6.570')] -[2023-10-09 03:36:39,305][88327] Updated weights for policy 1, policy_version 86380 (0.0010) -[2023-10-09 03:36:39,670][88327] Updated weights for policy 1, policy_version 86390 (0.0009) -[2023-10-09 03:36:40,032][88327] Updated weights for policy 1, policy_version 86400 (0.0008) -[2023-10-09 03:36:42,495][88326] Updated weights for policy 0, policy_version 86312 (0.0007) -[2023-10-09 03:36:42,860][88326] Updated weights for policy 0, policy_version 86322 (0.0008) -[2023-10-09 03:36:43,231][88326] Updated weights for policy 0, policy_version 86332 (0.0009) -[2023-10-09 03:36:43,934][88327] Updated weights for policy 1, policy_version 86410 (0.0011) -[2023-10-09 03:36:43,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 176881664. Throughput: 0: 1689.7, 1: 1714.8. Samples: 44227684. Policy #0 lag: (min: 13.0, avg: 15.8, max: 43.0) -[2023-10-09 03:36:43,975][87372] Avg episode reward: [(0, '8.400'), (1, '7.140')] -[2023-10-09 03:36:44,303][88327] Updated weights for policy 1, policy_version 86420 (0.0011) -[2023-10-09 03:36:44,661][88327] Updated weights for policy 1, policy_version 86430 (0.0009) -[2023-10-09 03:36:47,379][88326] Updated weights for policy 0, policy_version 86342 (0.0010) -[2023-10-09 03:36:47,762][88326] Updated weights for policy 0, policy_version 86352 (0.0011) -[2023-10-09 03:36:48,124][88326] Updated weights for policy 0, policy_version 86362 (0.0011) -[2023-10-09 03:36:48,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 176947200. Throughput: 0: 1659.8, 1: 1710.3. Samples: 44247186. Policy #0 lag: (min: 13.0, avg: 15.8, max: 43.0) -[2023-10-09 03:36:48,975][87372] Avg episode reward: [(0, '7.630'), (1, '7.260')] -[2023-10-09 03:36:48,989][88327] Updated weights for policy 1, policy_version 86440 (0.0011) -[2023-10-09 03:36:49,359][88327] Updated weights for policy 1, policy_version 86450 (0.0009) -[2023-10-09 03:36:49,719][88327] Updated weights for policy 1, policy_version 86460 (0.0008) -[2023-10-09 03:36:52,249][88326] Updated weights for policy 0, policy_version 86372 (0.0007) -[2023-10-09 03:36:52,623][88326] Updated weights for policy 0, policy_version 86382 (0.0007) -[2023-10-09 03:36:52,989][88326] Updated weights for policy 0, policy_version 86392 (0.0009) -[2023-10-09 03:36:53,638][88327] Updated weights for policy 1, policy_version 86470 (0.0009) -[2023-10-09 03:36:53,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 177012736. Throughput: 0: 1683.6, 1: 1700.1. Samples: 44257382. Policy #0 lag: (min: 13.0, avg: 15.8, max: 43.0) -[2023-10-09 03:36:53,975][87372] Avg episode reward: [(0, '7.260'), (1, '7.390')] -[2023-10-09 03:36:54,000][88327] Updated weights for policy 1, policy_version 86480 (0.0010) -[2023-10-09 03:36:54,370][88327] Updated weights for policy 1, policy_version 86490 (0.0009) -[2023-10-09 03:36:56,924][88326] Updated weights for policy 0, policy_version 86402 (0.0008) -[2023-10-09 03:36:57,287][88326] Updated weights for policy 0, policy_version 86412 (0.0010) -[2023-10-09 03:36:57,671][88326] Updated weights for policy 0, policy_version 86422 (0.0007) -[2023-10-09 03:36:58,043][88326] Updated weights for policy 0, policy_version 86432 (0.0009) -[2023-10-09 03:36:58,536][88327] Updated weights for policy 1, policy_version 86500 (0.0010) -[2023-10-09 03:36:58,904][88327] Updated weights for policy 1, policy_version 86510 (0.0010) -[2023-10-09 03:36:58,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 177078272. Throughput: 0: 1679.8, 1: 1698.0. Samples: 44277814. Policy #0 lag: (min: 13.0, avg: 15.8, max: 43.0) -[2023-10-09 03:36:58,974][87372] Avg episode reward: [(0, '6.610'), (1, '7.640')] -[2023-10-09 03:36:59,258][88327] Updated weights for policy 1, policy_version 86520 (0.0009) -[2023-10-09 03:37:02,032][88326] Updated weights for policy 0, policy_version 86442 (0.0009) -[2023-10-09 03:37:02,395][88326] Updated weights for policy 0, policy_version 86452 (0.0009) -[2023-10-09 03:37:02,771][88326] Updated weights for policy 0, policy_version 86462 (0.0009) -[2023-10-09 03:37:03,299][88327] Updated weights for policy 1, policy_version 86530 (0.0007) -[2023-10-09 03:37:03,661][88327] Updated weights for policy 1, policy_version 86540 (0.0011) -[2023-10-09 03:37:03,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 177143808. Throughput: 0: 1666.8, 1: 1693.6. Samples: 44297848. Policy #0 lag: (min: 13.0, avg: 15.8, max: 43.0) -[2023-10-09 03:37:03,975][87372] Avg episode reward: [(0, '6.280'), (1, '7.510')] -[2023-10-09 03:37:04,033][88327] Updated weights for policy 1, policy_version 86550 (0.0009) -[2023-10-09 03:37:04,387][88327] Updated weights for policy 1, policy_version 86560 (0.0009) -[2023-10-09 03:37:06,840][88326] Updated weights for policy 0, policy_version 86472 (0.0010) -[2023-10-09 03:37:07,202][88326] Updated weights for policy 0, policy_version 86482 (0.0009) -[2023-10-09 03:37:07,570][88326] Updated weights for policy 0, policy_version 86492 (0.0009) -[2023-10-09 03:37:08,327][88327] Updated weights for policy 1, policy_version 86570 (0.0008) -[2023-10-09 03:37:08,696][88327] Updated weights for policy 1, policy_version 86580 (0.0008) -[2023-10-09 03:37:08,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 177209344. Throughput: 0: 1687.8, 1: 1688.2. Samples: 44308140. Policy #0 lag: (min: 13.0, avg: 15.8, max: 43.0) -[2023-10-09 03:37:08,975][87372] Avg episode reward: [(0, '6.730'), (1, '6.960')] -[2023-10-09 03:37:09,065][88327] Updated weights for policy 1, policy_version 86590 (0.0009) -[2023-10-09 03:37:11,675][88326] Updated weights for policy 0, policy_version 86502 (0.0011) -[2023-10-09 03:37:12,051][88326] Updated weights for policy 0, policy_version 86512 (0.0010) -[2023-10-09 03:37:12,423][88326] Updated weights for policy 0, policy_version 86522 (0.0010) -[2023-10-09 03:37:13,151][88327] Updated weights for policy 1, policy_version 86600 (0.0010) -[2023-10-09 03:37:13,517][88327] Updated weights for policy 1, policy_version 86610 (0.0010) -[2023-10-09 03:37:13,883][88327] Updated weights for policy 1, policy_version 86620 (0.0012) -[2023-10-09 03:37:13,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 177274880. Throughput: 0: 1669.7, 1: 1685.9. Samples: 44328102. Policy #0 lag: (min: 13.0, avg: 15.8, max: 43.0) -[2023-10-09 03:37:13,974][87372] Avg episode reward: [(0, '6.550'), (1, '7.110')] -[2023-10-09 03:37:16,353][88326] Updated weights for policy 0, policy_version 86532 (0.0011) -[2023-10-09 03:37:16,722][88326] Updated weights for policy 0, policy_version 86542 (0.0008) -[2023-10-09 03:37:17,094][88326] Updated weights for policy 0, policy_version 86552 (0.0007) -[2023-10-09 03:37:17,721][88327] Updated weights for policy 1, policy_version 86630 (0.0009) -[2023-10-09 03:37:18,094][88327] Updated weights for policy 1, policy_version 86640 (0.0008) -[2023-10-09 03:37:18,460][88327] Updated weights for policy 1, policy_version 86650 (0.0007) -[2023-10-09 03:37:18,974][87372] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 13662.6). Total num frames: 177373184. Throughput: 0: 1677.5, 1: 1678.1. Samples: 44348092. Policy #0 lag: (min: 13.0, avg: 15.8, max: 43.0) -[2023-10-09 03:37:18,975][87372] Avg episode reward: [(0, '6.930'), (1, '7.190')] -[2023-10-09 03:37:21,144][88326] Updated weights for policy 0, policy_version 86562 (0.0008) -[2023-10-09 03:37:21,510][88326] Updated weights for policy 0, policy_version 86572 (0.0009) -[2023-10-09 03:37:21,878][88326] Updated weights for policy 0, policy_version 86582 (0.0011) -[2023-10-09 03:37:22,239][88326] Updated weights for policy 0, policy_version 86592 (0.0008) -[2023-10-09 03:37:22,809][88327] Updated weights for policy 1, policy_version 86660 (0.0007) -[2023-10-09 03:37:23,205][88327] Updated weights for policy 1, policy_version 86670 (0.0007) -[2023-10-09 03:37:23,564][88327] Updated weights for policy 1, policy_version 86680 (0.0007) -[2023-10-09 03:37:23,974][87372] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 13662.6). Total num frames: 177438720. Throughput: 0: 1687.5, 1: 1695.5. Samples: 44358906. Policy #0 lag: (min: 13.0, avg: 15.8, max: 43.0) -[2023-10-09 03:37:23,975][87372] Avg episode reward: [(0, '7.430'), (1, '7.440')] -[2023-10-09 03:37:26,290][88326] Updated weights for policy 0, policy_version 86602 (0.0008) -[2023-10-09 03:37:26,647][88326] Updated weights for policy 0, policy_version 86612 (0.0007) -[2023-10-09 03:37:27,023][88326] Updated weights for policy 0, policy_version 86622 (0.0008) -[2023-10-09 03:37:27,316][88327] Updated weights for policy 1, policy_version 86690 (0.0008) -[2023-10-09 03:37:27,682][88327] Updated weights for policy 1, policy_version 86700 (0.0007) -[2023-10-09 03:37:28,054][88327] Updated weights for policy 1, policy_version 86710 (0.0008) -[2023-10-09 03:37:28,414][88327] Updated weights for policy 1, policy_version 86720 (0.0009) -[2023-10-09 03:37:28,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13662.6). Total num frames: 177504256. Throughput: 0: 1662.3, 1: 1693.1. Samples: 44378674. Policy #0 lag: (min: 26.0, avg: 32.5, max: 58.0) -[2023-10-09 03:37:28,975][87372] Avg episode reward: [(0, '6.850'), (1, '7.620')] -[2023-10-09 03:37:31,174][88326] Updated weights for policy 0, policy_version 86632 (0.0010) -[2023-10-09 03:37:31,550][88326] Updated weights for policy 0, policy_version 86642 (0.0009) -[2023-10-09 03:37:31,922][88326] Updated weights for policy 0, policy_version 86652 (0.0009) -[2023-10-09 03:37:32,357][88327] Updated weights for policy 1, policy_version 86730 (0.0008) -[2023-10-09 03:37:32,716][88327] Updated weights for policy 1, policy_version 86740 (0.0008) -[2023-10-09 03:37:33,086][88327] Updated weights for policy 1, policy_version 86750 (0.0008) -[2023-10-09 03:37:33,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 177569792. Throughput: 0: 1694.4, 1: 1669.9. Samples: 44398578. Policy #0 lag: (min: 26.0, avg: 32.5, max: 58.0) -[2023-10-09 03:37:33,975][87372] Avg episode reward: [(0, '7.260'), (1, '7.550')] -[2023-10-09 03:37:35,907][88326] Updated weights for policy 0, policy_version 86662 (0.0007) -[2023-10-09 03:37:36,274][88326] Updated weights for policy 0, policy_version 86672 (0.0007) -[2023-10-09 03:37:36,643][88326] Updated weights for policy 0, policy_version 86682 (0.0011) -[2023-10-09 03:37:37,164][88327] Updated weights for policy 1, policy_version 86760 (0.0010) -[2023-10-09 03:37:37,519][88327] Updated weights for policy 1, policy_version 86770 (0.0009) -[2023-10-09 03:37:37,889][88327] Updated weights for policy 1, policy_version 86780 (0.0009) -[2023-10-09 03:37:38,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 177635328. Throughput: 0: 1684.7, 1: 1701.4. Samples: 44409756. Policy #0 lag: (min: 26.0, avg: 32.5, max: 58.0) -[2023-10-09 03:37:38,975][87372] Avg episode reward: [(0, '7.360'), (1, '7.280')] -[2023-10-09 03:37:40,635][88326] Updated weights for policy 0, policy_version 86692 (0.0010) -[2023-10-09 03:37:41,014][88326] Updated weights for policy 0, policy_version 86702 (0.0009) -[2023-10-09 03:37:41,381][88326] Updated weights for policy 0, policy_version 86712 (0.0011) -[2023-10-09 03:37:42,089][88327] Updated weights for policy 1, policy_version 86790 (0.0011) -[2023-10-09 03:37:42,461][88327] Updated weights for policy 1, policy_version 86800 (0.0008) -[2023-10-09 03:37:42,832][88327] Updated weights for policy 1, policy_version 86810 (0.0007) -[2023-10-09 03:37:43,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 177700864. Throughput: 0: 1672.8, 1: 1695.5. Samples: 44429384. Policy #0 lag: (min: 26.0, avg: 32.5, max: 58.0) -[2023-10-09 03:37:43,975][87372] Avg episode reward: [(0, '7.130'), (1, '8.070')] -[2023-10-09 03:37:45,558][88326] Updated weights for policy 0, policy_version 86722 (0.0010) -[2023-10-09 03:37:45,924][88326] Updated weights for policy 0, policy_version 86732 (0.0009) -[2023-10-09 03:37:46,300][88326] Updated weights for policy 0, policy_version 86742 (0.0011) -[2023-10-09 03:37:46,668][88326] Updated weights for policy 0, policy_version 86752 (0.0008) -[2023-10-09 03:37:47,085][88327] Updated weights for policy 1, policy_version 86820 (0.0009) -[2023-10-09 03:37:47,453][88327] Updated weights for policy 1, policy_version 86830 (0.0008) -[2023-10-09 03:37:47,824][88327] Updated weights for policy 1, policy_version 86840 (0.0008) -[2023-10-09 03:37:48,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 177766400. Throughput: 0: 1695.3, 1: 1667.3. Samples: 44449164. Policy #0 lag: (min: 26.0, avg: 32.5, max: 58.0) -[2023-10-09 03:37:48,975][87372] Avg episode reward: [(0, '7.150'), (1, '7.560')] -[2023-10-09 03:37:50,877][88326] Updated weights for policy 0, policy_version 86762 (0.0008) -[2023-10-09 03:37:51,238][88326] Updated weights for policy 0, policy_version 86772 (0.0008) -[2023-10-09 03:37:51,603][88326] Updated weights for policy 0, policy_version 86782 (0.0008) -[2023-10-09 03:37:51,789][88327] Updated weights for policy 1, policy_version 86850 (0.0010) -[2023-10-09 03:37:52,163][88327] Updated weights for policy 1, policy_version 86860 (0.0008) -[2023-10-09 03:37:52,530][88327] Updated weights for policy 1, policy_version 86870 (0.0007) -[2023-10-09 03:37:52,889][88327] Updated weights for policy 1, policy_version 86880 (0.0008) -[2023-10-09 03:37:53,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 177831936. Throughput: 0: 1672.7, 1: 1699.9. Samples: 44459912. Policy #0 lag: (min: 26.0, avg: 32.5, max: 58.0) -[2023-10-09 03:37:53,975][87372] Avg episode reward: [(0, '7.710'), (1, '7.200')] -[2023-10-09 03:37:55,623][88326] Updated weights for policy 0, policy_version 86792 (0.0010) -[2023-10-09 03:37:55,993][88326] Updated weights for policy 0, policy_version 86802 (0.0007) -[2023-10-09 03:37:56,363][88326] Updated weights for policy 0, policy_version 86812 (0.0011) -[2023-10-09 03:37:56,885][88327] Updated weights for policy 1, policy_version 86890 (0.0010) -[2023-10-09 03:37:57,244][88327] Updated weights for policy 1, policy_version 86900 (0.0010) -[2023-10-09 03:37:57,615][88327] Updated weights for policy 1, policy_version 86910 (0.0010) -[2023-10-09 03:37:58,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 177897472. Throughput: 0: 1683.5, 1: 1684.2. Samples: 44479652. Policy #0 lag: (min: 26.0, avg: 32.5, max: 58.0) -[2023-10-09 03:37:58,975][87372] Avg episode reward: [(0, '7.340'), (1, '7.300')] -[2023-10-09 03:38:00,358][88326] Updated weights for policy 0, policy_version 86822 (0.0008) -[2023-10-09 03:38:00,746][88326] Updated weights for policy 0, policy_version 86832 (0.0009) -[2023-10-09 03:38:01,111][88326] Updated weights for policy 0, policy_version 86842 (0.0010) -[2023-10-09 03:38:01,750][88327] Updated weights for policy 1, policy_version 86920 (0.0008) -[2023-10-09 03:38:02,105][88327] Updated weights for policy 1, policy_version 86930 (0.0008) -[2023-10-09 03:38:02,465][88327] Updated weights for policy 1, policy_version 86940 (0.0007) -[2023-10-09 03:38:03,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 177963008. Throughput: 0: 1688.2, 1: 1681.1. Samples: 44499710. Policy #0 lag: (min: 26.0, avg: 32.5, max: 58.0) -[2023-10-09 03:38:03,975][87372] Avg episode reward: [(0, '6.750'), (1, '7.420')] -[2023-10-09 03:38:05,060][88326] Updated weights for policy 0, policy_version 86852 (0.0008) -[2023-10-09 03:38:05,422][88326] Updated weights for policy 0, policy_version 86862 (0.0008) -[2023-10-09 03:38:05,788][88326] Updated weights for policy 0, policy_version 86872 (0.0009) -[2023-10-09 03:38:06,428][88327] Updated weights for policy 1, policy_version 86950 (0.0010) -[2023-10-09 03:38:06,782][88327] Updated weights for policy 1, policy_version 86960 (0.0008) -[2023-10-09 03:38:07,152][88327] Updated weights for policy 1, policy_version 86970 (0.0008) -[2023-10-09 03:38:08,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 178028544. Throughput: 0: 1665.7, 1: 1699.8. Samples: 44510354. Policy #0 lag: (min: 26.0, avg: 32.5, max: 58.0) -[2023-10-09 03:38:08,975][87372] Avg episode reward: [(0, '6.590'), (1, '7.520')] -[2023-10-09 03:38:09,902][88326] Updated weights for policy 0, policy_version 86882 (0.0010) -[2023-10-09 03:38:10,281][88326] Updated weights for policy 0, policy_version 86892 (0.0010) -[2023-10-09 03:38:10,656][88326] Updated weights for policy 0, policy_version 86902 (0.0009) -[2023-10-09 03:38:11,010][88326] Updated weights for policy 0, policy_version 86912 (0.0007) -[2023-10-09 03:38:11,081][88327] Updated weights for policy 1, policy_version 86980 (0.0009) -[2023-10-09 03:38:11,454][88327] Updated weights for policy 1, policy_version 86990 (0.0009) -[2023-10-09 03:38:11,822][88327] Updated weights for policy 1, policy_version 87000 (0.0008) -[2023-10-09 03:38:13,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 178094080. Throughput: 0: 1689.8, 1: 1671.8. Samples: 44529946. Policy #0 lag: (min: 26.0, avg: 32.5, max: 58.0) -[2023-10-09 03:38:13,975][87372] Avg episode reward: [(0, '6.350'), (1, '7.650')] -[2023-10-09 03:38:15,076][88326] Updated weights for policy 0, policy_version 86922 (0.0009) -[2023-10-09 03:38:15,456][88326] Updated weights for policy 0, policy_version 86932 (0.0009) -[2023-10-09 03:38:15,822][88326] Updated weights for policy 0, policy_version 86942 (0.0010) -[2023-10-09 03:38:15,991][88327] Updated weights for policy 1, policy_version 87010 (0.0009) -[2023-10-09 03:38:16,403][88327] Updated weights for policy 1, policy_version 87020 (0.0007) -[2023-10-09 03:38:16,768][88327] Updated weights for policy 1, policy_version 87030 (0.0007) -[2023-10-09 03:38:17,127][88327] Updated weights for policy 1, policy_version 87040 (0.0008) -[2023-10-09 03:38:18,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 178159616. Throughput: 0: 1685.2, 1: 1690.3. Samples: 44550476. Policy #0 lag: (min: 26.0, avg: 32.5, max: 58.0) -[2023-10-09 03:38:18,975][87372] Avg episode reward: [(0, '7.050'), (1, '7.180')] -[2023-10-09 03:38:19,841][88326] Updated weights for policy 0, policy_version 86952 (0.0008) -[2023-10-09 03:38:20,210][88326] Updated weights for policy 0, policy_version 86962 (0.0008) -[2023-10-09 03:38:20,576][88326] Updated weights for policy 0, policy_version 86972 (0.0008) -[2023-10-09 03:38:21,254][88327] Updated weights for policy 1, policy_version 87050 (0.0007) -[2023-10-09 03:38:21,619][88327] Updated weights for policy 1, policy_version 87060 (0.0007) -[2023-10-09 03:38:21,979][88327] Updated weights for policy 1, policy_version 87070 (0.0008) -[2023-10-09 03:38:23,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 178225152. Throughput: 0: 1667.6, 1: 1681.4. Samples: 44560460. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) -[2023-10-09 03:38:23,975][87372] Avg episode reward: [(0, '6.820'), (1, '7.640')] -[2023-10-09 03:38:24,717][88326] Updated weights for policy 0, policy_version 86982 (0.0008) -[2023-10-09 03:38:25,088][88326] Updated weights for policy 0, policy_version 86992 (0.0009) -[2023-10-09 03:38:25,457][88326] Updated weights for policy 0, policy_version 87002 (0.0009) -[2023-10-09 03:38:26,012][88327] Updated weights for policy 1, policy_version 87080 (0.0011) -[2023-10-09 03:38:26,389][88327] Updated weights for policy 1, policy_version 87090 (0.0009) -[2023-10-09 03:38:26,755][88327] Updated weights for policy 1, policy_version 87100 (0.0010) -[2023-10-09 03:38:28,974][87372] Fps is (10 sec: 13107.8, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 178290688. Throughput: 0: 1683.7, 1: 1670.6. Samples: 44580326. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) -[2023-10-09 03:38:28,975][87372] Avg episode reward: [(0, '7.050'), (1, '7.480')] -[2023-10-09 03:38:29,468][88326] Updated weights for policy 0, policy_version 87012 (0.0008) -[2023-10-09 03:38:29,833][88326] Updated weights for policy 0, policy_version 87022 (0.0008) -[2023-10-09 03:38:30,195][88326] Updated weights for policy 0, policy_version 87032 (0.0008) -[2023-10-09 03:38:30,848][88327] Updated weights for policy 1, policy_version 87110 (0.0010) -[2023-10-09 03:38:31,222][88327] Updated weights for policy 1, policy_version 87120 (0.0010) -[2023-10-09 03:38:31,589][88327] Updated weights for policy 1, policy_version 87130 (0.0007) -[2023-10-09 03:38:33,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 178356224. Throughput: 0: 1684.2, 1: 1694.7. Samples: 44601214. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) -[2023-10-09 03:38:33,975][87372] Avg episode reward: [(0, '6.730'), (1, '7.870')] -[2023-10-09 03:38:33,986][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000087136_89227264.pth... -[2023-10-09 03:38:33,986][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000087040_89128960.pth... -[2023-10-09 03:38:34,020][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000085472_87523328.pth -[2023-10-09 03:38:34,025][88088] Saving a milestone ./train_atari/atari_battlezone_APPO/checkpoint_p0/milestones/checkpoint_000087040_89128960.pth -[2023-10-09 03:38:34,025][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000085568_87621632.pth -[2023-10-09 03:38:34,029][88168] Saving a milestone ./train_atari/atari_battlezone_APPO/checkpoint_p1/milestones/checkpoint_000087136_89227264.pth -[2023-10-09 03:38:34,274][88326] Updated weights for policy 0, policy_version 87042 (0.0008) -[2023-10-09 03:38:34,645][88326] Updated weights for policy 0, policy_version 87052 (0.0009) -[2023-10-09 03:38:35,003][88326] Updated weights for policy 0, policy_version 87062 (0.0010) -[2023-10-09 03:38:35,366][88326] Updated weights for policy 0, policy_version 87072 (0.0009) -[2023-10-09 03:38:35,444][88327] Updated weights for policy 1, policy_version 87140 (0.0007) -[2023-10-09 03:38:35,806][88327] Updated weights for policy 1, policy_version 87150 (0.0008) -[2023-10-09 03:38:36,166][88327] Updated weights for policy 1, policy_version 87160 (0.0007) -[2023-10-09 03:38:38,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 178421760. Throughput: 0: 1676.1, 1: 1676.1. Samples: 44610764. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) -[2023-10-09 03:38:38,975][87372] Avg episode reward: [(0, '6.690'), (1, '7.490')] -[2023-10-09 03:38:39,577][88326] Updated weights for policy 0, policy_version 87082 (0.0007) -[2023-10-09 03:38:39,945][88326] Updated weights for policy 0, policy_version 87092 (0.0009) -[2023-10-09 03:38:40,238][88327] Updated weights for policy 1, policy_version 87170 (0.0008) -[2023-10-09 03:38:40,313][88326] Updated weights for policy 0, policy_version 87102 (0.0009) -[2023-10-09 03:38:40,611][88327] Updated weights for policy 1, policy_version 87180 (0.0010) -[2023-10-09 03:38:40,969][88327] Updated weights for policy 1, policy_version 87190 (0.0007) -[2023-10-09 03:38:41,335][88327] Updated weights for policy 1, policy_version 87200 (0.0007) -[2023-10-09 03:38:43,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 178487296. Throughput: 0: 1683.6, 1: 1684.1. Samples: 44631198. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) -[2023-10-09 03:38:43,974][87372] Avg episode reward: [(0, '7.020'), (1, '7.690')] -[2023-10-09 03:38:44,296][88326] Updated weights for policy 0, policy_version 87112 (0.0009) -[2023-10-09 03:38:44,674][88326] Updated weights for policy 0, policy_version 87122 (0.0008) -[2023-10-09 03:38:45,051][88326] Updated weights for policy 0, policy_version 87132 (0.0009) -[2023-10-09 03:38:45,612][88327] Updated weights for policy 1, policy_version 87210 (0.0008) -[2023-10-09 03:38:45,974][88327] Updated weights for policy 1, policy_version 87220 (0.0009) -[2023-10-09 03:38:46,338][88327] Updated weights for policy 1, policy_version 87230 (0.0009) -[2023-10-09 03:38:48,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 178552832. Throughput: 0: 1692.1, 1: 1704.2. Samples: 44652542. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) -[2023-10-09 03:38:48,975][87372] Avg episode reward: [(0, '7.040'), (1, '7.190')] -[2023-10-09 03:38:49,119][88326] Updated weights for policy 0, policy_version 87142 (0.0008) -[2023-10-09 03:38:49,485][88326] Updated weights for policy 0, policy_version 87152 (0.0007) -[2023-10-09 03:38:49,861][88326] Updated weights for policy 0, policy_version 87162 (0.0007) -[2023-10-09 03:38:50,280][88327] Updated weights for policy 1, policy_version 87240 (0.0009) -[2023-10-09 03:38:50,640][88327] Updated weights for policy 1, policy_version 87250 (0.0011) -[2023-10-09 03:38:51,006][88327] Updated weights for policy 1, policy_version 87260 (0.0012) -[2023-10-09 03:38:53,783][88326] Updated weights for policy 0, policy_version 87172 (0.0007) -[2023-10-09 03:38:53,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 178618368. Throughput: 0: 1690.0, 1: 1674.0. Samples: 44661734. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) -[2023-10-09 03:38:53,975][87372] Avg episode reward: [(0, '7.290'), (1, '6.800')] -[2023-10-09 03:38:54,154][88326] Updated weights for policy 0, policy_version 87182 (0.0008) -[2023-10-09 03:38:54,528][88326] Updated weights for policy 0, policy_version 87192 (0.0009) -[2023-10-09 03:38:55,063][88327] Updated weights for policy 1, policy_version 87270 (0.0009) -[2023-10-09 03:38:55,426][88327] Updated weights for policy 1, policy_version 87280 (0.0009) -[2023-10-09 03:38:55,790][88327] Updated weights for policy 1, policy_version 87290 (0.0008) -[2023-10-09 03:38:58,544][88326] Updated weights for policy 0, policy_version 87202 (0.0008) -[2023-10-09 03:38:58,907][88326] Updated weights for policy 0, policy_version 87212 (0.0009) -[2023-10-09 03:38:58,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 178683904. Throughput: 0: 1690.3, 1: 1702.0. Samples: 44682602. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) -[2023-10-09 03:38:58,975][87372] Avg episode reward: [(0, '7.450'), (1, '7.350')] -[2023-10-09 03:38:59,281][88326] Updated weights for policy 0, policy_version 87222 (0.0007) -[2023-10-09 03:38:59,648][88326] Updated weights for policy 0, policy_version 87232 (0.0007) -[2023-10-09 03:38:59,661][88327] Updated weights for policy 1, policy_version 87300 (0.0007) -[2023-10-09 03:39:00,023][88327] Updated weights for policy 1, policy_version 87310 (0.0007) -[2023-10-09 03:39:00,390][88327] Updated weights for policy 1, policy_version 87320 (0.0009) -[2023-10-09 03:39:03,525][88326] Updated weights for policy 0, policy_version 87242 (0.0007) -[2023-10-09 03:39:03,899][88326] Updated weights for policy 0, policy_version 87252 (0.0009) -[2023-10-09 03:39:03,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 178749440. Throughput: 0: 1692.1, 1: 1714.2. Samples: 44703758. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) -[2023-10-09 03:39:03,975][87372] Avg episode reward: [(0, '7.410'), (1, '7.690')] -[2023-10-09 03:39:04,265][88326] Updated weights for policy 0, policy_version 87262 (0.0008) -[2023-10-09 03:39:04,330][88327] Updated weights for policy 1, policy_version 87330 (0.0009) -[2023-10-09 03:39:04,744][88327] Updated weights for policy 1, policy_version 87340 (0.0009) -[2023-10-09 03:39:05,105][88327] Updated weights for policy 1, policy_version 87350 (0.0009) -[2023-10-09 03:39:05,470][88327] Updated weights for policy 1, policy_version 87360 (0.0008) -[2023-10-09 03:39:08,407][88326] Updated weights for policy 0, policy_version 87272 (0.0010) -[2023-10-09 03:39:08,771][88326] Updated weights for policy 0, policy_version 87282 (0.0011) -[2023-10-09 03:39:08,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 178814976. Throughput: 0: 1695.2, 1: 1691.8. Samples: 44712876. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) -[2023-10-09 03:39:08,975][87372] Avg episode reward: [(0, '6.810'), (1, '7.220')] -[2023-10-09 03:39:09,146][88326] Updated weights for policy 0, policy_version 87292 (0.0009) -[2023-10-09 03:39:09,516][88327] Updated weights for policy 1, policy_version 87370 (0.0007) -[2023-10-09 03:39:09,886][88327] Updated weights for policy 1, policy_version 87380 (0.0007) -[2023-10-09 03:39:10,255][88327] Updated weights for policy 1, policy_version 87390 (0.0007) -[2023-10-09 03:39:13,163][88326] Updated weights for policy 0, policy_version 87302 (0.0009) -[2023-10-09 03:39:13,521][88326] Updated weights for policy 0, policy_version 87312 (0.0010) -[2023-10-09 03:39:13,898][88326] Updated weights for policy 0, policy_version 87322 (0.0010) -[2023-10-09 03:39:13,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 178880512. Throughput: 0: 1695.4, 1: 1709.8. Samples: 44733558. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) -[2023-10-09 03:39:13,975][87372] Avg episode reward: [(0, '7.230'), (1, '7.660')] -[2023-10-09 03:39:14,287][88327] Updated weights for policy 1, policy_version 87400 (0.0008) -[2023-10-09 03:39:14,652][88327] Updated weights for policy 1, policy_version 87410 (0.0007) -[2023-10-09 03:39:15,011][88327] Updated weights for policy 1, policy_version 87420 (0.0007) -[2023-10-09 03:39:17,857][88326] Updated weights for policy 0, policy_version 87332 (0.0008) -[2023-10-09 03:39:18,234][88326] Updated weights for policy 0, policy_version 87342 (0.0008) -[2023-10-09 03:39:18,603][88326] Updated weights for policy 0, policy_version 87352 (0.0007) -[2023-10-09 03:39:18,974][87372] Fps is (10 sec: 16384.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 178978816. Throughput: 0: 1685.8, 1: 1713.2. Samples: 44754170. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 03:39:18,975][87372] Avg episode reward: [(0, '7.130'), (1, '7.440')] -[2023-10-09 03:39:19,154][88327] Updated weights for policy 1, policy_version 87430 (0.0007) -[2023-10-09 03:39:19,511][88327] Updated weights for policy 1, policy_version 87440 (0.0009) -[2023-10-09 03:39:19,887][88327] Updated weights for policy 1, policy_version 87450 (0.0008) -[2023-10-09 03:39:22,846][88326] Updated weights for policy 0, policy_version 87362 (0.0010) -[2023-10-09 03:39:23,226][88326] Updated weights for policy 0, policy_version 87372 (0.0010) -[2023-10-09 03:39:23,585][88326] Updated weights for policy 0, policy_version 87382 (0.0007) -[2023-10-09 03:39:23,818][88327] Updated weights for policy 1, policy_version 87460 (0.0008) -[2023-10-09 03:39:23,955][88326] Updated weights for policy 0, policy_version 87392 (0.0008) -[2023-10-09 03:39:23,974][87372] Fps is (10 sec: 16384.0, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 179044352. Throughput: 0: 1695.3, 1: 1703.9. Samples: 44763730. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 03:39:23,975][87372] Avg episode reward: [(0, '6.610'), (1, '6.790')] -[2023-10-09 03:39:24,179][88327] Updated weights for policy 1, policy_version 87470 (0.0010) -[2023-10-09 03:39:24,542][88327] Updated weights for policy 1, policy_version 87480 (0.0010) -[2023-10-09 03:39:28,081][88326] Updated weights for policy 0, policy_version 87402 (0.0008) -[2023-10-09 03:39:28,448][88326] Updated weights for policy 0, policy_version 87412 (0.0009) -[2023-10-09 03:39:28,613][88327] Updated weights for policy 1, policy_version 87490 (0.0010) -[2023-10-09 03:39:28,827][88326] Updated weights for policy 0, policy_version 87422 (0.0007) -[2023-10-09 03:39:28,969][88327] Updated weights for policy 1, policy_version 87500 (0.0010) -[2023-10-09 03:39:28,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 179109888. Throughput: 0: 1697.3, 1: 1710.5. Samples: 44784552. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 03:39:28,974][87372] Avg episode reward: [(0, '6.370'), (1, '7.790')] -[2023-10-09 03:39:29,332][88327] Updated weights for policy 1, policy_version 87510 (0.0010) -[2023-10-09 03:39:29,695][88327] Updated weights for policy 1, policy_version 87520 (0.0010) -[2023-10-09 03:39:32,901][88326] Updated weights for policy 0, policy_version 87432 (0.0008) -[2023-10-09 03:39:33,265][88326] Updated weights for policy 0, policy_version 87442 (0.0009) -[2023-10-09 03:39:33,615][88327] Updated weights for policy 1, policy_version 87530 (0.0007) -[2023-10-09 03:39:33,636][88326] Updated weights for policy 0, policy_version 87452 (0.0007) -[2023-10-09 03:39:33,972][88327] Updated weights for policy 1, policy_version 87540 (0.0008) -[2023-10-09 03:39:33,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 179175424. Throughput: 0: 1677.1, 1: 1706.5. Samples: 44804804. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 03:39:33,975][87372] Avg episode reward: [(0, '6.760'), (1, '7.810')] -[2023-10-09 03:39:34,344][88327] Updated weights for policy 1, policy_version 87550 (0.0009) -[2023-10-09 03:39:37,595][88326] Updated weights for policy 0, policy_version 87462 (0.0008) -[2023-10-09 03:39:37,983][88326] Updated weights for policy 0, policy_version 87472 (0.0007) -[2023-10-09 03:39:38,353][88326] Updated weights for policy 0, policy_version 87482 (0.0009) -[2023-10-09 03:39:38,442][88327] Updated weights for policy 1, policy_version 87560 (0.0007) -[2023-10-09 03:39:38,812][88327] Updated weights for policy 1, policy_version 87570 (0.0008) -[2023-10-09 03:39:38,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 179240960. Throughput: 0: 1694.2, 1: 1704.6. Samples: 44814680. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 03:39:38,975][87372] Avg episode reward: [(0, '7.180'), (1, '7.400')] -[2023-10-09 03:39:39,183][88327] Updated weights for policy 1, policy_version 87580 (0.0010) -[2023-10-09 03:39:42,219][88326] Updated weights for policy 0, policy_version 87492 (0.0009) -[2023-10-09 03:39:42,580][88326] Updated weights for policy 0, policy_version 87502 (0.0007) -[2023-10-09 03:39:42,945][88326] Updated weights for policy 0, policy_version 87512 (0.0007) -[2023-10-09 03:39:43,278][88327] Updated weights for policy 1, policy_version 87590 (0.0009) -[2023-10-09 03:39:43,647][88327] Updated weights for policy 1, policy_version 87600 (0.0009) -[2023-10-09 03:39:43,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 179306496. Throughput: 0: 1688.4, 1: 1697.9. Samples: 44834986. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 03:39:43,975][87372] Avg episode reward: [(0, '7.140'), (1, '8.020')] -[2023-10-09 03:39:44,019][88327] Updated weights for policy 1, policy_version 87610 (0.0008) -[2023-10-09 03:39:46,978][88326] Updated weights for policy 0, policy_version 87522 (0.0007) -[2023-10-09 03:39:47,349][88326] Updated weights for policy 0, policy_version 87532 (0.0007) -[2023-10-09 03:39:47,712][88326] Updated weights for policy 0, policy_version 87542 (0.0008) -[2023-10-09 03:39:48,079][88327] Updated weights for policy 1, policy_version 87620 (0.0008) -[2023-10-09 03:39:48,082][88326] Updated weights for policy 0, policy_version 87552 (0.0009) -[2023-10-09 03:39:48,448][88327] Updated weights for policy 1, policy_version 87630 (0.0009) -[2023-10-09 03:39:48,810][88327] Updated weights for policy 1, policy_version 87640 (0.0008) -[2023-10-09 03:39:48,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 179372032. Throughput: 0: 1664.0, 1: 1685.0. Samples: 44854466. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 03:39:48,975][87372] Avg episode reward: [(0, '7.710'), (1, '8.120')] -[2023-10-09 03:39:52,020][88326] Updated weights for policy 0, policy_version 87562 (0.0007) -[2023-10-09 03:39:52,387][88326] Updated weights for policy 0, policy_version 87572 (0.0008) -[2023-10-09 03:39:52,769][88326] Updated weights for policy 0, policy_version 87582 (0.0008) -[2023-10-09 03:39:53,022][88327] Updated weights for policy 1, policy_version 87650 (0.0008) -[2023-10-09 03:39:53,441][88327] Updated weights for policy 1, policy_version 87660 (0.0007) -[2023-10-09 03:39:53,809][88327] Updated weights for policy 1, policy_version 87670 (0.0008) -[2023-10-09 03:39:53,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 179437568. Throughput: 0: 1697.1, 1: 1687.6. Samples: 44865188. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 03:39:53,975][87372] Avg episode reward: [(0, '6.480'), (1, '6.980')] -[2023-10-09 03:39:54,176][88327] Updated weights for policy 1, policy_version 87680 (0.0008) -[2023-10-09 03:39:56,781][88326] Updated weights for policy 0, policy_version 87592 (0.0011) -[2023-10-09 03:39:57,154][88326] Updated weights for policy 0, policy_version 87602 (0.0007) -[2023-10-09 03:39:57,518][88326] Updated weights for policy 0, policy_version 87612 (0.0008) -[2023-10-09 03:39:58,034][88327] Updated weights for policy 1, policy_version 87690 (0.0008) -[2023-10-09 03:39:58,396][88327] Updated weights for policy 1, policy_version 87700 (0.0009) -[2023-10-09 03:39:58,760][88327] Updated weights for policy 1, policy_version 87710 (0.0009) -[2023-10-09 03:39:58,974][87372] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 179535872. Throughput: 0: 1681.9, 1: 1692.0. Samples: 44885382. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 03:39:58,975][87372] Avg episode reward: [(0, '6.860'), (1, '7.300')] -[2023-10-09 03:40:01,454][88326] Updated weights for policy 0, policy_version 87622 (0.0007) -[2023-10-09 03:40:01,828][88326] Updated weights for policy 0, policy_version 87632 (0.0007) -[2023-10-09 03:40:02,186][88326] Updated weights for policy 0, policy_version 87642 (0.0007) -[2023-10-09 03:40:02,821][88327] Updated weights for policy 1, policy_version 87720 (0.0008) -[2023-10-09 03:40:03,184][88327] Updated weights for policy 1, policy_version 87730 (0.0009) -[2023-10-09 03:40:03,543][88327] Updated weights for policy 1, policy_version 87740 (0.0007) -[2023-10-09 03:40:03,974][87372] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 179601408. Throughput: 0: 1687.2, 1: 1673.6. Samples: 44905408. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 03:40:03,975][87372] Avg episode reward: [(0, '6.880'), (1, '6.950')] -[2023-10-09 03:40:06,283][88326] Updated weights for policy 0, policy_version 87652 (0.0008) -[2023-10-09 03:40:06,652][88326] Updated weights for policy 0, policy_version 87662 (0.0010) -[2023-10-09 03:40:07,018][88326] Updated weights for policy 0, policy_version 87672 (0.0011) -[2023-10-09 03:40:07,436][88327] Updated weights for policy 1, policy_version 87750 (0.0010) -[2023-10-09 03:40:07,796][88327] Updated weights for policy 1, policy_version 87760 (0.0009) -[2023-10-09 03:40:08,164][88327] Updated weights for policy 1, policy_version 87770 (0.0010) -[2023-10-09 03:40:08,974][87372] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 179666944. Throughput: 0: 1702.5, 1: 1688.9. Samples: 44916342. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 03:40:08,975][87372] Avg episode reward: [(0, '6.800'), (1, '7.160')] -[2023-10-09 03:40:11,170][88326] Updated weights for policy 0, policy_version 87682 (0.0007) -[2023-10-09 03:40:11,544][88326] Updated weights for policy 0, policy_version 87692 (0.0007) -[2023-10-09 03:40:11,911][88326] Updated weights for policy 0, policy_version 87702 (0.0007) -[2023-10-09 03:40:12,274][88327] Updated weights for policy 1, policy_version 87780 (0.0009) -[2023-10-09 03:40:12,277][88326] Updated weights for policy 0, policy_version 87712 (0.0008) -[2023-10-09 03:40:12,640][88327] Updated weights for policy 1, policy_version 87790 (0.0010) -[2023-10-09 03:40:13,003][88327] Updated weights for policy 1, policy_version 87800 (0.0007) -[2023-10-09 03:40:13,974][87372] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 179732480. Throughput: 0: 1678.1, 1: 1692.8. Samples: 44936244. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-09 03:40:13,975][87372] Avg episode reward: [(0, '7.480'), (1, '7.370')] -[2023-10-09 03:40:16,428][88326] Updated weights for policy 0, policy_version 87722 (0.0009) -[2023-10-09 03:40:16,801][88326] Updated weights for policy 0, policy_version 87732 (0.0010) -[2023-10-09 03:40:17,017][88327] Updated weights for policy 1, policy_version 87810 (0.0007) -[2023-10-09 03:40:17,164][88326] Updated weights for policy 0, policy_version 87742 (0.0008) -[2023-10-09 03:40:17,377][88327] Updated weights for policy 1, policy_version 87820 (0.0008) -[2023-10-09 03:40:17,731][88327] Updated weights for policy 1, policy_version 87830 (0.0010) -[2023-10-09 03:40:18,098][88327] Updated weights for policy 1, policy_version 87840 (0.0008) -[2023-10-09 03:40:18,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 179798016. Throughput: 0: 1687.8, 1: 1664.4. Samples: 44955652. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:40:18,975][87372] Avg episode reward: [(0, '6.840'), (1, '7.360')] -[2023-10-09 03:40:21,196][88326] Updated weights for policy 0, policy_version 87752 (0.0009) -[2023-10-09 03:40:21,558][88326] Updated weights for policy 0, policy_version 87762 (0.0008) -[2023-10-09 03:40:21,938][88326] Updated weights for policy 0, policy_version 87772 (0.0011) -[2023-10-09 03:40:22,262][88327] Updated weights for policy 1, policy_version 87850 (0.0008) -[2023-10-09 03:40:22,616][88327] Updated weights for policy 1, policy_version 87860 (0.0009) -[2023-10-09 03:40:22,983][88327] Updated weights for policy 1, policy_version 87870 (0.0010) -[2023-10-09 03:40:23,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 179863552. Throughput: 0: 1693.3, 1: 1689.4. Samples: 44966904. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:40:23,975][87372] Avg episode reward: [(0, '7.150'), (1, '7.970')] -[2023-10-09 03:40:26,080][88326] Updated weights for policy 0, policy_version 87782 (0.0007) -[2023-10-09 03:40:26,458][88326] Updated weights for policy 0, policy_version 87792 (0.0008) -[2023-10-09 03:40:26,819][88326] Updated weights for policy 0, policy_version 87802 (0.0007) -[2023-10-09 03:40:26,995][88327] Updated weights for policy 1, policy_version 87880 (0.0009) -[2023-10-09 03:40:27,354][88327] Updated weights for policy 1, policy_version 87890 (0.0009) -[2023-10-09 03:40:27,718][88327] Updated weights for policy 1, policy_version 87900 (0.0011) -[2023-10-09 03:40:28,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 179929088. Throughput: 0: 1676.2, 1: 1686.5. Samples: 44986308. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:40:28,975][87372] Avg episode reward: [(0, '7.440'), (1, '7.600')] -[2023-10-09 03:40:30,852][88326] Updated weights for policy 0, policy_version 87812 (0.0008) -[2023-10-09 03:40:31,223][88326] Updated weights for policy 0, policy_version 87822 (0.0008) -[2023-10-09 03:40:31,580][88326] Updated weights for policy 0, policy_version 87832 (0.0009) -[2023-10-09 03:40:31,846][88327] Updated weights for policy 1, policy_version 87910 (0.0009) -[2023-10-09 03:40:32,215][88327] Updated weights for policy 1, policy_version 87920 (0.0008) -[2023-10-09 03:40:32,583][88327] Updated weights for policy 1, policy_version 87930 (0.0008) -[2023-10-09 03:40:33,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 179994624. Throughput: 0: 1703.2, 1: 1675.1. Samples: 45006486. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:40:33,975][87372] Avg episode reward: [(0, '6.840'), (1, '7.340')] -[2023-10-09 03:40:33,986][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000087936_90046464.pth... -[2023-10-09 03:40:33,987][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000087840_89948160.pth... -[2023-10-09 03:40:34,029][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000086368_88440832.pth -[2023-10-09 03:40:34,029][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000086272_88342528.pth -[2023-10-09 03:40:35,688][88326] Updated weights for policy 0, policy_version 87842 (0.0008) -[2023-10-09 03:40:36,053][88326] Updated weights for policy 0, policy_version 87852 (0.0009) -[2023-10-09 03:40:36,422][88326] Updated weights for policy 0, policy_version 87862 (0.0011) -[2023-10-09 03:40:36,737][88327] Updated weights for policy 1, policy_version 87940 (0.0007) -[2023-10-09 03:40:36,795][88326] Updated weights for policy 0, policy_version 87872 (0.0007) -[2023-10-09 03:40:37,097][88327] Updated weights for policy 1, policy_version 87950 (0.0007) -[2023-10-09 03:40:37,467][88327] Updated weights for policy 1, policy_version 87960 (0.0007) -[2023-10-09 03:40:38,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 180060160. Throughput: 0: 1681.9, 1: 1700.8. Samples: 45017408. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:40:38,975][87372] Avg episode reward: [(0, '6.760'), (1, '7.120')] -[2023-10-09 03:40:40,873][88326] Updated weights for policy 0, policy_version 87882 (0.0011) -[2023-10-09 03:40:41,244][88326] Updated weights for policy 0, policy_version 87892 (0.0007) -[2023-10-09 03:40:41,588][88327] Updated weights for policy 1, policy_version 87970 (0.0008) -[2023-10-09 03:40:41,614][88326] Updated weights for policy 0, policy_version 87902 (0.0007) -[2023-10-09 03:40:42,013][88327] Updated weights for policy 1, policy_version 87980 (0.0009) -[2023-10-09 03:40:42,374][88327] Updated weights for policy 1, policy_version 87990 (0.0007) -[2023-10-09 03:40:42,735][88327] Updated weights for policy 1, policy_version 88000 (0.0007) -[2023-10-09 03:40:43,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 180125696. Throughput: 0: 1683.2, 1: 1680.7. Samples: 45036754. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:40:43,975][87372] Avg episode reward: [(0, '6.810'), (1, '7.080')] -[2023-10-09 03:40:45,588][88326] Updated weights for policy 0, policy_version 87912 (0.0011) -[2023-10-09 03:40:45,953][88326] Updated weights for policy 0, policy_version 87922 (0.0010) -[2023-10-09 03:40:46,329][88326] Updated weights for policy 0, policy_version 87932 (0.0010) -[2023-10-09 03:40:46,587][88327] Updated weights for policy 1, policy_version 88010 (0.0011) -[2023-10-09 03:40:46,949][88327] Updated weights for policy 1, policy_version 88020 (0.0009) -[2023-10-09 03:40:47,309][88327] Updated weights for policy 1, policy_version 88030 (0.0007) -[2023-10-09 03:40:48,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 180191232. Throughput: 0: 1691.4, 1: 1678.0. Samples: 45057030. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:40:48,975][87372] Avg episode reward: [(0, '6.920'), (1, '6.770')] -[2023-10-09 03:40:50,247][88326] Updated weights for policy 0, policy_version 87942 (0.0009) -[2023-10-09 03:40:50,611][88326] Updated weights for policy 0, policy_version 87952 (0.0007) -[2023-10-09 03:40:50,973][88326] Updated weights for policy 0, policy_version 87962 (0.0008) -[2023-10-09 03:40:51,374][88327] Updated weights for policy 1, policy_version 88040 (0.0009) -[2023-10-09 03:40:51,736][88327] Updated weights for policy 1, policy_version 88050 (0.0008) -[2023-10-09 03:40:52,098][88327] Updated weights for policy 1, policy_version 88060 (0.0008) -[2023-10-09 03:40:53,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 180256768. Throughput: 0: 1668.6, 1: 1688.8. Samples: 45067424. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:40:53,975][87372] Avg episode reward: [(0, '6.920'), (1, '7.350')] -[2023-10-09 03:40:54,869][88326] Updated weights for policy 0, policy_version 87972 (0.0008) -[2023-10-09 03:40:55,239][88326] Updated weights for policy 0, policy_version 87982 (0.0008) -[2023-10-09 03:40:55,605][88326] Updated weights for policy 0, policy_version 87992 (0.0009) -[2023-10-09 03:40:56,146][88327] Updated weights for policy 1, policy_version 88070 (0.0007) -[2023-10-09 03:40:56,512][88327] Updated weights for policy 1, policy_version 88080 (0.0009) -[2023-10-09 03:40:56,868][88327] Updated weights for policy 1, policy_version 88090 (0.0010) -[2023-10-09 03:40:58,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 180322304. Throughput: 0: 1698.3, 1: 1660.5. Samples: 45087392. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:40:58,975][87372] Avg episode reward: [(0, '7.340'), (1, '7.260')] -[2023-10-09 03:40:59,555][88326] Updated weights for policy 0, policy_version 88002 (0.0010) -[2023-10-09 03:40:59,924][88326] Updated weights for policy 0, policy_version 88012 (0.0009) -[2023-10-09 03:41:00,297][88326] Updated weights for policy 0, policy_version 88022 (0.0007) -[2023-10-09 03:41:00,657][88326] Updated weights for policy 0, policy_version 88032 (0.0008) -[2023-10-09 03:41:00,804][88327] Updated weights for policy 1, policy_version 88100 (0.0010) -[2023-10-09 03:41:01,173][88327] Updated weights for policy 1, policy_version 88110 (0.0010) -[2023-10-09 03:41:01,549][88327] Updated weights for policy 1, policy_version 88120 (0.0010) -[2023-10-09 03:41:03,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 180387840. Throughput: 0: 1705.3, 1: 1692.4. Samples: 45108548. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:41:03,975][87372] Avg episode reward: [(0, '7.690'), (1, '7.840')] -[2023-10-09 03:41:04,761][88326] Updated weights for policy 0, policy_version 88042 (0.0010) -[2023-10-09 03:41:05,124][88326] Updated weights for policy 0, policy_version 88052 (0.0010) -[2023-10-09 03:41:05,497][88326] Updated weights for policy 0, policy_version 88062 (0.0010) -[2023-10-09 03:41:05,507][88327] Updated weights for policy 1, policy_version 88130 (0.0011) -[2023-10-09 03:41:05,877][88327] Updated weights for policy 1, policy_version 88140 (0.0009) -[2023-10-09 03:41:06,251][88327] Updated weights for policy 1, policy_version 88150 (0.0007) -[2023-10-09 03:41:06,618][88327] Updated weights for policy 1, policy_version 88160 (0.0008) -[2023-10-09 03:41:08,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 180453376. Throughput: 0: 1682.4, 1: 1683.1. Samples: 45118350. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:41:08,974][87372] Avg episode reward: [(0, '6.940'), (1, '8.310')] -[2023-10-09 03:41:09,685][88326] Updated weights for policy 0, policy_version 88072 (0.0008) -[2023-10-09 03:41:10,064][88326] Updated weights for policy 0, policy_version 88082 (0.0008) -[2023-10-09 03:41:10,440][88326] Updated weights for policy 0, policy_version 88092 (0.0009) -[2023-10-09 03:41:10,623][88327] Updated weights for policy 1, policy_version 88170 (0.0007) -[2023-10-09 03:41:10,979][88327] Updated weights for policy 1, policy_version 88180 (0.0009) -[2023-10-09 03:41:11,345][88327] Updated weights for policy 1, policy_version 88190 (0.0008) -[2023-10-09 03:41:13,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 180518912. Throughput: 0: 1704.3, 1: 1683.9. Samples: 45138776. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:41:13,975][87372] Avg episode reward: [(0, '6.640'), (1, '7.880')] -[2023-10-09 03:41:14,446][88326] Updated weights for policy 0, policy_version 88102 (0.0008) -[2023-10-09 03:41:14,823][88326] Updated weights for policy 0, policy_version 88112 (0.0008) -[2023-10-09 03:41:15,185][88326] Updated weights for policy 0, policy_version 88122 (0.0008) -[2023-10-09 03:41:15,365][88327] Updated weights for policy 1, policy_version 88200 (0.0009) -[2023-10-09 03:41:15,733][88327] Updated weights for policy 1, policy_version 88210 (0.0009) -[2023-10-09 03:41:16,090][88327] Updated weights for policy 1, policy_version 88220 (0.0011) -[2023-10-09 03:41:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 180584448. Throughput: 0: 1701.4, 1: 1706.4. Samples: 45159838. Policy #0 lag: (min: 35.0, avg: 53.9, max: 56.0) -[2023-10-09 03:41:18,975][87372] Avg episode reward: [(0, '7.280'), (1, '7.160')] -[2023-10-09 03:41:19,162][88326] Updated weights for policy 0, policy_version 88132 (0.0008) -[2023-10-09 03:41:19,539][88326] Updated weights for policy 0, policy_version 88142 (0.0007) -[2023-10-09 03:41:19,914][88326] Updated weights for policy 0, policy_version 88152 (0.0009) -[2023-10-09 03:41:20,158][88327] Updated weights for policy 1, policy_version 88230 (0.0010) -[2023-10-09 03:41:20,523][88327] Updated weights for policy 1, policy_version 88240 (0.0008) -[2023-10-09 03:41:20,882][88327] Updated weights for policy 1, policy_version 88250 (0.0010) -[2023-10-09 03:41:23,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 180649984. Throughput: 0: 1689.6, 1: 1679.3. Samples: 45169008. Policy #0 lag: (min: 35.0, avg: 53.9, max: 56.0) -[2023-10-09 03:41:23,974][87372] Avg episode reward: [(0, '6.930'), (1, '7.620')] -[2023-10-09 03:41:24,063][88326] Updated weights for policy 0, policy_version 88162 (0.0010) -[2023-10-09 03:41:24,446][88326] Updated weights for policy 0, policy_version 88172 (0.0007) -[2023-10-09 03:41:24,814][88326] Updated weights for policy 0, policy_version 88182 (0.0007) -[2023-10-09 03:41:24,850][88327] Updated weights for policy 1, policy_version 88260 (0.0008) -[2023-10-09 03:41:25,181][88326] Updated weights for policy 0, policy_version 88192 (0.0009) -[2023-10-09 03:41:25,218][88327] Updated weights for policy 1, policy_version 88270 (0.0008) -[2023-10-09 03:41:25,578][88327] Updated weights for policy 1, policy_version 88280 (0.0011) -[2023-10-09 03:41:28,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 180715520. Throughput: 0: 1703.5, 1: 1702.1. Samples: 45190004. Policy #0 lag: (min: 35.0, avg: 53.9, max: 56.0) -[2023-10-09 03:41:28,974][87372] Avg episode reward: [(0, '7.630'), (1, '7.300')] -[2023-10-09 03:41:29,150][88326] Updated weights for policy 0, policy_version 88202 (0.0009) -[2023-10-09 03:41:29,519][88326] Updated weights for policy 0, policy_version 88212 (0.0007) -[2023-10-09 03:41:29,535][88327] Updated weights for policy 1, policy_version 88290 (0.0009) -[2023-10-09 03:41:29,878][88326] Updated weights for policy 0, policy_version 88222 (0.0010) -[2023-10-09 03:41:29,932][88327] Updated weights for policy 1, policy_version 88300 (0.0007) -[2023-10-09 03:41:30,287][88327] Updated weights for policy 1, policy_version 88310 (0.0007) -[2023-10-09 03:41:30,649][88327] Updated weights for policy 1, policy_version 88320 (0.0007) -[2023-10-09 03:41:33,902][88326] Updated weights for policy 0, policy_version 88232 (0.0009) -[2023-10-09 03:41:33,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 180781056. Throughput: 0: 1702.4, 1: 1721.8. Samples: 45211120. Policy #0 lag: (min: 35.0, avg: 53.9, max: 56.0) -[2023-10-09 03:41:33,975][87372] Avg episode reward: [(0, '7.270'), (1, '7.230')] -[2023-10-09 03:41:34,265][88326] Updated weights for policy 0, policy_version 88242 (0.0008) -[2023-10-09 03:41:34,468][88327] Updated weights for policy 1, policy_version 88330 (0.0009) -[2023-10-09 03:41:34,636][88326] Updated weights for policy 0, policy_version 88252 (0.0007) -[2023-10-09 03:41:34,828][88327] Updated weights for policy 1, policy_version 88340 (0.0009) -[2023-10-09 03:41:35,204][88327] Updated weights for policy 1, policy_version 88350 (0.0009) -[2023-10-09 03:41:38,542][88326] Updated weights for policy 0, policy_version 88262 (0.0007) -[2023-10-09 03:41:38,910][88326] Updated weights for policy 0, policy_version 88272 (0.0009) -[2023-10-09 03:41:38,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 180846592. Throughput: 0: 1701.1, 1: 1696.5. Samples: 45220318. Policy #0 lag: (min: 35.0, avg: 53.9, max: 56.0) -[2023-10-09 03:41:38,974][87372] Avg episode reward: [(0, '6.850'), (1, '7.540')] -[2023-10-09 03:41:39,271][88327] Updated weights for policy 1, policy_version 88360 (0.0008) -[2023-10-09 03:41:39,274][88326] Updated weights for policy 0, policy_version 88282 (0.0010) -[2023-10-09 03:41:39,642][88327] Updated weights for policy 1, policy_version 88370 (0.0009) -[2023-10-09 03:41:40,006][88327] Updated weights for policy 1, policy_version 88380 (0.0008) -[2023-10-09 03:41:43,261][88326] Updated weights for policy 0, policy_version 88292 (0.0010) -[2023-10-09 03:41:43,631][88326] Updated weights for policy 0, policy_version 88302 (0.0008) -[2023-10-09 03:41:43,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 180912128. Throughput: 0: 1701.2, 1: 1722.0. Samples: 45241436. Policy #0 lag: (min: 35.0, avg: 53.9, max: 56.0) -[2023-10-09 03:41:43,975][87372] Avg episode reward: [(0, '7.390'), (1, '8.050')] -[2023-10-09 03:41:43,996][88326] Updated weights for policy 0, policy_version 88312 (0.0008) -[2023-10-09 03:41:44,122][88327] Updated weights for policy 1, policy_version 88390 (0.0009) -[2023-10-09 03:41:44,488][88327] Updated weights for policy 1, policy_version 88400 (0.0009) -[2023-10-09 03:41:44,850][88327] Updated weights for policy 1, policy_version 88410 (0.0007) -[2023-10-09 03:41:47,869][88326] Updated weights for policy 0, policy_version 88322 (0.0007) -[2023-10-09 03:41:48,236][88326] Updated weights for policy 0, policy_version 88332 (0.0010) -[2023-10-09 03:41:48,615][88326] Updated weights for policy 0, policy_version 88342 (0.0007) -[2023-10-09 03:41:48,974][87372] Fps is (10 sec: 16384.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 181010432. Throughput: 0: 1693.3, 1: 1713.3. Samples: 45261844. Policy #0 lag: (min: 35.0, avg: 53.9, max: 56.0) -[2023-10-09 03:41:48,974][87372] Avg episode reward: [(0, '7.200'), (1, '7.380')] -[2023-10-09 03:41:48,977][88326] Updated weights for policy 0, policy_version 88352 (0.0008) -[2023-10-09 03:41:48,980][88327] Updated weights for policy 1, policy_version 88420 (0.0007) -[2023-10-09 03:41:49,350][88327] Updated weights for policy 1, policy_version 88430 (0.0008) -[2023-10-09 03:41:49,717][88327] Updated weights for policy 1, policy_version 88440 (0.0007) -[2023-10-09 03:41:53,020][88326] Updated weights for policy 0, policy_version 88362 (0.0009) -[2023-10-09 03:41:53,393][88326] Updated weights for policy 0, policy_version 88372 (0.0008) -[2023-10-09 03:41:53,766][88326] Updated weights for policy 0, policy_version 88382 (0.0008) -[2023-10-09 03:41:53,904][88327] Updated weights for policy 1, policy_version 88450 (0.0008) -[2023-10-09 03:41:53,974][87372] Fps is (10 sec: 16384.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 181075968. Throughput: 0: 1703.6, 1: 1697.6. Samples: 45271408. Policy #0 lag: (min: 35.0, avg: 53.9, max: 56.0) -[2023-10-09 03:41:53,975][87372] Avg episode reward: [(0, '7.440'), (1, '7.660')] -[2023-10-09 03:41:54,269][88327] Updated weights for policy 1, policy_version 88460 (0.0010) -[2023-10-09 03:41:54,639][88327] Updated weights for policy 1, policy_version 88470 (0.0009) -[2023-10-09 03:41:54,996][88327] Updated weights for policy 1, policy_version 88480 (0.0010) -[2023-10-09 03:41:57,924][88326] Updated weights for policy 0, policy_version 88392 (0.0009) -[2023-10-09 03:41:58,297][88326] Updated weights for policy 0, policy_version 88402 (0.0008) -[2023-10-09 03:41:58,676][88326] Updated weights for policy 0, policy_version 88412 (0.0008) -[2023-10-09 03:41:58,974][87372] Fps is (10 sec: 13106.7, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 181141504. Throughput: 0: 1706.5, 1: 1702.1. Samples: 45292164. Policy #0 lag: (min: 35.0, avg: 53.9, max: 56.0) -[2023-10-09 03:41:58,976][87372] Avg episode reward: [(0, '8.030'), (1, '7.180')] -[2023-10-09 03:41:59,152][88327] Updated weights for policy 1, policy_version 88490 (0.0010) -[2023-10-09 03:41:59,517][88327] Updated weights for policy 1, policy_version 88500 (0.0010) -[2023-10-09 03:41:59,879][88327] Updated weights for policy 1, policy_version 88510 (0.0010) -[2023-10-09 03:42:02,787][88326] Updated weights for policy 0, policy_version 88422 (0.0007) -[2023-10-09 03:42:03,178][88326] Updated weights for policy 0, policy_version 88432 (0.0007) -[2023-10-09 03:42:03,556][88326] Updated weights for policy 0, policy_version 88442 (0.0009) -[2023-10-09 03:42:03,729][88327] Updated weights for policy 1, policy_version 88520 (0.0008) -[2023-10-09 03:42:03,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 181207040. Throughput: 0: 1686.6, 1: 1701.3. Samples: 45312294. Policy #0 lag: (min: 35.0, avg: 53.9, max: 56.0) -[2023-10-09 03:42:03,975][87372] Avg episode reward: [(0, '7.840'), (1, '7.230')] -[2023-10-09 03:42:04,094][88327] Updated weights for policy 1, policy_version 88530 (0.0008) -[2023-10-09 03:42:04,462][88327] Updated weights for policy 1, policy_version 88540 (0.0009) -[2023-10-09 03:42:07,669][88326] Updated weights for policy 0, policy_version 88452 (0.0007) -[2023-10-09 03:42:08,053][88326] Updated weights for policy 0, policy_version 88462 (0.0007) -[2023-10-09 03:42:08,352][88327] Updated weights for policy 1, policy_version 88550 (0.0008) -[2023-10-09 03:42:08,420][88326] Updated weights for policy 0, policy_version 88472 (0.0008) -[2023-10-09 03:42:08,715][88327] Updated weights for policy 1, policy_version 88560 (0.0009) -[2023-10-09 03:42:08,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 181272576. Throughput: 0: 1697.6, 1: 1704.8. Samples: 45322116. Policy #0 lag: (min: 35.0, avg: 53.9, max: 56.0) -[2023-10-09 03:42:08,975][87372] Avg episode reward: [(0, '7.600'), (1, '7.550')] -[2023-10-09 03:42:09,083][88327] Updated weights for policy 1, policy_version 88570 (0.0008) -[2023-10-09 03:42:12,441][88326] Updated weights for policy 0, policy_version 88482 (0.0008) -[2023-10-09 03:42:12,810][88326] Updated weights for policy 0, policy_version 88492 (0.0009) -[2023-10-09 03:42:13,091][88327] Updated weights for policy 1, policy_version 88580 (0.0007) -[2023-10-09 03:42:13,181][88326] Updated weights for policy 0, policy_version 88502 (0.0009) -[2023-10-09 03:42:13,451][88327] Updated weights for policy 1, policy_version 88590 (0.0009) -[2023-10-09 03:42:13,549][88326] Updated weights for policy 0, policy_version 88512 (0.0009) -[2023-10-09 03:42:13,808][88327] Updated weights for policy 1, policy_version 88600 (0.0010) -[2023-10-09 03:42:13,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 181338112. Throughput: 0: 1697.4, 1: 1699.5. Samples: 45342868. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) -[2023-10-09 03:42:13,976][87372] Avg episode reward: [(0, '7.350'), (1, '7.450')] -[2023-10-09 03:42:17,571][88326] Updated weights for policy 0, policy_version 88522 (0.0007) -[2023-10-09 03:42:17,918][88327] Updated weights for policy 1, policy_version 88610 (0.0009) -[2023-10-09 03:42:17,937][88326] Updated weights for policy 0, policy_version 88532 (0.0009) -[2023-10-09 03:42:18,302][88326] Updated weights for policy 0, policy_version 88542 (0.0007) -[2023-10-09 03:42:18,337][88327] Updated weights for policy 1, policy_version 88620 (0.0009) -[2023-10-09 03:42:18,704][88327] Updated weights for policy 1, policy_version 88630 (0.0009) -[2023-10-09 03:42:18,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 181403648. Throughput: 0: 1672.8, 1: 1688.6. Samples: 45362382. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) -[2023-10-09 03:42:18,975][87372] Avg episode reward: [(0, '7.540'), (1, '6.980')] -[2023-10-09 03:42:19,065][88327] Updated weights for policy 1, policy_version 88640 (0.0009) -[2023-10-09 03:42:22,270][88326] Updated weights for policy 0, policy_version 88552 (0.0009) -[2023-10-09 03:42:22,639][88326] Updated weights for policy 0, policy_version 88562 (0.0008) -[2023-10-09 03:42:23,008][88326] Updated weights for policy 0, policy_version 88572 (0.0007) -[2023-10-09 03:42:23,120][88327] Updated weights for policy 1, policy_version 88650 (0.0008) -[2023-10-09 03:42:23,481][88327] Updated weights for policy 1, policy_version 88660 (0.0009) -[2023-10-09 03:42:23,843][88327] Updated weights for policy 1, policy_version 88670 (0.0009) -[2023-10-09 03:42:23,974][87372] Fps is (10 sec: 16384.3, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 181501952. Throughput: 0: 1697.0, 1: 1693.9. Samples: 45372912. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) -[2023-10-09 03:42:23,975][87372] Avg episode reward: [(0, '6.680'), (1, '7.500')] -[2023-10-09 03:42:27,116][88326] Updated weights for policy 0, policy_version 88582 (0.0008) -[2023-10-09 03:42:27,489][88326] Updated weights for policy 0, policy_version 88592 (0.0009) -[2023-10-09 03:42:27,857][88326] Updated weights for policy 0, policy_version 88602 (0.0007) -[2023-10-09 03:42:27,978][88327] Updated weights for policy 1, policy_version 88680 (0.0009) -[2023-10-09 03:42:28,340][88327] Updated weights for policy 1, policy_version 88690 (0.0009) -[2023-10-09 03:42:28,703][88327] Updated weights for policy 1, policy_version 88700 (0.0010) -[2023-10-09 03:42:28,974][87372] Fps is (10 sec: 16384.1, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 181567488. Throughput: 0: 1684.2, 1: 1692.8. Samples: 45393400. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) -[2023-10-09 03:42:28,975][87372] Avg episode reward: [(0, '6.400'), (1, '8.250')] -[2023-10-09 03:42:31,910][88326] Updated weights for policy 0, policy_version 88612 (0.0007) -[2023-10-09 03:42:32,279][88326] Updated weights for policy 0, policy_version 88622 (0.0009) -[2023-10-09 03:42:32,613][88327] Updated weights for policy 1, policy_version 88710 (0.0008) -[2023-10-09 03:42:32,653][88326] Updated weights for policy 0, policy_version 88632 (0.0007) -[2023-10-09 03:42:32,987][88327] Updated weights for policy 1, policy_version 88720 (0.0010) -[2023-10-09 03:42:33,350][88327] Updated weights for policy 1, policy_version 88730 (0.0010) -[2023-10-09 03:42:33,974][87372] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 181633024. Throughput: 0: 1665.6, 1: 1680.4. Samples: 45412416. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) -[2023-10-09 03:42:33,975][87372] Avg episode reward: [(0, '7.190'), (1, '7.780')] -[2023-10-09 03:42:33,983][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000088736_90865664.pth... -[2023-10-09 03:42:33,983][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000088640_90767360.pth... -[2023-10-09 03:42:34,013][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000087136_89227264.pth -[2023-10-09 03:42:34,024][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000087040_89128960.pth -[2023-10-09 03:42:36,543][88326] Updated weights for policy 0, policy_version 88642 (0.0007) -[2023-10-09 03:42:36,906][88326] Updated weights for policy 0, policy_version 88652 (0.0007) -[2023-10-09 03:42:37,275][88326] Updated weights for policy 0, policy_version 88662 (0.0008) -[2023-10-09 03:42:37,276][88327] Updated weights for policy 1, policy_version 88740 (0.0009) -[2023-10-09 03:42:37,630][88327] Updated weights for policy 1, policy_version 88750 (0.0008) -[2023-10-09 03:42:37,643][88326] Updated weights for policy 0, policy_version 88672 (0.0007) -[2023-10-09 03:42:38,000][88327] Updated weights for policy 1, policy_version 88760 (0.0009) -[2023-10-09 03:42:38,974][87372] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 181698560. Throughput: 0: 1691.4, 1: 1697.6. Samples: 45423914. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) -[2023-10-09 03:42:38,975][87372] Avg episode reward: [(0, '6.900'), (1, '7.370')] -[2023-10-09 03:42:41,625][88326] Updated weights for policy 0, policy_version 88682 (0.0007) -[2023-10-09 03:42:41,992][88326] Updated weights for policy 0, policy_version 88692 (0.0010) -[2023-10-09 03:42:42,025][88327] Updated weights for policy 1, policy_version 88770 (0.0011) -[2023-10-09 03:42:42,359][88326] Updated weights for policy 0, policy_version 88702 (0.0008) -[2023-10-09 03:42:42,401][88327] Updated weights for policy 1, policy_version 88780 (0.0007) -[2023-10-09 03:42:42,761][88327] Updated weights for policy 1, policy_version 88790 (0.0009) -[2023-10-09 03:42:43,130][88327] Updated weights for policy 1, policy_version 88800 (0.0010) -[2023-10-09 03:42:43,974][87372] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 181764096. Throughput: 0: 1669.8, 1: 1701.1. Samples: 45443854. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) -[2023-10-09 03:42:43,976][87372] Avg episode reward: [(0, '7.180'), (1, '8.120')] -[2023-10-09 03:42:46,439][88326] Updated weights for policy 0, policy_version 88712 (0.0010) -[2023-10-09 03:42:46,801][88326] Updated weights for policy 0, policy_version 88722 (0.0010) -[2023-10-09 03:42:47,176][88326] Updated weights for policy 0, policy_version 88732 (0.0007) -[2023-10-09 03:42:47,235][88327] Updated weights for policy 1, policy_version 88810 (0.0007) -[2023-10-09 03:42:47,595][88327] Updated weights for policy 1, policy_version 88820 (0.0009) -[2023-10-09 03:42:47,959][88327] Updated weights for policy 1, policy_version 88830 (0.0010) -[2023-10-09 03:42:48,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 181829632. Throughput: 0: 1685.2, 1: 1670.1. Samples: 45463280. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) -[2023-10-09 03:42:48,975][87372] Avg episode reward: [(0, '6.220'), (1, '6.860')] -[2023-10-09 03:42:51,288][88326] Updated weights for policy 0, policy_version 88742 (0.0008) -[2023-10-09 03:42:51,671][88326] Updated weights for policy 0, policy_version 88752 (0.0007) -[2023-10-09 03:42:52,043][88326] Updated weights for policy 0, policy_version 88762 (0.0008) -[2023-10-09 03:42:52,132][88327] Updated weights for policy 1, policy_version 88840 (0.0009) -[2023-10-09 03:42:52,495][88327] Updated weights for policy 1, policy_version 88850 (0.0010) -[2023-10-09 03:42:52,873][88327] Updated weights for policy 1, policy_version 88860 (0.0008) -[2023-10-09 03:42:53,974][87372] Fps is (10 sec: 13107.7, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 181895168. Throughput: 0: 1696.7, 1: 1691.6. Samples: 45474588. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) -[2023-10-09 03:42:53,975][87372] Avg episode reward: [(0, '6.860'), (1, '6.920')] -[2023-10-09 03:42:55,993][88326] Updated weights for policy 0, policy_version 88772 (0.0008) -[2023-10-09 03:42:56,358][88326] Updated weights for policy 0, policy_version 88782 (0.0008) -[2023-10-09 03:42:56,722][88326] Updated weights for policy 0, policy_version 88792 (0.0008) -[2023-10-09 03:42:56,802][88327] Updated weights for policy 1, policy_version 88870 (0.0007) -[2023-10-09 03:42:57,161][88327] Updated weights for policy 1, policy_version 88880 (0.0007) -[2023-10-09 03:42:57,530][88327] Updated weights for policy 1, policy_version 88890 (0.0010) -[2023-10-09 03:42:58,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 181960704. Throughput: 0: 1668.9, 1: 1680.5. Samples: 45493592. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) -[2023-10-09 03:42:58,974][87372] Avg episode reward: [(0, '6.830'), (1, '7.320')] -[2023-10-09 03:43:01,011][88326] Updated weights for policy 0, policy_version 88802 (0.0008) -[2023-10-09 03:43:01,384][88326] Updated weights for policy 0, policy_version 88812 (0.0008) -[2023-10-09 03:43:01,665][88327] Updated weights for policy 1, policy_version 88900 (0.0008) -[2023-10-09 03:43:01,761][88326] Updated weights for policy 0, policy_version 88822 (0.0008) -[2023-10-09 03:43:02,042][88327] Updated weights for policy 1, policy_version 88910 (0.0009) -[2023-10-09 03:43:02,130][88326] Updated weights for policy 0, policy_version 88832 (0.0007) -[2023-10-09 03:43:02,405][88327] Updated weights for policy 1, policy_version 88920 (0.0010) -[2023-10-09 03:43:03,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 182026240. Throughput: 0: 1691.2, 1: 1673.1. Samples: 45513772. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) -[2023-10-09 03:43:03,975][87372] Avg episode reward: [(0, '6.600'), (1, '7.490')] -[2023-10-09 03:43:06,269][88326] Updated weights for policy 0, policy_version 88842 (0.0007) -[2023-10-09 03:43:06,614][88327] Updated weights for policy 1, policy_version 88930 (0.0009) -[2023-10-09 03:43:06,642][88326] Updated weights for policy 0, policy_version 88852 (0.0007) -[2023-10-09 03:43:07,007][88326] Updated weights for policy 0, policy_version 88862 (0.0008) -[2023-10-09 03:43:07,030][88327] Updated weights for policy 1, policy_version 88940 (0.0010) -[2023-10-09 03:43:07,381][88327] Updated weights for policy 1, policy_version 88950 (0.0011) -[2023-10-09 03:43:07,747][88327] Updated weights for policy 1, policy_version 88960 (0.0009) -[2023-10-09 03:43:08,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 182091776. Throughput: 0: 1684.2, 1: 1694.6. Samples: 45524958. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) -[2023-10-09 03:43:08,975][87372] Avg episode reward: [(0, '6.960'), (1, '7.640')] -[2023-10-09 03:43:10,969][88326] Updated weights for policy 0, policy_version 88872 (0.0009) -[2023-10-09 03:43:11,342][88326] Updated weights for policy 0, policy_version 88882 (0.0007) -[2023-10-09 03:43:11,722][88326] Updated weights for policy 0, policy_version 88892 (0.0008) -[2023-10-09 03:43:11,786][88327] Updated weights for policy 1, policy_version 88970 (0.0008) -[2023-10-09 03:43:12,150][88327] Updated weights for policy 1, policy_version 88980 (0.0008) -[2023-10-09 03:43:12,522][88327] Updated weights for policy 1, policy_version 88990 (0.0009) -[2023-10-09 03:43:13,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 182157312. Throughput: 0: 1670.3, 1: 1673.2. Samples: 45543856. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-09 03:43:13,975][87372] Avg episode reward: [(0, '6.760'), (1, '7.690')] -[2023-10-09 03:43:15,698][88326] Updated weights for policy 0, policy_version 88902 (0.0008) -[2023-10-09 03:43:16,062][88326] Updated weights for policy 0, policy_version 88912 (0.0008) -[2023-10-09 03:43:16,436][88326] Updated weights for policy 0, policy_version 88922 (0.0008) -[2023-10-09 03:43:16,539][88327] Updated weights for policy 1, policy_version 89000 (0.0009) -[2023-10-09 03:43:16,899][88327] Updated weights for policy 1, policy_version 89010 (0.0010) -[2023-10-09 03:43:17,260][88327] Updated weights for policy 1, policy_version 89020 (0.0008) -[2023-10-09 03:43:18,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 182222848. Throughput: 0: 1702.3, 1: 1673.8. Samples: 45564342. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-09 03:43:18,975][87372] Avg episode reward: [(0, '6.510'), (1, '7.840')] -[2023-10-09 03:43:20,305][88326] Updated weights for policy 0, policy_version 88932 (0.0009) -[2023-10-09 03:43:20,685][88326] Updated weights for policy 0, policy_version 88942 (0.0008) -[2023-10-09 03:43:21,048][88326] Updated weights for policy 0, policy_version 88952 (0.0008) -[2023-10-09 03:43:21,255][88327] Updated weights for policy 1, policy_version 89030 (0.0008) -[2023-10-09 03:43:21,619][88327] Updated weights for policy 1, policy_version 89040 (0.0009) -[2023-10-09 03:43:21,988][88327] Updated weights for policy 1, policy_version 89050 (0.0007) -[2023-10-09 03:43:23,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 182288384. Throughput: 0: 1675.9, 1: 1684.4. Samples: 45575130. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-09 03:43:23,975][87372] Avg episode reward: [(0, '7.360'), (1, '7.260')] -[2023-10-09 03:43:25,198][88326] Updated weights for policy 0, policy_version 88962 (0.0007) -[2023-10-09 03:43:25,567][88326] Updated weights for policy 0, policy_version 88972 (0.0009) -[2023-10-09 03:43:25,935][88326] Updated weights for policy 0, policy_version 88982 (0.0007) -[2023-10-09 03:43:26,123][88327] Updated weights for policy 1, policy_version 89060 (0.0009) -[2023-10-09 03:43:26,299][88326] Updated weights for policy 0, policy_version 88992 (0.0007) -[2023-10-09 03:43:26,490][88327] Updated weights for policy 1, policy_version 89070 (0.0009) -[2023-10-09 03:43:26,851][88327] Updated weights for policy 1, policy_version 89080 (0.0009) -[2023-10-09 03:43:28,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 182353920. Throughput: 0: 1692.6, 1: 1657.8. Samples: 45594622. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-09 03:43:28,975][87372] Avg episode reward: [(0, '7.080'), (1, '7.140')] -[2023-10-09 03:43:30,188][88326] Updated weights for policy 0, policy_version 89002 (0.0010) -[2023-10-09 03:43:30,569][88326] Updated weights for policy 0, policy_version 89012 (0.0012) -[2023-10-09 03:43:30,904][88327] Updated weights for policy 1, policy_version 89090 (0.0008) -[2023-10-09 03:43:30,931][88326] Updated weights for policy 0, policy_version 89022 (0.0009) -[2023-10-09 03:43:31,256][88327] Updated weights for policy 1, policy_version 89100 (0.0009) -[2023-10-09 03:43:31,621][88327] Updated weights for policy 1, policy_version 89110 (0.0008) -[2023-10-09 03:43:31,979][88327] Updated weights for policy 1, policy_version 89120 (0.0007) -[2023-10-09 03:43:33,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 182419456. Throughput: 0: 1697.7, 1: 1683.7. Samples: 45615442. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-09 03:43:33,976][87372] Avg episode reward: [(0, '7.460'), (1, '7.560')] -[2023-10-09 03:43:34,927][88326] Updated weights for policy 0, policy_version 89032 (0.0010) -[2023-10-09 03:43:35,307][88326] Updated weights for policy 0, policy_version 89042 (0.0010) -[2023-10-09 03:43:35,677][88326] Updated weights for policy 0, policy_version 89052 (0.0010) -[2023-10-09 03:43:36,037][88327] Updated weights for policy 1, policy_version 89130 (0.0009) -[2023-10-09 03:43:36,398][88327] Updated weights for policy 1, policy_version 89140 (0.0011) -[2023-10-09 03:43:36,768][88327] Updated weights for policy 1, policy_version 89150 (0.0007) -[2023-10-09 03:43:38,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 182484992. Throughput: 0: 1673.6, 1: 1676.0. Samples: 45625324. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-09 03:43:38,975][87372] Avg episode reward: [(0, '6.710'), (1, '7.240')] -[2023-10-09 03:43:39,705][88326] Updated weights for policy 0, policy_version 89062 (0.0008) -[2023-10-09 03:43:40,081][88326] Updated weights for policy 0, policy_version 89072 (0.0010) -[2023-10-09 03:43:40,452][88326] Updated weights for policy 0, policy_version 89082 (0.0010) -[2023-10-09 03:43:40,884][88327] Updated weights for policy 1, policy_version 89160 (0.0008) -[2023-10-09 03:43:41,248][88327] Updated weights for policy 1, policy_version 89170 (0.0008) -[2023-10-09 03:43:41,621][88327] Updated weights for policy 1, policy_version 89180 (0.0009) -[2023-10-09 03:43:43,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 182550528. Throughput: 0: 1703.6, 1: 1670.4. Samples: 45645426. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-09 03:43:43,975][87372] Avg episode reward: [(0, '6.160'), (1, '7.770')] -[2023-10-09 03:43:44,641][88326] Updated weights for policy 0, policy_version 89092 (0.0008) -[2023-10-09 03:43:45,033][88326] Updated weights for policy 0, policy_version 89102 (0.0007) -[2023-10-09 03:43:45,403][88326] Updated weights for policy 0, policy_version 89112 (0.0007) -[2023-10-09 03:43:45,566][88327] Updated weights for policy 1, policy_version 89190 (0.0008) -[2023-10-09 03:43:45,927][88327] Updated weights for policy 1, policy_version 89200 (0.0009) -[2023-10-09 03:43:46,290][88327] Updated weights for policy 1, policy_version 89210 (0.0012) -[2023-10-09 03:43:48,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 182616064. Throughput: 0: 1703.2, 1: 1685.0. Samples: 45666242. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-09 03:43:48,975][87372] Avg episode reward: [(0, '6.860'), (1, '7.760')] -[2023-10-09 03:43:49,189][88326] Updated weights for policy 0, policy_version 89122 (0.0008) -[2023-10-09 03:43:49,566][88326] Updated weights for policy 0, policy_version 89132 (0.0008) -[2023-10-09 03:43:49,931][88326] Updated weights for policy 0, policy_version 89142 (0.0010) -[2023-10-09 03:43:50,299][88326] Updated weights for policy 0, policy_version 89152 (0.0009) -[2023-10-09 03:43:50,460][88327] Updated weights for policy 1, policy_version 89220 (0.0010) -[2023-10-09 03:43:50,827][88327] Updated weights for policy 1, policy_version 89230 (0.0009) -[2023-10-09 03:43:51,199][88327] Updated weights for policy 1, policy_version 89240 (0.0007) -[2023-10-09 03:43:53,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 182681600. Throughput: 0: 1687.2, 1: 1666.2. Samples: 45675858. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-09 03:43:53,975][87372] Avg episode reward: [(0, '6.880'), (1, '7.330')] -[2023-10-09 03:43:54,436][88326] Updated weights for policy 0, policy_version 89162 (0.0008) -[2023-10-09 03:43:54,807][88326] Updated weights for policy 0, policy_version 89172 (0.0010) -[2023-10-09 03:43:55,175][88326] Updated weights for policy 0, policy_version 89182 (0.0007) -[2023-10-09 03:43:55,329][88327] Updated weights for policy 1, policy_version 89250 (0.0009) -[2023-10-09 03:43:55,746][88327] Updated weights for policy 1, policy_version 89260 (0.0008) -[2023-10-09 03:43:56,107][88327] Updated weights for policy 1, policy_version 89270 (0.0008) -[2023-10-09 03:43:56,467][88327] Updated weights for policy 1, policy_version 89280 (0.0008) -[2023-10-09 03:43:58,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 182747136. Throughput: 0: 1710.1, 1: 1671.5. Samples: 45696030. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-09 03:43:58,975][87372] Avg episode reward: [(0, '6.770'), (1, '7.340')] -[2023-10-09 03:43:59,134][88326] Updated weights for policy 0, policy_version 89192 (0.0009) -[2023-10-09 03:43:59,501][88326] Updated weights for policy 0, policy_version 89202 (0.0007) -[2023-10-09 03:43:59,870][88326] Updated weights for policy 0, policy_version 89212 (0.0007) -[2023-10-09 03:44:00,504][88327] Updated weights for policy 1, policy_version 89290 (0.0010) -[2023-10-09 03:44:00,868][88327] Updated weights for policy 1, policy_version 89300 (0.0010) -[2023-10-09 03:44:01,227][88327] Updated weights for policy 1, policy_version 89310 (0.0008) -[2023-10-09 03:44:03,897][88326] Updated weights for policy 0, policy_version 89222 (0.0007) -[2023-10-09 03:44:03,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 182812672. Throughput: 0: 1709.2, 1: 1686.9. Samples: 45717162. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-09 03:44:03,975][87372] Avg episode reward: [(0, '7.430'), (1, '7.490')] -[2023-10-09 03:44:04,275][88326] Updated weights for policy 0, policy_version 89232 (0.0007) -[2023-10-09 03:44:04,655][88326] Updated weights for policy 0, policy_version 89242 (0.0009) -[2023-10-09 03:44:05,224][88327] Updated weights for policy 1, policy_version 89320 (0.0008) -[2023-10-09 03:44:05,585][88327] Updated weights for policy 1, policy_version 89330 (0.0008) -[2023-10-09 03:44:05,943][88327] Updated weights for policy 1, policy_version 89340 (0.0009) -[2023-10-09 03:44:08,613][88326] Updated weights for policy 0, policy_version 89252 (0.0009) -[2023-10-09 03:44:08,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 182878208. Throughput: 0: 1701.3, 1: 1661.8. Samples: 45726470. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-09 03:44:08,974][87372] Avg episode reward: [(0, '6.900'), (1, '7.810')] -[2023-10-09 03:44:08,987][88326] Updated weights for policy 0, policy_version 89262 (0.0010) -[2023-10-09 03:44:09,358][88326] Updated weights for policy 0, policy_version 89272 (0.0009) -[2023-10-09 03:44:09,910][88327] Updated weights for policy 1, policy_version 89350 (0.0008) -[2023-10-09 03:44:10,280][88327] Updated weights for policy 1, policy_version 89360 (0.0009) -[2023-10-09 03:44:10,635][88327] Updated weights for policy 1, policy_version 89370 (0.0009) -[2023-10-09 03:44:13,268][88326] Updated weights for policy 0, policy_version 89282 (0.0008) -[2023-10-09 03:44:13,634][88326] Updated weights for policy 0, policy_version 89292 (0.0008) -[2023-10-09 03:44:13,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 182943744. Throughput: 0: 1706.5, 1: 1691.1. Samples: 45747514. Policy #0 lag: (min: 31.0, avg: 31.1, max: 39.0) -[2023-10-09 03:44:13,974][87372] Avg episode reward: [(0, '7.010'), (1, '7.410')] -[2023-10-09 03:44:14,002][88326] Updated weights for policy 0, policy_version 89302 (0.0008) -[2023-10-09 03:44:14,374][88326] Updated weights for policy 0, policy_version 89312 (0.0009) -[2023-10-09 03:44:14,583][88327] Updated weights for policy 1, policy_version 89380 (0.0008) -[2023-10-09 03:44:14,946][88327] Updated weights for policy 1, policy_version 89390 (0.0007) -[2023-10-09 03:44:15,305][88327] Updated weights for policy 1, policy_version 89400 (0.0009) -[2023-10-09 03:44:18,316][88326] Updated weights for policy 0, policy_version 89322 (0.0009) -[2023-10-09 03:44:18,693][88326] Updated weights for policy 0, policy_version 89332 (0.0007) -[2023-10-09 03:44:18,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 183009280. Throughput: 0: 1702.1, 1: 1700.3. Samples: 45768550. Policy #0 lag: (min: 31.0, avg: 31.1, max: 39.0) -[2023-10-09 03:44:18,975][87372] Avg episode reward: [(0, '7.160'), (1, '6.890')] -[2023-10-09 03:44:19,071][88326] Updated weights for policy 0, policy_version 89342 (0.0007) -[2023-10-09 03:44:19,369][88327] Updated weights for policy 1, policy_version 89410 (0.0010) -[2023-10-09 03:44:19,741][88327] Updated weights for policy 1, policy_version 89420 (0.0010) -[2023-10-09 03:44:20,097][88327] Updated weights for policy 1, policy_version 89430 (0.0007) -[2023-10-09 03:44:20,466][88327] Updated weights for policy 1, policy_version 89440 (0.0007) -[2023-10-09 03:44:23,169][88326] Updated weights for policy 0, policy_version 89352 (0.0007) -[2023-10-09 03:44:23,531][88326] Updated weights for policy 0, policy_version 89362 (0.0008) -[2023-10-09 03:44:23,902][88326] Updated weights for policy 0, policy_version 89372 (0.0008) -[2023-10-09 03:44:23,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 183074816. Throughput: 0: 1708.2, 1: 1684.1. Samples: 45777974. Policy #0 lag: (min: 31.0, avg: 31.1, max: 39.0) -[2023-10-09 03:44:23,975][87372] Avg episode reward: [(0, '7.200'), (1, '7.570')] -[2023-10-09 03:44:24,524][88327] Updated weights for policy 1, policy_version 89450 (0.0009) -[2023-10-09 03:44:24,882][88327] Updated weights for policy 1, policy_version 89460 (0.0008) -[2023-10-09 03:44:25,246][88327] Updated weights for policy 1, policy_version 89470 (0.0008) -[2023-10-09 03:44:27,793][88326] Updated weights for policy 0, policy_version 89382 (0.0008) -[2023-10-09 03:44:28,172][88326] Updated weights for policy 0, policy_version 89392 (0.0007) -[2023-10-09 03:44:28,544][88326] Updated weights for policy 0, policy_version 89402 (0.0009) -[2023-10-09 03:44:28,974][87372] Fps is (10 sec: 16384.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 183173120. Throughput: 0: 1709.3, 1: 1707.3. Samples: 45799172. Policy #0 lag: (min: 31.0, avg: 31.1, max: 39.0) -[2023-10-09 03:44:28,975][87372] Avg episode reward: [(0, '7.270'), (1, '7.380')] -[2023-10-09 03:44:29,244][88327] Updated weights for policy 1, policy_version 89480 (0.0009) -[2023-10-09 03:44:29,611][88327] Updated weights for policy 1, policy_version 89490 (0.0008) -[2023-10-09 03:44:29,971][88327] Updated weights for policy 1, policy_version 89500 (0.0009) -[2023-10-09 03:44:32,700][88326] Updated weights for policy 0, policy_version 89412 (0.0011) -[2023-10-09 03:44:33,083][88326] Updated weights for policy 0, policy_version 89422 (0.0008) -[2023-10-09 03:44:33,447][88326] Updated weights for policy 0, policy_version 89432 (0.0007) -[2023-10-09 03:44:33,901][88327] Updated weights for policy 1, policy_version 89510 (0.0009) -[2023-10-09 03:44:33,974][87372] Fps is (10 sec: 16383.9, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 183238656. Throughput: 0: 1691.3, 1: 1709.9. Samples: 45819298. Policy #0 lag: (min: 31.0, avg: 31.1, max: 39.0) -[2023-10-09 03:44:33,975][87372] Avg episode reward: [(0, '6.770'), (1, '7.210')] -[2023-10-09 03:44:33,981][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000089440_91586560.pth... -[2023-10-09 03:44:34,011][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000087840_89948160.pth -[2023-10-09 03:44:34,259][88327] Updated weights for policy 1, policy_version 89520 (0.0011) -[2023-10-09 03:44:34,629][88327] Updated weights for policy 1, policy_version 89530 (0.0010) -[2023-10-09 03:44:34,846][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000089536_91684864.pth... -[2023-10-09 03:44:34,874][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000087936_90046464.pth -[2023-10-09 03:44:37,452][88326] Updated weights for policy 0, policy_version 89442 (0.0008) -[2023-10-09 03:44:37,818][88326] Updated weights for policy 0, policy_version 89452 (0.0009) -[2023-10-09 03:44:38,188][88326] Updated weights for policy 0, policy_version 89462 (0.0007) -[2023-10-09 03:44:38,560][88326] Updated weights for policy 0, policy_version 89472 (0.0008) -[2023-10-09 03:44:38,596][88327] Updated weights for policy 1, policy_version 89540 (0.0008) -[2023-10-09 03:44:38,958][88327] Updated weights for policy 1, policy_version 89550 (0.0008) -[2023-10-09 03:44:38,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 183304192. Throughput: 0: 1706.4, 1: 1701.7. Samples: 45829220. Policy #0 lag: (min: 31.0, avg: 31.1, max: 39.0) -[2023-10-09 03:44:38,975][87372] Avg episode reward: [(0, '7.570'), (1, '7.400')] -[2023-10-09 03:44:39,323][88327] Updated weights for policy 1, policy_version 89560 (0.0009) -[2023-10-09 03:44:42,657][88326] Updated weights for policy 0, policy_version 89482 (0.0009) -[2023-10-09 03:44:43,040][88326] Updated weights for policy 0, policy_version 89492 (0.0009) -[2023-10-09 03:44:43,404][88326] Updated weights for policy 0, policy_version 89502 (0.0007) -[2023-10-09 03:44:43,454][88327] Updated weights for policy 1, policy_version 89570 (0.0009) -[2023-10-09 03:44:43,836][88327] Updated weights for policy 1, policy_version 89580 (0.0010) -[2023-10-09 03:44:43,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 183369728. Throughput: 0: 1704.5, 1: 1721.2. Samples: 45850186. Policy #0 lag: (min: 31.0, avg: 31.1, max: 39.0) -[2023-10-09 03:44:43,975][87372] Avg episode reward: [(0, '6.900'), (1, '7.400')] -[2023-10-09 03:44:44,197][88327] Updated weights for policy 1, policy_version 89590 (0.0009) -[2023-10-09 03:44:44,560][88327] Updated weights for policy 1, policy_version 89600 (0.0008) -[2023-10-09 03:44:47,469][88326] Updated weights for policy 0, policy_version 89512 (0.0008) -[2023-10-09 03:44:47,846][88326] Updated weights for policy 0, policy_version 89522 (0.0009) -[2023-10-09 03:44:48,204][88326] Updated weights for policy 0, policy_version 89532 (0.0009) -[2023-10-09 03:44:48,545][88327] Updated weights for policy 1, policy_version 89610 (0.0007) -[2023-10-09 03:44:48,907][88327] Updated weights for policy 1, policy_version 89620 (0.0008) -[2023-10-09 03:44:48,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 183435264. Throughput: 0: 1673.0, 1: 1722.9. Samples: 45869980. Policy #0 lag: (min: 31.0, avg: 31.1, max: 39.0) -[2023-10-09 03:44:48,974][87372] Avg episode reward: [(0, '6.570'), (1, '7.610')] -[2023-10-09 03:44:49,272][88327] Updated weights for policy 1, policy_version 89630 (0.0007) -[2023-10-09 03:44:52,292][88326] Updated weights for policy 0, policy_version 89542 (0.0010) -[2023-10-09 03:44:52,667][88326] Updated weights for policy 0, policy_version 89552 (0.0010) -[2023-10-09 03:44:53,048][88326] Updated weights for policy 0, policy_version 89562 (0.0008) -[2023-10-09 03:44:53,333][88327] Updated weights for policy 1, policy_version 89640 (0.0009) -[2023-10-09 03:44:53,699][88327] Updated weights for policy 1, policy_version 89650 (0.0010) -[2023-10-09 03:44:53,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 183500800. Throughput: 0: 1694.7, 1: 1722.3. Samples: 45880236. Policy #0 lag: (min: 31.0, avg: 31.1, max: 39.0) -[2023-10-09 03:44:53,975][87372] Avg episode reward: [(0, '6.980'), (1, '7.440')] -[2023-10-09 03:44:54,080][88327] Updated weights for policy 1, policy_version 89660 (0.0009) -[2023-10-09 03:44:57,010][88326] Updated weights for policy 0, policy_version 89572 (0.0009) -[2023-10-09 03:44:57,376][88326] Updated weights for policy 0, policy_version 89582 (0.0010) -[2023-10-09 03:44:57,753][88326] Updated weights for policy 0, policy_version 89592 (0.0009) -[2023-10-09 03:44:57,831][88327] Updated weights for policy 1, policy_version 89670 (0.0008) -[2023-10-09 03:44:58,189][88327] Updated weights for policy 1, policy_version 89680 (0.0009) -[2023-10-09 03:44:58,553][88327] Updated weights for policy 1, policy_version 89690 (0.0010) -[2023-10-09 03:44:58,974][87372] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 183599104. Throughput: 0: 1685.6, 1: 1721.1. Samples: 45900818. Policy #0 lag: (min: 31.0, avg: 31.1, max: 39.0) -[2023-10-09 03:44:58,975][87372] Avg episode reward: [(0, '6.590'), (1, '7.040')] -[2023-10-09 03:45:01,859][88326] Updated weights for policy 0, policy_version 89602 (0.0008) -[2023-10-09 03:45:02,227][88326] Updated weights for policy 0, policy_version 89612 (0.0007) -[2023-10-09 03:45:02,538][88327] Updated weights for policy 1, policy_version 89700 (0.0007) -[2023-10-09 03:45:02,592][88326] Updated weights for policy 0, policy_version 89622 (0.0008) -[2023-10-09 03:45:02,896][88327] Updated weights for policy 1, policy_version 89710 (0.0008) -[2023-10-09 03:45:02,950][88326] Updated weights for policy 0, policy_version 89632 (0.0008) -[2023-10-09 03:45:03,263][88327] Updated weights for policy 1, policy_version 89720 (0.0009) -[2023-10-09 03:45:03,974][87372] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 183664640. Throughput: 0: 1668.7, 1: 1701.5. Samples: 45920208. Policy #0 lag: (min: 31.0, avg: 31.1, max: 39.0) -[2023-10-09 03:45:03,975][87372] Avg episode reward: [(0, '6.750'), (1, '7.620')] -[2023-10-09 03:45:07,045][88326] Updated weights for policy 0, policy_version 89642 (0.0008) -[2023-10-09 03:45:07,420][88326] Updated weights for policy 0, policy_version 89652 (0.0007) -[2023-10-09 03:45:07,574][88327] Updated weights for policy 1, policy_version 89730 (0.0007) -[2023-10-09 03:45:07,789][88326] Updated weights for policy 0, policy_version 89662 (0.0008) -[2023-10-09 03:45:07,943][88327] Updated weights for policy 1, policy_version 89740 (0.0008) -[2023-10-09 03:45:08,308][88327] Updated weights for policy 1, policy_version 89750 (0.0009) -[2023-10-09 03:45:08,661][88327] Updated weights for policy 1, policy_version 89760 (0.0009) -[2023-10-09 03:45:08,974][87372] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 183730176. Throughput: 0: 1690.2, 1: 1717.4. Samples: 45931314. Policy #0 lag: (min: 18.0, avg: 18.0, max: 22.0) -[2023-10-09 03:45:08,975][87372] Avg episode reward: [(0, '6.420'), (1, '8.580')] -[2023-10-09 03:45:11,921][88326] Updated weights for policy 0, policy_version 89672 (0.0010) -[2023-10-09 03:45:12,297][88326] Updated weights for policy 0, policy_version 89682 (0.0008) -[2023-10-09 03:45:12,658][88326] Updated weights for policy 0, policy_version 89692 (0.0007) -[2023-10-09 03:45:12,787][88327] Updated weights for policy 1, policy_version 89770 (0.0007) -[2023-10-09 03:45:13,152][88327] Updated weights for policy 1, policy_version 89780 (0.0008) -[2023-10-09 03:45:13,522][88327] Updated weights for policy 1, policy_version 89790 (0.0009) -[2023-10-09 03:45:13,974][87372] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 183795712. Throughput: 0: 1674.0, 1: 1715.5. Samples: 45951700. Policy #0 lag: (min: 18.0, avg: 18.0, max: 22.0) -[2023-10-09 03:45:13,975][87372] Avg episode reward: [(0, '6.230'), (1, '8.000')] -[2023-10-09 03:45:16,624][88326] Updated weights for policy 0, policy_version 89702 (0.0007) -[2023-10-09 03:45:16,985][88326] Updated weights for policy 0, policy_version 89712 (0.0008) -[2023-10-09 03:45:17,348][88326] Updated weights for policy 0, policy_version 89722 (0.0008) -[2023-10-09 03:45:17,524][88327] Updated weights for policy 1, policy_version 89800 (0.0007) -[2023-10-09 03:45:17,895][88327] Updated weights for policy 1, policy_version 89810 (0.0009) -[2023-10-09 03:45:18,263][88327] Updated weights for policy 1, policy_version 89820 (0.0009) -[2023-10-09 03:45:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 183861248. Throughput: 0: 1682.4, 1: 1692.0. Samples: 45971142. Policy #0 lag: (min: 18.0, avg: 18.0, max: 22.0) -[2023-10-09 03:45:18,975][87372] Avg episode reward: [(0, '6.890'), (1, '7.320')] -[2023-10-09 03:45:21,359][88326] Updated weights for policy 0, policy_version 89732 (0.0010) -[2023-10-09 03:45:21,729][88326] Updated weights for policy 0, policy_version 89742 (0.0009) -[2023-10-09 03:45:22,089][88326] Updated weights for policy 0, policy_version 89752 (0.0008) -[2023-10-09 03:45:22,313][88327] Updated weights for policy 1, policy_version 89830 (0.0008) -[2023-10-09 03:45:22,677][88327] Updated weights for policy 1, policy_version 89840 (0.0008) -[2023-10-09 03:45:23,048][88327] Updated weights for policy 1, policy_version 89850 (0.0009) -[2023-10-09 03:45:23,974][87372] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 183926784. Throughput: 0: 1692.6, 1: 1710.8. Samples: 45982374. Policy #0 lag: (min: 18.0, avg: 18.0, max: 22.0) -[2023-10-09 03:45:23,975][87372] Avg episode reward: [(0, '6.970'), (1, '7.400')] -[2023-10-09 03:45:26,206][88326] Updated weights for policy 0, policy_version 89762 (0.0008) -[2023-10-09 03:45:26,573][88326] Updated weights for policy 0, policy_version 89772 (0.0009) -[2023-10-09 03:45:26,882][88327] Updated weights for policy 1, policy_version 89860 (0.0009) -[2023-10-09 03:45:26,935][88326] Updated weights for policy 0, policy_version 89782 (0.0010) -[2023-10-09 03:45:27,250][88327] Updated weights for policy 1, policy_version 89870 (0.0009) -[2023-10-09 03:45:27,302][88326] Updated weights for policy 0, policy_version 89792 (0.0007) -[2023-10-09 03:45:27,615][88327] Updated weights for policy 1, policy_version 89880 (0.0009) -[2023-10-09 03:45:28,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 183992320. Throughput: 0: 1665.2, 1: 1703.5. Samples: 46001778. Policy #0 lag: (min: 18.0, avg: 18.0, max: 22.0) -[2023-10-09 03:45:28,975][87372] Avg episode reward: [(0, '7.410'), (1, '6.810')] -[2023-10-09 03:45:31,297][88326] Updated weights for policy 0, policy_version 89802 (0.0008) -[2023-10-09 03:45:31,625][88327] Updated weights for policy 1, policy_version 89890 (0.0009) -[2023-10-09 03:45:31,668][88326] Updated weights for policy 0, policy_version 89812 (0.0011) -[2023-10-09 03:45:32,036][88327] Updated weights for policy 1, policy_version 89900 (0.0010) -[2023-10-09 03:45:32,039][88326] Updated weights for policy 0, policy_version 89822 (0.0007) -[2023-10-09 03:45:32,408][88327] Updated weights for policy 1, policy_version 89910 (0.0009) -[2023-10-09 03:45:32,767][88327] Updated weights for policy 1, policy_version 89920 (0.0009) -[2023-10-09 03:45:33,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 184057856. Throughput: 0: 1691.1, 1: 1678.5. Samples: 46021610. Policy #0 lag: (min: 18.0, avg: 18.0, max: 22.0) -[2023-10-09 03:45:33,975][87372] Avg episode reward: [(0, '6.760'), (1, '6.470')] -[2023-10-09 03:45:35,887][88326] Updated weights for policy 0, policy_version 89832 (0.0009) -[2023-10-09 03:45:36,250][88326] Updated weights for policy 0, policy_version 89842 (0.0008) -[2023-10-09 03:45:36,618][88326] Updated weights for policy 0, policy_version 89852 (0.0007) -[2023-10-09 03:45:36,716][88327] Updated weights for policy 1, policy_version 89930 (0.0009) -[2023-10-09 03:45:37,076][88327] Updated weights for policy 1, policy_version 89940 (0.0010) -[2023-10-09 03:45:37,436][88327] Updated weights for policy 1, policy_version 89950 (0.0011) -[2023-10-09 03:45:38,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 184123392. Throughput: 0: 1682.1, 1: 1707.2. Samples: 46032756. Policy #0 lag: (min: 18.0, avg: 18.0, max: 22.0) -[2023-10-09 03:45:38,975][87372] Avg episode reward: [(0, '6.780'), (1, '6.970')] -[2023-10-09 03:45:40,653][88326] Updated weights for policy 0, policy_version 89862 (0.0009) -[2023-10-09 03:45:41,029][88326] Updated weights for policy 0, policy_version 89872 (0.0010) -[2023-10-09 03:45:41,401][88326] Updated weights for policy 0, policy_version 89882 (0.0010) -[2023-10-09 03:45:41,654][88327] Updated weights for policy 1, policy_version 89960 (0.0009) -[2023-10-09 03:45:42,023][88327] Updated weights for policy 1, policy_version 89970 (0.0009) -[2023-10-09 03:45:42,391][88327] Updated weights for policy 1, policy_version 89980 (0.0009) -[2023-10-09 03:45:43,974][87372] Fps is (10 sec: 13107.6, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 184188928. Throughput: 0: 1677.4, 1: 1686.3. Samples: 46052182. Policy #0 lag: (min: 18.0, avg: 18.0, max: 22.0) -[2023-10-09 03:45:43,975][87372] Avg episode reward: [(0, '7.230'), (1, '7.360')] -[2023-10-09 03:45:45,238][88326] Updated weights for policy 0, policy_version 89892 (0.0008) -[2023-10-09 03:45:45,612][88326] Updated weights for policy 0, policy_version 89902 (0.0010) -[2023-10-09 03:45:45,986][88326] Updated weights for policy 0, policy_version 89912 (0.0007) -[2023-10-09 03:45:46,414][88327] Updated weights for policy 1, policy_version 89990 (0.0008) -[2023-10-09 03:45:46,784][88327] Updated weights for policy 1, policy_version 90000 (0.0007) -[2023-10-09 03:45:47,144][88327] Updated weights for policy 1, policy_version 90010 (0.0009) -[2023-10-09 03:45:48,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.2, 300 sec: 13551.5). Total num frames: 184254464. Throughput: 0: 1701.9, 1: 1688.7. Samples: 46072788. Policy #0 lag: (min: 18.0, avg: 18.0, max: 22.0) -[2023-10-09 03:45:48,975][87372] Avg episode reward: [(0, '6.960'), (1, '7.200')] -[2023-10-09 03:45:50,098][88326] Updated weights for policy 0, policy_version 89922 (0.0008) -[2023-10-09 03:45:50,467][88326] Updated weights for policy 0, policy_version 89932 (0.0008) -[2023-10-09 03:45:50,837][88326] Updated weights for policy 0, policy_version 89942 (0.0009) -[2023-10-09 03:45:51,200][88326] Updated weights for policy 0, policy_version 89952 (0.0009) -[2023-10-09 03:45:51,304][88327] Updated weights for policy 1, policy_version 90020 (0.0010) -[2023-10-09 03:45:51,671][88327] Updated weights for policy 1, policy_version 90030 (0.0008) -[2023-10-09 03:45:52,040][88327] Updated weights for policy 1, policy_version 90040 (0.0008) -[2023-10-09 03:45:53,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 184320000. Throughput: 0: 1673.6, 1: 1699.7. Samples: 46083114. Policy #0 lag: (min: 18.0, avg: 18.0, max: 22.0) -[2023-10-09 03:45:53,975][87372] Avg episode reward: [(0, '7.080'), (1, '7.540')] -[2023-10-09 03:45:55,242][88326] Updated weights for policy 0, policy_version 89962 (0.0007) -[2023-10-09 03:45:55,604][88326] Updated weights for policy 0, policy_version 89972 (0.0007) -[2023-10-09 03:45:55,971][88326] Updated weights for policy 0, policy_version 89982 (0.0008) -[2023-10-09 03:45:55,975][88327] Updated weights for policy 1, policy_version 90050 (0.0009) -[2023-10-09 03:45:56,351][88327] Updated weights for policy 1, policy_version 90060 (0.0009) -[2023-10-09 03:45:56,718][88327] Updated weights for policy 1, policy_version 90070 (0.0008) -[2023-10-09 03:45:57,081][88327] Updated weights for policy 1, policy_version 90080 (0.0008) -[2023-10-09 03:45:58,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 184385536. Throughput: 0: 1693.9, 1: 1671.5. Samples: 46103144. Policy #0 lag: (min: 18.0, avg: 18.0, max: 22.0) -[2023-10-09 03:45:58,975][87372] Avg episode reward: [(0, '6.430'), (1, '7.510')] -[2023-10-09 03:46:00,052][88326] Updated weights for policy 0, policy_version 89992 (0.0007) -[2023-10-09 03:46:00,420][88326] Updated weights for policy 0, policy_version 90002 (0.0008) -[2023-10-09 03:46:00,786][88326] Updated weights for policy 0, policy_version 90012 (0.0009) -[2023-10-09 03:46:01,040][88327] Updated weights for policy 1, policy_version 90090 (0.0009) -[2023-10-09 03:46:01,424][88327] Updated weights for policy 1, policy_version 90100 (0.0009) -[2023-10-09 03:46:01,785][88327] Updated weights for policy 1, policy_version 90110 (0.0010) -[2023-10-09 03:46:03,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 184451072. Throughput: 0: 1705.4, 1: 1691.1. Samples: 46123984. Policy #0 lag: (min: 18.0, avg: 18.0, max: 22.0) -[2023-10-09 03:46:03,975][87372] Avg episode reward: [(0, '7.290'), (1, '7.750')] -[2023-10-09 03:46:04,881][88326] Updated weights for policy 0, policy_version 90022 (0.0008) -[2023-10-09 03:46:05,254][88326] Updated weights for policy 0, policy_version 90032 (0.0008) -[2023-10-09 03:46:05,623][88326] Updated weights for policy 0, policy_version 90042 (0.0007) -[2023-10-09 03:46:05,784][88327] Updated weights for policy 1, policy_version 90120 (0.0009) -[2023-10-09 03:46:06,158][88327] Updated weights for policy 1, policy_version 90130 (0.0009) -[2023-10-09 03:46:06,516][88327] Updated weights for policy 1, policy_version 90140 (0.0010) -[2023-10-09 03:46:08,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 184516608. Throughput: 0: 1675.6, 1: 1685.6. Samples: 46133628. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:46:08,975][87372] Avg episode reward: [(0, '7.370'), (1, '7.490')] -[2023-10-09 03:46:09,662][88326] Updated weights for policy 0, policy_version 90052 (0.0007) -[2023-10-09 03:46:10,026][88326] Updated weights for policy 0, policy_version 90062 (0.0007) -[2023-10-09 03:46:10,396][88326] Updated weights for policy 0, policy_version 90072 (0.0008) -[2023-10-09 03:46:10,636][88327] Updated weights for policy 1, policy_version 90150 (0.0008) -[2023-10-09 03:46:10,998][88327] Updated weights for policy 1, policy_version 90160 (0.0009) -[2023-10-09 03:46:11,363][88327] Updated weights for policy 1, policy_version 90170 (0.0008) -[2023-10-09 03:46:13,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 184582144. Throughput: 0: 1704.2, 1: 1672.9. Samples: 46153748. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:46:13,975][87372] Avg episode reward: [(0, '7.460'), (1, '7.530')] -[2023-10-09 03:46:14,523][88326] Updated weights for policy 0, policy_version 90082 (0.0007) -[2023-10-09 03:46:14,931][88326] Updated weights for policy 0, policy_version 90092 (0.0008) -[2023-10-09 03:46:15,298][88326] Updated weights for policy 0, policy_version 90102 (0.0008) -[2023-10-09 03:46:15,329][88327] Updated weights for policy 1, policy_version 90180 (0.0008) -[2023-10-09 03:46:15,666][88326] Updated weights for policy 0, policy_version 90112 (0.0009) -[2023-10-09 03:46:15,699][88327] Updated weights for policy 1, policy_version 90190 (0.0008) -[2023-10-09 03:46:16,058][88327] Updated weights for policy 1, policy_version 90200 (0.0008) -[2023-10-09 03:46:18,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 184647680. Throughput: 0: 1705.4, 1: 1697.8. Samples: 46174754. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:46:18,974][87372] Avg episode reward: [(0, '7.330'), (1, '7.800')] -[2023-10-09 03:46:19,558][88326] Updated weights for policy 0, policy_version 90122 (0.0007) -[2023-10-09 03:46:19,917][88326] Updated weights for policy 0, policy_version 90132 (0.0008) -[2023-10-09 03:46:20,087][88327] Updated weights for policy 1, policy_version 90210 (0.0009) -[2023-10-09 03:46:20,282][88326] Updated weights for policy 0, policy_version 90142 (0.0008) -[2023-10-09 03:46:20,511][88327] Updated weights for policy 1, policy_version 90220 (0.0008) -[2023-10-09 03:46:20,879][88327] Updated weights for policy 1, policy_version 90230 (0.0011) -[2023-10-09 03:46:21,253][88327] Updated weights for policy 1, policy_version 90240 (0.0009) -[2023-10-09 03:46:23,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 184713216. Throughput: 0: 1687.7, 1: 1669.0. Samples: 46183808. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:46:23,975][87372] Avg episode reward: [(0, '7.390'), (1, '7.800')] -[2023-10-09 03:46:24,505][88326] Updated weights for policy 0, policy_version 90152 (0.0008) -[2023-10-09 03:46:24,883][88326] Updated weights for policy 0, policy_version 90162 (0.0008) -[2023-10-09 03:46:25,110][88327] Updated weights for policy 1, policy_version 90250 (0.0007) -[2023-10-09 03:46:25,261][88326] Updated weights for policy 0, policy_version 90172 (0.0008) -[2023-10-09 03:46:25,465][88327] Updated weights for policy 1, policy_version 90260 (0.0008) -[2023-10-09 03:46:25,830][88327] Updated weights for policy 1, policy_version 90270 (0.0009) -[2023-10-09 03:46:28,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 184778752. Throughput: 0: 1699.9, 1: 1685.7. Samples: 46204536. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:46:28,975][87372] Avg episode reward: [(0, '6.600'), (1, '7.240')] -[2023-10-09 03:46:29,458][88326] Updated weights for policy 0, policy_version 90182 (0.0008) -[2023-10-09 03:46:29,831][88326] Updated weights for policy 0, policy_version 90192 (0.0009) -[2023-10-09 03:46:29,941][88327] Updated weights for policy 1, policy_version 90280 (0.0007) -[2023-10-09 03:46:30,212][88326] Updated weights for policy 0, policy_version 90202 (0.0007) -[2023-10-09 03:46:30,303][88327] Updated weights for policy 1, policy_version 90290 (0.0007) -[2023-10-09 03:46:30,671][88327] Updated weights for policy 1, policy_version 90300 (0.0008) -[2023-10-09 03:46:33,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 184844288. Throughput: 0: 1690.5, 1: 1700.1. Samples: 46225368. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:46:33,976][87372] Avg episode reward: [(0, '7.010'), (1, '7.890')] -[2023-10-09 03:46:33,991][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000090304_92471296.pth... -[2023-10-09 03:46:33,991][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000090208_92372992.pth... -[2023-10-09 03:46:34,033][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000088640_90767360.pth -[2023-10-09 03:46:34,033][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000088736_90865664.pth -[2023-10-09 03:46:34,312][88326] Updated weights for policy 0, policy_version 90212 (0.0008) -[2023-10-09 03:46:34,598][88327] Updated weights for policy 1, policy_version 90310 (0.0007) -[2023-10-09 03:46:34,685][88326] Updated weights for policy 0, policy_version 90222 (0.0009) -[2023-10-09 03:46:34,963][88327] Updated weights for policy 1, policy_version 90320 (0.0007) -[2023-10-09 03:46:35,051][88326] Updated weights for policy 0, policy_version 90232 (0.0008) -[2023-10-09 03:46:35,318][88327] Updated weights for policy 1, policy_version 90330 (0.0009) -[2023-10-09 03:46:38,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 184909824. Throughput: 0: 1689.9, 1: 1673.5. Samples: 46234466. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:46:38,975][87372] Avg episode reward: [(0, '7.390'), (1, '7.010')] -[2023-10-09 03:46:39,049][88326] Updated weights for policy 0, policy_version 90242 (0.0008) -[2023-10-09 03:46:39,423][88326] Updated weights for policy 0, policy_version 90252 (0.0008) -[2023-10-09 03:46:39,447][88327] Updated weights for policy 1, policy_version 90340 (0.0010) -[2023-10-09 03:46:39,795][88326] Updated weights for policy 0, policy_version 90262 (0.0007) -[2023-10-09 03:46:39,811][88327] Updated weights for policy 1, policy_version 90350 (0.0008) -[2023-10-09 03:46:40,155][88326] Updated weights for policy 0, policy_version 90272 (0.0008) -[2023-10-09 03:46:40,169][88327] Updated weights for policy 1, policy_version 90360 (0.0009) -[2023-10-09 03:46:43,974][87372] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 184975360. Throughput: 0: 1681.8, 1: 1696.5. Samples: 46255168. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:46:43,975][87372] Avg episode reward: [(0, '7.420'), (1, '7.100')] -[2023-10-09 03:46:44,088][88327] Updated weights for policy 1, policy_version 90370 (0.0009) -[2023-10-09 03:46:44,244][88326] Updated weights for policy 0, policy_version 90282 (0.0009) -[2023-10-09 03:46:44,455][88327] Updated weights for policy 1, policy_version 90380 (0.0009) -[2023-10-09 03:46:44,611][88326] Updated weights for policy 0, policy_version 90292 (0.0009) -[2023-10-09 03:46:44,822][88327] Updated weights for policy 1, policy_version 90390 (0.0007) -[2023-10-09 03:46:44,977][88326] Updated weights for policy 0, policy_version 90302 (0.0009) -[2023-10-09 03:46:45,185][88327] Updated weights for policy 1, policy_version 90400 (0.0007) -[2023-10-09 03:46:48,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.3, 300 sec: 13440.4). Total num frames: 185040896. Throughput: 0: 1679.1, 1: 1697.6. Samples: 46275934. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:46:48,975][87372] Avg episode reward: [(0, '6.940'), (1, '7.170')] -[2023-10-09 03:46:49,174][88326] Updated weights for policy 0, policy_version 90312 (0.0007) -[2023-10-09 03:46:49,242][88327] Updated weights for policy 1, policy_version 90410 (0.0008) -[2023-10-09 03:46:49,538][88326] Updated weights for policy 0, policy_version 90322 (0.0009) -[2023-10-09 03:46:49,602][88327] Updated weights for policy 1, policy_version 90420 (0.0008) -[2023-10-09 03:46:49,904][88326] Updated weights for policy 0, policy_version 90332 (0.0007) -[2023-10-09 03:46:49,958][88327] Updated weights for policy 1, policy_version 90430 (0.0008) -[2023-10-09 03:46:53,919][88326] Updated weights for policy 0, policy_version 90342 (0.0008) -[2023-10-09 03:46:53,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 185106432. Throughput: 0: 1680.3, 1: 1682.4. Samples: 46284948. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:46:53,975][87372] Avg episode reward: [(0, '7.370'), (1, '7.470')] -[2023-10-09 03:46:54,175][88327] Updated weights for policy 1, policy_version 90440 (0.0007) -[2023-10-09 03:46:54,284][88326] Updated weights for policy 0, policy_version 90352 (0.0008) -[2023-10-09 03:46:54,533][88327] Updated weights for policy 1, policy_version 90450 (0.0007) -[2023-10-09 03:46:54,649][88326] Updated weights for policy 0, policy_version 90362 (0.0007) -[2023-10-09 03:46:54,897][88327] Updated weights for policy 1, policy_version 90460 (0.0007) -[2023-10-09 03:46:58,673][88326] Updated weights for policy 0, policy_version 90372 (0.0008) -[2023-10-09 03:46:58,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.3, 300 sec: 13440.4). Total num frames: 185171968. Throughput: 0: 1677.6, 1: 1700.1. Samples: 46305742. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:46:58,975][87372] Avg episode reward: [(0, '7.020'), (1, '7.580')] -[2023-10-09 03:46:59,045][88326] Updated weights for policy 0, policy_version 90382 (0.0008) -[2023-10-09 03:46:59,056][88327] Updated weights for policy 1, policy_version 90470 (0.0007) -[2023-10-09 03:46:59,405][88326] Updated weights for policy 0, policy_version 90392 (0.0008) -[2023-10-09 03:46:59,415][88327] Updated weights for policy 1, policy_version 90480 (0.0008) -[2023-10-09 03:46:59,785][88327] Updated weights for policy 1, policy_version 90490 (0.0010) -[2023-10-09 03:47:03,452][88326] Updated weights for policy 0, policy_version 90402 (0.0008) -[2023-10-09 03:47:03,809][88327] Updated weights for policy 1, policy_version 90500 (0.0009) -[2023-10-09 03:47:03,848][88326] Updated weights for policy 0, policy_version 90412 (0.0009) -[2023-10-09 03:47:03,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 185237504. Throughput: 0: 1675.8, 1: 1694.6. Samples: 46326422. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:47:03,974][87372] Avg episode reward: [(0, '7.160'), (1, '6.920')] -[2023-10-09 03:47:04,181][88327] Updated weights for policy 1, policy_version 90510 (0.0008) -[2023-10-09 03:47:04,216][88326] Updated weights for policy 0, policy_version 90422 (0.0009) -[2023-10-09 03:47:04,548][88327] Updated weights for policy 1, policy_version 90520 (0.0007) -[2023-10-09 03:47:04,579][88326] Updated weights for policy 0, policy_version 90432 (0.0007) -[2023-10-09 03:47:08,663][88326] Updated weights for policy 0, policy_version 90442 (0.0009) -[2023-10-09 03:47:08,811][88327] Updated weights for policy 1, policy_version 90530 (0.0010) -[2023-10-09 03:47:08,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 185303040. Throughput: 0: 1676.5, 1: 1691.6. Samples: 46335376. Policy #0 lag: (min: 5.0, avg: 11.8, max: 37.0) -[2023-10-09 03:47:08,975][87372] Avg episode reward: [(0, '7.010'), (1, '6.810')] -[2023-10-09 03:47:09,032][88326] Updated weights for policy 0, policy_version 90452 (0.0009) -[2023-10-09 03:47:09,196][88327] Updated weights for policy 1, policy_version 90540 (0.0009) -[2023-10-09 03:47:09,406][88326] Updated weights for policy 0, policy_version 90462 (0.0007) -[2023-10-09 03:47:09,564][88327] Updated weights for policy 1, policy_version 90550 (0.0009) -[2023-10-09 03:47:09,940][88327] Updated weights for policy 1, policy_version 90560 (0.0009) -[2023-10-09 03:47:13,472][88326] Updated weights for policy 0, policy_version 90472 (0.0010) -[2023-10-09 03:47:13,837][88326] Updated weights for policy 0, policy_version 90482 (0.0010) -[2023-10-09 03:47:13,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 185368576. Throughput: 0: 1673.7, 1: 1690.9. Samples: 46355944. Policy #0 lag: (min: 5.0, avg: 11.8, max: 37.0) -[2023-10-09 03:47:13,975][87372] Avg episode reward: [(0, '7.190'), (1, '7.150')] -[2023-10-09 03:47:13,978][88327] Updated weights for policy 1, policy_version 90570 (0.0009) -[2023-10-09 03:47:14,216][88326] Updated weights for policy 0, policy_version 90492 (0.0007) -[2023-10-09 03:47:14,338][88327] Updated weights for policy 1, policy_version 90580 (0.0007) -[2023-10-09 03:47:14,701][88327] Updated weights for policy 1, policy_version 90590 (0.0007) -[2023-10-09 03:47:18,329][88326] Updated weights for policy 0, policy_version 90502 (0.0009) -[2023-10-09 03:47:18,643][88327] Updated weights for policy 1, policy_version 90600 (0.0009) -[2023-10-09 03:47:18,706][88326] Updated weights for policy 0, policy_version 90512 (0.0009) -[2023-10-09 03:47:18,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 185434112. Throughput: 0: 1675.3, 1: 1696.9. Samples: 46377112. Policy #0 lag: (min: 5.0, avg: 11.8, max: 37.0) -[2023-10-09 03:47:18,974][87372] Avg episode reward: [(0, '6.900'), (1, '6.730')] -[2023-10-09 03:47:18,996][88327] Updated weights for policy 1, policy_version 90610 (0.0009) -[2023-10-09 03:47:19,065][88326] Updated weights for policy 0, policy_version 90522 (0.0009) -[2023-10-09 03:47:19,353][88327] Updated weights for policy 1, policy_version 90620 (0.0010) -[2023-10-09 03:47:22,975][88326] Updated weights for policy 0, policy_version 90532 (0.0009) -[2023-10-09 03:47:23,345][88326] Updated weights for policy 0, policy_version 90542 (0.0009) -[2023-10-09 03:47:23,501][88327] Updated weights for policy 1, policy_version 90630 (0.0010) -[2023-10-09 03:47:23,707][88326] Updated weights for policy 0, policy_version 90552 (0.0009) -[2023-10-09 03:47:23,858][88327] Updated weights for policy 1, policy_version 90640 (0.0007) -[2023-10-09 03:47:23,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 185499648. Throughput: 0: 1680.8, 1: 1695.6. Samples: 46386404. Policy #0 lag: (min: 5.0, avg: 11.8, max: 37.0) -[2023-10-09 03:47:23,974][87372] Avg episode reward: [(0, '6.710'), (1, '7.120')] -[2023-10-09 03:47:24,231][88327] Updated weights for policy 1, policy_version 90650 (0.0010) -[2023-10-09 03:47:27,685][88326] Updated weights for policy 0, policy_version 90562 (0.0009) -[2023-10-09 03:47:28,056][88326] Updated weights for policy 0, policy_version 90572 (0.0009) -[2023-10-09 03:47:28,201][88327] Updated weights for policy 1, policy_version 90660 (0.0009) -[2023-10-09 03:47:28,423][88326] Updated weights for policy 0, policy_version 90582 (0.0007) -[2023-10-09 03:47:28,569][88327] Updated weights for policy 1, policy_version 90670 (0.0008) -[2023-10-09 03:47:28,793][88326] Updated weights for policy 0, policy_version 90592 (0.0008) -[2023-10-09 03:47:28,930][88327] Updated weights for policy 1, policy_version 90680 (0.0008) -[2023-10-09 03:47:28,974][87372] Fps is (10 sec: 16383.7, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 185597952. Throughput: 0: 1686.9, 1: 1693.9. Samples: 46407304. Policy #0 lag: (min: 5.0, avg: 11.8, max: 37.0) -[2023-10-09 03:47:28,975][87372] Avg episode reward: [(0, '7.700'), (1, '7.660')] -[2023-10-09 03:47:32,685][88326] Updated weights for policy 0, policy_version 90602 (0.0009) -[2023-10-09 03:47:32,894][88327] Updated weights for policy 1, policy_version 90690 (0.0010) -[2023-10-09 03:47:33,052][88326] Updated weights for policy 0, policy_version 90612 (0.0007) -[2023-10-09 03:47:33,253][88327] Updated weights for policy 1, policy_version 90700 (0.0007) -[2023-10-09 03:47:33,416][88326] Updated weights for policy 0, policy_version 90622 (0.0008) -[2023-10-09 03:47:33,621][88327] Updated weights for policy 1, policy_version 90710 (0.0007) -[2023-10-09 03:47:33,974][87372] Fps is (10 sec: 16383.5, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 185663488. Throughput: 0: 1670.4, 1: 1686.9. Samples: 46427016. Policy #0 lag: (min: 5.0, avg: 11.8, max: 37.0) -[2023-10-09 03:47:33,975][87372] Avg episode reward: [(0, '7.880'), (1, '7.730')] -[2023-10-09 03:47:33,984][88327] Updated weights for policy 1, policy_version 90720 (0.0011) -[2023-10-09 03:47:37,497][88326] Updated weights for policy 0, policy_version 90632 (0.0009) -[2023-10-09 03:47:37,852][88326] Updated weights for policy 0, policy_version 90642 (0.0007) -[2023-10-09 03:47:38,014][88327] Updated weights for policy 1, policy_version 90730 (0.0007) -[2023-10-09 03:47:38,212][88326] Updated weights for policy 0, policy_version 90652 (0.0009) -[2023-10-09 03:47:38,380][88327] Updated weights for policy 1, policy_version 90740 (0.0009) -[2023-10-09 03:47:38,750][88327] Updated weights for policy 1, policy_version 90750 (0.0010) -[2023-10-09 03:47:38,974][87372] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 185761792. Throughput: 0: 1690.4, 1: 1693.5. Samples: 46437220. Policy #0 lag: (min: 5.0, avg: 11.8, max: 37.0) -[2023-10-09 03:47:38,975][87372] Avg episode reward: [(0, '7.240'), (1, '7.290')] -[2023-10-09 03:47:42,517][88326] Updated weights for policy 0, policy_version 90662 (0.0008) -[2023-10-09 03:47:42,759][88327] Updated weights for policy 1, policy_version 90760 (0.0008) -[2023-10-09 03:47:42,887][88326] Updated weights for policy 0, policy_version 90672 (0.0008) -[2023-10-09 03:47:43,129][88327] Updated weights for policy 1, policy_version 90770 (0.0007) -[2023-10-09 03:47:43,255][88326] Updated weights for policy 0, policy_version 90682 (0.0008) -[2023-10-09 03:47:43,497][88327] Updated weights for policy 1, policy_version 90780 (0.0010) -[2023-10-09 03:47:43,974][87372] Fps is (10 sec: 16384.1, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 185827328. Throughput: 0: 1689.1, 1: 1690.1. Samples: 46457808. Policy #0 lag: (min: 5.0, avg: 11.8, max: 37.0) -[2023-10-09 03:47:43,975][87372] Avg episode reward: [(0, '7.460'), (1, '7.540')] -[2023-10-09 03:47:47,128][88326] Updated weights for policy 0, policy_version 90692 (0.0008) -[2023-10-09 03:47:47,495][88326] Updated weights for policy 0, policy_version 90702 (0.0007) -[2023-10-09 03:47:47,664][88327] Updated weights for policy 1, policy_version 90790 (0.0009) -[2023-10-09 03:47:47,853][88326] Updated weights for policy 0, policy_version 90712 (0.0008) -[2023-10-09 03:47:48,034][88327] Updated weights for policy 1, policy_version 90800 (0.0008) -[2023-10-09 03:47:48,396][88327] Updated weights for policy 1, policy_version 90810 (0.0009) -[2023-10-09 03:47:48,974][87372] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 185892864. Throughput: 0: 1664.9, 1: 1678.0. Samples: 46476850. Policy #0 lag: (min: 5.0, avg: 11.8, max: 37.0) -[2023-10-09 03:47:48,975][87372] Avg episode reward: [(0, '6.530'), (1, '7.160')] -[2023-10-09 03:47:51,947][88326] Updated weights for policy 0, policy_version 90722 (0.0007) -[2023-10-09 03:47:52,354][88326] Updated weights for policy 0, policy_version 90732 (0.0009) -[2023-10-09 03:47:52,366][88327] Updated weights for policy 1, policy_version 90820 (0.0009) -[2023-10-09 03:47:52,718][88327] Updated weights for policy 1, policy_version 90830 (0.0009) -[2023-10-09 03:47:52,720][88326] Updated weights for policy 0, policy_version 90742 (0.0010) -[2023-10-09 03:47:53,076][88327] Updated weights for policy 1, policy_version 90840 (0.0007) -[2023-10-09 03:47:53,092][88326] Updated weights for policy 0, policy_version 90752 (0.0007) -[2023-10-09 03:47:53,974][87372] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 185958400. Throughput: 0: 1697.9, 1: 1695.7. Samples: 46488088. Policy #0 lag: (min: 5.0, avg: 11.8, max: 37.0) -[2023-10-09 03:47:53,975][87372] Avg episode reward: [(0, '6.590'), (1, '7.420')] -[2023-10-09 03:47:57,073][88326] Updated weights for policy 0, policy_version 90762 (0.0009) -[2023-10-09 03:47:57,236][88327] Updated weights for policy 1, policy_version 90850 (0.0009) -[2023-10-09 03:47:57,440][88326] Updated weights for policy 0, policy_version 90772 (0.0009) -[2023-10-09 03:47:57,649][88327] Updated weights for policy 1, policy_version 90860 (0.0007) -[2023-10-09 03:47:57,810][88326] Updated weights for policy 0, policy_version 90782 (0.0007) -[2023-10-09 03:47:58,017][88327] Updated weights for policy 1, policy_version 90870 (0.0008) -[2023-10-09 03:47:58,378][88327] Updated weights for policy 1, policy_version 90880 (0.0007) -[2023-10-09 03:47:58,974][87372] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 186023936. Throughput: 0: 1687.2, 1: 1696.8. Samples: 46508224. Policy #0 lag: (min: 5.0, avg: 11.8, max: 37.0) -[2023-10-09 03:47:58,975][87372] Avg episode reward: [(0, '6.340'), (1, '7.420')] -[2023-10-09 03:48:01,995][88326] Updated weights for policy 0, policy_version 90792 (0.0010) -[2023-10-09 03:48:02,278][88327] Updated weights for policy 1, policy_version 90890 (0.0009) -[2023-10-09 03:48:02,351][88326] Updated weights for policy 0, policy_version 90802 (0.0007) -[2023-10-09 03:48:02,645][88327] Updated weights for policy 1, policy_version 90900 (0.0008) -[2023-10-09 03:48:02,719][88326] Updated weights for policy 0, policy_version 90812 (0.0007) -[2023-10-09 03:48:03,017][88327] Updated weights for policy 1, policy_version 90910 (0.0009) -[2023-10-09 03:48:03,974][87372] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 186089472. Throughput: 0: 1672.4, 1: 1657.6. Samples: 46526958. Policy #0 lag: (min: 31.0, avg: 31.8, max: 50.0) -[2023-10-09 03:48:03,975][87372] Avg episode reward: [(0, '6.770'), (1, '7.200')] -[2023-10-09 03:48:06,722][88326] Updated weights for policy 0, policy_version 90822 (0.0010) -[2023-10-09 03:48:07,065][88327] Updated weights for policy 1, policy_version 90920 (0.0010) -[2023-10-09 03:48:07,086][88326] Updated weights for policy 0, policy_version 90832 (0.0009) -[2023-10-09 03:48:07,424][88327] Updated weights for policy 1, policy_version 90930 (0.0008) -[2023-10-09 03:48:07,458][88326] Updated weights for policy 0, policy_version 90842 (0.0008) -[2023-10-09 03:48:07,792][88327] Updated weights for policy 1, policy_version 90940 (0.0007) -[2023-10-09 03:48:08,974][87372] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 186155008. Throughput: 0: 1695.8, 1: 1689.3. Samples: 46538732. Policy #0 lag: (min: 31.0, avg: 31.8, max: 50.0) -[2023-10-09 03:48:08,975][87372] Avg episode reward: [(0, '7.410'), (1, '7.220')] -[2023-10-09 03:48:11,575][88326] Updated weights for policy 0, policy_version 90852 (0.0007) -[2023-10-09 03:48:11,819][88327] Updated weights for policy 1, policy_version 90950 (0.0008) -[2023-10-09 03:48:11,936][88326] Updated weights for policy 0, policy_version 90862 (0.0009) -[2023-10-09 03:48:12,178][88327] Updated weights for policy 1, policy_version 90960 (0.0009) -[2023-10-09 03:48:12,307][88326] Updated weights for policy 0, policy_version 90872 (0.0009) -[2023-10-09 03:48:12,543][88327] Updated weights for policy 1, policy_version 90970 (0.0008) -[2023-10-09 03:48:13,974][87372] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 186220544. Throughput: 0: 1675.4, 1: 1681.9. Samples: 46558384. Policy #0 lag: (min: 31.0, avg: 31.8, max: 50.0) -[2023-10-09 03:48:13,975][87372] Avg episode reward: [(0, '7.460'), (1, '7.980')] -[2023-10-09 03:48:16,179][88326] Updated weights for policy 0, policy_version 90882 (0.0008) -[2023-10-09 03:48:16,454][88327] Updated weights for policy 1, policy_version 90980 (0.0008) -[2023-10-09 03:48:16,542][88326] Updated weights for policy 0, policy_version 90892 (0.0007) -[2023-10-09 03:48:16,815][88327] Updated weights for policy 1, policy_version 90990 (0.0008) -[2023-10-09 03:48:16,915][88326] Updated weights for policy 0, policy_version 90902 (0.0007) -[2023-10-09 03:48:17,177][88327] Updated weights for policy 1, policy_version 91000 (0.0008) -[2023-10-09 03:48:17,274][88326] Updated weights for policy 0, policy_version 90912 (0.0010) -[2023-10-09 03:48:18,974][87372] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 186286080. Throughput: 0: 1688.9, 1: 1675.1. Samples: 46578394. Policy #0 lag: (min: 31.0, avg: 31.8, max: 50.0) -[2023-10-09 03:48:18,974][87372] Avg episode reward: [(0, '7.150'), (1, '7.990')] -[2023-10-09 03:48:21,283][88326] Updated weights for policy 0, policy_version 90922 (0.0010) -[2023-10-09 03:48:21,354][88327] Updated weights for policy 1, policy_version 91010 (0.0009) -[2023-10-09 03:48:21,639][88326] Updated weights for policy 0, policy_version 90932 (0.0009) -[2023-10-09 03:48:21,718][88327] Updated weights for policy 1, policy_version 91020 (0.0010) -[2023-10-09 03:48:22,012][88326] Updated weights for policy 0, policy_version 90942 (0.0010) -[2023-10-09 03:48:22,092][88327] Updated weights for policy 1, policy_version 91030 (0.0008) -[2023-10-09 03:48:22,450][88327] Updated weights for policy 1, policy_version 91040 (0.0008) -[2023-10-09 03:48:23,974][87372] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 186351616. Throughput: 0: 1692.2, 1: 1694.4. Samples: 46589616. Policy #0 lag: (min: 31.0, avg: 31.8, max: 50.0) -[2023-10-09 03:48:23,975][87372] Avg episode reward: [(0, '7.810'), (1, '8.170')] -[2023-10-09 03:48:26,065][88326] Updated weights for policy 0, policy_version 90952 (0.0008) -[2023-10-09 03:48:26,429][88326] Updated weights for policy 0, policy_version 90962 (0.0007) -[2023-10-09 03:48:26,569][88327] Updated weights for policy 1, policy_version 91050 (0.0009) -[2023-10-09 03:48:26,804][88326] Updated weights for policy 0, policy_version 90972 (0.0009) -[2023-10-09 03:48:26,936][88327] Updated weights for policy 1, policy_version 91060 (0.0008) -[2023-10-09 03:48:27,308][88327] Updated weights for policy 1, policy_version 91070 (0.0009) -[2023-10-09 03:48:28,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 186417152. Throughput: 0: 1673.2, 1: 1674.4. Samples: 46608448. Policy #0 lag: (min: 31.0, avg: 31.8, max: 50.0) -[2023-10-09 03:48:28,975][87372] Avg episode reward: [(0, '7.730'), (1, '7.620')] -[2023-10-09 03:48:30,849][88326] Updated weights for policy 0, policy_version 90982 (0.0009) -[2023-10-09 03:48:31,211][88326] Updated weights for policy 0, policy_version 90992 (0.0010) -[2023-10-09 03:48:31,398][88327] Updated weights for policy 1, policy_version 91080 (0.0008) -[2023-10-09 03:48:31,577][88326] Updated weights for policy 0, policy_version 91002 (0.0007) -[2023-10-09 03:48:31,755][88327] Updated weights for policy 1, policy_version 91090 (0.0007) -[2023-10-09 03:48:32,125][88327] Updated weights for policy 1, policy_version 91100 (0.0009) -[2023-10-09 03:48:33,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 186482688. Throughput: 0: 1704.2, 1: 1682.2. Samples: 46629238. Policy #0 lag: (min: 31.0, avg: 31.8, max: 50.0) -[2023-10-09 03:48:33,975][87372] Avg episode reward: [(0, '7.350'), (1, '7.570')] -[2023-10-09 03:48:33,987][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000091008_93192192.pth... -[2023-10-09 03:48:33,988][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000091104_93290496.pth... -[2023-10-09 03:48:34,022][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000089536_91684864.pth -[2023-10-09 03:48:34,024][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000089440_91586560.pth -[2023-10-09 03:48:35,666][88326] Updated weights for policy 0, policy_version 91012 (0.0008) -[2023-10-09 03:48:36,038][88326] Updated weights for policy 0, policy_version 91022 (0.0010) -[2023-10-09 03:48:36,157][88327] Updated weights for policy 1, policy_version 91110 (0.0007) -[2023-10-09 03:48:36,404][88326] Updated weights for policy 0, policy_version 91032 (0.0009) -[2023-10-09 03:48:36,527][88327] Updated weights for policy 1, policy_version 91120 (0.0007) -[2023-10-09 03:48:36,890][88327] Updated weights for policy 1, policy_version 91130 (0.0007) -[2023-10-09 03:48:38,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 186548224. Throughput: 0: 1684.3, 1: 1691.7. Samples: 46640008. Policy #0 lag: (min: 31.0, avg: 31.8, max: 50.0) -[2023-10-09 03:48:38,975][87372] Avg episode reward: [(0, '7.170'), (1, '7.620')] -[2023-10-09 03:48:40,295][88326] Updated weights for policy 0, policy_version 91042 (0.0008) -[2023-10-09 03:48:40,657][88326] Updated weights for policy 0, policy_version 91052 (0.0008) -[2023-10-09 03:48:41,023][88326] Updated weights for policy 0, policy_version 91062 (0.0008) -[2023-10-09 03:48:41,123][88327] Updated weights for policy 1, policy_version 91140 (0.0009) -[2023-10-09 03:48:41,391][88326] Updated weights for policy 0, policy_version 91072 (0.0008) -[2023-10-09 03:48:41,485][88327] Updated weights for policy 1, policy_version 91150 (0.0007) -[2023-10-09 03:48:41,851][88327] Updated weights for policy 1, policy_version 91160 (0.0007) -[2023-10-09 03:48:43,974][87372] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 186613760. Throughput: 0: 1689.8, 1: 1669.4. Samples: 46659390. Policy #0 lag: (min: 31.0, avg: 31.8, max: 50.0) -[2023-10-09 03:48:43,975][87372] Avg episode reward: [(0, '7.780'), (1, '7.970')] -[2023-10-09 03:48:45,596][88326] Updated weights for policy 0, policy_version 91082 (0.0011) -[2023-10-09 03:48:45,920][88327] Updated weights for policy 1, policy_version 91170 (0.0007) -[2023-10-09 03:48:45,969][88326] Updated weights for policy 0, policy_version 91092 (0.0009) -[2023-10-09 03:48:46,334][88326] Updated weights for policy 0, policy_version 91102 (0.0007) -[2023-10-09 03:48:46,343][88327] Updated weights for policy 1, policy_version 91180 (0.0007) -[2023-10-09 03:48:46,716][88327] Updated weights for policy 1, policy_version 91190 (0.0008) -[2023-10-09 03:48:47,087][88327] Updated weights for policy 1, policy_version 91200 (0.0008) -[2023-10-09 03:48:48,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 186679296. Throughput: 0: 1705.0, 1: 1691.1. Samples: 46679782. Policy #0 lag: (min: 31.0, avg: 31.8, max: 50.0) -[2023-10-09 03:48:48,975][87372] Avg episode reward: [(0, '7.380'), (1, '7.300')] -[2023-10-09 03:48:50,462][88326] Updated weights for policy 0, policy_version 91112 (0.0010) -[2023-10-09 03:48:50,831][88326] Updated weights for policy 0, policy_version 91122 (0.0009) -[2023-10-09 03:48:51,130][88327] Updated weights for policy 1, policy_version 91210 (0.0009) -[2023-10-09 03:48:51,200][88326] Updated weights for policy 0, policy_version 91132 (0.0010) -[2023-10-09 03:48:51,493][88327] Updated weights for policy 1, policy_version 91220 (0.0009) -[2023-10-09 03:48:51,848][88327] Updated weights for policy 1, policy_version 91230 (0.0008) -[2023-10-09 03:48:53,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 186744832. Throughput: 0: 1680.6, 1: 1680.8. Samples: 46689992. Policy #0 lag: (min: 31.0, avg: 31.8, max: 50.0) -[2023-10-09 03:48:53,974][87372] Avg episode reward: [(0, '6.660'), (1, '7.600')] -[2023-10-09 03:48:55,257][88326] Updated weights for policy 0, policy_version 91142 (0.0010) -[2023-10-09 03:48:55,620][88326] Updated weights for policy 0, policy_version 91152 (0.0009) -[2023-10-09 03:48:55,819][88327] Updated weights for policy 1, policy_version 91240 (0.0007) -[2023-10-09 03:48:55,990][88326] Updated weights for policy 0, policy_version 91162 (0.0008) -[2023-10-09 03:48:56,180][88327] Updated weights for policy 1, policy_version 91250 (0.0007) -[2023-10-09 03:48:56,543][88327] Updated weights for policy 1, policy_version 91260 (0.0009) -[2023-10-09 03:48:58,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 186810368. Throughput: 0: 1692.8, 1: 1672.0. Samples: 46709802. Policy #0 lag: (min: 31.0, avg: 31.8, max: 50.0) -[2023-10-09 03:48:58,975][87372] Avg episode reward: [(0, '6.800'), (1, '7.730')] -[2023-10-09 03:48:59,758][88326] Updated weights for policy 0, policy_version 91172 (0.0008) -[2023-10-09 03:49:00,121][88326] Updated weights for policy 0, policy_version 91182 (0.0010) -[2023-10-09 03:49:00,485][88326] Updated weights for policy 0, policy_version 91192 (0.0008) -[2023-10-09 03:49:00,617][88327] Updated weights for policy 1, policy_version 91270 (0.0007) -[2023-10-09 03:49:00,984][88327] Updated weights for policy 1, policy_version 91280 (0.0008) -[2023-10-09 03:49:01,356][88327] Updated weights for policy 1, policy_version 91290 (0.0010) -[2023-10-09 03:49:03,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 186875904. Throughput: 0: 1703.3, 1: 1686.8. Samples: 46730952. Policy #0 lag: (min: 6.0, avg: 8.9, max: 38.0) -[2023-10-09 03:49:03,975][87372] Avg episode reward: [(0, '7.250'), (1, '6.710')] -[2023-10-09 03:49:04,441][88326] Updated weights for policy 0, policy_version 91202 (0.0009) -[2023-10-09 03:49:04,802][88326] Updated weights for policy 0, policy_version 91212 (0.0007) -[2023-10-09 03:49:05,166][88326] Updated weights for policy 0, policy_version 91222 (0.0007) -[2023-10-09 03:49:05,240][88327] Updated weights for policy 1, policy_version 91300 (0.0009) -[2023-10-09 03:49:05,529][88326] Updated weights for policy 0, policy_version 91232 (0.0008) -[2023-10-09 03:49:05,603][88327] Updated weights for policy 1, policy_version 91310 (0.0010) -[2023-10-09 03:49:05,965][88327] Updated weights for policy 1, policy_version 91320 (0.0010) -[2023-10-09 03:49:08,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 186941440. Throughput: 0: 1683.1, 1: 1666.5. Samples: 46740348. Policy #0 lag: (min: 6.0, avg: 8.9, max: 38.0) -[2023-10-09 03:49:08,975][87372] Avg episode reward: [(0, '7.130'), (1, '6.940')] -[2023-10-09 03:49:09,391][88326] Updated weights for policy 0, policy_version 91242 (0.0008) -[2023-10-09 03:49:09,752][88326] Updated weights for policy 0, policy_version 91252 (0.0007) -[2023-10-09 03:49:10,117][88326] Updated weights for policy 0, policy_version 91262 (0.0008) -[2023-10-09 03:49:10,191][88327] Updated weights for policy 1, policy_version 91330 (0.0010) -[2023-10-09 03:49:10,550][88327] Updated weights for policy 1, policy_version 91340 (0.0008) -[2023-10-09 03:49:10,918][88327] Updated weights for policy 1, policy_version 91350 (0.0009) -[2023-10-09 03:49:11,288][88327] Updated weights for policy 1, policy_version 91360 (0.0010) -[2023-10-09 03:49:13,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 187006976. Throughput: 0: 1710.8, 1: 1685.8. Samples: 46761292. Policy #0 lag: (min: 6.0, avg: 8.9, max: 38.0) -[2023-10-09 03:49:13,975][87372] Avg episode reward: [(0, '7.120'), (1, '6.430')] -[2023-10-09 03:49:14,121][88326] Updated weights for policy 0, policy_version 91272 (0.0008) -[2023-10-09 03:49:14,491][88326] Updated weights for policy 0, policy_version 91282 (0.0008) -[2023-10-09 03:49:14,867][88326] Updated weights for policy 0, policy_version 91292 (0.0008) -[2023-10-09 03:49:15,362][88327] Updated weights for policy 1, policy_version 91370 (0.0010) -[2023-10-09 03:49:15,729][88327] Updated weights for policy 1, policy_version 91380 (0.0009) -[2023-10-09 03:49:16,097][88327] Updated weights for policy 1, policy_version 91390 (0.0009) -[2023-10-09 03:49:18,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 187072512. Throughput: 0: 1705.8, 1: 1695.0. Samples: 46782274. Policy #0 lag: (min: 6.0, avg: 8.9, max: 38.0) -[2023-10-09 03:49:18,975][87372] Avg episode reward: [(0, '7.400'), (1, '7.170')] -[2023-10-09 03:49:18,994][88326] Updated weights for policy 0, policy_version 91302 (0.0009) -[2023-10-09 03:49:19,365][88326] Updated weights for policy 0, policy_version 91312 (0.0010) -[2023-10-09 03:49:19,734][88326] Updated weights for policy 0, policy_version 91322 (0.0008) -[2023-10-09 03:49:20,175][88327] Updated weights for policy 1, policy_version 91400 (0.0010) -[2023-10-09 03:49:20,535][88327] Updated weights for policy 1, policy_version 91410 (0.0007) -[2023-10-09 03:49:20,898][88327] Updated weights for policy 1, policy_version 91420 (0.0008) -[2023-10-09 03:49:23,565][88326] Updated weights for policy 0, policy_version 91332 (0.0007) -[2023-10-09 03:49:23,926][88326] Updated weights for policy 0, policy_version 91342 (0.0007) -[2023-10-09 03:49:23,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 187138048. Throughput: 0: 1697.4, 1: 1667.3. Samples: 46791422. Policy #0 lag: (min: 6.0, avg: 8.9, max: 38.0) -[2023-10-09 03:49:23,975][87372] Avg episode reward: [(0, '7.360'), (1, '7.810')] -[2023-10-09 03:49:24,304][88326] Updated weights for policy 0, policy_version 91352 (0.0007) -[2023-10-09 03:49:24,870][88327] Updated weights for policy 1, policy_version 91430 (0.0010) -[2023-10-09 03:49:25,231][88327] Updated weights for policy 1, policy_version 91440 (0.0009) -[2023-10-09 03:49:25,601][88327] Updated weights for policy 1, policy_version 91450 (0.0010) -[2023-10-09 03:49:28,616][88326] Updated weights for policy 0, policy_version 91362 (0.0009) -[2023-10-09 03:49:28,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 187203584. Throughput: 0: 1709.7, 1: 1692.7. Samples: 46812502. Policy #0 lag: (min: 6.0, avg: 8.9, max: 38.0) -[2023-10-09 03:49:28,975][87372] Avg episode reward: [(0, '7.260'), (1, '7.980')] -[2023-10-09 03:49:28,986][88326] Updated weights for policy 0, policy_version 91372 (0.0009) -[2023-10-09 03:49:29,350][88326] Updated weights for policy 0, policy_version 91382 (0.0008) -[2023-10-09 03:49:29,701][88327] Updated weights for policy 1, policy_version 91460 (0.0009) -[2023-10-09 03:49:29,713][88326] Updated weights for policy 0, policy_version 91392 (0.0010) -[2023-10-09 03:49:30,070][88327] Updated weights for policy 1, policy_version 91470 (0.0008) -[2023-10-09 03:49:30,431][88327] Updated weights for policy 1, policy_version 91480 (0.0009) -[2023-10-09 03:49:33,909][88326] Updated weights for policy 0, policy_version 91402 (0.0009) -[2023-10-09 03:49:33,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 187269120. Throughput: 0: 1709.1, 1: 1699.4. Samples: 46833164. Policy #0 lag: (min: 6.0, avg: 8.9, max: 38.0) -[2023-10-09 03:49:33,975][87372] Avg episode reward: [(0, '6.980'), (1, '7.470')] -[2023-10-09 03:49:34,283][88326] Updated weights for policy 0, policy_version 91412 (0.0010) -[2023-10-09 03:49:34,451][88327] Updated weights for policy 1, policy_version 91490 (0.0008) -[2023-10-09 03:49:34,648][88326] Updated weights for policy 0, policy_version 91422 (0.0007) -[2023-10-09 03:49:34,883][88327] Updated weights for policy 1, policy_version 91500 (0.0007) -[2023-10-09 03:49:35,247][88327] Updated weights for policy 1, policy_version 91510 (0.0009) -[2023-10-09 03:49:35,611][88327] Updated weights for policy 1, policy_version 91520 (0.0010) -[2023-10-09 03:49:38,662][88326] Updated weights for policy 0, policy_version 91432 (0.0008) -[2023-10-09 03:49:38,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 187334656. Throughput: 0: 1703.0, 1: 1676.8. Samples: 46842082. Policy #0 lag: (min: 6.0, avg: 8.9, max: 38.0) -[2023-10-09 03:49:38,975][87372] Avg episode reward: [(0, '7.400'), (1, '8.630')] -[2023-10-09 03:49:39,032][88326] Updated weights for policy 0, policy_version 91442 (0.0009) -[2023-10-09 03:49:39,406][88326] Updated weights for policy 0, policy_version 91452 (0.0007) -[2023-10-09 03:49:39,837][88327] Updated weights for policy 1, policy_version 91530 (0.0007) -[2023-10-09 03:49:40,193][88327] Updated weights for policy 1, policy_version 91540 (0.0007) -[2023-10-09 03:49:40,564][88327] Updated weights for policy 1, policy_version 91550 (0.0007) -[2023-10-09 03:49:43,639][88326] Updated weights for policy 0, policy_version 91462 (0.0007) -[2023-10-09 03:49:43,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 187400192. Throughput: 0: 1704.2, 1: 1693.4. Samples: 46862694. Policy #0 lag: (min: 6.0, avg: 8.9, max: 38.0) -[2023-10-09 03:49:43,974][87372] Avg episode reward: [(0, '7.160'), (1, '6.700')] -[2023-10-09 03:49:44,005][88326] Updated weights for policy 0, policy_version 91472 (0.0008) -[2023-10-09 03:49:44,386][88326] Updated weights for policy 0, policy_version 91482 (0.0008) -[2023-10-09 03:49:44,514][88327] Updated weights for policy 1, policy_version 91560 (0.0008) -[2023-10-09 03:49:44,882][88327] Updated weights for policy 1, policy_version 91570 (0.0009) -[2023-10-09 03:49:45,252][88327] Updated weights for policy 1, policy_version 91580 (0.0007) -[2023-10-09 03:49:48,361][88326] Updated weights for policy 0, policy_version 91492 (0.0008) -[2023-10-09 03:49:48,735][88326] Updated weights for policy 0, policy_version 91502 (0.0009) -[2023-10-09 03:49:48,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 187465728. Throughput: 0: 1690.4, 1: 1694.8. Samples: 46883282. Policy #0 lag: (min: 6.0, avg: 8.9, max: 38.0) -[2023-10-09 03:49:48,975][87372] Avg episode reward: [(0, '6.730'), (1, '7.060')] -[2023-10-09 03:49:49,094][88326] Updated weights for policy 0, policy_version 91512 (0.0007) -[2023-10-09 03:49:49,219][88327] Updated weights for policy 1, policy_version 91590 (0.0008) -[2023-10-09 03:49:49,581][88327] Updated weights for policy 1, policy_version 91600 (0.0010) -[2023-10-09 03:49:49,955][88327] Updated weights for policy 1, policy_version 91610 (0.0009) -[2023-10-09 03:49:53,193][88326] Updated weights for policy 0, policy_version 91522 (0.0007) -[2023-10-09 03:49:53,561][88326] Updated weights for policy 0, policy_version 91532 (0.0008) -[2023-10-09 03:49:53,930][88326] Updated weights for policy 0, policy_version 91542 (0.0009) -[2023-10-09 03:49:53,970][88327] Updated weights for policy 1, policy_version 91620 (0.0009) -[2023-10-09 03:49:53,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 187531264. Throughput: 0: 1689.8, 1: 1688.8. Samples: 46892384. Policy #0 lag: (min: 6.0, avg: 8.9, max: 38.0) -[2023-10-09 03:49:53,974][87372] Avg episode reward: [(0, '6.820'), (1, '7.170')] -[2023-10-09 03:49:54,306][88326] Updated weights for policy 0, policy_version 91552 (0.0008) -[2023-10-09 03:49:54,335][88327] Updated weights for policy 1, policy_version 91630 (0.0007) -[2023-10-09 03:49:54,702][88327] Updated weights for policy 1, policy_version 91640 (0.0008) -[2023-10-09 03:49:58,146][88326] Updated weights for policy 0, policy_version 91562 (0.0010) -[2023-10-09 03:49:58,511][88326] Updated weights for policy 0, policy_version 91572 (0.0008) -[2023-10-09 03:49:58,742][88327] Updated weights for policy 1, policy_version 91650 (0.0008) -[2023-10-09 03:49:58,876][88326] Updated weights for policy 0, policy_version 91582 (0.0008) -[2023-10-09 03:49:58,974][87372] Fps is (10 sec: 16383.7, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 187629568. Throughput: 0: 1686.1, 1: 1695.1. Samples: 46913446. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:49:58,975][87372] Avg episode reward: [(0, '7.340'), (1, '7.660')] -[2023-10-09 03:49:59,106][88327] Updated weights for policy 1, policy_version 91660 (0.0010) -[2023-10-09 03:49:59,472][88327] Updated weights for policy 1, policy_version 91670 (0.0008) -[2023-10-09 03:49:59,837][88327] Updated weights for policy 1, policy_version 91680 (0.0007) -[2023-10-09 03:50:02,913][88326] Updated weights for policy 0, policy_version 91592 (0.0007) -[2023-10-09 03:50:03,281][88326] Updated weights for policy 0, policy_version 91602 (0.0007) -[2023-10-09 03:50:03,655][88326] Updated weights for policy 0, policy_version 91612 (0.0007) -[2023-10-09 03:50:03,759][88327] Updated weights for policy 1, policy_version 91690 (0.0008) -[2023-10-09 03:50:03,974][87372] Fps is (10 sec: 16384.1, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 187695104. Throughput: 0: 1674.5, 1: 1698.4. Samples: 46934056. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:50:03,974][87372] Avg episode reward: [(0, '6.630'), (1, '6.830')] -[2023-10-09 03:50:04,121][88327] Updated weights for policy 1, policy_version 91700 (0.0007) -[2023-10-09 03:50:04,478][88327] Updated weights for policy 1, policy_version 91710 (0.0008) -[2023-10-09 03:50:07,546][88326] Updated weights for policy 0, policy_version 91622 (0.0010) -[2023-10-09 03:50:07,912][88326] Updated weights for policy 0, policy_version 91632 (0.0009) -[2023-10-09 03:50:08,281][88326] Updated weights for policy 0, policy_version 91642 (0.0007) -[2023-10-09 03:50:08,478][88327] Updated weights for policy 1, policy_version 91720 (0.0008) -[2023-10-09 03:50:08,846][88327] Updated weights for policy 1, policy_version 91730 (0.0007) -[2023-10-09 03:50:08,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 187760640. Throughput: 0: 1687.9, 1: 1698.0. Samples: 46943786. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:50:08,974][87372] Avg episode reward: [(0, '6.630'), (1, '7.270')] -[2023-10-09 03:50:09,213][88327] Updated weights for policy 1, policy_version 91740 (0.0009) -[2023-10-09 03:50:12,307][88326] Updated weights for policy 0, policy_version 91652 (0.0007) -[2023-10-09 03:50:12,685][88326] Updated weights for policy 0, policy_version 91662 (0.0007) -[2023-10-09 03:50:13,055][88326] Updated weights for policy 0, policy_version 91672 (0.0007) -[2023-10-09 03:50:13,339][88327] Updated weights for policy 1, policy_version 91750 (0.0008) -[2023-10-09 03:50:13,699][88327] Updated weights for policy 1, policy_version 91760 (0.0010) -[2023-10-09 03:50:13,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 187826176. Throughput: 0: 1688.8, 1: 1695.0. Samples: 46964772. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:50:13,975][87372] Avg episode reward: [(0, '6.920'), (1, '7.180')] -[2023-10-09 03:50:14,069][88327] Updated weights for policy 1, policy_version 91770 (0.0008) -[2023-10-09 03:50:17,114][88326] Updated weights for policy 0, policy_version 91682 (0.0008) -[2023-10-09 03:50:17,471][88326] Updated weights for policy 0, policy_version 91692 (0.0008) -[2023-10-09 03:50:17,845][88326] Updated weights for policy 0, policy_version 91702 (0.0008) -[2023-10-09 03:50:18,084][88327] Updated weights for policy 1, policy_version 91780 (0.0008) -[2023-10-09 03:50:18,204][88326] Updated weights for policy 0, policy_version 91712 (0.0010) -[2023-10-09 03:50:18,454][88327] Updated weights for policy 1, policy_version 91790 (0.0007) -[2023-10-09 03:50:18,814][88327] Updated weights for policy 1, policy_version 91800 (0.0008) -[2023-10-09 03:50:18,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 187891712. Throughput: 0: 1670.9, 1: 1694.4. Samples: 46984602. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:50:18,975][87372] Avg episode reward: [(0, '6.450'), (1, '6.850')] -[2023-10-09 03:50:22,302][88326] Updated weights for policy 0, policy_version 91722 (0.0009) -[2023-10-09 03:50:22,680][88326] Updated weights for policy 0, policy_version 91732 (0.0008) -[2023-10-09 03:50:22,903][88327] Updated weights for policy 1, policy_version 91810 (0.0008) -[2023-10-09 03:50:23,053][88326] Updated weights for policy 0, policy_version 91742 (0.0007) -[2023-10-09 03:50:23,324][88327] Updated weights for policy 1, policy_version 91820 (0.0010) -[2023-10-09 03:50:23,686][88327] Updated weights for policy 1, policy_version 91830 (0.0010) -[2023-10-09 03:50:23,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 187957248. Throughput: 0: 1700.5, 1: 1699.8. Samples: 46995094. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:50:23,975][87372] Avg episode reward: [(0, '7.420'), (1, '7.140')] -[2023-10-09 03:50:24,051][88327] Updated weights for policy 1, policy_version 91840 (0.0008) -[2023-10-09 03:50:27,087][88326] Updated weights for policy 0, policy_version 91752 (0.0008) -[2023-10-09 03:50:27,460][88326] Updated weights for policy 0, policy_version 91762 (0.0008) -[2023-10-09 03:50:27,827][88326] Updated weights for policy 0, policy_version 91772 (0.0009) -[2023-10-09 03:50:27,864][88327] Updated weights for policy 1, policy_version 91850 (0.0008) -[2023-10-09 03:50:28,229][88327] Updated weights for policy 1, policy_version 91860 (0.0009) -[2023-10-09 03:50:28,592][88327] Updated weights for policy 1, policy_version 91870 (0.0009) -[2023-10-09 03:50:28,974][87372] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 188055552. Throughput: 0: 1689.9, 1: 1701.9. Samples: 47015326. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:50:28,975][87372] Avg episode reward: [(0, '7.520'), (1, '7.630')] -[2023-10-09 03:50:32,030][88326] Updated weights for policy 0, policy_version 91782 (0.0008) -[2023-10-09 03:50:32,403][88326] Updated weights for policy 0, policy_version 91792 (0.0009) -[2023-10-09 03:50:32,667][88327] Updated weights for policy 1, policy_version 91880 (0.0009) -[2023-10-09 03:50:32,782][88326] Updated weights for policy 0, policy_version 91802 (0.0007) -[2023-10-09 03:50:33,035][88327] Updated weights for policy 1, policy_version 91890 (0.0008) -[2023-10-09 03:50:33,403][88327] Updated weights for policy 1, policy_version 91900 (0.0007) -[2023-10-09 03:50:33,974][87372] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 188121088. Throughput: 0: 1673.0, 1: 1685.9. Samples: 47034432. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:50:33,975][87372] Avg episode reward: [(0, '7.010'), (1, '7.670')] -[2023-10-09 03:50:33,986][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000091808_94011392.pth... -[2023-10-09 03:50:33,986][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000091904_94109696.pth... -[2023-10-09 03:50:34,016][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000090208_92372992.pth -[2023-10-09 03:50:34,028][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000090304_92471296.pth -[2023-10-09 03:50:36,903][88326] Updated weights for policy 0, policy_version 91812 (0.0010) -[2023-10-09 03:50:37,272][88326] Updated weights for policy 0, policy_version 91822 (0.0008) -[2023-10-09 03:50:37,537][88327] Updated weights for policy 1, policy_version 91910 (0.0008) -[2023-10-09 03:50:37,643][88326] Updated weights for policy 0, policy_version 91832 (0.0007) -[2023-10-09 03:50:37,912][88327] Updated weights for policy 1, policy_version 91920 (0.0009) -[2023-10-09 03:50:38,276][88327] Updated weights for policy 1, policy_version 91930 (0.0008) -[2023-10-09 03:50:38,974][87372] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 188186624. Throughput: 0: 1701.9, 1: 1701.0. Samples: 47045514. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:50:38,975][87372] Avg episode reward: [(0, '7.190'), (1, '7.940')] -[2023-10-09 03:50:41,803][88326] Updated weights for policy 0, policy_version 91842 (0.0007) -[2023-10-09 03:50:42,169][88326] Updated weights for policy 0, policy_version 91852 (0.0010) -[2023-10-09 03:50:42,394][88327] Updated weights for policy 1, policy_version 91940 (0.0007) -[2023-10-09 03:50:42,540][88326] Updated weights for policy 0, policy_version 91862 (0.0008) -[2023-10-09 03:50:42,755][88327] Updated weights for policy 1, policy_version 91950 (0.0007) -[2023-10-09 03:50:42,907][88326] Updated weights for policy 0, policy_version 91872 (0.0008) -[2023-10-09 03:50:43,126][88327] Updated weights for policy 1, policy_version 91960 (0.0009) -[2023-10-09 03:50:43,974][87372] Fps is (10 sec: 13107.5, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 188252160. Throughput: 0: 1683.2, 1: 1698.6. Samples: 47065626. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:50:43,975][87372] Avg episode reward: [(0, '6.950'), (1, '7.860')] -[2023-10-09 03:50:47,036][88327] Updated weights for policy 1, policy_version 91970 (0.0009) -[2023-10-09 03:50:47,098][88326] Updated weights for policy 0, policy_version 91882 (0.0007) -[2023-10-09 03:50:47,393][88327] Updated weights for policy 1, policy_version 91980 (0.0008) -[2023-10-09 03:50:47,463][88326] Updated weights for policy 0, policy_version 91892 (0.0007) -[2023-10-09 03:50:47,763][88327] Updated weights for policy 1, policy_version 91990 (0.0008) -[2023-10-09 03:50:47,838][88326] Updated weights for policy 0, policy_version 91902 (0.0007) -[2023-10-09 03:50:48,120][88327] Updated weights for policy 1, policy_version 92000 (0.0009) -[2023-10-09 03:50:48,974][87372] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 188317696. Throughput: 0: 1673.3, 1: 1666.3. Samples: 47084338. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:50:48,975][87372] Avg episode reward: [(0, '6.670'), (1, '7.370')] -[2023-10-09 03:50:51,845][88326] Updated weights for policy 0, policy_version 91912 (0.0007) -[2023-10-09 03:50:52,209][88327] Updated weights for policy 1, policy_version 92010 (0.0008) -[2023-10-09 03:50:52,212][88326] Updated weights for policy 0, policy_version 91922 (0.0007) -[2023-10-09 03:50:52,583][88327] Updated weights for policy 1, policy_version 92020 (0.0007) -[2023-10-09 03:50:52,586][88326] Updated weights for policy 0, policy_version 91932 (0.0009) -[2023-10-09 03:50:52,943][88327] Updated weights for policy 1, policy_version 92030 (0.0008) -[2023-10-09 03:50:53,974][87372] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 188383232. Throughput: 0: 1685.6, 1: 1696.4. Samples: 47095980. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:50:53,975][87372] Avg episode reward: [(0, '6.710'), (1, '6.610')] -[2023-10-09 03:50:56,626][88326] Updated weights for policy 0, policy_version 91942 (0.0007) -[2023-10-09 03:50:57,005][88326] Updated weights for policy 0, policy_version 91952 (0.0007) -[2023-10-09 03:50:57,012][88327] Updated weights for policy 1, policy_version 92040 (0.0009) -[2023-10-09 03:50:57,366][88326] Updated weights for policy 0, policy_version 91962 (0.0009) -[2023-10-09 03:50:57,372][88327] Updated weights for policy 1, policy_version 92050 (0.0009) -[2023-10-09 03:50:57,750][88327] Updated weights for policy 1, policy_version 92060 (0.0008) -[2023-10-09 03:50:58,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 188448768. Throughput: 0: 1663.9, 1: 1691.8. Samples: 47115778. Policy #0 lag: (min: 31.0, avg: 32.2, max: 54.0) -[2023-10-09 03:50:58,975][87372] Avg episode reward: [(0, '7.240'), (1, '6.800')] -[2023-10-09 03:51:01,392][88326] Updated weights for policy 0, policy_version 91972 (0.0007) -[2023-10-09 03:51:01,712][88327] Updated weights for policy 1, policy_version 92070 (0.0009) -[2023-10-09 03:51:01,752][88326] Updated weights for policy 0, policy_version 91982 (0.0008) -[2023-10-09 03:51:02,073][88327] Updated weights for policy 1, policy_version 92080 (0.0007) -[2023-10-09 03:51:02,126][88326] Updated weights for policy 0, policy_version 91992 (0.0008) -[2023-10-09 03:51:02,440][88327] Updated weights for policy 1, policy_version 92090 (0.0007) -[2023-10-09 03:51:03,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 188514304. Throughput: 0: 1679.9, 1: 1675.5. Samples: 47135592. Policy #0 lag: (min: 31.0, avg: 32.2, max: 54.0) -[2023-10-09 03:51:03,975][87372] Avg episode reward: [(0, '6.650'), (1, '7.550')] -[2023-10-09 03:51:06,057][88326] Updated weights for policy 0, policy_version 92002 (0.0008) -[2023-10-09 03:51:06,343][88327] Updated weights for policy 1, policy_version 92100 (0.0008) -[2023-10-09 03:51:06,456][88326] Updated weights for policy 0, policy_version 92012 (0.0007) -[2023-10-09 03:51:06,707][88327] Updated weights for policy 1, policy_version 92110 (0.0008) -[2023-10-09 03:51:06,825][88326] Updated weights for policy 0, policy_version 92022 (0.0008) -[2023-10-09 03:51:07,064][88327] Updated weights for policy 1, policy_version 92120 (0.0007) -[2023-10-09 03:51:07,183][88326] Updated weights for policy 0, policy_version 92032 (0.0009) -[2023-10-09 03:51:08,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 188579840. Throughput: 0: 1677.3, 1: 1703.4. Samples: 47147226. Policy #0 lag: (min: 31.0, avg: 32.2, max: 54.0) -[2023-10-09 03:51:08,975][87372] Avg episode reward: [(0, '6.630'), (1, '7.480')] -[2023-10-09 03:51:11,240][88327] Updated weights for policy 1, policy_version 92130 (0.0007) -[2023-10-09 03:51:11,278][88326] Updated weights for policy 0, policy_version 92042 (0.0009) -[2023-10-09 03:51:11,603][88327] Updated weights for policy 1, policy_version 92140 (0.0011) -[2023-10-09 03:51:11,647][88326] Updated weights for policy 0, policy_version 92052 (0.0008) -[2023-10-09 03:51:11,976][88327] Updated weights for policy 1, policy_version 92150 (0.0009) -[2023-10-09 03:51:12,002][88326] Updated weights for policy 0, policy_version 92062 (0.0010) -[2023-10-09 03:51:12,340][88327] Updated weights for policy 1, policy_version 92160 (0.0009) -[2023-10-09 03:51:13,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 188645376. Throughput: 0: 1662.6, 1: 1681.8. Samples: 47165824. Policy #0 lag: (min: 31.0, avg: 32.2, max: 54.0) -[2023-10-09 03:51:13,975][87372] Avg episode reward: [(0, '6.760'), (1, '7.500')] -[2023-10-09 03:51:15,985][88326] Updated weights for policy 0, policy_version 92072 (0.0008) -[2023-10-09 03:51:16,297][88327] Updated weights for policy 1, policy_version 92170 (0.0008) -[2023-10-09 03:51:16,348][88326] Updated weights for policy 0, policy_version 92082 (0.0007) -[2023-10-09 03:51:16,662][88327] Updated weights for policy 1, policy_version 92180 (0.0008) -[2023-10-09 03:51:16,714][88326] Updated weights for policy 0, policy_version 92092 (0.0007) -[2023-10-09 03:51:17,015][88327] Updated weights for policy 1, policy_version 92190 (0.0009) -[2023-10-09 03:51:18,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 188710912. Throughput: 0: 1690.9, 1: 1686.1. Samples: 47186398. Policy #0 lag: (min: 31.0, avg: 32.2, max: 54.0) -[2023-10-09 03:51:18,975][87372] Avg episode reward: [(0, '7.070'), (1, '8.020')] -[2023-10-09 03:51:20,708][88326] Updated weights for policy 0, policy_version 92102 (0.0008) -[2023-10-09 03:51:21,078][88326] Updated weights for policy 0, policy_version 92112 (0.0009) -[2023-10-09 03:51:21,155][88327] Updated weights for policy 1, policy_version 92200 (0.0007) -[2023-10-09 03:51:21,451][88326] Updated weights for policy 0, policy_version 92122 (0.0009) -[2023-10-09 03:51:21,522][88327] Updated weights for policy 1, policy_version 92210 (0.0008) -[2023-10-09 03:51:21,894][88327] Updated weights for policy 1, policy_version 92220 (0.0009) -[2023-10-09 03:51:23,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 188776448. Throughput: 0: 1677.0, 1: 1692.0. Samples: 47197120. Policy #0 lag: (min: 31.0, avg: 32.2, max: 54.0) -[2023-10-09 03:51:23,975][87372] Avg episode reward: [(0, '7.050'), (1, '8.090')] -[2023-10-09 03:51:25,510][88326] Updated weights for policy 0, policy_version 92132 (0.0007) -[2023-10-09 03:51:25,883][88326] Updated weights for policy 0, policy_version 92142 (0.0007) -[2023-10-09 03:51:25,918][88327] Updated weights for policy 1, policy_version 92230 (0.0008) -[2023-10-09 03:51:26,252][88326] Updated weights for policy 0, policy_version 92152 (0.0009) -[2023-10-09 03:51:26,287][88327] Updated weights for policy 1, policy_version 92240 (0.0007) -[2023-10-09 03:51:26,650][88327] Updated weights for policy 1, policy_version 92250 (0.0008) -[2023-10-09 03:51:28,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 188841984. Throughput: 0: 1681.2, 1: 1676.7. Samples: 47216732. Policy #0 lag: (min: 31.0, avg: 32.2, max: 54.0) -[2023-10-09 03:51:28,974][87372] Avg episode reward: [(0, '7.390'), (1, '7.710')] -[2023-10-09 03:51:30,130][88326] Updated weights for policy 0, policy_version 92162 (0.0010) -[2023-10-09 03:51:30,512][88326] Updated weights for policy 0, policy_version 92172 (0.0008) -[2023-10-09 03:51:30,855][88327] Updated weights for policy 1, policy_version 92260 (0.0009) -[2023-10-09 03:51:30,886][88326] Updated weights for policy 0, policy_version 92182 (0.0009) -[2023-10-09 03:51:31,229][88327] Updated weights for policy 1, policy_version 92270 (0.0008) -[2023-10-09 03:51:31,252][88326] Updated weights for policy 0, policy_version 92192 (0.0007) -[2023-10-09 03:51:31,589][88327] Updated weights for policy 1, policy_version 92280 (0.0010) -[2023-10-09 03:51:33,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 188907520. Throughput: 0: 1707.9, 1: 1703.5. Samples: 47237852. Policy #0 lag: (min: 31.0, avg: 32.2, max: 54.0) -[2023-10-09 03:51:33,975][87372] Avg episode reward: [(0, '7.680'), (1, '7.480')] -[2023-10-09 03:51:35,062][88326] Updated weights for policy 0, policy_version 92202 (0.0010) -[2023-10-09 03:51:35,426][88326] Updated weights for policy 0, policy_version 92212 (0.0010) -[2023-10-09 03:51:35,522][88327] Updated weights for policy 1, policy_version 92290 (0.0010) -[2023-10-09 03:51:35,797][88326] Updated weights for policy 0, policy_version 92222 (0.0007) -[2023-10-09 03:51:35,873][88327] Updated weights for policy 1, policy_version 92300 (0.0007) -[2023-10-09 03:51:36,238][88327] Updated weights for policy 1, policy_version 92310 (0.0007) -[2023-10-09 03:51:36,599][88327] Updated weights for policy 1, policy_version 92320 (0.0008) -[2023-10-09 03:51:38,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 188973056. Throughput: 0: 1680.2, 1: 1690.8. Samples: 47247676. Policy #0 lag: (min: 31.0, avg: 32.2, max: 54.0) -[2023-10-09 03:51:38,975][87372] Avg episode reward: [(0, '7.430'), (1, '7.730')] -[2023-10-09 03:51:39,907][88326] Updated weights for policy 0, policy_version 92232 (0.0008) -[2023-10-09 03:51:40,273][88326] Updated weights for policy 0, policy_version 92242 (0.0007) -[2023-10-09 03:51:40,481][88327] Updated weights for policy 1, policy_version 92330 (0.0009) -[2023-10-09 03:51:40,640][88326] Updated weights for policy 0, policy_version 92252 (0.0008) -[2023-10-09 03:51:40,850][88327] Updated weights for policy 1, policy_version 92340 (0.0008) -[2023-10-09 03:51:41,212][88327] Updated weights for policy 1, policy_version 92350 (0.0009) -[2023-10-09 03:51:43,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 189038592. Throughput: 0: 1694.9, 1: 1689.6. Samples: 47268080. Policy #0 lag: (min: 31.0, avg: 32.2, max: 54.0) -[2023-10-09 03:51:43,975][87372] Avg episode reward: [(0, '7.300'), (1, '7.880')] -[2023-10-09 03:51:44,639][88326] Updated weights for policy 0, policy_version 92262 (0.0011) -[2023-10-09 03:51:45,000][88326] Updated weights for policy 0, policy_version 92272 (0.0008) -[2023-10-09 03:51:45,098][88327] Updated weights for policy 1, policy_version 92360 (0.0007) -[2023-10-09 03:51:45,364][88326] Updated weights for policy 0, policy_version 92282 (0.0009) -[2023-10-09 03:51:45,478][88327] Updated weights for policy 1, policy_version 92370 (0.0008) -[2023-10-09 03:51:45,837][88327] Updated weights for policy 1, policy_version 92380 (0.0010) -[2023-10-09 03:51:48,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 189104128. Throughput: 0: 1705.7, 1: 1708.4. Samples: 47289230. Policy #0 lag: (min: 31.0, avg: 32.2, max: 54.0) -[2023-10-09 03:51:48,975][87372] Avg episode reward: [(0, '7.300'), (1, '7.400')] -[2023-10-09 03:51:49,245][88326] Updated weights for policy 0, policy_version 92292 (0.0008) -[2023-10-09 03:51:49,611][88326] Updated weights for policy 0, policy_version 92302 (0.0011) -[2023-10-09 03:51:49,855][88327] Updated weights for policy 1, policy_version 92390 (0.0009) -[2023-10-09 03:51:49,980][88326] Updated weights for policy 0, policy_version 92312 (0.0010) -[2023-10-09 03:51:50,221][88327] Updated weights for policy 1, policy_version 92400 (0.0008) -[2023-10-09 03:51:50,584][88327] Updated weights for policy 1, policy_version 92410 (0.0007) -[2023-10-09 03:51:53,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 189169664. Throughput: 0: 1682.9, 1: 1676.5. Samples: 47298398. Policy #0 lag: (min: 31.0, avg: 32.2, max: 54.0) -[2023-10-09 03:51:53,974][87372] Avg episode reward: [(0, '7.130'), (1, '7.910')] -[2023-10-09 03:51:54,104][88326] Updated weights for policy 0, policy_version 92322 (0.0008) -[2023-10-09 03:51:54,500][88326] Updated weights for policy 0, policy_version 92332 (0.0009) -[2023-10-09 03:51:54,615][88327] Updated weights for policy 1, policy_version 92420 (0.0010) -[2023-10-09 03:51:54,863][88326] Updated weights for policy 0, policy_version 92342 (0.0008) -[2023-10-09 03:51:54,973][88327] Updated weights for policy 1, policy_version 92430 (0.0008) -[2023-10-09 03:51:55,239][88326] Updated weights for policy 0, policy_version 92352 (0.0008) -[2023-10-09 03:51:55,336][88327] Updated weights for policy 1, policy_version 92440 (0.0007) -[2023-10-09 03:51:58,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 189235200. Throughput: 0: 1710.2, 1: 1702.7. Samples: 47319404. Policy #0 lag: (min: 10.0, avg: 12.9, max: 42.0) -[2023-10-09 03:51:58,974][87372] Avg episode reward: [(0, '7.040'), (1, '7.530')] -[2023-10-09 03:51:59,251][88327] Updated weights for policy 1, policy_version 92450 (0.0009) -[2023-10-09 03:51:59,262][88326] Updated weights for policy 0, policy_version 92362 (0.0009) -[2023-10-09 03:51:59,614][88327] Updated weights for policy 1, policy_version 92460 (0.0008) -[2023-10-09 03:51:59,629][88326] Updated weights for policy 0, policy_version 92372 (0.0009) -[2023-10-09 03:51:59,978][88327] Updated weights for policy 1, policy_version 92470 (0.0008) -[2023-10-09 03:52:00,004][88326] Updated weights for policy 0, policy_version 92382 (0.0009) -[2023-10-09 03:52:00,338][88327] Updated weights for policy 1, policy_version 92480 (0.0011) -[2023-10-09 03:52:03,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 189300736. Throughput: 0: 1704.3, 1: 1716.5. Samples: 47340332. Policy #0 lag: (min: 10.0, avg: 12.9, max: 42.0) -[2023-10-09 03:52:03,975][87372] Avg episode reward: [(0, '7.330'), (1, '7.670')] -[2023-10-09 03:52:04,103][88326] Updated weights for policy 0, policy_version 92392 (0.0009) -[2023-10-09 03:52:04,476][88326] Updated weights for policy 0, policy_version 92402 (0.0009) -[2023-10-09 03:52:04,526][88327] Updated weights for policy 1, policy_version 92490 (0.0011) -[2023-10-09 03:52:04,847][88326] Updated weights for policy 0, policy_version 92412 (0.0007) -[2023-10-09 03:52:04,900][88327] Updated weights for policy 1, policy_version 92500 (0.0008) -[2023-10-09 03:52:05,262][88327] Updated weights for policy 1, policy_version 92510 (0.0009) -[2023-10-09 03:52:08,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 189366272. Throughput: 0: 1686.2, 1: 1691.1. Samples: 47349096. Policy #0 lag: (min: 10.0, avg: 12.9, max: 42.0) -[2023-10-09 03:52:08,975][87372] Avg episode reward: [(0, '6.760'), (1, '7.050')] -[2023-10-09 03:52:08,992][88326] Updated weights for policy 0, policy_version 92422 (0.0010) -[2023-10-09 03:52:09,322][88327] Updated weights for policy 1, policy_version 92520 (0.0008) -[2023-10-09 03:52:09,359][88326] Updated weights for policy 0, policy_version 92432 (0.0008) -[2023-10-09 03:52:09,688][88327] Updated weights for policy 1, policy_version 92530 (0.0009) -[2023-10-09 03:52:09,727][88326] Updated weights for policy 0, policy_version 92442 (0.0007) -[2023-10-09 03:52:10,057][88327] Updated weights for policy 1, policy_version 92540 (0.0008) -[2023-10-09 03:52:13,885][88326] Updated weights for policy 0, policy_version 92452 (0.0008) -[2023-10-09 03:52:13,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 189431808. Throughput: 0: 1697.2, 1: 1704.1. Samples: 47369792. Policy #0 lag: (min: 10.0, avg: 12.9, max: 42.0) -[2023-10-09 03:52:13,975][87372] Avg episode reward: [(0, '7.060'), (1, '7.170')] -[2023-10-09 03:52:14,251][88326] Updated weights for policy 0, policy_version 92462 (0.0010) -[2023-10-09 03:52:14,260][88327] Updated weights for policy 1, policy_version 92550 (0.0009) -[2023-10-09 03:52:14,612][88326] Updated weights for policy 0, policy_version 92472 (0.0009) -[2023-10-09 03:52:14,621][88327] Updated weights for policy 1, policy_version 92560 (0.0007) -[2023-10-09 03:52:14,979][88327] Updated weights for policy 1, policy_version 92570 (0.0009) -[2023-10-09 03:52:18,624][88326] Updated weights for policy 0, policy_version 92482 (0.0010) -[2023-10-09 03:52:18,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 189497344. Throughput: 0: 1690.1, 1: 1703.2. Samples: 47390550. Policy #0 lag: (min: 10.0, avg: 12.9, max: 42.0) -[2023-10-09 03:52:18,975][87372] Avg episode reward: [(0, '6.990'), (1, '7.560')] -[2023-10-09 03:52:18,978][88327] Updated weights for policy 1, policy_version 92580 (0.0009) -[2023-10-09 03:52:18,999][88326] Updated weights for policy 0, policy_version 92492 (0.0009) -[2023-10-09 03:52:19,335][88327] Updated weights for policy 1, policy_version 92590 (0.0007) -[2023-10-09 03:52:19,377][88326] Updated weights for policy 0, policy_version 92502 (0.0008) -[2023-10-09 03:52:19,703][88327] Updated weights for policy 1, policy_version 92600 (0.0008) -[2023-10-09 03:52:19,754][88326] Updated weights for policy 0, policy_version 92512 (0.0008) -[2023-10-09 03:52:23,719][88327] Updated weights for policy 1, policy_version 92610 (0.0007) -[2023-10-09 03:52:23,862][88326] Updated weights for policy 0, policy_version 92522 (0.0007) -[2023-10-09 03:52:23,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 189562880. Throughput: 0: 1687.6, 1: 1690.4. Samples: 47399684. Policy #0 lag: (min: 10.0, avg: 12.9, max: 42.0) -[2023-10-09 03:52:23,975][87372] Avg episode reward: [(0, '6.730'), (1, '7.700')] -[2023-10-09 03:52:24,078][88327] Updated weights for policy 1, policy_version 92620 (0.0007) -[2023-10-09 03:52:24,235][88326] Updated weights for policy 0, policy_version 92532 (0.0007) -[2023-10-09 03:52:24,441][88327] Updated weights for policy 1, policy_version 92630 (0.0007) -[2023-10-09 03:52:24,605][88326] Updated weights for policy 0, policy_version 92542 (0.0008) -[2023-10-09 03:52:24,801][88327] Updated weights for policy 1, policy_version 92640 (0.0007) -[2023-10-09 03:52:28,613][88326] Updated weights for policy 0, policy_version 92552 (0.0009) -[2023-10-09 03:52:28,716][88327] Updated weights for policy 1, policy_version 92650 (0.0008) -[2023-10-09 03:52:28,971][88326] Updated weights for policy 0, policy_version 92562 (0.0008) -[2023-10-09 03:52:28,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 189628416. Throughput: 0: 1689.4, 1: 1701.6. Samples: 47420674. Policy #0 lag: (min: 10.0, avg: 12.9, max: 42.0) -[2023-10-09 03:52:28,974][87372] Avg episode reward: [(0, '7.040'), (1, '7.640')] -[2023-10-09 03:52:29,081][88327] Updated weights for policy 1, policy_version 92660 (0.0008) -[2023-10-09 03:52:29,342][88326] Updated weights for policy 0, policy_version 92572 (0.0009) -[2023-10-09 03:52:29,451][88327] Updated weights for policy 1, policy_version 92670 (0.0008) -[2023-10-09 03:52:33,426][88326] Updated weights for policy 0, policy_version 92582 (0.0008) -[2023-10-09 03:52:33,720][88327] Updated weights for policy 1, policy_version 92680 (0.0009) -[2023-10-09 03:52:33,791][88326] Updated weights for policy 0, policy_version 92592 (0.0008) -[2023-10-09 03:52:33,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 189693952. Throughput: 0: 1681.1, 1: 1695.5. Samples: 47441178. Policy #0 lag: (min: 10.0, avg: 12.9, max: 42.0) -[2023-10-09 03:52:33,975][87372] Avg episode reward: [(0, '7.260'), (1, '7.970')] -[2023-10-09 03:52:34,080][88327] Updated weights for policy 1, policy_version 92690 (0.0009) -[2023-10-09 03:52:34,170][88326] Updated weights for policy 0, policy_version 92602 (0.0009) -[2023-10-09 03:52:34,391][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000092608_94830592.pth... -[2023-10-09 03:52:34,428][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000091008_93192192.pth -[2023-10-09 03:52:34,451][88327] Updated weights for policy 1, policy_version 92700 (0.0007) -[2023-10-09 03:52:34,595][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000092704_94928896.pth... -[2023-10-09 03:52:34,634][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000091104_93290496.pth -[2023-10-09 03:52:38,223][88326] Updated weights for policy 0, policy_version 92612 (0.0008) -[2023-10-09 03:52:38,354][88327] Updated weights for policy 1, policy_version 92710 (0.0009) -[2023-10-09 03:52:38,606][88326] Updated weights for policy 0, policy_version 92622 (0.0009) -[2023-10-09 03:52:38,712][88327] Updated weights for policy 1, policy_version 92720 (0.0008) -[2023-10-09 03:52:38,964][88326] Updated weights for policy 0, policy_version 92632 (0.0008) -[2023-10-09 03:52:38,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 189759488. Throughput: 0: 1684.9, 1: 1693.8. Samples: 47450440. Policy #0 lag: (min: 10.0, avg: 12.9, max: 42.0) -[2023-10-09 03:52:38,975][87372] Avg episode reward: [(0, '6.950'), (1, '7.770')] -[2023-10-09 03:52:39,081][88327] Updated weights for policy 1, policy_version 92730 (0.0009) -[2023-10-09 03:52:43,119][88326] Updated weights for policy 0, policy_version 92642 (0.0008) -[2023-10-09 03:52:43,179][88327] Updated weights for policy 1, policy_version 92740 (0.0010) -[2023-10-09 03:52:43,483][88326] Updated weights for policy 0, policy_version 92652 (0.0009) -[2023-10-09 03:52:43,544][88327] Updated weights for policy 1, policy_version 92750 (0.0008) -[2023-10-09 03:52:43,845][88326] Updated weights for policy 0, policy_version 92662 (0.0009) -[2023-10-09 03:52:43,905][88327] Updated weights for policy 1, policy_version 92760 (0.0007) -[2023-10-09 03:52:43,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 189825024. Throughput: 0: 1679.9, 1: 1690.8. Samples: 47471088. Policy #0 lag: (min: 10.0, avg: 12.9, max: 42.0) -[2023-10-09 03:52:43,975][87372] Avg episode reward: [(0, '7.140'), (1, '7.670')] -[2023-10-09 03:52:44,211][88326] Updated weights for policy 0, policy_version 92672 (0.0008) -[2023-10-09 03:52:47,866][88327] Updated weights for policy 1, policy_version 92770 (0.0008) -[2023-10-09 03:52:48,236][88327] Updated weights for policy 1, policy_version 92780 (0.0009) -[2023-10-09 03:52:48,446][88326] Updated weights for policy 0, policy_version 92682 (0.0008) -[2023-10-09 03:52:48,592][88327] Updated weights for policy 1, policy_version 92790 (0.0008) -[2023-10-09 03:52:48,819][88326] Updated weights for policy 0, policy_version 92692 (0.0008) -[2023-10-09 03:52:48,955][88327] Updated weights for policy 1, policy_version 92800 (0.0008) -[2023-10-09 03:52:48,974][87372] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 189923328. Throughput: 0: 1674.7, 1: 1685.1. Samples: 47491522. Policy #0 lag: (min: 10.0, avg: 12.9, max: 42.0) -[2023-10-09 03:52:48,975][87372] Avg episode reward: [(0, '7.230'), (1, '7.590')] -[2023-10-09 03:52:49,187][88326] Updated weights for policy 0, policy_version 92702 (0.0009) -[2023-10-09 03:52:52,916][88327] Updated weights for policy 1, policy_version 92810 (0.0008) -[2023-10-09 03:52:53,284][88326] Updated weights for policy 0, policy_version 92712 (0.0009) -[2023-10-09 03:52:53,290][88327] Updated weights for policy 1, policy_version 92820 (0.0009) -[2023-10-09 03:52:53,646][88326] Updated weights for policy 0, policy_version 92722 (0.0008) -[2023-10-09 03:52:53,658][88327] Updated weights for policy 1, policy_version 92830 (0.0008) -[2023-10-09 03:52:53,974][87372] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 189988864. Throughput: 0: 1681.7, 1: 1699.4. Samples: 47501248. Policy #0 lag: (min: 10.0, avg: 12.9, max: 42.0) -[2023-10-09 03:52:53,975][87372] Avg episode reward: [(0, '6.550'), (1, '6.960')] -[2023-10-09 03:52:54,012][88326] Updated weights for policy 0, policy_version 92732 (0.0007) -[2023-10-09 03:52:57,918][88327] Updated weights for policy 1, policy_version 92840 (0.0010) -[2023-10-09 03:52:58,085][88326] Updated weights for policy 0, policy_version 92742 (0.0009) -[2023-10-09 03:52:58,279][88327] Updated weights for policy 1, policy_version 92850 (0.0010) -[2023-10-09 03:52:58,452][88326] Updated weights for policy 0, policy_version 92752 (0.0009) -[2023-10-09 03:52:58,646][88327] Updated weights for policy 1, policy_version 92860 (0.0008) -[2023-10-09 03:52:58,818][88326] Updated weights for policy 0, policy_version 92762 (0.0009) -[2023-10-09 03:52:58,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 190054400. Throughput: 0: 1683.0, 1: 1693.8. Samples: 47521748. Policy #0 lag: (min: 31.0, avg: 45.2, max: 63.0) -[2023-10-09 03:52:58,975][87372] Avg episode reward: [(0, '6.810'), (1, '7.520')] -[2023-10-09 03:53:02,764][88326] Updated weights for policy 0, policy_version 92772 (0.0009) -[2023-10-09 03:53:02,963][88327] Updated weights for policy 1, policy_version 92870 (0.0009) -[2023-10-09 03:53:03,131][88326] Updated weights for policy 0, policy_version 92782 (0.0008) -[2023-10-09 03:53:03,316][88327] Updated weights for policy 1, policy_version 92880 (0.0009) -[2023-10-09 03:53:03,508][88326] Updated weights for policy 0, policy_version 92792 (0.0008) -[2023-10-09 03:53:03,675][88327] Updated weights for policy 1, policy_version 92890 (0.0010) -[2023-10-09 03:53:03,974][87372] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 190152704. Throughput: 0: 1670.5, 1: 1679.7. Samples: 47541312. Policy #0 lag: (min: 31.0, avg: 45.2, max: 63.0) -[2023-10-09 03:53:03,975][87372] Avg episode reward: [(0, '6.630'), (1, '7.030')] -[2023-10-09 03:53:07,565][88326] Updated weights for policy 0, policy_version 92802 (0.0008) -[2023-10-09 03:53:07,921][88327] Updated weights for policy 1, policy_version 92900 (0.0009) -[2023-10-09 03:53:07,936][88326] Updated weights for policy 0, policy_version 92812 (0.0007) -[2023-10-09 03:53:08,281][88327] Updated weights for policy 1, policy_version 92910 (0.0007) -[2023-10-09 03:53:08,299][88326] Updated weights for policy 0, policy_version 92822 (0.0007) -[2023-10-09 03:53:08,639][88327] Updated weights for policy 1, policy_version 92920 (0.0008) -[2023-10-09 03:53:08,658][88326] Updated weights for policy 0, policy_version 92832 (0.0007) -[2023-10-09 03:53:08,974][87372] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 190218240. Throughput: 0: 1688.6, 1: 1685.2. Samples: 47551506. Policy #0 lag: (min: 31.0, avg: 45.2, max: 63.0) -[2023-10-09 03:53:08,975][87372] Avg episode reward: [(0, '6.520'), (1, '7.630')] -[2023-10-09 03:53:12,562][88326] Updated weights for policy 0, policy_version 92842 (0.0011) -[2023-10-09 03:53:12,797][88327] Updated weights for policy 1, policy_version 92930 (0.0009) -[2023-10-09 03:53:12,936][88326] Updated weights for policy 0, policy_version 92852 (0.0010) -[2023-10-09 03:53:13,146][88327] Updated weights for policy 1, policy_version 92940 (0.0008) -[2023-10-09 03:53:13,311][88326] Updated weights for policy 0, policy_version 92862 (0.0008) -[2023-10-09 03:53:13,515][88327] Updated weights for policy 1, policy_version 92950 (0.0007) -[2023-10-09 03:53:13,882][88327] Updated weights for policy 1, policy_version 92960 (0.0008) -[2023-10-09 03:53:13,974][87372] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 190283776. Throughput: 0: 1689.9, 1: 1680.5. Samples: 47572340. Policy #0 lag: (min: 31.0, avg: 45.2, max: 63.0) -[2023-10-09 03:53:13,975][87372] Avg episode reward: [(0, '7.420'), (1, '7.380')] -[2023-10-09 03:53:17,389][88326] Updated weights for policy 0, policy_version 92872 (0.0009) -[2023-10-09 03:53:17,768][88326] Updated weights for policy 0, policy_version 92882 (0.0007) -[2023-10-09 03:53:17,802][88327] Updated weights for policy 1, policy_version 92970 (0.0009) -[2023-10-09 03:53:18,131][88326] Updated weights for policy 0, policy_version 92892 (0.0010) -[2023-10-09 03:53:18,158][88327] Updated weights for policy 1, policy_version 92980 (0.0009) -[2023-10-09 03:53:18,533][88327] Updated weights for policy 1, policy_version 92990 (0.0009) -[2023-10-09 03:53:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 190349312. Throughput: 0: 1666.1, 1: 1672.6. Samples: 47591420. Policy #0 lag: (min: 31.0, avg: 45.2, max: 63.0) -[2023-10-09 03:53:18,975][87372] Avg episode reward: [(0, '7.290'), (1, '7.630')] -[2023-10-09 03:53:22,260][88326] Updated weights for policy 0, policy_version 92902 (0.0008) -[2023-10-09 03:53:22,539][88327] Updated weights for policy 1, policy_version 93000 (0.0008) -[2023-10-09 03:53:22,628][88326] Updated weights for policy 0, policy_version 92912 (0.0009) -[2023-10-09 03:53:22,901][88327] Updated weights for policy 1, policy_version 93010 (0.0007) -[2023-10-09 03:53:22,988][88326] Updated weights for policy 0, policy_version 92922 (0.0009) -[2023-10-09 03:53:23,267][88327] Updated weights for policy 1, policy_version 93020 (0.0008) -[2023-10-09 03:53:23,974][87372] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 190414848. Throughput: 0: 1688.5, 1: 1687.0. Samples: 47602338. Policy #0 lag: (min: 31.0, avg: 45.2, max: 63.0) -[2023-10-09 03:53:23,975][87372] Avg episode reward: [(0, '7.410'), (1, '7.150')] -[2023-10-09 03:53:27,110][88326] Updated weights for policy 0, policy_version 92932 (0.0007) -[2023-10-09 03:53:27,254][88327] Updated weights for policy 1, policy_version 93030 (0.0010) -[2023-10-09 03:53:27,499][88326] Updated weights for policy 0, policy_version 92942 (0.0010) -[2023-10-09 03:53:27,614][88327] Updated weights for policy 1, policy_version 93040 (0.0007) -[2023-10-09 03:53:27,857][88326] Updated weights for policy 0, policy_version 92952 (0.0008) -[2023-10-09 03:53:27,982][88327] Updated weights for policy 1, policy_version 93050 (0.0007) -[2023-10-09 03:53:28,974][87372] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 190480384. Throughput: 0: 1682.6, 1: 1686.0. Samples: 47622676. Policy #0 lag: (min: 31.0, avg: 45.2, max: 63.0) -[2023-10-09 03:53:28,975][87372] Avg episode reward: [(0, '7.330'), (1, '7.390')] -[2023-10-09 03:53:31,962][88327] Updated weights for policy 1, policy_version 93060 (0.0008) -[2023-10-09 03:53:32,063][88326] Updated weights for policy 0, policy_version 92962 (0.0009) -[2023-10-09 03:53:32,319][88327] Updated weights for policy 1, policy_version 93070 (0.0007) -[2023-10-09 03:53:32,430][88326] Updated weights for policy 0, policy_version 92972 (0.0009) -[2023-10-09 03:53:32,685][88327] Updated weights for policy 1, policy_version 93080 (0.0007) -[2023-10-09 03:53:32,790][88326] Updated weights for policy 0, policy_version 92982 (0.0008) -[2023-10-09 03:53:33,173][88326] Updated weights for policy 0, policy_version 92992 (0.0008) -[2023-10-09 03:53:33,974][87372] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 190545920. Throughput: 0: 1664.5, 1: 1665.7. Samples: 47641380. Policy #0 lag: (min: 31.0, avg: 45.2, max: 63.0) -[2023-10-09 03:53:33,975][87372] Avg episode reward: [(0, '6.460'), (1, '7.720')] -[2023-10-09 03:53:36,776][88327] Updated weights for policy 1, policy_version 93090 (0.0007) -[2023-10-09 03:53:37,136][88327] Updated weights for policy 1, policy_version 93100 (0.0007) -[2023-10-09 03:53:37,226][88326] Updated weights for policy 0, policy_version 93002 (0.0008) -[2023-10-09 03:53:37,496][88327] Updated weights for policy 1, policy_version 93110 (0.0007) -[2023-10-09 03:53:37,608][88326] Updated weights for policy 0, policy_version 93012 (0.0009) -[2023-10-09 03:53:37,858][88327] Updated weights for policy 1, policy_version 93120 (0.0009) -[2023-10-09 03:53:37,974][88326] Updated weights for policy 0, policy_version 93022 (0.0010) -[2023-10-09 03:53:38,974][87372] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 190611456. Throughput: 0: 1683.2, 1: 1684.5. Samples: 47652792. Policy #0 lag: (min: 31.0, avg: 45.2, max: 63.0) -[2023-10-09 03:53:38,975][87372] Avg episode reward: [(0, '6.790'), (1, '8.350')] -[2023-10-09 03:53:41,916][88326] Updated weights for policy 0, policy_version 93032 (0.0008) -[2023-10-09 03:53:42,156][88327] Updated weights for policy 1, policy_version 93130 (0.0007) -[2023-10-09 03:53:42,290][88326] Updated weights for policy 0, policy_version 93042 (0.0008) -[2023-10-09 03:53:42,517][88327] Updated weights for policy 1, policy_version 93140 (0.0010) -[2023-10-09 03:53:42,646][88326] Updated weights for policy 0, policy_version 93052 (0.0009) -[2023-10-09 03:53:42,877][88327] Updated weights for policy 1, policy_version 93150 (0.0008) -[2023-10-09 03:53:43,974][87372] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 190676992. Throughput: 0: 1674.1, 1: 1674.5. Samples: 47672436. Policy #0 lag: (min: 31.0, avg: 45.2, max: 63.0) -[2023-10-09 03:53:43,974][87372] Avg episode reward: [(0, '6.680'), (1, '7.410')] -[2023-10-09 03:53:46,639][88326] Updated weights for policy 0, policy_version 93062 (0.0008) -[2023-10-09 03:53:46,942][88327] Updated weights for policy 1, policy_version 93160 (0.0009) -[2023-10-09 03:53:47,011][88326] Updated weights for policy 0, policy_version 93072 (0.0007) -[2023-10-09 03:53:47,295][88327] Updated weights for policy 1, policy_version 93170 (0.0008) -[2023-10-09 03:53:47,372][88326] Updated weights for policy 0, policy_version 93082 (0.0008) -[2023-10-09 03:53:47,654][88327] Updated weights for policy 1, policy_version 93180 (0.0010) -[2023-10-09 03:53:48,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 190742528. Throughput: 0: 1675.2, 1: 1668.0. Samples: 47691754. Policy #0 lag: (min: 31.0, avg: 45.2, max: 63.0) -[2023-10-09 03:53:48,976][87372] Avg episode reward: [(0, '6.580'), (1, '7.640')] -[2023-10-09 03:53:51,516][88326] Updated weights for policy 0, policy_version 93092 (0.0008) -[2023-10-09 03:53:51,855][88327] Updated weights for policy 1, policy_version 93190 (0.0008) -[2023-10-09 03:53:51,874][88326] Updated weights for policy 0, policy_version 93102 (0.0007) -[2023-10-09 03:53:52,216][88327] Updated weights for policy 1, policy_version 93200 (0.0007) -[2023-10-09 03:53:52,237][88326] Updated weights for policy 0, policy_version 93112 (0.0008) -[2023-10-09 03:53:52,576][88327] Updated weights for policy 1, policy_version 93210 (0.0007) -[2023-10-09 03:53:53,974][87372] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 190808064. Throughput: 0: 1688.0, 1: 1683.9. Samples: 47703242. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:53:53,975][87372] Avg episode reward: [(0, '7.360'), (1, '8.360')] -[2023-10-09 03:53:56,281][88326] Updated weights for policy 0, policy_version 93122 (0.0008) -[2023-10-09 03:53:56,631][88327] Updated weights for policy 1, policy_version 93220 (0.0007) -[2023-10-09 03:53:56,657][88326] Updated weights for policy 0, policy_version 93132 (0.0008) -[2023-10-09 03:53:56,992][88327] Updated weights for policy 1, policy_version 93230 (0.0007) -[2023-10-09 03:53:57,026][88326] Updated weights for policy 0, policy_version 93142 (0.0007) -[2023-10-09 03:53:57,351][88327] Updated weights for policy 1, policy_version 93240 (0.0007) -[2023-10-09 03:53:57,397][88326] Updated weights for policy 0, policy_version 93152 (0.0007) -[2023-10-09 03:53:58,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 190873600. Throughput: 0: 1664.9, 1: 1668.8. Samples: 47722358. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:53:58,975][87372] Avg episode reward: [(0, '7.350'), (1, '8.000')] -[2023-10-09 03:54:01,381][88327] Updated weights for policy 1, policy_version 93250 (0.0010) -[2023-10-09 03:54:01,405][88326] Updated weights for policy 0, policy_version 93162 (0.0008) -[2023-10-09 03:54:01,743][88327] Updated weights for policy 1, policy_version 93260 (0.0008) -[2023-10-09 03:54:01,770][88326] Updated weights for policy 0, policy_version 93172 (0.0008) -[2023-10-09 03:54:02,109][88327] Updated weights for policy 1, policy_version 93270 (0.0007) -[2023-10-09 03:54:02,140][88326] Updated weights for policy 0, policy_version 93182 (0.0008) -[2023-10-09 03:54:02,471][88327] Updated weights for policy 1, policy_version 93280 (0.0009) -[2023-10-09 03:54:03,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 190939136. Throughput: 0: 1686.6, 1: 1669.4. Samples: 47742440. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:54:03,975][87372] Avg episode reward: [(0, '7.340'), (1, '7.470')] -[2023-10-09 03:54:06,133][88326] Updated weights for policy 0, policy_version 93192 (0.0008) -[2023-10-09 03:54:06,379][88327] Updated weights for policy 1, policy_version 93290 (0.0007) -[2023-10-09 03:54:06,502][88326] Updated weights for policy 0, policy_version 93202 (0.0009) -[2023-10-09 03:54:06,743][88327] Updated weights for policy 1, policy_version 93300 (0.0007) -[2023-10-09 03:54:06,876][88326] Updated weights for policy 0, policy_version 93212 (0.0008) -[2023-10-09 03:54:07,114][88327] Updated weights for policy 1, policy_version 93310 (0.0008) -[2023-10-09 03:54:08,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 191004672. Throughput: 0: 1679.6, 1: 1688.9. Samples: 47753920. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:54:08,975][87372] Avg episode reward: [(0, '7.490'), (1, '7.410')] -[2023-10-09 03:54:10,906][88326] Updated weights for policy 0, policy_version 93222 (0.0007) -[2023-10-09 03:54:11,065][88327] Updated weights for policy 1, policy_version 93320 (0.0009) -[2023-10-09 03:54:11,275][88326] Updated weights for policy 0, policy_version 93232 (0.0007) -[2023-10-09 03:54:11,422][88327] Updated weights for policy 1, policy_version 93330 (0.0009) -[2023-10-09 03:54:11,638][88326] Updated weights for policy 0, policy_version 93242 (0.0009) -[2023-10-09 03:54:11,790][88327] Updated weights for policy 1, policy_version 93340 (0.0009) -[2023-10-09 03:54:13,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 191070208. Throughput: 0: 1669.1, 1: 1665.6. Samples: 47772740. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:54:13,975][87372] Avg episode reward: [(0, '7.970'), (1, '8.160')] -[2023-10-09 03:54:15,788][88326] Updated weights for policy 0, policy_version 93252 (0.0009) -[2023-10-09 03:54:15,912][88327] Updated weights for policy 1, policy_version 93350 (0.0007) -[2023-10-09 03:54:16,174][88326] Updated weights for policy 0, policy_version 93262 (0.0008) -[2023-10-09 03:54:16,271][88327] Updated weights for policy 1, policy_version 93360 (0.0007) -[2023-10-09 03:54:16,545][88326] Updated weights for policy 0, policy_version 93272 (0.0008) -[2023-10-09 03:54:16,641][88327] Updated weights for policy 1, policy_version 93370 (0.0007) -[2023-10-09 03:54:18,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 191135744. Throughput: 0: 1690.8, 1: 1686.5. Samples: 47793358. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:54:18,975][87372] Avg episode reward: [(0, '6.930'), (1, '7.800')] -[2023-10-09 03:54:20,480][88326] Updated weights for policy 0, policy_version 93282 (0.0007) -[2023-10-09 03:54:20,662][88327] Updated weights for policy 1, policy_version 93380 (0.0008) -[2023-10-09 03:54:20,841][88326] Updated weights for policy 0, policy_version 93292 (0.0009) -[2023-10-09 03:54:21,022][88327] Updated weights for policy 1, policy_version 93390 (0.0009) -[2023-10-09 03:54:21,211][88326] Updated weights for policy 0, policy_version 93302 (0.0008) -[2023-10-09 03:54:21,387][88327] Updated weights for policy 1, policy_version 93400 (0.0008) -[2023-10-09 03:54:21,577][88326] Updated weights for policy 0, policy_version 93312 (0.0007) -[2023-10-09 03:54:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 191201280. Throughput: 0: 1675.4, 1: 1672.0. Samples: 47803422. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:54:23,975][87372] Avg episode reward: [(0, '7.200'), (1, '7.990')] -[2023-10-09 03:54:25,507][88327] Updated weights for policy 1, policy_version 93410 (0.0008) -[2023-10-09 03:54:25,675][88326] Updated weights for policy 0, policy_version 93322 (0.0008) -[2023-10-09 03:54:25,876][88327] Updated weights for policy 1, policy_version 93420 (0.0008) -[2023-10-09 03:54:26,054][88326] Updated weights for policy 0, policy_version 93332 (0.0008) -[2023-10-09 03:54:26,236][88327] Updated weights for policy 1, policy_version 93430 (0.0009) -[2023-10-09 03:54:26,431][88326] Updated weights for policy 0, policy_version 93342 (0.0008) -[2023-10-09 03:54:26,612][88327] Updated weights for policy 1, policy_version 93440 (0.0008) -[2023-10-09 03:54:28,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 191266816. Throughput: 0: 1677.0, 1: 1676.3. Samples: 47823332. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:54:28,975][87372] Avg episode reward: [(0, '7.460'), (1, '8.360')] -[2023-10-09 03:54:30,528][88327] Updated weights for policy 1, policy_version 93450 (0.0009) -[2023-10-09 03:54:30,535][88326] Updated weights for policy 0, policy_version 93352 (0.0007) -[2023-10-09 03:54:30,895][88327] Updated weights for policy 1, policy_version 93460 (0.0008) -[2023-10-09 03:54:30,907][88326] Updated weights for policy 0, policy_version 93362 (0.0007) -[2023-10-09 03:54:31,270][88327] Updated weights for policy 1, policy_version 93470 (0.0009) -[2023-10-09 03:54:31,274][88326] Updated weights for policy 0, policy_version 93372 (0.0007) -[2023-10-09 03:54:33,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 191332352. Throughput: 0: 1687.1, 1: 1701.6. Samples: 47844246. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:54:33,975][87372] Avg episode reward: [(0, '7.460'), (1, '7.230')] -[2023-10-09 03:54:33,987][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000093376_95617024.pth... -[2023-10-09 03:54:33,987][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000093472_95715328.pth... -[2023-10-09 03:54:34,024][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000091904_94109696.pth -[2023-10-09 03:54:34,025][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000091808_94011392.pth -[2023-10-09 03:54:35,232][88326] Updated weights for policy 0, policy_version 93382 (0.0009) -[2023-10-09 03:54:35,461][88327] Updated weights for policy 1, policy_version 93480 (0.0008) -[2023-10-09 03:54:35,596][88326] Updated weights for policy 0, policy_version 93392 (0.0008) -[2023-10-09 03:54:35,823][88327] Updated weights for policy 1, policy_version 93490 (0.0008) -[2023-10-09 03:54:35,968][88326] Updated weights for policy 0, policy_version 93402 (0.0008) -[2023-10-09 03:54:36,186][88327] Updated weights for policy 1, policy_version 93500 (0.0008) -[2023-10-09 03:54:38,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 191397888. Throughput: 0: 1661.8, 1: 1680.8. Samples: 47853656. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:54:38,975][87372] Avg episode reward: [(0, '7.090'), (1, '7.640')] -[2023-10-09 03:54:39,939][88326] Updated weights for policy 0, policy_version 93412 (0.0008) -[2023-10-09 03:54:40,259][88327] Updated weights for policy 1, policy_version 93510 (0.0007) -[2023-10-09 03:54:40,318][88326] Updated weights for policy 0, policy_version 93422 (0.0007) -[2023-10-09 03:54:40,626][88327] Updated weights for policy 1, policy_version 93520 (0.0008) -[2023-10-09 03:54:40,682][88326] Updated weights for policy 0, policy_version 93432 (0.0007) -[2023-10-09 03:54:40,993][88327] Updated weights for policy 1, policy_version 93530 (0.0009) -[2023-10-09 03:54:43,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 191463424. Throughput: 0: 1688.1, 1: 1687.8. Samples: 47874274. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:54:43,975][87372] Avg episode reward: [(0, '7.530'), (1, '6.960')] -[2023-10-09 03:54:44,620][88326] Updated weights for policy 0, policy_version 93442 (0.0008) -[2023-10-09 03:54:44,985][88326] Updated weights for policy 0, policy_version 93452 (0.0010) -[2023-10-09 03:54:45,055][88327] Updated weights for policy 1, policy_version 93540 (0.0010) -[2023-10-09 03:54:45,365][88326] Updated weights for policy 0, policy_version 93462 (0.0008) -[2023-10-09 03:54:45,422][88327] Updated weights for policy 1, policy_version 93550 (0.0009) -[2023-10-09 03:54:45,727][88326] Updated weights for policy 0, policy_version 93472 (0.0008) -[2023-10-09 03:54:45,778][88327] Updated weights for policy 1, policy_version 93560 (0.0010) -[2023-10-09 03:54:48,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 191528960. Throughput: 0: 1697.3, 1: 1696.4. Samples: 47895160. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:54:48,975][87372] Avg episode reward: [(0, '6.780'), (1, '7.410')] -[2023-10-09 03:54:49,797][88326] Updated weights for policy 0, policy_version 93482 (0.0008) -[2023-10-09 03:54:49,888][88327] Updated weights for policy 1, policy_version 93570 (0.0007) -[2023-10-09 03:54:50,164][88326] Updated weights for policy 0, policy_version 93492 (0.0008) -[2023-10-09 03:54:50,251][88327] Updated weights for policy 1, policy_version 93580 (0.0009) -[2023-10-09 03:54:50,540][88326] Updated weights for policy 0, policy_version 93502 (0.0007) -[2023-10-09 03:54:50,620][88327] Updated weights for policy 1, policy_version 93590 (0.0008) -[2023-10-09 03:54:50,977][88327] Updated weights for policy 1, policy_version 93600 (0.0010) -[2023-10-09 03:54:53,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 191594496. Throughput: 0: 1676.4, 1: 1664.3. Samples: 47904250. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:54:53,975][87372] Avg episode reward: [(0, '7.040'), (1, '7.500')] -[2023-10-09 03:54:54,646][88326] Updated weights for policy 0, policy_version 93512 (0.0009) -[2023-10-09 03:54:54,931][88327] Updated weights for policy 1, policy_version 93610 (0.0007) -[2023-10-09 03:54:55,005][88326] Updated weights for policy 0, policy_version 93522 (0.0010) -[2023-10-09 03:54:55,290][88327] Updated weights for policy 1, policy_version 93620 (0.0009) -[2023-10-09 03:54:55,370][88326] Updated weights for policy 0, policy_version 93532 (0.0008) -[2023-10-09 03:54:55,655][88327] Updated weights for policy 1, policy_version 93630 (0.0009) -[2023-10-09 03:54:58,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 191660032. Throughput: 0: 1697.3, 1: 1688.9. Samples: 47925114. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:54:58,974][87372] Avg episode reward: [(0, '7.630'), (1, '7.350')] -[2023-10-09 03:54:59,342][88326] Updated weights for policy 0, policy_version 93542 (0.0009) -[2023-10-09 03:54:59,711][88326] Updated weights for policy 0, policy_version 93552 (0.0009) -[2023-10-09 03:54:59,725][88327] Updated weights for policy 1, policy_version 93640 (0.0009) -[2023-10-09 03:55:00,081][88326] Updated weights for policy 0, policy_version 93562 (0.0008) -[2023-10-09 03:55:00,088][88327] Updated weights for policy 1, policy_version 93650 (0.0007) -[2023-10-09 03:55:00,457][88327] Updated weights for policy 1, policy_version 93660 (0.0008) -[2023-10-09 03:55:03,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 191725568. Throughput: 0: 1704.7, 1: 1697.6. Samples: 47946462. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:55:03,974][87372] Avg episode reward: [(0, '7.370'), (1, '7.380')] -[2023-10-09 03:55:04,237][88326] Updated weights for policy 0, policy_version 93572 (0.0007) -[2023-10-09 03:55:04,341][88327] Updated weights for policy 1, policy_version 93670 (0.0009) -[2023-10-09 03:55:04,620][88326] Updated weights for policy 0, policy_version 93582 (0.0007) -[2023-10-09 03:55:04,701][88327] Updated weights for policy 1, policy_version 93680 (0.0009) -[2023-10-09 03:55:05,001][88326] Updated weights for policy 0, policy_version 93592 (0.0007) -[2023-10-09 03:55:05,057][88327] Updated weights for policy 1, policy_version 93690 (0.0007) -[2023-10-09 03:55:08,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 191791104. Throughput: 0: 1694.4, 1: 1683.7. Samples: 47955436. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:55:08,974][87372] Avg episode reward: [(0, '7.350'), (1, '7.410')] -[2023-10-09 03:55:09,008][88326] Updated weights for policy 0, policy_version 93602 (0.0007) -[2023-10-09 03:55:09,064][88327] Updated weights for policy 1, policy_version 93700 (0.0008) -[2023-10-09 03:55:09,375][88326] Updated weights for policy 0, policy_version 93612 (0.0007) -[2023-10-09 03:55:09,423][88327] Updated weights for policy 1, policy_version 93710 (0.0009) -[2023-10-09 03:55:09,736][88326] Updated weights for policy 0, policy_version 93622 (0.0007) -[2023-10-09 03:55:09,780][88327] Updated weights for policy 1, policy_version 93720 (0.0008) -[2023-10-09 03:55:10,103][88326] Updated weights for policy 0, policy_version 93632 (0.0007) -[2023-10-09 03:55:13,948][88327] Updated weights for policy 1, policy_version 93730 (0.0008) -[2023-10-09 03:55:13,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 191856640. Throughput: 0: 1702.0, 1: 1696.1. Samples: 47976246. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:55:13,975][87372] Avg episode reward: [(0, '7.480'), (1, '7.430')] -[2023-10-09 03:55:14,121][88326] Updated weights for policy 0, policy_version 93642 (0.0007) -[2023-10-09 03:55:14,298][88327] Updated weights for policy 1, policy_version 93740 (0.0010) -[2023-10-09 03:55:14,495][88326] Updated weights for policy 0, policy_version 93652 (0.0008) -[2023-10-09 03:55:14,669][88327] Updated weights for policy 1, policy_version 93750 (0.0008) -[2023-10-09 03:55:14,858][88326] Updated weights for policy 0, policy_version 93662 (0.0008) -[2023-10-09 03:55:15,032][88327] Updated weights for policy 1, policy_version 93760 (0.0009) -[2023-10-09 03:55:18,847][88326] Updated weights for policy 0, policy_version 93672 (0.0009) -[2023-10-09 03:55:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 191922176. Throughput: 0: 1702.3, 1: 1691.0. Samples: 47996946. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:55:18,974][87372] Avg episode reward: [(0, '7.330'), (1, '7.540')] -[2023-10-09 03:55:19,179][88327] Updated weights for policy 1, policy_version 93770 (0.0009) -[2023-10-09 03:55:19,216][88326] Updated weights for policy 0, policy_version 93682 (0.0008) -[2023-10-09 03:55:19,543][88327] Updated weights for policy 1, policy_version 93780 (0.0009) -[2023-10-09 03:55:19,577][88326] Updated weights for policy 0, policy_version 93692 (0.0009) -[2023-10-09 03:55:19,903][88327] Updated weights for policy 1, policy_version 93790 (0.0008) -[2023-10-09 03:55:23,691][88326] Updated weights for policy 0, policy_version 93702 (0.0008) -[2023-10-09 03:55:23,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 191987712. Throughput: 0: 1698.7, 1: 1680.8. Samples: 48005734. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:55:23,974][87372] Avg episode reward: [(0, '7.210'), (1, '7.630')] -[2023-10-09 03:55:24,018][88327] Updated weights for policy 1, policy_version 93800 (0.0008) -[2023-10-09 03:55:24,056][88326] Updated weights for policy 0, policy_version 93712 (0.0009) -[2023-10-09 03:55:24,385][88327] Updated weights for policy 1, policy_version 93810 (0.0008) -[2023-10-09 03:55:24,429][88326] Updated weights for policy 0, policy_version 93722 (0.0008) -[2023-10-09 03:55:24,751][88327] Updated weights for policy 1, policy_version 93820 (0.0010) -[2023-10-09 03:55:28,499][88326] Updated weights for policy 0, policy_version 93732 (0.0009) -[2023-10-09 03:55:28,744][88327] Updated weights for policy 1, policy_version 93830 (0.0008) -[2023-10-09 03:55:28,862][88326] Updated weights for policy 0, policy_version 93742 (0.0007) -[2023-10-09 03:55:28,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 192053248. Throughput: 0: 1693.5, 1: 1691.1. Samples: 48026580. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:55:28,974][87372] Avg episode reward: [(0, '7.070'), (1, '6.920')] -[2023-10-09 03:55:29,115][88327] Updated weights for policy 1, policy_version 93840 (0.0010) -[2023-10-09 03:55:29,232][88326] Updated weights for policy 0, policy_version 93752 (0.0007) -[2023-10-09 03:55:29,477][88327] Updated weights for policy 1, policy_version 93850 (0.0008) -[2023-10-09 03:55:33,294][88326] Updated weights for policy 0, policy_version 93762 (0.0007) -[2023-10-09 03:55:33,479][88327] Updated weights for policy 1, policy_version 93860 (0.0008) -[2023-10-09 03:55:33,666][88326] Updated weights for policy 0, policy_version 93772 (0.0009) -[2023-10-09 03:55:33,840][88327] Updated weights for policy 1, policy_version 93870 (0.0009) -[2023-10-09 03:55:33,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 192118784. Throughput: 0: 1692.4, 1: 1696.4. Samples: 48047656. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:55:33,975][87372] Avg episode reward: [(0, '6.880'), (1, '7.360')] -[2023-10-09 03:55:34,030][88326] Updated weights for policy 0, policy_version 93782 (0.0009) -[2023-10-09 03:55:34,195][88327] Updated weights for policy 1, policy_version 93880 (0.0007) -[2023-10-09 03:55:34,399][88326] Updated weights for policy 0, policy_version 93792 (0.0008) -[2023-10-09 03:55:38,325][88326] Updated weights for policy 0, policy_version 93802 (0.0009) -[2023-10-09 03:55:38,397][88327] Updated weights for policy 1, policy_version 93890 (0.0009) -[2023-10-09 03:55:38,688][88326] Updated weights for policy 0, policy_version 93812 (0.0009) -[2023-10-09 03:55:38,751][88327] Updated weights for policy 1, policy_version 93900 (0.0007) -[2023-10-09 03:55:38,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 192184320. Throughput: 0: 1696.9, 1: 1695.0. Samples: 48056884. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:55:38,975][87372] Avg episode reward: [(0, '6.470'), (1, '7.830')] -[2023-10-09 03:55:39,060][88326] Updated weights for policy 0, policy_version 93822 (0.0010) -[2023-10-09 03:55:39,120][88327] Updated weights for policy 1, policy_version 93910 (0.0008) -[2023-10-09 03:55:39,478][88327] Updated weights for policy 1, policy_version 93920 (0.0009) -[2023-10-09 03:55:43,011][88326] Updated weights for policy 0, policy_version 93832 (0.0009) -[2023-10-09 03:55:43,396][88326] Updated weights for policy 0, policy_version 93842 (0.0008) -[2023-10-09 03:55:43,605][88327] Updated weights for policy 1, policy_version 93930 (0.0008) -[2023-10-09 03:55:43,754][88326] Updated weights for policy 0, policy_version 93852 (0.0008) -[2023-10-09 03:55:43,968][88327] Updated weights for policy 1, policy_version 93940 (0.0009) -[2023-10-09 03:55:43,974][87372] Fps is (10 sec: 16384.2, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 192282624. Throughput: 0: 1699.5, 1: 1693.0. Samples: 48077778. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:55:43,975][87372] Avg episode reward: [(0, '6.910'), (1, '7.280')] -[2023-10-09 03:55:44,333][88327] Updated weights for policy 1, policy_version 93950 (0.0009) -[2023-10-09 03:55:47,872][88326] Updated weights for policy 0, policy_version 93862 (0.0009) -[2023-10-09 03:55:48,243][88326] Updated weights for policy 0, policy_version 93872 (0.0008) -[2023-10-09 03:55:48,335][88327] Updated weights for policy 1, policy_version 93960 (0.0008) -[2023-10-09 03:55:48,603][88326] Updated weights for policy 0, policy_version 93882 (0.0008) -[2023-10-09 03:55:48,703][88327] Updated weights for policy 1, policy_version 93970 (0.0008) -[2023-10-09 03:55:48,974][87372] Fps is (10 sec: 16383.6, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 192348160. Throughput: 0: 1683.8, 1: 1686.5. Samples: 48098124. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:55:48,976][87372] Avg episode reward: [(0, '7.510'), (1, '7.320')] -[2023-10-09 03:55:49,062][88327] Updated weights for policy 1, policy_version 93980 (0.0009) -[2023-10-09 03:55:52,584][88326] Updated weights for policy 0, policy_version 93892 (0.0008) -[2023-10-09 03:55:52,966][88326] Updated weights for policy 0, policy_version 93902 (0.0007) -[2023-10-09 03:55:53,159][88327] Updated weights for policy 1, policy_version 93990 (0.0008) -[2023-10-09 03:55:53,331][88326] Updated weights for policy 0, policy_version 93912 (0.0009) -[2023-10-09 03:55:53,524][88327] Updated weights for policy 1, policy_version 94000 (0.0008) -[2023-10-09 03:55:53,881][88327] Updated weights for policy 1, policy_version 94010 (0.0009) -[2023-10-09 03:55:53,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 192413696. Throughput: 0: 1701.6, 1: 1690.3. Samples: 48108072. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:55:53,975][87372] Avg episode reward: [(0, '7.220'), (1, '7.030')] -[2023-10-09 03:55:57,272][88326] Updated weights for policy 0, policy_version 93922 (0.0007) -[2023-10-09 03:55:57,651][88326] Updated weights for policy 0, policy_version 93932 (0.0008) -[2023-10-09 03:55:57,952][88327] Updated weights for policy 1, policy_version 94020 (0.0010) -[2023-10-09 03:55:58,017][88326] Updated weights for policy 0, policy_version 93942 (0.0008) -[2023-10-09 03:55:58,323][88327] Updated weights for policy 1, policy_version 94030 (0.0009) -[2023-10-09 03:55:58,385][88326] Updated weights for policy 0, policy_version 93952 (0.0008) -[2023-10-09 03:55:58,684][88327] Updated weights for policy 1, policy_version 94040 (0.0009) -[2023-10-09 03:55:58,974][87372] Fps is (10 sec: 16384.4, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 192512000. Throughput: 0: 1703.1, 1: 1691.7. Samples: 48129012. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:55:58,975][87372] Avg episode reward: [(0, '6.990'), (1, '7.170')] -[2023-10-09 03:56:02,333][88326] Updated weights for policy 0, policy_version 93962 (0.0007) -[2023-10-09 03:56:02,706][88326] Updated weights for policy 0, policy_version 93972 (0.0007) -[2023-10-09 03:56:02,878][88327] Updated weights for policy 1, policy_version 94050 (0.0009) -[2023-10-09 03:56:03,080][88326] Updated weights for policy 0, policy_version 93982 (0.0007) -[2023-10-09 03:56:03,245][88327] Updated weights for policy 1, policy_version 94060 (0.0009) -[2023-10-09 03:56:03,609][88327] Updated weights for policy 1, policy_version 94070 (0.0007) -[2023-10-09 03:56:03,967][88327] Updated weights for policy 1, policy_version 94080 (0.0008) -[2023-10-09 03:56:03,974][87372] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 192577536. Throughput: 0: 1678.5, 1: 1683.2. Samples: 48148222. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:56:03,975][87372] Avg episode reward: [(0, '7.100'), (1, '7.330')] -[2023-10-09 03:56:07,102][88326] Updated weights for policy 0, policy_version 93992 (0.0009) -[2023-10-09 03:56:07,464][88326] Updated weights for policy 0, policy_version 94002 (0.0010) -[2023-10-09 03:56:07,829][88326] Updated weights for policy 0, policy_version 94012 (0.0008) -[2023-10-09 03:56:07,946][88327] Updated weights for policy 1, policy_version 94090 (0.0008) -[2023-10-09 03:56:08,318][88327] Updated weights for policy 1, policy_version 94100 (0.0009) -[2023-10-09 03:56:08,687][88327] Updated weights for policy 1, policy_version 94110 (0.0009) -[2023-10-09 03:56:08,974][87372] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 192643072. Throughput: 0: 1707.1, 1: 1698.0. Samples: 48158964. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:56:08,975][87372] Avg episode reward: [(0, '7.090'), (1, '7.520')] -[2023-10-09 03:56:12,074][88326] Updated weights for policy 0, policy_version 94022 (0.0009) -[2023-10-09 03:56:12,444][88326] Updated weights for policy 0, policy_version 94032 (0.0008) -[2023-10-09 03:56:12,805][88327] Updated weights for policy 1, policy_version 94120 (0.0007) -[2023-10-09 03:56:12,809][88326] Updated weights for policy 0, policy_version 94042 (0.0008) -[2023-10-09 03:56:13,165][88327] Updated weights for policy 1, policy_version 94130 (0.0008) -[2023-10-09 03:56:13,536][88327] Updated weights for policy 1, policy_version 94140 (0.0008) -[2023-10-09 03:56:13,974][87372] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 192708608. Throughput: 0: 1700.4, 1: 1693.5. Samples: 48179304. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:56:13,975][87372] Avg episode reward: [(0, '7.160'), (1, '7.680')] -[2023-10-09 03:56:16,814][88326] Updated weights for policy 0, policy_version 94052 (0.0007) -[2023-10-09 03:56:17,180][88326] Updated weights for policy 0, policy_version 94062 (0.0007) -[2023-10-09 03:56:17,423][88327] Updated weights for policy 1, policy_version 94150 (0.0007) -[2023-10-09 03:56:17,561][88326] Updated weights for policy 0, policy_version 94072 (0.0008) -[2023-10-09 03:56:17,781][88327] Updated weights for policy 1, policy_version 94160 (0.0007) -[2023-10-09 03:56:18,144][88327] Updated weights for policy 1, policy_version 94170 (0.0011) -[2023-10-09 03:56:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 192774144. Throughput: 0: 1676.9, 1: 1667.5. Samples: 48198154. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:56:18,975][87372] Avg episode reward: [(0, '7.860'), (1, '7.280')] -[2023-10-09 03:56:21,757][88326] Updated weights for policy 0, policy_version 94082 (0.0007) -[2023-10-09 03:56:22,046][88327] Updated weights for policy 1, policy_version 94180 (0.0010) -[2023-10-09 03:56:22,123][88326] Updated weights for policy 0, policy_version 94092 (0.0009) -[2023-10-09 03:56:22,415][88327] Updated weights for policy 1, policy_version 94190 (0.0010) -[2023-10-09 03:56:22,495][88326] Updated weights for policy 0, policy_version 94102 (0.0009) -[2023-10-09 03:56:22,776][88327] Updated weights for policy 1, policy_version 94200 (0.0008) -[2023-10-09 03:56:22,857][88326] Updated weights for policy 0, policy_version 94112 (0.0007) -[2023-10-09 03:56:23,974][87372] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 192839680. Throughput: 0: 1700.4, 1: 1692.0. Samples: 48209546. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:56:23,975][87372] Avg episode reward: [(0, '8.030'), (1, '8.160')] -[2023-10-09 03:56:26,777][88327] Updated weights for policy 1, policy_version 94210 (0.0007) -[2023-10-09 03:56:26,863][88326] Updated weights for policy 0, policy_version 94122 (0.0010) -[2023-10-09 03:56:27,149][88327] Updated weights for policy 1, policy_version 94220 (0.0008) -[2023-10-09 03:56:27,240][88326] Updated weights for policy 0, policy_version 94132 (0.0008) -[2023-10-09 03:56:27,506][88327] Updated weights for policy 1, policy_version 94230 (0.0008) -[2023-10-09 03:56:27,604][88326] Updated weights for policy 0, policy_version 94142 (0.0007) -[2023-10-09 03:56:27,868][88327] Updated weights for policy 1, policy_version 94240 (0.0010) -[2023-10-09 03:56:28,974][87372] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 192905216. Throughput: 0: 1680.8, 1: 1687.4. Samples: 48229350. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:56:28,975][87372] Avg episode reward: [(0, '7.230'), (1, '7.770')] -[2023-10-09 03:56:31,616][88326] Updated weights for policy 0, policy_version 94152 (0.0008) -[2023-10-09 03:56:31,880][88327] Updated weights for policy 1, policy_version 94250 (0.0008) -[2023-10-09 03:56:31,984][88326] Updated weights for policy 0, policy_version 94162 (0.0008) -[2023-10-09 03:56:32,245][88327] Updated weights for policy 1, policy_version 94260 (0.0008) -[2023-10-09 03:56:32,356][88326] Updated weights for policy 0, policy_version 94172 (0.0007) -[2023-10-09 03:56:32,600][88327] Updated weights for policy 1, policy_version 94270 (0.0009) -[2023-10-09 03:56:33,974][87372] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 192970752. Throughput: 0: 1680.7, 1: 1670.8. Samples: 48248940. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:56:33,975][87372] Avg episode reward: [(0, '7.710'), (1, '7.260')] -[2023-10-09 03:56:33,984][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000094176_96436224.pth... -[2023-10-09 03:56:33,984][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000094272_96534528.pth... -[2023-10-09 03:56:34,023][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000092704_94928896.pth -[2023-10-09 03:56:34,024][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000092608_94830592.pth -[2023-10-09 03:56:36,359][88326] Updated weights for policy 0, policy_version 94182 (0.0007) -[2023-10-09 03:56:36,725][88326] Updated weights for policy 0, policy_version 94192 (0.0007) -[2023-10-09 03:56:36,806][88327] Updated weights for policy 1, policy_version 94280 (0.0009) -[2023-10-09 03:56:37,095][88326] Updated weights for policy 0, policy_version 94202 (0.0007) -[2023-10-09 03:56:37,169][88327] Updated weights for policy 1, policy_version 94290 (0.0008) -[2023-10-09 03:56:37,523][88327] Updated weights for policy 1, policy_version 94300 (0.0008) -[2023-10-09 03:56:38,974][87372] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 193036288. Throughput: 0: 1692.8, 1: 1698.2. Samples: 48260670. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:56:38,974][87372] Avg episode reward: [(0, '7.510'), (1, '7.950')] -[2023-10-09 03:56:41,097][88326] Updated weights for policy 0, policy_version 94212 (0.0008) -[2023-10-09 03:56:41,469][88326] Updated weights for policy 0, policy_version 94222 (0.0007) -[2023-10-09 03:56:41,587][88327] Updated weights for policy 1, policy_version 94310 (0.0009) -[2023-10-09 03:56:41,827][88326] Updated weights for policy 0, policy_version 94232 (0.0008) -[2023-10-09 03:56:41,952][88327] Updated weights for policy 1, policy_version 94320 (0.0007) -[2023-10-09 03:56:42,323][88327] Updated weights for policy 1, policy_version 94330 (0.0008) -[2023-10-09 03:56:43,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 193101824. Throughput: 0: 1663.0, 1: 1679.6. Samples: 48279426. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 03:56:43,975][87372] Avg episode reward: [(0, '7.400'), (1, '7.140')] -[2023-10-09 03:56:46,036][88326] Updated weights for policy 0, policy_version 94242 (0.0007) -[2023-10-09 03:56:46,242][88327] Updated weights for policy 1, policy_version 94340 (0.0008) -[2023-10-09 03:56:46,437][88326] Updated weights for policy 0, policy_version 94252 (0.0009) -[2023-10-09 03:56:46,604][88327] Updated weights for policy 1, policy_version 94350 (0.0008) -[2023-10-09 03:56:46,793][88326] Updated weights for policy 0, policy_version 94262 (0.0008) -[2023-10-09 03:56:46,970][88327] Updated weights for policy 1, policy_version 94360 (0.0007) -[2023-10-09 03:56:47,164][88326] Updated weights for policy 0, policy_version 94272 (0.0008) -[2023-10-09 03:56:48,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 193167360. Throughput: 0: 1683.6, 1: 1681.9. Samples: 48299674. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) -[2023-10-09 03:56:48,975][87372] Avg episode reward: [(0, '6.850'), (1, '7.520')] -[2023-10-09 03:56:51,163][88326] Updated weights for policy 0, policy_version 94282 (0.0008) -[2023-10-09 03:56:51,183][88327] Updated weights for policy 1, policy_version 94370 (0.0009) -[2023-10-09 03:56:51,528][88326] Updated weights for policy 0, policy_version 94292 (0.0007) -[2023-10-09 03:56:51,549][88327] Updated weights for policy 1, policy_version 94380 (0.0007) -[2023-10-09 03:56:51,904][88326] Updated weights for policy 0, policy_version 94302 (0.0007) -[2023-10-09 03:56:51,908][88327] Updated weights for policy 1, policy_version 94390 (0.0008) -[2023-10-09 03:56:52,284][88327] Updated weights for policy 1, policy_version 94400 (0.0008) -[2023-10-09 03:56:53,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 193232896. Throughput: 0: 1671.6, 1: 1702.2. Samples: 48310782. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) -[2023-10-09 03:56:53,975][87372] Avg episode reward: [(0, '6.830'), (1, '7.640')] -[2023-10-09 03:56:55,801][88326] Updated weights for policy 0, policy_version 94312 (0.0007) -[2023-10-09 03:56:56,169][88326] Updated weights for policy 0, policy_version 94322 (0.0009) -[2023-10-09 03:56:56,228][88327] Updated weights for policy 1, policy_version 94410 (0.0008) -[2023-10-09 03:56:56,542][88326] Updated weights for policy 0, policy_version 94332 (0.0007) -[2023-10-09 03:56:56,589][88327] Updated weights for policy 1, policy_version 94420 (0.0008) -[2023-10-09 03:56:56,956][88327] Updated weights for policy 1, policy_version 94430 (0.0007) -[2023-10-09 03:56:58,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 193298432. Throughput: 0: 1666.5, 1: 1676.2. Samples: 48329726. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) -[2023-10-09 03:56:58,975][87372] Avg episode reward: [(0, '7.210'), (1, '8.120')] -[2023-10-09 03:57:00,523][88326] Updated weights for policy 0, policy_version 94342 (0.0008) -[2023-10-09 03:57:00,884][88326] Updated weights for policy 0, policy_version 94352 (0.0009) -[2023-10-09 03:57:00,924][88327] Updated weights for policy 1, policy_version 94440 (0.0009) -[2023-10-09 03:57:01,252][88326] Updated weights for policy 0, policy_version 94362 (0.0009) -[2023-10-09 03:57:01,288][88327] Updated weights for policy 1, policy_version 94450 (0.0008) -[2023-10-09 03:57:01,643][88327] Updated weights for policy 1, policy_version 94460 (0.0010) -[2023-10-09 03:57:03,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 193363968. Throughput: 0: 1689.2, 1: 1703.8. Samples: 48350840. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) -[2023-10-09 03:57:03,975][87372] Avg episode reward: [(0, '7.330'), (1, '7.840')] -[2023-10-09 03:57:05,192][88326] Updated weights for policy 0, policy_version 94372 (0.0009) -[2023-10-09 03:57:05,557][88327] Updated weights for policy 1, policy_version 94470 (0.0008) -[2023-10-09 03:57:05,567][88326] Updated weights for policy 0, policy_version 94382 (0.0009) -[2023-10-09 03:57:05,922][88326] Updated weights for policy 0, policy_version 94392 (0.0008) -[2023-10-09 03:57:05,928][88327] Updated weights for policy 1, policy_version 94480 (0.0007) -[2023-10-09 03:57:06,286][88327] Updated weights for policy 1, policy_version 94490 (0.0007) -[2023-10-09 03:57:08,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 193429504. Throughput: 0: 1666.2, 1: 1690.5. Samples: 48360596. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) -[2023-10-09 03:57:08,975][87372] Avg episode reward: [(0, '7.370'), (1, '7.760')] -[2023-10-09 03:57:10,061][88326] Updated weights for policy 0, policy_version 94402 (0.0009) -[2023-10-09 03:57:10,302][88327] Updated weights for policy 1, policy_version 94500 (0.0008) -[2023-10-09 03:57:10,427][88326] Updated weights for policy 0, policy_version 94412 (0.0009) -[2023-10-09 03:57:10,666][88327] Updated weights for policy 1, policy_version 94510 (0.0009) -[2023-10-09 03:57:10,799][88326] Updated weights for policy 0, policy_version 94422 (0.0007) -[2023-10-09 03:57:11,032][88327] Updated weights for policy 1, policy_version 94520 (0.0008) -[2023-10-09 03:57:11,172][88326] Updated weights for policy 0, policy_version 94432 (0.0009) -[2023-10-09 03:57:13,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 193495040. Throughput: 0: 1680.9, 1: 1682.6. Samples: 48380706. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) -[2023-10-09 03:57:13,975][87372] Avg episode reward: [(0, '8.060'), (1, '7.740')] -[2023-10-09 03:57:15,124][88327] Updated weights for policy 1, policy_version 94530 (0.0009) -[2023-10-09 03:57:15,194][88326] Updated weights for policy 0, policy_version 94442 (0.0008) -[2023-10-09 03:57:15,484][88327] Updated weights for policy 1, policy_version 94540 (0.0008) -[2023-10-09 03:57:15,569][88326] Updated weights for policy 0, policy_version 94452 (0.0010) -[2023-10-09 03:57:15,850][88327] Updated weights for policy 1, policy_version 94550 (0.0008) -[2023-10-09 03:57:15,943][88326] Updated weights for policy 0, policy_version 94462 (0.0008) -[2023-10-09 03:57:16,206][88327] Updated weights for policy 1, policy_version 94560 (0.0009) -[2023-10-09 03:57:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 193560576. Throughput: 0: 1698.9, 1: 1697.6. Samples: 48401784. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) -[2023-10-09 03:57:18,975][87372] Avg episode reward: [(0, '6.480'), (1, '7.610')] -[2023-10-09 03:57:19,771][88326] Updated weights for policy 0, policy_version 94472 (0.0007) -[2023-10-09 03:57:20,145][88326] Updated weights for policy 0, policy_version 94482 (0.0007) -[2023-10-09 03:57:20,335][88327] Updated weights for policy 1, policy_version 94570 (0.0010) -[2023-10-09 03:57:20,517][88326] Updated weights for policy 0, policy_version 94492 (0.0009) -[2023-10-09 03:57:20,695][88327] Updated weights for policy 1, policy_version 94580 (0.0008) -[2023-10-09 03:57:21,063][88327] Updated weights for policy 1, policy_version 94590 (0.0008) -[2023-10-09 03:57:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 193626112. Throughput: 0: 1675.6, 1: 1669.8. Samples: 48411214. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) -[2023-10-09 03:57:23,975][87372] Avg episode reward: [(0, '6.450'), (1, '7.370')] -[2023-10-09 03:57:24,600][88326] Updated weights for policy 0, policy_version 94502 (0.0009) -[2023-10-09 03:57:24,969][88326] Updated weights for policy 0, policy_version 94512 (0.0009) -[2023-10-09 03:57:25,082][88327] Updated weights for policy 1, policy_version 94600 (0.0008) -[2023-10-09 03:57:25,336][88326] Updated weights for policy 0, policy_version 94522 (0.0010) -[2023-10-09 03:57:25,451][88327] Updated weights for policy 1, policy_version 94610 (0.0009) -[2023-10-09 03:57:25,810][88327] Updated weights for policy 1, policy_version 94620 (0.0009) -[2023-10-09 03:57:28,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 193691648. Throughput: 0: 1707.8, 1: 1686.5. Samples: 48432172. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) -[2023-10-09 03:57:28,975][87372] Avg episode reward: [(0, '7.030'), (1, '7.470')] -[2023-10-09 03:57:29,409][88326] Updated weights for policy 0, policy_version 94532 (0.0008) -[2023-10-09 03:57:29,784][88326] Updated weights for policy 0, policy_version 94542 (0.0007) -[2023-10-09 03:57:30,124][88327] Updated weights for policy 1, policy_version 94630 (0.0009) -[2023-10-09 03:57:30,143][88326] Updated weights for policy 0, policy_version 94552 (0.0007) -[2023-10-09 03:57:30,487][88327] Updated weights for policy 1, policy_version 94640 (0.0010) -[2023-10-09 03:57:30,859][88327] Updated weights for policy 1, policy_version 94650 (0.0009) -[2023-10-09 03:57:33,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 193757184. Throughput: 0: 1714.5, 1: 1691.5. Samples: 48452944. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) -[2023-10-09 03:57:33,975][87372] Avg episode reward: [(0, '6.370'), (1, '7.400')] -[2023-10-09 03:57:34,154][88326] Updated weights for policy 0, policy_version 94562 (0.0008) -[2023-10-09 03:57:34,539][88326] Updated weights for policy 0, policy_version 94572 (0.0010) -[2023-10-09 03:57:34,830][88327] Updated weights for policy 1, policy_version 94660 (0.0008) -[2023-10-09 03:57:34,911][88326] Updated weights for policy 0, policy_version 94582 (0.0008) -[2023-10-09 03:57:35,193][88327] Updated weights for policy 1, policy_version 94670 (0.0007) -[2023-10-09 03:57:35,277][88326] Updated weights for policy 0, policy_version 94592 (0.0007) -[2023-10-09 03:57:35,566][88327] Updated weights for policy 1, policy_version 94680 (0.0011) -[2023-10-09 03:57:38,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 193822720. Throughput: 0: 1696.8, 1: 1664.1. Samples: 48462022. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) -[2023-10-09 03:57:38,975][87372] Avg episode reward: [(0, '6.880'), (1, '6.900')] -[2023-10-09 03:57:39,467][88326] Updated weights for policy 0, policy_version 94602 (0.0010) -[2023-10-09 03:57:39,624][88327] Updated weights for policy 1, policy_version 94690 (0.0007) -[2023-10-09 03:57:39,833][88326] Updated weights for policy 0, policy_version 94612 (0.0007) -[2023-10-09 03:57:39,993][88327] Updated weights for policy 1, policy_version 94700 (0.0007) -[2023-10-09 03:57:40,194][88326] Updated weights for policy 0, policy_version 94622 (0.0007) -[2023-10-09 03:57:40,362][88327] Updated weights for policy 1, policy_version 94710 (0.0009) -[2023-10-09 03:57:40,727][88327] Updated weights for policy 1, policy_version 94720 (0.0010) -[2023-10-09 03:57:43,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.3, 300 sec: 13440.4). Total num frames: 193888256. Throughput: 0: 1709.0, 1: 1691.2. Samples: 48482734. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) -[2023-10-09 03:57:43,975][87372] Avg episode reward: [(0, '6.940'), (1, '7.850')] -[2023-10-09 03:57:44,170][88326] Updated weights for policy 0, policy_version 94632 (0.0009) -[2023-10-09 03:57:44,535][88326] Updated weights for policy 0, policy_version 94642 (0.0008) -[2023-10-09 03:57:44,834][88327] Updated weights for policy 1, policy_version 94730 (0.0008) -[2023-10-09 03:57:44,904][88326] Updated weights for policy 0, policy_version 94652 (0.0008) -[2023-10-09 03:57:45,199][88327] Updated weights for policy 1, policy_version 94740 (0.0007) -[2023-10-09 03:57:45,563][88327] Updated weights for policy 1, policy_version 94750 (0.0010) -[2023-10-09 03:57:48,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 193953792. Throughput: 0: 1706.9, 1: 1685.9. Samples: 48503512. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) -[2023-10-09 03:57:48,975][87372] Avg episode reward: [(0, '6.970'), (1, '7.710')] -[2023-10-09 03:57:49,110][88326] Updated weights for policy 0, policy_version 94662 (0.0008) -[2023-10-09 03:57:49,476][88326] Updated weights for policy 0, policy_version 94672 (0.0007) -[2023-10-09 03:57:49,592][88327] Updated weights for policy 1, policy_version 94760 (0.0008) -[2023-10-09 03:57:49,844][88326] Updated weights for policy 0, policy_version 94682 (0.0007) -[2023-10-09 03:57:49,952][88327] Updated weights for policy 1, policy_version 94770 (0.0008) -[2023-10-09 03:57:50,325][88327] Updated weights for policy 1, policy_version 94780 (0.0010) -[2023-10-09 03:57:53,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 194019328. Throughput: 0: 1701.8, 1: 1673.8. Samples: 48512496. Policy #0 lag: (min: 20.0, avg: 22.5, max: 52.0) -[2023-10-09 03:57:53,975][87372] Avg episode reward: [(0, '6.710'), (1, '7.570')] -[2023-10-09 03:57:54,065][88326] Updated weights for policy 0, policy_version 94692 (0.0007) -[2023-10-09 03:57:54,424][88326] Updated weights for policy 0, policy_version 94702 (0.0007) -[2023-10-09 03:57:54,456][88327] Updated weights for policy 1, policy_version 94790 (0.0010) -[2023-10-09 03:57:54,799][88326] Updated weights for policy 0, policy_version 94712 (0.0010) -[2023-10-09 03:57:54,815][88327] Updated weights for policy 1, policy_version 94800 (0.0008) -[2023-10-09 03:57:55,190][88327] Updated weights for policy 1, policy_version 94810 (0.0009) -[2023-10-09 03:57:58,599][88326] Updated weights for policy 0, policy_version 94722 (0.0008) -[2023-10-09 03:57:58,960][88326] Updated weights for policy 0, policy_version 94732 (0.0008) -[2023-10-09 03:57:58,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 194084864. Throughput: 0: 1701.1, 1: 1686.9. Samples: 48533164. Policy #0 lag: (min: 20.0, avg: 22.5, max: 52.0) -[2023-10-09 03:57:58,975][87372] Avg episode reward: [(0, '7.420'), (1, '7.830')] -[2023-10-09 03:57:59,097][88327] Updated weights for policy 1, policy_version 94820 (0.0007) -[2023-10-09 03:57:59,333][88326] Updated weights for policy 0, policy_version 94742 (0.0007) -[2023-10-09 03:57:59,465][88327] Updated weights for policy 1, policy_version 94830 (0.0009) -[2023-10-09 03:57:59,692][88326] Updated weights for policy 0, policy_version 94752 (0.0007) -[2023-10-09 03:57:59,819][88327] Updated weights for policy 1, policy_version 94840 (0.0009) -[2023-10-09 03:58:03,711][88326] Updated weights for policy 0, policy_version 94762 (0.0008) -[2023-10-09 03:58:03,914][88327] Updated weights for policy 1, policy_version 94850 (0.0009) -[2023-10-09 03:58:03,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 194150400. Throughput: 0: 1695.0, 1: 1687.3. Samples: 48553990. Policy #0 lag: (min: 20.0, avg: 22.5, max: 52.0) -[2023-10-09 03:58:03,974][87372] Avg episode reward: [(0, '7.630'), (1, '8.640')] -[2023-10-09 03:58:04,076][88326] Updated weights for policy 0, policy_version 94772 (0.0010) -[2023-10-09 03:58:04,273][88327] Updated weights for policy 1, policy_version 94860 (0.0008) -[2023-10-09 03:58:04,447][88326] Updated weights for policy 0, policy_version 94782 (0.0009) -[2023-10-09 03:58:04,643][88327] Updated weights for policy 1, policy_version 94870 (0.0007) -[2023-10-09 03:58:04,997][88327] Updated weights for policy 1, policy_version 94880 (0.0007) -[2023-10-09 03:58:08,552][88326] Updated weights for policy 0, policy_version 94792 (0.0007) -[2023-10-09 03:58:08,914][88326] Updated weights for policy 0, policy_version 94802 (0.0008) -[2023-10-09 03:58:08,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 194215936. Throughput: 0: 1692.0, 1: 1682.7. Samples: 48563074. Policy #0 lag: (min: 20.0, avg: 22.5, max: 52.0) -[2023-10-09 03:58:08,975][87372] Avg episode reward: [(0, '7.860'), (1, '7.870')] -[2023-10-09 03:58:09,283][88326] Updated weights for policy 0, policy_version 94812 (0.0010) -[2023-10-09 03:58:09,358][88327] Updated weights for policy 1, policy_version 94890 (0.0008) -[2023-10-09 03:58:09,731][88327] Updated weights for policy 1, policy_version 94900 (0.0007) -[2023-10-09 03:58:10,092][88327] Updated weights for policy 1, policy_version 94910 (0.0007) -[2023-10-09 03:58:13,199][88326] Updated weights for policy 0, policy_version 94822 (0.0009) -[2023-10-09 03:58:13,555][88326] Updated weights for policy 0, policy_version 94832 (0.0010) -[2023-10-09 03:58:13,921][88326] Updated weights for policy 0, policy_version 94842 (0.0008) -[2023-10-09 03:58:13,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 194281472. Throughput: 0: 1690.4, 1: 1681.2. Samples: 48583896. Policy #0 lag: (min: 20.0, avg: 22.5, max: 52.0) -[2023-10-09 03:58:13,975][87372] Avg episode reward: [(0, '7.980'), (1, '7.880')] -[2023-10-09 03:58:14,245][88327] Updated weights for policy 1, policy_version 94920 (0.0008) -[2023-10-09 03:58:14,609][88327] Updated weights for policy 1, policy_version 94930 (0.0007) -[2023-10-09 03:58:14,973][88327] Updated weights for policy 1, policy_version 94940 (0.0011) -[2023-10-09 03:58:17,961][88326] Updated weights for policy 0, policy_version 94852 (0.0008) -[2023-10-09 03:58:18,322][88326] Updated weights for policy 0, policy_version 94862 (0.0009) -[2023-10-09 03:58:18,685][88326] Updated weights for policy 0, policy_version 94872 (0.0008) -[2023-10-09 03:58:18,882][88327] Updated weights for policy 1, policy_version 94950 (0.0010) -[2023-10-09 03:58:18,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 194347008. Throughput: 0: 1681.1, 1: 1686.8. Samples: 48604500. Policy #0 lag: (min: 20.0, avg: 22.5, max: 52.0) -[2023-10-09 03:58:18,974][87372] Avg episode reward: [(0, '7.070'), (1, '7.690')] -[2023-10-09 03:58:19,249][88327] Updated weights for policy 1, policy_version 94960 (0.0008) -[2023-10-09 03:58:19,610][88327] Updated weights for policy 1, policy_version 94970 (0.0007) -[2023-10-09 03:58:22,809][88326] Updated weights for policy 0, policy_version 94882 (0.0007) -[2023-10-09 03:58:23,210][88326] Updated weights for policy 0, policy_version 94892 (0.0009) -[2023-10-09 03:58:23,578][88326] Updated weights for policy 0, policy_version 94902 (0.0010) -[2023-10-09 03:58:23,734][88327] Updated weights for policy 1, policy_version 94980 (0.0008) -[2023-10-09 03:58:23,945][88326] Updated weights for policy 0, policy_version 94912 (0.0010) -[2023-10-09 03:58:23,974][87372] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 194445312. Throughput: 0: 1695.6, 1: 1688.8. Samples: 48614316. Policy #0 lag: (min: 20.0, avg: 22.5, max: 52.0) -[2023-10-09 03:58:23,975][87372] Avg episode reward: [(0, '6.620'), (1, '7.610')] -[2023-10-09 03:58:24,098][88327] Updated weights for policy 1, policy_version 94990 (0.0010) -[2023-10-09 03:58:24,461][88327] Updated weights for policy 1, policy_version 95000 (0.0007) -[2023-10-09 03:58:27,791][88326] Updated weights for policy 0, policy_version 94922 (0.0008) -[2023-10-09 03:58:28,156][88326] Updated weights for policy 0, policy_version 94932 (0.0009) -[2023-10-09 03:58:28,469][88327] Updated weights for policy 1, policy_version 95010 (0.0008) -[2023-10-09 03:58:28,534][88326] Updated weights for policy 0, policy_version 94942 (0.0008) -[2023-10-09 03:58:28,845][88327] Updated weights for policy 1, policy_version 95020 (0.0009) -[2023-10-09 03:58:28,974][87372] Fps is (10 sec: 16383.7, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 194510848. Throughput: 0: 1699.7, 1: 1689.9. Samples: 48635266. Policy #0 lag: (min: 20.0, avg: 22.5, max: 52.0) -[2023-10-09 03:58:28,975][87372] Avg episode reward: [(0, '7.230'), (1, '7.710')] -[2023-10-09 03:58:29,202][88327] Updated weights for policy 1, policy_version 95030 (0.0010) -[2023-10-09 03:58:29,565][88327] Updated weights for policy 1, policy_version 95040 (0.0008) -[2023-10-09 03:58:32,588][88326] Updated weights for policy 0, policy_version 94952 (0.0007) -[2023-10-09 03:58:32,960][88326] Updated weights for policy 0, policy_version 94962 (0.0007) -[2023-10-09 03:58:33,328][88326] Updated weights for policy 0, policy_version 94972 (0.0008) -[2023-10-09 03:58:33,605][88327] Updated weights for policy 1, policy_version 95050 (0.0007) -[2023-10-09 03:58:33,973][88327] Updated weights for policy 1, policy_version 95060 (0.0008) -[2023-10-09 03:58:33,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 194576384. Throughput: 0: 1678.0, 1: 1695.8. Samples: 48655330. Policy #0 lag: (min: 20.0, avg: 22.5, max: 52.0) -[2023-10-09 03:58:33,975][87372] Avg episode reward: [(0, '6.650'), (1, '8.110')] -[2023-10-09 03:58:33,982][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000094976_97255424.pth... -[2023-10-09 03:58:34,016][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000093376_95617024.pth -[2023-10-09 03:58:34,020][88088] Saving a milestone ./train_atari/atari_battlezone_APPO/checkpoint_p0/milestones/checkpoint_000094976_97255424.pth -[2023-10-09 03:58:34,345][88327] Updated weights for policy 1, policy_version 95070 (0.0011) -[2023-10-09 03:58:34,419][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000095072_97353728.pth... -[2023-10-09 03:58:34,458][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000093472_95715328.pth -[2023-10-09 03:58:34,463][88168] Saving a milestone ./train_atari/atari_battlezone_APPO/checkpoint_p1/milestones/checkpoint_000095072_97353728.pth -[2023-10-09 03:58:37,330][88326] Updated weights for policy 0, policy_version 94982 (0.0009) -[2023-10-09 03:58:37,704][88326] Updated weights for policy 0, policy_version 94992 (0.0011) -[2023-10-09 03:58:38,066][88326] Updated weights for policy 0, policy_version 95002 (0.0008) -[2023-10-09 03:58:38,144][88327] Updated weights for policy 1, policy_version 95080 (0.0008) -[2023-10-09 03:58:38,499][88327] Updated weights for policy 1, policy_version 95090 (0.0008) -[2023-10-09 03:58:38,870][88327] Updated weights for policy 1, policy_version 95100 (0.0009) -[2023-10-09 03:58:38,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 194641920. Throughput: 0: 1703.7, 1: 1694.0. Samples: 48665394. Policy #0 lag: (min: 20.0, avg: 22.5, max: 52.0) -[2023-10-09 03:58:38,975][87372] Avg episode reward: [(0, '6.950'), (1, '7.780')] -[2023-10-09 03:58:42,133][88326] Updated weights for policy 0, policy_version 95012 (0.0009) -[2023-10-09 03:58:42,505][88326] Updated weights for policy 0, policy_version 95022 (0.0007) -[2023-10-09 03:58:42,885][88326] Updated weights for policy 0, policy_version 95032 (0.0008) -[2023-10-09 03:58:43,091][88327] Updated weights for policy 1, policy_version 95110 (0.0008) -[2023-10-09 03:58:43,458][88327] Updated weights for policy 1, policy_version 95120 (0.0009) -[2023-10-09 03:58:43,823][88327] Updated weights for policy 1, policy_version 95130 (0.0010) -[2023-10-09 03:58:43,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 194707456. Throughput: 0: 1702.5, 1: 1696.4. Samples: 48686112. Policy #0 lag: (min: 20.0, avg: 22.5, max: 52.0) -[2023-10-09 03:58:43,975][87372] Avg episode reward: [(0, '7.400'), (1, '7.540')] -[2023-10-09 03:58:46,997][88326] Updated weights for policy 0, policy_version 95042 (0.0008) -[2023-10-09 03:58:47,369][88326] Updated weights for policy 0, policy_version 95052 (0.0008) -[2023-10-09 03:58:47,664][88327] Updated weights for policy 1, policy_version 95140 (0.0008) -[2023-10-09 03:58:47,743][88326] Updated weights for policy 0, policy_version 95062 (0.0007) -[2023-10-09 03:58:48,024][88327] Updated weights for policy 1, policy_version 95150 (0.0010) -[2023-10-09 03:58:48,107][88326] Updated weights for policy 0, policy_version 95072 (0.0008) -[2023-10-09 03:58:48,383][88327] Updated weights for policy 1, policy_version 95160 (0.0011) -[2023-10-09 03:58:48,974][87372] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 194805760. Throughput: 0: 1678.8, 1: 1684.4. Samples: 48705334. Policy #0 lag: (min: 18.0, avg: 20.2, max: 41.0) -[2023-10-09 03:58:48,974][87372] Avg episode reward: [(0, '7.030'), (1, '7.920')] -[2023-10-09 03:58:52,188][88326] Updated weights for policy 0, policy_version 95082 (0.0010) -[2023-10-09 03:58:52,550][88326] Updated weights for policy 0, policy_version 95092 (0.0010) -[2023-10-09 03:58:52,560][88327] Updated weights for policy 1, policy_version 95170 (0.0010) -[2023-10-09 03:58:52,918][88326] Updated weights for policy 0, policy_version 95102 (0.0008) -[2023-10-09 03:58:52,921][88327] Updated weights for policy 1, policy_version 95180 (0.0008) -[2023-10-09 03:58:53,291][88327] Updated weights for policy 1, policy_version 95190 (0.0010) -[2023-10-09 03:58:53,643][88327] Updated weights for policy 1, policy_version 95200 (0.0011) -[2023-10-09 03:58:53,974][87372] Fps is (10 sec: 16384.2, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 194871296. Throughput: 0: 1708.8, 1: 1700.0. Samples: 48716470. Policy #0 lag: (min: 18.0, avg: 20.2, max: 41.0) -[2023-10-09 03:58:53,975][87372] Avg episode reward: [(0, '7.870'), (1, '8.020')] -[2023-10-09 03:58:57,008][88326] Updated weights for policy 0, policy_version 95112 (0.0007) -[2023-10-09 03:58:57,388][88326] Updated weights for policy 0, policy_version 95122 (0.0009) -[2023-10-09 03:58:57,752][88326] Updated weights for policy 0, policy_version 95132 (0.0009) -[2023-10-09 03:58:57,774][88327] Updated weights for policy 1, policy_version 95210 (0.0009) -[2023-10-09 03:58:58,147][88327] Updated weights for policy 1, policy_version 95220 (0.0008) -[2023-10-09 03:58:58,509][88327] Updated weights for policy 1, policy_version 95230 (0.0008) -[2023-10-09 03:58:58,974][87372] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 194936832. Throughput: 0: 1696.2, 1: 1707.7. Samples: 48737074. Policy #0 lag: (min: 18.0, avg: 20.2, max: 41.0) -[2023-10-09 03:58:58,975][87372] Avg episode reward: [(0, '7.390'), (1, '7.680')] -[2023-10-09 03:59:01,778][88326] Updated weights for policy 0, policy_version 95142 (0.0009) -[2023-10-09 03:59:02,154][88326] Updated weights for policy 0, policy_version 95152 (0.0010) -[2023-10-09 03:59:02,412][88327] Updated weights for policy 1, policy_version 95240 (0.0008) -[2023-10-09 03:59:02,522][88326] Updated weights for policy 0, policy_version 95162 (0.0009) -[2023-10-09 03:59:02,771][88327] Updated weights for policy 1, policy_version 95250 (0.0008) -[2023-10-09 03:59:03,137][88327] Updated weights for policy 1, policy_version 95260 (0.0008) -[2023-10-09 03:59:03,974][87372] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 195002368. Throughput: 0: 1686.1, 1: 1681.0. Samples: 48756022. Policy #0 lag: (min: 18.0, avg: 20.2, max: 41.0) -[2023-10-09 03:59:03,975][87372] Avg episode reward: [(0, '7.530'), (1, '8.210')] -[2023-10-09 03:59:06,543][88326] Updated weights for policy 0, policy_version 95172 (0.0009) -[2023-10-09 03:59:06,907][88326] Updated weights for policy 0, policy_version 95182 (0.0008) -[2023-10-09 03:59:07,011][88327] Updated weights for policy 1, policy_version 95270 (0.0008) -[2023-10-09 03:59:07,277][88326] Updated weights for policy 0, policy_version 95192 (0.0008) -[2023-10-09 03:59:07,364][88327] Updated weights for policy 1, policy_version 95280 (0.0009) -[2023-10-09 03:59:07,729][88327] Updated weights for policy 1, policy_version 95290 (0.0009) -[2023-10-09 03:59:08,974][87372] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 195067904. Throughput: 0: 1701.3, 1: 1704.0. Samples: 48767552. Policy #0 lag: (min: 18.0, avg: 20.2, max: 41.0) -[2023-10-09 03:59:08,974][87372] Avg episode reward: [(0, '7.820'), (1, '7.770')] -[2023-10-09 03:59:11,066][88326] Updated weights for policy 0, policy_version 95202 (0.0009) -[2023-10-09 03:59:11,434][88326] Updated weights for policy 0, policy_version 95212 (0.0010) -[2023-10-09 03:59:11,809][88326] Updated weights for policy 0, policy_version 95222 (0.0009) -[2023-10-09 03:59:11,854][88327] Updated weights for policy 1, policy_version 95300 (0.0012) -[2023-10-09 03:59:12,178][88326] Updated weights for policy 0, policy_version 95232 (0.0008) -[2023-10-09 03:59:12,218][88327] Updated weights for policy 1, policy_version 95310 (0.0010) -[2023-10-09 03:59:12,584][88327] Updated weights for policy 1, policy_version 95320 (0.0007) -[2023-10-09 03:59:13,974][87372] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 195133440. Throughput: 0: 1669.3, 1: 1693.2. Samples: 48786582. Policy #0 lag: (min: 18.0, avg: 20.2, max: 41.0) -[2023-10-09 03:59:13,975][87372] Avg episode reward: [(0, '7.110'), (1, '7.850')] -[2023-10-09 03:59:16,528][88326] Updated weights for policy 0, policy_version 95242 (0.0008) -[2023-10-09 03:59:16,645][88327] Updated weights for policy 1, policy_version 95330 (0.0008) -[2023-10-09 03:59:16,884][88326] Updated weights for policy 0, policy_version 95252 (0.0009) -[2023-10-09 03:59:17,008][88327] Updated weights for policy 1, policy_version 95340 (0.0009) -[2023-10-09 03:59:17,256][88326] Updated weights for policy 0, policy_version 95262 (0.0007) -[2023-10-09 03:59:17,369][88327] Updated weights for policy 1, policy_version 95350 (0.0007) -[2023-10-09 03:59:17,730][88327] Updated weights for policy 1, policy_version 95360 (0.0008) -[2023-10-09 03:59:18,974][87372] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 195198976. Throughput: 0: 1687.0, 1: 1672.7. Samples: 48806514. Policy #0 lag: (min: 18.0, avg: 20.2, max: 41.0) -[2023-10-09 03:59:18,975][87372] Avg episode reward: [(0, '7.270'), (1, '7.610')] -[2023-10-09 03:59:21,325][88326] Updated weights for policy 0, policy_version 95272 (0.0007) -[2023-10-09 03:59:21,692][88326] Updated weights for policy 0, policy_version 95282 (0.0009) -[2023-10-09 03:59:22,054][88326] Updated weights for policy 0, policy_version 95292 (0.0009) -[2023-10-09 03:59:22,061][88327] Updated weights for policy 1, policy_version 95370 (0.0007) -[2023-10-09 03:59:22,435][88327] Updated weights for policy 1, policy_version 95380 (0.0010) -[2023-10-09 03:59:22,805][88327] Updated weights for policy 1, policy_version 95390 (0.0010) -[2023-10-09 03:59:23,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 195264512. Throughput: 0: 1686.4, 1: 1703.7. Samples: 48817950. Policy #0 lag: (min: 18.0, avg: 20.2, max: 41.0) -[2023-10-09 03:59:23,975][87372] Avg episode reward: [(0, '6.920'), (1, '7.450')] -[2023-10-09 03:59:26,110][88326] Updated weights for policy 0, policy_version 95302 (0.0010) -[2023-10-09 03:59:26,486][88326] Updated weights for policy 0, policy_version 95312 (0.0007) -[2023-10-09 03:59:26,699][88327] Updated weights for policy 1, policy_version 95400 (0.0009) -[2023-10-09 03:59:26,856][88326] Updated weights for policy 0, policy_version 95322 (0.0008) -[2023-10-09 03:59:27,061][88327] Updated weights for policy 1, policy_version 95410 (0.0009) -[2023-10-09 03:59:27,422][88327] Updated weights for policy 1, policy_version 95420 (0.0008) -[2023-10-09 03:59:28,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 195330048. Throughput: 0: 1668.4, 1: 1688.0. Samples: 48837150. Policy #0 lag: (min: 18.0, avg: 20.2, max: 41.0) -[2023-10-09 03:59:28,975][87372] Avg episode reward: [(0, '6.660'), (1, '7.930')] -[2023-10-09 03:59:30,682][88326] Updated weights for policy 0, policy_version 95332 (0.0009) -[2023-10-09 03:59:31,048][88326] Updated weights for policy 0, policy_version 95342 (0.0009) -[2023-10-09 03:59:31,414][88326] Updated weights for policy 0, policy_version 95352 (0.0009) -[2023-10-09 03:59:31,448][88327] Updated weights for policy 1, policy_version 95430 (0.0009) -[2023-10-09 03:59:31,814][88327] Updated weights for policy 1, policy_version 95440 (0.0009) -[2023-10-09 03:59:32,168][88327] Updated weights for policy 1, policy_version 95450 (0.0011) -[2023-10-09 03:59:33,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 195395584. Throughput: 0: 1695.8, 1: 1686.4. Samples: 48857532. Policy #0 lag: (min: 18.0, avg: 20.2, max: 41.0) -[2023-10-09 03:59:33,975][87372] Avg episode reward: [(0, '7.160'), (1, '7.340')] -[2023-10-09 03:59:35,580][88326] Updated weights for policy 0, policy_version 95362 (0.0007) -[2023-10-09 03:59:35,944][88326] Updated weights for policy 0, policy_version 95372 (0.0007) -[2023-10-09 03:59:36,164][88327] Updated weights for policy 1, policy_version 95460 (0.0007) -[2023-10-09 03:59:36,298][88326] Updated weights for policy 0, policy_version 95382 (0.0008) -[2023-10-09 03:59:36,521][88327] Updated weights for policy 1, policy_version 95470 (0.0007) -[2023-10-09 03:59:36,666][88326] Updated weights for policy 0, policy_version 95392 (0.0007) -[2023-10-09 03:59:36,897][88327] Updated weights for policy 1, policy_version 95480 (0.0008) -[2023-10-09 03:59:38,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 195461120. Throughput: 0: 1672.8, 1: 1699.7. Samples: 48868234. Policy #0 lag: (min: 18.0, avg: 20.2, max: 41.0) -[2023-10-09 03:59:38,975][87372] Avg episode reward: [(0, '7.170'), (1, '6.780')] -[2023-10-09 03:59:40,811][88326] Updated weights for policy 0, policy_version 95402 (0.0008) -[2023-10-09 03:59:40,872][88327] Updated weights for policy 1, policy_version 95490 (0.0008) -[2023-10-09 03:59:41,171][88326] Updated weights for policy 0, policy_version 95412 (0.0009) -[2023-10-09 03:59:41,233][88327] Updated weights for policy 1, policy_version 95500 (0.0010) -[2023-10-09 03:59:41,530][88326] Updated weights for policy 0, policy_version 95422 (0.0007) -[2023-10-09 03:59:41,594][88327] Updated weights for policy 1, policy_version 95510 (0.0007) -[2023-10-09 03:59:41,954][88327] Updated weights for policy 1, policy_version 95520 (0.0010) -[2023-10-09 03:59:43,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 195526656. Throughput: 0: 1670.8, 1: 1672.3. Samples: 48887510. Policy #0 lag: (min: 18.0, avg: 20.2, max: 41.0) -[2023-10-09 03:59:43,975][87372] Avg episode reward: [(0, '7.520'), (1, '7.470')] -[2023-10-09 03:59:45,420][88326] Updated weights for policy 0, policy_version 95432 (0.0009) -[2023-10-09 03:59:45,785][88326] Updated weights for policy 0, policy_version 95442 (0.0010) -[2023-10-09 03:59:46,033][88327] Updated weights for policy 1, policy_version 95530 (0.0008) -[2023-10-09 03:59:46,155][88326] Updated weights for policy 0, policy_version 95452 (0.0008) -[2023-10-09 03:59:46,397][88327] Updated weights for policy 1, policy_version 95540 (0.0007) -[2023-10-09 03:59:46,759][88327] Updated weights for policy 1, policy_version 95550 (0.0008) -[2023-10-09 03:59:48,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 195592192. Throughput: 0: 1692.7, 1: 1695.9. Samples: 48908510. Policy #0 lag: (min: 12.0, avg: 13.7, max: 41.0) -[2023-10-09 03:59:48,975][87372] Avg episode reward: [(0, '7.750'), (1, '7.900')] -[2023-10-09 03:59:50,181][88326] Updated weights for policy 0, policy_version 95462 (0.0008) -[2023-10-09 03:59:50,542][88326] Updated weights for policy 0, policy_version 95472 (0.0007) -[2023-10-09 03:59:50,749][88327] Updated weights for policy 1, policy_version 95560 (0.0008) -[2023-10-09 03:59:50,906][88326] Updated weights for policy 0, policy_version 95482 (0.0007) -[2023-10-09 03:59:51,106][88327] Updated weights for policy 1, policy_version 95570 (0.0008) -[2023-10-09 03:59:51,464][88327] Updated weights for policy 1, policy_version 95580 (0.0009) -[2023-10-09 03:59:53,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 195657728. Throughput: 0: 1666.4, 1: 1687.5. Samples: 48918480. Policy #0 lag: (min: 12.0, avg: 13.7, max: 41.0) -[2023-10-09 03:59:53,975][87372] Avg episode reward: [(0, '7.100'), (1, '7.850')] -[2023-10-09 03:59:54,961][88326] Updated weights for policy 0, policy_version 95492 (0.0007) -[2023-10-09 03:59:55,307][88327] Updated weights for policy 1, policy_version 95590 (0.0008) -[2023-10-09 03:59:55,323][88326] Updated weights for policy 0, policy_version 95502 (0.0007) -[2023-10-09 03:59:55,675][88327] Updated weights for policy 1, policy_version 95600 (0.0010) -[2023-10-09 03:59:55,696][88326] Updated weights for policy 0, policy_version 95512 (0.0007) -[2023-10-09 03:59:56,034][88327] Updated weights for policy 1, policy_version 95610 (0.0009) -[2023-10-09 03:59:58,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 195723264. Throughput: 0: 1695.1, 1: 1691.2. Samples: 48938962. Policy #0 lag: (min: 12.0, avg: 13.7, max: 41.0) -[2023-10-09 03:59:58,975][87372] Avg episode reward: [(0, '7.010'), (1, '7.460')] -[2023-10-09 03:59:59,799][88326] Updated weights for policy 0, policy_version 95522 (0.0009) -[2023-10-09 04:00:00,039][88327] Updated weights for policy 1, policy_version 95620 (0.0009) -[2023-10-09 04:00:00,177][88326] Updated weights for policy 0, policy_version 95532 (0.0009) -[2023-10-09 04:00:00,410][88327] Updated weights for policy 1, policy_version 95630 (0.0008) -[2023-10-09 04:00:00,524][88326] Updated weights for policy 0, policy_version 95542 (0.0008) -[2023-10-09 04:00:00,773][88327] Updated weights for policy 1, policy_version 95640 (0.0010) -[2023-10-09 04:00:00,891][88326] Updated weights for policy 0, policy_version 95552 (0.0008) -[2023-10-09 04:00:03,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 195788800. Throughput: 0: 1699.7, 1: 1706.5. Samples: 48959796. Policy #0 lag: (min: 12.0, avg: 13.7, max: 41.0) -[2023-10-09 04:00:03,975][87372] Avg episode reward: [(0, '7.070'), (1, '7.610')] -[2023-10-09 04:00:04,869][88327] Updated weights for policy 1, policy_version 95650 (0.0009) -[2023-10-09 04:00:04,961][88326] Updated weights for policy 0, policy_version 95562 (0.0008) -[2023-10-09 04:00:05,236][88327] Updated weights for policy 1, policy_version 95660 (0.0009) -[2023-10-09 04:00:05,331][88326] Updated weights for policy 0, policy_version 95572 (0.0007) -[2023-10-09 04:00:05,599][88327] Updated weights for policy 1, policy_version 95670 (0.0008) -[2023-10-09 04:00:05,692][88326] Updated weights for policy 0, policy_version 95582 (0.0008) -[2023-10-09 04:00:05,963][88327] Updated weights for policy 1, policy_version 95680 (0.0008) -[2023-10-09 04:00:08,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 195854336. Throughput: 0: 1672.7, 1: 1680.0. Samples: 48968820. Policy #0 lag: (min: 12.0, avg: 13.7, max: 41.0) -[2023-10-09 04:00:08,975][87372] Avg episode reward: [(0, '7.760'), (1, '7.310')] -[2023-10-09 04:00:09,585][88326] Updated weights for policy 0, policy_version 95592 (0.0010) -[2023-10-09 04:00:09,954][88326] Updated weights for policy 0, policy_version 95602 (0.0007) -[2023-10-09 04:00:10,056][88327] Updated weights for policy 1, policy_version 95690 (0.0008) -[2023-10-09 04:00:10,318][88326] Updated weights for policy 0, policy_version 95612 (0.0007) -[2023-10-09 04:00:10,418][88327] Updated weights for policy 1, policy_version 95700 (0.0008) -[2023-10-09 04:00:10,782][88327] Updated weights for policy 1, policy_version 95710 (0.0010) -[2023-10-09 04:00:13,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 195919872. Throughput: 0: 1697.8, 1: 1697.7. Samples: 48989948. Policy #0 lag: (min: 12.0, avg: 13.7, max: 41.0) -[2023-10-09 04:00:13,975][87372] Avg episode reward: [(0, '7.500'), (1, '7.140')] -[2023-10-09 04:00:14,456][88326] Updated weights for policy 0, policy_version 95622 (0.0009) -[2023-10-09 04:00:14,820][88326] Updated weights for policy 0, policy_version 95632 (0.0007) -[2023-10-09 04:00:14,974][88327] Updated weights for policy 1, policy_version 95720 (0.0007) -[2023-10-09 04:00:15,197][88326] Updated weights for policy 0, policy_version 95642 (0.0008) -[2023-10-09 04:00:15,341][88327] Updated weights for policy 1, policy_version 95730 (0.0008) -[2023-10-09 04:00:15,701][88327] Updated weights for policy 1, policy_version 95740 (0.0008) -[2023-10-09 04:00:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 195985408. Throughput: 0: 1701.4, 1: 1710.7. Samples: 49011076. Policy #0 lag: (min: 12.0, avg: 13.7, max: 41.0) -[2023-10-09 04:00:18,975][87372] Avg episode reward: [(0, '6.980'), (1, '7.720')] -[2023-10-09 04:00:19,044][88326] Updated weights for policy 0, policy_version 95652 (0.0009) -[2023-10-09 04:00:19,406][88326] Updated weights for policy 0, policy_version 95662 (0.0010) -[2023-10-09 04:00:19,599][88327] Updated weights for policy 1, policy_version 95750 (0.0009) -[2023-10-09 04:00:19,786][88326] Updated weights for policy 0, policy_version 95672 (0.0008) -[2023-10-09 04:00:19,965][88327] Updated weights for policy 1, policy_version 95760 (0.0008) -[2023-10-09 04:00:20,324][88327] Updated weights for policy 1, policy_version 95770 (0.0011) -[2023-10-09 04:00:23,786][88326] Updated weights for policy 0, policy_version 95682 (0.0007) -[2023-10-09 04:00:23,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 196050944. Throughput: 0: 1692.8, 1: 1684.5. Samples: 49020212. Policy #0 lag: (min: 12.0, avg: 13.7, max: 41.0) -[2023-10-09 04:00:23,974][87372] Avg episode reward: [(0, '6.690'), (1, '7.690')] -[2023-10-09 04:00:24,135][88326] Updated weights for policy 0, policy_version 95692 (0.0008) -[2023-10-09 04:00:24,416][88327] Updated weights for policy 1, policy_version 95780 (0.0008) -[2023-10-09 04:00:24,510][88326] Updated weights for policy 0, policy_version 95702 (0.0007) -[2023-10-09 04:00:24,781][88327] Updated weights for policy 1, policy_version 95790 (0.0007) -[2023-10-09 04:00:24,875][88326] Updated weights for policy 0, policy_version 95712 (0.0007) -[2023-10-09 04:00:25,138][88327] Updated weights for policy 1, policy_version 95800 (0.0010) -[2023-10-09 04:00:28,799][88326] Updated weights for policy 0, policy_version 95722 (0.0007) -[2023-10-09 04:00:28,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 196116480. Throughput: 0: 1711.7, 1: 1708.1. Samples: 49041402. Policy #0 lag: (min: 12.0, avg: 13.7, max: 41.0) -[2023-10-09 04:00:28,975][87372] Avg episode reward: [(0, '6.390'), (1, '7.650')] -[2023-10-09 04:00:29,146][88327] Updated weights for policy 1, policy_version 95810 (0.0008) -[2023-10-09 04:00:29,171][88326] Updated weights for policy 0, policy_version 95732 (0.0009) -[2023-10-09 04:00:29,515][88327] Updated weights for policy 1, policy_version 95820 (0.0009) -[2023-10-09 04:00:29,543][88326] Updated weights for policy 0, policy_version 95742 (0.0007) -[2023-10-09 04:00:29,875][88327] Updated weights for policy 1, policy_version 95830 (0.0010) -[2023-10-09 04:00:30,229][88327] Updated weights for policy 1, policy_version 95840 (0.0009) -[2023-10-09 04:00:33,520][88326] Updated weights for policy 0, policy_version 95752 (0.0010) -[2023-10-09 04:00:33,883][88326] Updated weights for policy 0, policy_version 95762 (0.0008) -[2023-10-09 04:00:33,974][87372] Fps is (10 sec: 13106.8, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 196182016. Throughput: 0: 1711.6, 1: 1712.3. Samples: 49062586. Policy #0 lag: (min: 12.0, avg: 13.7, max: 41.0) -[2023-10-09 04:00:33,975][87372] Avg episode reward: [(0, '7.010'), (1, '7.230')] -[2023-10-09 04:00:34,189][88327] Updated weights for policy 1, policy_version 95850 (0.0007) -[2023-10-09 04:00:34,253][88326] Updated weights for policy 0, policy_version 95772 (0.0008) -[2023-10-09 04:00:34,399][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000095776_98074624.pth... -[2023-10-09 04:00:34,429][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000094176_96436224.pth -[2023-10-09 04:00:34,555][88327] Updated weights for policy 1, policy_version 95860 (0.0008) -[2023-10-09 04:00:34,925][88327] Updated weights for policy 1, policy_version 95870 (0.0008) -[2023-10-09 04:00:34,996][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000095872_98172928.pth... -[2023-10-09 04:00:35,026][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000094272_96534528.pth -[2023-10-09 04:00:38,289][88326] Updated weights for policy 0, policy_version 95782 (0.0009) -[2023-10-09 04:00:38,650][88326] Updated weights for policy 0, policy_version 95792 (0.0007) -[2023-10-09 04:00:38,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 196247552. Throughput: 0: 1707.6, 1: 1695.8. Samples: 49071632. Policy #0 lag: (min: 12.0, avg: 13.7, max: 41.0) -[2023-10-09 04:00:38,975][87372] Avg episode reward: [(0, '6.800'), (1, '8.260')] -[2023-10-09 04:00:39,012][88326] Updated weights for policy 0, policy_version 95802 (0.0007) -[2023-10-09 04:00:39,063][88327] Updated weights for policy 1, policy_version 95880 (0.0009) -[2023-10-09 04:00:39,433][88327] Updated weights for policy 1, policy_version 95890 (0.0009) -[2023-10-09 04:00:39,797][88327] Updated weights for policy 1, policy_version 95900 (0.0007) -[2023-10-09 04:00:43,098][88326] Updated weights for policy 0, policy_version 95812 (0.0007) -[2023-10-09 04:00:43,462][88326] Updated weights for policy 0, policy_version 95822 (0.0008) -[2023-10-09 04:00:43,826][88326] Updated weights for policy 0, policy_version 95832 (0.0011) -[2023-10-09 04:00:43,974][87372] Fps is (10 sec: 13107.7, 60 sec: 13107.2, 300 sec: 13440.5). Total num frames: 196313088. Throughput: 0: 1709.0, 1: 1696.0. Samples: 49092186. Policy #0 lag: (min: 12.0, avg: 13.7, max: 41.0) -[2023-10-09 04:00:43,974][87372] Avg episode reward: [(0, '6.810'), (1, '7.580')] -[2023-10-09 04:00:43,979][88327] Updated weights for policy 1, policy_version 95910 (0.0007) -[2023-10-09 04:00:44,347][88327] Updated weights for policy 1, policy_version 95920 (0.0007) -[2023-10-09 04:00:44,710][88327] Updated weights for policy 1, policy_version 95930 (0.0007) -[2023-10-09 04:00:47,874][88326] Updated weights for policy 0, policy_version 95842 (0.0008) -[2023-10-09 04:00:48,250][88326] Updated weights for policy 0, policy_version 95852 (0.0010) -[2023-10-09 04:00:48,611][88326] Updated weights for policy 0, policy_version 95862 (0.0008) -[2023-10-09 04:00:48,649][88327] Updated weights for policy 1, policy_version 95940 (0.0008) -[2023-10-09 04:00:48,973][88326] Updated weights for policy 0, policy_version 95872 (0.0009) -[2023-10-09 04:00:48,974][87372] Fps is (10 sec: 16383.3, 60 sec: 13653.2, 300 sec: 13551.5). Total num frames: 196411392. Throughput: 0: 1698.6, 1: 1698.5. Samples: 49112668. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-09 04:00:48,976][87372] Avg episode reward: [(0, '6.780'), (1, '7.440')] -[2023-10-09 04:00:49,014][88327] Updated weights for policy 1, policy_version 95950 (0.0009) -[2023-10-09 04:00:49,373][88327] Updated weights for policy 1, policy_version 95960 (0.0009) -[2023-10-09 04:00:52,961][88326] Updated weights for policy 0, policy_version 95882 (0.0007) -[2023-10-09 04:00:53,333][88326] Updated weights for policy 0, policy_version 95892 (0.0008) -[2023-10-09 04:00:53,472][88327] Updated weights for policy 1, policy_version 95970 (0.0008) -[2023-10-09 04:00:53,711][88326] Updated weights for policy 0, policy_version 95902 (0.0008) -[2023-10-09 04:00:53,842][88327] Updated weights for policy 1, policy_version 95980 (0.0008) -[2023-10-09 04:00:53,974][87372] Fps is (10 sec: 16383.9, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 196476928. Throughput: 0: 1713.7, 1: 1695.9. Samples: 49122250. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-09 04:00:53,974][87372] Avg episode reward: [(0, '6.840'), (1, '7.980')] -[2023-10-09 04:00:54,209][88327] Updated weights for policy 1, policy_version 95990 (0.0010) -[2023-10-09 04:00:54,575][88327] Updated weights for policy 1, policy_version 96000 (0.0011) -[2023-10-09 04:00:57,760][88326] Updated weights for policy 0, policy_version 95912 (0.0009) -[2023-10-09 04:00:58,135][88326] Updated weights for policy 0, policy_version 95922 (0.0010) -[2023-10-09 04:00:58,499][88326] Updated weights for policy 0, policy_version 95932 (0.0007) -[2023-10-09 04:00:58,618][88327] Updated weights for policy 1, policy_version 96010 (0.0008) -[2023-10-09 04:00:58,974][87372] Fps is (10 sec: 13107.6, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 196542464. Throughput: 0: 1711.4, 1: 1690.0. Samples: 49143012. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-09 04:00:58,975][87372] Avg episode reward: [(0, '6.730'), (1, '7.960')] -[2023-10-09 04:00:58,985][88327] Updated weights for policy 1, policy_version 96020 (0.0007) -[2023-10-09 04:00:59,353][88327] Updated weights for policy 1, policy_version 96030 (0.0008) -[2023-10-09 04:01:02,651][88326] Updated weights for policy 0, policy_version 95942 (0.0008) -[2023-10-09 04:01:03,016][88326] Updated weights for policy 0, policy_version 95952 (0.0009) -[2023-10-09 04:01:03,378][88326] Updated weights for policy 0, policy_version 95962 (0.0011) -[2023-10-09 04:01:03,704][88327] Updated weights for policy 1, policy_version 96040 (0.0009) -[2023-10-09 04:01:03,974][87372] Fps is (10 sec: 13106.7, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 196608000. Throughput: 0: 1683.6, 1: 1685.9. Samples: 49162702. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-09 04:01:03,976][87372] Avg episode reward: [(0, '6.870'), (1, '7.570')] -[2023-10-09 04:01:04,083][88327] Updated weights for policy 1, policy_version 96050 (0.0008) -[2023-10-09 04:01:04,443][88327] Updated weights for policy 1, policy_version 96060 (0.0011) -[2023-10-09 04:01:07,555][88326] Updated weights for policy 0, policy_version 95972 (0.0008) -[2023-10-09 04:01:07,915][88326] Updated weights for policy 0, policy_version 95982 (0.0009) -[2023-10-09 04:01:08,282][88326] Updated weights for policy 0, policy_version 95992 (0.0007) -[2023-10-09 04:01:08,423][88327] Updated weights for policy 1, policy_version 96070 (0.0010) -[2023-10-09 04:01:08,787][88327] Updated weights for policy 1, policy_version 96080 (0.0008) -[2023-10-09 04:01:08,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 196673536. Throughput: 0: 1698.8, 1: 1683.7. Samples: 49172426. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-09 04:01:08,975][87372] Avg episode reward: [(0, '7.400'), (1, '7.930')] -[2023-10-09 04:01:09,151][88327] Updated weights for policy 1, policy_version 96090 (0.0011) -[2023-10-09 04:01:12,313][88326] Updated weights for policy 0, policy_version 96002 (0.0009) -[2023-10-09 04:01:12,689][88326] Updated weights for policy 0, policy_version 96012 (0.0009) -[2023-10-09 04:01:13,062][88326] Updated weights for policy 0, policy_version 96022 (0.0009) -[2023-10-09 04:01:13,222][88327] Updated weights for policy 1, policy_version 96100 (0.0010) -[2023-10-09 04:01:13,419][88326] Updated weights for policy 0, policy_version 96032 (0.0009) -[2023-10-09 04:01:13,577][88327] Updated weights for policy 1, policy_version 96110 (0.0009) -[2023-10-09 04:01:13,938][88327] Updated weights for policy 1, policy_version 96120 (0.0010) -[2023-10-09 04:01:13,974][87372] Fps is (10 sec: 13107.7, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 196739072. Throughput: 0: 1695.0, 1: 1681.0. Samples: 49193322. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-09 04:01:13,974][87372] Avg episode reward: [(0, '7.400'), (1, '8.260')] -[2023-10-09 04:01:17,324][88326] Updated weights for policy 0, policy_version 96042 (0.0008) -[2023-10-09 04:01:17,687][88326] Updated weights for policy 0, policy_version 96052 (0.0009) -[2023-10-09 04:01:18,064][88326] Updated weights for policy 0, policy_version 96062 (0.0009) -[2023-10-09 04:01:18,106][88327] Updated weights for policy 1, policy_version 96130 (0.0010) -[2023-10-09 04:01:18,468][88327] Updated weights for policy 1, policy_version 96140 (0.0007) -[2023-10-09 04:01:18,822][88327] Updated weights for policy 1, policy_version 96150 (0.0010) -[2023-10-09 04:01:18,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 196804608. Throughput: 0: 1662.6, 1: 1672.2. Samples: 49212654. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-09 04:01:18,975][87372] Avg episode reward: [(0, '6.850'), (1, '7.580')] -[2023-10-09 04:01:19,189][88327] Updated weights for policy 1, policy_version 96160 (0.0010) -[2023-10-09 04:01:22,154][88326] Updated weights for policy 0, policy_version 96072 (0.0009) -[2023-10-09 04:01:22,536][88326] Updated weights for policy 0, policy_version 96082 (0.0009) -[2023-10-09 04:01:22,890][88326] Updated weights for policy 0, policy_version 96092 (0.0009) -[2023-10-09 04:01:23,228][88327] Updated weights for policy 1, policy_version 96170 (0.0008) -[2023-10-09 04:01:23,590][88327] Updated weights for policy 1, policy_version 96180 (0.0011) -[2023-10-09 04:01:23,954][88327] Updated weights for policy 1, policy_version 96190 (0.0011) -[2023-10-09 04:01:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 196870144. Throughput: 0: 1696.1, 1: 1673.3. Samples: 49223256. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-09 04:01:23,974][87372] Avg episode reward: [(0, '6.990'), (1, '7.520')] -[2023-10-09 04:01:26,890][88326] Updated weights for policy 0, policy_version 96102 (0.0009) -[2023-10-09 04:01:27,255][88326] Updated weights for policy 0, policy_version 96112 (0.0007) -[2023-10-09 04:01:27,624][88326] Updated weights for policy 0, policy_version 96122 (0.0007) -[2023-10-09 04:01:27,985][88327] Updated weights for policy 1, policy_version 96200 (0.0009) -[2023-10-09 04:01:28,354][88327] Updated weights for policy 1, policy_version 96210 (0.0009) -[2023-10-09 04:01:28,717][88327] Updated weights for policy 1, policy_version 96220 (0.0009) -[2023-10-09 04:01:28,974][87372] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 196968448. Throughput: 0: 1684.0, 1: 1683.7. Samples: 49243730. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-09 04:01:28,974][87372] Avg episode reward: [(0, '6.800'), (1, '7.650')] -[2023-10-09 04:01:31,606][88326] Updated weights for policy 0, policy_version 96132 (0.0008) -[2023-10-09 04:01:31,971][88326] Updated weights for policy 0, policy_version 96142 (0.0010) -[2023-10-09 04:01:32,349][88326] Updated weights for policy 0, policy_version 96152 (0.0009) -[2023-10-09 04:01:32,706][88327] Updated weights for policy 1, policy_version 96230 (0.0008) -[2023-10-09 04:01:33,072][88327] Updated weights for policy 1, policy_version 96240 (0.0008) -[2023-10-09 04:01:33,439][88327] Updated weights for policy 1, policy_version 96250 (0.0010) -[2023-10-09 04:01:33,974][87372] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 13551.5). Total num frames: 197033984. Throughput: 0: 1676.0, 1: 1669.2. Samples: 49263200. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-09 04:01:33,975][87372] Avg episode reward: [(0, '7.520'), (1, '7.540')] -[2023-10-09 04:01:36,444][88326] Updated weights for policy 0, policy_version 96162 (0.0008) -[2023-10-09 04:01:36,813][88326] Updated weights for policy 0, policy_version 96172 (0.0007) -[2023-10-09 04:01:37,183][88326] Updated weights for policy 0, policy_version 96182 (0.0008) -[2023-10-09 04:01:37,520][88327] Updated weights for policy 1, policy_version 96260 (0.0009) -[2023-10-09 04:01:37,539][88326] Updated weights for policy 0, policy_version 96192 (0.0008) -[2023-10-09 04:01:37,887][88327] Updated weights for policy 1, policy_version 96270 (0.0008) -[2023-10-09 04:01:38,258][88327] Updated weights for policy 1, policy_version 96280 (0.0010) -[2023-10-09 04:01:38,974][87372] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 197099520. Throughput: 0: 1691.5, 1: 1684.8. Samples: 49274182. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-09 04:01:38,975][87372] Avg episode reward: [(0, '7.280'), (1, '7.420')] -[2023-10-09 04:01:41,624][88326] Updated weights for policy 0, policy_version 96202 (0.0009) -[2023-10-09 04:01:41,999][88326] Updated weights for policy 0, policy_version 96212 (0.0011) -[2023-10-09 04:01:42,270][88327] Updated weights for policy 1, policy_version 96290 (0.0010) -[2023-10-09 04:01:42,375][88326] Updated weights for policy 0, policy_version 96222 (0.0008) -[2023-10-09 04:01:42,633][88327] Updated weights for policy 1, policy_version 96300 (0.0008) -[2023-10-09 04:01:42,998][88327] Updated weights for policy 1, policy_version 96310 (0.0007) -[2023-10-09 04:01:43,359][88327] Updated weights for policy 1, policy_version 96320 (0.0008) -[2023-10-09 04:01:43,974][87372] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13551.5). Total num frames: 197165056. Throughput: 0: 1668.2, 1: 1688.4. Samples: 49294060. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-09 04:01:43,975][87372] Avg episode reward: [(0, '7.400'), (1, '7.660')] -[2023-10-09 04:01:46,649][88326] Updated weights for policy 0, policy_version 96232 (0.0008) -[2023-10-09 04:01:47,015][88326] Updated weights for policy 0, policy_version 96242 (0.0008) -[2023-10-09 04:01:47,376][88326] Updated weights for policy 0, policy_version 96252 (0.0007) -[2023-10-09 04:01:47,395][88327] Updated weights for policy 1, policy_version 96330 (0.0009) -[2023-10-09 04:01:47,753][88327] Updated weights for policy 1, policy_version 96340 (0.0008) -[2023-10-09 04:01:48,120][88327] Updated weights for policy 1, policy_version 96350 (0.0009) -[2023-10-09 04:01:48,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 197230592. Throughput: 0: 1677.3, 1: 1664.3. Samples: 49313070. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-09 04:01:48,975][87372] Avg episode reward: [(0, '7.700'), (1, '7.230')] -[2023-10-09 04:01:51,571][88326] Updated weights for policy 0, policy_version 96262 (0.0008) -[2023-10-09 04:01:51,938][88326] Updated weights for policy 0, policy_version 96272 (0.0007) -[2023-10-09 04:01:52,193][88327] Updated weights for policy 1, policy_version 96360 (0.0007) -[2023-10-09 04:01:52,310][88326] Updated weights for policy 0, policy_version 96282 (0.0008) -[2023-10-09 04:01:52,567][88327] Updated weights for policy 1, policy_version 96370 (0.0008) -[2023-10-09 04:01:52,942][88327] Updated weights for policy 1, policy_version 96380 (0.0008) -[2023-10-09 04:01:53,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 197296128. Throughput: 0: 1690.5, 1: 1688.4. Samples: 49324474. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-09 04:01:53,975][87372] Avg episode reward: [(0, '7.780'), (1, '7.340')] -[2023-10-09 04:01:56,299][88326] Updated weights for policy 0, policy_version 96292 (0.0007) -[2023-10-09 04:01:56,677][88326] Updated weights for policy 0, policy_version 96302 (0.0008) -[2023-10-09 04:01:56,961][88327] Updated weights for policy 1, policy_version 96390 (0.0009) -[2023-10-09 04:01:57,040][88326] Updated weights for policy 0, policy_version 96312 (0.0008) -[2023-10-09 04:01:57,327][88327] Updated weights for policy 1, policy_version 96400 (0.0007) -[2023-10-09 04:01:57,688][88327] Updated weights for policy 1, policy_version 96410 (0.0011) -[2023-10-09 04:01:58,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13551.5). Total num frames: 197361664. Throughput: 0: 1665.6, 1: 1682.7. Samples: 49343994. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-09 04:01:58,974][87372] Avg episode reward: [(0, '7.680'), (1, '7.540')] -[2023-10-09 04:02:01,235][88326] Updated weights for policy 0, policy_version 96322 (0.0008) -[2023-10-09 04:02:01,594][88326] Updated weights for policy 0, policy_version 96332 (0.0009) -[2023-10-09 04:02:01,900][88327] Updated weights for policy 1, policy_version 96420 (0.0009) -[2023-10-09 04:02:01,967][88326] Updated weights for policy 0, policy_version 96342 (0.0009) -[2023-10-09 04:02:02,269][88327] Updated weights for policy 1, policy_version 96430 (0.0007) -[2023-10-09 04:02:02,332][88326] Updated weights for policy 0, policy_version 96352 (0.0008) -[2023-10-09 04:02:02,635][88327] Updated weights for policy 1, policy_version 96440 (0.0007) -[2023-10-09 04:02:03,974][87372] Fps is (10 sec: 13106.6, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 197427200. Throughput: 0: 1688.6, 1: 1666.7. Samples: 49363644. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-09 04:02:03,976][87372] Avg episode reward: [(0, '7.760'), (1, '7.480')] -[2023-10-09 04:02:06,423][88326] Updated weights for policy 0, policy_version 96362 (0.0008) -[2023-10-09 04:02:06,739][88327] Updated weights for policy 1, policy_version 96450 (0.0011) -[2023-10-09 04:02:06,797][88326] Updated weights for policy 0, policy_version 96372 (0.0009) -[2023-10-09 04:02:07,103][88327] Updated weights for policy 1, policy_version 96460 (0.0008) -[2023-10-09 04:02:07,171][88326] Updated weights for policy 0, policy_version 96382 (0.0008) -[2023-10-09 04:02:07,475][88327] Updated weights for policy 1, policy_version 96470 (0.0007) -[2023-10-09 04:02:07,835][88327] Updated weights for policy 1, policy_version 96480 (0.0008) -[2023-10-09 04:02:08,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 197492736. Throughput: 0: 1679.3, 1: 1693.7. Samples: 49375044. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-09 04:02:08,975][87372] Avg episode reward: [(0, '7.140'), (1, '7.350')] -[2023-10-09 04:02:11,298][88326] Updated weights for policy 0, policy_version 96392 (0.0010) -[2023-10-09 04:02:11,661][88326] Updated weights for policy 0, policy_version 96402 (0.0010) -[2023-10-09 04:02:11,981][88327] Updated weights for policy 1, policy_version 96490 (0.0008) -[2023-10-09 04:02:12,035][88326] Updated weights for policy 0, policy_version 96412 (0.0010) -[2023-10-09 04:02:12,350][88327] Updated weights for policy 1, policy_version 96500 (0.0008) -[2023-10-09 04:02:12,712][88327] Updated weights for policy 1, policy_version 96510 (0.0009) -[2023-10-09 04:02:13,974][87372] Fps is (10 sec: 13107.7, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 197558272. Throughput: 0: 1662.0, 1: 1679.1. Samples: 49394080. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-09 04:02:13,975][87372] Avg episode reward: [(0, '6.890'), (1, '7.790')] -[2023-10-09 04:02:16,276][88326] Updated weights for policy 0, policy_version 96422 (0.0010) -[2023-10-09 04:02:16,638][88326] Updated weights for policy 0, policy_version 96432 (0.0009) -[2023-10-09 04:02:16,908][88327] Updated weights for policy 1, policy_version 96520 (0.0008) -[2023-10-09 04:02:17,016][88326] Updated weights for policy 0, policy_version 96442 (0.0007) -[2023-10-09 04:02:17,264][88327] Updated weights for policy 1, policy_version 96530 (0.0009) -[2023-10-09 04:02:17,634][88327] Updated weights for policy 1, policy_version 96540 (0.0008) -[2023-10-09 04:02:18,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 197623808. Throughput: 0: 1669.8, 1: 1669.2. Samples: 49413456. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-09 04:02:18,975][87372] Avg episode reward: [(0, '6.260'), (1, '8.660')] -[2023-10-09 04:02:21,110][88326] Updated weights for policy 0, policy_version 96452 (0.0009) -[2023-10-09 04:02:21,478][88326] Updated weights for policy 0, policy_version 96462 (0.0008) -[2023-10-09 04:02:21,840][88327] Updated weights for policy 1, policy_version 96550 (0.0010) -[2023-10-09 04:02:21,845][88326] Updated weights for policy 0, policy_version 96472 (0.0009) -[2023-10-09 04:02:22,209][88327] Updated weights for policy 1, policy_version 96560 (0.0010) -[2023-10-09 04:02:22,574][88327] Updated weights for policy 1, policy_version 96570 (0.0009) -[2023-10-09 04:02:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13551.5). Total num frames: 197689344. Throughput: 0: 1660.7, 1: 1676.0. Samples: 49424332. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-09 04:02:23,974][87372] Avg episode reward: [(0, '6.630'), (1, '7.880')] -[2023-10-09 04:02:25,811][88326] Updated weights for policy 0, policy_version 96482 (0.0010) -[2023-10-09 04:02:26,188][88326] Updated weights for policy 0, policy_version 96492 (0.0008) -[2023-10-09 04:02:26,553][88326] Updated weights for policy 0, policy_version 96502 (0.0011) -[2023-10-09 04:02:26,742][88327] Updated weights for policy 1, policy_version 96580 (0.0009) -[2023-10-09 04:02:26,915][88326] Updated weights for policy 0, policy_version 96512 (0.0007) -[2023-10-09 04:02:27,107][88327] Updated weights for policy 1, policy_version 96590 (0.0009) -[2023-10-09 04:02:27,474][88327] Updated weights for policy 1, policy_version 96600 (0.0009) -[2023-10-09 04:02:28,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 197754880. Throughput: 0: 1661.3, 1: 1653.6. Samples: 49443232. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-09 04:02:28,975][87372] Avg episode reward: [(0, '7.220'), (1, '8.440')] -[2023-10-09 04:02:31,205][88326] Updated weights for policy 0, policy_version 96522 (0.0008) -[2023-10-09 04:02:31,527][88327] Updated weights for policy 1, policy_version 96610 (0.0007) -[2023-10-09 04:02:31,569][88326] Updated weights for policy 0, policy_version 96532 (0.0009) -[2023-10-09 04:02:31,889][88327] Updated weights for policy 1, policy_version 96620 (0.0009) -[2023-10-09 04:02:31,933][88326] Updated weights for policy 0, policy_version 96542 (0.0010) -[2023-10-09 04:02:32,244][88327] Updated weights for policy 1, policy_version 96630 (0.0009) -[2023-10-09 04:02:32,608][88327] Updated weights for policy 1, policy_version 96640 (0.0008) -[2023-10-09 04:02:33,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 197820416. Throughput: 0: 1663.0, 1: 1662.5. Samples: 49462718. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-09 04:02:33,975][87372] Avg episode reward: [(0, '7.180'), (1, '8.480')] -[2023-10-09 04:02:33,982][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000096544_98861056.pth... -[2023-10-09 04:02:33,982][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000096640_98959360.pth... -[2023-10-09 04:02:34,021][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000094976_97255424.pth -[2023-10-09 04:02:34,024][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000095072_97353728.pth -[2023-10-09 04:02:36,125][88326] Updated weights for policy 0, policy_version 96552 (0.0008) -[2023-10-09 04:02:36,494][88326] Updated weights for policy 0, policy_version 96562 (0.0008) -[2023-10-09 04:02:36,863][88326] Updated weights for policy 0, policy_version 96572 (0.0008) -[2023-10-09 04:02:36,992][88327] Updated weights for policy 1, policy_version 96650 (0.0009) -[2023-10-09 04:02:37,359][88327] Updated weights for policy 1, policy_version 96660 (0.0011) -[2023-10-09 04:02:37,723][88327] Updated weights for policy 1, policy_version 96670 (0.0009) -[2023-10-09 04:02:38,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 197885952. Throughput: 0: 1650.9, 1: 1662.3. Samples: 49473570. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-09 04:02:38,975][87372] Avg episode reward: [(0, '7.400'), (1, '8.360')] -[2023-10-09 04:02:41,079][88326] Updated weights for policy 0, policy_version 96582 (0.0008) -[2023-10-09 04:02:41,445][88326] Updated weights for policy 0, policy_version 96592 (0.0010) -[2023-10-09 04:02:41,804][88326] Updated weights for policy 0, policy_version 96602 (0.0009) -[2023-10-09 04:02:41,809][88327] Updated weights for policy 1, policy_version 96680 (0.0010) -[2023-10-09 04:02:42,166][88327] Updated weights for policy 1, policy_version 96690 (0.0009) -[2023-10-09 04:02:42,535][88327] Updated weights for policy 1, policy_version 96700 (0.0009) -[2023-10-09 04:02:43,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 197951488. Throughput: 0: 1644.8, 1: 1645.7. Samples: 49492066. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-09 04:02:43,975][87372] Avg episode reward: [(0, '6.570'), (1, '7.670')] -[2023-10-09 04:02:45,957][88326] Updated weights for policy 0, policy_version 96612 (0.0009) -[2023-10-09 04:02:46,337][88326] Updated weights for policy 0, policy_version 96622 (0.0011) -[2023-10-09 04:02:46,698][88326] Updated weights for policy 0, policy_version 96632 (0.0009) -[2023-10-09 04:02:46,766][88327] Updated weights for policy 1, policy_version 96710 (0.0009) -[2023-10-09 04:02:47,125][88327] Updated weights for policy 1, policy_version 96720 (0.0010) -[2023-10-09 04:02:47,493][88327] Updated weights for policy 1, policy_version 96730 (0.0008) -[2023-10-09 04:02:48,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 198017024. Throughput: 0: 1640.1, 1: 1643.9. Samples: 49511422. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-09 04:02:48,975][87372] Avg episode reward: [(0, '6.840'), (1, '8.130')] -[2023-10-09 04:02:51,050][88326] Updated weights for policy 0, policy_version 96642 (0.0009) -[2023-10-09 04:02:51,408][88326] Updated weights for policy 0, policy_version 96652 (0.0009) -[2023-10-09 04:02:51,774][88327] Updated weights for policy 1, policy_version 96740 (0.0010) -[2023-10-09 04:02:51,777][88326] Updated weights for policy 0, policy_version 96662 (0.0009) -[2023-10-09 04:02:52,131][88327] Updated weights for policy 1, policy_version 96750 (0.0009) -[2023-10-09 04:02:52,142][88326] Updated weights for policy 0, policy_version 96672 (0.0011) -[2023-10-09 04:02:52,493][88327] Updated weights for policy 1, policy_version 96760 (0.0010) -[2023-10-09 04:02:53,974][87372] Fps is (10 sec: 13106.8, 60 sec: 13107.1, 300 sec: 13551.5). Total num frames: 198082560. Throughput: 0: 1634.4, 1: 1635.9. Samples: 49522210. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-09 04:02:53,975][87372] Avg episode reward: [(0, '6.790'), (1, '7.400')] -[2023-10-09 04:02:56,440][88326] Updated weights for policy 0, policy_version 96682 (0.0010) -[2023-10-09 04:02:56,802][88327] Updated weights for policy 1, policy_version 96770 (0.0008) -[2023-10-09 04:02:56,806][88326] Updated weights for policy 0, policy_version 96692 (0.0010) -[2023-10-09 04:02:57,158][88327] Updated weights for policy 1, policy_version 96780 (0.0010) -[2023-10-09 04:02:57,171][88326] Updated weights for policy 0, policy_version 96702 (0.0007) -[2023-10-09 04:02:57,533][88327] Updated weights for policy 1, policy_version 96790 (0.0009) -[2023-10-09 04:02:57,884][88327] Updated weights for policy 1, policy_version 96800 (0.0008) -[2023-10-09 04:02:58,974][87372] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 198148096. Throughput: 0: 1633.9, 1: 1632.0. Samples: 49541048. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-09 04:02:58,975][87372] Avg episode reward: [(0, '7.060'), (1, '7.020')] -[2023-10-09 04:03:01,246][88326] Updated weights for policy 0, policy_version 96712 (0.0009) -[2023-10-09 04:03:01,620][88326] Updated weights for policy 0, policy_version 96722 (0.0008) -[2023-10-09 04:03:01,900][88327] Updated weights for policy 1, policy_version 96810 (0.0009) -[2023-10-09 04:03:01,990][88326] Updated weights for policy 0, policy_version 96732 (0.0008) -[2023-10-09 04:03:02,267][88327] Updated weights for policy 1, policy_version 96820 (0.0008) -[2023-10-09 04:03:02,636][88327] Updated weights for policy 1, policy_version 96830 (0.0008) -[2023-10-09 04:03:03,974][87372] Fps is (10 sec: 13107.6, 60 sec: 13107.3, 300 sec: 13551.5). Total num frames: 198213632. Throughput: 0: 1640.6, 1: 1637.9. Samples: 49560988. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-09 04:03:03,975][87372] Avg episode reward: [(0, '7.080'), (1, '7.160')] -[2023-10-09 04:03:05,938][88326] Updated weights for policy 0, policy_version 96742 (0.0007) -[2023-10-09 04:03:06,308][88326] Updated weights for policy 0, policy_version 96752 (0.0008) -[2023-10-09 04:03:06,573][88327] Updated weights for policy 1, policy_version 96840 (0.0007) -[2023-10-09 04:03:06,671][88326] Updated weights for policy 0, policy_version 96762 (0.0008) -[2023-10-09 04:03:06,934][88327] Updated weights for policy 1, policy_version 96850 (0.0008) -[2023-10-09 04:03:07,307][88327] Updated weights for policy 1, policy_version 96860 (0.0009) -[2023-10-09 04:03:08,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 198279168. Throughput: 0: 1640.2, 1: 1646.9. Samples: 49572254. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-09 04:03:08,975][87372] Avg episode reward: [(0, '7.170'), (1, '7.540')] -[2023-10-09 04:03:10,684][88326] Updated weights for policy 0, policy_version 96772 (0.0008) -[2023-10-09 04:03:11,041][88326] Updated weights for policy 0, policy_version 96782 (0.0009) -[2023-10-09 04:03:11,418][88326] Updated weights for policy 0, policy_version 96792 (0.0007) -[2023-10-09 04:03:11,420][88327] Updated weights for policy 1, policy_version 96870 (0.0009) -[2023-10-09 04:03:11,785][88327] Updated weights for policy 1, policy_version 96880 (0.0008) -[2023-10-09 04:03:12,143][88327] Updated weights for policy 1, policy_version 96890 (0.0007) -[2023-10-09 04:03:13,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13551.5). Total num frames: 198344704. Throughput: 0: 1645.3, 1: 1643.5. Samples: 49591226. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-09 04:03:13,975][87372] Avg episode reward: [(0, '7.180'), (1, '7.330')] -[2023-10-09 04:03:15,715][88326] Updated weights for policy 0, policy_version 96802 (0.0007) -[2023-10-09 04:03:16,126][88326] Updated weights for policy 0, policy_version 96812 (0.0010) -[2023-10-09 04:03:16,199][88327] Updated weights for policy 1, policy_version 96900 (0.0008) -[2023-10-09 04:03:16,491][88326] Updated weights for policy 0, policy_version 96822 (0.0009) -[2023-10-09 04:03:16,570][88327] Updated weights for policy 1, policy_version 96910 (0.0009) -[2023-10-09 04:03:16,854][88326] Updated weights for policy 0, policy_version 96832 (0.0010) -[2023-10-09 04:03:16,932][88327] Updated weights for policy 1, policy_version 96920 (0.0009) -[2023-10-09 04:03:18,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.3, 300 sec: 13440.4). Total num frames: 198410240. Throughput: 0: 1648.2, 1: 1649.3. Samples: 49611108. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-09 04:03:18,975][87372] Avg episode reward: [(0, '7.650'), (1, '8.390')] -[2023-10-09 04:03:20,881][88326] Updated weights for policy 0, policy_version 96842 (0.0010) -[2023-10-09 04:03:21,140][88327] Updated weights for policy 1, policy_version 96930 (0.0008) -[2023-10-09 04:03:21,244][88326] Updated weights for policy 0, policy_version 96852 (0.0010) -[2023-10-09 04:03:21,502][88327] Updated weights for policy 1, policy_version 96940 (0.0009) -[2023-10-09 04:03:21,618][88326] Updated weights for policy 0, policy_version 96862 (0.0009) -[2023-10-09 04:03:21,863][88327] Updated weights for policy 1, policy_version 96950 (0.0009) -[2023-10-09 04:03:22,232][88327] Updated weights for policy 1, policy_version 96960 (0.0009) -[2023-10-09 04:03:23,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.1, 300 sec: 13440.4). Total num frames: 198475776. Throughput: 0: 1642.4, 1: 1648.8. Samples: 49621672. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-09 04:03:23,975][87372] Avg episode reward: [(0, '6.870'), (1, '8.290')] -[2023-10-09 04:03:25,839][88326] Updated weights for policy 0, policy_version 96872 (0.0010) -[2023-10-09 04:03:26,195][88326] Updated weights for policy 0, policy_version 96882 (0.0009) -[2023-10-09 04:03:26,561][88326] Updated weights for policy 0, policy_version 96892 (0.0007) -[2023-10-09 04:03:26,588][88327] Updated weights for policy 1, policy_version 96970 (0.0009) -[2023-10-09 04:03:26,959][88327] Updated weights for policy 1, policy_version 96980 (0.0010) -[2023-10-09 04:03:27,322][88327] Updated weights for policy 1, policy_version 96990 (0.0009) -[2023-10-09 04:03:28,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 198541312. Throughput: 0: 1651.0, 1: 1643.6. Samples: 49640324. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-09 04:03:28,975][87372] Avg episode reward: [(0, '7.600'), (1, '7.980')] -[2023-10-09 04:03:30,832][88326] Updated weights for policy 0, policy_version 96902 (0.0009) -[2023-10-09 04:03:31,207][88326] Updated weights for policy 0, policy_version 96912 (0.0008) -[2023-10-09 04:03:31,404][88327] Updated weights for policy 1, policy_version 97000 (0.0009) -[2023-10-09 04:03:31,579][88326] Updated weights for policy 0, policy_version 96922 (0.0009) -[2023-10-09 04:03:31,765][88327] Updated weights for policy 1, policy_version 97010 (0.0008) -[2023-10-09 04:03:32,124][88327] Updated weights for policy 1, policy_version 97020 (0.0008) -[2023-10-09 04:03:33,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 198606848. Throughput: 0: 1648.8, 1: 1653.9. Samples: 49660040. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-09 04:03:33,975][87372] Avg episode reward: [(0, '7.760'), (1, '7.860')] -[2023-10-09 04:03:35,808][88326] Updated weights for policy 0, policy_version 96932 (0.0010) -[2023-10-09 04:03:36,177][88326] Updated weights for policy 0, policy_version 96942 (0.0009) -[2023-10-09 04:03:36,452][88327] Updated weights for policy 1, policy_version 97030 (0.0009) -[2023-10-09 04:03:36,546][88326] Updated weights for policy 0, policy_version 96952 (0.0008) -[2023-10-09 04:03:36,814][88327] Updated weights for policy 1, policy_version 97040 (0.0010) -[2023-10-09 04:03:37,177][88327] Updated weights for policy 1, policy_version 97050 (0.0010) -[2023-10-09 04:03:38,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13440.4). Total num frames: 198672384. Throughput: 0: 1642.6, 1: 1658.5. Samples: 49670758. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-09 04:03:38,974][87372] Avg episode reward: [(0, '6.790'), (1, '7.880')] -[2023-10-09 04:03:40,598][88326] Updated weights for policy 0, policy_version 96962 (0.0010) -[2023-10-09 04:03:40,966][88326] Updated weights for policy 0, policy_version 96972 (0.0010) -[2023-10-09 04:03:41,290][88327] Updated weights for policy 1, policy_version 97060 (0.0008) -[2023-10-09 04:03:41,332][88326] Updated weights for policy 0, policy_version 96982 (0.0008) -[2023-10-09 04:03:41,657][88327] Updated weights for policy 1, policy_version 97070 (0.0008) -[2023-10-09 04:03:41,700][88326] Updated weights for policy 0, policy_version 96992 (0.0008) -[2023-10-09 04:03:42,025][88327] Updated weights for policy 1, policy_version 97080 (0.0008) -[2023-10-09 04:03:43,974][87372] Fps is (10 sec: 13106.8, 60 sec: 13107.1, 300 sec: 13329.3). Total num frames: 198737920. Throughput: 0: 1652.4, 1: 1644.5. Samples: 49689408. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-09 04:03:43,975][87372] Avg episode reward: [(0, '7.250'), (1, '7.560')] -[2023-10-09 04:03:45,780][88326] Updated weights for policy 0, policy_version 97002 (0.0011) -[2023-10-09 04:03:46,077][88327] Updated weights for policy 1, policy_version 97090 (0.0007) -[2023-10-09 04:03:46,153][88326] Updated weights for policy 0, policy_version 97012 (0.0007) -[2023-10-09 04:03:46,438][88327] Updated weights for policy 1, policy_version 97100 (0.0009) -[2023-10-09 04:03:46,523][88326] Updated weights for policy 0, policy_version 97022 (0.0007) -[2023-10-09 04:03:46,810][88327] Updated weights for policy 1, policy_version 97110 (0.0009) -[2023-10-09 04:03:47,164][88327] Updated weights for policy 1, policy_version 97120 (0.0009) -[2023-10-09 04:03:48,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 198803456. Throughput: 0: 1655.1, 1: 1656.0. Samples: 49709986. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 04:03:48,975][87372] Avg episode reward: [(0, '7.860'), (1, '7.690')] -[2023-10-09 04:03:50,557][88326] Updated weights for policy 0, policy_version 97032 (0.0009) -[2023-10-09 04:03:50,915][88326] Updated weights for policy 0, policy_version 97042 (0.0010) -[2023-10-09 04:03:51,268][88327] Updated weights for policy 1, policy_version 97130 (0.0008) -[2023-10-09 04:03:51,295][88326] Updated weights for policy 0, policy_version 97052 (0.0008) -[2023-10-09 04:03:51,636][88327] Updated weights for policy 1, policy_version 97140 (0.0009) -[2023-10-09 04:03:51,998][88327] Updated weights for policy 1, policy_version 97150 (0.0009) -[2023-10-09 04:03:53,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 198868992. Throughput: 0: 1646.9, 1: 1650.0. Samples: 49720614. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 04:03:53,975][87372] Avg episode reward: [(0, '7.710'), (1, '7.870')] -[2023-10-09 04:03:55,328][88326] Updated weights for policy 0, policy_version 97062 (0.0007) -[2023-10-09 04:03:55,696][88326] Updated weights for policy 0, policy_version 97072 (0.0010) -[2023-10-09 04:03:56,029][88327] Updated weights for policy 1, policy_version 97160 (0.0008) -[2023-10-09 04:03:56,057][88326] Updated weights for policy 0, policy_version 97082 (0.0007) -[2023-10-09 04:03:56,396][88327] Updated weights for policy 1, policy_version 97170 (0.0008) -[2023-10-09 04:03:56,766][88327] Updated weights for policy 1, policy_version 97180 (0.0011) -[2023-10-09 04:03:58,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 198934528. Throughput: 0: 1662.4, 1: 1650.8. Samples: 49740322. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 04:03:58,975][87372] Avg episode reward: [(0, '7.510'), (1, '7.860')] -[2023-10-09 04:03:59,782][88326] Updated weights for policy 0, policy_version 97092 (0.0009) -[2023-10-09 04:04:00,159][88326] Updated weights for policy 0, policy_version 97102 (0.0010) -[2023-10-09 04:04:00,529][88326] Updated weights for policy 0, policy_version 97112 (0.0010) -[2023-10-09 04:04:00,750][88327] Updated weights for policy 1, policy_version 97190 (0.0009) -[2023-10-09 04:04:01,106][88327] Updated weights for policy 1, policy_version 97200 (0.0009) -[2023-10-09 04:04:01,462][88327] Updated weights for policy 1, policy_version 97210 (0.0010) -[2023-10-09 04:04:03,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 199000064. Throughput: 0: 1677.3, 1: 1669.2. Samples: 49761702. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 04:04:03,974][87372] Avg episode reward: [(0, '7.550'), (1, '7.990')] -[2023-10-09 04:04:04,553][88326] Updated weights for policy 0, policy_version 97122 (0.0008) -[2023-10-09 04:04:04,970][88326] Updated weights for policy 0, policy_version 97132 (0.0010) -[2023-10-09 04:04:05,336][88326] Updated weights for policy 0, policy_version 97142 (0.0009) -[2023-10-09 04:04:05,464][88327] Updated weights for policy 1, policy_version 97220 (0.0009) -[2023-10-09 04:04:05,701][88326] Updated weights for policy 0, policy_version 97152 (0.0007) -[2023-10-09 04:04:05,828][88327] Updated weights for policy 1, policy_version 97230 (0.0008) -[2023-10-09 04:04:06,192][88327] Updated weights for policy 1, policy_version 97240 (0.0010) -[2023-10-09 04:04:08,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 199065600. Throughput: 0: 1664.2, 1: 1657.9. Samples: 49771164. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 04:04:08,975][87372] Avg episode reward: [(0, '7.250'), (1, '7.850')] -[2023-10-09 04:04:09,737][88326] Updated weights for policy 0, policy_version 97162 (0.0008) -[2023-10-09 04:04:10,103][88326] Updated weights for policy 0, policy_version 97172 (0.0008) -[2023-10-09 04:04:10,345][88327] Updated weights for policy 1, policy_version 97250 (0.0009) -[2023-10-09 04:04:10,462][88326] Updated weights for policy 0, policy_version 97182 (0.0009) -[2023-10-09 04:04:10,711][88327] Updated weights for policy 1, policy_version 97260 (0.0009) -[2023-10-09 04:04:11,072][88327] Updated weights for policy 1, policy_version 97270 (0.0010) -[2023-10-09 04:04:11,436][88327] Updated weights for policy 1, policy_version 97280 (0.0010) -[2023-10-09 04:04:13,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 199131136. Throughput: 0: 1686.4, 1: 1675.9. Samples: 49791628. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 04:04:13,975][87372] Avg episode reward: [(0, '6.810'), (1, '7.700')] -[2023-10-09 04:04:14,318][88326] Updated weights for policy 0, policy_version 97192 (0.0008) -[2023-10-09 04:04:14,688][88326] Updated weights for policy 0, policy_version 97202 (0.0007) -[2023-10-09 04:04:15,057][88326] Updated weights for policy 0, policy_version 97212 (0.0009) -[2023-10-09 04:04:15,662][88327] Updated weights for policy 1, policy_version 97290 (0.0007) -[2023-10-09 04:04:16,020][88327] Updated weights for policy 1, policy_version 97300 (0.0008) -[2023-10-09 04:04:16,391][88327] Updated weights for policy 1, policy_version 97310 (0.0008) -[2023-10-09 04:04:18,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.1, 300 sec: 13329.4). Total num frames: 199196672. Throughput: 0: 1706.0, 1: 1688.9. Samples: 49812812. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 04:04:18,975][87372] Avg episode reward: [(0, '6.730'), (1, '7.730')] -[2023-10-09 04:04:19,002][88326] Updated weights for policy 0, policy_version 97222 (0.0008) -[2023-10-09 04:04:19,377][88326] Updated weights for policy 0, policy_version 97232 (0.0009) -[2023-10-09 04:04:19,750][88326] Updated weights for policy 0, policy_version 97242 (0.0008) -[2023-10-09 04:04:20,488][88327] Updated weights for policy 1, policy_version 97320 (0.0008) -[2023-10-09 04:04:20,851][88327] Updated weights for policy 1, policy_version 97330 (0.0011) -[2023-10-09 04:04:21,228][88327] Updated weights for policy 1, policy_version 97340 (0.0011) -[2023-10-09 04:04:23,870][88326] Updated weights for policy 0, policy_version 97252 (0.0009) -[2023-10-09 04:04:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.3, 300 sec: 13329.4). Total num frames: 199262208. Throughput: 0: 1696.4, 1: 1668.3. Samples: 49822170. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 04:04:23,975][87372] Avg episode reward: [(0, '6.730'), (1, '8.100')] -[2023-10-09 04:04:24,247][88326] Updated weights for policy 0, policy_version 97262 (0.0009) -[2023-10-09 04:04:24,617][88326] Updated weights for policy 0, policy_version 97272 (0.0009) -[2023-10-09 04:04:25,229][88327] Updated weights for policy 1, policy_version 97350 (0.0007) -[2023-10-09 04:04:25,585][88327] Updated weights for policy 1, policy_version 97360 (0.0009) -[2023-10-09 04:04:25,956][88327] Updated weights for policy 1, policy_version 97370 (0.0008) -[2023-10-09 04:04:28,769][88326] Updated weights for policy 0, policy_version 97282 (0.0011) -[2023-10-09 04:04:28,974][87372] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 199327744. Throughput: 0: 1711.6, 1: 1690.4. Samples: 49842496. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 04:04:28,974][87372] Avg episode reward: [(0, '6.670'), (1, '7.460')] -[2023-10-09 04:04:29,130][88326] Updated weights for policy 0, policy_version 97292 (0.0008) -[2023-10-09 04:04:29,507][88326] Updated weights for policy 0, policy_version 97302 (0.0007) -[2023-10-09 04:04:29,799][88327] Updated weights for policy 1, policy_version 97380 (0.0008) -[2023-10-09 04:04:29,867][88326] Updated weights for policy 0, policy_version 97312 (0.0007) -[2023-10-09 04:04:30,174][88327] Updated weights for policy 1, policy_version 97390 (0.0010) -[2023-10-09 04:04:30,533][88327] Updated weights for policy 1, policy_version 97400 (0.0009) -[2023-10-09 04:04:33,974][87372] Fps is (10 sec: 13106.8, 60 sec: 13107.1, 300 sec: 13329.4). Total num frames: 199393280. Throughput: 0: 1708.1, 1: 1697.0. Samples: 49863216. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 04:04:33,975][87372] Avg episode reward: [(0, '6.960'), (1, '7.620')] -[2023-10-09 04:04:33,987][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000097408_99745792.pth... -[2023-10-09 04:04:34,021][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000095872_98172928.pth -[2023-10-09 04:04:34,040][88326] Updated weights for policy 0, policy_version 97322 (0.0010) -[2023-10-09 04:04:34,410][88326] Updated weights for policy 0, policy_version 97332 (0.0008) -[2023-10-09 04:04:34,714][88327] Updated weights for policy 1, policy_version 97410 (0.0009) -[2023-10-09 04:04:34,786][88326] Updated weights for policy 0, policy_version 97342 (0.0008) -[2023-10-09 04:04:34,853][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000097344_99680256.pth... -[2023-10-09 04:04:34,883][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000095776_98074624.pth -[2023-10-09 04:04:35,071][88327] Updated weights for policy 1, policy_version 97420 (0.0009) -[2023-10-09 04:04:35,438][88327] Updated weights for policy 1, policy_version 97430 (0.0009) -[2023-10-09 04:04:35,806][88327] Updated weights for policy 1, policy_version 97440 (0.0007) -[2023-10-09 04:04:38,801][88326] Updated weights for policy 0, policy_version 97352 (0.0007) -[2023-10-09 04:04:38,974][87372] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 199458816. Throughput: 0: 1696.7, 1: 1674.0. Samples: 49872294. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 04:04:38,975][87372] Avg episode reward: [(0, '6.660'), (1, '8.580')] -[2023-10-09 04:04:39,179][88326] Updated weights for policy 0, policy_version 97362 (0.0009) -[2023-10-09 04:04:39,546][88326] Updated weights for policy 0, policy_version 97372 (0.0008) -[2023-10-09 04:04:39,876][88327] Updated weights for policy 1, policy_version 97450 (0.0009) -[2023-10-09 04:04:40,239][88327] Updated weights for policy 1, policy_version 97460 (0.0008) -[2023-10-09 04:04:40,612][88327] Updated weights for policy 1, policy_version 97470 (0.0007) -[2023-10-09 04:04:43,514][88326] Updated weights for policy 0, policy_version 97382 (0.0008) -[2023-10-09 04:04:43,892][88326] Updated weights for policy 0, policy_version 97392 (0.0009) -[2023-10-09 04:04:43,974][87372] Fps is (10 sec: 13107.5, 60 sec: 13107.3, 300 sec: 13329.4). Total num frames: 199524352. Throughput: 0: 1703.2, 1: 1693.4. Samples: 49893166. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 04:04:43,975][87372] Avg episode reward: [(0, '6.610'), (1, '8.050')] -[2023-10-09 04:04:44,252][88326] Updated weights for policy 0, policy_version 97402 (0.0008) -[2023-10-09 04:04:44,665][88327] Updated weights for policy 1, policy_version 97480 (0.0010) -[2023-10-09 04:04:45,019][88327] Updated weights for policy 1, policy_version 97490 (0.0007) -[2023-10-09 04:04:45,387][88327] Updated weights for policy 1, policy_version 97500 (0.0009) -[2023-10-09 04:04:48,334][88326] Updated weights for policy 0, policy_version 97412 (0.0009) -[2023-10-09 04:04:48,706][88326] Updated weights for policy 0, policy_version 97422 (0.0010) -[2023-10-09 04:04:48,974][87372] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 199589888. Throughput: 0: 1693.4, 1: 1690.1. Samples: 49913960. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 04:04:48,974][87372] Avg episode reward: [(0, '7.560'), (1, '7.970')] -[2023-10-09 04:04:49,074][88326] Updated weights for policy 0, policy_version 97432 (0.0010) -[2023-10-09 04:04:49,452][88327] Updated weights for policy 1, policy_version 97510 (0.0010) -[2023-10-09 04:04:49,812][88327] Updated weights for policy 1, policy_version 97520 (0.0009) -[2023-10-09 04:04:50,170][88327] Updated weights for policy 1, policy_version 97530 (0.0009) -[2023-10-09 04:04:53,333][88326] Updated weights for policy 0, policy_version 97442 (0.0008) -[2023-10-09 04:04:53,730][88326] Updated weights for policy 0, policy_version 97452 (0.0009) -[2023-10-09 04:04:53,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 199655424. Throughput: 0: 1696.8, 1: 1678.9. Samples: 49923070. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 04:04:53,975][87372] Avg episode reward: [(0, '7.660'), (1, '8.300')] -[2023-10-09 04:04:54,104][88326] Updated weights for policy 0, policy_version 97462 (0.0010) -[2023-10-09 04:04:54,182][88327] Updated weights for policy 1, policy_version 97540 (0.0010) -[2023-10-09 04:04:54,473][88326] Updated weights for policy 0, policy_version 97472 (0.0008) -[2023-10-09 04:04:54,539][88327] Updated weights for policy 1, policy_version 97550 (0.0008) -[2023-10-09 04:04:54,905][88327] Updated weights for policy 1, policy_version 97560 (0.0009) -[2023-10-09 04:04:58,432][88326] Updated weights for policy 0, policy_version 97482 (0.0011) -[2023-10-09 04:04:58,793][88326] Updated weights for policy 0, policy_version 97492 (0.0008) -[2023-10-09 04:04:58,944][88327] Updated weights for policy 1, policy_version 97570 (0.0009) -[2023-10-09 04:04:58,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 199720960. Throughput: 0: 1688.8, 1: 1691.3. Samples: 49943736. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 04:04:58,975][87372] Avg episode reward: [(0, '7.650'), (1, '8.280')] -[2023-10-09 04:04:59,168][88326] Updated weights for policy 0, policy_version 97502 (0.0008) -[2023-10-09 04:04:59,304][88327] Updated weights for policy 1, policy_version 97580 (0.0009) -[2023-10-09 04:04:59,677][88327] Updated weights for policy 1, policy_version 97590 (0.0008) -[2023-10-09 04:05:00,037][88327] Updated weights for policy 1, policy_version 97600 (0.0011) -[2023-10-09 04:05:03,129][88326] Updated weights for policy 0, policy_version 97512 (0.0010) -[2023-10-09 04:05:03,497][88326] Updated weights for policy 0, policy_version 97522 (0.0008) -[2023-10-09 04:05:03,870][88326] Updated weights for policy 0, policy_version 97532 (0.0007) -[2023-10-09 04:05:03,974][87372] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13329.4). Total num frames: 199786496. Throughput: 0: 1675.5, 1: 1693.1. Samples: 49964398. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 04:05:03,975][87372] Avg episode reward: [(0, '7.730'), (1, '7.220')] -[2023-10-09 04:05:04,159][88327] Updated weights for policy 1, policy_version 97610 (0.0008) -[2023-10-09 04:05:04,531][88327] Updated weights for policy 1, policy_version 97620 (0.0009) -[2023-10-09 04:05:04,892][88327] Updated weights for policy 1, policy_version 97630 (0.0009) -[2023-10-09 04:05:07,907][88326] Updated weights for policy 0, policy_version 97542 (0.0008) -[2023-10-09 04:05:08,283][88326] Updated weights for policy 0, policy_version 97552 (0.0008) -[2023-10-09 04:05:08,650][88326] Updated weights for policy 0, policy_version 97562 (0.0010) -[2023-10-09 04:05:08,960][88327] Updated weights for policy 1, policy_version 97640 (0.0010) -[2023-10-09 04:05:08,974][87372] Fps is (10 sec: 16383.8, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 199884800. Throughput: 0: 1685.7, 1: 1684.3. Samples: 49973822. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 04:05:08,975][87372] Avg episode reward: [(0, '7.460'), (1, '7.380')] -[2023-10-09 04:05:09,327][88327] Updated weights for policy 1, policy_version 97650 (0.0011) -[2023-10-09 04:05:09,695][88327] Updated weights for policy 1, policy_version 97660 (0.0009) -[2023-10-09 04:05:12,629][88326] Updated weights for policy 0, policy_version 97572 (0.0008) -[2023-10-09 04:05:12,998][88326] Updated weights for policy 0, policy_version 97582 (0.0009) -[2023-10-09 04:05:13,369][88326] Updated weights for policy 0, policy_version 97592 (0.0007) -[2023-10-09 04:05:13,635][88327] Updated weights for policy 1, policy_version 97670 (0.0008) -[2023-10-09 04:05:13,974][87372] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 199950336. Throughput: 0: 1692.3, 1: 1693.2. Samples: 49994846. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 04:05:13,975][87372] Avg episode reward: [(0, '7.400'), (1, '7.720')] -[2023-10-09 04:05:14,006][88327] Updated weights for policy 1, policy_version 97680 (0.0011) -[2023-10-09 04:05:14,378][88327] Updated weights for policy 1, policy_version 97690 (0.0009) -[2023-10-09 04:05:17,479][88326] Updated weights for policy 0, policy_version 97602 (0.0009) -[2023-10-09 04:05:17,842][88326] Updated weights for policy 0, policy_version 97612 (0.0009) -[2023-10-09 04:05:18,214][88326] Updated weights for policy 0, policy_version 97622 (0.0010) -[2023-10-09 04:05:18,383][88327] Updated weights for policy 1, policy_version 97700 (0.0007) -[2023-10-09 04:05:18,588][88326] Updated weights for policy 0, policy_version 97632 (0.0007) -[2023-10-09 04:05:18,749][88327] Updated weights for policy 1, policy_version 97710 (0.0008) -[2023-10-09 04:05:18,974][87372] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 13440.4). Total num frames: 200015872. Throughput: 0: 1677.8, 1: 1692.8. Samples: 50014890. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 04:05:18,975][87372] Avg episode reward: [(0, '7.300'), (1, '7.720')] -[2023-10-09 04:05:19,109][88327] Updated weights for policy 1, policy_version 97720 (0.0010) -[2023-10-09 04:05:22,849][88326] Updated weights for policy 0, policy_version 97642 (0.0010) -[2023-10-09 04:05:23,213][88327] Updated weights for policy 1, policy_version 97730 (0.0008) -[2023-10-09 04:05:23,214][88326] Updated weights for policy 0, policy_version 97652 (0.0008) -[2023-10-09 04:05:23,581][88326] Updated weights for policy 0, policy_version 97662 (0.0007) -[2023-10-09 04:05:23,581][88327] Updated weights for policy 1, policy_version 97740 (0.0009) -[2023-10-09 04:05:23,951][88327] Updated weights for policy 1, policy_version 97750 (0.0009) -[2023-10-09 04:05:23,974][87372] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13440.4). Total num frames: 200081408. Throughput: 0: 1691.9, 1: 1691.3. Samples: 50024536. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-09 04:05:23,975][87372] Avg episode reward: [(0, '7.000'), (1, '8.130')] -[2023-10-09 04:05:24,321][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000097760_100106240.pth... -[2023-10-09 04:05:24,321][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000097664_100007936.pth... -[2023-10-09 04:05:24,321][88373] Stopping RolloutWorker_w13... -[2023-10-09 04:05:24,321][88371] Stopping RolloutWorker_w9... -[2023-10-09 04:05:24,321][88368] Stopping RolloutWorker_w8... -[2023-10-09 04:05:24,321][89058] Stopping RolloutWorker_w14... -[2023-10-09 04:05:24,321][88367] Stopping RolloutWorker_w7... -[2023-10-09 04:05:24,322][88373] Loop rollout_proc13_evt_loop terminating... -[2023-10-09 04:05:24,321][88372] Stopping RolloutWorker_w12... -[2023-10-09 04:05:24,322][88371] Loop rollout_proc9_evt_loop terminating... -[2023-10-09 04:05:24,322][88364] Stopping RolloutWorker_w5... -[2023-10-09 04:05:24,322][88368] Loop rollout_proc8_evt_loop terminating... -[2023-10-09 04:05:24,322][88362] Stopping RolloutWorker_w2... -[2023-10-09 04:05:24,322][88367] Loop rollout_proc7_evt_loop terminating... -[2023-10-09 04:05:24,322][89058] Loop rollout_proc14_evt_loop terminating... -[2023-10-09 04:05:24,322][88364] Loop rollout_proc5_evt_loop terminating... -[2023-10-09 04:05:24,322][88372] Loop rollout_proc12_evt_loop terminating... -[2023-10-09 04:05:24,322][88362] Loop rollout_proc2_evt_loop terminating... -[2023-10-09 04:05:24,322][88327] Updated weights for policy 1, policy_version 97760 (0.0009) -[2023-10-09 04:05:24,322][88359] Stopping RolloutWorker_w0... -[2023-10-09 04:05:24,322][88363] Stopping RolloutWorker_w3... -[2023-10-09 04:05:24,322][87372] Component RolloutWorker_w13 stopped! -[2023-10-09 04:05:24,323][88363] Loop rollout_proc3_evt_loop terminating... -[2023-10-09 04:05:24,323][88370] Stopping RolloutWorker_w11... -[2023-10-09 04:05:24,323][88359] Loop rollout_proc0_evt_loop terminating... -[2023-10-09 04:05:24,323][88370] Loop rollout_proc11_evt_loop terminating... -[2023-10-09 04:05:24,323][87372] Component RolloutWorker_w9 stopped! -[2023-10-09 04:05:24,324][87372] Component RolloutWorker_w14 stopped! -[2023-10-09 04:05:24,326][88366] Stopping RolloutWorker_w6... -[2023-10-09 04:05:24,326][89096] Stopping RolloutWorker_w15... -[2023-10-09 04:05:24,326][87372] Component RolloutWorker_w7 stopped! -[2023-10-09 04:05:24,326][88366] Loop rollout_proc6_evt_loop terminating... -[2023-10-09 04:05:24,326][88360] Stopping RolloutWorker_w1... -[2023-10-09 04:05:24,326][88369] Stopping RolloutWorker_w10... -[2023-10-09 04:05:24,326][89096] Loop rollout_proc15_evt_loop terminating... -[2023-10-09 04:05:24,327][88360] Loop rollout_proc1_evt_loop terminating... -[2023-10-09 04:05:24,327][88369] Loop rollout_proc10_evt_loop terminating... -[2023-10-09 04:05:24,327][87372] Component RolloutWorker_w8 stopped! -[2023-10-09 04:05:24,328][87372] Component RolloutWorker_w12 stopped! -[2023-10-09 04:05:24,329][87372] Component RolloutWorker_w5 stopped! -[2023-10-09 04:05:24,330][87372] Component RolloutWorker_w2 stopped! -[2023-10-09 04:05:24,330][87372] Component RolloutWorker_w0 stopped! -[2023-10-09 04:05:24,330][87372] Component RolloutWorker_w3 stopped! -[2023-10-09 04:05:24,331][87372] Component RolloutWorker_w11 stopped! -[2023-10-09 04:05:24,331][87372] Component RolloutWorker_w6 stopped! -[2023-10-09 04:05:24,331][87372] Component RolloutWorker_w15 stopped! -[2023-10-09 04:05:24,332][87372] Component RolloutWorker_w1 stopped! -[2023-10-09 04:05:24,332][87372] Component RolloutWorker_w10 stopped! -[2023-10-09 04:05:24,333][88365] Stopping RolloutWorker_w4... -[2023-10-09 04:05:24,333][87372] Component Batcher_1 stopped! -[2023-10-09 04:05:24,334][88365] Loop rollout_proc4_evt_loop terminating... -[2023-10-09 04:05:24,334][87372] Component RolloutWorker_w4 stopped! -[2023-10-09 04:05:24,334][87372] Component Batcher_0 stopped! -[2023-10-09 04:05:24,340][88326] Weights refcount: 2 0 -[2023-10-09 04:05:24,342][88326] Stopping InferenceWorker_p0-w0... -[2023-10-09 04:05:24,342][88326] Loop inference_proc0-0_evt_loop terminating... -[2023-10-09 04:05:24,342][87372] Component InferenceWorker_p0-w0 stopped! -[2023-10-09 04:05:24,334][88088] Stopping Batcher_0... -[2023-10-09 04:05:24,343][88168] Stopping Batcher_1... -[2023-10-09 04:05:24,354][88327] Weights refcount: 2 0 -[2023-10-09 04:05:24,354][88168] Loop batcher_evt_loop terminating... -[2023-10-09 04:05:24,354][88168] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000096640_98959360.pth -[2023-10-09 04:05:24,355][88327] Stopping InferenceWorker_p1-w0... -[2023-10-09 04:05:24,356][88327] Loop inference_proc1-0_evt_loop terminating... -[2023-10-09 04:05:24,355][87372] Component InferenceWorker_p1-w0 stopped! -[2023-10-09 04:05:24,360][88168] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p1/checkpoint_000097760_100106240.pth... -[2023-10-09 04:05:24,359][88088] Loop batcher_evt_loop terminating... -[2023-10-09 04:05:24,362][88088] Removing ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000096544_98861056.pth -[2023-10-09 04:05:24,367][88088] Saving ./train_atari/atari_battlezone_APPO/checkpoint_p0/checkpoint_000097664_100007936.pth... -[2023-10-09 04:05:24,414][88168] Stopping LearnerWorker_p1... -[2023-10-09 04:05:24,414][88168] Loop learner_proc1_evt_loop terminating... -[2023-10-09 04:05:24,414][87372] Component LearnerWorker_p1 stopped! -[2023-10-09 04:05:24,421][88088] Stopping LearnerWorker_p0... -[2023-10-09 04:05:24,422][88088] Loop learner_proc0_evt_loop terminating... -[2023-10-09 04:05:24,421][87372] Component LearnerWorker_p0 stopped! -[2023-10-09 04:05:24,422][87372] Waiting for process learner_proc0 to stop... -[2023-10-09 04:05:25,291][87372] Waiting for process learner_proc1 to stop... -[2023-10-09 04:05:25,338][87372] Waiting for process inference_proc0-0 to join... -[2023-10-09 04:05:25,339][87372] Waiting for process inference_proc1-0 to join... -[2023-10-09 04:05:25,339][87372] Waiting for process rollout_proc0 to join... -[2023-10-09 04:05:25,340][87372] Waiting for process rollout_proc1 to join... -[2023-10-09 04:05:25,341][87372] Waiting for process rollout_proc2 to join... -[2023-10-09 04:05:25,341][87372] Waiting for process rollout_proc3 to join... -[2023-10-09 04:05:25,342][87372] Waiting for process rollout_proc4 to join... -[2023-10-09 04:05:25,343][87372] Waiting for process rollout_proc5 to join... -[2023-10-09 04:05:25,343][87372] Waiting for process rollout_proc6 to join... -[2023-10-09 04:05:25,344][87372] Waiting for process rollout_proc7 to join... -[2023-10-09 04:05:25,345][87372] Waiting for process rollout_proc8 to join... -[2023-10-09 04:05:25,345][87372] Waiting for process rollout_proc9 to join... -[2023-10-09 04:05:25,346][87372] Waiting for process rollout_proc10 to join... -[2023-10-09 04:05:25,347][87372] Waiting for process rollout_proc11 to join... -[2023-10-09 04:05:25,347][87372] Waiting for process rollout_proc12 to join... -[2023-10-09 04:05:25,348][87372] Waiting for process rollout_proc13 to join... -[2023-10-09 04:05:25,349][87372] Waiting for process rollout_proc14 to join... -[2023-10-09 04:05:25,349][87372] Waiting for process rollout_proc15 to join... -[2023-10-09 04:05:25,350][87372] Batcher 0 profile tree view: -batching: 170.9793, releasing_batches: 0.0882 -[2023-10-09 04:05:25,350][87372] Batcher 1 profile tree view: -batching: 171.4116, releasing_batches: 0.0903 -[2023-10-09 04:05:25,350][87372] InferenceWorker_p0-w0 profile tree view: -wait_policy: 0.0000 - wait_policy_total: 2606.7281 -update_model: 207.8673 - weight_update: 0.0007 -one_step: 0.0017 - handle_policy_step: 11304.1831 - deserialize: 63.9268, stack: 195.2796, obs_to_device_normalize: 2511.4658, forward: 5128.1684, prepare_outputs: 2442.6910, send_messages: 460.9053 -[2023-10-09 04:05:25,351][87372] InferenceWorker_p1-w0 profile tree view: -wait_policy: 0.0001 - wait_policy_total: 2606.9388 -update_model: 201.6727 - weight_update: 0.0009 -one_step: 0.0032 - handle_policy_step: 11284.7328 - deserialize: 63.4394, stack: 193.0934, obs_to_device_normalize: 2522.6873, forward: 5097.2209, prepare_outputs: 2430.7249, send_messages: 478.9736 -[2023-10-09 04:05:25,351][87372] Learner 0 profile tree view: -misc: 0.0178, prepare_batch: 260.8811 -train: 3621.5035 - epoch_init: 0.1892, minibatch_init: 13.2894, losses_postprocess: 886.3390, kl_divergence: 32.3832, update: 392.3542, after_optimizer: 2111.2958 - calculate_losses: 168.7430 - losses_init: 0.4147, forward_head: 56.7750, bptt_initial: 1.4458, bptt: 1.8384, tail: 38.4470, advantages_returns: 11.3571, losses: 44.5066 -[2023-10-09 04:05:25,351][87372] Learner 1 profile tree view: -misc: 0.0182, prepare_batch: 260.7179 -train: 3592.1974 - epoch_init: 0.1874, minibatch_init: 13.0634, losses_postprocess: 885.1269, kl_divergence: 31.7114, update: 385.7576, after_optimizer: 2092.1593 - calculate_losses: 167.3328 - losses_init: 0.3858, forward_head: 55.7610, bptt_initial: 1.4129, bptt: 1.7831, tail: 38.7275, advantages_returns: 11.2622, losses: 44.2923 -[2023-10-09 04:05:25,351][87372] RolloutWorker_w0 profile tree view: -wait_for_trajectories: 1.2380, enqueue_policy_requests: 403.8793, process_policy_outputs: 194.1812, env_step: 7574.1876, finalize_trajectories: 3.4620, complete_rollouts: 2.8850 -post_env_step: 380.3331 - process_env_step: 86.2391 -[2023-10-09 04:05:25,352][87372] RolloutWorker_w15 profile tree view: -wait_for_trajectories: 1.2494, enqueue_policy_requests: 411.3151, process_policy_outputs: 192.8648, env_step: 7519.3949, finalize_trajectories: 3.5639, complete_rollouts: 2.8960 -post_env_step: 379.9174 - process_env_step: 84.5949 -[2023-10-09 04:05:25,353][87372] Loop Runner_EvtLoop terminating... -[2023-10-09 04:05:25,353][87372] Runner profile tree view: -main_loop: 14806.8216 -[2023-10-09 04:05:25,353][87372] Collected {0: 100007936, 1: 100106240}, FPS: 13515.0 +version https://git-lfs.github.com/spec/v1 +oid sha256:c2d9ce2b46d9279774afac868145bafb7cacec3afdacd8d15e5f2be6e9e391e9 +size 49299689