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.1702513428.rhmmedcatt-proliant-ml350-gen10 b/.summary/0/events.out.tfevents.1702513428.rhmmedcatt-proliant-ml350-gen10 new file mode 100644 index 0000000000000000000000000000000000000000..a352c6f3cecaef0a5ff123dc907da81b5fdc6aed --- /dev/null +++ b/.summary/0/events.out.tfevents.1702513428.rhmmedcatt-proliant-ml350-gen10 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:459a32fa052fbc1b7ef7de5bfd0d4964b2e41cb89905f6754c1ea4d87211c9f7 +size 85718318 diff --git a/.summary/1/events.out.tfevents.1702513428.rhmmedcatt-proliant-ml350-gen10 b/.summary/1/events.out.tfevents.1702513428.rhmmedcatt-proliant-ml350-gen10 new file mode 100644 index 0000000000000000000000000000000000000000..4fb63a299036ddb5ca07c2cdcfe3dd5ccc3a03a9 --- /dev/null +++ b/.summary/1/events.out.tfevents.1702513428.rhmmedcatt-proliant-ml350-gen10 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3cb015724c9597fd2985e88f4dc8c002474f5ccf29d9b6d034cef34c9adba5f +size 45030587 diff --git a/README.md b/README.md index 36d623a52c1aba90505601ece38da0bebf4ee23b..f026c3457fc7a3513c0029e8bbad6b5617b010a6 100644 --- a/README.md +++ b/README.md @@ -15,35 +15,39 @@ model-index: type: atari_wizardofwor metrics: - type: mean_reward - value: 13670.00 +/- 8376.40 + value: 53850.00 +/- 11044.21 name: mean_reward verified: false --- -A(n) **APPO** model trained on the **atari_wizardofwor** 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_wizardofwor -``` +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_wizardofwor** 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_wizardofwor +``` + + ## Using the model To run the model after download, use the `enjoy` script corresponding to this environment: diff --git a/checkpoint_p0/best_001860256_476225536_reward_33.130.pth b/checkpoint_p0/best_001860256_476225536_reward_33.130.pth new file mode 100644 index 0000000000000000000000000000000000000000..a407ed33278e0921fbdb3fb954b3937d4869c1d5 --- /dev/null +++ b/checkpoint_p0/best_001860256_476225536_reward_33.130.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:221d059feb7e6f4e281fbceab368e5049575d74349c131dc8eaf4e0575692682 +size 20746419 diff --git a/checkpoint_p0/checkpoint_001951904_499687424.pth b/checkpoint_p0/checkpoint_001951904_499687424.pth new file mode 100644 index 0000000000000000000000000000000000000000..51b06baa6fd4dc8123fdc4554229a7f6061a26a8 --- /dev/null +++ b/checkpoint_p0/checkpoint_001951904_499687424.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f6fd168fc335099f5f6d25b767f508c29f390da25b76946bf112cc9b4b5da73 +size 20746755 diff --git a/checkpoint_p0/checkpoint_001953120_500006912.pth b/checkpoint_p0/checkpoint_001953120_500006912.pth new file mode 100644 index 0000000000000000000000000000000000000000..f3499880cd542230ebe1384a77b1e67a497faa95 --- /dev/null +++ b/checkpoint_p0/checkpoint_001953120_500006912.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfa07a876fdada8729fd56f275128e8331267d64fbd43a0d89a1ef6b2f6d83b3 +size 20746755 diff --git a/checkpoint_p0/milestones/checkpoint_000013024_3334144.pth b/checkpoint_p0/milestones/checkpoint_000013024_3334144.pth new file mode 100644 index 0000000000000000000000000000000000000000..f7252366c772f96d6df63dd620ea375d75ca3784 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000013024_3334144.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54c40df58b4a04da0080041e041d17c6cfa72af94299486c16e33a4b729991df +size 20747611 diff --git a/checkpoint_p0/milestones/checkpoint_000026400_6758400.pth b/checkpoint_p0/milestones/checkpoint_000026400_6758400.pth new file mode 100644 index 0000000000000000000000000000000000000000..2e7b0827d4749c5c54cdea78644e3ff4bb0a961b --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000026400_6758400.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:105bffde17046ed650eb49864e32df323d9809ed893634206a2b7c6f68cce0ae +size 20747611 diff --git a/checkpoint_p0/milestones/checkpoint_000039808_10190848.pth b/checkpoint_p0/milestones/checkpoint_000039808_10190848.pth new file mode 100644 index 0000000000000000000000000000000000000000..0b75c38197511c9207b9a98c48e80cff6c26d359 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000039808_10190848.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3796f3aad7a94c8bb394f850b676cbc53d995a22ae9ddf966545c74eee8cfc9d +size 20747667 diff --git a/checkpoint_p0/milestones/checkpoint_000053184_13615104.pth b/checkpoint_p0/milestones/checkpoint_000053184_13615104.pth new file mode 100644 index 0000000000000000000000000000000000000000..099b8330aff3c579dab2c2bf83bda3dae90d796e --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000053184_13615104.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef878d5e8b1ff6b90ab2710d01c5e156a36c0377865f17643c64376802d973b0 +size 20747667 diff --git a/checkpoint_p0/milestones/checkpoint_000066592_17047552.pth b/checkpoint_p0/milestones/checkpoint_000066592_17047552.pth new file mode 100644 index 0000000000000000000000000000000000000000..e1de9ee7c44d50ad13f9e18c40031a310463d1b1 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000066592_17047552.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f958f2ceb363d1f2bcdef35bc8321aac6df7c1aa12f27da67fe97fa59dbd435b +size 20747667 diff --git a/checkpoint_p0/milestones/checkpoint_000079968_20471808.pth b/checkpoint_p0/milestones/checkpoint_000079968_20471808.pth new file mode 100644 index 0000000000000000000000000000000000000000..c8217c454c3246c2a08a87d06cb87074121a1b54 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000079968_20471808.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd0d4d230c7c9e340bab8adedca1b84cb42ff81d510c0dd4516a28ef46528451 +size 20747667 diff --git a/checkpoint_p0/milestones/checkpoint_000093440_23920640.pth b/checkpoint_p0/milestones/checkpoint_000093440_23920640.pth new file mode 100644 index 0000000000000000000000000000000000000000..53abfa3eb67222265bebf8e1c5cbb4b172d408f8 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000093440_23920640.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3a9350f1b8db7cec779604584a51bef81e73e45b2a6be9d7e01907ca566d77d +size 20747667 diff --git a/checkpoint_p0/milestones/checkpoint_000106848_27353088.pth b/checkpoint_p0/milestones/checkpoint_000106848_27353088.pth new file mode 100644 index 0000000000000000000000000000000000000000..a6eb675341337e3bacc6bd18b73d1e4ced4be77b --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000106848_27353088.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d32cc2b94d4f9989f52cf9211ad90569b0c33d6600ea80da355e4e317288ae56 +size 20747667 diff --git a/checkpoint_p0/milestones/checkpoint_000120288_30793728.pth b/checkpoint_p0/milestones/checkpoint_000120288_30793728.pth new file mode 100644 index 0000000000000000000000000000000000000000..aae6fd094e05cb29a4bad32431a1e2074ea5862d --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000120288_30793728.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3dad62e5aa6543d4450529c36b3b34d7a41064749a9e156c6aa4defcc24bbff5 +size 20747667 diff --git a/checkpoint_p0/milestones/checkpoint_000133728_34234368.pth b/checkpoint_p0/milestones/checkpoint_000133728_34234368.pth new file mode 100644 index 0000000000000000000000000000000000000000..8d6f7b0de6a2591e192bd236ee410fdd7d696a17 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000133728_34234368.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59e92648030ea364d8ad8cd2e1aa1387e49e4494e508fffd882d5203e0b0cf65 +size 20747667 diff --git a/checkpoint_p0/milestones/checkpoint_000147136_37666816.pth b/checkpoint_p0/milestones/checkpoint_000147136_37666816.pth new file mode 100644 index 0000000000000000000000000000000000000000..141864b70ed2e4721f894b26850c2869a579f4d8 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000147136_37666816.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:703dc18959731edc9038fb0c6a1e8ae6d4464c0e6e394b54b1e961add3a73680 +size 20747667 diff --git a/checkpoint_p0/milestones/checkpoint_000160576_41107456.pth b/checkpoint_p0/milestones/checkpoint_000160576_41107456.pth new file mode 100644 index 0000000000000000000000000000000000000000..7aa4cbb4497c8db32b126aca394dd69fe92f9f4d --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000160576_41107456.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4718b0f7808c6c85ab80c9ef755c0bbbb03acc70657837840b294e5a4f431523 +size 20747667 diff --git a/checkpoint_p0/milestones/checkpoint_000174048_44556288.pth b/checkpoint_p0/milestones/checkpoint_000174048_44556288.pth new file mode 100644 index 0000000000000000000000000000000000000000..494c9228d4a0b788615b738c809dd97bceb8bf20 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000174048_44556288.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:665abe9fc9f8b4a65c9be00895f75864df010183ee1856117d5e11da988d4428 +size 20747667 diff --git a/checkpoint_p0/milestones/checkpoint_000187488_47996928.pth b/checkpoint_p0/milestones/checkpoint_000187488_47996928.pth new file mode 100644 index 0000000000000000000000000000000000000000..f800dc46c67fab530a422bbdc9e7ffa6879c68cc --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000187488_47996928.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d80d656ed00b97b436d8fa3c9c4dc3394a15a09a23b8e0fe5bcf3747a78d3d70 +size 20747667 diff --git a/checkpoint_p0/milestones/checkpoint_000200896_51429376.pth b/checkpoint_p0/milestones/checkpoint_000200896_51429376.pth new file mode 100644 index 0000000000000000000000000000000000000000..06f1aaa1ea462331477181d1809bb34e230c1cc5 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000200896_51429376.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38067b0afd82828638b3646af7add02a69f0afb3d0ef5ea05c96ca014c4695f7 +size 20747667 diff --git a/checkpoint_p0/milestones/checkpoint_000214368_54878208.pth b/checkpoint_p0/milestones/checkpoint_000214368_54878208.pth new file mode 100644 index 0000000000000000000000000000000000000000..6fa91cec8977c2d16c7648911fd3630c1f9d09df --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000214368_54878208.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2b2af0edad99deed7996a5c327744709f8dbdfbc21e631b3a9ad99eb69c68c3 +size 20747667 diff --git a/checkpoint_p0/milestones/checkpoint_000227872_58335232.pth b/checkpoint_p0/milestones/checkpoint_000227872_58335232.pth new file mode 100644 index 0000000000000000000000000000000000000000..7129ea2d3fc55c641b53b9f3beb1af669d91215d --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000227872_58335232.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:662e873252108e0092faf2b16ec2c56473a076a9cee64dbbc430e166d601d109 +size 20747667 diff --git a/checkpoint_p0/milestones/checkpoint_000241120_61726720.pth b/checkpoint_p0/milestones/checkpoint_000241120_61726720.pth new file mode 100644 index 0000000000000000000000000000000000000000..72a14726b9b9ae41f169e90abb93e35b44a96967 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000241120_61726720.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e23360b791bdc5b74453faabeccc9c7e1be34f8f54a64d33f55447b2acb17071 +size 20747667 diff --git a/checkpoint_p0/milestones/checkpoint_000254592_65175552.pth b/checkpoint_p0/milestones/checkpoint_000254592_65175552.pth new file mode 100644 index 0000000000000000000000000000000000000000..09394769edb25e23f9d716e05a0fef88f46a55b4 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000254592_65175552.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30c91b3669817b78477509ce344dd69dfedb430f29ed6773d135b21f86fa4096 +size 20747667 diff --git a/checkpoint_p0/milestones/checkpoint_000268032_68616192.pth b/checkpoint_p0/milestones/checkpoint_000268032_68616192.pth new file mode 100644 index 0000000000000000000000000000000000000000..f3b5869f3ba41c0740a6f5c7c5e847286d364cad --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000268032_68616192.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e7430dffcaa4f0e79e123ca43f200949ac6809e182649167397d478f424c0a6 +size 20747667 diff --git a/checkpoint_p0/milestones/checkpoint_000281504_72065024.pth b/checkpoint_p0/milestones/checkpoint_000281504_72065024.pth new file mode 100644 index 0000000000000000000000000000000000000000..93d572c8e0f0d10645bc8c27bb50e4cd7c64ce83 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000281504_72065024.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3773b6169259501cf34cc57ed5ea2058de1d93282f4142532aecb23d0ca69647 +size 20747667 diff --git a/checkpoint_p0/milestones/checkpoint_000294880_75489280.pth b/checkpoint_p0/milestones/checkpoint_000294880_75489280.pth new file mode 100644 index 0000000000000000000000000000000000000000..0cf0ca518a9b3e1599c5536f539c8184ada24b9d --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000294880_75489280.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68838fb23d5f6c1c238939fc9be936a6c06d31d9e5c88ebe479419fe6fd4c2d6 +size 20747667 diff --git a/checkpoint_p0/milestones/checkpoint_000308320_78929920.pth b/checkpoint_p0/milestones/checkpoint_000308320_78929920.pth new file mode 100644 index 0000000000000000000000000000000000000000..de95c31e2872d09e6bba339d01df487339d69aaf --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000308320_78929920.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f17c766da2d3a2fd83792c473776a292ccd7d1eee8b7d1d775694aa45e6a4ece +size 20747667 diff --git a/checkpoint_p0/milestones/checkpoint_000321760_82370560.pth b/checkpoint_p0/milestones/checkpoint_000321760_82370560.pth new file mode 100644 index 0000000000000000000000000000000000000000..d5f10e657301ae4cd8538e657c91fd9edcc2e6c8 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000321760_82370560.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca35e64ba6a7c804baf135530b47239250113a393cfebd8d80476cbbfadbb8ba +size 20747667 diff --git a/checkpoint_p0/milestones/checkpoint_000335200_85811200.pth b/checkpoint_p0/milestones/checkpoint_000335200_85811200.pth new file mode 100644 index 0000000000000000000000000000000000000000..e54695a25cff95b39bfeb557a2232a91798778cb --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000335200_85811200.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db14f0af8644a709f29d9a9a934e2238e0385f8514701a46e2f758fda6786c92 +size 20747667 diff --git a/checkpoint_p0/milestones/checkpoint_000348608_89243648.pth b/checkpoint_p0/milestones/checkpoint_000348608_89243648.pth new file mode 100644 index 0000000000000000000000000000000000000000..70c15e202322fb64a828ebbdc4861532db32aca3 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000348608_89243648.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a25ad8aa46aeaceb498b2df4de5b3289ae533bed242226bce8ac8b6cede1ffd5 +size 20747667 diff --git a/checkpoint_p0/milestones/checkpoint_000362016_92676096.pth b/checkpoint_p0/milestones/checkpoint_000362016_92676096.pth new file mode 100644 index 0000000000000000000000000000000000000000..266bf135315a4fce0b8166f1daeccbc6f3f566fc --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000362016_92676096.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c71bf3489264ab439681d603a8feae7f9aa2da5cb2aa62530f6eb564522d7e7 +size 20747667 diff --git a/checkpoint_p0/milestones/checkpoint_000375424_96108544.pth b/checkpoint_p0/milestones/checkpoint_000375424_96108544.pth new file mode 100644 index 0000000000000000000000000000000000000000..7f63bf36d43d3eb706266965695abf9e041b62a3 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000375424_96108544.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e747792dfe8b1dab18b84015ccc06a04ac62bcb1b6d70fd315c20787933aa05 +size 20747667 diff --git a/checkpoint_p0/milestones/checkpoint_000388736_99516416.pth b/checkpoint_p0/milestones/checkpoint_000388736_99516416.pth new file mode 100644 index 0000000000000000000000000000000000000000..353b89c6d6fd5bc63183ebdf33dc65feaaee8bb0 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000388736_99516416.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:314c2a84b369f7c5cfcc76c5439da2b8a163aa2ea95d9770f662d184311429ba +size 20747667 diff --git a/checkpoint_p0/milestones/checkpoint_000401984_102907904.pth b/checkpoint_p0/milestones/checkpoint_000401984_102907904.pth new file mode 100644 index 0000000000000000000000000000000000000000..45edd7916a512bbc70537c0a4f0fb4bb48d6bd6b --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000401984_102907904.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c11fa4eb41b051f56126421327375d4e7a5330a0c3fef679cc64b02278689c4 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000415328_106323968.pth b/checkpoint_p0/milestones/checkpoint_000415328_106323968.pth new file mode 100644 index 0000000000000000000000000000000000000000..3aaf1fb5432b6f7e7e344d3a225b4acf8de24ba8 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000415328_106323968.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d749d442da69d454d6bce4459e716bc8c7ff5d7fd10ec4a3711af698c96ee5a +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000428608_109723648.pth b/checkpoint_p0/milestones/checkpoint_000428608_109723648.pth new file mode 100644 index 0000000000000000000000000000000000000000..c0939aef5d03ab4fd27fba57ba3a4fe731d71f32 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000428608_109723648.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2b2c3a1ca637a69b7d1637fc370c4701d10a296c7e69d5e864bb244d135a7e1 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000441920_113131520.pth b/checkpoint_p0/milestones/checkpoint_000441920_113131520.pth new file mode 100644 index 0000000000000000000000000000000000000000..e615a52f6cc02f07fadd6644a6f6de08826f96bb --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000441920_113131520.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c5e650db3ac3520f99e68619993c0a55203a64d77c9c7d14cc44d450dec6a6f +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000455232_116539392.pth b/checkpoint_p0/milestones/checkpoint_000455232_116539392.pth new file mode 100644 index 0000000000000000000000000000000000000000..80dc7d8d3877bd180b4dcb3da00fdb564f3544d4 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000455232_116539392.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4ce30827ba88e3e85fb5ebe0f0ad169c009a317f60bcf85b3b3c4c69f4c46aa +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000468512_119939072.pth b/checkpoint_p0/milestones/checkpoint_000468512_119939072.pth new file mode 100644 index 0000000000000000000000000000000000000000..157d0b2c85a33e32bc08dcc1b021a266c9b97153 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000468512_119939072.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5be180855c31989a0de3b47650882c2700d9774bfc83180bbb4d8400eaf63815 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000481792_123338752.pth b/checkpoint_p0/milestones/checkpoint_000481792_123338752.pth new file mode 100644 index 0000000000000000000000000000000000000000..799b0b6b19679251f4082bcd5c7d17a5bc52fb0d --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000481792_123338752.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:667ef3dc27ae80f55b303a3e3f4a792827b6be7a2fef8d26d6611c4151738187 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000495040_126730240.pth b/checkpoint_p0/milestones/checkpoint_000495040_126730240.pth new file mode 100644 index 0000000000000000000000000000000000000000..8a39c63eb3231bbbe013d71fe488d6051a0a3879 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000495040_126730240.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67f483dd413e976dde015f0aa3de0641051ffb0519b7f2a72f9eb6c51571fe08 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000508192_130097152.pth b/checkpoint_p0/milestones/checkpoint_000508192_130097152.pth new file mode 100644 index 0000000000000000000000000000000000000000..ee4849b32ef0e24218f25fb9a2174a87f330827a --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000508192_130097152.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c61cbc1373888a875f4d6b5139e0044513f4d0e1ad8274df5ab43bf6f7d74bfb +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000521440_133488640.pth b/checkpoint_p0/milestones/checkpoint_000521440_133488640.pth new file mode 100644 index 0000000000000000000000000000000000000000..3d0b43bd007f12ed199f9c1d896ed26a3c7af2c6 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000521440_133488640.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02041a562535b52a7c6bc732d7ed87873cff145b6fafd415e069647ce2c9fecb +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000534688_136880128.pth b/checkpoint_p0/milestones/checkpoint_000534688_136880128.pth new file mode 100644 index 0000000000000000000000000000000000000000..eb4bfcb755600b1260011c21ddc13a554d77e17c --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000534688_136880128.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2d74c5f9cb455fe6c6f034fba21383bc5ab910079688ea33df28a6d0f9dacde +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000547968_140279808.pth b/checkpoint_p0/milestones/checkpoint_000547968_140279808.pth new file mode 100644 index 0000000000000000000000000000000000000000..1b02c79367d059508a1053f15a3e8371a58332d8 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000547968_140279808.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a52891dd3911becc872586d7db32651049d2412a05ba790dd2cb27c0ab05f4fc +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000561248_143679488.pth b/checkpoint_p0/milestones/checkpoint_000561248_143679488.pth new file mode 100644 index 0000000000000000000000000000000000000000..2032b137de7123e55c52ae1ea00522f43097845f --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000561248_143679488.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36ae46b83b4a9fa0c4c6aabe30d087ea063804636c9777ded31f8bfc2c872e90 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000574560_147087360.pth b/checkpoint_p0/milestones/checkpoint_000574560_147087360.pth new file mode 100644 index 0000000000000000000000000000000000000000..75001736997bc3eb3c58459d81bfa2d0b7002b7f --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000574560_147087360.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:602e61b63ea5351999248dc21dd83cac6d1baad746df293e3b266f663215550f +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000587840_150487040.pth b/checkpoint_p0/milestones/checkpoint_000587840_150487040.pth new file mode 100644 index 0000000000000000000000000000000000000000..2648aa2c1d696810a326c2c9193682ea4346c2a5 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000587840_150487040.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42bdbf667171f0b297b863cbb1f9e55b014fb86ae8ac0e2339663f69cd8b3f0f +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000601152_153894912.pth b/checkpoint_p0/milestones/checkpoint_000601152_153894912.pth new file mode 100644 index 0000000000000000000000000000000000000000..6dad96aa82fc1bee96facecc8819584478d905f2 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000601152_153894912.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:452118bb218ddf697c06941c5a82be89d16e5babb9aaec5817e7fe7083d0c8cf +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000614400_157286400.pth b/checkpoint_p0/milestones/checkpoint_000614400_157286400.pth new file mode 100644 index 0000000000000000000000000000000000000000..d3e11bdfda82a0ae634254e75da53b66b159dddf --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000614400_157286400.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61be7b6fe97e04aff7b07cfe83d5dc7038e2ec31da9f45eb200915bf7903597c +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000627776_160710656.pth b/checkpoint_p0/milestones/checkpoint_000627776_160710656.pth new file mode 100644 index 0000000000000000000000000000000000000000..4112d4bcbbec60d3b3318edb7ccb714a95e072d1 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000627776_160710656.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88bac445e7da618dd26683fec26b820b97cdcd03b6ef7d2e8eb6284cde8e71b9 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000641088_164118528.pth b/checkpoint_p0/milestones/checkpoint_000641088_164118528.pth new file mode 100644 index 0000000000000000000000000000000000000000..d375a1b516b3405dbd19b383021cc69e0215da1e --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000641088_164118528.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e32dfbb42e85503de92f31cf0e174ea7471b342995b54e58a95375ab398ccd83 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000654432_167534592.pth b/checkpoint_p0/milestones/checkpoint_000654432_167534592.pth new file mode 100644 index 0000000000000000000000000000000000000000..020942146d939d71c5effe3feef15e670e242adc --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000654432_167534592.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6375a44ee30ef53038f8122dd83a117a45fe7448a59a1cdecb788001ab750a74 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000667712_170934272.pth b/checkpoint_p0/milestones/checkpoint_000667712_170934272.pth new file mode 100644 index 0000000000000000000000000000000000000000..3ea83fecf004b9dac79aa8b9ec9031b466493c68 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000667712_170934272.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f3699ab9fdd0c836e90ca3d7e4d4e1d421daeb953e55a89f18d6b74cedf0bac +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000681024_174342144.pth b/checkpoint_p0/milestones/checkpoint_000681024_174342144.pth new file mode 100644 index 0000000000000000000000000000000000000000..46b489f8fce727c9ec1d066781600b5bf8cb3975 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000681024_174342144.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09906224e71753606f83f68161b30379827f1fac51c4f138466dd9828d00ddb8 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000694304_177741824.pth b/checkpoint_p0/milestones/checkpoint_000694304_177741824.pth new file mode 100644 index 0000000000000000000000000000000000000000..793c9b900151942b5a4717dc8a31f0f47c81d7a7 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000694304_177741824.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90d0c6193b4ed7a6b9fcda59abbabd6969930af584d8fea2d3e62b248ffd3421 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000707552_181133312.pth b/checkpoint_p0/milestones/checkpoint_000707552_181133312.pth new file mode 100644 index 0000000000000000000000000000000000000000..a7e0d6f583c546a29e3b7521e330a08b2f024a03 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000707552_181133312.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57c9ee9df4f4fd90827041c2e52993a0f748d48c26353a5ab0934e42d2f882b5 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000720864_184541184.pth b/checkpoint_p0/milestones/checkpoint_000720864_184541184.pth new file mode 100644 index 0000000000000000000000000000000000000000..5d59a935a57f0707bc7fc9d24a2cfc1b69968702 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000720864_184541184.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e706cb02f50f8acbdecc74dd65f1f79b43ee2f2548f050a96ac4ade17eb736be +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000734048_187916288.pth b/checkpoint_p0/milestones/checkpoint_000734048_187916288.pth new file mode 100644 index 0000000000000000000000000000000000000000..e74ee8f2cbe00cdee6e486dfb493030131f76dc6 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000734048_187916288.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd2100a18b87ec842f8a840a32822c912915b52d36f1a43362ebe6197ba135d7 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000747328_191315968.pth b/checkpoint_p0/milestones/checkpoint_000747328_191315968.pth new file mode 100644 index 0000000000000000000000000000000000000000..0d5a9105837c04d61e825adb454aecef7293d02f --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000747328_191315968.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1132793db9cce43a68e4e3c285c24b17cd09dfb9040c3ea9b2e878a95eab80c +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000760768_194756608.pth b/checkpoint_p0/milestones/checkpoint_000760768_194756608.pth new file mode 100644 index 0000000000000000000000000000000000000000..5ad6128f115c74480a16573c20b88e9831d43e94 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000760768_194756608.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d81f4611418ba6ed20dd59a81ee089ef0923239e267ab50a49df0a6ff6a685b +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000774176_198189056.pth b/checkpoint_p0/milestones/checkpoint_000774176_198189056.pth new file mode 100644 index 0000000000000000000000000000000000000000..090f0e5da3c7098829c046f9e1daaba5b6144bed --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000774176_198189056.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1b641c96bc439919258d72370e4da0de4eb6d734073d06223d5453363edac60 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000787616_201629696.pth b/checkpoint_p0/milestones/checkpoint_000787616_201629696.pth new file mode 100644 index 0000000000000000000000000000000000000000..6519aa6f362dd37452924d3378965b8beaeb299f --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000787616_201629696.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f1a8594b26ec3bc5884f4cc1868efd9b570b9e2add526eedbf5280954599f2b +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000801024_205062144.pth b/checkpoint_p0/milestones/checkpoint_000801024_205062144.pth new file mode 100644 index 0000000000000000000000000000000000000000..543b81f79a578353cd6738f0ae59c612c7ce1c44 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000801024_205062144.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d630371e403b02ebda6582de69ecddb3e0388a94321ec12f8c0343276c25071 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000814400_208486400.pth b/checkpoint_p0/milestones/checkpoint_000814400_208486400.pth new file mode 100644 index 0000000000000000000000000000000000000000..ea28fd246759b821582167a2fb91638e2dc1d2bf --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000814400_208486400.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3cf24c92484ad7ee530ee03ddc68af453185183f09cedcfdd3e81a980406c7ad +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000827808_211918848.pth b/checkpoint_p0/milestones/checkpoint_000827808_211918848.pth new file mode 100644 index 0000000000000000000000000000000000000000..54514cfcfd228838846c143f4d6154fb8e49434b --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000827808_211918848.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15b14c15aadabbf6c21a9d5664e04e2acca535544ee1ff200cf6b0ad1a361e23 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000841280_215367680.pth b/checkpoint_p0/milestones/checkpoint_000841280_215367680.pth new file mode 100644 index 0000000000000000000000000000000000000000..a96a47e060482e8153f8279bb2c51d8b9f31f71e --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000841280_215367680.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31978126426c385e38cca78511a3482663fd022909a8ed4f7adf8eda77f066d5 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000854720_218808320.pth b/checkpoint_p0/milestones/checkpoint_000854720_218808320.pth new file mode 100644 index 0000000000000000000000000000000000000000..619d22e6116c13ab9caf2b92a5872f27f06e67bc --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000854720_218808320.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42540019b1cabb65887b45170daad3dfb990fa8da62a66e2a58ca1382d4dc4cc +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000868032_222216192.pth b/checkpoint_p0/milestones/checkpoint_000868032_222216192.pth new file mode 100644 index 0000000000000000000000000000000000000000..33f2e2a84ba406c057b67892c5048699d8d141c6 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000868032_222216192.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d6e1b246bf3efc54abc7918f58b313a937d24ef3c08e6ce6a38e1e71cb03779 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000881504_225665024.pth b/checkpoint_p0/milestones/checkpoint_000881504_225665024.pth new file mode 100644 index 0000000000000000000000000000000000000000..8e771120cf5ef020eebe8bb6d9f18b4cec013d10 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000881504_225665024.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fae3620e970bad6fe04923946c99240b599829ecdd0cd67b805cc41efa644f6 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000894944_229105664.pth b/checkpoint_p0/milestones/checkpoint_000894944_229105664.pth new file mode 100644 index 0000000000000000000000000000000000000000..5a7d5df86765102339fa23f934976c767064a4ff --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000894944_229105664.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4f4fb7b50c8115ef9f699ecc7bf41e931401236c12affb274e7e5a0b775dfdf +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000908352_232538112.pth b/checkpoint_p0/milestones/checkpoint_000908352_232538112.pth new file mode 100644 index 0000000000000000000000000000000000000000..1319875063291df75e39463f627c1607da3a7824 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000908352_232538112.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db737d101f1bf3a09826938420531125e297455b3201552a81949264070bc666 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000921792_235978752.pth b/checkpoint_p0/milestones/checkpoint_000921792_235978752.pth new file mode 100644 index 0000000000000000000000000000000000000000..a5059c23ac568a077768703eee8cb2f9d8b1d1c1 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000921792_235978752.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5534bf9592e8e4ca56f8454845e1807632eeb6475b2f523042fc61eaf157acb0 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000935200_239411200.pth b/checkpoint_p0/milestones/checkpoint_000935200_239411200.pth new file mode 100644 index 0000000000000000000000000000000000000000..bda5c6c6aa87c2cdc10b4d65253724d0ca9214c2 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000935200_239411200.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2e2eee6934c9b372cca62d33f49ed450e08219ad8cf07d871c16f8ee2ac76c7 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000948480_242810880.pth b/checkpoint_p0/milestones/checkpoint_000948480_242810880.pth new file mode 100644 index 0000000000000000000000000000000000000000..094c4f269945ab740f0a8748ee00afd33624b636 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000948480_242810880.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f029bde4b094c369202b6cd7b7d055a9508910395832ca5bfa48eae47499ada +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000961824_246226944.pth b/checkpoint_p0/milestones/checkpoint_000961824_246226944.pth new file mode 100644 index 0000000000000000000000000000000000000000..f6debdbc802a73132c8477af0bbfd40c35551b12 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000961824_246226944.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97f762673e5e2e527474f97d3381cf794b64c1fc1a06d702813d339c37d2e45c +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000975264_249667584.pth b/checkpoint_p0/milestones/checkpoint_000975264_249667584.pth new file mode 100644 index 0000000000000000000000000000000000000000..b92672fd668bc8595ce97245424451b254cbc253 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000975264_249667584.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29d51bcb0e8aaf18497577171a76214077ed2073095abacdd71c070f44e472f4 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_000988672_253100032.pth b/checkpoint_p0/milestones/checkpoint_000988672_253100032.pth new file mode 100644 index 0000000000000000000000000000000000000000..5f1123c8357707d1d64e6a8a6d52827c13b48b85 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000988672_253100032.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bba0dfceb45052154e6eca37fd06900a3213b70e4d503c10a45d80e7e4b87d99 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001002144_256548864.pth b/checkpoint_p0/milestones/checkpoint_001002144_256548864.pth new file mode 100644 index 0000000000000000000000000000000000000000..4961d3fb0e6b668c4700264417cf41a6d2f4c3a7 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001002144_256548864.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95a3d3c0595baebc6d95464d1afac03a54dafd6c44b1a3bd49bbef91aa6642cc +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001015584_259989504.pth b/checkpoint_p0/milestones/checkpoint_001015584_259989504.pth new file mode 100644 index 0000000000000000000000000000000000000000..6f1459c5a59aab2a229191295e4f88e2503ec57a --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001015584_259989504.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ee9259b32d3719150b606ce2921ab12cc71524865f96076f5b8ec12d23e9753 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001028992_263421952.pth b/checkpoint_p0/milestones/checkpoint_001028992_263421952.pth new file mode 100644 index 0000000000000000000000000000000000000000..315c887fc8bafe3fd49a570fda695fd51b625b24 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001028992_263421952.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:114f482d05148297c1ad091254d670077f127ca22214d246dfd33d2c8c4d9978 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001042464_266870784.pth b/checkpoint_p0/milestones/checkpoint_001042464_266870784.pth new file mode 100644 index 0000000000000000000000000000000000000000..b2e21d30f3747f2228550017076c698f3c835d05 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001042464_266870784.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c2d770eba28d9911dbab904557bf4d8f90a78ba14163f5917caa64e38b7c654 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001055904_270311424.pth b/checkpoint_p0/milestones/checkpoint_001055904_270311424.pth new file mode 100644 index 0000000000000000000000000000000000000000..cb26edf0663acfc77ff0eb4e1cc10cd6bea0c7ef --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001055904_270311424.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0780ead5b82140dd1b5e67ec2c1747732a779e6b5199e32177a342990c797681 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001069344_273752064.pth b/checkpoint_p0/milestones/checkpoint_001069344_273752064.pth new file mode 100644 index 0000000000000000000000000000000000000000..bc6fccc80fa52993d7a34461f580dd8828fc9aa6 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001069344_273752064.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9122893d96d2cbfa16a83757e9cceb09997c0a092fed10af6c73049b76200437 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001082752_277184512.pth b/checkpoint_p0/milestones/checkpoint_001082752_277184512.pth new file mode 100644 index 0000000000000000000000000000000000000000..263b93b28819683dfb764142cb156daa0be1496f --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001082752_277184512.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6caaf0335a32a228c96539bc73811e31165a2a8c8f5cbfa771231c46505c5c6b +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001096192_280625152.pth b/checkpoint_p0/milestones/checkpoint_001096192_280625152.pth new file mode 100644 index 0000000000000000000000000000000000000000..d3056c62282189b494510072ab60f1ecb5f52d91 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001096192_280625152.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d211448f3a19a84c40832a56bbd0a3437c6f7bd3986af7238a0a055f7ff643d +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001109632_284065792.pth b/checkpoint_p0/milestones/checkpoint_001109632_284065792.pth new file mode 100644 index 0000000000000000000000000000000000000000..15cc1cdf799ce84f8c7b899e1c4593efd2b3fa35 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001109632_284065792.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c5c4933397563058f9ccec19bb62df572480411bc89a26ab1846d142b8bbdbb +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001123072_287506432.pth b/checkpoint_p0/milestones/checkpoint_001123072_287506432.pth new file mode 100644 index 0000000000000000000000000000000000000000..ee3d1debe3e7fdb4f3639122bbdd771918e6cdc0 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001123072_287506432.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dabcd3ce04b4f264fe216e3b4a277eb0b8c94eb9dbe78f6cf6504af73035f52a +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001136512_290947072.pth b/checkpoint_p0/milestones/checkpoint_001136512_290947072.pth new file mode 100644 index 0000000000000000000000000000000000000000..4a90fe507725926772eaa4c2fdecc88d5ba90884 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001136512_290947072.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b670e18bd891f3f1e82a7504c28defeb60824414302f2efe8d630dd965cd97f3 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001149952_294387712.pth b/checkpoint_p0/milestones/checkpoint_001149952_294387712.pth new file mode 100644 index 0000000000000000000000000000000000000000..f46b94ec1c1595c44e95169db636ad7108f2b115 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001149952_294387712.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24ab6e64ab772f54cc8a65d9b8d0989f3f3acd86816ee809817a962cfe3a6c9c +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001163360_297820160.pth b/checkpoint_p0/milestones/checkpoint_001163360_297820160.pth new file mode 100644 index 0000000000000000000000000000000000000000..8eadeb95a50201f836dcf4819dc09f13cc6f4c4e --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001163360_297820160.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74caeafdfb72ffb3354c55905d5af37be5fb40682edd734beeff4fa83323a442 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001176832_301268992.pth b/checkpoint_p0/milestones/checkpoint_001176832_301268992.pth new file mode 100644 index 0000000000000000000000000000000000000000..88975a7811d16990424a66d522139c41bb682789 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001176832_301268992.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a57ae005ab94bd119886a265d3a216f36ab8e197a60f7c389b4d6b0210d74c1d +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001190240_304701440.pth b/checkpoint_p0/milestones/checkpoint_001190240_304701440.pth new file mode 100644 index 0000000000000000000000000000000000000000..9832e43c5c99227f006acf845ce4f793c6b38b91 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001190240_304701440.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9977c3b211c4baeb71892dee3e2297ef1edb2a37c68ef907f5fbe0fac756e324 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001203648_308133888.pth b/checkpoint_p0/milestones/checkpoint_001203648_308133888.pth new file mode 100644 index 0000000000000000000000000000000000000000..89f0a1002a1464717e44174279cb900c552e0b69 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001203648_308133888.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:183e4d7c54a76fde0f1603616e7c03d04b3a7bb2f1ca2e32c54c3a788b312e79 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001217088_311574528.pth b/checkpoint_p0/milestones/checkpoint_001217088_311574528.pth new file mode 100644 index 0000000000000000000000000000000000000000..85952e1a024c6dc1ec548f3556271302173d18c0 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001217088_311574528.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b81e97e7f047ad6e88aba8881b287d2ee999b0a440de9df686c3d9a54bf76c1e +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001230560_315023360.pth b/checkpoint_p0/milestones/checkpoint_001230560_315023360.pth new file mode 100644 index 0000000000000000000000000000000000000000..246bddb02a962df54a0b7550f65a430a4866306f --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001230560_315023360.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c6d319fcfd4adfec6851468ebf7f47db405cd16d885a9d2fc29f4944417ff4c +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001244096_318488576.pth b/checkpoint_p0/milestones/checkpoint_001244096_318488576.pth new file mode 100644 index 0000000000000000000000000000000000000000..68f1755b9579c0145b072a61f0a0b920791cf82d --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001244096_318488576.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1763f9bfe38f5846a261e7f0de69d7d4ae46e5faf183d8e5dfc0fb334c5fe666 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001257536_321929216.pth b/checkpoint_p0/milestones/checkpoint_001257536_321929216.pth new file mode 100644 index 0000000000000000000000000000000000000000..94ac2f2852c38edf47ed3158d7f7bf502c98f0c5 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001257536_321929216.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24a30259dc5f030002c72fcb68d7356322d7970e91c0fd0ca7a458ec6afb4624 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001270976_325369856.pth b/checkpoint_p0/milestones/checkpoint_001270976_325369856.pth new file mode 100644 index 0000000000000000000000000000000000000000..37730c4af06109868b125698906896632ff69b6e --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001270976_325369856.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8e67d0cf5f5f3e42d2292825fca5bc5050944b5f7636703baac36084ab20cb9 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001284384_328802304.pth b/checkpoint_p0/milestones/checkpoint_001284384_328802304.pth new file mode 100644 index 0000000000000000000000000000000000000000..c7ad3950cc0d8126259282de359592b73874e9a6 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001284384_328802304.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2aba8c93325f58d8c2b0c62a299f28127315f01d331a3910cb0e7bde867567c6 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001297664_332201984.pth b/checkpoint_p0/milestones/checkpoint_001297664_332201984.pth new file mode 100644 index 0000000000000000000000000000000000000000..b6c90429997d66eb5246a69ef4e9401c915151cb --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001297664_332201984.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:034c1555f572f21ea22a6eb59c463f1e37a5d8231336cbe92119cb204a8979c9 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001311072_335634432.pth b/checkpoint_p0/milestones/checkpoint_001311072_335634432.pth new file mode 100644 index 0000000000000000000000000000000000000000..8be4c450285297fcf767f6d7811e566a5f098aec --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001311072_335634432.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d836f41eea378569a92fe38ad254056c79c55909c4e44215ff43fe0496c824a +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001324512_339075072.pth b/checkpoint_p0/milestones/checkpoint_001324512_339075072.pth new file mode 100644 index 0000000000000000000000000000000000000000..dbfe55eff73d59fcaa18770fd77426c7d28085ff --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001324512_339075072.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3617519ebb2f4ae7e564947f8e9786bee0a75f723d789d648b72ba36b0060055 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001337952_342515712.pth b/checkpoint_p0/milestones/checkpoint_001337952_342515712.pth new file mode 100644 index 0000000000000000000000000000000000000000..863b170bb0b219f990568dc4d9fe879909fe0a34 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001337952_342515712.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1945ae999961c5d1af08aeb2a6cd222d31d9a50e46331d939f165aa0b8fa8a6e +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001351328_345939968.pth b/checkpoint_p0/milestones/checkpoint_001351328_345939968.pth new file mode 100644 index 0000000000000000000000000000000000000000..21785a2a580785899855044ad6ec5a383ed9e79a --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001351328_345939968.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9cec9c509116530005783640e973d210aec658d3f58051250ebd26f6c17c8877 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001364736_349372416.pth b/checkpoint_p0/milestones/checkpoint_001364736_349372416.pth new file mode 100644 index 0000000000000000000000000000000000000000..f56f9c17cff3638bcb3f66825b2c20024da97eaf --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001364736_349372416.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b66e2aa554ca6c77ab257739cfd257d2d58a81a6dc40651b8222a5c0111f3875 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001378144_352804864.pth b/checkpoint_p0/milestones/checkpoint_001378144_352804864.pth new file mode 100644 index 0000000000000000000000000000000000000000..16c17c8fe064148f640ad56ec20d66b9c116388e --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001378144_352804864.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01797247fbc302f22c1daad61eef0000880208408dcaf6521ad488cfa83ab687 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001391552_356237312.pth b/checkpoint_p0/milestones/checkpoint_001391552_356237312.pth new file mode 100644 index 0000000000000000000000000000000000000000..dad7fe5d5692350ae96306c3e38689de11487128 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001391552_356237312.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5724ab0571a4d04f5da203fff2a7af3ac9d2a50daa71e51f8098e745feb3c65b +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001404992_359677952.pth b/checkpoint_p0/milestones/checkpoint_001404992_359677952.pth new file mode 100644 index 0000000000000000000000000000000000000000..1936f918418abd277e3c820f668b5c99f3896afe --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001404992_359677952.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60ce8b2769c2ad7bfda96802db4b1bd02b75664122e8c7554c00d9ce6acd8415 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001418432_363118592.pth b/checkpoint_p0/milestones/checkpoint_001418432_363118592.pth new file mode 100644 index 0000000000000000000000000000000000000000..b673f806f79077c1a8aacf378b05e8bea086d6b9 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001418432_363118592.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:453e71d0f30f365f33912f751412eaaed8f67fff3c0852bc8cdf979c5feeaf8b +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001431872_366559232.pth b/checkpoint_p0/milestones/checkpoint_001431872_366559232.pth new file mode 100644 index 0000000000000000000000000000000000000000..77d62406aee55608a84a98bdddd0eff4dafe0eb1 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001431872_366559232.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6359d3e8cd827ffbfa78f79a5a9b55ec1665486dc614d85111a2c7a635a343f +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001445312_369999872.pth b/checkpoint_p0/milestones/checkpoint_001445312_369999872.pth new file mode 100644 index 0000000000000000000000000000000000000000..324272533e2541527b0903a4d2a7c2529ad260cb --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001445312_369999872.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5de7bc90050423f2afc14fc71fc7795f5120a579efaf0f12b7954d9f776bfbbf +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001458784_373448704.pth b/checkpoint_p0/milestones/checkpoint_001458784_373448704.pth new file mode 100644 index 0000000000000000000000000000000000000000..1fbb4a725a12265856ccf7b86f7ad6cfa99df824 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001458784_373448704.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad0eade630e05224b1caf644755e06571bca3e68ada20aecca46394d49bdc0d8 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001472256_376897536.pth b/checkpoint_p0/milestones/checkpoint_001472256_376897536.pth new file mode 100644 index 0000000000000000000000000000000000000000..a7554708c8b37bdee6e1e3b453b08abac56fcf4d --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001472256_376897536.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fda32295c41126ce1adb8a85056110c35804fcf2725f6b4486636b0bb3d66ee8 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001485664_380329984.pth b/checkpoint_p0/milestones/checkpoint_001485664_380329984.pth new file mode 100644 index 0000000000000000000000000000000000000000..1c7cfc288bed793f629b068e18a25ea62a45775e --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001485664_380329984.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a000a37a1a3edf3fc57b2960a8d10f221ae43ba06ba8c61e3483c6d4019180a4 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001499136_383778816.pth b/checkpoint_p0/milestones/checkpoint_001499136_383778816.pth new file mode 100644 index 0000000000000000000000000000000000000000..b98d5eb4696e2f74bd68dc0ff6e4ed5b5f840327 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001499136_383778816.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b89fb79593f8c446b8e07f7875de75940bb18efd945d19b1a2a1a82444cbdceb +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001512608_387227648.pth b/checkpoint_p0/milestones/checkpoint_001512608_387227648.pth new file mode 100644 index 0000000000000000000000000000000000000000..2db8e62d47d0ae08534a8a4f346c9731c62e4ba1 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001512608_387227648.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be2f18a6159ad022fd6da6b7713c09e680861265ef50ba8fe29d5560ea88bc93 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001526048_390668288.pth b/checkpoint_p0/milestones/checkpoint_001526048_390668288.pth new file mode 100644 index 0000000000000000000000000000000000000000..4a7bfb6ab22c26b7aba4e05b1423802ab57447dc --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001526048_390668288.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6d8a21840cfff0c2b06b0349a59bd2d931c179c48f4d6330cc1aa91b632d96f +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001539424_394092544.pth b/checkpoint_p0/milestones/checkpoint_001539424_394092544.pth new file mode 100644 index 0000000000000000000000000000000000000000..15fc6d8863bea071a69471350100865662498ce8 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001539424_394092544.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:098959d7169bf821aae4d1a02aa285b7d76cddb97b984e5735620d6763e7aa6c +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001552800_397516800.pth b/checkpoint_p0/milestones/checkpoint_001552800_397516800.pth new file mode 100644 index 0000000000000000000000000000000000000000..cc396e4203c388ab9426de2911208a9f73b61b2f --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001552800_397516800.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a16a1d30033d5db45f043cc08e562bfbd042c091bc43b8b4cc5794539970b9e6 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001566304_400973824.pth b/checkpoint_p0/milestones/checkpoint_001566304_400973824.pth new file mode 100644 index 0000000000000000000000000000000000000000..88d0c95a26b8113d3b4c905a1eb64b3cd863bbb9 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001566304_400973824.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08f2305ca76c23c702981e047f741a08bdfc52516b1db96cbbf972d0bcf237c7 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001579776_404422656.pth b/checkpoint_p0/milestones/checkpoint_001579776_404422656.pth new file mode 100644 index 0000000000000000000000000000000000000000..26f23a1cd10ea60e790f65f2d7ebb0694c909ffc --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001579776_404422656.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:149498c6869aa146dfa64b2f179ecb40f5987d6eef0dfc89ffff667d2d77f60f +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001593216_407863296.pth b/checkpoint_p0/milestones/checkpoint_001593216_407863296.pth new file mode 100644 index 0000000000000000000000000000000000000000..244b032a13df2c415923c445148441a81716e4b6 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001593216_407863296.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1100050976300227da37620ba54bb51507a071da71af4357f232cef19e271297 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001606656_411303936.pth b/checkpoint_p0/milestones/checkpoint_001606656_411303936.pth new file mode 100644 index 0000000000000000000000000000000000000000..2cef4ef77adc82ad6c34554328ed613c3ab6b148 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001606656_411303936.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c48550dc7fd6f507e300f49d5aa7dd805a3cbd4cd50373fc52928a07785e68f7 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001620096_414744576.pth b/checkpoint_p0/milestones/checkpoint_001620096_414744576.pth new file mode 100644 index 0000000000000000000000000000000000000000..78bdd828172a9bfeb175d096fd0f74b8ef060f9c --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001620096_414744576.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83ceec6af4df1a29a444c3d49ff6fc8c2969e29984f4cd2bac5b832d566e7b4a +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001633472_418168832.pth b/checkpoint_p0/milestones/checkpoint_001633472_418168832.pth new file mode 100644 index 0000000000000000000000000000000000000000..84890ebbce0345b30a47e113e1cde01e3ea90e2b --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001633472_418168832.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:886b799a998b9f4fb54cca8e22c777a4568fb6e833cafeaf6332aff9c76e94d9 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001646912_421609472.pth b/checkpoint_p0/milestones/checkpoint_001646912_421609472.pth new file mode 100644 index 0000000000000000000000000000000000000000..135e9c6f29f5f96a497c4ee038cd2ea2e03c8899 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001646912_421609472.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06c49160e8583b4e80dc8f4fe7018a8aceac2ae828b7f2354162717b130e0093 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001660384_425058304.pth b/checkpoint_p0/milestones/checkpoint_001660384_425058304.pth new file mode 100644 index 0000000000000000000000000000000000000000..e3828a5b4b7f0b4ea03885de90f92374dee9a304 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001660384_425058304.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e2a2af65879a9ad5b662073c60a2dc1d4db55df0c093d7f30429cc8b94ca029 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001673824_428498944.pth b/checkpoint_p0/milestones/checkpoint_001673824_428498944.pth new file mode 100644 index 0000000000000000000000000000000000000000..c7c59d5010dce754132982a995861cc3c7e83420 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001673824_428498944.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfeb38f2a509489f391872a6203748b3373ef03bd715d0fdaef005c281b874dd +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001687264_431939584.pth b/checkpoint_p0/milestones/checkpoint_001687264_431939584.pth new file mode 100644 index 0000000000000000000000000000000000000000..c2c4f70ecbba3348a6e24cda6c0e290a599aabab --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001687264_431939584.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3dd618b3d142bc7cdf9050bcab7e9d4f999e6a1f9fd82fea2503d1f4810303f +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001700704_435380224.pth b/checkpoint_p0/milestones/checkpoint_001700704_435380224.pth new file mode 100644 index 0000000000000000000000000000000000000000..fa916e58e7da845fd658e19e909e97ee7cde2345 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001700704_435380224.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ca25c3c52c2716594e7d096d83613e364ab54f22d26b9b823c43d459e08f98e +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001714112_438812672.pth b/checkpoint_p0/milestones/checkpoint_001714112_438812672.pth new file mode 100644 index 0000000000000000000000000000000000000000..05840eb3eaaff1a88a9ba1723cbde09189a8ba76 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001714112_438812672.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d38f4175d21fc9b6f0dfcede534ecac0ba8fcec282e72556d751bc82e48e5d58 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001727648_442277888.pth b/checkpoint_p0/milestones/checkpoint_001727648_442277888.pth new file mode 100644 index 0000000000000000000000000000000000000000..ab8158581d638e05946fe98190947853ca642e66 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001727648_442277888.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:baab469d33cc1be05c5f4384d95f840a2ec053a4c25f385345eef6320d89c546 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001741152_445734912.pth b/checkpoint_p0/milestones/checkpoint_001741152_445734912.pth new file mode 100644 index 0000000000000000000000000000000000000000..48671ae38cee4cac00366019c3387d7c379805fb --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001741152_445734912.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8df90a379018e71f44627f6642678f1fde94a1129c1516a5e7ec530cb1230ae8 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001754592_449175552.pth b/checkpoint_p0/milestones/checkpoint_001754592_449175552.pth new file mode 100644 index 0000000000000000000000000000000000000000..50ca6c5f796cb6dc47a030b42974586ca5a83c04 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001754592_449175552.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db08a448ad5b55318f5bba8b78720a16fa7b7471d2700cf33deab89c9455e281 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001768032_452616192.pth b/checkpoint_p0/milestones/checkpoint_001768032_452616192.pth new file mode 100644 index 0000000000000000000000000000000000000000..a742b231795ad9431890443a7a2b9fbda807a120 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001768032_452616192.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e5dd9ab6279fa7579c395e3ca8bfeb870a0211eef728a883b3e45f7c93a2089 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001781472_456056832.pth b/checkpoint_p0/milestones/checkpoint_001781472_456056832.pth new file mode 100644 index 0000000000000000000000000000000000000000..4343b4045583fd1fe6a58c3ec191ff89db632442 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001781472_456056832.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af6d8579c9585deba41b0d6bb5b3b228d1257eeec860df2e2658ee127bb4f177 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001794880_459489280.pth b/checkpoint_p0/milestones/checkpoint_001794880_459489280.pth new file mode 100644 index 0000000000000000000000000000000000000000..c25191b69174c7888fd98dcdbf3181a6d81a55e9 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001794880_459489280.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fc37989c96cdf210ac14d0b4e0f6502afbd06431b0bb03f9fb65d9cd7d40239 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001808288_462921728.pth b/checkpoint_p0/milestones/checkpoint_001808288_462921728.pth new file mode 100644 index 0000000000000000000000000000000000000000..1234cdc4a74a71bf936e17695974085c1b614d77 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001808288_462921728.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f36bb4c5ed0366c718b974884e8321bcbd758d2572c3e91ed4d3342c97df50b4 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001821728_466362368.pth b/checkpoint_p0/milestones/checkpoint_001821728_466362368.pth new file mode 100644 index 0000000000000000000000000000000000000000..8a8746ffc83442a9f425b1bfdb7974c74a84a615 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001821728_466362368.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3650b12058f2ed9a21b320425afbee56c38bfd6ef651533e3f0c8edefeb05a3 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001835136_469794816.pth b/checkpoint_p0/milestones/checkpoint_001835136_469794816.pth new file mode 100644 index 0000000000000000000000000000000000000000..2e53e79f9324fd7cef924f3566faf5a4f894e609 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001835136_469794816.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40f6a2d891639c53941fd7d2bb21a00d712f8e91a46796ea31d1cc3679f4479e +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001848576_473235456.pth b/checkpoint_p0/milestones/checkpoint_001848576_473235456.pth new file mode 100644 index 0000000000000000000000000000000000000000..c1d7684594ad098a21178abd0410a06b20df2184 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001848576_473235456.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10dba6c6ddfbafb2427dbc9b09025ef6b458fffcc63aaaafb7552997a6f1bb3d +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001862080_476692480.pth b/checkpoint_p0/milestones/checkpoint_001862080_476692480.pth new file mode 100644 index 0000000000000000000000000000000000000000..17c4128e95bc6e6d3f90d44101b48e1eb4542c82 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001862080_476692480.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ca2d65f10a521881fcdaecaad5f5c1f4b56eb1a761f6d482c1d75e7d8857ad3 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001875520_480133120.pth b/checkpoint_p0/milestones/checkpoint_001875520_480133120.pth new file mode 100644 index 0000000000000000000000000000000000000000..9ee6e5f0e9787b9b94481aadf822f94c7ef626a3 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001875520_480133120.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b10e966769957d9e949e3ae41bca89904b303053dcab4fd535be44ad9bbde6e +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001888960_483573760.pth b/checkpoint_p0/milestones/checkpoint_001888960_483573760.pth new file mode 100644 index 0000000000000000000000000000000000000000..3ad685dec137ef6444015ef5ab9432ce7612ca9a --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001888960_483573760.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fbbf145480d3d116f6b8e877893d4a18240f75236dea1a7292f9d89c4dfd41e +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001902368_487006208.pth b/checkpoint_p0/milestones/checkpoint_001902368_487006208.pth new file mode 100644 index 0000000000000000000000000000000000000000..f59cd6b4a84dc50b72033f552c1d46c2f7b28e2d --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001902368_487006208.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a422f4d9c694b5a930c0ff61f2b7b4c44d6cdab366c522e684903f83d44fd5bc +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001915712_490422272.pth b/checkpoint_p0/milestones/checkpoint_001915712_490422272.pth new file mode 100644 index 0000000000000000000000000000000000000000..05ae7778c642732e68f946f7443a546c18585e55 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001915712_490422272.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fc0537fb829865d510566bf61fc6de7ea31ec2bdb127681314fc1d9974ba995 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001929024_493830144.pth b/checkpoint_p0/milestones/checkpoint_001929024_493830144.pth new file mode 100644 index 0000000000000000000000000000000000000000..f04a7653eb83b21ac9c43f35f0e4970723b1409a --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001929024_493830144.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85a8bc6337d0328b13cb64a09b82194962f9503e9a59fcee246b6e192fe7d280 +size 20747723 diff --git a/checkpoint_p0/milestones/checkpoint_001942464_497270784.pth b/checkpoint_p0/milestones/checkpoint_001942464_497270784.pth new file mode 100644 index 0000000000000000000000000000000000000000..a2e29a4f0a835cd14fc50c188b36361db478fa51 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001942464_497270784.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f4321b9b94a555bede5e7766e6f9973f91e2eb3f98d84212579cdd469023cc6 +size 20747723 diff --git a/checkpoint_p1/best_001898112_485916672_reward_34.440.pth b/checkpoint_p1/best_001898112_485916672_reward_34.440.pth new file mode 100644 index 0000000000000000000000000000000000000000..91d05c61d0b28ecdfe651276de820f344e7b35ac --- /dev/null +++ b/checkpoint_p1/best_001898112_485916672_reward_34.440.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a4915177d1870c0a931cc589cf6fc2770f1dd18d42ba6e3d95d29adb3e143d4 +size 20746419 diff --git a/checkpoint_p1/checkpoint_001955616_501284864.pth b/checkpoint_p1/checkpoint_001955616_501284864.pth new file mode 100644 index 0000000000000000000000000000000000000000..7092a2ab76fd8a17b9d5a31bc1df1b495f7e3c84 --- /dev/null +++ b/checkpoint_p1/checkpoint_001955616_501284864.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b523ef0a7500771932b1ed993b9ee19810ebc067711975d55563ed790fb2acf +size 20746755 diff --git a/checkpoint_p1/checkpoint_001956288_501628928.pth b/checkpoint_p1/checkpoint_001956288_501628928.pth new file mode 100644 index 0000000000000000000000000000000000000000..8005da3292569995160b7b39935eada80b0de830 --- /dev/null +++ b/checkpoint_p1/checkpoint_001956288_501628928.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba842916683a210bf20d2817d5f33afb80f7a6b3372e83a1e72a079fc9c0118a +size 20746755 diff --git a/checkpoint_p1/milestones/checkpoint_000013056_3342336.pth b/checkpoint_p1/milestones/checkpoint_000013056_3342336.pth new file mode 100644 index 0000000000000000000000000000000000000000..904bc34ce3c437e795045577e44a48b63aec4f66 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000013056_3342336.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8e2dfd8c103b7f1ed919d883397d5f15082013f04b3f03d2d88638083a3eaf7 +size 20747611 diff --git a/checkpoint_p1/milestones/checkpoint_000026432_6766592.pth b/checkpoint_p1/milestones/checkpoint_000026432_6766592.pth new file mode 100644 index 0000000000000000000000000000000000000000..5bb32bc1725acbf33732abafd932076b55ea785c --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000026432_6766592.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58e396f47c0f7ae1aca16342b52d9b9e2c6b5a09391e08889e93a56e8f19bd23 +size 20747611 diff --git a/checkpoint_p1/milestones/checkpoint_000039904_10215424.pth b/checkpoint_p1/milestones/checkpoint_000039904_10215424.pth new file mode 100644 index 0000000000000000000000000000000000000000..f5b3f4f8375b99f6f145821a4e6dba0b44f59f7e --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000039904_10215424.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea1c5ba924c8472966ea3b7248b18caad135b98ec4d8b2dcd2441ba30809f5f3 +size 20747667 diff --git a/checkpoint_p1/milestones/checkpoint_000053344_13656064.pth b/checkpoint_p1/milestones/checkpoint_000053344_13656064.pth new file mode 100644 index 0000000000000000000000000000000000000000..3a4f3d94d1f04666323df35903da0b1bfe283766 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000053344_13656064.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbb50b9fcb32b7c9cb9343ad16e2f680a594617a8fe9ee533e848869337634d1 +size 20747667 diff --git a/checkpoint_p1/milestones/checkpoint_000066816_17104896.pth b/checkpoint_p1/milestones/checkpoint_000066816_17104896.pth new file mode 100644 index 0000000000000000000000000000000000000000..7e6c6b3a1f1685711c375c49ffd00b61b41ead4e --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000066816_17104896.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50ea4ecf2905ee61b7fd69b2407a264f6af82127bf54e1a6ad9aecc85b16a0ee +size 20747667 diff --git a/checkpoint_p1/milestones/checkpoint_000080320_20561920.pth b/checkpoint_p1/milestones/checkpoint_000080320_20561920.pth new file mode 100644 index 0000000000000000000000000000000000000000..816d8cc91d9fc59d373d1f76fd5482dfd9bd56da --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000080320_20561920.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:260215bfed7e98ebbe3eeabfb753b9f9046975bf170bcf52da0f0fad6b8e235f +size 20747667 diff --git a/checkpoint_p1/milestones/checkpoint_000093792_24010752.pth b/checkpoint_p1/milestones/checkpoint_000093792_24010752.pth new file mode 100644 index 0000000000000000000000000000000000000000..3113e555038b4f2cfdde17879672a913a3af842a --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000093792_24010752.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6de389294edaf7f22b9b32aebe8d26421b18cdab7e86c9f738c9f648631533be +size 20747667 diff --git a/checkpoint_p1/milestones/checkpoint_000107200_27443200.pth b/checkpoint_p1/milestones/checkpoint_000107200_27443200.pth new file mode 100644 index 0000000000000000000000000000000000000000..37389f9a35fb53513e678daaee44f0be54ca0e56 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000107200_27443200.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17abb92ab675bbf9b3f22cd3f9c7429623563325bd89e86c0470310f7152870c +size 20747667 diff --git a/checkpoint_p1/milestones/checkpoint_000120672_30892032.pth b/checkpoint_p1/milestones/checkpoint_000120672_30892032.pth new file mode 100644 index 0000000000000000000000000000000000000000..70d63e6a953f299051b2534624ba4461e72a842f --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000120672_30892032.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61c7c35c900cc612191c9b9c8801476e586dab9c45d78bef5652aa29579d163e +size 20747667 diff --git a/checkpoint_p1/milestones/checkpoint_000134112_34332672.pth b/checkpoint_p1/milestones/checkpoint_000134112_34332672.pth new file mode 100644 index 0000000000000000000000000000000000000000..73c447e3aa26879362daff5787cc56ac5b76befd --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000134112_34332672.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c4d2e787aa19690953d4edfbed1b93d679b033b71b1bfc1218768bc4323f80d +size 20747667 diff --git a/checkpoint_p1/milestones/checkpoint_000147552_37773312.pth b/checkpoint_p1/milestones/checkpoint_000147552_37773312.pth new file mode 100644 index 0000000000000000000000000000000000000000..a25085ef41a0d53e7a9daf8e209102f7d8ff2476 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000147552_37773312.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e40a722d8bd73f0361fb8d6d3b9d2ddc1c2bcdca3606f18962ea9c3e2d812bb3 +size 20747667 diff --git a/checkpoint_p1/milestones/checkpoint_000160992_41213952.pth b/checkpoint_p1/milestones/checkpoint_000160992_41213952.pth new file mode 100644 index 0000000000000000000000000000000000000000..886558ffd38e9c0db1a356c9265b204f9fa259c5 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000160992_41213952.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7b0e8be8d3b61fea0700d3f694b839b05ae31f5318acc451594c2607a1294e2 +size 20747667 diff --git a/checkpoint_p1/milestones/checkpoint_000174464_44662784.pth b/checkpoint_p1/milestones/checkpoint_000174464_44662784.pth new file mode 100644 index 0000000000000000000000000000000000000000..2ba19b5c2bafac1a6c05f3298010a9979b22b423 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000174464_44662784.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6192a76759e0b7eb0f58e164b2b69e05316ba3b0506abc12e7af283f3219d4fc +size 20747667 diff --git a/checkpoint_p1/milestones/checkpoint_000187936_48111616.pth b/checkpoint_p1/milestones/checkpoint_000187936_48111616.pth new file mode 100644 index 0000000000000000000000000000000000000000..bb2b8a7f4e44cc70537d430885c864064cf3f31e --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000187936_48111616.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a33cecb5b04b414ba2d5293862a73e93f1bebeb97d6446b2bedf17c7be17b53 +size 20747667 diff --git a/checkpoint_p1/milestones/checkpoint_000201472_51576832.pth b/checkpoint_p1/milestones/checkpoint_000201472_51576832.pth new file mode 100644 index 0000000000000000000000000000000000000000..344f587e727b0a92816da39e1c497f3274abefd4 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000201472_51576832.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8875462112008cf48c428d2cf4425cf13954861862eb9a846e725d1efc2186b7 +size 20747667 diff --git a/checkpoint_p1/milestones/checkpoint_000214944_55025664.pth b/checkpoint_p1/milestones/checkpoint_000214944_55025664.pth new file mode 100644 index 0000000000000000000000000000000000000000..6d5013380bcf921921f65f932bb703af1da8f7d5 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000214944_55025664.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ea0f15b1845a012c85370d9e39c5f7b3bf6a5cfee83ec7aa18337cc151c9964 +size 20747667 diff --git a/checkpoint_p1/milestones/checkpoint_000228448_58482688.pth b/checkpoint_p1/milestones/checkpoint_000228448_58482688.pth new file mode 100644 index 0000000000000000000000000000000000000000..16502dde475b3d2ff2b8b157829104ec7de5c4bd --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000228448_58482688.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bf2e3805a7432743d38e44847a6d4cd8c62cc81e9b39715943f0ac6bc4b16e0 +size 20747667 diff --git a/checkpoint_p1/milestones/checkpoint_000241728_61882368.pth b/checkpoint_p1/milestones/checkpoint_000241728_61882368.pth new file mode 100644 index 0000000000000000000000000000000000000000..f28243f162eaf13a0b5adbdad298a19424705d36 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000241728_61882368.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01bc924d11a907e92a394008d1f3ccebc8488d94bae4c13c166bbc3f17c49f8b +size 20747667 diff --git a/checkpoint_p1/milestones/checkpoint_000255232_65339392.pth b/checkpoint_p1/milestones/checkpoint_000255232_65339392.pth new file mode 100644 index 0000000000000000000000000000000000000000..14ad5b41da2e40e6991ce630ecddddf91b7827df --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000255232_65339392.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68dcd88a9c3b9417da1b6c8dc398e98ad1e5e26d187d847485d1c51555bef3c1 +size 20747667 diff --git a/checkpoint_p1/milestones/checkpoint_000268640_68771840.pth b/checkpoint_p1/milestones/checkpoint_000268640_68771840.pth new file mode 100644 index 0000000000000000000000000000000000000000..8be48e66de501dae3488af421eb1ca7c2bb2f840 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000268640_68771840.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01c4eab11a481fc23a55cb4452f85b59a1fbbb6f4e02675ed8d35f29d6550b7a +size 20747667 diff --git a/checkpoint_p1/milestones/checkpoint_000282112_72220672.pth b/checkpoint_p1/milestones/checkpoint_000282112_72220672.pth new file mode 100644 index 0000000000000000000000000000000000000000..3a1566cbb8a3fc44cfd348406502bb5753e3f124 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000282112_72220672.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa04e182cfcfe4efa81b15ef8056c570325fac89a2c1012f984bdd6f06514566 +size 20747667 diff --git a/checkpoint_p1/milestones/checkpoint_000295520_75653120.pth b/checkpoint_p1/milestones/checkpoint_000295520_75653120.pth new file mode 100644 index 0000000000000000000000000000000000000000..6f0fb8447cfb72aa0f3f76c07d50e701bb39a249 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000295520_75653120.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f19fc09ef1be9f5801a69547091de1f8959019a455a2698f4af159136a69dfa7 +size 20747667 diff --git a/checkpoint_p1/milestones/checkpoint_000308992_79101952.pth b/checkpoint_p1/milestones/checkpoint_000308992_79101952.pth new file mode 100644 index 0000000000000000000000000000000000000000..01b90a3770f92d74f89beb14af7017e03a92955c --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000308992_79101952.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1990c0e63a7cb2c0e571c41b3cec338382e1de861d015885167481f2b38edcb0 +size 20747667 diff --git a/checkpoint_p1/milestones/checkpoint_000322432_82542592.pth b/checkpoint_p1/milestones/checkpoint_000322432_82542592.pth new file mode 100644 index 0000000000000000000000000000000000000000..c17841dd6f2fcc513ac261a05e3cdf9df037215c --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000322432_82542592.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ba3b29c66a52eea0286c7b9cdf1a857cc1b48c21596eab7364fc5f9b3be6cf9 +size 20747667 diff --git a/checkpoint_p1/milestones/checkpoint_000335904_85991424.pth b/checkpoint_p1/milestones/checkpoint_000335904_85991424.pth new file mode 100644 index 0000000000000000000000000000000000000000..8fe8bf8b563081f78acf7aee413f570081f2ee81 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000335904_85991424.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:872a40451a20a2d93ee59b96173e712740016de157550b495c802e47d87178a2 +size 20747667 diff --git a/checkpoint_p1/milestones/checkpoint_000349312_89423872.pth b/checkpoint_p1/milestones/checkpoint_000349312_89423872.pth new file mode 100644 index 0000000000000000000000000000000000000000..f946ed0162fbb7d20689a7f7b72e4d17ecfd4a7b --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000349312_89423872.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:227d2d08599b505315ebf0e3b58549de5f249713625f23be6c271d594c694eda +size 20747667 diff --git a/checkpoint_p1/milestones/checkpoint_000362816_92880896.pth b/checkpoint_p1/milestones/checkpoint_000362816_92880896.pth new file mode 100644 index 0000000000000000000000000000000000000000..5b93e3da45d35e43d1d0f2663192b82920acf3d6 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000362816_92880896.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b46526b334a153ed0390bfe9394c52bbdd3bcc27b90d291feafbb3483f08426 +size 20747667 diff --git a/checkpoint_p1/milestones/checkpoint_000376224_96313344.pth b/checkpoint_p1/milestones/checkpoint_000376224_96313344.pth new file mode 100644 index 0000000000000000000000000000000000000000..7711db803f6170ce998a7083373b8737951c0071 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000376224_96313344.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88fe85961b25e6bbe279ad4d1ceb5a3c1a359f2ccfdeb07a488cfd590182013d +size 20747667 diff --git a/checkpoint_p1/milestones/checkpoint_000389536_99721216.pth b/checkpoint_p1/milestones/checkpoint_000389536_99721216.pth new file mode 100644 index 0000000000000000000000000000000000000000..c4c933175211373b3920952c11caa8c47c6a21a6 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000389536_99721216.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db2793c127f16f6ab4a6d1dbfdaa82ba6737e608134989c629d4a73a82253d97 +size 20747667 diff --git a/checkpoint_p1/milestones/checkpoint_000402880_103137280.pth b/checkpoint_p1/milestones/checkpoint_000402880_103137280.pth new file mode 100644 index 0000000000000000000000000000000000000000..8eb168c4a80626d78856b10f48cb074b649d310e --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000402880_103137280.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02dbdb2c12d711d681e48d96e4347cfd2bfcc7dac9b1e3d0657e667e6fb11199 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000416192_106545152.pth b/checkpoint_p1/milestones/checkpoint_000416192_106545152.pth new file mode 100644 index 0000000000000000000000000000000000000000..a90ddd9721edd4b4ed68e1a7404ea2b5fadc8d3f --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000416192_106545152.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:578a396ec8ed0370f20ca256732bbba7a37129656fdacaa0d8cfac7342600e71 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000429504_109953024.pth b/checkpoint_p1/milestones/checkpoint_000429504_109953024.pth new file mode 100644 index 0000000000000000000000000000000000000000..2bbb9c0ac86baab8591b01a814f9cb0670b6c6f6 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000429504_109953024.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d06bfa4ec7b396bd521276d8f7a5c29999e557e1c451259f32abd1de6ca210c0 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000442848_113369088.pth b/checkpoint_p1/milestones/checkpoint_000442848_113369088.pth new file mode 100644 index 0000000000000000000000000000000000000000..b01433ab4c1ec5703791912f2e4d823f0d0650d0 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000442848_113369088.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e0181a186a57f893ee6197d88b1e3ea342d515f0dac70ff62abe55a7bed52af +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000456256_116801536.pth b/checkpoint_p1/milestones/checkpoint_000456256_116801536.pth new file mode 100644 index 0000000000000000000000000000000000000000..8f7c7f9b10024998174eb77fe5137c0a00284116 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000456256_116801536.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0240562a3546066f2333e4565b6777c6c7c3765895485acedc08c8909bddb85 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000469536_120201216.pth b/checkpoint_p1/milestones/checkpoint_000469536_120201216.pth new file mode 100644 index 0000000000000000000000000000000000000000..980c11741079113004fc44e581b23c268d6dcc8b --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000469536_120201216.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c369879753524205a79f5e0180b79fb05a01a139decf8b4b1179ced9aa820e93 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000482816_123600896.pth b/checkpoint_p1/milestones/checkpoint_000482816_123600896.pth new file mode 100644 index 0000000000000000000000000000000000000000..fa72e345f080ce827d129fb04b5adcd94c8bd7d1 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000482816_123600896.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08c6b548d00b6d360910c78036d80b17664e9f3b6751ca2ae6bef73d344af16f +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000496096_127000576.pth b/checkpoint_p1/milestones/checkpoint_000496096_127000576.pth new file mode 100644 index 0000000000000000000000000000000000000000..398d99f062799948e4b13cd830957654276383d3 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000496096_127000576.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb356d8e4f477f3734ba9e03d8a66b402d7a98d13c85d9e6595a436c9b47b68c +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000509280_130375680.pth b/checkpoint_p1/milestones/checkpoint_000509280_130375680.pth new file mode 100644 index 0000000000000000000000000000000000000000..6ccada8ba38331909f1b942c1b5bef2d7247f553 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000509280_130375680.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78827f627182d1a55404ad312f5bc0dba38d6b8a9d8ae6dd0ecb828191bede82 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000522688_133808128.pth b/checkpoint_p1/milestones/checkpoint_000522688_133808128.pth new file mode 100644 index 0000000000000000000000000000000000000000..bfd8246e3e9f84f94c96a0ca0aa1e1979c51bb8b --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000522688_133808128.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9fbf8c0bf289e2df42af50ff86af7a0a6d9d03cb172489fcfaa6434a91b23ab +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000535968_137207808.pth b/checkpoint_p1/milestones/checkpoint_000535968_137207808.pth new file mode 100644 index 0000000000000000000000000000000000000000..e5867cac5f7cb76d97356c8fddd2d31cdddb11fa --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000535968_137207808.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d3bf0670a74a017cf0d38ea9402dd54ef8e2f9666d8a8b7b8daa158d70b67b9 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000549312_140623872.pth b/checkpoint_p1/milestones/checkpoint_000549312_140623872.pth new file mode 100644 index 0000000000000000000000000000000000000000..7699ca1c6c72c61288907e1e2bfa1960d00c0112 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000549312_140623872.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3e5ebde067be9e5f30683749695cc8eb00e9fc303a1937012fcbfd8acac8db1 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000562624_144031744.pth b/checkpoint_p1/milestones/checkpoint_000562624_144031744.pth new file mode 100644 index 0000000000000000000000000000000000000000..93b32dda25bf163d27a43cd1665fca3c18cd9562 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000562624_144031744.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29699add4aa4bb8f9a270aa3f25ff9055c08347abc0ec1d4bd2943ba5cc1a259 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000576000_147456000.pth b/checkpoint_p1/milestones/checkpoint_000576000_147456000.pth new file mode 100644 index 0000000000000000000000000000000000000000..b6ac617a1b8b27c8c3af5adeaecd26efa7049363 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000576000_147456000.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fe1be37befe4b52c7dc46d8b9e3c56a2566b734b12960b25c2c978070c948b5 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000589376_150880256.pth b/checkpoint_p1/milestones/checkpoint_000589376_150880256.pth new file mode 100644 index 0000000000000000000000000000000000000000..1f17357ef538ef71649110ff4a06eaecee8d4275 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000589376_150880256.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3de6845bac64c11f4b2c6a52b759a0812c2eed0ea45b06c351534adc8bea4b4 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000602752_154304512.pth b/checkpoint_p1/milestones/checkpoint_000602752_154304512.pth new file mode 100644 index 0000000000000000000000000000000000000000..28467a30e6ec8ff7a1fe9c761b1f0eeb495b6d6a --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000602752_154304512.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e8aecf6466f45b65a959bd2ab665d5f3f173ebda351ca8fc5b5a306d131e332 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000616096_157720576.pth b/checkpoint_p1/milestones/checkpoint_000616096_157720576.pth new file mode 100644 index 0000000000000000000000000000000000000000..3a2ca4ecb97ed014c89f849232950e5c0bea7bb1 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000616096_157720576.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7436c61c27c31f13c915f91f20b9cc18f40f9d2848bc1c9f7d39274a7e3c984c +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000629408_161128448.pth b/checkpoint_p1/milestones/checkpoint_000629408_161128448.pth new file mode 100644 index 0000000000000000000000000000000000000000..91549feef5b020dcb5b19e7fb83f3cb997c470db --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000629408_161128448.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4990ae3897ee56ac44154cb6ec703392f2c8962682b69c487f0bd7b4a0471b9 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000642752_164544512.pth b/checkpoint_p1/milestones/checkpoint_000642752_164544512.pth new file mode 100644 index 0000000000000000000000000000000000000000..5831c2a00f0e78b059b36636099f2555f357fb85 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000642752_164544512.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abf044f3f8bf55621e8aa2062e70de76fd1c533ff2d1f7ed0661acffe1f1f0d3 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000656128_167968768.pth b/checkpoint_p1/milestones/checkpoint_000656128_167968768.pth new file mode 100644 index 0000000000000000000000000000000000000000..9839f4203c570322cf9286d858402b9a1d4a2478 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000656128_167968768.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac41584895266e98354e2b86ea74e6162f0759d51f6d6e85be3038779296737e +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000669472_171384832.pth b/checkpoint_p1/milestones/checkpoint_000669472_171384832.pth new file mode 100644 index 0000000000000000000000000000000000000000..5e990c7701a3f67781d3ab93bf9387a5e22ce220 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000669472_171384832.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9d954b5a5c90301efbc0f1a46dda3e433b633db5d7dacce3bb001617cb80a0b +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000682784_174792704.pth b/checkpoint_p1/milestones/checkpoint_000682784_174792704.pth new file mode 100644 index 0000000000000000000000000000000000000000..7c6aa2262f3f959d05605e4b232b7f795dc54cf7 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000682784_174792704.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d03c8dc893e8ee24a137e6e1df99a048005a671f3144728762c72e41c0880e0 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000696128_178208768.pth b/checkpoint_p1/milestones/checkpoint_000696128_178208768.pth new file mode 100644 index 0000000000000000000000000000000000000000..4d017d370eb859f6f25b83a663042300cc34b366 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000696128_178208768.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb4978e6cb7ba6caaea54adb6a2027ff6a2e44a0b5b796b506e17c40d5c35459 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000709440_181616640.pth b/checkpoint_p1/milestones/checkpoint_000709440_181616640.pth new file mode 100644 index 0000000000000000000000000000000000000000..7e661647df758404ba78c5f315dde4df5ece4338 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000709440_181616640.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5eda84725e1e991667b9ae4205bc9a9425529014988714f263c1459912521a5 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000722816_185040896.pth b/checkpoint_p1/milestones/checkpoint_000722816_185040896.pth new file mode 100644 index 0000000000000000000000000000000000000000..7d991588815de88ee30ee0b97ad6eb7ef6acbb6b --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000722816_185040896.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:368016a1c11016fedfb6eacd940d5af6f3e92a2219e270e2cc075bf6f29955e2 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000736096_188440576.pth b/checkpoint_p1/milestones/checkpoint_000736096_188440576.pth new file mode 100644 index 0000000000000000000000000000000000000000..9896805b6611457dbc36ab493efb9615f852d753 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000736096_188440576.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61b3e709d43b241094b60fd70d9dceaab8bcbb73d421d6d1a86ce8a143c69a98 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000749472_191864832.pth b/checkpoint_p1/milestones/checkpoint_000749472_191864832.pth new file mode 100644 index 0000000000000000000000000000000000000000..2fbb6703238e323506b5e5df6a8a1ef702ef0302 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000749472_191864832.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32adeb76bf61fbeb8ae449353920f82abad65c61c74353e6d424da6393b1f5e5 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000762944_195313664.pth b/checkpoint_p1/milestones/checkpoint_000762944_195313664.pth new file mode 100644 index 0000000000000000000000000000000000000000..301dadb94ca750376adf526580026679030b7e3b --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000762944_195313664.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1111847fdac6022fb9f1779ad66724348878961a8c7141b04e87407d8f2b15df +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000776384_198754304.pth b/checkpoint_p1/milestones/checkpoint_000776384_198754304.pth new file mode 100644 index 0000000000000000000000000000000000000000..0d5659b939d3bec11617e8e3f38c8c0e3b272540 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000776384_198754304.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4118df4d28c2aaa11c42088c1c4f0449e6438a73369329f76f231d40807a0b25 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000789824_202194944.pth b/checkpoint_p1/milestones/checkpoint_000789824_202194944.pth new file mode 100644 index 0000000000000000000000000000000000000000..560dbb6aeebae2c037ad57404d263699ea2f09c1 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000789824_202194944.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4095129967e4c21bbae966ef5db092b5bbe09d5e579230ad72a014d4c8228322 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000803232_205627392.pth b/checkpoint_p1/milestones/checkpoint_000803232_205627392.pth new file mode 100644 index 0000000000000000000000000000000000000000..6a8015a450f4370cbf7d3b7cbc28964e179fb1da --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000803232_205627392.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f48de89b97598ec5dedc6b2b7a8406418d387e0b53929644572967f6dd7ad99 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000816800_209100800.pth b/checkpoint_p1/milestones/checkpoint_000816800_209100800.pth new file mode 100644 index 0000000000000000000000000000000000000000..b327ebc0069442556c01b652d50b20ae054c2335 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000816800_209100800.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea7c879e59d7c748c2f642efe38307b1a1363dc680bccabbc78d5aef59d82f3d +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000830240_212541440.pth b/checkpoint_p1/milestones/checkpoint_000830240_212541440.pth new file mode 100644 index 0000000000000000000000000000000000000000..4fcae1cfb152b5e88412ac607373f185457a52cf --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000830240_212541440.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1571855b1583b3a93faad1f09a94f9cc739e99dd5823e254d9d5f97a2af3c61 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000843680_215982080.pth b/checkpoint_p1/milestones/checkpoint_000843680_215982080.pth new file mode 100644 index 0000000000000000000000000000000000000000..840f2e6b13628bd9c57b8dfd8c4f430d379177cb --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000843680_215982080.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c83db668f11f033a543b37fe920841f59528e7581b4cf18480f780d47c1ee40a +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000857152_219430912.pth b/checkpoint_p1/milestones/checkpoint_000857152_219430912.pth new file mode 100644 index 0000000000000000000000000000000000000000..77df81bf8e99d125cc3784af011925010efa15b5 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000857152_219430912.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1a245a534a244bc1883673c3d7c8689d259ded5fa5276a6c25f65eae6b17f51 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000870592_222871552.pth b/checkpoint_p1/milestones/checkpoint_000870592_222871552.pth new file mode 100644 index 0000000000000000000000000000000000000000..d1615b841f3433cf649b46dc21fe2dc99df8c795 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000870592_222871552.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9eab88029290ec4304e4879672671ff5da4ee546d8e85d541a1c9a11dbf0de5c +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000884032_226312192.pth b/checkpoint_p1/milestones/checkpoint_000884032_226312192.pth new file mode 100644 index 0000000000000000000000000000000000000000..ad7d4348cd4bcdf67f00026bdc3b12fd10a43be6 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000884032_226312192.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0004261f6b27db036ea5acc8441de7befbdde223c1f3e3d7ca1b9208da3e043 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000897568_229777408.pth b/checkpoint_p1/milestones/checkpoint_000897568_229777408.pth new file mode 100644 index 0000000000000000000000000000000000000000..1241976b44024f18c600c6572104ab9915468b61 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000897568_229777408.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cadb410e69be327e537f067ecfcd235e877ef4c2176d5ac2d280ba7b1156cc4a +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000911104_233242624.pth b/checkpoint_p1/milestones/checkpoint_000911104_233242624.pth new file mode 100644 index 0000000000000000000000000000000000000000..aa6161768931e7edbe0f7f0c509be75a5cb53912 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000911104_233242624.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a1d842ffac21c132589ed75058241131b403563487ad1e18bb700e2ab3f2882 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000924608_236699648.pth b/checkpoint_p1/milestones/checkpoint_000924608_236699648.pth new file mode 100644 index 0000000000000000000000000000000000000000..4d1fb4489437cb30437f788eb9c382f3118ee1fd --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000924608_236699648.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:395536901cd0014d311c2b74fd1cf11a15bebf41d16ccade77e8c0d56b97f36c +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000938080_240148480.pth b/checkpoint_p1/milestones/checkpoint_000938080_240148480.pth new file mode 100644 index 0000000000000000000000000000000000000000..f9fa9522997f2b4ad8c3aa3b26984abbd0460623 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000938080_240148480.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e333d758a0dbba40274c75a04283c2cc1cdfebfc0fb7aa375ac69fcfa9279d3c +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000951392_243556352.pth b/checkpoint_p1/milestones/checkpoint_000951392_243556352.pth new file mode 100644 index 0000000000000000000000000000000000000000..431a2948dd44789cd5739c2038f991efee56cda5 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000951392_243556352.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a31563d95818054b13a0ec2577687eca697b23a033fd9235ea8dff47443085d +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000964704_246964224.pth b/checkpoint_p1/milestones/checkpoint_000964704_246964224.pth new file mode 100644 index 0000000000000000000000000000000000000000..45454738c71572e8f3e226d4b83a78682c095159 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000964704_246964224.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec7d5d34642ca84bfdd89b6634cbf7710ad6c3f82382da511dc3fd34c66c90e1 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000978144_250404864.pth b/checkpoint_p1/milestones/checkpoint_000978144_250404864.pth new file mode 100644 index 0000000000000000000000000000000000000000..4b2615a9e30422a22bcefc9bf7eb2115412cd61b --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000978144_250404864.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5ef2ba4215188e7229b4bafa1894e616c8bbaa99d074f48c3a20cd49a6beb87 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_000991616_253853696.pth b/checkpoint_p1/milestones/checkpoint_000991616_253853696.pth new file mode 100644 index 0000000000000000000000000000000000000000..ffcf510d9e64f1b93cf67a50b8b79f261fc46d78 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000991616_253853696.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ce59c246bf372350646446cc354b5e0e6254da7f839fc43d10a99b499fa9410 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001005120_257310720.pth b/checkpoint_p1/milestones/checkpoint_001005120_257310720.pth new file mode 100644 index 0000000000000000000000000000000000000000..77a6f78ed5e504ee3409d7b5967786b49b308162 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001005120_257310720.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:655865d98818ec3ea4a3aeb87613a3e5e7f61c0ac8b8ecbaf41c213f58fe2255 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001018624_260767744.pth b/checkpoint_p1/milestones/checkpoint_001018624_260767744.pth new file mode 100644 index 0000000000000000000000000000000000000000..7046bdd3a970d87de87494babb2a29562d5f1883 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001018624_260767744.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:449c82975757c7fee8862018feb1967cd1260ca7cfbf9dc132d93830df29adbd +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001032160_264232960.pth b/checkpoint_p1/milestones/checkpoint_001032160_264232960.pth new file mode 100644 index 0000000000000000000000000000000000000000..31e03b7a04541a83ff5e0480821f7080dec46a29 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001032160_264232960.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea480fb7793ac8d8abcc9c546f740e0245ca30dc2925f93fecea7a6cbd302ad5 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001045632_267681792.pth b/checkpoint_p1/milestones/checkpoint_001045632_267681792.pth new file mode 100644 index 0000000000000000000000000000000000000000..a021dd5e633fff02ed39b6d3669b3f693bd2969c --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001045632_267681792.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73f49fca6cfa2375a8e4921b90cd759108e4a0dd2a17dd55385fcf6b3df169c4 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001059136_271138816.pth b/checkpoint_p1/milestones/checkpoint_001059136_271138816.pth new file mode 100644 index 0000000000000000000000000000000000000000..ec53c60f5aaee5d67e865dbf660ee148c3966d73 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001059136_271138816.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8fe96c773f60c4e53b08943849da3591955436246a4ca311b848a143b719607 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001072640_274595840.pth b/checkpoint_p1/milestones/checkpoint_001072640_274595840.pth new file mode 100644 index 0000000000000000000000000000000000000000..b54e4cc6099b33c295e2fade76ef62dceeddb5eb --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001072640_274595840.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76dc687f9a48421a36d0fa4fa977ce393eb5dfe6accf9ff533af0b55285cf0e8 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001086144_278052864.pth b/checkpoint_p1/milestones/checkpoint_001086144_278052864.pth new file mode 100644 index 0000000000000000000000000000000000000000..46dca1d05a896fafcb4784552152104613f41299 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001086144_278052864.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9bf779f821e0dee12e98c88f66a517fb355aeb65873167b1b05b26e3b7b1c0e +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001099584_281493504.pth b/checkpoint_p1/milestones/checkpoint_001099584_281493504.pth new file mode 100644 index 0000000000000000000000000000000000000000..06f20a8399e3b38323af8a3458e5b26772af5ef1 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001099584_281493504.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e69824da1734f145b57edc32024ac7463eb5e1faaa60629fe9884e055fe26861 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001113056_284942336.pth b/checkpoint_p1/milestones/checkpoint_001113056_284942336.pth new file mode 100644 index 0000000000000000000000000000000000000000..1d942845fef7481d3f8b610ad21c5b29239b2703 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001113056_284942336.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa9ebd60c90539f0c56033c62070ce565d97073a33cd857ada4777cf039492a2 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001126528_288391168.pth b/checkpoint_p1/milestones/checkpoint_001126528_288391168.pth new file mode 100644 index 0000000000000000000000000000000000000000..c4c05d24a4f5025e15850a1557827fb9c8bc93fc --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001126528_288391168.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2e8b3e121a35af0b8cf8a6107b54e50e28ad526ab4630d682eb14dbe5df64d1 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001139968_291831808.pth b/checkpoint_p1/milestones/checkpoint_001139968_291831808.pth new file mode 100644 index 0000000000000000000000000000000000000000..3a821f91aca962ed8e5dff42ff0997dbb6a49b01 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001139968_291831808.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:322ce7d9588ff662357c6a1a927570c16c6ebfb4ea6987b2f150d74342eae6cc +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001153440_295280640.pth b/checkpoint_p1/milestones/checkpoint_001153440_295280640.pth new file mode 100644 index 0000000000000000000000000000000000000000..d7df5b59cb7f3ff42a55d665e69b83b31755d2cc --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001153440_295280640.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c386bb1f7c7e867bb09df07f69975f13cb7e2cb7b76dcc01088af728ab625ed9 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001166912_298729472.pth b/checkpoint_p1/milestones/checkpoint_001166912_298729472.pth new file mode 100644 index 0000000000000000000000000000000000000000..65195cf3d5e7359f60343c8b1b78b982868f0cdb --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001166912_298729472.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:396543ed69a527e34984fbd7b71c8e9663f531ea4825f2b1613f5e7351d343ba +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001180384_302178304.pth b/checkpoint_p1/milestones/checkpoint_001180384_302178304.pth new file mode 100644 index 0000000000000000000000000000000000000000..e5046e1c9c66796db23e381821041c55e9de0ec0 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001180384_302178304.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a049c5fc30d69cd09e77df35ac04676340a9e8964920c0ab87ba62eebe8dacca +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001193824_305618944.pth b/checkpoint_p1/milestones/checkpoint_001193824_305618944.pth new file mode 100644 index 0000000000000000000000000000000000000000..d7a71ca2aa16834b452db18df0f57c62a71799a6 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001193824_305618944.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93a2c2dc0440ce6ff91cc82eaa2b952f57b005864e3b4261e5b22a7658b45e12 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001207328_309075968.pth b/checkpoint_p1/milestones/checkpoint_001207328_309075968.pth new file mode 100644 index 0000000000000000000000000000000000000000..4119b458dba76a4a10390e6650b68861d55114d3 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001207328_309075968.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fcc459c6732177c5a9b238eea2bdd5ce19cb898cdd162e54d4829aaca780c29 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001220832_312532992.pth b/checkpoint_p1/milestones/checkpoint_001220832_312532992.pth new file mode 100644 index 0000000000000000000000000000000000000000..2a4ddf81d1f2ede79fa63550314472955c8b2e96 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001220832_312532992.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d25ff497362db70e1563e8559c2cf6f33d3ec60b9e14d6353e72763f08c4dd3 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001234336_315990016.pth b/checkpoint_p1/milestones/checkpoint_001234336_315990016.pth new file mode 100644 index 0000000000000000000000000000000000000000..0a3aafdfef2f278282565f204b6421d02fb0f588 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001234336_315990016.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc60fbe987d529b9c0cbc1492cc96c2dc028abbb14dbf7e0c96a3e4194097d3c +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001247808_319438848.pth b/checkpoint_p1/milestones/checkpoint_001247808_319438848.pth new file mode 100644 index 0000000000000000000000000000000000000000..02d7bad7eae26bda6e86fee8df6c072987135ac9 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001247808_319438848.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52ff6c2d8151c183c026eb96d779214076d95585d51c233420e6a96cd936b856 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001261280_322887680.pth b/checkpoint_p1/milestones/checkpoint_001261280_322887680.pth new file mode 100644 index 0000000000000000000000000000000000000000..072adba4b90504574f3ed18bd1c88ecab3eaff6d --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001261280_322887680.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbc98c0574e36d14dbc3b5d8197bb92a874bb573f15d3d6724a65c5a9d982ebc +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001274688_326320128.pth b/checkpoint_p1/milestones/checkpoint_001274688_326320128.pth new file mode 100644 index 0000000000000000000000000000000000000000..4850a9ff585ffb75ad1c869744e25e6dc3880a23 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001274688_326320128.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cfbed1e7fd40f48119cdeb47c8633f79290b563be1ba0a3737174549a917d39 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001288192_329777152.pth b/checkpoint_p1/milestones/checkpoint_001288192_329777152.pth new file mode 100644 index 0000000000000000000000000000000000000000..5c049f1146b64198639d99747561345eb3d08534 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001288192_329777152.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88b456ac3afa361a4bacd133a7027dfa7c0f6824181e0548812276f28d910b31 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001301536_333193216.pth b/checkpoint_p1/milestones/checkpoint_001301536_333193216.pth new file mode 100644 index 0000000000000000000000000000000000000000..f8a84f5385c61c6438a934f1d28fa020b9d5472f --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001301536_333193216.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a6a96c9a64684ed620dc2501c3181ea66c3aac5a47852a96fc4c500c4a5d629 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001315008_336642048.pth b/checkpoint_p1/milestones/checkpoint_001315008_336642048.pth new file mode 100644 index 0000000000000000000000000000000000000000..1e65896272c4754df0b67af0d775730c354fd6e5 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001315008_336642048.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6cc0474309a9269eb6b98ebbd9fe155f9e96013ed7e54c9b35a0d0cd4ca43248 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001328512_340099072.pth b/checkpoint_p1/milestones/checkpoint_001328512_340099072.pth new file mode 100644 index 0000000000000000000000000000000000000000..0e33f74f43a85e8324a9158318e606d8a762d549 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001328512_340099072.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c12b93d5661313c7b632c6242f04a06e942289a09b8ca36cf7c36757e6649586 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001342048_343564288.pth b/checkpoint_p1/milestones/checkpoint_001342048_343564288.pth new file mode 100644 index 0000000000000000000000000000000000000000..03fd6b82f3bbcc6859061f0575511b911ff75d9e --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001342048_343564288.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b65df6f13cdf251f4cab327d1f3b07f08bb77f0547673c1afc8466d84dea206c +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001355392_346980352.pth b/checkpoint_p1/milestones/checkpoint_001355392_346980352.pth new file mode 100644 index 0000000000000000000000000000000000000000..3fb1a9d0589b5d58854eebeb3c7ba46738bf12b5 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001355392_346980352.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:195b48da707a91a1404aaffd1bdcb9623af403a5f34474126d0c0b28fc69ab8f +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001368800_350412800.pth b/checkpoint_p1/milestones/checkpoint_001368800_350412800.pth new file mode 100644 index 0000000000000000000000000000000000000000..51948812db9d8625afd78806912fd5ea3a477824 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001368800_350412800.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d5c41456e5b3a501d49f646f771c2c4de78508b823e6ed009f12fe75622cd3c +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001382240_353853440.pth b/checkpoint_p1/milestones/checkpoint_001382240_353853440.pth new file mode 100644 index 0000000000000000000000000000000000000000..6576e69586c2d2ff6c6d3934bbc32739435d9295 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001382240_353853440.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02bc886adb9f5535982019798fa6543be439900fe4df6b46d11f7a7721f4f230 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001395744_357310464.pth b/checkpoint_p1/milestones/checkpoint_001395744_357310464.pth new file mode 100644 index 0000000000000000000000000000000000000000..aa5594f132a322002128df7d21895fec29887790 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001395744_357310464.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a1ed75a1a7471c17da4764de1fa7ac5f8530b30b53151040a9afcf665a6c6f7 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001409216_360759296.pth b/checkpoint_p1/milestones/checkpoint_001409216_360759296.pth new file mode 100644 index 0000000000000000000000000000000000000000..105649bdf5b2f6aa89b8bfc8e319154ffcb11293 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001409216_360759296.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81eea78df5c864e070ba2950b7147e0a528b2855e96f0647b3e1582840032189 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001422656_364199936.pth b/checkpoint_p1/milestones/checkpoint_001422656_364199936.pth new file mode 100644 index 0000000000000000000000000000000000000000..3d68af3b5258089216815e3ce594aff2ddd4c8d9 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001422656_364199936.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:addbdf71cfa7fd2c141bd461a2f31ab644062cf1d6b024a3a5bf25fc8f183125 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001436192_367665152.pth b/checkpoint_p1/milestones/checkpoint_001436192_367665152.pth new file mode 100644 index 0000000000000000000000000000000000000000..f816a642c3297cda83abf8a9d8962c595024d86d --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001436192_367665152.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:647ddecf5544fdc212bcfeee4b18cc4ee49d82e9ac1f2d5044551d265e2645f9 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001449664_371113984.pth b/checkpoint_p1/milestones/checkpoint_001449664_371113984.pth new file mode 100644 index 0000000000000000000000000000000000000000..87b21413ad09551ef4a76c754b22c5c90ee36bb2 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001449664_371113984.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:041ec82e01b7af814d51b8ee78f7ea4e4db4b3e7e053626438d2e4421c7a1d55 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001463136_374562816.pth b/checkpoint_p1/milestones/checkpoint_001463136_374562816.pth new file mode 100644 index 0000000000000000000000000000000000000000..5f415d723441299b7eca1c88fd2f83fba8f117d2 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001463136_374562816.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:011c31d47124e3a59524591b3f2b53eff4dee01ee525a1deecf8710aa92edffc +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001476672_378028032.pth b/checkpoint_p1/milestones/checkpoint_001476672_378028032.pth new file mode 100644 index 0000000000000000000000000000000000000000..3713ae61c2464d3285f5192ac72e1a57edc13909 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001476672_378028032.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a4fe2c60615fde88fe15380356618c5deb708890a9382577bb0c32592d4a069 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001490080_381460480.pth b/checkpoint_p1/milestones/checkpoint_001490080_381460480.pth new file mode 100644 index 0000000000000000000000000000000000000000..8af3f31ea8726c753b8282d192a965ae58753b91 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001490080_381460480.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5275f723b1587d062465f738dae828139749a359ddfdcd357393b75b157c7515 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001503552_384909312.pth b/checkpoint_p1/milestones/checkpoint_001503552_384909312.pth new file mode 100644 index 0000000000000000000000000000000000000000..48646cf1a6490808cb74c99fae1c50b6efd89aaa --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001503552_384909312.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49e8550fdd62d3f11e79e69bc5dab906f5869ef7671c3dc905bfa3c6a725a0ed +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001517056_388366336.pth b/checkpoint_p1/milestones/checkpoint_001517056_388366336.pth new file mode 100644 index 0000000000000000000000000000000000000000..d25a7740709ea9781c6960069e3078b74b968a7a --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001517056_388366336.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8180d8b0a68a172897a78843762aaadfd2c4edf6102786c21385f76645da4f8c +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001530560_391823360.pth b/checkpoint_p1/milestones/checkpoint_001530560_391823360.pth new file mode 100644 index 0000000000000000000000000000000000000000..c64ca4c3324a6258ad33d335bda79b7779b94588 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001530560_391823360.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a794eb11e40c5eee57d41a4fc45ee3f9a64aa3204484f08d23d0ab2299c553c6 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001544064_395280384.pth b/checkpoint_p1/milestones/checkpoint_001544064_395280384.pth new file mode 100644 index 0000000000000000000000000000000000000000..fd5b8653dd0bbd7a98d975caace90544e4b37f68 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001544064_395280384.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6dc51f616412878bfc4d8db68406886ce5dda55a8583cfed72ffc715529aa8b5 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001557536_398729216.pth b/checkpoint_p1/milestones/checkpoint_001557536_398729216.pth new file mode 100644 index 0000000000000000000000000000000000000000..a0f3e13565edd2d57702c05383db41ec1830645e --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001557536_398729216.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3da4cb00f076ba52b474b9b68d7c1305945c1770b111e5289627ea7fd34f7a73 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001571040_402186240.pth b/checkpoint_p1/milestones/checkpoint_001571040_402186240.pth new file mode 100644 index 0000000000000000000000000000000000000000..c3dfe6d5b22ff0252b402634192384205d05a22f --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001571040_402186240.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0e8ef3d37a2fc585311d13bfc90e6ad96ef26f851dcbacd46406ff90dc90a04 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001584576_405651456.pth b/checkpoint_p1/milestones/checkpoint_001584576_405651456.pth new file mode 100644 index 0000000000000000000000000000000000000000..e5448aa0867fdfc960ffa1e6323ba085b3f5e628 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001584576_405651456.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86a53e1b3287b4d5f34bc7d6b29cf81edc9bf57e7a8e684f56ef86ef3cad9265 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001598016_409092096.pth b/checkpoint_p1/milestones/checkpoint_001598016_409092096.pth new file mode 100644 index 0000000000000000000000000000000000000000..a63daf6d39be18dbeb5ae0c08774349f2925f7e6 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001598016_409092096.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b986dc9c2b1c8a08a2292e12f30e7bff40da1453918a3ed9e8c2e04ceaa56ed +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001611584_412565504.pth b/checkpoint_p1/milestones/checkpoint_001611584_412565504.pth new file mode 100644 index 0000000000000000000000000000000000000000..07d6b51cb5efacb43ac26dd10826f7b5883f3ff6 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001611584_412565504.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7657503aebd8fd97c5b0ed57d7684380dfe85733e7342b1fada0580cb77a0c51 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001625120_416030720.pth b/checkpoint_p1/milestones/checkpoint_001625120_416030720.pth new file mode 100644 index 0000000000000000000000000000000000000000..62bb02f04ff5d759617af3be068ff449559b2381 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001625120_416030720.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fa917ed22c9d2d3155ccb4eb3af40a571b8b8e886037a3fb47ae0f1c2fce092 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001638624_419487744.pth b/checkpoint_p1/milestones/checkpoint_001638624_419487744.pth new file mode 100644 index 0000000000000000000000000000000000000000..fdf84d1676c21cd012ff3e79ed65b19871e6632c --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001638624_419487744.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e0f74a101b50c5b4e7d0c4ab5d2d36faf12452753574e8c863b41cfecad3268 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001652096_422936576.pth b/checkpoint_p1/milestones/checkpoint_001652096_422936576.pth new file mode 100644 index 0000000000000000000000000000000000000000..895cb3d53638a94c6ca7974936bd18f70ed7aea2 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001652096_422936576.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f4598ed7a140d0dd2baefbd8f5072f92601ec56182de359850dbbf103675469 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001665600_426393600.pth b/checkpoint_p1/milestones/checkpoint_001665600_426393600.pth new file mode 100644 index 0000000000000000000000000000000000000000..72033cada34d83e5ace36c57662eab418571b84b --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001665600_426393600.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44d18e53d7f63c0b5f029a66e23a5e845972613c096d9f97da086f7dbd45881a +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001679040_429834240.pth b/checkpoint_p1/milestones/checkpoint_001679040_429834240.pth new file mode 100644 index 0000000000000000000000000000000000000000..d4ae1ed5612822eb0fadadfdaaf7575bc93fd3b5 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001679040_429834240.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57bd578579103dc064a19f866ae7de49e26dc6283fcac797661ae67da224adf3 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001692544_433291264.pth b/checkpoint_p1/milestones/checkpoint_001692544_433291264.pth new file mode 100644 index 0000000000000000000000000000000000000000..ebe111bdfffb4acf9c38c4d8a6a11fb654ed16c9 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001692544_433291264.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c906760bde0d7f5824981973b4626d4938591d416f180e70cb1df3451ce9fb7 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001705952_436723712.pth b/checkpoint_p1/milestones/checkpoint_001705952_436723712.pth new file mode 100644 index 0000000000000000000000000000000000000000..c4d6c3dea60d248f299a70441a5ecf0f77cc0511 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001705952_436723712.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2ecd68aa33b732940551763d7c6157e2b91d420c24737f93c134981fc1c0c7f +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001719456_440180736.pth b/checkpoint_p1/milestones/checkpoint_001719456_440180736.pth new file mode 100644 index 0000000000000000000000000000000000000000..7cc9ab471c76c979bdec9b0275a8fbf1d05f5bd7 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001719456_440180736.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96df8ca4ea1a0b76560e9038ccacef6771e4602d4e2555e6e13fbf7f7f47efbb +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001732960_443637760.pth b/checkpoint_p1/milestones/checkpoint_001732960_443637760.pth new file mode 100644 index 0000000000000000000000000000000000000000..5e2401e9cf7f4eefbc6f21f5f45dea322db2c346 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001732960_443637760.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5354ed05be31d20aeaa38afb02e81ddd09de801e63ea43956d066b87d046f2e +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001746400_447078400.pth b/checkpoint_p1/milestones/checkpoint_001746400_447078400.pth new file mode 100644 index 0000000000000000000000000000000000000000..921b7f37cac98c38c5fe71fa109a4200a91ecd44 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001746400_447078400.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7552b2a62bb5a0819ff8dd3ecb6d5f21776c0830cafe80982fc9a616afab7cbc +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001759872_450527232.pth b/checkpoint_p1/milestones/checkpoint_001759872_450527232.pth new file mode 100644 index 0000000000000000000000000000000000000000..eb29d65830a1dbd73192cfd390b459b461b8c0ec --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001759872_450527232.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac2de87107fce8fcdbb5bdccf372104cf9010d410a0f7363c39fe700432ef3d4 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001773344_453976064.pth b/checkpoint_p1/milestones/checkpoint_001773344_453976064.pth new file mode 100644 index 0000000000000000000000000000000000000000..b8d2a56ca11b93efaa35950045099bfcb047a034 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001773344_453976064.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db52a8d825afa4cef8eeb5b19af92f6533b759b9a8920d23bb513ce27a822275 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001786848_457433088.pth b/checkpoint_p1/milestones/checkpoint_001786848_457433088.pth new file mode 100644 index 0000000000000000000000000000000000000000..82e7c3df6732a31726ffdb7aafb7af145e891b80 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001786848_457433088.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:781dc050273d45670d534e31944696ed461ad3ceac14d4da3bfcf18166eb604e +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001800320_460881920.pth b/checkpoint_p1/milestones/checkpoint_001800320_460881920.pth new file mode 100644 index 0000000000000000000000000000000000000000..7ed31b5e10c5902aad0641b4213544080312ce94 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001800320_460881920.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f3186ff441946940eace3ebf636f1ec9bb318585524aa87c1c5165900191580 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001813856_464347136.pth b/checkpoint_p1/milestones/checkpoint_001813856_464347136.pth new file mode 100644 index 0000000000000000000000000000000000000000..6e6413073edc74449f2d8813187b1944226163fe --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001813856_464347136.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2ed792b19d52827e8b82c9d97cc8d31a1f6b8624d193e6730ce31244d68cc84 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001827328_467795968.pth b/checkpoint_p1/milestones/checkpoint_001827328_467795968.pth new file mode 100644 index 0000000000000000000000000000000000000000..a6e2cdbebae1de29daa7eda24a35c0af2146c2ac --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001827328_467795968.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3124db5f016fa9a5ff049bd96bca2818f868953121e2706948cf2328b4b287db +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001840800_471244800.pth b/checkpoint_p1/milestones/checkpoint_001840800_471244800.pth new file mode 100644 index 0000000000000000000000000000000000000000..b34e387891d1d40207c16e7cea8469cd97c651a4 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001840800_471244800.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72641d149bbef9d7294c4c3a6b6e16a25f821adb16cf72e5af46e929844fdfd3 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001854272_474693632.pth b/checkpoint_p1/milestones/checkpoint_001854272_474693632.pth new file mode 100644 index 0000000000000000000000000000000000000000..fcd56b54ace974347319a347e3dca9ce13633e73 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001854272_474693632.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3984be1a7a88301c8ebf01b7ddab7d2831f922f6e55cf0c330b97127905cc8f4 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001867744_478142464.pth b/checkpoint_p1/milestones/checkpoint_001867744_478142464.pth new file mode 100644 index 0000000000000000000000000000000000000000..b39e2b7b496faaa00d1dfa73484d8ef54bbb33ce --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001867744_478142464.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d178a85ec64ad0738d4ccde1cdd9dddf6af0660b479c37c116e4bc74dbc0323 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001881216_481591296.pth b/checkpoint_p1/milestones/checkpoint_001881216_481591296.pth new file mode 100644 index 0000000000000000000000000000000000000000..24d72b9224c70ab45a21be1ddcd226c6d01bb41f --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001881216_481591296.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:671922ae2bbe6b4a336feeba715c9fff9af6205e71c816990a9e1e554ab5c360 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001894688_485040128.pth b/checkpoint_p1/milestones/checkpoint_001894688_485040128.pth new file mode 100644 index 0000000000000000000000000000000000000000..d74ef510c07dce5d6e827b7e3be06e7177e1cae1 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001894688_485040128.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe62e73f71ee494ff4047361f309d967949c626487e8dc748aa8a6764b945f0d +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001908192_488497152.pth b/checkpoint_p1/milestones/checkpoint_001908192_488497152.pth new file mode 100644 index 0000000000000000000000000000000000000000..726e59ab65f3e3a3b22721431efef515c64a7647 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001908192_488497152.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e747ec3041039006a38fe0641129196e6837b8389854ec96f913c1cd6093b8b9 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001921536_491913216.pth b/checkpoint_p1/milestones/checkpoint_001921536_491913216.pth new file mode 100644 index 0000000000000000000000000000000000000000..1ca13219a16a611f9ebe6d63ec36a2b29317856d --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001921536_491913216.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9997f22130cff7f98f3111b210b675c02901f71938c4742ea10f933a3d23134 +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001934912_495337472.pth b/checkpoint_p1/milestones/checkpoint_001934912_495337472.pth new file mode 100644 index 0000000000000000000000000000000000000000..bec297060307b044e61036a3719508af4e383966 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001934912_495337472.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97d7365e9e1f8e075e68d085160c52d79d1fad682810396cd7e2e0468226c8af +size 20747723 diff --git a/checkpoint_p1/milestones/checkpoint_001948384_498786304.pth b/checkpoint_p1/milestones/checkpoint_001948384_498786304.pth new file mode 100644 index 0000000000000000000000000000000000000000..bee6a0732849c74cd20eb55efae3bc0127ba9d65 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001948384_498786304.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f12f837274a6276cfd920c320ea87d63476c4972441a736a95f154f2e978365a +size 20747723 diff --git a/config.json b/config.json index 5908b8e74a1f286ef2379715b948a6cc5b9f899b..2e8c6237cf3b032ce4047b97a3dc573800b0a0cf 100644 --- a/config.json +++ b/config.json @@ -4,7 +4,7 @@ "env": "atari_wizardofwor", "experiment": "atari_wizardofwor_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_wizardofwor --experiment=atari_wizardofwor_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_wizardofwor --wandb_job_type=SF --wandb_tags=atari", + "command_line": "--algo=APPO --env=atari_wizardofwor --experiment=atari_wizardofwor_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_wizardofwor --wandb_job_type=SF --wandb_tags=atari", "cli_args": { "algo": "APPO", "env": "atari_wizardofwor", "experiment": "atari_wizardofwor_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_wizardofwor_APPO_20231017_001529_368527" + "wandb_unique_id": "atari_wizardofwor_APPO_20231214_002345_411434" } \ No newline at end of file diff --git a/git.diff b/git.diff index 960bf7b013feefe7b56842bffdcf222f0bdf7dbd..f2014ff0d08b4ad19d4c267f4668e0df6f312c93 100644 --- a/git.diff +++ b/git.diff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:3357904f421d3f4924836316b1741bf64d5dd0e807d5e80ac07059b4c52a7008 -size 14426734 +oid sha256:de4fecb91705490b8f6f89418f0c59ae52b7bc523a512f22d64b0d2006864d31 +size 380928 diff --git a/replay.mp4 b/replay.mp4 index feaef2c18d4e0db85aa0fefe7392b068cf68f5ff..d9b4f3e0d72bc239704cc0dcfb31367dac06b129 100644 --- a/replay.mp4 +++ b/replay.mp4 @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:e1dd6a6075b509c5969f83a03b5642ad4a4e18d8ea8a880393fbbe36310a6810 -size 3366316 +oid sha256:ab2e52e56a6ec01e38568c46bd442bf30ff209a25e90fc0d70957b888ecdbf5f +size 8680470 diff --git a/sf_log.txt b/sf_log.txt index 12f7b96ac67ce0ea7d8933d35fffde41b6570802..2201e12adfc6e0b97191cf3b18c24185e0baea93 100644 --- a/sf_log.txt +++ b/sf_log.txt @@ -1,26313 +1,3 @@ -[2023-10-17 00:15:36,191][61453] Saving configuration to ./train_atari/atari_wizardofwor_APPO/config.json... -[2023-10-17 00:15:36,508][61453] Rollout worker 0 uses device cpu -[2023-10-17 00:15:36,509][61453] Rollout worker 1 uses device cpu -[2023-10-17 00:15:36,509][61453] Rollout worker 2 uses device cpu -[2023-10-17 00:15:36,510][61453] Rollout worker 3 uses device cpu -[2023-10-17 00:15:36,511][61453] Rollout worker 4 uses device cpu -[2023-10-17 00:15:36,511][61453] Rollout worker 5 uses device cpu -[2023-10-17 00:15:36,512][61453] Rollout worker 6 uses device cpu -[2023-10-17 00:15:36,512][61453] Rollout worker 7 uses device cpu -[2023-10-17 00:15:36,513][61453] Rollout worker 8 uses device cpu -[2023-10-17 00:15:36,513][61453] Rollout worker 9 uses device cpu -[2023-10-17 00:15:36,514][61453] Rollout worker 10 uses device cpu -[2023-10-17 00:15:36,514][61453] Rollout worker 11 uses device cpu -[2023-10-17 00:15:36,514][61453] Rollout worker 12 uses device cpu -[2023-10-17 00:15:36,515][61453] Rollout worker 13 uses device cpu -[2023-10-17 00:15:36,515][61453] Rollout worker 14 uses device cpu -[2023-10-17 00:15:36,515][61453] Rollout worker 15 uses device cpu -[2023-10-17 00:15:36,803][61453] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2023-10-17 00:15:36,804][61453] InferenceWorker_p0-w0: min num requests: 2 -[2023-10-17 00:15:36,807][61453] Using GPUs [1] for process 1 (actually maps to GPUs [1]) -[2023-10-17 00:15:36,807][61453] InferenceWorker_p1-w0: min num requests: 2 -[2023-10-17 00:15:36,857][61453] Starting all processes... -[2023-10-17 00:15:36,857][61453] Starting process learner_proc0 -[2023-10-17 00:15:38,571][61453] Starting process learner_proc1 -[2023-10-17 00:15:38,574][62094] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2023-10-17 00:15:38,575][62094] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0 -[2023-10-17 00:15:38,593][62094] Num visible devices: 1 -[2023-10-17 00:15:38,608][62094] Setting fixed seed 1234 -[2023-10-17 00:15:38,609][62094] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2023-10-17 00:15:38,610][62094] Initializing actor-critic model on device cuda:0 -[2023-10-17 00:15:38,610][62094] RunningMeanStd input shape: (4, 84, 84) -[2023-10-17 00:15:38,610][62094] RunningMeanStd input shape: (1,) -[2023-10-17 00:15:38,622][62094] ConvEncoder: input_channels=4 -[2023-10-17 00:15:38,775][62094] Conv encoder output size: 512 -[2023-10-17 00:15:38,777][62094] Created Actor Critic model with architecture: -[2023-10-17 00:15:38,777][62094] 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=10, bias=True) - ) -) -[2023-10-17 00:15:39,356][62094] Using optimizer -[2023-10-17 00:15:39,357][62094] No checkpoints found -[2023-10-17 00:15:39,357][62094] Did not load from checkpoint, starting from scratch! -[2023-10-17 00:15:39,357][62094] Initialized policy 0 weights for model version 0 -[2023-10-17 00:15:39,359][62094] LearnerWorker_p0 finished initialization! -[2023-10-17 00:15:39,359][62094] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2023-10-17 00:15:40,345][61453] Starting all processes... -[2023-10-17 00:15:40,348][62252] Using GPUs [1] for process 1 (actually maps to GPUs [1]) -[2023-10-17 00:15:40,348][62252] Set environment var CUDA_VISIBLE_DEVICES to '1' (GPU indices [1]) for learning process 1 -[2023-10-17 00:15:40,354][61453] Starting process inference_proc0-0 -[2023-10-17 00:15:40,355][61453] Starting process rollout_proc2 -[2023-10-17 00:15:40,354][61453] Starting process rollout_proc0 -[2023-10-17 00:15:40,367][62252] Num visible devices: 1 -[2023-10-17 00:15:40,355][61453] Starting process rollout_proc1 -[2023-10-17 00:15:40,354][61453] Starting process inference_proc1-0 -[2023-10-17 00:15:40,355][61453] Starting process rollout_proc3 -[2023-10-17 00:15:40,385][62252] Setting fixed seed 1234 -[2023-10-17 00:15:40,386][62252] Using GPUs [0] for process 1 (actually maps to GPUs [1]) -[2023-10-17 00:15:40,386][62252] Initializing actor-critic model on device cuda:0 -[2023-10-17 00:15:40,386][62252] RunningMeanStd input shape: (4, 84, 84) -[2023-10-17 00:15:40,387][62252] RunningMeanStd input shape: (1,) -[2023-10-17 00:15:40,356][61453] Starting process rollout_proc4 -[2023-10-17 00:15:40,363][61453] Starting process rollout_proc5 -[2023-10-17 00:15:40,364][61453] Starting process rollout_proc6 -[2023-10-17 00:15:40,365][61453] Starting process rollout_proc7 -[2023-10-17 00:15:40,365][61453] Starting process rollout_proc8 -[2023-10-17 00:15:40,400][62252] ConvEncoder: input_channels=4 -[2023-10-17 00:15:40,366][61453] Starting process rollout_proc9 -[2023-10-17 00:15:40,369][61453] Starting process rollout_proc10 -[2023-10-17 00:15:40,370][61453] Starting process rollout_proc11 -[2023-10-17 00:15:40,371][61453] Starting process rollout_proc12 -[2023-10-17 00:15:40,371][61453] Starting process rollout_proc13 -[2023-10-17 00:15:40,813][62252] Conv encoder output size: 512 -[2023-10-17 00:15:40,824][62252] Created Actor Critic model with architecture: -[2023-10-17 00:15:40,827][62252] 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=10, bias=True) - ) -) -[2023-10-17 00:15:41,461][62252] Using optimizer -[2023-10-17 00:15:41,462][62252] No checkpoints found -[2023-10-17 00:15:41,462][62252] Did not load from checkpoint, starting from scratch! -[2023-10-17 00:15:41,462][62252] Initialized policy 1 weights for model version 0 -[2023-10-17 00:15:41,464][62252] LearnerWorker_p1 finished initialization! -[2023-10-17 00:15:41,465][62252] Using GPUs [0] for process 1 (actually maps to GPUs [1]) -[2023-10-17 00:15:42,588][61453] Starting process rollout_proc14 -[2023-10-17 00:15:42,594][62429] Worker 8 uses CPU cores [16, 17] -[2023-10-17 00:15:42,667][61453] Starting process rollout_proc15 -[2023-10-17 00:15:42,675][62431] Worker 10 uses CPU cores [20, 21] -[2023-10-17 00:15:42,676][62372] Worker 2 uses CPU cores [4, 5] -[2023-10-17 00:15:42,777][62434] Worker 13 uses CPU cores [26, 27] -[2023-10-17 00:15:42,813][62430] Worker 9 uses CPU cores [18, 19] -[2023-10-17 00:15:42,888][62421] Worker 7 uses CPU cores [14, 15] -[2023-10-17 00:15:42,899][62408] Using GPUs [1] for process 1 (actually maps to GPUs [1]) -[2023-10-17 00:15:42,899][62408] Set environment var CUDA_VISIBLE_DEVICES to '1' (GPU indices [1]) for inference process 1 -[2023-10-17 00:15:42,918][62408] Num visible devices: 1 -[2023-10-17 00:15:42,949][62405] Worker 0 uses CPU cores [0, 1] -[2023-10-17 00:15:42,954][62417] Worker 5 uses CPU cores [10, 11] -[2023-10-17 00:15:42,956][62432] Worker 11 uses CPU cores [22, 23] -[2023-10-17 00:15:43,015][62433] Worker 12 uses CPU cores [24, 25] -[2023-10-17 00:15:43,028][62409] Worker 3 uses CPU cores [6, 7] -[2023-10-17 00:15:43,045][62418] Worker 6 uses CPU cores [12, 13] -[2023-10-17 00:15:43,099][62373] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2023-10-17 00:15:43,099][62373] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0 -[2023-10-17 00:15:43,118][62373] Num visible devices: 1 -[2023-10-17 00:15:43,261][62416] Worker 4 uses CPU cores [8, 9] -[2023-10-17 00:15:43,283][62406] Worker 1 uses CPU cores [2, 3] -[2023-10-17 00:15:43,625][62408] RunningMeanStd input shape: (4, 84, 84) -[2023-10-17 00:15:43,626][62408] RunningMeanStd input shape: (1,) -[2023-10-17 00:15:43,645][62408] ConvEncoder: input_channels=4 -[2023-10-17 00:15:43,753][62373] RunningMeanStd input shape: (4, 84, 84) -[2023-10-17 00:15:43,753][62373] RunningMeanStd input shape: (1,) -[2023-10-17 00:15:43,765][62373] ConvEncoder: input_channels=4 -[2023-10-17 00:15:43,786][62408] Conv encoder output size: 512 -[2023-10-17 00:15:43,865][62373] Conv encoder output size: 512 -[2023-10-17 00:15:44,546][61453] Inference worker 1-0 is ready! -[2023-10-17 00:15:44,548][63019] Worker 14 uses CPU cores [28, 29] -[2023-10-17 00:15:44,548][63085] Worker 15 uses CPU cores [30, 31] -[2023-10-17 00:15:44,548][61453] Inference worker 0-0 is ready! -[2023-10-17 00:15:44,548][61453] All inference workers are ready! Signal rollout workers to start! -[2023-10-17 00:15:44,550][62432] EnvRunner 11-0 uses policy 1 -[2023-10-17 00:15:44,550][62372] EnvRunner 2-0 uses policy 0 -[2023-10-17 00:15:44,550][62434] EnvRunner 13-0 uses policy 1 -[2023-10-17 00:15:44,550][62418] EnvRunner 6-0 uses policy 0 -[2023-10-17 00:15:44,550][62406] EnvRunner 1-0 uses policy 1 -[2023-10-17 00:15:44,550][62430] EnvRunner 9-0 uses policy 1 -[2023-10-17 00:15:44,550][62417] EnvRunner 5-0 uses policy 1 -[2023-10-17 00:15:44,550][62416] EnvRunner 4-0 uses policy 0 -[2023-10-17 00:15:44,550][62431] EnvRunner 10-0 uses policy 0 -[2023-10-17 00:15:44,550][62429] EnvRunner 8-0 uses policy 0 -[2023-10-17 00:15:44,550][62405] EnvRunner 0-0 uses policy 0 -[2023-10-17 00:15:44,550][61453] 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) -[2023-10-17 00:15:44,550][62421] EnvRunner 7-0 uses policy 1 -[2023-10-17 00:15:44,550][62409] EnvRunner 3-0 uses policy 1 -[2023-10-17 00:15:44,550][62433] EnvRunner 12-0 uses policy 0 -[2023-10-17 00:15:44,651][63019] EnvRunner 14-0 uses policy 0 -[2023-10-17 00:15:44,703][63085] EnvRunner 15-0 uses policy 1 -[2023-10-17 00:15:46,790][61453] Heartbeat connected on Batcher_0 -[2023-10-17 00:15:46,793][61453] Heartbeat connected on LearnerWorker_p0 -[2023-10-17 00:15:46,796][61453] Heartbeat connected on Batcher_1 -[2023-10-17 00:15:46,799][61453] Heartbeat connected on LearnerWorker_p1 -[2023-10-17 00:15:46,807][61453] Heartbeat connected on InferenceWorker_p0-w0 -[2023-10-17 00:15:46,811][61453] Heartbeat connected on RolloutWorker_w0 -[2023-10-17 00:15:46,812][61453] Heartbeat connected on InferenceWorker_p1-w0 -[2023-10-17 00:15:46,817][61453] Heartbeat connected on RolloutWorker_w2 -[2023-10-17 00:15:46,817][61453] Heartbeat connected on RolloutWorker_w1 -[2023-10-17 00:15:46,820][61453] Heartbeat connected on RolloutWorker_w3 -[2023-10-17 00:15:46,825][61453] Heartbeat connected on RolloutWorker_w4 -[2023-10-17 00:15:46,826][61453] Heartbeat connected on RolloutWorker_w5 -[2023-10-17 00:15:46,829][61453] Heartbeat connected on RolloutWorker_w6 -[2023-10-17 00:15:46,835][61453] Heartbeat connected on RolloutWorker_w8 -[2023-10-17 00:15:46,835][61453] Heartbeat connected on RolloutWorker_w7 -[2023-10-17 00:15:46,838][61453] Heartbeat connected on RolloutWorker_w9 -[2023-10-17 00:15:46,841][61453] Heartbeat connected on RolloutWorker_w10 -[2023-10-17 00:15:46,844][61453] Heartbeat connected on RolloutWorker_w11 -[2023-10-17 00:15:46,851][61453] Heartbeat connected on RolloutWorker_w13 -[2023-10-17 00:15:46,851][61453] Heartbeat connected on RolloutWorker_w12 -[2023-10-17 00:15:46,857][61453] Heartbeat connected on RolloutWorker_w14 -[2023-10-17 00:15:46,858][61453] Heartbeat connected on RolloutWorker_w15 -[2023-10-17 00:15:47,214][61453] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 620.8, 1: 650.9. Samples: 3388. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) -[2023-10-17 00:15:47,215][61453] Avg episode reward: [(0, '0.000'), (1, '0.000')] -[2023-10-17 00:15:52,214][61453] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 1015.1, 1: 1039.1. Samples: 15744. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) -[2023-10-17 00:15:52,215][61453] Avg episode reward: [(0, '0.952'), (1, '0.704')] -[2023-10-17 00:15:54,264][62373] Updated weights for policy 0, policy_version 10 (0.0009) -[2023-10-17 00:15:54,545][62408] Updated weights for policy 1, policy_version 10 (0.0008) -[2023-10-17 00:15:54,618][62373] Updated weights for policy 0, policy_version 20 (0.0008) -[2023-10-17 00:15:54,907][62408] Updated weights for policy 1, policy_version 20 (0.0008) -[2023-10-17 00:15:54,992][62373] Updated weights for policy 0, policy_version 30 (0.0009) -[2023-10-17 00:15:55,272][62408] Updated weights for policy 1, policy_version 30 (0.0008) -[2023-10-17 00:15:57,214][61453] Fps is (10 sec: 6553.7, 60 sec: 5175.0, 300 sec: 5175.0). Total num frames: 65536. Throughput: 0: 1301.2, 1: 1284.3. Samples: 32742. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-17 00:15:57,215][61453] Avg episode reward: [(0, '1.167'), (1, '1.163')] -[2023-10-17 00:15:57,379][62373] Updated weights for policy 0, policy_version 40 (0.0007) -[2023-10-17 00:15:57,391][62408] Updated weights for policy 1, policy_version 40 (0.0007) -[2023-10-17 00:15:57,743][62373] Updated weights for policy 0, policy_version 50 (0.0008) -[2023-10-17 00:15:57,747][62408] Updated weights for policy 1, policy_version 50 (0.0007) -[2023-10-17 00:15:58,106][62373] Updated weights for policy 0, policy_version 60 (0.0009) -[2023-10-17 00:15:58,112][62408] Updated weights for policy 1, policy_version 60 (0.0007) -[2023-10-17 00:16:01,476][62373] Updated weights for policy 0, policy_version 70 (0.0008) -[2023-10-17 00:16:01,506][62408] Updated weights for policy 1, policy_version 70 (0.0007) -[2023-10-17 00:16:01,841][62373] Updated weights for policy 0, policy_version 80 (0.0008) -[2023-10-17 00:16:01,872][62408] Updated weights for policy 1, policy_version 80 (0.0007) -[2023-10-17 00:16:02,208][62373] Updated weights for policy 0, policy_version 90 (0.0008) -[2023-10-17 00:16:02,214][61453] Fps is (10 sec: 13107.1, 60 sec: 7420.2, 300 sec: 7420.2). Total num frames: 131072. Throughput: 0: 1502.5, 1: 1504.9. Samples: 53122. Policy #0 lag: (min: 33.0, avg: 33.0, max: 33.0) -[2023-10-17 00:16:02,215][61453] Avg episode reward: [(0, '1.346'), (1, '1.231')] -[2023-10-17 00:16:02,225][62408] Updated weights for policy 1, policy_version 90 (0.0008) -[2023-10-17 00:16:05,662][62373] Updated weights for policy 0, policy_version 100 (0.0007) -[2023-10-17 00:16:05,721][62408] Updated weights for policy 1, policy_version 100 (0.0009) -[2023-10-17 00:16:06,028][62373] Updated weights for policy 0, policy_version 110 (0.0011) -[2023-10-17 00:16:06,080][62408] Updated weights for policy 1, policy_version 110 (0.0007) -[2023-10-17 00:16:06,386][62373] Updated weights for policy 0, policy_version 120 (0.0008) -[2023-10-17 00:16:06,447][62408] Updated weights for policy 1, policy_version 120 (0.0007) -[2023-10-17 00:16:07,214][61453] Fps is (10 sec: 19660.5, 60 sec: 11566.5, 300 sec: 11566.5). Total num frames: 262144. Throughput: 0: 1419.0, 1: 1416.9. Samples: 64272. Policy #0 lag: (min: 22.0, avg: 29.7, max: 54.0) -[2023-10-17 00:16:07,215][61453] Avg episode reward: [(0, '1.391'), (1, '1.329')] -[2023-10-17 00:16:07,216][62094] Saving new best policy, reward=1.391! -[2023-10-17 00:16:07,217][62252] Saving new best policy, reward=1.329! -[2023-10-17 00:16:10,297][62408] Updated weights for policy 1, policy_version 130 (0.0008) -[2023-10-17 00:16:10,545][62373] Updated weights for policy 0, policy_version 130 (0.0009) -[2023-10-17 00:16:10,651][62408] Updated weights for policy 1, policy_version 140 (0.0008) -[2023-10-17 00:16:10,901][62373] Updated weights for policy 0, policy_version 140 (0.0009) -[2023-10-17 00:16:11,019][62408] Updated weights for policy 1, policy_version 150 (0.0008) -[2023-10-17 00:16:11,271][62373] Updated weights for policy 0, policy_version 150 (0.0009) -[2023-10-17 00:16:11,383][62408] Updated weights for policy 1, policy_version 160 (0.0008) -[2023-10-17 00:16:11,641][62373] Updated weights for policy 0, policy_version 160 (0.0007) -[2023-10-17 00:16:12,214][61453] Fps is (10 sec: 19661.3, 60 sec: 11845.0, 300 sec: 11845.0). Total num frames: 327680. Throughput: 0: 1534.3, 1: 1536.7. Samples: 84956. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:16:12,214][61453] Avg episode reward: [(0, '1.333'), (1, '1.400')] -[2023-10-17 00:16:12,215][62252] Saving new best policy, reward=1.400! -[2023-10-17 00:16:15,246][62408] Updated weights for policy 1, policy_version 170 (0.0009) -[2023-10-17 00:16:15,432][62373] Updated weights for policy 0, policy_version 170 (0.0008) -[2023-10-17 00:16:15,600][62408] Updated weights for policy 1, policy_version 180 (0.0008) -[2023-10-17 00:16:15,798][62373] Updated weights for policy 0, policy_version 180 (0.0008) -[2023-10-17 00:16:15,966][62408] Updated weights for policy 1, policy_version 190 (0.0007) -[2023-10-17 00:16:16,166][62373] Updated weights for policy 0, policy_version 190 (0.0008) -[2023-10-17 00:16:17,214][61453] Fps is (10 sec: 13107.2, 60 sec: 12038.2, 300 sec: 12038.2). Total num frames: 393216. Throughput: 0: 1608.7, 1: 1617.7. Samples: 105388. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:16:17,215][61453] Avg episode reward: [(0, '1.510'), (1, '1.620')] -[2023-10-17 00:16:17,224][62252] Saving new best policy, reward=1.620! -[2023-10-17 00:16:17,224][62094] Saving new best policy, reward=1.510! -[2023-10-17 00:16:19,808][62408] Updated weights for policy 1, policy_version 200 (0.0007) -[2023-10-17 00:16:20,072][62373] Updated weights for policy 0, policy_version 200 (0.0008) -[2023-10-17 00:16:20,171][62408] Updated weights for policy 1, policy_version 210 (0.0008) -[2023-10-17 00:16:20,439][62373] Updated weights for policy 0, policy_version 210 (0.0008) -[2023-10-17 00:16:20,530][62408] Updated weights for policy 1, policy_version 220 (0.0008) -[2023-10-17 00:16:20,813][62373] Updated weights for policy 0, policy_version 220 (0.0009) -[2023-10-17 00:16:22,214][61453] Fps is (10 sec: 13107.2, 60 sec: 12180.2, 300 sec: 12180.2). Total num frames: 458752. Throughput: 0: 1554.0, 1: 1559.4. Samples: 117260. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) -[2023-10-17 00:16:22,214][61453] Avg episode reward: [(0, '1.660'), (1, '1.470')] -[2023-10-17 00:16:22,215][62094] Saving new best policy, reward=1.660! -[2023-10-17 00:16:24,263][62408] Updated weights for policy 1, policy_version 230 (0.0007) -[2023-10-17 00:16:24,519][62373] Updated weights for policy 0, policy_version 230 (0.0008) -[2023-10-17 00:16:24,626][62408] Updated weights for policy 1, policy_version 240 (0.0008) -[2023-10-17 00:16:24,882][62373] Updated weights for policy 0, policy_version 240 (0.0007) -[2023-10-17 00:16:24,989][62408] Updated weights for policy 1, policy_version 250 (0.0009) -[2023-10-17 00:16:25,242][62373] Updated weights for policy 0, policy_version 250 (0.0009) -[2023-10-17 00:16:27,214][61453] Fps is (10 sec: 13107.5, 60 sec: 12288.8, 300 sec: 12288.8). Total num frames: 524288. Throughput: 0: 1599.8, 1: 1616.6. Samples: 137222. Policy #0 lag: (min: 4.0, avg: 15.2, max: 36.0) -[2023-10-17 00:16:27,214][61453] Avg episode reward: [(0, '1.810'), (1, '1.730')] -[2023-10-17 00:16:27,215][62094] Saving new best policy, reward=1.810! -[2023-10-17 00:16:27,215][62252] Saving new best policy, reward=1.730! -[2023-10-17 00:16:28,810][62408] Updated weights for policy 1, policy_version 260 (0.0008) -[2023-10-17 00:16:29,138][62373] Updated weights for policy 0, policy_version 260 (0.0009) -[2023-10-17 00:16:29,167][62408] Updated weights for policy 1, policy_version 270 (0.0009) -[2023-10-17 00:16:29,512][62373] Updated weights for policy 0, policy_version 270 (0.0008) -[2023-10-17 00:16:29,531][62408] Updated weights for policy 1, policy_version 280 (0.0007) -[2023-10-17 00:16:29,888][62373] Updated weights for policy 0, policy_version 280 (0.0009) -[2023-10-17 00:16:32,214][61453] Fps is (10 sec: 13107.0, 60 sec: 12374.6, 300 sec: 12374.6). Total num frames: 589824. Throughput: 0: 1723.5, 1: 1735.9. Samples: 159060. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-17 00:16:32,215][61453] Avg episode reward: [(0, '1.720'), (1, '1.620')] -[2023-10-17 00:16:33,312][62408] Updated weights for policy 1, policy_version 290 (0.0009) -[2023-10-17 00:16:33,682][62408] Updated weights for policy 1, policy_version 300 (0.0008) -[2023-10-17 00:16:33,925][62373] Updated weights for policy 0, policy_version 290 (0.0010) -[2023-10-17 00:16:34,042][62408] Updated weights for policy 1, policy_version 310 (0.0008) -[2023-10-17 00:16:34,329][62373] Updated weights for policy 0, policy_version 300 (0.0007) -[2023-10-17 00:16:34,411][62408] Updated weights for policy 1, policy_version 320 (0.0007) -[2023-10-17 00:16:34,696][62373] Updated weights for policy 0, policy_version 310 (0.0007) -[2023-10-17 00:16:35,071][62373] Updated weights for policy 0, policy_version 320 (0.0007) -[2023-10-17 00:16:37,214][61453] Fps is (10 sec: 13106.9, 60 sec: 12444.2, 300 sec: 12444.2). Total num frames: 655360. Throughput: 0: 1695.1, 1: 1700.6. Samples: 168550. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-17 00:16:37,215][61453] Avg episode reward: [(0, '1.670'), (1, '1.660')] -[2023-10-17 00:16:38,341][62408] Updated weights for policy 1, policy_version 330 (0.0007) -[2023-10-17 00:16:38,708][62408] Updated weights for policy 1, policy_version 340 (0.0007) -[2023-10-17 00:16:38,902][62373] Updated weights for policy 0, policy_version 330 (0.0008) -[2023-10-17 00:16:39,074][62408] Updated weights for policy 1, policy_version 350 (0.0007) -[2023-10-17 00:16:39,261][62373] Updated weights for policy 0, policy_version 340 (0.0009) -[2023-10-17 00:16:39,642][62373] Updated weights for policy 0, policy_version 350 (0.0007) -[2023-10-17 00:16:42,214][61453] Fps is (10 sec: 13107.2, 60 sec: 12501.7, 300 sec: 12501.7). Total num frames: 720896. Throughput: 0: 1741.6, 1: 1758.8. Samples: 190256. Policy #0 lag: (min: 26.0, avg: 33.9, max: 58.0) -[2023-10-17 00:16:42,215][61453] Avg episode reward: [(0, '1.520'), (1, '1.740')] -[2023-10-17 00:16:42,216][62252] Saving new best policy, reward=1.740! -[2023-10-17 00:16:43,066][62408] Updated weights for policy 1, policy_version 360 (0.0007) -[2023-10-17 00:16:43,439][62408] Updated weights for policy 1, policy_version 370 (0.0009) -[2023-10-17 00:16:43,444][62373] Updated weights for policy 0, policy_version 360 (0.0008) -[2023-10-17 00:16:43,806][62408] Updated weights for policy 1, policy_version 380 (0.0008) -[2023-10-17 00:16:43,807][62373] Updated weights for policy 0, policy_version 370 (0.0008) -[2023-10-17 00:16:44,177][62373] Updated weights for policy 0, policy_version 380 (0.0009) -[2023-10-17 00:16:47,214][61453] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12550.0). Total num frames: 786432. Throughput: 0: 1759.2, 1: 1770.2. Samples: 211944. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:16:47,215][61453] Avg episode reward: [(0, '1.550'), (1, '1.900')] -[2023-10-17 00:16:47,218][62252] Saving new best policy, reward=1.900! -[2023-10-17 00:16:47,630][62408] Updated weights for policy 1, policy_version 390 (0.0008) -[2023-10-17 00:16:47,997][62408] Updated weights for policy 1, policy_version 400 (0.0008) -[2023-10-17 00:16:48,137][62373] Updated weights for policy 0, policy_version 390 (0.0008) -[2023-10-17 00:16:48,368][62408] Updated weights for policy 1, policy_version 410 (0.0008) -[2023-10-17 00:16:48,505][62373] Updated weights for policy 0, policy_version 400 (0.0008) -[2023-10-17 00:16:48,861][62373] Updated weights for policy 0, policy_version 410 (0.0009) -[2023-10-17 00:16:52,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 12591.2). Total num frames: 851968. Throughput: 0: 1740.5, 1: 1749.5. Samples: 221322. Policy #0 lag: (min: 22.0, avg: 24.1, max: 53.0) -[2023-10-17 00:16:52,214][61453] Avg episode reward: [(0, '1.580'), (1, '2.130')] -[2023-10-17 00:16:52,340][62408] Updated weights for policy 1, policy_version 420 (0.0008) -[2023-10-17 00:16:52,706][62408] Updated weights for policy 1, policy_version 430 (0.0008) -[2023-10-17 00:16:52,709][62373] Updated weights for policy 0, policy_version 420 (0.0009) -[2023-10-17 00:16:53,068][62408] Updated weights for policy 1, policy_version 440 (0.0008) -[2023-10-17 00:16:53,077][62373] Updated weights for policy 0, policy_version 430 (0.0008) -[2023-10-17 00:16:53,364][62252] Saving new best policy, reward=2.130! -[2023-10-17 00:16:53,443][62373] Updated weights for policy 0, policy_version 440 (0.0007) -[2023-10-17 00:16:56,968][62408] Updated weights for policy 1, policy_version 450 (0.0008) -[2023-10-17 00:16:57,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 12626.7). Total num frames: 917504. Throughput: 0: 1754.8, 1: 1762.6. Samples: 243240. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-10-17 00:16:57,214][61453] Avg episode reward: [(0, '1.690'), (1, '2.100')] -[2023-10-17 00:16:57,305][62373] Updated weights for policy 0, policy_version 450 (0.0009) -[2023-10-17 00:16:57,339][62408] Updated weights for policy 1, policy_version 460 (0.0008) -[2023-10-17 00:16:57,677][62373] Updated weights for policy 0, policy_version 460 (0.0007) -[2023-10-17 00:16:57,706][62408] Updated weights for policy 1, policy_version 470 (0.0008) -[2023-10-17 00:16:58,042][62373] Updated weights for policy 0, policy_version 470 (0.0007) -[2023-10-17 00:16:58,068][62408] Updated weights for policy 1, policy_version 480 (0.0008) -[2023-10-17 00:16:58,412][62373] Updated weights for policy 0, policy_version 480 (0.0009) -[2023-10-17 00:17:01,813][62408] Updated weights for policy 1, policy_version 490 (0.0007) -[2023-10-17 00:17:02,173][62408] Updated weights for policy 1, policy_version 500 (0.0007) -[2023-10-17 00:17:02,189][62373] Updated weights for policy 0, policy_version 490 (0.0009) -[2023-10-17 00:17:02,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 12657.6). Total num frames: 983040. Throughput: 0: 1769.0, 1: 1768.5. Samples: 264578. Policy #0 lag: (min: 1.0, avg: 4.6, max: 33.0) -[2023-10-17 00:17:02,214][61453] Avg episode reward: [(0, '1.820'), (1, '2.200')] -[2023-10-17 00:17:02,528][62408] Updated weights for policy 1, policy_version 510 (0.0009) -[2023-10-17 00:17:02,564][62373] Updated weights for policy 0, policy_version 500 (0.0008) -[2023-10-17 00:17:02,600][62252] Saving new best policy, reward=2.200! -[2023-10-17 00:17:02,937][62373] Updated weights for policy 0, policy_version 510 (0.0010) -[2023-10-17 00:17:03,007][62094] Saving new best policy, reward=1.820! -[2023-10-17 00:17:06,411][62408] Updated weights for policy 1, policy_version 520 (0.0008) -[2023-10-17 00:17:06,785][62408] Updated weights for policy 1, policy_version 530 (0.0008) -[2023-10-17 00:17:06,840][62373] Updated weights for policy 0, policy_version 520 (0.0008) -[2023-10-17 00:17:07,138][62408] Updated weights for policy 1, policy_version 540 (0.0009) -[2023-10-17 00:17:07,204][62373] Updated weights for policy 0, policy_version 530 (0.0008) -[2023-10-17 00:17:07,214][61453] Fps is (10 sec: 13107.2, 60 sec: 13107.3, 300 sec: 12684.8). Total num frames: 1048576. Throughput: 0: 1745.8, 1: 1755.0. Samples: 274794. Policy #0 lag: (min: 26.0, avg: 26.2, max: 36.0) -[2023-10-17 00:17:07,214][61453] Avg episode reward: [(0, '1.970'), (1, '2.250')] -[2023-10-17 00:17:07,287][62252] Saving new best policy, reward=2.250! -[2023-10-17 00:17:07,574][62373] Updated weights for policy 0, policy_version 540 (0.0008) -[2023-10-17 00:17:07,718][62094] Saving new best policy, reward=1.970! -[2023-10-17 00:17:10,665][62408] Updated weights for policy 1, policy_version 550 (0.0008) -[2023-10-17 00:17:11,035][62408] Updated weights for policy 1, policy_version 560 (0.0010) -[2023-10-17 00:17:11,404][62408] Updated weights for policy 1, policy_version 570 (0.0008) -[2023-10-17 00:17:11,522][62373] Updated weights for policy 0, policy_version 550 (0.0007) -[2023-10-17 00:17:11,892][62373] Updated weights for policy 0, policy_version 560 (0.0007) -[2023-10-17 00:17:12,214][61453] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 13082.7). Total num frames: 1146880. Throughput: 0: 1771.7, 1: 1768.0. Samples: 296510. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:17:12,215][61453] Avg episode reward: [(0, '1.910'), (1, '2.250')] -[2023-10-17 00:17:12,259][62373] Updated weights for policy 0, policy_version 570 (0.0011) -[2023-10-17 00:17:15,315][62408] Updated weights for policy 1, policy_version 580 (0.0008) -[2023-10-17 00:17:15,676][62408] Updated weights for policy 1, policy_version 590 (0.0007) -[2023-10-17 00:17:16,040][62408] Updated weights for policy 1, policy_version 600 (0.0008) -[2023-10-17 00:17:16,069][62373] Updated weights for policy 0, policy_version 580 (0.0007) -[2023-10-17 00:17:16,436][62373] Updated weights for policy 0, policy_version 590 (0.0010) -[2023-10-17 00:17:16,814][62373] Updated weights for policy 0, policy_version 600 (0.0010) -[2023-10-17 00:17:17,214][61453] Fps is (10 sec: 19660.6, 60 sec: 14199.5, 300 sec: 13437.6). Total num frames: 1245184. Throughput: 0: 1747.1, 1: 1750.0. Samples: 316428. Policy #0 lag: (min: 17.0, avg: 27.9, max: 49.0) -[2023-10-17 00:17:17,215][61453] Avg episode reward: [(0, '1.700'), (1, '2.070')] -[2023-10-17 00:17:19,905][62408] Updated weights for policy 1, policy_version 610 (0.0007) -[2023-10-17 00:17:20,276][62408] Updated weights for policy 1, policy_version 620 (0.0008) -[2023-10-17 00:17:20,623][62373] Updated weights for policy 0, policy_version 610 (0.0009) -[2023-10-17 00:17:20,636][62408] Updated weights for policy 1, policy_version 630 (0.0008) -[2023-10-17 00:17:21,000][62408] Updated weights for policy 1, policy_version 640 (0.0009) -[2023-10-17 00:17:21,027][62373] Updated weights for policy 0, policy_version 620 (0.0008) -[2023-10-17 00:17:21,404][62373] Updated weights for policy 0, policy_version 630 (0.0008) -[2023-10-17 00:17:21,779][62373] Updated weights for policy 0, policy_version 640 (0.0007) -[2023-10-17 00:17:22,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 13420.7). Total num frames: 1310720. Throughput: 0: 1772.7, 1: 1784.8. Samples: 328634. Policy #0 lag: (min: 28.0, avg: 38.8, max: 60.0) -[2023-10-17 00:17:22,215][61453] Avg episode reward: [(0, '1.920'), (1, '2.080')] -[2023-10-17 00:17:24,872][62408] Updated weights for policy 1, policy_version 650 (0.0007) -[2023-10-17 00:17:25,232][62408] Updated weights for policy 1, policy_version 660 (0.0008) -[2023-10-17 00:17:25,413][62373] Updated weights for policy 0, policy_version 650 (0.0007) -[2023-10-17 00:17:25,593][62408] Updated weights for policy 1, policy_version 670 (0.0009) -[2023-10-17 00:17:25,778][62373] Updated weights for policy 0, policy_version 660 (0.0010) -[2023-10-17 00:17:26,151][62373] Updated weights for policy 0, policy_version 670 (0.0010) -[2023-10-17 00:17:27,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13405.5). Total num frames: 1376256. Throughput: 0: 1756.1, 1: 1756.2. Samples: 348308. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:17:27,215][61453] Avg episode reward: [(0, '2.010'), (1, '2.010')] -[2023-10-17 00:17:27,215][62094] Saving new best policy, reward=2.010! -[2023-10-17 00:17:29,559][62408] Updated weights for policy 1, policy_version 680 (0.0007) -[2023-10-17 00:17:29,930][62408] Updated weights for policy 1, policy_version 690 (0.0007) -[2023-10-17 00:17:29,957][62373] Updated weights for policy 0, policy_version 680 (0.0008) -[2023-10-17 00:17:30,299][62408] Updated weights for policy 1, policy_version 700 (0.0007) -[2023-10-17 00:17:30,339][62373] Updated weights for policy 0, policy_version 690 (0.0007) -[2023-10-17 00:17:30,700][62373] Updated weights for policy 0, policy_version 700 (0.0008) -[2023-10-17 00:17:32,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13391.6). Total num frames: 1441792. Throughput: 0: 1756.0, 1: 1751.2. Samples: 369768. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-17 00:17:32,215][61453] Avg episode reward: [(0, '1.560'), (1, '2.000')] -[2023-10-17 00:17:32,223][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000000704_720896.pth... -[2023-10-17 00:17:32,223][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000000704_720896.pth... -[2023-10-17 00:17:33,968][62408] Updated weights for policy 1, policy_version 710 (0.0007) -[2023-10-17 00:17:34,325][62408] Updated weights for policy 1, policy_version 720 (0.0010) -[2023-10-17 00:17:34,460][62373] Updated weights for policy 0, policy_version 710 (0.0008) -[2023-10-17 00:17:34,696][62408] Updated weights for policy 1, policy_version 730 (0.0007) -[2023-10-17 00:17:34,835][62373] Updated weights for policy 0, policy_version 720 (0.0007) -[2023-10-17 00:17:35,206][62373] Updated weights for policy 0, policy_version 730 (0.0007) -[2023-10-17 00:17:37,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13379.0). Total num frames: 1507328. Throughput: 0: 1772.1, 1: 1761.5. Samples: 380334. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-17 00:17:37,215][61453] Avg episode reward: [(0, '1.530'), (1, '2.180')] -[2023-10-17 00:17:38,563][62408] Updated weights for policy 1, policy_version 740 (0.0008) -[2023-10-17 00:17:38,928][62408] Updated weights for policy 1, policy_version 750 (0.0008) -[2023-10-17 00:17:39,011][62373] Updated weights for policy 0, policy_version 740 (0.0008) -[2023-10-17 00:17:39,296][62408] Updated weights for policy 1, policy_version 760 (0.0009) -[2023-10-17 00:17:39,380][62373] Updated weights for policy 0, policy_version 750 (0.0008) -[2023-10-17 00:17:39,757][62373] Updated weights for policy 0, policy_version 760 (0.0009) -[2023-10-17 00:17:42,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13367.4). Total num frames: 1572864. Throughput: 0: 1759.3, 1: 1759.6. Samples: 401590. Policy #0 lag: (min: 31.0, avg: 32.1, max: 51.0) -[2023-10-17 00:17:42,214][61453] Avg episode reward: [(0, '1.580'), (1, '2.290')] -[2023-10-17 00:17:42,215][62252] Saving new best policy, reward=2.290! -[2023-10-17 00:17:43,119][62408] Updated weights for policy 1, policy_version 770 (0.0008) -[2023-10-17 00:17:43,499][62408] Updated weights for policy 1, policy_version 780 (0.0009) -[2023-10-17 00:17:43,690][62373] Updated weights for policy 0, policy_version 770 (0.0009) -[2023-10-17 00:17:43,857][62408] Updated weights for policy 1, policy_version 790 (0.0009) -[2023-10-17 00:17:44,053][62373] Updated weights for policy 0, policy_version 780 (0.0007) -[2023-10-17 00:17:44,214][62408] Updated weights for policy 1, policy_version 800 (0.0009) -[2023-10-17 00:17:44,426][62373] Updated weights for policy 0, policy_version 790 (0.0007) -[2023-10-17 00:17:44,792][62373] Updated weights for policy 0, policy_version 800 (0.0009) -[2023-10-17 00:17:47,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13356.8). Total num frames: 1638400. Throughput: 0: 1764.7, 1: 1772.4. Samples: 423750. Policy #0 lag: (min: 15.0, avg: 15.4, max: 28.0) -[2023-10-17 00:17:47,214][61453] Avg episode reward: [(0, '1.720'), (1, '2.470')] -[2023-10-17 00:17:47,223][62252] Saving new best policy, reward=2.470! -[2023-10-17 00:17:48,044][62408] Updated weights for policy 1, policy_version 810 (0.0010) -[2023-10-17 00:17:48,418][62408] Updated weights for policy 1, policy_version 820 (0.0009) -[2023-10-17 00:17:48,646][62373] Updated weights for policy 0, policy_version 810 (0.0008) -[2023-10-17 00:17:48,791][62408] Updated weights for policy 1, policy_version 830 (0.0008) -[2023-10-17 00:17:49,015][62373] Updated weights for policy 0, policy_version 820 (0.0008) -[2023-10-17 00:17:49,379][62373] Updated weights for policy 0, policy_version 830 (0.0007) -[2023-10-17 00:17:52,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13347.0). Total num frames: 1703936. Throughput: 0: 1759.9, 1: 1760.9. Samples: 433232. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-17 00:17:52,215][61453] Avg episode reward: [(0, '1.700'), (1, '2.640')] -[2023-10-17 00:17:52,217][62252] Saving new best policy, reward=2.640! -[2023-10-17 00:17:52,737][62408] Updated weights for policy 1, policy_version 840 (0.0008) -[2023-10-17 00:17:53,073][62373] Updated weights for policy 0, policy_version 840 (0.0009) -[2023-10-17 00:17:53,103][62408] Updated weights for policy 1, policy_version 850 (0.0009) -[2023-10-17 00:17:53,449][62373] Updated weights for policy 0, policy_version 850 (0.0010) -[2023-10-17 00:17:53,474][62408] Updated weights for policy 1, policy_version 860 (0.0007) -[2023-10-17 00:17:53,814][62373] Updated weights for policy 0, policy_version 860 (0.0007) -[2023-10-17 00:17:57,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13338.0). Total num frames: 1769472. Throughput: 0: 1768.1, 1: 1761.2. Samples: 455330. Policy #0 lag: (min: 8.0, avg: 30.4, max: 40.0) -[2023-10-17 00:17:57,215][61453] Avg episode reward: [(0, '1.860'), (1, '2.440')] -[2023-10-17 00:17:57,407][62408] Updated weights for policy 1, policy_version 870 (0.0009) -[2023-10-17 00:17:57,595][62373] Updated weights for policy 0, policy_version 870 (0.0007) -[2023-10-17 00:17:57,768][62408] Updated weights for policy 1, policy_version 880 (0.0007) -[2023-10-17 00:17:57,966][62373] Updated weights for policy 0, policy_version 880 (0.0007) -[2023-10-17 00:17:58,139][62408] Updated weights for policy 1, policy_version 890 (0.0009) -[2023-10-17 00:17:58,339][62373] Updated weights for policy 0, policy_version 890 (0.0007) -[2023-10-17 00:18:01,954][62408] Updated weights for policy 1, policy_version 900 (0.0007) -[2023-10-17 00:18:02,166][62373] Updated weights for policy 0, policy_version 900 (0.0008) -[2023-10-17 00:18:02,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13329.6). Total num frames: 1835008. Throughput: 0: 1797.7, 1: 1780.9. Samples: 477466. Policy #0 lag: (min: 16.0, avg: 18.3, max: 46.0) -[2023-10-17 00:18:02,215][61453] Avg episode reward: [(0, '2.130'), (1, '2.470')] -[2023-10-17 00:18:02,317][62408] Updated weights for policy 1, policy_version 910 (0.0007) -[2023-10-17 00:18:02,547][62373] Updated weights for policy 0, policy_version 910 (0.0007) -[2023-10-17 00:18:02,691][62408] Updated weights for policy 1, policy_version 920 (0.0007) -[2023-10-17 00:18:02,928][62373] Updated weights for policy 0, policy_version 920 (0.0007) -[2023-10-17 00:18:03,226][62094] Saving new best policy, reward=2.130! -[2023-10-17 00:18:06,555][62408] Updated weights for policy 1, policy_version 930 (0.0007) -[2023-10-17 00:18:06,802][62373] Updated weights for policy 0, policy_version 930 (0.0009) -[2023-10-17 00:18:06,934][62408] Updated weights for policy 1, policy_version 940 (0.0009) -[2023-10-17 00:18:07,203][62373] Updated weights for policy 0, policy_version 940 (0.0008) -[2023-10-17 00:18:07,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13321.8). Total num frames: 1900544. Throughput: 0: 1770.4, 1: 1750.2. Samples: 487060. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:18:07,215][61453] Avg episode reward: [(0, '2.390'), (1, '2.690')] -[2023-10-17 00:18:07,295][62408] Updated weights for policy 1, policy_version 950 (0.0007) -[2023-10-17 00:18:07,568][62373] Updated weights for policy 0, policy_version 950 (0.0007) -[2023-10-17 00:18:07,671][62252] Saving new best policy, reward=2.690! -[2023-10-17 00:18:07,673][62408] Updated weights for policy 1, policy_version 960 (0.0009) -[2023-10-17 00:18:07,929][62094] Saving new best policy, reward=2.390! -[2023-10-17 00:18:07,932][62373] Updated weights for policy 0, policy_version 960 (0.0007) -[2023-10-17 00:18:11,520][62408] Updated weights for policy 1, policy_version 970 (0.0007) -[2023-10-17 00:18:11,783][62373] Updated weights for policy 0, policy_version 970 (0.0010) -[2023-10-17 00:18:11,891][62408] Updated weights for policy 1, policy_version 980 (0.0007) -[2023-10-17 00:18:12,144][62373] Updated weights for policy 0, policy_version 980 (0.0007) -[2023-10-17 00:18:12,214][61453] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 13314.6). Total num frames: 1966080. Throughput: 0: 1787.0, 1: 1771.4. Samples: 508436. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-17 00:18:12,215][61453] Avg episode reward: [(0, '2.290'), (1, '2.460')] -[2023-10-17 00:18:12,258][62408] Updated weights for policy 1, policy_version 990 (0.0007) -[2023-10-17 00:18:12,519][62373] Updated weights for policy 0, policy_version 990 (0.0008) -[2023-10-17 00:18:16,263][62408] Updated weights for policy 1, policy_version 1000 (0.0009) -[2023-10-17 00:18:16,328][62373] Updated weights for policy 0, policy_version 1000 (0.0008) -[2023-10-17 00:18:16,648][62408] Updated weights for policy 1, policy_version 1010 (0.0010) -[2023-10-17 00:18:16,707][62373] Updated weights for policy 0, policy_version 1010 (0.0007) -[2023-10-17 00:18:17,008][62408] Updated weights for policy 1, policy_version 1020 (0.0007) -[2023-10-17 00:18:17,084][62373] Updated weights for policy 0, policy_version 1020 (0.0009) -[2023-10-17 00:18:17,214][61453] Fps is (10 sec: 16384.1, 60 sec: 13653.3, 300 sec: 13522.4). Total num frames: 2064384. Throughput: 0: 1767.9, 1: 1750.5. Samples: 528094. Policy #0 lag: (min: 21.0, avg: 26.6, max: 53.0) -[2023-10-17 00:18:17,215][61453] Avg episode reward: [(0, '2.210'), (1, '2.140')] -[2023-10-17 00:18:20,759][62408] Updated weights for policy 1, policy_version 1030 (0.0007) -[2023-10-17 00:18:20,900][62373] Updated weights for policy 0, policy_version 1030 (0.0008) -[2023-10-17 00:18:21,121][62408] Updated weights for policy 1, policy_version 1040 (0.0009) -[2023-10-17 00:18:21,258][62373] Updated weights for policy 0, policy_version 1040 (0.0007) -[2023-10-17 00:18:21,488][62408] Updated weights for policy 1, policy_version 1050 (0.0008) -[2023-10-17 00:18:21,635][62373] Updated weights for policy 0, policy_version 1050 (0.0008) -[2023-10-17 00:18:22,214][61453] Fps is (10 sec: 19660.5, 60 sec: 14199.4, 300 sec: 13717.1). Total num frames: 2162688. Throughput: 0: 1773.6, 1: 1767.3. Samples: 539676. Policy #0 lag: (min: 3.0, avg: 12.9, max: 35.0) -[2023-10-17 00:18:22,215][61453] Avg episode reward: [(0, '2.230'), (1, '2.530')] -[2023-10-17 00:18:25,377][62408] Updated weights for policy 1, policy_version 1060 (0.0008) -[2023-10-17 00:18:25,471][62373] Updated weights for policy 0, policy_version 1060 (0.0007) -[2023-10-17 00:18:25,740][62408] Updated weights for policy 1, policy_version 1070 (0.0010) -[2023-10-17 00:18:25,844][62373] Updated weights for policy 0, policy_version 1070 (0.0011) -[2023-10-17 00:18:26,105][62408] Updated weights for policy 1, policy_version 1080 (0.0008) -[2023-10-17 00:18:26,214][62373] Updated weights for policy 0, policy_version 1080 (0.0008) -[2023-10-17 00:18:27,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 13698.3). Total num frames: 2228224. Throughput: 0: 1772.1, 1: 1753.9. Samples: 560260. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-10-17 00:18:27,215][61453] Avg episode reward: [(0, '2.230'), (1, '2.050')] -[2023-10-17 00:18:29,927][62373] Updated weights for policy 0, policy_version 1090 (0.0009) -[2023-10-17 00:18:30,081][62408] Updated weights for policy 1, policy_version 1090 (0.0007) -[2023-10-17 00:18:30,305][62373] Updated weights for policy 0, policy_version 1100 (0.0009) -[2023-10-17 00:18:30,446][62408] Updated weights for policy 1, policy_version 1100 (0.0009) -[2023-10-17 00:18:30,670][62373] Updated weights for policy 0, policy_version 1110 (0.0009) -[2023-10-17 00:18:30,809][62408] Updated weights for policy 1, policy_version 1110 (0.0008) -[2023-10-17 00:18:31,037][62373] Updated weights for policy 0, policy_version 1120 (0.0010) -[2023-10-17 00:18:31,178][62408] Updated weights for policy 1, policy_version 1120 (0.0009) -[2023-10-17 00:18:32,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13680.7). Total num frames: 2293760. Throughput: 0: 1758.4, 1: 1731.0. Samples: 580774. Policy #0 lag: (min: 6.0, avg: 14.9, max: 38.0) -[2023-10-17 00:18:32,215][61453] Avg episode reward: [(0, '2.000'), (1, '1.830')] -[2023-10-17 00:18:34,860][62373] Updated weights for policy 0, policy_version 1130 (0.0007) -[2023-10-17 00:18:34,974][62408] Updated weights for policy 1, policy_version 1130 (0.0009) -[2023-10-17 00:18:35,232][62373] Updated weights for policy 0, policy_version 1140 (0.0007) -[2023-10-17 00:18:35,336][62408] Updated weights for policy 1, policy_version 1140 (0.0008) -[2023-10-17 00:18:35,597][62373] Updated weights for policy 0, policy_version 1150 (0.0009) -[2023-10-17 00:18:35,716][62408] Updated weights for policy 1, policy_version 1150 (0.0009) -[2023-10-17 00:18:37,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13664.1). Total num frames: 2359296. Throughput: 0: 1777.1, 1: 1755.3. Samples: 592188. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:18:37,215][61453] Avg episode reward: [(0, '2.000'), (1, '1.930')] -[2023-10-17 00:18:39,521][62373] Updated weights for policy 0, policy_version 1160 (0.0008) -[2023-10-17 00:18:39,598][62408] Updated weights for policy 1, policy_version 1160 (0.0008) -[2023-10-17 00:18:39,886][62373] Updated weights for policy 0, policy_version 1170 (0.0008) -[2023-10-17 00:18:39,962][62408] Updated weights for policy 1, policy_version 1170 (0.0007) -[2023-10-17 00:18:40,253][62373] Updated weights for policy 0, policy_version 1180 (0.0008) -[2023-10-17 00:18:40,333][62408] Updated weights for policy 1, policy_version 1180 (0.0007) -[2023-10-17 00:18:42,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13648.4). Total num frames: 2424832. Throughput: 0: 1746.7, 1: 1730.4. Samples: 611798. Policy #0 lag: (min: 31.0, avg: 36.6, max: 63.0) -[2023-10-17 00:18:42,215][61453] Avg episode reward: [(0, '2.150'), (1, '1.560')] -[2023-10-17 00:18:44,090][62373] Updated weights for policy 0, policy_version 1190 (0.0010) -[2023-10-17 00:18:44,165][62408] Updated weights for policy 1, policy_version 1190 (0.0010) -[2023-10-17 00:18:44,458][62373] Updated weights for policy 0, policy_version 1200 (0.0009) -[2023-10-17 00:18:44,536][62408] Updated weights for policy 1, policy_version 1200 (0.0008) -[2023-10-17 00:18:44,830][62373] Updated weights for policy 0, policy_version 1210 (0.0008) -[2023-10-17 00:18:44,900][62408] Updated weights for policy 1, policy_version 1210 (0.0008) -[2023-10-17 00:18:47,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13633.6). Total num frames: 2490368. Throughput: 0: 1742.6, 1: 1729.5. Samples: 633708. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:18:47,215][61453] Avg episode reward: [(0, '2.020'), (1, '1.820')] -[2023-10-17 00:18:48,673][62373] Updated weights for policy 0, policy_version 1220 (0.0007) -[2023-10-17 00:18:48,851][62408] Updated weights for policy 1, policy_version 1220 (0.0009) -[2023-10-17 00:18:49,047][62373] Updated weights for policy 0, policy_version 1230 (0.0008) -[2023-10-17 00:18:49,220][62408] Updated weights for policy 1, policy_version 1230 (0.0009) -[2023-10-17 00:18:49,404][62373] Updated weights for policy 0, policy_version 1240 (0.0007) -[2023-10-17 00:18:49,581][62408] Updated weights for policy 1, policy_version 1240 (0.0008) -[2023-10-17 00:18:52,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13619.6). Total num frames: 2555904. Throughput: 0: 1746.4, 1: 1728.3. Samples: 643418. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:18:52,215][61453] Avg episode reward: [(0, '1.950'), (1, '2.130')] -[2023-10-17 00:18:53,237][62373] Updated weights for policy 0, policy_version 1250 (0.0007) -[2023-10-17 00:18:53,353][62408] Updated weights for policy 1, policy_version 1250 (0.0007) -[2023-10-17 00:18:53,613][62373] Updated weights for policy 0, policy_version 1260 (0.0008) -[2023-10-17 00:18:53,717][62408] Updated weights for policy 1, policy_version 1260 (0.0007) -[2023-10-17 00:18:53,985][62373] Updated weights for policy 0, policy_version 1270 (0.0008) -[2023-10-17 00:18:54,079][62408] Updated weights for policy 1, policy_version 1270 (0.0007) -[2023-10-17 00:18:54,349][62373] Updated weights for policy 0, policy_version 1280 (0.0007) -[2023-10-17 00:18:54,446][62408] Updated weights for policy 1, policy_version 1280 (0.0007) -[2023-10-17 00:18:57,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13606.3). Total num frames: 2621440. Throughput: 0: 1750.2, 1: 1730.0. Samples: 665044. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) -[2023-10-17 00:18:57,215][61453] Avg episode reward: [(0, '2.100'), (1, '2.120')] -[2023-10-17 00:18:58,200][62373] Updated weights for policy 0, policy_version 1290 (0.0007) -[2023-10-17 00:18:58,400][62408] Updated weights for policy 1, policy_version 1290 (0.0007) -[2023-10-17 00:18:58,573][62373] Updated weights for policy 0, policy_version 1300 (0.0007) -[2023-10-17 00:18:58,771][62408] Updated weights for policy 1, policy_version 1300 (0.0007) -[2023-10-17 00:18:58,951][62373] Updated weights for policy 0, policy_version 1310 (0.0009) -[2023-10-17 00:18:59,138][62408] Updated weights for policy 1, policy_version 1310 (0.0007) -[2023-10-17 00:19:02,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13593.7). Total num frames: 2686976. Throughput: 0: 1776.5, 1: 1757.0. Samples: 687102. Policy #0 lag: (min: 26.0, avg: 28.0, max: 58.0) -[2023-10-17 00:19:02,214][61453] Avg episode reward: [(0, '2.010'), (1, '2.390')] -[2023-10-17 00:19:02,707][62373] Updated weights for policy 0, policy_version 1320 (0.0008) -[2023-10-17 00:19:03,050][62408] Updated weights for policy 1, policy_version 1320 (0.0007) -[2023-10-17 00:19:03,080][62373] Updated weights for policy 0, policy_version 1330 (0.0010) -[2023-10-17 00:19:03,423][62408] Updated weights for policy 1, policy_version 1330 (0.0008) -[2023-10-17 00:19:03,461][62373] Updated weights for policy 0, policy_version 1340 (0.0008) -[2023-10-17 00:19:03,784][62408] Updated weights for policy 1, policy_version 1340 (0.0010) -[2023-10-17 00:19:07,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 13581.6). Total num frames: 2752512. Throughput: 0: 1756.3, 1: 1732.4. Samples: 696668. Policy #0 lag: (min: 28.0, avg: 30.1, max: 59.0) -[2023-10-17 00:19:07,215][61453] Avg episode reward: [(0, '2.120'), (1, '2.200')] -[2023-10-17 00:19:07,324][62373] Updated weights for policy 0, policy_version 1350 (0.0008) -[2023-10-17 00:19:07,693][62373] Updated weights for policy 0, policy_version 1360 (0.0008) -[2023-10-17 00:19:07,823][62408] Updated weights for policy 1, policy_version 1350 (0.0009) -[2023-10-17 00:19:08,062][62373] Updated weights for policy 0, policy_version 1370 (0.0007) -[2023-10-17 00:19:08,179][62408] Updated weights for policy 1, policy_version 1360 (0.0008) -[2023-10-17 00:19:08,544][62408] Updated weights for policy 1, policy_version 1370 (0.0008) -[2023-10-17 00:19:11,887][62373] Updated weights for policy 0, policy_version 1380 (0.0009) -[2023-10-17 00:19:12,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13570.2). Total num frames: 2818048. Throughput: 0: 1768.7, 1: 1740.1. Samples: 718158. Policy #0 lag: (min: 10.0, avg: 10.0, max: 10.0) -[2023-10-17 00:19:12,215][61453] Avg episode reward: [(0, '2.240'), (1, '2.120')] -[2023-10-17 00:19:12,253][62373] Updated weights for policy 0, policy_version 1390 (0.0010) -[2023-10-17 00:19:12,530][62408] Updated weights for policy 1, policy_version 1380 (0.0007) -[2023-10-17 00:19:12,622][62373] Updated weights for policy 0, policy_version 1400 (0.0008) -[2023-10-17 00:19:12,895][62408] Updated weights for policy 1, policy_version 1390 (0.0008) -[2023-10-17 00:19:13,271][62408] Updated weights for policy 1, policy_version 1400 (0.0010) -[2023-10-17 00:19:16,430][62373] Updated weights for policy 0, policy_version 1410 (0.0008) -[2023-10-17 00:19:16,801][62373] Updated weights for policy 0, policy_version 1420 (0.0009) -[2023-10-17 00:19:17,180][62373] Updated weights for policy 0, policy_version 1430 (0.0007) -[2023-10-17 00:19:17,214][61453] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13559.3). Total num frames: 2883584. Throughput: 0: 1772.9, 1: 1758.8. Samples: 739696. Policy #0 lag: (min: 10.0, avg: 10.0, max: 10.0) -[2023-10-17 00:19:17,215][61453] Avg episode reward: [(0, '2.280'), (1, '2.260')] -[2023-10-17 00:19:17,232][62408] Updated weights for policy 1, policy_version 1410 (0.0008) -[2023-10-17 00:19:17,554][62373] Updated weights for policy 0, policy_version 1440 (0.0008) -[2023-10-17 00:19:17,600][62408] Updated weights for policy 1, policy_version 1420 (0.0010) -[2023-10-17 00:19:17,979][62408] Updated weights for policy 1, policy_version 1430 (0.0011) -[2023-10-17 00:19:18,349][62408] Updated weights for policy 1, policy_version 1440 (0.0011) -[2023-10-17 00:19:21,363][62373] Updated weights for policy 0, policy_version 1450 (0.0009) -[2023-10-17 00:19:21,724][62373] Updated weights for policy 0, policy_version 1460 (0.0010) -[2023-10-17 00:19:22,102][62373] Updated weights for policy 0, policy_version 1470 (0.0007) -[2023-10-17 00:19:22,214][61453] Fps is (10 sec: 16384.3, 60 sec: 13653.4, 300 sec: 13699.5). Total num frames: 2981888. Throughput: 0: 1771.3, 1: 1733.8. Samples: 749920. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-17 00:19:22,215][61453] Avg episode reward: [(0, '2.210'), (1, '2.170')] -[2023-10-17 00:19:22,263][62408] Updated weights for policy 1, policy_version 1450 (0.0009) -[2023-10-17 00:19:22,625][62408] Updated weights for policy 1, policy_version 1460 (0.0008) -[2023-10-17 00:19:23,007][62408] Updated weights for policy 1, policy_version 1470 (0.0011) -[2023-10-17 00:19:26,003][62373] Updated weights for policy 0, policy_version 1480 (0.0011) -[2023-10-17 00:19:26,359][62373] Updated weights for policy 0, policy_version 1490 (0.0010) -[2023-10-17 00:19:26,731][62373] Updated weights for policy 0, policy_version 1500 (0.0009) -[2023-10-17 00:19:26,821][62408] Updated weights for policy 1, policy_version 1480 (0.0009) -[2023-10-17 00:19:27,199][62408] Updated weights for policy 1, policy_version 1490 (0.0008) -[2023-10-17 00:19:27,214][61453] Fps is (10 sec: 16383.9, 60 sec: 13653.4, 300 sec: 13686.2). Total num frames: 3047424. Throughput: 0: 1784.9, 1: 1758.0. Samples: 771228. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:19:27,215][61453] Avg episode reward: [(0, '2.060'), (1, '2.230')] -[2023-10-17 00:19:27,567][62408] Updated weights for policy 1, policy_version 1500 (0.0007) -[2023-10-17 00:19:30,611][62373] Updated weights for policy 0, policy_version 1510 (0.0010) -[2023-10-17 00:19:30,980][62373] Updated weights for policy 0, policy_version 1520 (0.0009) -[2023-10-17 00:19:31,358][62373] Updated weights for policy 0, policy_version 1530 (0.0008) -[2023-10-17 00:19:31,365][62408] Updated weights for policy 1, policy_version 1510 (0.0010) -[2023-10-17 00:19:31,738][62408] Updated weights for policy 1, policy_version 1520 (0.0009) -[2023-10-17 00:19:32,107][62408] Updated weights for policy 1, policy_version 1530 (0.0010) -[2023-10-17 00:19:32,214][61453] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13673.5). Total num frames: 3112960. Throughput: 0: 1758.5, 1: 1743.5. Samples: 791298. Policy #0 lag: (min: 5.0, avg: 15.2, max: 37.0) -[2023-10-17 00:19:32,214][61453] Avg episode reward: [(0, '2.140'), (1, '2.140')] -[2023-10-17 00:19:32,227][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000001536_1572864.pth... -[2023-10-17 00:19:32,332][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000001536_1572864.pth... -[2023-10-17 00:19:35,045][62373] Updated weights for policy 0, policy_version 1540 (0.0007) -[2023-10-17 00:19:35,411][62373] Updated weights for policy 0, policy_version 1550 (0.0007) -[2023-10-17 00:19:35,789][62373] Updated weights for policy 0, policy_version 1560 (0.0009) -[2023-10-17 00:19:35,945][62408] Updated weights for policy 1, policy_version 1540 (0.0010) -[2023-10-17 00:19:36,317][62408] Updated weights for policy 1, policy_version 1550 (0.0009) -[2023-10-17 00:19:36,694][62408] Updated weights for policy 1, policy_version 1560 (0.0008) -[2023-10-17 00:19:37,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 13802.1). Total num frames: 3211264. Throughput: 0: 1788.7, 1: 1759.7. Samples: 803094. Policy #0 lag: (min: 17.0, avg: 29.3, max: 49.0) -[2023-10-17 00:19:37,215][61453] Avg episode reward: [(0, '2.200'), (1, '2.390')] -[2023-10-17 00:19:39,644][62373] Updated weights for policy 0, policy_version 1570 (0.0009) -[2023-10-17 00:19:40,010][62373] Updated weights for policy 0, policy_version 1580 (0.0007) -[2023-10-17 00:19:40,379][62373] Updated weights for policy 0, policy_version 1590 (0.0009) -[2023-10-17 00:19:40,517][62408] Updated weights for policy 1, policy_version 1570 (0.0008) -[2023-10-17 00:19:40,744][62373] Updated weights for policy 0, policy_version 1600 (0.0008) -[2023-10-17 00:19:40,881][62408] Updated weights for policy 1, policy_version 1580 (0.0010) -[2023-10-17 00:19:41,239][62408] Updated weights for policy 1, policy_version 1590 (0.0007) -[2023-10-17 00:19:41,616][62408] Updated weights for policy 1, policy_version 1600 (0.0007) -[2023-10-17 00:19:42,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 13787.5). Total num frames: 3276800. Throughput: 0: 1757.4, 1: 1758.6. Samples: 823266. Policy #0 lag: (min: 30.0, avg: 33.1, max: 62.0) -[2023-10-17 00:19:42,215][61453] Avg episode reward: [(0, '2.400'), (1, '2.520')] -[2023-10-17 00:19:42,216][62094] Saving new best policy, reward=2.400! -[2023-10-17 00:19:44,563][62373] Updated weights for policy 0, policy_version 1610 (0.0010) -[2023-10-17 00:19:44,931][62373] Updated weights for policy 0, policy_version 1620 (0.0010) -[2023-10-17 00:19:45,307][62373] Updated weights for policy 0, policy_version 1630 (0.0009) -[2023-10-17 00:19:45,475][62408] Updated weights for policy 1, policy_version 1610 (0.0008) -[2023-10-17 00:19:45,848][62408] Updated weights for policy 1, policy_version 1620 (0.0007) -[2023-10-17 00:19:46,210][62408] Updated weights for policy 1, policy_version 1630 (0.0008) -[2023-10-17 00:19:47,214][61453] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 13773.5). Total num frames: 3342336. Throughput: 0: 1757.0, 1: 1736.0. Samples: 844284. Policy #0 lag: (min: 13.0, avg: 15.3, max: 45.0) -[2023-10-17 00:19:47,214][61453] Avg episode reward: [(0, '2.580'), (1, '2.730')] -[2023-10-17 00:19:47,221][62094] Saving new best policy, reward=2.580! -[2023-10-17 00:19:47,221][62252] Saving new best policy, reward=2.730! -[2023-10-17 00:19:49,085][62373] Updated weights for policy 0, policy_version 1640 (0.0010) -[2023-10-17 00:19:49,462][62373] Updated weights for policy 0, policy_version 1650 (0.0010) -[2023-10-17 00:19:49,825][62373] Updated weights for policy 0, policy_version 1660 (0.0007) -[2023-10-17 00:19:50,098][62408] Updated weights for policy 1, policy_version 1640 (0.0007) -[2023-10-17 00:19:50,479][62408] Updated weights for policy 1, policy_version 1650 (0.0008) -[2023-10-17 00:19:50,849][62408] Updated weights for policy 1, policy_version 1660 (0.0008) -[2023-10-17 00:19:52,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13760.1). Total num frames: 3407872. Throughput: 0: 1756.8, 1: 1762.7. Samples: 855046. Policy #0 lag: (min: 4.0, avg: 7.0, max: 36.0) -[2023-10-17 00:19:52,215][61453] Avg episode reward: [(0, '2.570'), (1, '2.660')] -[2023-10-17 00:19:53,653][62373] Updated weights for policy 0, policy_version 1670 (0.0008) -[2023-10-17 00:19:54,010][62373] Updated weights for policy 0, policy_version 1680 (0.0009) -[2023-10-17 00:19:54,389][62373] Updated weights for policy 0, policy_version 1690 (0.0008) -[2023-10-17 00:19:54,747][62408] Updated weights for policy 1, policy_version 1670 (0.0010) -[2023-10-17 00:19:55,107][62408] Updated weights for policy 1, policy_version 1680 (0.0007) -[2023-10-17 00:19:55,470][62408] Updated weights for policy 1, policy_version 1690 (0.0010) -[2023-10-17 00:19:57,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13747.1). Total num frames: 3473408. Throughput: 0: 1759.7, 1: 1741.3. Samples: 875702. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:19:57,215][61453] Avg episode reward: [(0, '2.400'), (1, '2.510')] -[2023-10-17 00:19:58,185][62373] Updated weights for policy 0, policy_version 1700 (0.0008) -[2023-10-17 00:19:58,553][62373] Updated weights for policy 0, policy_version 1710 (0.0008) -[2023-10-17 00:19:58,915][62373] Updated weights for policy 0, policy_version 1720 (0.0007) -[2023-10-17 00:19:59,287][62408] Updated weights for policy 1, policy_version 1700 (0.0009) -[2023-10-17 00:19:59,667][62408] Updated weights for policy 1, policy_version 1710 (0.0009) -[2023-10-17 00:20:00,044][62408] Updated weights for policy 1, policy_version 1720 (0.0008) -[2023-10-17 00:20:02,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13734.7). Total num frames: 3538944. Throughput: 0: 1774.0, 1: 1742.5. Samples: 897942. Policy #0 lag: (min: 31.0, avg: 33.3, max: 63.0) -[2023-10-17 00:20:02,214][61453] Avg episode reward: [(0, '2.350'), (1, '2.440')] -[2023-10-17 00:20:02,728][62373] Updated weights for policy 0, policy_version 1730 (0.0008) -[2023-10-17 00:20:03,098][62373] Updated weights for policy 0, policy_version 1740 (0.0008) -[2023-10-17 00:20:03,458][62373] Updated weights for policy 0, policy_version 1750 (0.0009) -[2023-10-17 00:20:03,755][62408] Updated weights for policy 1, policy_version 1730 (0.0008) -[2023-10-17 00:20:03,836][62373] Updated weights for policy 0, policy_version 1760 (0.0008) -[2023-10-17 00:20:04,116][62408] Updated weights for policy 1, policy_version 1740 (0.0008) -[2023-10-17 00:20:04,484][62408] Updated weights for policy 1, policy_version 1750 (0.0007) -[2023-10-17 00:20:04,849][62408] Updated weights for policy 1, policy_version 1760 (0.0009) -[2023-10-17 00:20:07,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13722.8). Total num frames: 3604480. Throughput: 0: 1760.3, 1: 1747.4. Samples: 907764. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:20:07,215][61453] Avg episode reward: [(0, '2.220'), (1, '2.450')] -[2023-10-17 00:20:07,526][62373] Updated weights for policy 0, policy_version 1770 (0.0010) -[2023-10-17 00:20:07,888][62373] Updated weights for policy 0, policy_version 1780 (0.0008) -[2023-10-17 00:20:08,252][62373] Updated weights for policy 0, policy_version 1790 (0.0007) -[2023-10-17 00:20:08,637][62408] Updated weights for policy 1, policy_version 1770 (0.0007) -[2023-10-17 00:20:08,997][62408] Updated weights for policy 1, policy_version 1780 (0.0007) -[2023-10-17 00:20:09,376][62408] Updated weights for policy 1, policy_version 1790 (0.0010) -[2023-10-17 00:20:12,019][62373] Updated weights for policy 0, policy_version 1800 (0.0009) -[2023-10-17 00:20:12,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13711.3). Total num frames: 3670016. Throughput: 0: 1777.2, 1: 1748.0. Samples: 929860. Policy #0 lag: (min: 29.0, avg: 39.7, max: 40.0) -[2023-10-17 00:20:12,215][61453] Avg episode reward: [(0, '2.440'), (1, '2.510')] -[2023-10-17 00:20:12,381][62373] Updated weights for policy 0, policy_version 1810 (0.0009) -[2023-10-17 00:20:12,759][62373] Updated weights for policy 0, policy_version 1820 (0.0009) -[2023-10-17 00:20:13,331][62408] Updated weights for policy 1, policy_version 1800 (0.0009) -[2023-10-17 00:20:13,695][62408] Updated weights for policy 1, policy_version 1810 (0.0007) -[2023-10-17 00:20:14,068][62408] Updated weights for policy 1, policy_version 1820 (0.0009) -[2023-10-17 00:20:16,677][62373] Updated weights for policy 0, policy_version 1830 (0.0007) -[2023-10-17 00:20:17,039][62373] Updated weights for policy 0, policy_version 1840 (0.0009) -[2023-10-17 00:20:17,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13700.2). Total num frames: 3735552. Throughput: 0: 1791.2, 1: 1762.8. Samples: 951226. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-17 00:20:17,214][61453] Avg episode reward: [(0, '2.430'), (1, '2.380')] -[2023-10-17 00:20:17,404][62373] Updated weights for policy 0, policy_version 1850 (0.0011) -[2023-10-17 00:20:17,891][62408] Updated weights for policy 1, policy_version 1830 (0.0008) -[2023-10-17 00:20:18,257][62408] Updated weights for policy 1, policy_version 1840 (0.0008) -[2023-10-17 00:20:18,633][62408] Updated weights for policy 1, policy_version 1850 (0.0008) -[2023-10-17 00:20:21,111][62373] Updated weights for policy 0, policy_version 1860 (0.0008) -[2023-10-17 00:20:21,484][62373] Updated weights for policy 0, policy_version 1870 (0.0010) -[2023-10-17 00:20:21,849][62373] Updated weights for policy 0, policy_version 1880 (0.0007) -[2023-10-17 00:20:22,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 13807.5). Total num frames: 3833856. Throughput: 0: 1773.3, 1: 1748.0. Samples: 961548. Policy #0 lag: (min: 26.0, avg: 28.4, max: 58.0) -[2023-10-17 00:20:22,214][61453] Avg episode reward: [(0, '2.590'), (1, '2.190')] -[2023-10-17 00:20:22,215][62094] Saving new best policy, reward=2.590! -[2023-10-17 00:20:22,443][62408] Updated weights for policy 1, policy_version 1860 (0.0009) -[2023-10-17 00:20:22,812][62408] Updated weights for policy 1, policy_version 1870 (0.0008) -[2023-10-17 00:20:23,177][62408] Updated weights for policy 1, policy_version 1880 (0.0008) -[2023-10-17 00:20:25,500][62373] Updated weights for policy 0, policy_version 1890 (0.0009) -[2023-10-17 00:20:25,880][62373] Updated weights for policy 0, policy_version 1900 (0.0010) -[2023-10-17 00:20:26,252][62373] Updated weights for policy 0, policy_version 1910 (0.0009) -[2023-10-17 00:20:26,632][62373] Updated weights for policy 0, policy_version 1920 (0.0010) -[2023-10-17 00:20:26,989][62408] Updated weights for policy 1, policy_version 1890 (0.0008) -[2023-10-17 00:20:27,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 13795.1). Total num frames: 3899392. Throughput: 0: 1795.7, 1: 1760.5. Samples: 983294. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:20:27,215][61453] Avg episode reward: [(0, '2.430'), (1, '2.240')] -[2023-10-17 00:20:27,354][62408] Updated weights for policy 1, policy_version 1900 (0.0009) -[2023-10-17 00:20:27,722][62408] Updated weights for policy 1, policy_version 1910 (0.0007) -[2023-10-17 00:20:28,086][62408] Updated weights for policy 1, policy_version 1920 (0.0010) -[2023-10-17 00:20:30,423][62373] Updated weights for policy 0, policy_version 1930 (0.0007) -[2023-10-17 00:20:30,802][62373] Updated weights for policy 0, policy_version 1940 (0.0008) -[2023-10-17 00:20:31,164][62373] Updated weights for policy 0, policy_version 1950 (0.0009) -[2023-10-17 00:20:31,955][62408] Updated weights for policy 1, policy_version 1930 (0.0008) -[2023-10-17 00:20:32,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13783.2). Total num frames: 3964928. Throughput: 0: 1773.6, 1: 1781.0. Samples: 1004240. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:20:32,215][61453] Avg episode reward: [(0, '2.540'), (1, '2.270')] -[2023-10-17 00:20:32,323][62408] Updated weights for policy 1, policy_version 1940 (0.0008) -[2023-10-17 00:20:32,691][62408] Updated weights for policy 1, policy_version 1950 (0.0010) -[2023-10-17 00:20:35,045][62373] Updated weights for policy 0, policy_version 1960 (0.0007) -[2023-10-17 00:20:35,423][62373] Updated weights for policy 0, policy_version 1970 (0.0009) -[2023-10-17 00:20:35,779][62373] Updated weights for policy 0, policy_version 1980 (0.0011) -[2023-10-17 00:20:36,615][62408] Updated weights for policy 1, policy_version 1960 (0.0008) -[2023-10-17 00:20:36,989][62408] Updated weights for policy 1, policy_version 1970 (0.0008) -[2023-10-17 00:20:37,214][61453] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13771.6). Total num frames: 4030464. Throughput: 0: 1799.4, 1: 1762.3. Samples: 1015322. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-17 00:20:37,215][61453] Avg episode reward: [(0, '2.410'), (1, '2.320')] -[2023-10-17 00:20:37,355][62408] Updated weights for policy 1, policy_version 1980 (0.0007) -[2023-10-17 00:20:39,784][62373] Updated weights for policy 0, policy_version 1990 (0.0010) -[2023-10-17 00:20:40,151][62373] Updated weights for policy 0, policy_version 2000 (0.0007) -[2023-10-17 00:20:40,528][62373] Updated weights for policy 0, policy_version 2010 (0.0007) -[2023-10-17 00:20:41,217][62408] Updated weights for policy 1, policy_version 1990 (0.0008) -[2023-10-17 00:20:41,598][62408] Updated weights for policy 1, policy_version 2000 (0.0010) -[2023-10-17 00:20:41,971][62408] Updated weights for policy 1, policy_version 2010 (0.0010) -[2023-10-17 00:20:42,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 4128768. Throughput: 0: 1768.3, 1: 1790.3. Samples: 1035840. Policy #0 lag: (min: 1.0, avg: 11.2, max: 33.0) -[2023-10-17 00:20:42,215][61453] Avg episode reward: [(0, '2.480'), (1, '2.230')] -[2023-10-17 00:20:44,376][62373] Updated weights for policy 0, policy_version 2020 (0.0008) -[2023-10-17 00:20:44,752][62373] Updated weights for policy 0, policy_version 2030 (0.0008) -[2023-10-17 00:20:45,127][62373] Updated weights for policy 0, policy_version 2040 (0.0009) -[2023-10-17 00:20:45,839][62408] Updated weights for policy 1, policy_version 2020 (0.0010) -[2023-10-17 00:20:46,209][62408] Updated weights for policy 1, policy_version 2030 (0.0009) -[2023-10-17 00:20:46,574][62408] Updated weights for policy 1, policy_version 2040 (0.0007) -[2023-10-17 00:20:47,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 4194304. Throughput: 0: 1771.5, 1: 1759.3. Samples: 1056830. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:20:47,215][61453] Avg episode reward: [(0, '2.770'), (1, '2.190')] -[2023-10-17 00:20:47,228][62094] Saving new best policy, reward=2.770! -[2023-10-17 00:20:48,749][62373] Updated weights for policy 0, policy_version 2050 (0.0010) -[2023-10-17 00:20:49,115][62373] Updated weights for policy 0, policy_version 2060 (0.0010) -[2023-10-17 00:20:49,480][62373] Updated weights for policy 0, policy_version 2070 (0.0010) -[2023-10-17 00:20:49,851][62373] Updated weights for policy 0, policy_version 2080 (0.0010) -[2023-10-17 00:20:50,341][62408] Updated weights for policy 1, policy_version 2050 (0.0007) -[2023-10-17 00:20:50,711][62408] Updated weights for policy 1, policy_version 2060 (0.0008) -[2023-10-17 00:20:51,085][62408] Updated weights for policy 1, policy_version 2070 (0.0011) -[2023-10-17 00:20:51,450][62408] Updated weights for policy 1, policy_version 2080 (0.0011) -[2023-10-17 00:20:52,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 4259840. Throughput: 0: 1768.0, 1: 1786.5. Samples: 1067716. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:20:52,215][61453] Avg episode reward: [(0, '3.000'), (1, '2.260')] -[2023-10-17 00:20:52,216][62094] Saving new best policy, reward=3.000! -[2023-10-17 00:20:53,705][62373] Updated weights for policy 0, policy_version 2090 (0.0009) -[2023-10-17 00:20:54,080][62373] Updated weights for policy 0, policy_version 2100 (0.0009) -[2023-10-17 00:20:54,450][62373] Updated weights for policy 0, policy_version 2110 (0.0010) -[2023-10-17 00:20:55,287][62408] Updated weights for policy 1, policy_version 2090 (0.0008) -[2023-10-17 00:20:55,651][62408] Updated weights for policy 1, policy_version 2100 (0.0007) -[2023-10-17 00:20:56,016][62408] Updated weights for policy 1, policy_version 2110 (0.0009) -[2023-10-17 00:20:57,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 4325376. Throughput: 0: 1760.4, 1: 1766.0. Samples: 1088548. Policy #0 lag: (min: 26.0, avg: 36.8, max: 58.0) -[2023-10-17 00:20:57,215][61453] Avg episode reward: [(0, '3.010'), (1, '2.380')] -[2023-10-17 00:20:57,216][62094] Saving new best policy, reward=3.010! -[2023-10-17 00:20:58,306][62373] Updated weights for policy 0, policy_version 2120 (0.0011) -[2023-10-17 00:20:58,684][62373] Updated weights for policy 0, policy_version 2130 (0.0010) -[2023-10-17 00:20:59,054][62373] Updated weights for policy 0, policy_version 2140 (0.0010) -[2023-10-17 00:20:59,715][62408] Updated weights for policy 1, policy_version 2120 (0.0008) -[2023-10-17 00:21:00,079][62408] Updated weights for policy 1, policy_version 2130 (0.0007) -[2023-10-17 00:21:00,448][62408] Updated weights for policy 1, policy_version 2140 (0.0009) -[2023-10-17 00:21:02,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 4390912. Throughput: 0: 1768.9, 1: 1763.9. Samples: 1110200. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:21:02,215][61453] Avg episode reward: [(0, '3.120'), (1, '2.300')] -[2023-10-17 00:21:02,225][62094] Saving new best policy, reward=3.120! -[2023-10-17 00:21:02,770][62373] Updated weights for policy 0, policy_version 2150 (0.0009) -[2023-10-17 00:21:03,135][62373] Updated weights for policy 0, policy_version 2160 (0.0009) -[2023-10-17 00:21:03,499][62373] Updated weights for policy 0, policy_version 2170 (0.0008) -[2023-10-17 00:21:04,310][62408] Updated weights for policy 1, policy_version 2150 (0.0010) -[2023-10-17 00:21:04,679][62408] Updated weights for policy 1, policy_version 2160 (0.0008) -[2023-10-17 00:21:05,056][62408] Updated weights for policy 1, policy_version 2170 (0.0007) -[2023-10-17 00:21:07,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 4456448. Throughput: 0: 1756.6, 1: 1773.6. Samples: 1120410. Policy #0 lag: (min: 31.0, avg: 31.6, max: 47.0) -[2023-10-17 00:21:07,215][61453] Avg episode reward: [(0, '2.540'), (1, '2.470')] -[2023-10-17 00:21:07,249][62373] Updated weights for policy 0, policy_version 2180 (0.0008) -[2023-10-17 00:21:07,613][62373] Updated weights for policy 0, policy_version 2190 (0.0010) -[2023-10-17 00:21:07,986][62373] Updated weights for policy 0, policy_version 2200 (0.0011) -[2023-10-17 00:21:08,798][62408] Updated weights for policy 1, policy_version 2180 (0.0009) -[2023-10-17 00:21:09,169][62408] Updated weights for policy 1, policy_version 2190 (0.0009) -[2023-10-17 00:21:09,539][62408] Updated weights for policy 1, policy_version 2200 (0.0008) -[2023-10-17 00:21:11,844][62373] Updated weights for policy 0, policy_version 2210 (0.0010) -[2023-10-17 00:21:12,214][61453] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 4521984. Throughput: 0: 1773.1, 1: 1754.6. Samples: 1142038. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:21:12,214][61453] Avg episode reward: [(0, '2.580'), (1, '2.350')] -[2023-10-17 00:21:12,217][62373] Updated weights for policy 0, policy_version 2220 (0.0007) -[2023-10-17 00:21:12,595][62373] Updated weights for policy 0, policy_version 2230 (0.0009) -[2023-10-17 00:21:12,971][62373] Updated weights for policy 0, policy_version 2240 (0.0009) -[2023-10-17 00:21:13,257][62408] Updated weights for policy 1, policy_version 2210 (0.0008) -[2023-10-17 00:21:13,635][62408] Updated weights for policy 1, policy_version 2220 (0.0008) -[2023-10-17 00:21:14,009][62408] Updated weights for policy 1, policy_version 2230 (0.0008) -[2023-10-17 00:21:14,372][62408] Updated weights for policy 1, policy_version 2240 (0.0010) -[2023-10-17 00:21:16,811][62373] Updated weights for policy 0, policy_version 2250 (0.0010) -[2023-10-17 00:21:17,183][62373] Updated weights for policy 0, policy_version 2260 (0.0009) -[2023-10-17 00:21:17,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 4587520. Throughput: 0: 1777.4, 1: 1760.6. Samples: 1163450. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:21:17,215][61453] Avg episode reward: [(0, '2.660'), (1, '2.380')] -[2023-10-17 00:21:17,544][62373] Updated weights for policy 0, policy_version 2270 (0.0010) -[2023-10-17 00:21:18,332][62408] Updated weights for policy 1, policy_version 2250 (0.0009) -[2023-10-17 00:21:18,705][62408] Updated weights for policy 1, policy_version 2260 (0.0007) -[2023-10-17 00:21:19,075][62408] Updated weights for policy 1, policy_version 2270 (0.0007) -[2023-10-17 00:21:21,369][62373] Updated weights for policy 0, policy_version 2280 (0.0010) -[2023-10-17 00:21:21,757][62373] Updated weights for policy 0, policy_version 2290 (0.0009) -[2023-10-17 00:21:22,125][62373] Updated weights for policy 0, policy_version 2300 (0.0010) -[2023-10-17 00:21:22,214][61453] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13995.8). Total num frames: 4653056. Throughput: 0: 1763.4, 1: 1754.3. Samples: 1173620. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:21:22,214][61453] Avg episode reward: [(0, '2.230'), (1, '2.440')] -[2023-10-17 00:21:23,018][62408] Updated weights for policy 1, policy_version 2280 (0.0008) -[2023-10-17 00:21:23,394][62408] Updated weights for policy 1, policy_version 2290 (0.0010) -[2023-10-17 00:21:23,755][62408] Updated weights for policy 1, policy_version 2300 (0.0009) -[2023-10-17 00:21:25,867][62373] Updated weights for policy 0, policy_version 2310 (0.0010) -[2023-10-17 00:21:26,239][62373] Updated weights for policy 0, policy_version 2320 (0.0010) -[2023-10-17 00:21:26,604][62373] Updated weights for policy 0, policy_version 2330 (0.0011) -[2023-10-17 00:21:27,214][61453] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 4751360. Throughput: 0: 1791.4, 1: 1752.2. Samples: 1195302. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:21:27,214][61453] Avg episode reward: [(0, '2.600'), (1, '2.150')] -[2023-10-17 00:21:27,516][62408] Updated weights for policy 1, policy_version 2310 (0.0007) -[2023-10-17 00:21:27,876][62408] Updated weights for policy 1, policy_version 2320 (0.0009) -[2023-10-17 00:21:28,252][62408] Updated weights for policy 1, policy_version 2330 (0.0010) -[2023-10-17 00:21:30,407][62373] Updated weights for policy 0, policy_version 2340 (0.0010) -[2023-10-17 00:21:30,788][62373] Updated weights for policy 0, policy_version 2350 (0.0007) -[2023-10-17 00:21:31,146][62373] Updated weights for policy 0, policy_version 2360 (0.0007) -[2023-10-17 00:21:31,970][62408] Updated weights for policy 1, policy_version 2340 (0.0009) -[2023-10-17 00:21:32,214][61453] Fps is (10 sec: 16383.5, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 4816896. Throughput: 0: 1758.8, 1: 1782.5. Samples: 1216192. Policy #0 lag: (min: 14.0, avg: 15.1, max: 37.0) -[2023-10-17 00:21:32,215][61453] Avg episode reward: [(0, '2.310'), (1, '2.120')] -[2023-10-17 00:21:32,225][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000002368_2424832.pth... -[2023-10-17 00:21:32,258][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000000704_720896.pth -[2023-10-17 00:21:32,335][62408] Updated weights for policy 1, policy_version 2350 (0.0007) -[2023-10-17 00:21:32,714][62408] Updated weights for policy 1, policy_version 2360 (0.0007) -[2023-10-17 00:21:33,002][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000002368_2424832.pth... -[2023-10-17 00:21:33,031][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000000704_720896.pth -[2023-10-17 00:21:34,979][62373] Updated weights for policy 0, policy_version 2370 (0.0007) -[2023-10-17 00:21:35,350][62373] Updated weights for policy 0, policy_version 2380 (0.0008) -[2023-10-17 00:21:35,729][62373] Updated weights for policy 0, policy_version 2390 (0.0009) -[2023-10-17 00:21:36,098][62373] Updated weights for policy 0, policy_version 2400 (0.0010) -[2023-10-17 00:21:36,641][62408] Updated weights for policy 1, policy_version 2370 (0.0008) -[2023-10-17 00:21:37,007][62408] Updated weights for policy 1, policy_version 2380 (0.0007) -[2023-10-17 00:21:37,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 4882432. Throughput: 0: 1794.5, 1: 1753.8. Samples: 1227388. Policy #0 lag: (min: 31.0, avg: 32.9, max: 60.0) -[2023-10-17 00:21:37,215][61453] Avg episode reward: [(0, '1.980'), (1, '2.230')] -[2023-10-17 00:21:37,371][62408] Updated weights for policy 1, policy_version 2390 (0.0007) -[2023-10-17 00:21:37,747][62408] Updated weights for policy 1, policy_version 2400 (0.0008) -[2023-10-17 00:21:39,995][62373] Updated weights for policy 0, policy_version 2410 (0.0010) -[2023-10-17 00:21:40,378][62373] Updated weights for policy 0, policy_version 2420 (0.0009) -[2023-10-17 00:21:40,741][62373] Updated weights for policy 0, policy_version 2430 (0.0008) -[2023-10-17 00:21:41,582][62408] Updated weights for policy 1, policy_version 2410 (0.0008) -[2023-10-17 00:21:41,938][62408] Updated weights for policy 1, policy_version 2420 (0.0010) -[2023-10-17 00:21:42,214][61453] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 4947968. Throughput: 0: 1764.8, 1: 1776.9. Samples: 1247922. Policy #0 lag: (min: 4.0, avg: 4.3, max: 17.0) -[2023-10-17 00:21:42,215][61453] Avg episode reward: [(0, '2.180'), (1, '2.150')] -[2023-10-17 00:21:42,313][62408] Updated weights for policy 1, policy_version 2430 (0.0008) -[2023-10-17 00:21:44,482][62373] Updated weights for policy 0, policy_version 2440 (0.0007) -[2023-10-17 00:21:44,851][62373] Updated weights for policy 0, policy_version 2450 (0.0007) -[2023-10-17 00:21:45,223][62373] Updated weights for policy 0, policy_version 2460 (0.0009) -[2023-10-17 00:21:46,047][62408] Updated weights for policy 1, policy_version 2440 (0.0008) -[2023-10-17 00:21:46,418][62408] Updated weights for policy 1, policy_version 2450 (0.0007) -[2023-10-17 00:21:46,782][62408] Updated weights for policy 1, policy_version 2460 (0.0010) -[2023-10-17 00:21:47,214][61453] Fps is (10 sec: 16384.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 5046272. Throughput: 0: 1777.0, 1: 1752.7. Samples: 1269036. Policy #0 lag: (min: 31.0, avg: 31.8, max: 50.0) -[2023-10-17 00:21:47,214][61453] Avg episode reward: [(0, '1.950'), (1, '2.280')] -[2023-10-17 00:21:48,919][62373] Updated weights for policy 0, policy_version 2470 (0.0009) -[2023-10-17 00:21:49,286][62373] Updated weights for policy 0, policy_version 2480 (0.0008) -[2023-10-17 00:21:49,662][62373] Updated weights for policy 0, policy_version 2490 (0.0008) -[2023-10-17 00:21:50,666][62408] Updated weights for policy 1, policy_version 2470 (0.0009) -[2023-10-17 00:21:51,032][62408] Updated weights for policy 1, policy_version 2480 (0.0008) -[2023-10-17 00:21:51,403][62408] Updated weights for policy 1, policy_version 2490 (0.0008) -[2023-10-17 00:21:52,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 5111808. Throughput: 0: 1776.5, 1: 1768.5. Samples: 1279934. Policy #0 lag: (min: 31.0, avg: 31.8, max: 50.0) -[2023-10-17 00:21:52,214][61453] Avg episode reward: [(0, '2.160'), (1, '2.460')] -[2023-10-17 00:21:53,344][62373] Updated weights for policy 0, policy_version 2500 (0.0008) -[2023-10-17 00:21:53,713][62373] Updated weights for policy 0, policy_version 2510 (0.0007) -[2023-10-17 00:21:54,098][62373] Updated weights for policy 0, policy_version 2520 (0.0008) -[2023-10-17 00:21:55,261][62408] Updated weights for policy 1, policy_version 2500 (0.0007) -[2023-10-17 00:21:55,633][62408] Updated weights for policy 1, policy_version 2510 (0.0010) -[2023-10-17 00:21:56,004][62408] Updated weights for policy 1, policy_version 2520 (0.0008) -[2023-10-17 00:21:57,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 5177344. Throughput: 0: 1774.3, 1: 1766.0. Samples: 1301356. Policy #0 lag: (min: 18.0, avg: 25.6, max: 50.0) -[2023-10-17 00:21:57,215][61453] Avg episode reward: [(0, '2.620'), (1, '2.630')] -[2023-10-17 00:21:57,756][62373] Updated weights for policy 0, policy_version 2530 (0.0008) -[2023-10-17 00:21:58,128][62373] Updated weights for policy 0, policy_version 2540 (0.0009) -[2023-10-17 00:21:58,506][62373] Updated weights for policy 0, policy_version 2550 (0.0009) -[2023-10-17 00:21:58,877][62373] Updated weights for policy 0, policy_version 2560 (0.0008) -[2023-10-17 00:21:59,752][62408] Updated weights for policy 1, policy_version 2530 (0.0008) -[2023-10-17 00:22:00,125][62408] Updated weights for policy 1, policy_version 2540 (0.0009) -[2023-10-17 00:22:00,495][62408] Updated weights for policy 1, policy_version 2550 (0.0009) -[2023-10-17 00:22:00,860][62408] Updated weights for policy 1, policy_version 2560 (0.0009) -[2023-10-17 00:22:02,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 5242880. Throughput: 0: 1792.5, 1: 1758.4. Samples: 1323242. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:22:02,214][61453] Avg episode reward: [(0, '2.630'), (1, '2.580')] -[2023-10-17 00:22:02,828][62373] Updated weights for policy 0, policy_version 2570 (0.0007) -[2023-10-17 00:22:03,204][62373] Updated weights for policy 0, policy_version 2580 (0.0008) -[2023-10-17 00:22:03,581][62373] Updated weights for policy 0, policy_version 2590 (0.0007) -[2023-10-17 00:22:04,558][62408] Updated weights for policy 1, policy_version 2570 (0.0007) -[2023-10-17 00:22:04,934][62408] Updated weights for policy 1, policy_version 2580 (0.0008) -[2023-10-17 00:22:05,300][62408] Updated weights for policy 1, policy_version 2590 (0.0008) -[2023-10-17 00:22:07,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 5308416. Throughput: 0: 1780.8, 1: 1775.5. Samples: 1333650. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:22:07,214][61453] Avg episode reward: [(0, '2.710'), (1, '2.560')] -[2023-10-17 00:22:07,277][62373] Updated weights for policy 0, policy_version 2600 (0.0008) -[2023-10-17 00:22:07,648][62373] Updated weights for policy 0, policy_version 2610 (0.0009) -[2023-10-17 00:22:08,023][62373] Updated weights for policy 0, policy_version 2620 (0.0007) -[2023-10-17 00:22:09,258][62408] Updated weights for policy 1, policy_version 2600 (0.0007) -[2023-10-17 00:22:09,628][62408] Updated weights for policy 1, policy_version 2610 (0.0007) -[2023-10-17 00:22:09,993][62408] Updated weights for policy 1, policy_version 2620 (0.0008) -[2023-10-17 00:22:11,857][62373] Updated weights for policy 0, policy_version 2630 (0.0008) -[2023-10-17 00:22:12,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 5373952. Throughput: 0: 1785.1, 1: 1759.6. Samples: 1354816. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:22:12,215][61453] Avg episode reward: [(0, '2.800'), (1, '2.520')] -[2023-10-17 00:22:12,234][62373] Updated weights for policy 0, policy_version 2640 (0.0009) -[2023-10-17 00:22:12,606][62373] Updated weights for policy 0, policy_version 2650 (0.0009) -[2023-10-17 00:22:13,896][62408] Updated weights for policy 1, policy_version 2630 (0.0007) -[2023-10-17 00:22:14,274][62408] Updated weights for policy 1, policy_version 2640 (0.0009) -[2023-10-17 00:22:14,644][62408] Updated weights for policy 1, policy_version 2650 (0.0011) -[2023-10-17 00:22:16,353][62373] Updated weights for policy 0, policy_version 2660 (0.0007) -[2023-10-17 00:22:16,723][62373] Updated weights for policy 0, policy_version 2670 (0.0008) -[2023-10-17 00:22:17,085][62373] Updated weights for policy 0, policy_version 2680 (0.0007) -[2023-10-17 00:22:17,214][61453] Fps is (10 sec: 13106.5, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 5439488. Throughput: 0: 1796.6, 1: 1756.5. Samples: 1376084. Policy #0 lag: (min: 31.0, avg: 42.5, max: 63.0) -[2023-10-17 00:22:17,216][61453] Avg episode reward: [(0, '2.900'), (1, '2.370')] -[2023-10-17 00:22:18,638][62408] Updated weights for policy 1, policy_version 2660 (0.0010) -[2023-10-17 00:22:19,003][62408] Updated weights for policy 1, policy_version 2670 (0.0009) -[2023-10-17 00:22:19,376][62408] Updated weights for policy 1, policy_version 2680 (0.0007) -[2023-10-17 00:22:20,909][62373] Updated weights for policy 0, policy_version 2690 (0.0009) -[2023-10-17 00:22:21,285][62373] Updated weights for policy 0, policy_version 2700 (0.0010) -[2023-10-17 00:22:21,660][62373] Updated weights for policy 0, policy_version 2710 (0.0010) -[2023-10-17 00:22:22,023][62373] Updated weights for policy 0, policy_version 2720 (0.0008) -[2023-10-17 00:22:22,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14745.5, 300 sec: 14106.9). Total num frames: 5537792. Throughput: 0: 1784.4, 1: 1753.4. Samples: 1386590. Policy #0 lag: (min: 14.0, avg: 17.0, max: 46.0) -[2023-10-17 00:22:22,215][61453] Avg episode reward: [(0, '2.760'), (1, '2.690')] -[2023-10-17 00:22:23,037][62408] Updated weights for policy 1, policy_version 2690 (0.0007) -[2023-10-17 00:22:23,396][62408] Updated weights for policy 1, policy_version 2700 (0.0008) -[2023-10-17 00:22:23,761][62408] Updated weights for policy 1, policy_version 2710 (0.0007) -[2023-10-17 00:22:24,133][62408] Updated weights for policy 1, policy_version 2720 (0.0008) -[2023-10-17 00:22:25,659][62373] Updated weights for policy 0, policy_version 2730 (0.0007) -[2023-10-17 00:22:26,031][62373] Updated weights for policy 0, policy_version 2740 (0.0008) -[2023-10-17 00:22:26,414][62373] Updated weights for policy 0, policy_version 2750 (0.0009) -[2023-10-17 00:22:27,214][61453] Fps is (10 sec: 16384.6, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 5603328. Throughput: 0: 1799.8, 1: 1759.6. Samples: 1408096. Policy #0 lag: (min: 15.0, avg: 15.7, max: 34.0) -[2023-10-17 00:22:27,215][61453] Avg episode reward: [(0, '2.490'), (1, '2.960')] -[2023-10-17 00:22:27,216][62252] Saving new best policy, reward=2.960! -[2023-10-17 00:22:28,011][62408] Updated weights for policy 1, policy_version 2730 (0.0009) -[2023-10-17 00:22:28,389][62408] Updated weights for policy 1, policy_version 2740 (0.0007) -[2023-10-17 00:22:28,760][62408] Updated weights for policy 1, policy_version 2750 (0.0007) -[2023-10-17 00:22:30,282][62373] Updated weights for policy 0, policy_version 2760 (0.0009) -[2023-10-17 00:22:30,644][62373] Updated weights for policy 0, policy_version 2770 (0.0010) -[2023-10-17 00:22:31,013][62373] Updated weights for policy 0, policy_version 2780 (0.0009) -[2023-10-17 00:22:32,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 5668864. Throughput: 0: 1780.4, 1: 1789.6. Samples: 1429686. Policy #0 lag: (min: 25.0, avg: 35.1, max: 57.0) -[2023-10-17 00:22:32,215][61453] Avg episode reward: [(0, '2.350'), (1, '3.140')] -[2023-10-17 00:22:32,562][62408] Updated weights for policy 1, policy_version 2760 (0.0008) -[2023-10-17 00:22:32,938][62408] Updated weights for policy 1, policy_version 2770 (0.0009) -[2023-10-17 00:22:33,305][62408] Updated weights for policy 1, policy_version 2780 (0.0008) -[2023-10-17 00:22:33,453][62252] Saving new best policy, reward=3.140! -[2023-10-17 00:22:34,712][62373] Updated weights for policy 0, policy_version 2790 (0.0007) -[2023-10-17 00:22:35,086][62373] Updated weights for policy 0, policy_version 2800 (0.0009) -[2023-10-17 00:22:35,461][62373] Updated weights for policy 0, policy_version 2810 (0.0009) -[2023-10-17 00:22:37,173][62408] Updated weights for policy 1, policy_version 2790 (0.0008) -[2023-10-17 00:22:37,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 5734400. Throughput: 0: 1803.2, 1: 1760.0. Samples: 1440278. Policy #0 lag: (min: 25.0, avg: 35.1, max: 57.0) -[2023-10-17 00:22:37,215][61453] Avg episode reward: [(0, '2.440'), (1, '2.930')] -[2023-10-17 00:22:37,549][62408] Updated weights for policy 1, policy_version 2800 (0.0008) -[2023-10-17 00:22:37,934][62408] Updated weights for policy 1, policy_version 2810 (0.0007) -[2023-10-17 00:22:39,349][62373] Updated weights for policy 0, policy_version 2820 (0.0008) -[2023-10-17 00:22:39,721][62373] Updated weights for policy 0, policy_version 2830 (0.0008) -[2023-10-17 00:22:40,092][62373] Updated weights for policy 0, policy_version 2840 (0.0009) -[2023-10-17 00:22:41,842][62408] Updated weights for policy 1, policy_version 2820 (0.0009) -[2023-10-17 00:22:42,215][61453] Fps is (10 sec: 13105.7, 60 sec: 14199.2, 300 sec: 14106.8). Total num frames: 5799936. Throughput: 0: 1780.8, 1: 1774.8. Samples: 1461360. Policy #0 lag: (min: 31.0, avg: 32.5, max: 57.0) -[2023-10-17 00:22:42,216][61453] Avg episode reward: [(0, '2.770'), (1, '3.050')] -[2023-10-17 00:22:42,218][62408] Updated weights for policy 1, policy_version 2830 (0.0010) -[2023-10-17 00:22:42,587][62408] Updated weights for policy 1, policy_version 2840 (0.0008) -[2023-10-17 00:22:43,877][62373] Updated weights for policy 0, policy_version 2850 (0.0011) -[2023-10-17 00:22:44,254][62373] Updated weights for policy 0, policy_version 2860 (0.0010) -[2023-10-17 00:22:44,613][62373] Updated weights for policy 0, policy_version 2870 (0.0008) -[2023-10-17 00:22:44,991][62373] Updated weights for policy 0, policy_version 2880 (0.0007) -[2023-10-17 00:22:46,378][62408] Updated weights for policy 1, policy_version 2850 (0.0007) -[2023-10-17 00:22:46,749][62408] Updated weights for policy 1, policy_version 2860 (0.0008) -[2023-10-17 00:22:47,125][62408] Updated weights for policy 1, policy_version 2870 (0.0007) -[2023-10-17 00:22:47,214][61453] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 5865472. Throughput: 0: 1776.8, 1: 1766.9. Samples: 1482712. Policy #0 lag: (min: 31.0, avg: 32.5, max: 57.0) -[2023-10-17 00:22:47,215][61453] Avg episode reward: [(0, '3.110'), (1, '2.760')] -[2023-10-17 00:22:47,493][62408] Updated weights for policy 1, policy_version 2880 (0.0007) -[2023-10-17 00:22:48,863][62373] Updated weights for policy 0, policy_version 2890 (0.0008) -[2023-10-17 00:22:49,249][62373] Updated weights for policy 0, policy_version 2900 (0.0008) -[2023-10-17 00:22:49,617][62373] Updated weights for policy 0, policy_version 2910 (0.0010) -[2023-10-17 00:22:51,191][62408] Updated weights for policy 1, policy_version 2890 (0.0010) -[2023-10-17 00:22:51,560][62408] Updated weights for policy 1, policy_version 2900 (0.0009) -[2023-10-17 00:22:51,934][62408] Updated weights for policy 1, policy_version 2910 (0.0007) -[2023-10-17 00:22:52,214][61453] Fps is (10 sec: 16386.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 5963776. Throughput: 0: 1769.9, 1: 1764.7. Samples: 1492704. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-17 00:22:52,215][61453] Avg episode reward: [(0, '3.010'), (1, '2.760')] -[2023-10-17 00:22:53,231][62373] Updated weights for policy 0, policy_version 2920 (0.0011) -[2023-10-17 00:22:53,609][62373] Updated weights for policy 0, policy_version 2930 (0.0010) -[2023-10-17 00:22:53,976][62373] Updated weights for policy 0, policy_version 2940 (0.0009) -[2023-10-17 00:22:55,787][62408] Updated weights for policy 1, policy_version 2920 (0.0009) -[2023-10-17 00:22:56,168][62408] Updated weights for policy 1, policy_version 2930 (0.0009) -[2023-10-17 00:22:56,538][62408] Updated weights for policy 1, policy_version 2940 (0.0007) -[2023-10-17 00:22:57,214][61453] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 6029312. Throughput: 0: 1775.0, 1: 1774.2. Samples: 1514530. Policy #0 lag: (min: 3.0, avg: 11.0, max: 35.0) -[2023-10-17 00:22:57,215][61453] Avg episode reward: [(0, '2.620'), (1, '2.780')] -[2023-10-17 00:22:57,837][62373] Updated weights for policy 0, policy_version 2950 (0.0010) -[2023-10-17 00:22:58,203][62373] Updated weights for policy 0, policy_version 2960 (0.0009) -[2023-10-17 00:22:58,567][62373] Updated weights for policy 0, policy_version 2970 (0.0008) -[2023-10-17 00:23:00,255][62408] Updated weights for policy 1, policy_version 2950 (0.0008) -[2023-10-17 00:23:00,627][62408] Updated weights for policy 1, policy_version 2960 (0.0008) -[2023-10-17 00:23:00,981][62408] Updated weights for policy 1, policy_version 2970 (0.0009) -[2023-10-17 00:23:02,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 6094848. Throughput: 0: 1788.6, 1: 1755.3. Samples: 1535558. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:23:02,215][61453] Avg episode reward: [(0, '2.410'), (1, '3.180')] -[2023-10-17 00:23:02,225][62252] Saving new best policy, reward=3.180! -[2023-10-17 00:23:02,506][62373] Updated weights for policy 0, policy_version 2980 (0.0009) -[2023-10-17 00:23:02,878][62373] Updated weights for policy 0, policy_version 2990 (0.0009) -[2023-10-17 00:23:03,254][62373] Updated weights for policy 0, policy_version 3000 (0.0009) -[2023-10-17 00:23:04,773][62408] Updated weights for policy 1, policy_version 2980 (0.0007) -[2023-10-17 00:23:05,146][62408] Updated weights for policy 1, policy_version 2990 (0.0009) -[2023-10-17 00:23:05,510][62408] Updated weights for policy 1, policy_version 3000 (0.0007) -[2023-10-17 00:23:06,895][62373] Updated weights for policy 0, policy_version 3010 (0.0008) -[2023-10-17 00:23:07,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 6160384. Throughput: 0: 1766.6, 1: 1784.3. Samples: 1546380. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:23:07,214][61453] Avg episode reward: [(0, '2.470'), (1, '3.190')] -[2023-10-17 00:23:07,215][62252] Saving new best policy, reward=3.190! -[2023-10-17 00:23:07,266][62373] Updated weights for policy 0, policy_version 3020 (0.0008) -[2023-10-17 00:23:07,641][62373] Updated weights for policy 0, policy_version 3030 (0.0009) -[2023-10-17 00:23:08,015][62373] Updated weights for policy 0, policy_version 3040 (0.0007) -[2023-10-17 00:23:09,430][62408] Updated weights for policy 1, policy_version 3010 (0.0007) -[2023-10-17 00:23:09,797][62408] Updated weights for policy 1, policy_version 3020 (0.0011) -[2023-10-17 00:23:10,166][62408] Updated weights for policy 1, policy_version 3030 (0.0009) -[2023-10-17 00:23:10,536][62408] Updated weights for policy 1, policy_version 3040 (0.0010) -[2023-10-17 00:23:11,825][62373] Updated weights for policy 0, policy_version 3050 (0.0007) -[2023-10-17 00:23:12,194][62373] Updated weights for policy 0, policy_version 3060 (0.0007) -[2023-10-17 00:23:12,214][61453] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 6225920. Throughput: 0: 1786.7, 1: 1753.9. Samples: 1567420. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:23:12,214][61453] Avg episode reward: [(0, '2.660'), (1, '3.090')] -[2023-10-17 00:23:12,574][62373] Updated weights for policy 0, policy_version 3070 (0.0007) -[2023-10-17 00:23:14,336][62408] Updated weights for policy 1, policy_version 3050 (0.0009) -[2023-10-17 00:23:14,707][62408] Updated weights for policy 1, policy_version 3060 (0.0008) -[2023-10-17 00:23:15,083][62408] Updated weights for policy 1, policy_version 3070 (0.0008) -[2023-10-17 00:23:16,295][62373] Updated weights for policy 0, policy_version 3080 (0.0008) -[2023-10-17 00:23:16,659][62373] Updated weights for policy 0, policy_version 3090 (0.0008) -[2023-10-17 00:23:17,033][62373] Updated weights for policy 0, policy_version 3100 (0.0008) -[2023-10-17 00:23:17,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14745.7, 300 sec: 14106.9). Total num frames: 6324224. Throughput: 0: 1777.7, 1: 1751.3. Samples: 1588490. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-17 00:23:17,214][61453] Avg episode reward: [(0, '2.470'), (1, '2.730')] -[2023-10-17 00:23:19,049][62408] Updated weights for policy 1, policy_version 3080 (0.0008) -[2023-10-17 00:23:19,430][62408] Updated weights for policy 1, policy_version 3090 (0.0009) -[2023-10-17 00:23:19,792][62408] Updated weights for policy 1, policy_version 3100 (0.0008) -[2023-10-17 00:23:20,762][62373] Updated weights for policy 0, policy_version 3110 (0.0009) -[2023-10-17 00:23:21,125][62373] Updated weights for policy 0, policy_version 3120 (0.0010) -[2023-10-17 00:23:21,494][62373] Updated weights for policy 0, policy_version 3130 (0.0010) -[2023-10-17 00:23:22,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 6389760. Throughput: 0: 1776.3, 1: 1756.5. Samples: 1599254. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:23:22,215][61453] Avg episode reward: [(0, '1.960'), (1, '2.740')] -[2023-10-17 00:23:23,741][62408] Updated weights for policy 1, policy_version 3110 (0.0008) -[2023-10-17 00:23:24,124][62408] Updated weights for policy 1, policy_version 3120 (0.0010) -[2023-10-17 00:23:24,485][62408] Updated weights for policy 1, policy_version 3130 (0.0011) -[2023-10-17 00:23:25,221][62373] Updated weights for policy 0, policy_version 3140 (0.0011) -[2023-10-17 00:23:25,591][62373] Updated weights for policy 0, policy_version 3150 (0.0010) -[2023-10-17 00:23:25,959][62373] Updated weights for policy 0, policy_version 3160 (0.0010) -[2023-10-17 00:23:27,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 6455296. Throughput: 0: 1775.6, 1: 1754.5. Samples: 1620212. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:23:27,215][61453] Avg episode reward: [(0, '2.160'), (1, '2.660')] -[2023-10-17 00:23:28,179][62408] Updated weights for policy 1, policy_version 3140 (0.0009) -[2023-10-17 00:23:28,551][62408] Updated weights for policy 1, policy_version 3150 (0.0010) -[2023-10-17 00:23:28,931][62408] Updated weights for policy 1, policy_version 3160 (0.0008) -[2023-10-17 00:23:29,853][62373] Updated weights for policy 0, policy_version 3170 (0.0009) -[2023-10-17 00:23:30,225][62373] Updated weights for policy 0, policy_version 3180 (0.0008) -[2023-10-17 00:23:30,587][62373] Updated weights for policy 0, policy_version 3190 (0.0007) -[2023-10-17 00:23:30,969][62373] Updated weights for policy 0, policy_version 3200 (0.0010) -[2023-10-17 00:23:32,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 6520832. Throughput: 0: 1769.2, 1: 1771.4. Samples: 1642040. Policy #0 lag: (min: 29.0, avg: 36.5, max: 61.0) -[2023-10-17 00:23:32,215][61453] Avg episode reward: [(0, '2.320'), (1, '2.800')] -[2023-10-17 00:23:32,227][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000003200_3276800.pth... -[2023-10-17 00:23:32,227][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000003168_3244032.pth... -[2023-10-17 00:23:32,279][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000001536_1572864.pth -[2023-10-17 00:23:32,279][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000001536_1572864.pth -[2023-10-17 00:23:32,785][62408] Updated weights for policy 1, policy_version 3170 (0.0010) -[2023-10-17 00:23:33,155][62408] Updated weights for policy 1, policy_version 3180 (0.0009) -[2023-10-17 00:23:33,534][62408] Updated weights for policy 1, policy_version 3190 (0.0009) -[2023-10-17 00:23:33,900][62408] Updated weights for policy 1, policy_version 3200 (0.0007) -[2023-10-17 00:23:34,733][62373] Updated weights for policy 0, policy_version 3210 (0.0009) -[2023-10-17 00:23:35,104][62373] Updated weights for policy 0, policy_version 3220 (0.0008) -[2023-10-17 00:23:35,490][62373] Updated weights for policy 0, policy_version 3230 (0.0007) -[2023-10-17 00:23:37,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 6586368. Throughput: 0: 1794.9, 1: 1754.4. Samples: 1652422. Policy #0 lag: (min: 29.0, avg: 36.5, max: 61.0) -[2023-10-17 00:23:37,215][61453] Avg episode reward: [(0, '2.720'), (1, '2.890')] -[2023-10-17 00:23:37,651][62408] Updated weights for policy 1, policy_version 3210 (0.0007) -[2023-10-17 00:23:38,015][62408] Updated weights for policy 1, policy_version 3220 (0.0008) -[2023-10-17 00:23:38,386][62408] Updated weights for policy 1, policy_version 3230 (0.0008) -[2023-10-17 00:23:39,266][62373] Updated weights for policy 0, policy_version 3240 (0.0007) -[2023-10-17 00:23:39,645][62373] Updated weights for policy 0, policy_version 3250 (0.0008) -[2023-10-17 00:23:40,012][62373] Updated weights for policy 0, policy_version 3260 (0.0011) -[2023-10-17 00:23:42,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.7, 300 sec: 14106.9). Total num frames: 6651904. Throughput: 0: 1774.6, 1: 1764.4. Samples: 1673784. Policy #0 lag: (min: 19.0, avg: 19.2, max: 29.0) -[2023-10-17 00:23:42,215][61453] Avg episode reward: [(0, '2.900'), (1, '2.920')] -[2023-10-17 00:23:42,436][62408] Updated weights for policy 1, policy_version 3240 (0.0009) -[2023-10-17 00:23:42,817][62408] Updated weights for policy 1, policy_version 3250 (0.0008) -[2023-10-17 00:23:43,191][62408] Updated weights for policy 1, policy_version 3260 (0.0007) -[2023-10-17 00:23:43,627][62373] Updated weights for policy 0, policy_version 3270 (0.0009) -[2023-10-17 00:23:43,997][62373] Updated weights for policy 0, policy_version 3280 (0.0007) -[2023-10-17 00:23:44,367][62373] Updated weights for policy 0, policy_version 3290 (0.0010) -[2023-10-17 00:23:46,863][62408] Updated weights for policy 1, policy_version 3270 (0.0009) -[2023-10-17 00:23:47,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 6717440. Throughput: 0: 1776.5, 1: 1774.8. Samples: 1695368. Policy #0 lag: (min: 19.0, avg: 19.2, max: 29.0) -[2023-10-17 00:23:47,216][61453] Avg episode reward: [(0, '3.270'), (1, '2.970')] -[2023-10-17 00:23:47,227][62094] Saving new best policy, reward=3.270! -[2023-10-17 00:23:47,229][62408] Updated weights for policy 1, policy_version 3280 (0.0008) -[2023-10-17 00:23:47,599][62408] Updated weights for policy 1, policy_version 3290 (0.0008) -[2023-10-17 00:23:48,334][62373] Updated weights for policy 0, policy_version 3300 (0.0010) -[2023-10-17 00:23:48,716][62373] Updated weights for policy 0, policy_version 3310 (0.0010) -[2023-10-17 00:23:49,079][62373] Updated weights for policy 0, policy_version 3320 (0.0007) -[2023-10-17 00:23:51,451][62408] Updated weights for policy 1, policy_version 3300 (0.0007) -[2023-10-17 00:23:51,821][62408] Updated weights for policy 1, policy_version 3310 (0.0008) -[2023-10-17 00:23:52,186][62408] Updated weights for policy 1, policy_version 3320 (0.0007) -[2023-10-17 00:23:52,214][61453] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 6782976. Throughput: 0: 1777.9, 1: 1755.2. Samples: 1705374. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) -[2023-10-17 00:23:52,215][61453] Avg episode reward: [(0, '3.100'), (1, '3.010')] -[2023-10-17 00:23:52,798][62373] Updated weights for policy 0, policy_version 3330 (0.0007) -[2023-10-17 00:23:53,170][62373] Updated weights for policy 0, policy_version 3340 (0.0008) -[2023-10-17 00:23:53,532][62373] Updated weights for policy 0, policy_version 3350 (0.0009) -[2023-10-17 00:23:53,903][62373] Updated weights for policy 0, policy_version 3360 (0.0007) -[2023-10-17 00:23:55,891][62408] Updated weights for policy 1, policy_version 3330 (0.0007) -[2023-10-17 00:23:56,260][62408] Updated weights for policy 1, policy_version 3340 (0.0007) -[2023-10-17 00:23:56,629][62408] Updated weights for policy 1, policy_version 3350 (0.0008) -[2023-10-17 00:23:57,001][62408] Updated weights for policy 1, policy_version 3360 (0.0008) -[2023-10-17 00:23:57,214][61453] Fps is (10 sec: 16384.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 6881280. Throughput: 0: 1776.0, 1: 1778.9. Samples: 1727390. Policy #0 lag: (min: 31.0, avg: 36.5, max: 63.0) -[2023-10-17 00:23:57,215][61453] Avg episode reward: [(0, '3.110'), (1, '2.920')] -[2023-10-17 00:23:57,721][62373] Updated weights for policy 0, policy_version 3370 (0.0008) -[2023-10-17 00:23:58,099][62373] Updated weights for policy 0, policy_version 3380 (0.0007) -[2023-10-17 00:23:58,470][62373] Updated weights for policy 0, policy_version 3390 (0.0007) -[2023-10-17 00:24:00,947][62408] Updated weights for policy 1, policy_version 3370 (0.0007) -[2023-10-17 00:24:01,324][62408] Updated weights for policy 1, policy_version 3380 (0.0011) -[2023-10-17 00:24:01,686][62408] Updated weights for policy 1, policy_version 3390 (0.0011) -[2023-10-17 00:24:02,214][61453] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 6946816. Throughput: 0: 1796.8, 1: 1743.2. Samples: 1747790. Policy #0 lag: (min: 31.0, avg: 31.5, max: 46.0) -[2023-10-17 00:24:02,214][61453] Avg episode reward: [(0, '3.020'), (1, '2.840')] -[2023-10-17 00:24:02,337][62373] Updated weights for policy 0, policy_version 3400 (0.0008) -[2023-10-17 00:24:02,719][62373] Updated weights for policy 0, policy_version 3410 (0.0011) -[2023-10-17 00:24:03,087][62373] Updated weights for policy 0, policy_version 3420 (0.0011) -[2023-10-17 00:24:05,666][62408] Updated weights for policy 1, policy_version 3400 (0.0010) -[2023-10-17 00:24:06,037][62408] Updated weights for policy 1, policy_version 3410 (0.0010) -[2023-10-17 00:24:06,415][62408] Updated weights for policy 1, policy_version 3420 (0.0011) -[2023-10-17 00:24:06,887][62373] Updated weights for policy 0, policy_version 3430 (0.0009) -[2023-10-17 00:24:07,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 7012352. Throughput: 0: 1770.8, 1: 1774.1. Samples: 1758776. Policy #0 lag: (min: 31.0, avg: 31.5, max: 46.0) -[2023-10-17 00:24:07,214][61453] Avg episode reward: [(0, '2.710'), (1, '2.970')] -[2023-10-17 00:24:07,253][62373] Updated weights for policy 0, policy_version 3440 (0.0009) -[2023-10-17 00:24:07,628][62373] Updated weights for policy 0, policy_version 3450 (0.0008) -[2023-10-17 00:24:10,180][62408] Updated weights for policy 1, policy_version 3430 (0.0010) -[2023-10-17 00:24:10,553][62408] Updated weights for policy 1, policy_version 3440 (0.0009) -[2023-10-17 00:24:10,923][62408] Updated weights for policy 1, policy_version 3450 (0.0008) -[2023-10-17 00:24:11,372][62373] Updated weights for policy 0, policy_version 3460 (0.0009) -[2023-10-17 00:24:11,747][62373] Updated weights for policy 0, policy_version 3470 (0.0009) -[2023-10-17 00:24:12,127][62373] Updated weights for policy 0, policy_version 3480 (0.0008) -[2023-10-17 00:24:12,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 7077888. Throughput: 0: 1790.9, 1: 1759.2. Samples: 1779970. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) -[2023-10-17 00:24:12,215][61453] Avg episode reward: [(0, '2.930'), (1, '3.240')] -[2023-10-17 00:24:12,217][62252] Saving new best policy, reward=3.240! -[2023-10-17 00:24:14,674][62408] Updated weights for policy 1, policy_version 3460 (0.0010) -[2023-10-17 00:24:15,050][62408] Updated weights for policy 1, policy_version 3470 (0.0010) -[2023-10-17 00:24:15,414][62408] Updated weights for policy 1, policy_version 3480 (0.0008) -[2023-10-17 00:24:15,818][62373] Updated weights for policy 0, policy_version 3490 (0.0007) -[2023-10-17 00:24:16,193][62373] Updated weights for policy 0, policy_version 3500 (0.0007) -[2023-10-17 00:24:16,558][62373] Updated weights for policy 0, policy_version 3510 (0.0007) -[2023-10-17 00:24:16,931][62373] Updated weights for policy 0, policy_version 3520 (0.0008) -[2023-10-17 00:24:17,214][61453] Fps is (10 sec: 16383.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 7176192. Throughput: 0: 1769.2, 1: 1748.1. Samples: 1800320. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) -[2023-10-17 00:24:17,215][61453] Avg episode reward: [(0, '2.830'), (1, '3.140')] -[2023-10-17 00:24:19,264][62408] Updated weights for policy 1, policy_version 3490 (0.0008) -[2023-10-17 00:24:19,639][62408] Updated weights for policy 1, policy_version 3500 (0.0008) -[2023-10-17 00:24:20,008][62408] Updated weights for policy 1, policy_version 3510 (0.0007) -[2023-10-17 00:24:20,383][62408] Updated weights for policy 1, policy_version 3520 (0.0007) -[2023-10-17 00:24:20,752][62373] Updated weights for policy 0, policy_version 3530 (0.0008) -[2023-10-17 00:24:21,124][62373] Updated weights for policy 0, policy_version 3540 (0.0008) -[2023-10-17 00:24:21,507][62373] Updated weights for policy 0, policy_version 3550 (0.0009) -[2023-10-17 00:24:22,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 7241728. Throughput: 0: 1781.9, 1: 1764.3. Samples: 1812002. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) -[2023-10-17 00:24:22,215][61453] Avg episode reward: [(0, '2.910'), (1, '3.230')] -[2023-10-17 00:24:24,114][62408] Updated weights for policy 1, policy_version 3530 (0.0010) -[2023-10-17 00:24:24,487][62408] Updated weights for policy 1, policy_version 3540 (0.0009) -[2023-10-17 00:24:24,853][62408] Updated weights for policy 1, policy_version 3550 (0.0007) -[2023-10-17 00:24:25,385][62373] Updated weights for policy 0, policy_version 3560 (0.0008) -[2023-10-17 00:24:25,759][62373] Updated weights for policy 0, policy_version 3570 (0.0007) -[2023-10-17 00:24:26,130][62373] Updated weights for policy 0, policy_version 3580 (0.0009) -[2023-10-17 00:24:27,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 7307264. Throughput: 0: 1772.7, 1: 1750.4. Samples: 1832322. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-10-17 00:24:27,215][61453] Avg episode reward: [(0, '2.970'), (1, '3.130')] -[2023-10-17 00:24:28,717][62408] Updated weights for policy 1, policy_version 3560 (0.0009) -[2023-10-17 00:24:29,092][62408] Updated weights for policy 1, policy_version 3570 (0.0010) -[2023-10-17 00:24:29,461][62408] Updated weights for policy 1, policy_version 3580 (0.0007) -[2023-10-17 00:24:29,942][62373] Updated weights for policy 0, policy_version 3590 (0.0007) -[2023-10-17 00:24:30,315][62373] Updated weights for policy 0, policy_version 3600 (0.0008) -[2023-10-17 00:24:30,697][62373] Updated weights for policy 0, policy_version 3610 (0.0008) -[2023-10-17 00:24:32,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 7372800. Throughput: 0: 1765.1, 1: 1763.2. Samples: 1854140. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-10-17 00:24:32,215][61453] Avg episode reward: [(0, '2.580'), (1, '3.020')] -[2023-10-17 00:24:33,263][62408] Updated weights for policy 1, policy_version 3590 (0.0009) -[2023-10-17 00:24:33,632][62408] Updated weights for policy 1, policy_version 3600 (0.0011) -[2023-10-17 00:24:34,005][62408] Updated weights for policy 1, policy_version 3610 (0.0009) -[2023-10-17 00:24:34,639][62373] Updated weights for policy 0, policy_version 3620 (0.0008) -[2023-10-17 00:24:35,018][62373] Updated weights for policy 0, policy_version 3630 (0.0008) -[2023-10-17 00:24:35,384][62373] Updated weights for policy 0, policy_version 3640 (0.0009) -[2023-10-17 00:24:37,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 7438336. Throughput: 0: 1784.4, 1: 1753.6. Samples: 1864582. Policy #0 lag: (min: 31.0, avg: 40.4, max: 63.0) -[2023-10-17 00:24:37,215][61453] Avg episode reward: [(0, '2.520'), (1, '3.180')] -[2023-10-17 00:24:37,933][62408] Updated weights for policy 1, policy_version 3620 (0.0009) -[2023-10-17 00:24:38,300][62408] Updated weights for policy 1, policy_version 3630 (0.0007) -[2023-10-17 00:24:38,676][62408] Updated weights for policy 1, policy_version 3640 (0.0008) -[2023-10-17 00:24:39,100][62373] Updated weights for policy 0, policy_version 3650 (0.0010) -[2023-10-17 00:24:39,461][62373] Updated weights for policy 0, policy_version 3660 (0.0007) -[2023-10-17 00:24:39,839][62373] Updated weights for policy 0, policy_version 3670 (0.0007) -[2023-10-17 00:24:40,204][62373] Updated weights for policy 0, policy_version 3680 (0.0007) -[2023-10-17 00:24:42,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 7503872. Throughput: 0: 1764.9, 1: 1753.7. Samples: 1885722. Policy #0 lag: (min: 31.0, avg: 40.4, max: 63.0) -[2023-10-17 00:24:42,215][61453] Avg episode reward: [(0, '2.760'), (1, '2.710')] -[2023-10-17 00:24:42,575][62408] Updated weights for policy 1, policy_version 3650 (0.0008) -[2023-10-17 00:24:42,941][62408] Updated weights for policy 1, policy_version 3660 (0.0009) -[2023-10-17 00:24:43,307][62408] Updated weights for policy 1, policy_version 3670 (0.0008) -[2023-10-17 00:24:43,678][62408] Updated weights for policy 1, policy_version 3680 (0.0007) -[2023-10-17 00:24:43,862][62373] Updated weights for policy 0, policy_version 3690 (0.0007) -[2023-10-17 00:24:44,230][62373] Updated weights for policy 0, policy_version 3700 (0.0008) -[2023-10-17 00:24:44,603][62373] Updated weights for policy 0, policy_version 3710 (0.0008) -[2023-10-17 00:24:47,214][61453] Fps is (10 sec: 13107.6, 60 sec: 14199.6, 300 sec: 14106.9). Total num frames: 7569408. Throughput: 0: 1766.0, 1: 1785.9. Samples: 1907626. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-17 00:24:47,214][61453] Avg episode reward: [(0, '2.870'), (1, '2.480')] -[2023-10-17 00:24:47,578][62408] Updated weights for policy 1, policy_version 3690 (0.0008) -[2023-10-17 00:24:47,952][62408] Updated weights for policy 1, policy_version 3700 (0.0008) -[2023-10-17 00:24:48,314][62408] Updated weights for policy 1, policy_version 3710 (0.0008) -[2023-10-17 00:24:48,510][62373] Updated weights for policy 0, policy_version 3720 (0.0007) -[2023-10-17 00:24:48,883][62373] Updated weights for policy 0, policy_version 3730 (0.0008) -[2023-10-17 00:24:49,249][62373] Updated weights for policy 0, policy_version 3740 (0.0007) -[2023-10-17 00:24:52,191][62408] Updated weights for policy 1, policy_version 3720 (0.0009) -[2023-10-17 00:24:52,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 7634944. Throughput: 0: 1769.2, 1: 1751.3. Samples: 1917200. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-17 00:24:52,214][61453] Avg episode reward: [(0, '3.030'), (1, '2.460')] -[2023-10-17 00:24:52,554][62408] Updated weights for policy 1, policy_version 3730 (0.0007) -[2023-10-17 00:24:52,926][62408] Updated weights for policy 1, policy_version 3740 (0.0007) -[2023-10-17 00:24:53,085][62373] Updated weights for policy 0, policy_version 3750 (0.0007) -[2023-10-17 00:24:53,461][62373] Updated weights for policy 0, policy_version 3760 (0.0010) -[2023-10-17 00:24:53,848][62373] Updated weights for policy 0, policy_version 3770 (0.0010) -[2023-10-17 00:24:56,951][62408] Updated weights for policy 1, policy_version 3750 (0.0007) -[2023-10-17 00:24:57,214][61453] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 7700480. Throughput: 0: 1769.2, 1: 1764.7. Samples: 1938992. Policy #0 lag: (min: 16.0, avg: 41.6, max: 48.0) -[2023-10-17 00:24:57,214][61453] Avg episode reward: [(0, '3.250'), (1, '2.460')] -[2023-10-17 00:24:57,321][62408] Updated weights for policy 1, policy_version 3760 (0.0008) -[2023-10-17 00:24:57,572][62373] Updated weights for policy 0, policy_version 3780 (0.0009) -[2023-10-17 00:24:57,690][62408] Updated weights for policy 1, policy_version 3770 (0.0007) -[2023-10-17 00:24:57,942][62373] Updated weights for policy 0, policy_version 3790 (0.0010) -[2023-10-17 00:24:58,319][62373] Updated weights for policy 0, policy_version 3800 (0.0010) -[2023-10-17 00:25:01,543][62408] Updated weights for policy 1, policy_version 3780 (0.0009) -[2023-10-17 00:25:01,914][62408] Updated weights for policy 1, policy_version 3790 (0.0008) -[2023-10-17 00:25:02,092][62373] Updated weights for policy 0, policy_version 3810 (0.0011) -[2023-10-17 00:25:02,214][61453] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 7766016. Throughput: 0: 1799.4, 1: 1755.6. Samples: 1960294. Policy #0 lag: (min: 16.0, avg: 41.6, max: 48.0) -[2023-10-17 00:25:02,214][61453] Avg episode reward: [(0, '3.110'), (1, '2.840')] -[2023-10-17 00:25:02,275][62408] Updated weights for policy 1, policy_version 3800 (0.0007) -[2023-10-17 00:25:02,454][62373] Updated weights for policy 0, policy_version 3820 (0.0008) -[2023-10-17 00:25:02,832][62373] Updated weights for policy 0, policy_version 3830 (0.0007) -[2023-10-17 00:25:03,207][62373] Updated weights for policy 0, policy_version 3840 (0.0008) -[2023-10-17 00:25:05,926][62408] Updated weights for policy 1, policy_version 3810 (0.0007) -[2023-10-17 00:25:06,303][62408] Updated weights for policy 1, policy_version 3820 (0.0011) -[2023-10-17 00:25:06,671][62408] Updated weights for policy 1, policy_version 3830 (0.0011) -[2023-10-17 00:25:07,044][62408] Updated weights for policy 1, policy_version 3840 (0.0008) -[2023-10-17 00:25:07,172][62373] Updated weights for policy 0, policy_version 3850 (0.0008) -[2023-10-17 00:25:07,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 7864320. Throughput: 0: 1764.8, 1: 1758.7. Samples: 1970558. Policy #0 lag: (min: 29.0, avg: 33.3, max: 61.0) -[2023-10-17 00:25:07,215][61453] Avg episode reward: [(0, '3.160'), (1, '2.920')] -[2023-10-17 00:25:07,543][62373] Updated weights for policy 0, policy_version 3860 (0.0007) -[2023-10-17 00:25:07,906][62373] Updated weights for policy 0, policy_version 3870 (0.0008) -[2023-10-17 00:25:10,879][62408] Updated weights for policy 1, policy_version 3850 (0.0007) -[2023-10-17 00:25:11,249][62408] Updated weights for policy 1, policy_version 3860 (0.0009) -[2023-10-17 00:25:11,613][62408] Updated weights for policy 1, policy_version 3870 (0.0009) -[2023-10-17 00:25:11,662][62373] Updated weights for policy 0, policy_version 3880 (0.0008) -[2023-10-17 00:25:12,031][62373] Updated weights for policy 0, policy_version 3890 (0.0007) -[2023-10-17 00:25:12,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 7929856. Throughput: 0: 1789.6, 1: 1765.8. Samples: 1992312. Policy #0 lag: (min: 29.0, avg: 33.3, max: 61.0) -[2023-10-17 00:25:12,215][61453] Avg episode reward: [(0, '2.960'), (1, '3.240')] -[2023-10-17 00:25:12,406][62373] Updated weights for policy 0, policy_version 3900 (0.0008) -[2023-10-17 00:25:15,543][62408] Updated weights for policy 1, policy_version 3880 (0.0008) -[2023-10-17 00:25:15,925][62408] Updated weights for policy 1, policy_version 3890 (0.0007) -[2023-10-17 00:25:16,188][62373] Updated weights for policy 0, policy_version 3910 (0.0008) -[2023-10-17 00:25:16,294][62408] Updated weights for policy 1, policy_version 3900 (0.0007) -[2023-10-17 00:25:16,561][62373] Updated weights for policy 0, policy_version 3920 (0.0009) -[2023-10-17 00:25:16,934][62373] Updated weights for policy 0, policy_version 3930 (0.0009) -[2023-10-17 00:25:17,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 8028160. Throughput: 0: 1771.3, 1: 1736.9. Samples: 2012010. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-10-17 00:25:17,215][61453] Avg episode reward: [(0, '2.730'), (1, '3.360')] -[2023-10-17 00:25:17,222][62252] Saving new best policy, reward=3.360! -[2023-10-17 00:25:19,938][62408] Updated weights for policy 1, policy_version 3910 (0.0007) -[2023-10-17 00:25:20,304][62408] Updated weights for policy 1, policy_version 3920 (0.0007) -[2023-10-17 00:25:20,672][62408] Updated weights for policy 1, policy_version 3930 (0.0009) -[2023-10-17 00:25:20,757][62373] Updated weights for policy 0, policy_version 3940 (0.0009) -[2023-10-17 00:25:21,129][62373] Updated weights for policy 0, policy_version 3950 (0.0009) -[2023-10-17 00:25:21,496][62373] Updated weights for policy 0, policy_version 3960 (0.0009) -[2023-10-17 00:25:22,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 8093696. Throughput: 0: 1776.5, 1: 1770.2. Samples: 2024184. Policy #0 lag: (min: 31.0, avg: 31.3, max: 44.0) -[2023-10-17 00:25:22,215][61453] Avg episode reward: [(0, '2.700'), (1, '3.320')] -[2023-10-17 00:25:24,410][62408] Updated weights for policy 1, policy_version 3940 (0.0009) -[2023-10-17 00:25:24,782][62408] Updated weights for policy 1, policy_version 3950 (0.0008) -[2023-10-17 00:25:25,155][62408] Updated weights for policy 1, policy_version 3960 (0.0008) -[2023-10-17 00:25:25,416][62373] Updated weights for policy 0, policy_version 3970 (0.0009) -[2023-10-17 00:25:25,789][62373] Updated weights for policy 0, policy_version 3980 (0.0010) -[2023-10-17 00:25:26,157][62373] Updated weights for policy 0, policy_version 3990 (0.0007) -[2023-10-17 00:25:26,530][62373] Updated weights for policy 0, policy_version 4000 (0.0008) -[2023-10-17 00:25:27,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 8159232. Throughput: 0: 1779.7, 1: 1745.1. Samples: 2044338. Policy #0 lag: (min: 31.0, avg: 31.3, max: 44.0) -[2023-10-17 00:25:27,214][61453] Avg episode reward: [(0, '2.940'), (1, '3.330')] -[2023-10-17 00:25:29,014][62408] Updated weights for policy 1, policy_version 3970 (0.0008) -[2023-10-17 00:25:29,380][62408] Updated weights for policy 1, policy_version 3980 (0.0009) -[2023-10-17 00:25:29,753][62408] Updated weights for policy 1, policy_version 3990 (0.0007) -[2023-10-17 00:25:30,127][62408] Updated weights for policy 1, policy_version 4000 (0.0007) -[2023-10-17 00:25:30,383][62373] Updated weights for policy 0, policy_version 4010 (0.0008) -[2023-10-17 00:25:30,747][62373] Updated weights for policy 0, policy_version 4020 (0.0009) -[2023-10-17 00:25:31,122][62373] Updated weights for policy 0, policy_version 4030 (0.0009) -[2023-10-17 00:25:32,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 8224768. Throughput: 0: 1757.5, 1: 1757.3. Samples: 2065790. Policy #0 lag: (min: 31.0, avg: 31.7, max: 48.0) -[2023-10-17 00:25:32,215][61453] Avg episode reward: [(0, '2.890'), (1, '3.260')] -[2023-10-17 00:25:32,227][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000004000_4096000.pth... -[2023-10-17 00:25:32,227][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000004032_4128768.pth... -[2023-10-17 00:25:32,257][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000002368_2424832.pth -[2023-10-17 00:25:32,263][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000002368_2424832.pth -[2023-10-17 00:25:33,941][62408] Updated weights for policy 1, policy_version 4010 (0.0007) -[2023-10-17 00:25:34,307][62408] Updated weights for policy 1, policy_version 4020 (0.0008) -[2023-10-17 00:25:34,684][62408] Updated weights for policy 1, policy_version 4030 (0.0009) -[2023-10-17 00:25:35,028][62373] Updated weights for policy 0, policy_version 4040 (0.0009) -[2023-10-17 00:25:35,392][62373] Updated weights for policy 0, policy_version 4050 (0.0009) -[2023-10-17 00:25:35,758][62373] Updated weights for policy 0, policy_version 4060 (0.0008) -[2023-10-17 00:25:37,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 8290304. Throughput: 0: 1781.5, 1: 1757.4. Samples: 2076452. Policy #0 lag: (min: 31.0, avg: 31.7, max: 48.0) -[2023-10-17 00:25:37,215][61453] Avg episode reward: [(0, '3.310'), (1, '2.910')] -[2023-10-17 00:25:37,216][62094] Saving new best policy, reward=3.310! -[2023-10-17 00:25:38,571][62408] Updated weights for policy 1, policy_version 4040 (0.0008) -[2023-10-17 00:25:38,948][62408] Updated weights for policy 1, policy_version 4050 (0.0007) -[2023-10-17 00:25:39,309][62408] Updated weights for policy 1, policy_version 4060 (0.0007) -[2023-10-17 00:25:39,457][62373] Updated weights for policy 0, policy_version 4070 (0.0009) -[2023-10-17 00:25:39,825][62373] Updated weights for policy 0, policy_version 4080 (0.0010) -[2023-10-17 00:25:40,186][62373] Updated weights for policy 0, policy_version 4090 (0.0007) -[2023-10-17 00:25:42,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 8355840. Throughput: 0: 1757.9, 1: 1765.8. Samples: 2097558. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-17 00:25:42,215][61453] Avg episode reward: [(0, '3.070'), (1, '2.900')] -[2023-10-17 00:25:42,935][62408] Updated weights for policy 1, policy_version 4070 (0.0007) -[2023-10-17 00:25:43,299][62408] Updated weights for policy 1, policy_version 4080 (0.0010) -[2023-10-17 00:25:43,673][62408] Updated weights for policy 1, policy_version 4090 (0.0009) -[2023-10-17 00:25:44,009][62373] Updated weights for policy 0, policy_version 4100 (0.0008) -[2023-10-17 00:25:44,388][62373] Updated weights for policy 0, policy_version 4110 (0.0011) -[2023-10-17 00:25:44,756][62373] Updated weights for policy 0, policy_version 4120 (0.0007) -[2023-10-17 00:25:47,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 8421376. Throughput: 0: 1754.1, 1: 1786.8. Samples: 2119636. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-17 00:25:47,215][61453] Avg episode reward: [(0, '2.750'), (1, '2.970')] -[2023-10-17 00:25:47,458][62408] Updated weights for policy 1, policy_version 4100 (0.0008) -[2023-10-17 00:25:47,830][62408] Updated weights for policy 1, policy_version 4110 (0.0011) -[2023-10-17 00:25:48,189][62408] Updated weights for policy 1, policy_version 4120 (0.0010) -[2023-10-17 00:25:48,783][62373] Updated weights for policy 0, policy_version 4130 (0.0007) -[2023-10-17 00:25:49,154][62373] Updated weights for policy 0, policy_version 4140 (0.0007) -[2023-10-17 00:25:49,526][62373] Updated weights for policy 0, policy_version 4150 (0.0009) -[2023-10-17 00:25:49,902][62373] Updated weights for policy 0, policy_version 4160 (0.0010) -[2023-10-17 00:25:51,954][62408] Updated weights for policy 1, policy_version 4130 (0.0009) -[2023-10-17 00:25:52,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 8486912. Throughput: 0: 1757.3, 1: 1770.5. Samples: 2129308. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:25:52,214][61453] Avg episode reward: [(0, '3.050'), (1, '2.900')] -[2023-10-17 00:25:52,314][62408] Updated weights for policy 1, policy_version 4140 (0.0011) -[2023-10-17 00:25:52,690][62408] Updated weights for policy 1, policy_version 4150 (0.0008) -[2023-10-17 00:25:53,048][62408] Updated weights for policy 1, policy_version 4160 (0.0007) -[2023-10-17 00:25:53,788][62373] Updated weights for policy 0, policy_version 4170 (0.0008) -[2023-10-17 00:25:54,158][62373] Updated weights for policy 0, policy_version 4180 (0.0008) -[2023-10-17 00:25:54,532][62373] Updated weights for policy 0, policy_version 4190 (0.0007) -[2023-10-17 00:25:56,900][62408] Updated weights for policy 1, policy_version 4170 (0.0007) -[2023-10-17 00:25:57,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 8552448. Throughput: 0: 1753.5, 1: 1782.0. Samples: 2151412. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:25:57,215][61453] Avg episode reward: [(0, '2.620'), (1, '2.980')] -[2023-10-17 00:25:57,273][62408] Updated weights for policy 1, policy_version 4180 (0.0007) -[2023-10-17 00:25:57,643][62408] Updated weights for policy 1, policy_version 4190 (0.0007) -[2023-10-17 00:25:58,283][62373] Updated weights for policy 0, policy_version 4200 (0.0009) -[2023-10-17 00:25:58,643][62373] Updated weights for policy 0, policy_version 4210 (0.0008) -[2023-10-17 00:25:59,015][62373] Updated weights for policy 0, policy_version 4220 (0.0008) -[2023-10-17 00:26:01,484][62408] Updated weights for policy 1, policy_version 4200 (0.0009) -[2023-10-17 00:26:01,861][62408] Updated weights for policy 1, policy_version 4210 (0.0009) -[2023-10-17 00:26:02,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 8617984. Throughput: 0: 1780.3, 1: 1789.8. Samples: 2172664. Policy #0 lag: (min: 31.0, avg: 32.3, max: 56.0) -[2023-10-17 00:26:02,215][61453] Avg episode reward: [(0, '2.820'), (1, '2.810')] -[2023-10-17 00:26:02,219][62408] Updated weights for policy 1, policy_version 4220 (0.0008) -[2023-10-17 00:26:02,716][62373] Updated weights for policy 0, policy_version 4230 (0.0009) -[2023-10-17 00:26:03,080][62373] Updated weights for policy 0, policy_version 4240 (0.0010) -[2023-10-17 00:26:03,456][62373] Updated weights for policy 0, policy_version 4250 (0.0009) -[2023-10-17 00:26:06,097][62408] Updated weights for policy 1, policy_version 4230 (0.0008) -[2023-10-17 00:26:06,476][62408] Updated weights for policy 1, policy_version 4240 (0.0007) -[2023-10-17 00:26:06,839][62408] Updated weights for policy 1, policy_version 4250 (0.0010) -[2023-10-17 00:26:07,098][62373] Updated weights for policy 0, policy_version 4260 (0.0008) -[2023-10-17 00:26:07,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 8716288. Throughput: 0: 1759.5, 1: 1773.7. Samples: 2183176. Policy #0 lag: (min: 31.0, avg: 32.3, max: 56.0) -[2023-10-17 00:26:07,215][61453] Avg episode reward: [(0, '3.010'), (1, '3.030')] -[2023-10-17 00:26:07,466][62373] Updated weights for policy 0, policy_version 4270 (0.0010) -[2023-10-17 00:26:07,845][62373] Updated weights for policy 0, policy_version 4280 (0.0010) -[2023-10-17 00:26:10,857][62408] Updated weights for policy 1, policy_version 4260 (0.0009) -[2023-10-17 00:26:11,220][62408] Updated weights for policy 1, policy_version 4270 (0.0007) -[2023-10-17 00:26:11,591][62408] Updated weights for policy 1, policy_version 4280 (0.0008) -[2023-10-17 00:26:11,615][62373] Updated weights for policy 0, policy_version 4290 (0.0007) -[2023-10-17 00:26:11,987][62373] Updated weights for policy 0, policy_version 4300 (0.0010) -[2023-10-17 00:26:12,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 8781824. Throughput: 0: 1775.7, 1: 1792.8. Samples: 2204924. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:26:12,214][61453] Avg episode reward: [(0, '3.300'), (1, '2.950')] -[2023-10-17 00:26:12,362][62373] Updated weights for policy 0, policy_version 4310 (0.0007) -[2023-10-17 00:26:12,737][62373] Updated weights for policy 0, policy_version 4320 (0.0007) -[2023-10-17 00:26:15,376][62408] Updated weights for policy 1, policy_version 4290 (0.0008) -[2023-10-17 00:26:15,748][62408] Updated weights for policy 1, policy_version 4300 (0.0007) -[2023-10-17 00:26:16,124][62408] Updated weights for policy 1, policy_version 4310 (0.0007) -[2023-10-17 00:26:16,471][62373] Updated weights for policy 0, policy_version 4330 (0.0009) -[2023-10-17 00:26:16,498][62408] Updated weights for policy 1, policy_version 4320 (0.0007) -[2023-10-17 00:26:16,848][62373] Updated weights for policy 0, policy_version 4340 (0.0008) -[2023-10-17 00:26:17,212][62373] Updated weights for policy 0, policy_version 4350 (0.0007) -[2023-10-17 00:26:17,214][61453] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 14218.0). Total num frames: 8847360. Throughput: 0: 1776.2, 1: 1756.7. Samples: 2224770. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:26:17,215][61453] Avg episode reward: [(0, '3.330'), (1, '3.130')] -[2023-10-17 00:26:17,285][62094] Saving new best policy, reward=3.330! -[2023-10-17 00:26:20,223][62408] Updated weights for policy 1, policy_version 4330 (0.0011) -[2023-10-17 00:26:20,608][62408] Updated weights for policy 1, policy_version 4340 (0.0010) -[2023-10-17 00:26:20,970][62408] Updated weights for policy 1, policy_version 4350 (0.0009) -[2023-10-17 00:26:21,068][62373] Updated weights for policy 0, policy_version 4360 (0.0009) -[2023-10-17 00:26:21,447][62373] Updated weights for policy 0, policy_version 4370 (0.0009) -[2023-10-17 00:26:21,816][62373] Updated weights for policy 0, policy_version 4380 (0.0007) -[2023-10-17 00:26:22,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 8945664. Throughput: 0: 1774.0, 1: 1790.6. Samples: 2236858. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:26:22,215][61453] Avg episode reward: [(0, '3.340'), (1, '3.180')] -[2023-10-17 00:26:22,215][62094] Saving new best policy, reward=3.340! -[2023-10-17 00:26:24,886][62408] Updated weights for policy 1, policy_version 4360 (0.0008) -[2023-10-17 00:26:25,261][62408] Updated weights for policy 1, policy_version 4370 (0.0010) -[2023-10-17 00:26:25,629][62408] Updated weights for policy 1, policy_version 4380 (0.0009) -[2023-10-17 00:26:25,655][62373] Updated weights for policy 0, policy_version 4390 (0.0007) -[2023-10-17 00:26:26,020][62373] Updated weights for policy 0, policy_version 4400 (0.0009) -[2023-10-17 00:26:26,397][62373] Updated weights for policy 0, policy_version 4410 (0.0007) -[2023-10-17 00:26:27,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 9011200. Throughput: 0: 1782.6, 1: 1752.8. Samples: 2256648. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:26:27,215][61453] Avg episode reward: [(0, '3.370'), (1, '3.290')] -[2023-10-17 00:26:27,215][62094] Saving new best policy, reward=3.370! -[2023-10-17 00:26:29,519][62408] Updated weights for policy 1, policy_version 4390 (0.0009) -[2023-10-17 00:26:29,893][62408] Updated weights for policy 1, policy_version 4400 (0.0010) -[2023-10-17 00:26:30,255][62408] Updated weights for policy 1, policy_version 4410 (0.0010) -[2023-10-17 00:26:30,260][62373] Updated weights for policy 0, policy_version 4420 (0.0008) -[2023-10-17 00:26:30,623][62373] Updated weights for policy 0, policy_version 4430 (0.0010) -[2023-10-17 00:26:30,993][62373] Updated weights for policy 0, policy_version 4440 (0.0010) -[2023-10-17 00:26:32,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 9076736. Throughput: 0: 1764.9, 1: 1751.4. Samples: 2277870. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:26:32,215][61453] Avg episode reward: [(0, '3.470'), (1, '3.180')] -[2023-10-17 00:26:32,226][62094] Saving new best policy, reward=3.470! -[2023-10-17 00:26:33,961][62408] Updated weights for policy 1, policy_version 4420 (0.0009) -[2023-10-17 00:26:34,325][62408] Updated weights for policy 1, policy_version 4430 (0.0008) -[2023-10-17 00:26:34,693][62408] Updated weights for policy 1, policy_version 4440 (0.0009) -[2023-10-17 00:26:34,758][62373] Updated weights for policy 0, policy_version 4450 (0.0008) -[2023-10-17 00:26:35,124][62373] Updated weights for policy 0, policy_version 4460 (0.0010) -[2023-10-17 00:26:35,493][62373] Updated weights for policy 0, policy_version 4470 (0.0008) -[2023-10-17 00:26:35,872][62373] Updated weights for policy 0, policy_version 4480 (0.0009) -[2023-10-17 00:26:37,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 9142272. Throughput: 0: 1792.9, 1: 1754.5. Samples: 2288942. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:26:37,214][61453] Avg episode reward: [(0, '3.240'), (1, '3.380')] -[2023-10-17 00:26:37,215][62252] Saving new best policy, reward=3.380! -[2023-10-17 00:26:38,747][62408] Updated weights for policy 1, policy_version 4450 (0.0010) -[2023-10-17 00:26:39,118][62408] Updated weights for policy 1, policy_version 4460 (0.0010) -[2023-10-17 00:26:39,492][62408] Updated weights for policy 1, policy_version 4470 (0.0009) -[2023-10-17 00:26:39,577][62373] Updated weights for policy 0, policy_version 4490 (0.0008) -[2023-10-17 00:26:39,853][62408] Updated weights for policy 1, policy_version 4480 (0.0008) -[2023-10-17 00:26:39,950][62373] Updated weights for policy 0, policy_version 4500 (0.0007) -[2023-10-17 00:26:40,327][62373] Updated weights for policy 0, policy_version 4510 (0.0008) -[2023-10-17 00:26:42,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 9207808. Throughput: 0: 1772.0, 1: 1741.2. Samples: 2309508. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:26:42,215][61453] Avg episode reward: [(0, '3.520'), (1, '3.330')] -[2023-10-17 00:26:42,217][62094] Saving new best policy, reward=3.520! -[2023-10-17 00:26:43,783][62408] Updated weights for policy 1, policy_version 4490 (0.0007) -[2023-10-17 00:26:44,156][62408] Updated weights for policy 1, policy_version 4500 (0.0009) -[2023-10-17 00:26:44,158][62373] Updated weights for policy 0, policy_version 4520 (0.0010) -[2023-10-17 00:26:44,516][62408] Updated weights for policy 1, policy_version 4510 (0.0008) -[2023-10-17 00:26:44,527][62373] Updated weights for policy 0, policy_version 4530 (0.0009) -[2023-10-17 00:26:44,889][62373] Updated weights for policy 0, policy_version 4540 (0.0009) -[2023-10-17 00:26:47,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 9273344. Throughput: 0: 1772.7, 1: 1760.4. Samples: 2331652. Policy #0 lag: (min: 31.0, avg: 34.2, max: 63.0) -[2023-10-17 00:26:47,214][61453] Avg episode reward: [(0, '3.250'), (1, '3.340')] -[2023-10-17 00:26:48,295][62408] Updated weights for policy 1, policy_version 4520 (0.0008) -[2023-10-17 00:26:48,628][62373] Updated weights for policy 0, policy_version 4550 (0.0009) -[2023-10-17 00:26:48,686][62408] Updated weights for policy 1, policy_version 4530 (0.0009) -[2023-10-17 00:26:48,991][62373] Updated weights for policy 0, policy_version 4560 (0.0010) -[2023-10-17 00:26:49,042][62408] Updated weights for policy 1, policy_version 4540 (0.0010) -[2023-10-17 00:26:49,360][62373] Updated weights for policy 0, policy_version 4570 (0.0008) -[2023-10-17 00:26:52,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 9338880. Throughput: 0: 1769.6, 1: 1740.1. Samples: 2341114. Policy #0 lag: (min: 31.0, avg: 34.2, max: 63.0) -[2023-10-17 00:26:52,215][61453] Avg episode reward: [(0, '3.160'), (1, '3.360')] -[2023-10-17 00:26:53,055][62408] Updated weights for policy 1, policy_version 4550 (0.0009) -[2023-10-17 00:26:53,151][62373] Updated weights for policy 0, policy_version 4580 (0.0009) -[2023-10-17 00:26:53,418][62408] Updated weights for policy 1, policy_version 4560 (0.0007) -[2023-10-17 00:26:53,529][62373] Updated weights for policy 0, policy_version 4590 (0.0010) -[2023-10-17 00:26:53,795][62408] Updated weights for policy 1, policy_version 4570 (0.0010) -[2023-10-17 00:26:53,904][62373] Updated weights for policy 0, policy_version 4600 (0.0008) -[2023-10-17 00:26:57,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 9404416. Throughput: 0: 1769.0, 1: 1743.9. Samples: 2363004. Policy #0 lag: (min: 10.0, avg: 18.2, max: 42.0) -[2023-10-17 00:26:57,214][61453] Avg episode reward: [(0, '3.360'), (1, '3.150')] -[2023-10-17 00:26:57,657][62408] Updated weights for policy 1, policy_version 4580 (0.0009) -[2023-10-17 00:26:57,728][62373] Updated weights for policy 0, policy_version 4610 (0.0009) -[2023-10-17 00:26:58,031][62408] Updated weights for policy 1, policy_version 4590 (0.0007) -[2023-10-17 00:26:58,101][62373] Updated weights for policy 0, policy_version 4620 (0.0008) -[2023-10-17 00:26:58,401][62408] Updated weights for policy 1, policy_version 4600 (0.0008) -[2023-10-17 00:26:58,468][62373] Updated weights for policy 0, policy_version 4630 (0.0008) -[2023-10-17 00:26:58,836][62373] Updated weights for policy 0, policy_version 4640 (0.0009) -[2023-10-17 00:27:02,163][62408] Updated weights for policy 1, policy_version 4610 (0.0008) -[2023-10-17 00:27:02,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 9469952. Throughput: 0: 1795.2, 1: 1772.9. Samples: 2385336. Policy #0 lag: (min: 10.0, avg: 18.2, max: 42.0) -[2023-10-17 00:27:02,215][61453] Avg episode reward: [(0, '3.300'), (1, '3.010')] -[2023-10-17 00:27:02,466][62373] Updated weights for policy 0, policy_version 4650 (0.0007) -[2023-10-17 00:27:02,538][62408] Updated weights for policy 1, policy_version 4620 (0.0007) -[2023-10-17 00:27:02,839][62373] Updated weights for policy 0, policy_version 4660 (0.0007) -[2023-10-17 00:27:02,899][62408] Updated weights for policy 1, policy_version 4630 (0.0008) -[2023-10-17 00:27:03,200][62373] Updated weights for policy 0, policy_version 4670 (0.0007) -[2023-10-17 00:27:03,271][62408] Updated weights for policy 1, policy_version 4640 (0.0008) -[2023-10-17 00:27:06,990][62373] Updated weights for policy 0, policy_version 4680 (0.0009) -[2023-10-17 00:27:07,029][62408] Updated weights for policy 1, policy_version 4650 (0.0009) -[2023-10-17 00:27:07,214][61453] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 9535488. Throughput: 0: 1774.3, 1: 1741.7. Samples: 2395076. Policy #0 lag: (min: 31.0, avg: 43.4, max: 63.0) -[2023-10-17 00:27:07,214][61453] Avg episode reward: [(0, '3.260'), (1, '2.900')] -[2023-10-17 00:27:07,361][62373] Updated weights for policy 0, policy_version 4690 (0.0007) -[2023-10-17 00:27:07,388][62408] Updated weights for policy 1, policy_version 4660 (0.0008) -[2023-10-17 00:27:07,741][62373] Updated weights for policy 0, policy_version 4700 (0.0009) -[2023-10-17 00:27:07,765][62408] Updated weights for policy 1, policy_version 4670 (0.0007) -[2023-10-17 00:27:11,640][62408] Updated weights for policy 1, policy_version 4680 (0.0007) -[2023-10-17 00:27:11,691][62373] Updated weights for policy 0, policy_version 4710 (0.0008) -[2023-10-17 00:27:12,016][62408] Updated weights for policy 1, policy_version 4690 (0.0007) -[2023-10-17 00:27:12,061][62373] Updated weights for policy 0, policy_version 4720 (0.0008) -[2023-10-17 00:27:12,214][61453] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 9601024. Throughput: 0: 1785.6, 1: 1772.0. Samples: 2416740. Policy #0 lag: (min: 31.0, avg: 43.4, max: 63.0) -[2023-10-17 00:27:12,215][61453] Avg episode reward: [(0, '3.220'), (1, '2.880')] -[2023-10-17 00:27:12,376][62408] Updated weights for policy 1, policy_version 4700 (0.0007) -[2023-10-17 00:27:12,428][62373] Updated weights for policy 0, policy_version 4730 (0.0007) -[2023-10-17 00:27:16,081][62373] Updated weights for policy 0, policy_version 4740 (0.0009) -[2023-10-17 00:27:16,346][62408] Updated weights for policy 1, policy_version 4710 (0.0009) -[2023-10-17 00:27:16,459][62373] Updated weights for policy 0, policy_version 4750 (0.0009) -[2023-10-17 00:27:16,707][62408] Updated weights for policy 1, policy_version 4720 (0.0008) -[2023-10-17 00:27:16,823][62373] Updated weights for policy 0, policy_version 4760 (0.0010) -[2023-10-17 00:27:17,074][62408] Updated weights for policy 1, policy_version 4730 (0.0008) -[2023-10-17 00:27:17,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 9699328. Throughput: 0: 1785.7, 1: 1744.6. Samples: 2436732. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:27:17,215][61453] Avg episode reward: [(0, '3.320'), (1, '3.130')] -[2023-10-17 00:27:20,528][62373] Updated weights for policy 0, policy_version 4770 (0.0007) -[2023-10-17 00:27:20,891][62373] Updated weights for policy 0, policy_version 4780 (0.0010) -[2023-10-17 00:27:20,913][62408] Updated weights for policy 1, policy_version 4740 (0.0008) -[2023-10-17 00:27:21,268][62373] Updated weights for policy 0, policy_version 4790 (0.0009) -[2023-10-17 00:27:21,276][62408] Updated weights for policy 1, policy_version 4750 (0.0008) -[2023-10-17 00:27:21,626][62373] Updated weights for policy 0, policy_version 4800 (0.0007) -[2023-10-17 00:27:21,643][62408] Updated weights for policy 1, policy_version 4760 (0.0008) -[2023-10-17 00:27:22,214][61453] Fps is (10 sec: 19661.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 9797632. Throughput: 0: 1786.0, 1: 1758.3. Samples: 2448436. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-17 00:27:22,214][61453] Avg episode reward: [(0, '2.970'), (1, '3.290')] -[2023-10-17 00:27:25,522][62408] Updated weights for policy 1, policy_version 4770 (0.0009) -[2023-10-17 00:27:25,612][62373] Updated weights for policy 0, policy_version 4810 (0.0008) -[2023-10-17 00:27:25,888][62408] Updated weights for policy 1, policy_version 4780 (0.0008) -[2023-10-17 00:27:25,989][62373] Updated weights for policy 0, policy_version 4820 (0.0007) -[2023-10-17 00:27:26,261][62408] Updated weights for policy 1, policy_version 4790 (0.0008) -[2023-10-17 00:27:26,361][62373] Updated weights for policy 0, policy_version 4830 (0.0008) -[2023-10-17 00:27:26,627][62408] Updated weights for policy 1, policy_version 4800 (0.0008) -[2023-10-17 00:27:27,214][61453] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 9863168. Throughput: 0: 1785.9, 1: 1756.9. Samples: 2468932. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-17 00:27:27,215][61453] Avg episode reward: [(0, '3.130'), (1, '3.390')] -[2023-10-17 00:27:27,216][62252] Saving new best policy, reward=3.390! -[2023-10-17 00:27:29,997][62373] Updated weights for policy 0, policy_version 4840 (0.0007) -[2023-10-17 00:27:30,370][62373] Updated weights for policy 0, policy_version 4850 (0.0007) -[2023-10-17 00:27:30,376][62408] Updated weights for policy 1, policy_version 4810 (0.0009) -[2023-10-17 00:27:30,731][62373] Updated weights for policy 0, policy_version 4860 (0.0008) -[2023-10-17 00:27:30,749][62408] Updated weights for policy 1, policy_version 4820 (0.0010) -[2023-10-17 00:27:31,122][62408] Updated weights for policy 1, policy_version 4830 (0.0008) -[2023-10-17 00:27:32,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 9928704. Throughput: 0: 1770.8, 1: 1737.3. Samples: 2489518. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-17 00:27:32,214][61453] Avg episode reward: [(0, '2.960'), (1, '3.340')] -[2023-10-17 00:27:32,225][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000004864_4980736.pth... -[2023-10-17 00:27:32,225][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000004832_4947968.pth... -[2023-10-17 00:27:32,260][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000003200_3276800.pth -[2023-10-17 00:27:32,267][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000003168_3244032.pth -[2023-10-17 00:27:34,586][62373] Updated weights for policy 0, policy_version 4870 (0.0008) -[2023-10-17 00:27:34,960][62373] Updated weights for policy 0, policy_version 4880 (0.0008) -[2023-10-17 00:27:34,971][62408] Updated weights for policy 1, policy_version 4840 (0.0008) -[2023-10-17 00:27:35,330][62373] Updated weights for policy 0, policy_version 4890 (0.0007) -[2023-10-17 00:27:35,334][62408] Updated weights for policy 1, policy_version 4850 (0.0008) -[2023-10-17 00:27:35,698][62408] Updated weights for policy 1, policy_version 4860 (0.0009) -[2023-10-17 00:27:37,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 9994240. Throughput: 0: 1786.9, 1: 1766.0. Samples: 2500998. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-17 00:27:37,215][61453] Avg episode reward: [(0, '3.000'), (1, '3.380')] -[2023-10-17 00:27:39,225][62373] Updated weights for policy 0, policy_version 4900 (0.0007) -[2023-10-17 00:27:39,385][62408] Updated weights for policy 1, policy_version 4870 (0.0009) -[2023-10-17 00:27:39,590][62373] Updated weights for policy 0, policy_version 4910 (0.0008) -[2023-10-17 00:27:39,750][62408] Updated weights for policy 1, policy_version 4880 (0.0007) -[2023-10-17 00:27:39,957][62373] Updated weights for policy 0, policy_version 4920 (0.0007) -[2023-10-17 00:27:40,121][62408] Updated weights for policy 1, policy_version 4890 (0.0008) -[2023-10-17 00:27:42,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 10059776. Throughput: 0: 1766.3, 1: 1745.2. Samples: 2521018. Policy #0 lag: (min: 31.0, avg: 42.5, max: 63.0) -[2023-10-17 00:27:42,214][61453] Avg episode reward: [(0, '3.100'), (1, '3.300')] -[2023-10-17 00:27:43,941][62373] Updated weights for policy 0, policy_version 4930 (0.0007) -[2023-10-17 00:27:44,091][62408] Updated weights for policy 1, policy_version 4900 (0.0009) -[2023-10-17 00:27:44,312][62373] Updated weights for policy 0, policy_version 4940 (0.0008) -[2023-10-17 00:27:44,460][62408] Updated weights for policy 1, policy_version 4910 (0.0008) -[2023-10-17 00:27:44,684][62373] Updated weights for policy 0, policy_version 4950 (0.0008) -[2023-10-17 00:27:44,830][62408] Updated weights for policy 1, policy_version 4920 (0.0008) -[2023-10-17 00:27:45,044][62373] Updated weights for policy 0, policy_version 4960 (0.0009) -[2023-10-17 00:27:47,214][61453] Fps is (10 sec: 13106.6, 60 sec: 14199.3, 300 sec: 14106.9). Total num frames: 10125312. Throughput: 0: 1758.1, 1: 1747.0. Samples: 2543066. Policy #0 lag: (min: 31.0, avg: 42.5, max: 63.0) -[2023-10-17 00:27:47,216][61453] Avg episode reward: [(0, '2.970'), (1, '3.410')] -[2023-10-17 00:27:47,227][62252] Saving new best policy, reward=3.410! -[2023-10-17 00:27:48,669][62408] Updated weights for policy 1, policy_version 4930 (0.0008) -[2023-10-17 00:27:48,875][62373] Updated weights for policy 0, policy_version 4970 (0.0007) -[2023-10-17 00:27:49,036][62408] Updated weights for policy 1, policy_version 4940 (0.0010) -[2023-10-17 00:27:49,238][62373] Updated weights for policy 0, policy_version 4980 (0.0010) -[2023-10-17 00:27:49,420][62408] Updated weights for policy 1, policy_version 4950 (0.0008) -[2023-10-17 00:27:49,610][62373] Updated weights for policy 0, policy_version 4990 (0.0008) -[2023-10-17 00:27:49,777][62408] Updated weights for policy 1, policy_version 4960 (0.0008) -[2023-10-17 00:27:52,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 10190848. Throughput: 0: 1755.4, 1: 1748.3. Samples: 2552744. Policy #0 lag: (min: 8.0, avg: 36.8, max: 40.0) -[2023-10-17 00:27:52,215][61453] Avg episode reward: [(0, '3.220'), (1, '3.610')] -[2023-10-17 00:27:52,216][62252] Saving new best policy, reward=3.610! -[2023-10-17 00:27:53,428][62373] Updated weights for policy 0, policy_version 5000 (0.0008) -[2023-10-17 00:27:53,619][62408] Updated weights for policy 1, policy_version 4970 (0.0008) -[2023-10-17 00:27:53,807][62373] Updated weights for policy 0, policy_version 5010 (0.0009) -[2023-10-17 00:27:53,989][62408] Updated weights for policy 1, policy_version 4980 (0.0008) -[2023-10-17 00:27:54,182][62373] Updated weights for policy 0, policy_version 5020 (0.0008) -[2023-10-17 00:27:54,361][62408] Updated weights for policy 1, policy_version 4990 (0.0009) -[2023-10-17 00:27:57,214][61453] Fps is (10 sec: 13107.6, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 10256384. Throughput: 0: 1757.6, 1: 1752.4. Samples: 2574690. Policy #0 lag: (min: 8.0, avg: 36.8, max: 40.0) -[2023-10-17 00:27:57,215][61453] Avg episode reward: [(0, '3.540'), (1, '3.440')] -[2023-10-17 00:27:57,216][62094] Saving new best policy, reward=3.540! -[2023-10-17 00:27:58,075][62373] Updated weights for policy 0, policy_version 5030 (0.0009) -[2023-10-17 00:27:58,203][62408] Updated weights for policy 1, policy_version 5000 (0.0007) -[2023-10-17 00:27:58,436][62373] Updated weights for policy 0, policy_version 5040 (0.0007) -[2023-10-17 00:27:58,573][62408] Updated weights for policy 1, policy_version 5010 (0.0007) -[2023-10-17 00:27:58,802][62373] Updated weights for policy 0, policy_version 5050 (0.0008) -[2023-10-17 00:27:58,939][62408] Updated weights for policy 1, policy_version 5020 (0.0008) -[2023-10-17 00:28:02,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 10321920. Throughput: 0: 1775.4, 1: 1781.6. Samples: 2596800. Policy #0 lag: (min: 27.0, avg: 27.1, max: 34.0) -[2023-10-17 00:28:02,215][61453] Avg episode reward: [(0, '3.420'), (1, '3.380')] -[2023-10-17 00:28:02,632][62373] Updated weights for policy 0, policy_version 5060 (0.0008) -[2023-10-17 00:28:02,670][62408] Updated weights for policy 1, policy_version 5030 (0.0008) -[2023-10-17 00:28:02,994][62373] Updated weights for policy 0, policy_version 5070 (0.0007) -[2023-10-17 00:28:03,039][62408] Updated weights for policy 1, policy_version 5040 (0.0008) -[2023-10-17 00:28:03,364][62373] Updated weights for policy 0, policy_version 5080 (0.0007) -[2023-10-17 00:28:03,417][62408] Updated weights for policy 1, policy_version 5050 (0.0009) -[2023-10-17 00:28:07,079][62373] Updated weights for policy 0, policy_version 5090 (0.0007) -[2023-10-17 00:28:07,214][62408] Updated weights for policy 1, policy_version 5060 (0.0007) -[2023-10-17 00:28:07,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 10387456. Throughput: 0: 1752.1, 1: 1765.3. Samples: 2606722. Policy #0 lag: (min: 27.0, avg: 27.1, max: 34.0) -[2023-10-17 00:28:07,214][61453] Avg episode reward: [(0, '3.440'), (1, '3.280')] -[2023-10-17 00:28:07,450][62373] Updated weights for policy 0, policy_version 5100 (0.0009) -[2023-10-17 00:28:07,580][62408] Updated weights for policy 1, policy_version 5070 (0.0007) -[2023-10-17 00:28:07,818][62373] Updated weights for policy 0, policy_version 5110 (0.0007) -[2023-10-17 00:28:07,954][62408] Updated weights for policy 1, policy_version 5080 (0.0007) -[2023-10-17 00:28:08,192][62373] Updated weights for policy 0, policy_version 5120 (0.0007) -[2023-10-17 00:28:11,737][62408] Updated weights for policy 1, policy_version 5090 (0.0007) -[2023-10-17 00:28:12,074][62373] Updated weights for policy 0, policy_version 5130 (0.0009) -[2023-10-17 00:28:12,105][62408] Updated weights for policy 1, policy_version 5100 (0.0008) -[2023-10-17 00:28:12,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 10452992. Throughput: 0: 1775.9, 1: 1777.7. Samples: 2628842. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:28:12,214][61453] Avg episode reward: [(0, '3.770'), (1, '3.290')] -[2023-10-17 00:28:12,436][62373] Updated weights for policy 0, policy_version 5140 (0.0008) -[2023-10-17 00:28:12,470][62408] Updated weights for policy 1, policy_version 5110 (0.0008) -[2023-10-17 00:28:12,801][62373] Updated weights for policy 0, policy_version 5150 (0.0008) -[2023-10-17 00:28:12,837][62408] Updated weights for policy 1, policy_version 5120 (0.0008) -[2023-10-17 00:28:12,871][62094] Saving new best policy, reward=3.770! -[2023-10-17 00:28:16,579][62373] Updated weights for policy 0, policy_version 5160 (0.0007) -[2023-10-17 00:28:16,760][62408] Updated weights for policy 1, policy_version 5130 (0.0007) -[2023-10-17 00:28:16,950][62373] Updated weights for policy 0, policy_version 5170 (0.0007) -[2023-10-17 00:28:17,129][62408] Updated weights for policy 1, policy_version 5140 (0.0009) -[2023-10-17 00:28:17,214][61453] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 13995.8). Total num frames: 10518528. Throughput: 0: 1768.9, 1: 1784.8. Samples: 2649436. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:28:17,215][61453] Avg episode reward: [(0, '3.860'), (1, '3.550')] -[2023-10-17 00:28:17,311][62373] Updated weights for policy 0, policy_version 5180 (0.0009) -[2023-10-17 00:28:17,460][62094] Saving new best policy, reward=3.860! -[2023-10-17 00:28:17,505][62408] Updated weights for policy 1, policy_version 5150 (0.0009) -[2023-10-17 00:28:21,076][62408] Updated weights for policy 1, policy_version 5160 (0.0008) -[2023-10-17 00:28:21,099][62373] Updated weights for policy 0, policy_version 5190 (0.0009) -[2023-10-17 00:28:21,449][62408] Updated weights for policy 1, policy_version 5170 (0.0010) -[2023-10-17 00:28:21,463][62373] Updated weights for policy 0, policy_version 5200 (0.0008) -[2023-10-17 00:28:21,811][62408] Updated weights for policy 1, policy_version 5180 (0.0007) -[2023-10-17 00:28:21,844][62373] Updated weights for policy 0, policy_version 5210 (0.0010) -[2023-10-17 00:28:22,214][61453] Fps is (10 sec: 19660.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 10649600. Throughput: 0: 1767.4, 1: 1781.2. Samples: 2660686. Policy #0 lag: (min: 26.0, avg: 26.0, max: 26.0) -[2023-10-17 00:28:22,215][61453] Avg episode reward: [(0, '3.450'), (1, '3.600')] -[2023-10-17 00:28:25,516][62408] Updated weights for policy 1, policy_version 5190 (0.0008) -[2023-10-17 00:28:25,699][62373] Updated weights for policy 0, policy_version 5220 (0.0009) -[2023-10-17 00:28:25,883][62408] Updated weights for policy 1, policy_version 5200 (0.0008) -[2023-10-17 00:28:26,068][62373] Updated weights for policy 0, policy_version 5230 (0.0009) -[2023-10-17 00:28:26,257][62408] Updated weights for policy 1, policy_version 5210 (0.0007) -[2023-10-17 00:28:26,427][62373] Updated weights for policy 0, policy_version 5240 (0.0008) -[2023-10-17 00:28:27,214][61453] Fps is (10 sec: 19661.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 10715136. Throughput: 0: 1776.0, 1: 1794.8. Samples: 2681706. Policy #0 lag: (min: 1.0, avg: 7.2, max: 33.0) -[2023-10-17 00:28:27,215][61453] Avg episode reward: [(0, '3.120'), (1, '3.550')] -[2023-10-17 00:28:30,073][62408] Updated weights for policy 1, policy_version 5220 (0.0008) -[2023-10-17 00:28:30,249][62373] Updated weights for policy 0, policy_version 5250 (0.0009) -[2023-10-17 00:28:30,431][62408] Updated weights for policy 1, policy_version 5230 (0.0008) -[2023-10-17 00:28:30,626][62373] Updated weights for policy 0, policy_version 5260 (0.0008) -[2023-10-17 00:28:30,801][62408] Updated weights for policy 1, policy_version 5240 (0.0008) -[2023-10-17 00:28:31,000][62373] Updated weights for policy 0, policy_version 5270 (0.0009) -[2023-10-17 00:28:31,366][62373] Updated weights for policy 0, policy_version 5280 (0.0009) -[2023-10-17 00:28:32,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 10780672. Throughput: 0: 1761.1, 1: 1773.8. Samples: 2702136. Policy #0 lag: (min: 1.0, avg: 7.2, max: 33.0) -[2023-10-17 00:28:32,214][61453] Avg episode reward: [(0, '3.080'), (1, '3.680')] -[2023-10-17 00:28:32,225][62252] Saving new best policy, reward=3.680! -[2023-10-17 00:28:34,650][62408] Updated weights for policy 1, policy_version 5250 (0.0008) -[2023-10-17 00:28:35,024][62408] Updated weights for policy 1, policy_version 5260 (0.0007) -[2023-10-17 00:28:35,043][62373] Updated weights for policy 0, policy_version 5290 (0.0008) -[2023-10-17 00:28:35,387][62408] Updated weights for policy 1, policy_version 5270 (0.0008) -[2023-10-17 00:28:35,398][62373] Updated weights for policy 0, policy_version 5300 (0.0009) -[2023-10-17 00:28:35,751][62408] Updated weights for policy 1, policy_version 5280 (0.0008) -[2023-10-17 00:28:35,775][62373] Updated weights for policy 0, policy_version 5310 (0.0008) -[2023-10-17 00:28:37,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 10846208. Throughput: 0: 1788.5, 1: 1795.4. Samples: 2714020. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:28:37,214][61453] Avg episode reward: [(0, '3.120'), (1, '3.530')] -[2023-10-17 00:28:39,564][62408] Updated weights for policy 1, policy_version 5290 (0.0007) -[2023-10-17 00:28:39,680][62373] Updated weights for policy 0, policy_version 5320 (0.0008) -[2023-10-17 00:28:39,940][62408] Updated weights for policy 1, policy_version 5300 (0.0008) -[2023-10-17 00:28:40,056][62373] Updated weights for policy 0, policy_version 5330 (0.0008) -[2023-10-17 00:28:40,300][62408] Updated weights for policy 1, policy_version 5310 (0.0007) -[2023-10-17 00:28:40,422][62373] Updated weights for policy 0, policy_version 5340 (0.0010) -[2023-10-17 00:28:42,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 10911744. Throughput: 0: 1761.1, 1: 1772.9. Samples: 2733718. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:28:42,215][61453] Avg episode reward: [(0, '3.290'), (1, '3.440')] -[2023-10-17 00:28:44,257][62408] Updated weights for policy 1, policy_version 5320 (0.0008) -[2023-10-17 00:28:44,263][62373] Updated weights for policy 0, policy_version 5350 (0.0008) -[2023-10-17 00:28:44,613][62408] Updated weights for policy 1, policy_version 5330 (0.0008) -[2023-10-17 00:28:44,623][62373] Updated weights for policy 0, policy_version 5360 (0.0007) -[2023-10-17 00:28:44,978][62408] Updated weights for policy 1, policy_version 5340 (0.0007) -[2023-10-17 00:28:44,999][62373] Updated weights for policy 0, policy_version 5370 (0.0009) -[2023-10-17 00:28:47,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.6, 300 sec: 14218.0). Total num frames: 10977280. Throughput: 0: 1763.2, 1: 1763.9. Samples: 2755518. Policy #0 lag: (min: 4.0, avg: 9.8, max: 36.0) -[2023-10-17 00:28:47,214][61453] Avg episode reward: [(0, '3.540'), (1, '3.610')] -[2023-10-17 00:28:48,805][62373] Updated weights for policy 0, policy_version 5380 (0.0008) -[2023-10-17 00:28:48,921][62408] Updated weights for policy 1, policy_version 5350 (0.0008) -[2023-10-17 00:28:49,175][62373] Updated weights for policy 0, policy_version 5390 (0.0008) -[2023-10-17 00:28:49,288][62408] Updated weights for policy 1, policy_version 5360 (0.0008) -[2023-10-17 00:28:49,555][62373] Updated weights for policy 0, policy_version 5400 (0.0008) -[2023-10-17 00:28:49,661][62408] Updated weights for policy 1, policy_version 5370 (0.0008) -[2023-10-17 00:28:52,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 11042816. Throughput: 0: 1757.1, 1: 1762.5. Samples: 2765102. Policy #0 lag: (min: 4.0, avg: 9.8, max: 36.0) -[2023-10-17 00:28:52,214][61453] Avg episode reward: [(0, '3.430'), (1, '3.310')] -[2023-10-17 00:28:53,345][62373] Updated weights for policy 0, policy_version 5410 (0.0010) -[2023-10-17 00:28:53,564][62408] Updated weights for policy 1, policy_version 5380 (0.0007) -[2023-10-17 00:28:53,712][62373] Updated weights for policy 0, policy_version 5420 (0.0008) -[2023-10-17 00:28:53,925][62408] Updated weights for policy 1, policy_version 5390 (0.0007) -[2023-10-17 00:28:54,087][62373] Updated weights for policy 0, policy_version 5430 (0.0010) -[2023-10-17 00:28:54,294][62408] Updated weights for policy 1, policy_version 5400 (0.0008) -[2023-10-17 00:28:54,449][62373] Updated weights for policy 0, policy_version 5440 (0.0007) -[2023-10-17 00:28:57,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 11108352. Throughput: 0: 1755.8, 1: 1755.5. Samples: 2786850. Policy #0 lag: (min: 2.0, avg: 5.5, max: 34.0) -[2023-10-17 00:28:57,216][61453] Avg episode reward: [(0, '3.680'), (1, '3.170')] -[2023-10-17 00:28:58,193][62408] Updated weights for policy 1, policy_version 5410 (0.0009) -[2023-10-17 00:28:58,522][62373] Updated weights for policy 0, policy_version 5450 (0.0008) -[2023-10-17 00:28:58,566][62408] Updated weights for policy 1, policy_version 5420 (0.0007) -[2023-10-17 00:28:58,888][62373] Updated weights for policy 0, policy_version 5460 (0.0009) -[2023-10-17 00:28:58,934][62408] Updated weights for policy 1, policy_version 5430 (0.0008) -[2023-10-17 00:28:59,261][62373] Updated weights for policy 0, policy_version 5470 (0.0008) -[2023-10-17 00:28:59,293][62408] Updated weights for policy 1, policy_version 5440 (0.0008) -[2023-10-17 00:29:02,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 11173888. Throughput: 0: 1767.3, 1: 1772.6. Samples: 2808734. Policy #0 lag: (min: 2.0, avg: 5.5, max: 34.0) -[2023-10-17 00:29:02,215][61453] Avg episode reward: [(0, '3.670'), (1, '3.280')] -[2023-10-17 00:29:02,961][62408] Updated weights for policy 1, policy_version 5450 (0.0009) -[2023-10-17 00:29:03,023][62373] Updated weights for policy 0, policy_version 5480 (0.0009) -[2023-10-17 00:29:03,331][62408] Updated weights for policy 1, policy_version 5460 (0.0008) -[2023-10-17 00:29:03,402][62373] Updated weights for policy 0, policy_version 5490 (0.0008) -[2023-10-17 00:29:03,699][62408] Updated weights for policy 1, policy_version 5470 (0.0007) -[2023-10-17 00:29:03,770][62373] Updated weights for policy 0, policy_version 5500 (0.0009) -[2023-10-17 00:29:07,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 11239424. Throughput: 0: 1753.0, 1: 1753.2. Samples: 2818462. Policy #0 lag: (min: 17.0, avg: 26.8, max: 49.0) -[2023-10-17 00:29:07,215][61453] Avg episode reward: [(0, '3.610'), (1, '3.490')] -[2023-10-17 00:29:07,552][62408] Updated weights for policy 1, policy_version 5480 (0.0007) -[2023-10-17 00:29:07,665][62373] Updated weights for policy 0, policy_version 5510 (0.0008) -[2023-10-17 00:29:07,931][62408] Updated weights for policy 1, policy_version 5490 (0.0007) -[2023-10-17 00:29:08,038][62373] Updated weights for policy 0, policy_version 5520 (0.0009) -[2023-10-17 00:29:08,296][62408] Updated weights for policy 1, policy_version 5500 (0.0008) -[2023-10-17 00:29:08,414][62373] Updated weights for policy 0, policy_version 5530 (0.0007) -[2023-10-17 00:29:12,070][62408] Updated weights for policy 1, policy_version 5510 (0.0007) -[2023-10-17 00:29:12,148][62373] Updated weights for policy 0, policy_version 5540 (0.0011) -[2023-10-17 00:29:12,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 11304960. Throughput: 0: 1762.5, 1: 1761.1. Samples: 2840266. Policy #0 lag: (min: 17.0, avg: 26.8, max: 49.0) -[2023-10-17 00:29:12,215][61453] Avg episode reward: [(0, '3.610'), (1, '3.200')] -[2023-10-17 00:29:12,439][62408] Updated weights for policy 1, policy_version 5520 (0.0009) -[2023-10-17 00:29:12,517][62373] Updated weights for policy 0, policy_version 5550 (0.0009) -[2023-10-17 00:29:12,808][62408] Updated weights for policy 1, policy_version 5530 (0.0008) -[2023-10-17 00:29:12,882][62373] Updated weights for policy 0, policy_version 5560 (0.0008) -[2023-10-17 00:29:16,667][62408] Updated weights for policy 1, policy_version 5540 (0.0009) -[2023-10-17 00:29:16,710][62373] Updated weights for policy 0, policy_version 5570 (0.0008) -[2023-10-17 00:29:17,038][62408] Updated weights for policy 1, policy_version 5550 (0.0009) -[2023-10-17 00:29:17,081][62373] Updated weights for policy 0, policy_version 5580 (0.0009) -[2023-10-17 00:29:17,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.6, 300 sec: 13995.8). Total num frames: 11370496. Throughput: 0: 1770.7, 1: 1772.4. Samples: 2861576. Policy #0 lag: (min: 17.0, avg: 17.0, max: 17.0) -[2023-10-17 00:29:17,214][61453] Avg episode reward: [(0, '3.660'), (1, '3.190')] -[2023-10-17 00:29:17,395][62408] Updated weights for policy 1, policy_version 5560 (0.0007) -[2023-10-17 00:29:17,444][62373] Updated weights for policy 0, policy_version 5590 (0.0008) -[2023-10-17 00:29:17,816][62373] Updated weights for policy 0, policy_version 5600 (0.0007) -[2023-10-17 00:29:21,213][62408] Updated weights for policy 1, policy_version 5570 (0.0007) -[2023-10-17 00:29:21,588][62408] Updated weights for policy 1, policy_version 5580 (0.0009) -[2023-10-17 00:29:21,765][62373] Updated weights for policy 0, policy_version 5610 (0.0009) -[2023-10-17 00:29:21,949][62408] Updated weights for policy 1, policy_version 5590 (0.0007) -[2023-10-17 00:29:22,133][62373] Updated weights for policy 0, policy_version 5620 (0.0009) -[2023-10-17 00:29:22,214][61453] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13995.8). Total num frames: 11436032. Throughput: 0: 1751.2, 1: 1757.6. Samples: 2871912. Policy #0 lag: (min: 17.0, avg: 17.0, max: 17.0) -[2023-10-17 00:29:22,215][61453] Avg episode reward: [(0, '3.470'), (1, '2.890')] -[2023-10-17 00:29:22,319][62408] Updated weights for policy 1, policy_version 5600 (0.0009) -[2023-10-17 00:29:22,505][62373] Updated weights for policy 0, policy_version 5630 (0.0008) -[2023-10-17 00:29:26,214][62408] Updated weights for policy 1, policy_version 5610 (0.0010) -[2023-10-17 00:29:26,390][62373] Updated weights for policy 0, policy_version 5640 (0.0008) -[2023-10-17 00:29:26,584][62408] Updated weights for policy 1, policy_version 5620 (0.0007) -[2023-10-17 00:29:26,754][62373] Updated weights for policy 0, policy_version 5650 (0.0009) -[2023-10-17 00:29:26,956][62408] Updated weights for policy 1, policy_version 5630 (0.0010) -[2023-10-17 00:29:27,126][62373] Updated weights for policy 0, policy_version 5660 (0.0009) -[2023-10-17 00:29:27,214][61453] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 11534336. Throughput: 0: 1777.2, 1: 1776.3. Samples: 2893624. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-17 00:29:27,215][61453] Avg episode reward: [(0, '3.340'), (1, '2.740')] -[2023-10-17 00:29:30,725][62408] Updated weights for policy 1, policy_version 5640 (0.0008) -[2023-10-17 00:29:30,982][62373] Updated weights for policy 0, policy_version 5670 (0.0008) -[2023-10-17 00:29:31,086][62408] Updated weights for policy 1, policy_version 5650 (0.0009) -[2023-10-17 00:29:31,351][62373] Updated weights for policy 0, policy_version 5680 (0.0007) -[2023-10-17 00:29:31,454][62408] Updated weights for policy 1, policy_version 5660 (0.0009) -[2023-10-17 00:29:31,723][62373] Updated weights for policy 0, policy_version 5690 (0.0008) -[2023-10-17 00:29:32,214][61453] Fps is (10 sec: 19660.6, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 11632640. Throughput: 0: 1745.9, 1: 1748.4. Samples: 2912760. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-17 00:29:32,215][61453] Avg episode reward: [(0, '3.610'), (1, '3.190')] -[2023-10-17 00:29:32,225][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000005664_5799936.pth... -[2023-10-17 00:29:32,225][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000005696_5832704.pth... -[2023-10-17 00:29:32,255][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000004000_4096000.pth -[2023-10-17 00:29:32,266][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000004032_4128768.pth -[2023-10-17 00:29:35,245][62408] Updated weights for policy 1, policy_version 5670 (0.0009) -[2023-10-17 00:29:35,588][62373] Updated weights for policy 0, policy_version 5700 (0.0008) -[2023-10-17 00:29:35,610][62408] Updated weights for policy 1, policy_version 5680 (0.0009) -[2023-10-17 00:29:35,969][62373] Updated weights for policy 0, policy_version 5710 (0.0008) -[2023-10-17 00:29:35,993][62408] Updated weights for policy 1, policy_version 5690 (0.0008) -[2023-10-17 00:29:36,326][62373] Updated weights for policy 0, policy_version 5720 (0.0010) -[2023-10-17 00:29:37,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 11698176. Throughput: 0: 1772.4, 1: 1780.8. Samples: 2924996. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-17 00:29:37,215][61453] Avg episode reward: [(0, '3.630'), (1, '3.500')] -[2023-10-17 00:29:39,835][62408] Updated weights for policy 1, policy_version 5700 (0.0009) -[2023-10-17 00:29:40,100][62373] Updated weights for policy 0, policy_version 5730 (0.0010) -[2023-10-17 00:29:40,202][62408] Updated weights for policy 1, policy_version 5710 (0.0009) -[2023-10-17 00:29:40,473][62373] Updated weights for policy 0, policy_version 5740 (0.0010) -[2023-10-17 00:29:40,566][62408] Updated weights for policy 1, policy_version 5720 (0.0008) -[2023-10-17 00:29:40,837][62373] Updated weights for policy 0, policy_version 5750 (0.0010) -[2023-10-17 00:29:41,210][62373] Updated weights for policy 0, policy_version 5760 (0.0008) -[2023-10-17 00:29:42,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 11763712. Throughput: 0: 1754.3, 1: 1755.7. Samples: 2944798. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:29:42,215][61453] Avg episode reward: [(0, '3.900'), (1, '3.650')] -[2023-10-17 00:29:42,216][62094] Saving new best policy, reward=3.900! -[2023-10-17 00:29:44,593][62408] Updated weights for policy 1, policy_version 5730 (0.0008) -[2023-10-17 00:29:44,961][62408] Updated weights for policy 1, policy_version 5740 (0.0007) -[2023-10-17 00:29:45,211][62373] Updated weights for policy 0, policy_version 5770 (0.0008) -[2023-10-17 00:29:45,335][62408] Updated weights for policy 1, policy_version 5750 (0.0007) -[2023-10-17 00:29:45,582][62373] Updated weights for policy 0, policy_version 5780 (0.0008) -[2023-10-17 00:29:45,695][62408] Updated weights for policy 1, policy_version 5760 (0.0008) -[2023-10-17 00:29:45,946][62373] Updated weights for policy 0, policy_version 5790 (0.0007) -[2023-10-17 00:29:47,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 11829248. Throughput: 0: 1752.4, 1: 1746.9. Samples: 2966204. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:29:47,215][61453] Avg episode reward: [(0, '3.630'), (1, '3.720')] -[2023-10-17 00:29:47,227][62252] Saving new best policy, reward=3.720! -[2023-10-17 00:29:49,588][62408] Updated weights for policy 1, policy_version 5770 (0.0008) -[2023-10-17 00:29:49,723][62373] Updated weights for policy 0, policy_version 5800 (0.0008) -[2023-10-17 00:29:49,965][62408] Updated weights for policy 1, policy_version 5780 (0.0009) -[2023-10-17 00:29:50,094][62373] Updated weights for policy 0, policy_version 5810 (0.0007) -[2023-10-17 00:29:50,321][62408] Updated weights for policy 1, policy_version 5790 (0.0008) -[2023-10-17 00:29:50,466][62373] Updated weights for policy 0, policy_version 5820 (0.0008) -[2023-10-17 00:29:52,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 11894784. Throughput: 0: 1768.1, 1: 1759.6. Samples: 2977212. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:29:52,215][61453] Avg episode reward: [(0, '3.700'), (1, '3.920')] -[2023-10-17 00:29:52,216][62252] Saving new best policy, reward=3.920! -[2023-10-17 00:29:54,185][62373] Updated weights for policy 0, policy_version 5830 (0.0009) -[2023-10-17 00:29:54,232][62408] Updated weights for policy 1, policy_version 5800 (0.0007) -[2023-10-17 00:29:54,552][62373] Updated weights for policy 0, policy_version 5840 (0.0009) -[2023-10-17 00:29:54,595][62408] Updated weights for policy 1, policy_version 5810 (0.0007) -[2023-10-17 00:29:54,932][62373] Updated weights for policy 0, policy_version 5850 (0.0008) -[2023-10-17 00:29:54,967][62408] Updated weights for policy 1, policy_version 5820 (0.0007) -[2023-10-17 00:29:57,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 11960320. Throughput: 0: 1753.2, 1: 1740.5. Samples: 2997482. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:29:57,214][61453] Avg episode reward: [(0, '3.680'), (1, '3.720')] -[2023-10-17 00:29:58,825][62373] Updated weights for policy 0, policy_version 5860 (0.0011) -[2023-10-17 00:29:58,835][62408] Updated weights for policy 1, policy_version 5830 (0.0008) -[2023-10-17 00:29:59,193][62373] Updated weights for policy 0, policy_version 5870 (0.0009) -[2023-10-17 00:29:59,204][62408] Updated weights for policy 1, policy_version 5840 (0.0008) -[2023-10-17 00:29:59,559][62373] Updated weights for policy 0, policy_version 5880 (0.0010) -[2023-10-17 00:29:59,570][62408] Updated weights for policy 1, policy_version 5850 (0.0007) -[2023-10-17 00:30:02,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 12025856. Throughput: 0: 1765.2, 1: 1747.6. Samples: 3019652. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:30:02,214][61453] Avg episode reward: [(0, '3.510'), (1, '3.520')] -[2023-10-17 00:30:03,296][62373] Updated weights for policy 0, policy_version 5890 (0.0009) -[2023-10-17 00:30:03,334][62408] Updated weights for policy 1, policy_version 5860 (0.0007) -[2023-10-17 00:30:03,661][62373] Updated weights for policy 0, policy_version 5900 (0.0010) -[2023-10-17 00:30:03,699][62408] Updated weights for policy 1, policy_version 5870 (0.0008) -[2023-10-17 00:30:04,028][62373] Updated weights for policy 0, policy_version 5910 (0.0008) -[2023-10-17 00:30:04,077][62408] Updated weights for policy 1, policy_version 5880 (0.0009) -[2023-10-17 00:30:04,397][62373] Updated weights for policy 0, policy_version 5920 (0.0009) -[2023-10-17 00:30:07,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 12091392. Throughput: 0: 1757.6, 1: 1739.6. Samples: 3029290. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:30:07,214][61453] Avg episode reward: [(0, '3.330'), (1, '3.370')] -[2023-10-17 00:30:07,905][62408] Updated weights for policy 1, policy_version 5890 (0.0008) -[2023-10-17 00:30:08,229][62373] Updated weights for policy 0, policy_version 5930 (0.0007) -[2023-10-17 00:30:08,283][62408] Updated weights for policy 1, policy_version 5900 (0.0008) -[2023-10-17 00:30:08,607][62373] Updated weights for policy 0, policy_version 5940 (0.0009) -[2023-10-17 00:30:08,644][62408] Updated weights for policy 1, policy_version 5910 (0.0008) -[2023-10-17 00:30:08,978][62373] Updated weights for policy 0, policy_version 5950 (0.0008) -[2023-10-17 00:30:09,008][62408] Updated weights for policy 1, policy_version 5920 (0.0008) -[2023-10-17 00:30:12,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 12156928. Throughput: 0: 1762.7, 1: 1739.9. Samples: 3051244. Policy #0 lag: (min: 17.0, avg: 19.6, max: 39.0) -[2023-10-17 00:30:12,215][61453] Avg episode reward: [(0, '3.580'), (1, '3.630')] -[2023-10-17 00:30:12,783][62408] Updated weights for policy 1, policy_version 5930 (0.0008) -[2023-10-17 00:30:12,828][62373] Updated weights for policy 0, policy_version 5960 (0.0008) -[2023-10-17 00:30:13,143][62408] Updated weights for policy 1, policy_version 5940 (0.0007) -[2023-10-17 00:30:13,194][62373] Updated weights for policy 0, policy_version 5970 (0.0008) -[2023-10-17 00:30:13,519][62408] Updated weights for policy 1, policy_version 5950 (0.0008) -[2023-10-17 00:30:13,560][62373] Updated weights for policy 0, policy_version 5980 (0.0007) -[2023-10-17 00:30:17,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 12222464. Throughput: 0: 1796.5, 1: 1771.9. Samples: 3073340. Policy #0 lag: (min: 17.0, avg: 19.6, max: 39.0) -[2023-10-17 00:30:17,214][61453] Avg episode reward: [(0, '3.300'), (1, '3.500')] -[2023-10-17 00:30:17,279][62373] Updated weights for policy 0, policy_version 5990 (0.0008) -[2023-10-17 00:30:17,348][62408] Updated weights for policy 1, policy_version 5960 (0.0009) -[2023-10-17 00:30:17,644][62373] Updated weights for policy 0, policy_version 6000 (0.0008) -[2023-10-17 00:30:17,726][62408] Updated weights for policy 1, policy_version 5970 (0.0010) -[2023-10-17 00:30:18,009][62373] Updated weights for policy 0, policy_version 6010 (0.0007) -[2023-10-17 00:30:18,085][62408] Updated weights for policy 1, policy_version 5980 (0.0007) -[2023-10-17 00:30:21,916][62373] Updated weights for policy 0, policy_version 6020 (0.0008) -[2023-10-17 00:30:21,951][62408] Updated weights for policy 1, policy_version 5990 (0.0007) -[2023-10-17 00:30:22,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 12288000. Throughput: 0: 1765.9, 1: 1740.4. Samples: 3082778. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-17 00:30:22,214][61453] Avg episode reward: [(0, '3.440'), (1, '3.370')] -[2023-10-17 00:30:22,286][62373] Updated weights for policy 0, policy_version 6030 (0.0008) -[2023-10-17 00:30:22,309][62408] Updated weights for policy 1, policy_version 6000 (0.0008) -[2023-10-17 00:30:22,656][62373] Updated weights for policy 0, policy_version 6040 (0.0009) -[2023-10-17 00:30:22,682][62408] Updated weights for policy 1, policy_version 6010 (0.0008) -[2023-10-17 00:30:26,576][62373] Updated weights for policy 0, policy_version 6050 (0.0008) -[2023-10-17 00:30:26,584][62408] Updated weights for policy 1, policy_version 6020 (0.0009) -[2023-10-17 00:30:26,940][62373] Updated weights for policy 0, policy_version 6060 (0.0007) -[2023-10-17 00:30:26,954][62408] Updated weights for policy 1, policy_version 6030 (0.0008) -[2023-10-17 00:30:27,214][61453] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13995.8). Total num frames: 12353536. Throughput: 0: 1780.7, 1: 1772.7. Samples: 3104700. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-17 00:30:27,215][61453] Avg episode reward: [(0, '3.540'), (1, '3.420')] -[2023-10-17 00:30:27,304][62373] Updated weights for policy 0, policy_version 6070 (0.0007) -[2023-10-17 00:30:27,333][62408] Updated weights for policy 1, policy_version 6040 (0.0009) -[2023-10-17 00:30:27,684][62373] Updated weights for policy 0, policy_version 6080 (0.0009) -[2023-10-17 00:30:31,294][62408] Updated weights for policy 1, policy_version 6050 (0.0009) -[2023-10-17 00:30:31,578][62373] Updated weights for policy 0, policy_version 6090 (0.0009) -[2023-10-17 00:30:31,652][62408] Updated weights for policy 1, policy_version 6060 (0.0008) -[2023-10-17 00:30:31,946][62373] Updated weights for policy 0, policy_version 6100 (0.0010) -[2023-10-17 00:30:32,032][62408] Updated weights for policy 1, policy_version 6070 (0.0010) -[2023-10-17 00:30:32,214][61453] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13995.8). Total num frames: 12419072. Throughput: 0: 1768.6, 1: 1756.3. Samples: 3124824. Policy #0 lag: (min: 31.0, avg: 32.0, max: 53.0) -[2023-10-17 00:30:32,215][61453] Avg episode reward: [(0, '3.790'), (1, '3.420')] -[2023-10-17 00:30:32,307][62373] Updated weights for policy 0, policy_version 6110 (0.0008) -[2023-10-17 00:30:32,402][62408] Updated weights for policy 1, policy_version 6080 (0.0008) -[2023-10-17 00:30:35,942][62373] Updated weights for policy 0, policy_version 6120 (0.0008) -[2023-10-17 00:30:36,159][62408] Updated weights for policy 1, policy_version 6090 (0.0011) -[2023-10-17 00:30:36,316][62373] Updated weights for policy 0, policy_version 6130 (0.0009) -[2023-10-17 00:30:36,531][62408] Updated weights for policy 1, policy_version 6100 (0.0008) -[2023-10-17 00:30:36,693][62373] Updated weights for policy 0, policy_version 6140 (0.0008) -[2023-10-17 00:30:36,892][62408] Updated weights for policy 1, policy_version 6110 (0.0008) -[2023-10-17 00:30:37,214][61453] Fps is (10 sec: 19661.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 12550144. Throughput: 0: 1771.5, 1: 1756.3. Samples: 3135960. Policy #0 lag: (min: 10.0, avg: 10.3, max: 22.0) -[2023-10-17 00:30:37,214][61453] Avg episode reward: [(0, '3.800'), (1, '3.470')] -[2023-10-17 00:30:40,585][62373] Updated weights for policy 0, policy_version 6150 (0.0009) -[2023-10-17 00:30:40,880][62408] Updated weights for policy 1, policy_version 6120 (0.0008) -[2023-10-17 00:30:40,944][62373] Updated weights for policy 0, policy_version 6160 (0.0007) -[2023-10-17 00:30:41,250][62408] Updated weights for policy 1, policy_version 6130 (0.0007) -[2023-10-17 00:30:41,314][62373] Updated weights for policy 0, policy_version 6170 (0.0007) -[2023-10-17 00:30:41,617][62408] Updated weights for policy 1, policy_version 6140 (0.0007) -[2023-10-17 00:30:42,214][61453] Fps is (10 sec: 19660.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 12615680. Throughput: 0: 1773.0, 1: 1767.7. Samples: 3156814. Policy #0 lag: (min: 10.0, avg: 10.3, max: 22.0) -[2023-10-17 00:30:42,215][61453] Avg episode reward: [(0, '4.100'), (1, '3.530')] -[2023-10-17 00:30:42,216][62094] Saving new best policy, reward=4.100! -[2023-10-17 00:30:45,101][62373] Updated weights for policy 0, policy_version 6180 (0.0008) -[2023-10-17 00:30:45,463][62373] Updated weights for policy 0, policy_version 6190 (0.0007) -[2023-10-17 00:30:45,507][62408] Updated weights for policy 1, policy_version 6150 (0.0008) -[2023-10-17 00:30:45,830][62373] Updated weights for policy 0, policy_version 6200 (0.0007) -[2023-10-17 00:30:45,883][62408] Updated weights for policy 1, policy_version 6160 (0.0008) -[2023-10-17 00:30:46,247][62408] Updated weights for policy 1, policy_version 6170 (0.0009) -[2023-10-17 00:30:47,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 12681216. Throughput: 0: 1759.5, 1: 1741.5. Samples: 3177198. Policy #0 lag: (min: 30.0, avg: 30.9, max: 51.0) -[2023-10-17 00:30:47,215][61453] Avg episode reward: [(0, '3.870'), (1, '3.540')] -[2023-10-17 00:30:49,635][62373] Updated weights for policy 0, policy_version 6210 (0.0008) -[2023-10-17 00:30:50,000][62373] Updated weights for policy 0, policy_version 6220 (0.0009) -[2023-10-17 00:30:50,091][62408] Updated weights for policy 1, policy_version 6180 (0.0008) -[2023-10-17 00:30:50,370][62373] Updated weights for policy 0, policy_version 6230 (0.0008) -[2023-10-17 00:30:50,451][62408] Updated weights for policy 1, policy_version 6190 (0.0008) -[2023-10-17 00:30:50,741][62373] Updated weights for policy 0, policy_version 6240 (0.0007) -[2023-10-17 00:30:50,822][62408] Updated weights for policy 1, policy_version 6200 (0.0009) -[2023-10-17 00:30:52,214][61453] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 12746752. Throughput: 0: 1780.4, 1: 1771.7. Samples: 3189136. Policy #0 lag: (min: 30.0, avg: 30.9, max: 51.0) -[2023-10-17 00:30:52,214][61453] Avg episode reward: [(0, '4.150'), (1, '4.000')] -[2023-10-17 00:30:52,215][62094] Saving new best policy, reward=4.150! -[2023-10-17 00:30:52,215][62252] Saving new best policy, reward=4.000! -[2023-10-17 00:30:54,615][62373] Updated weights for policy 0, policy_version 6250 (0.0007) -[2023-10-17 00:30:54,627][62408] Updated weights for policy 1, policy_version 6210 (0.0009) -[2023-10-17 00:30:54,982][62373] Updated weights for policy 0, policy_version 6260 (0.0008) -[2023-10-17 00:30:55,001][62408] Updated weights for policy 1, policy_version 6220 (0.0009) -[2023-10-17 00:30:55,347][62373] Updated weights for policy 0, policy_version 6270 (0.0010) -[2023-10-17 00:30:55,356][62408] Updated weights for policy 1, policy_version 6230 (0.0009) -[2023-10-17 00:30:55,723][62408] Updated weights for policy 1, policy_version 6240 (0.0009) -[2023-10-17 00:30:57,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 12812288. Throughput: 0: 1753.9, 1: 1747.5. Samples: 3208808. Policy #0 lag: (min: 31.0, avg: 32.7, max: 60.0) -[2023-10-17 00:30:57,215][61453] Avg episode reward: [(0, '3.790'), (1, '3.900')] -[2023-10-17 00:30:59,157][62373] Updated weights for policy 0, policy_version 6280 (0.0008) -[2023-10-17 00:30:59,533][62373] Updated weights for policy 0, policy_version 6290 (0.0008) -[2023-10-17 00:30:59,671][62408] Updated weights for policy 1, policy_version 6250 (0.0008) -[2023-10-17 00:30:59,900][62373] Updated weights for policy 0, policy_version 6300 (0.0009) -[2023-10-17 00:31:00,048][62408] Updated weights for policy 1, policy_version 6260 (0.0008) -[2023-10-17 00:31:00,430][62408] Updated weights for policy 1, policy_version 6270 (0.0007) -[2023-10-17 00:31:02,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 12877824. Throughput: 0: 1749.0, 1: 1744.6. Samples: 3230552. Policy #0 lag: (min: 31.0, avg: 32.7, max: 60.0) -[2023-10-17 00:31:02,215][61453] Avg episode reward: [(0, '4.020'), (1, '3.670')] -[2023-10-17 00:31:03,751][62373] Updated weights for policy 0, policy_version 6310 (0.0008) -[2023-10-17 00:31:04,122][62373] Updated weights for policy 0, policy_version 6320 (0.0009) -[2023-10-17 00:31:04,334][62408] Updated weights for policy 1, policy_version 6280 (0.0009) -[2023-10-17 00:31:04,499][62373] Updated weights for policy 0, policy_version 6330 (0.0010) -[2023-10-17 00:31:04,700][62408] Updated weights for policy 1, policy_version 6290 (0.0007) -[2023-10-17 00:31:05,070][62408] Updated weights for policy 1, policy_version 6300 (0.0008) -[2023-10-17 00:31:07,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 12943360. Throughput: 0: 1755.3, 1: 1755.4. Samples: 3240762. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) -[2023-10-17 00:31:07,215][61453] Avg episode reward: [(0, '3.590'), (1, '3.840')] -[2023-10-17 00:31:08,260][62373] Updated weights for policy 0, policy_version 6340 (0.0008) -[2023-10-17 00:31:08,633][62373] Updated weights for policy 0, policy_version 6350 (0.0008) -[2023-10-17 00:31:08,917][62408] Updated weights for policy 1, policy_version 6310 (0.0008) -[2023-10-17 00:31:09,009][62373] Updated weights for policy 0, policy_version 6360 (0.0008) -[2023-10-17 00:31:09,292][62408] Updated weights for policy 1, policy_version 6320 (0.0009) -[2023-10-17 00:31:09,658][62408] Updated weights for policy 1, policy_version 6330 (0.0008) -[2023-10-17 00:31:12,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 13008896. Throughput: 0: 1761.2, 1: 1739.8. Samples: 3262248. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) -[2023-10-17 00:31:12,215][61453] Avg episode reward: [(0, '3.910'), (1, '3.600')] -[2023-10-17 00:31:12,705][62373] Updated weights for policy 0, policy_version 6370 (0.0009) -[2023-10-17 00:31:13,084][62373] Updated weights for policy 0, policy_version 6380 (0.0009) -[2023-10-17 00:31:13,405][62408] Updated weights for policy 1, policy_version 6340 (0.0009) -[2023-10-17 00:31:13,464][62373] Updated weights for policy 0, policy_version 6390 (0.0009) -[2023-10-17 00:31:13,773][62408] Updated weights for policy 1, policy_version 6350 (0.0007) -[2023-10-17 00:31:13,838][62373] Updated weights for policy 0, policy_version 6400 (0.0008) -[2023-10-17 00:31:14,142][62408] Updated weights for policy 1, policy_version 6360 (0.0009) -[2023-10-17 00:31:17,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 13074432. Throughput: 0: 1784.9, 1: 1760.7. Samples: 3284374. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-10-17 00:31:17,216][61453] Avg episode reward: [(0, '3.800'), (1, '3.980')] -[2023-10-17 00:31:17,801][62373] Updated weights for policy 0, policy_version 6410 (0.0009) -[2023-10-17 00:31:18,035][62408] Updated weights for policy 1, policy_version 6370 (0.0009) -[2023-10-17 00:31:18,164][62373] Updated weights for policy 0, policy_version 6420 (0.0009) -[2023-10-17 00:31:18,402][62408] Updated weights for policy 1, policy_version 6380 (0.0008) -[2023-10-17 00:31:18,544][62373] Updated weights for policy 0, policy_version 6430 (0.0007) -[2023-10-17 00:31:18,769][62408] Updated weights for policy 1, policy_version 6390 (0.0008) -[2023-10-17 00:31:19,145][62408] Updated weights for policy 1, policy_version 6400 (0.0008) -[2023-10-17 00:31:22,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 13139968. Throughput: 0: 1762.4, 1: 1748.0. Samples: 3293928. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-10-17 00:31:22,215][61453] Avg episode reward: [(0, '3.850'), (1, '3.920')] -[2023-10-17 00:31:22,241][62373] Updated weights for policy 0, policy_version 6440 (0.0008) -[2023-10-17 00:31:22,610][62373] Updated weights for policy 0, policy_version 6450 (0.0008) -[2023-10-17 00:31:22,843][62408] Updated weights for policy 1, policy_version 6410 (0.0009) -[2023-10-17 00:31:22,980][62373] Updated weights for policy 0, policy_version 6460 (0.0009) -[2023-10-17 00:31:23,209][62408] Updated weights for policy 1, policy_version 6420 (0.0009) -[2023-10-17 00:31:23,586][62408] Updated weights for policy 1, policy_version 6430 (0.0007) -[2023-10-17 00:31:26,866][62373] Updated weights for policy 0, policy_version 6470 (0.0010) -[2023-10-17 00:31:27,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 13205504. Throughput: 0: 1780.1, 1: 1756.7. Samples: 3315970. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:31:27,215][61453] Avg episode reward: [(0, '3.710'), (1, '4.070')] -[2023-10-17 00:31:27,238][62373] Updated weights for policy 0, policy_version 6480 (0.0010) -[2023-10-17 00:31:27,602][62373] Updated weights for policy 0, policy_version 6490 (0.0008) -[2023-10-17 00:31:27,632][62408] Updated weights for policy 1, policy_version 6440 (0.0008) -[2023-10-17 00:31:28,001][62408] Updated weights for policy 1, policy_version 6450 (0.0008) -[2023-10-17 00:31:28,369][62408] Updated weights for policy 1, policy_version 6460 (0.0008) -[2023-10-17 00:31:28,509][62252] Saving new best policy, reward=4.070! -[2023-10-17 00:31:31,338][62373] Updated weights for policy 0, policy_version 6500 (0.0007) -[2023-10-17 00:31:31,714][62373] Updated weights for policy 0, policy_version 6510 (0.0009) -[2023-10-17 00:31:32,082][62373] Updated weights for policy 0, policy_version 6520 (0.0009) -[2023-10-17 00:31:32,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 13271040. Throughput: 0: 1772.3, 1: 1775.0. Samples: 3336826. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:31:32,214][61453] Avg episode reward: [(0, '4.340'), (1, '3.660')] -[2023-10-17 00:31:32,335][62408] Updated weights for policy 1, policy_version 6470 (0.0009) -[2023-10-17 00:31:32,374][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000006528_6684672.pth... -[2023-10-17 00:31:32,409][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000004864_4980736.pth -[2023-10-17 00:31:32,412][62094] Saving new best policy, reward=4.340! -[2023-10-17 00:31:32,694][62408] Updated weights for policy 1, policy_version 6480 (0.0008) -[2023-10-17 00:31:33,065][62408] Updated weights for policy 1, policy_version 6490 (0.0008) -[2023-10-17 00:31:33,282][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000006496_6651904.pth... -[2023-10-17 00:31:33,325][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000004832_4947968.pth -[2023-10-17 00:31:35,870][62373] Updated weights for policy 0, policy_version 6530 (0.0008) -[2023-10-17 00:31:36,247][62373] Updated weights for policy 0, policy_version 6540 (0.0008) -[2023-10-17 00:31:36,610][62373] Updated weights for policy 0, policy_version 6550 (0.0009) -[2023-10-17 00:31:36,982][62408] Updated weights for policy 1, policy_version 6500 (0.0011) -[2023-10-17 00:31:36,982][62373] Updated weights for policy 0, policy_version 6560 (0.0008) -[2023-10-17 00:31:37,214][61453] Fps is (10 sec: 16384.3, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 13369344. Throughput: 0: 1773.3, 1: 1739.8. Samples: 3347228. Policy #0 lag: (min: 0.0, avg: 28.6, max: 32.0) -[2023-10-17 00:31:37,214][61453] Avg episode reward: [(0, '4.330'), (1, '4.140')] -[2023-10-17 00:31:37,338][62408] Updated weights for policy 1, policy_version 6510 (0.0010) -[2023-10-17 00:31:37,700][62408] Updated weights for policy 1, policy_version 6520 (0.0009) -[2023-10-17 00:31:37,991][62252] Saving new best policy, reward=4.140! -[2023-10-17 00:31:40,667][62373] Updated weights for policy 0, policy_version 6570 (0.0010) -[2023-10-17 00:31:41,041][62373] Updated weights for policy 0, policy_version 6580 (0.0008) -[2023-10-17 00:31:41,421][62373] Updated weights for policy 0, policy_version 6590 (0.0008) -[2023-10-17 00:31:41,620][62408] Updated weights for policy 1, policy_version 6530 (0.0007) -[2023-10-17 00:31:41,984][62408] Updated weights for policy 1, policy_version 6540 (0.0009) -[2023-10-17 00:31:42,214][61453] Fps is (10 sec: 16383.9, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 13434880. Throughput: 0: 1785.4, 1: 1765.1. Samples: 3368578. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) -[2023-10-17 00:31:42,215][61453] Avg episode reward: [(0, '4.110'), (1, '4.120')] -[2023-10-17 00:31:42,355][62408] Updated weights for policy 1, policy_version 6550 (0.0007) -[2023-10-17 00:31:42,720][62408] Updated weights for policy 1, policy_version 6560 (0.0008) -[2023-10-17 00:31:44,988][62373] Updated weights for policy 0, policy_version 6600 (0.0008) -[2023-10-17 00:31:45,355][62373] Updated weights for policy 0, policy_version 6610 (0.0008) -[2023-10-17 00:31:45,729][62373] Updated weights for policy 0, policy_version 6620 (0.0011) -[2023-10-17 00:31:46,554][62408] Updated weights for policy 1, policy_version 6570 (0.0007) -[2023-10-17 00:31:46,933][62408] Updated weights for policy 1, policy_version 6580 (0.0008) -[2023-10-17 00:31:47,214][61453] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 13500416. Throughput: 0: 1776.9, 1: 1753.2. Samples: 3389408. Policy #0 lag: (min: 31.0, avg: 36.4, max: 63.0) -[2023-10-17 00:31:47,215][61453] Avg episode reward: [(0, '4.660'), (1, '4.210')] -[2023-10-17 00:31:47,226][62094] Saving new best policy, reward=4.660! -[2023-10-17 00:31:47,297][62408] Updated weights for policy 1, policy_version 6590 (0.0007) -[2023-10-17 00:31:47,371][62252] Saving new best policy, reward=4.210! -[2023-10-17 00:31:49,660][62373] Updated weights for policy 0, policy_version 6630 (0.0009) -[2023-10-17 00:31:50,038][62373] Updated weights for policy 0, policy_version 6640 (0.0011) -[2023-10-17 00:31:50,419][62373] Updated weights for policy 0, policy_version 6650 (0.0010) -[2023-10-17 00:31:51,171][62408] Updated weights for policy 1, policy_version 6600 (0.0008) -[2023-10-17 00:31:51,550][62408] Updated weights for policy 1, policy_version 6610 (0.0009) -[2023-10-17 00:31:51,917][62408] Updated weights for policy 1, policy_version 6620 (0.0009) -[2023-10-17 00:31:52,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 13598720. Throughput: 0: 1791.5, 1: 1756.6. Samples: 3400426. Policy #0 lag: (min: 31.0, avg: 31.9, max: 52.0) -[2023-10-17 00:31:52,215][61453] Avg episode reward: [(0, '4.620'), (1, '4.260')] -[2023-10-17 00:31:52,216][62252] Saving new best policy, reward=4.260! -[2023-10-17 00:31:54,029][62373] Updated weights for policy 0, policy_version 6660 (0.0008) -[2023-10-17 00:31:54,401][62373] Updated weights for policy 0, policy_version 6670 (0.0008) -[2023-10-17 00:31:54,770][62373] Updated weights for policy 0, policy_version 6680 (0.0009) -[2023-10-17 00:31:55,730][62408] Updated weights for policy 1, policy_version 6630 (0.0007) -[2023-10-17 00:31:56,101][62408] Updated weights for policy 1, policy_version 6640 (0.0009) -[2023-10-17 00:31:56,470][62408] Updated weights for policy 1, policy_version 6650 (0.0010) -[2023-10-17 00:31:57,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 13664256. Throughput: 0: 1775.7, 1: 1762.3. Samples: 3421456. Policy #0 lag: (min: 31.0, avg: 31.9, max: 52.0) -[2023-10-17 00:31:57,215][61453] Avg episode reward: [(0, '4.350'), (1, '4.440')] -[2023-10-17 00:31:57,217][62252] Saving new best policy, reward=4.440! -[2023-10-17 00:31:58,602][62373] Updated weights for policy 0, policy_version 6690 (0.0010) -[2023-10-17 00:31:58,963][62373] Updated weights for policy 0, policy_version 6700 (0.0007) -[2023-10-17 00:31:59,341][62373] Updated weights for policy 0, policy_version 6710 (0.0009) -[2023-10-17 00:31:59,719][62373] Updated weights for policy 0, policy_version 6720 (0.0009) -[2023-10-17 00:32:00,100][62408] Updated weights for policy 1, policy_version 6660 (0.0008) -[2023-10-17 00:32:00,465][62408] Updated weights for policy 1, policy_version 6670 (0.0009) -[2023-10-17 00:32:00,825][62408] Updated weights for policy 1, policy_version 6680 (0.0009) -[2023-10-17 00:32:02,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 13729792. Throughput: 0: 1773.7, 1: 1741.9. Samples: 3442578. Policy #0 lag: (min: 31.0, avg: 42.2, max: 63.0) -[2023-10-17 00:32:02,215][61453] Avg episode reward: [(0, '3.980'), (1, '4.410')] -[2023-10-17 00:32:03,675][62373] Updated weights for policy 0, policy_version 6730 (0.0007) -[2023-10-17 00:32:04,046][62373] Updated weights for policy 0, policy_version 6740 (0.0008) -[2023-10-17 00:32:04,425][62373] Updated weights for policy 0, policy_version 6750 (0.0009) -[2023-10-17 00:32:04,546][62408] Updated weights for policy 1, policy_version 6690 (0.0008) -[2023-10-17 00:32:04,905][62408] Updated weights for policy 1, policy_version 6700 (0.0008) -[2023-10-17 00:32:05,271][62408] Updated weights for policy 1, policy_version 6710 (0.0010) -[2023-10-17 00:32:05,639][62408] Updated weights for policy 1, policy_version 6720 (0.0007) -[2023-10-17 00:32:07,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 13795328. Throughput: 0: 1772.4, 1: 1760.9. Samples: 3452924. Policy #0 lag: (min: 31.0, avg: 42.2, max: 63.0) -[2023-10-17 00:32:07,214][61453] Avg episode reward: [(0, '4.020'), (1, '4.240')] -[2023-10-17 00:32:08,219][62373] Updated weights for policy 0, policy_version 6760 (0.0009) -[2023-10-17 00:32:08,597][62373] Updated weights for policy 0, policy_version 6770 (0.0007) -[2023-10-17 00:32:08,971][62373] Updated weights for policy 0, policy_version 6780 (0.0009) -[2023-10-17 00:32:09,395][62408] Updated weights for policy 1, policy_version 6730 (0.0010) -[2023-10-17 00:32:09,776][62408] Updated weights for policy 1, policy_version 6740 (0.0007) -[2023-10-17 00:32:10,146][62408] Updated weights for policy 1, policy_version 6750 (0.0008) -[2023-10-17 00:32:12,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 13860864. Throughput: 0: 1771.1, 1: 1741.2. Samples: 3474022. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:32:12,215][61453] Avg episode reward: [(0, '3.680'), (1, '3.830')] -[2023-10-17 00:32:12,775][62373] Updated weights for policy 0, policy_version 6790 (0.0007) -[2023-10-17 00:32:13,144][62373] Updated weights for policy 0, policy_version 6800 (0.0009) -[2023-10-17 00:32:13,521][62373] Updated weights for policy 0, policy_version 6810 (0.0009) -[2023-10-17 00:32:14,180][62408] Updated weights for policy 1, policy_version 6760 (0.0010) -[2023-10-17 00:32:14,555][62408] Updated weights for policy 1, policy_version 6770 (0.0008) -[2023-10-17 00:32:14,923][62408] Updated weights for policy 1, policy_version 6780 (0.0009) -[2023-10-17 00:32:17,159][62373] Updated weights for policy 0, policy_version 6820 (0.0008) -[2023-10-17 00:32:17,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 13926400. Throughput: 0: 1798.0, 1: 1747.2. Samples: 3496360. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:32:17,215][61453] Avg episode reward: [(0, '3.930'), (1, '3.770')] -[2023-10-17 00:32:17,526][62373] Updated weights for policy 0, policy_version 6830 (0.0008) -[2023-10-17 00:32:17,903][62373] Updated weights for policy 0, policy_version 6840 (0.0011) -[2023-10-17 00:32:18,838][62408] Updated weights for policy 1, policy_version 6790 (0.0008) -[2023-10-17 00:32:19,201][62408] Updated weights for policy 1, policy_version 6800 (0.0008) -[2023-10-17 00:32:19,576][62408] Updated weights for policy 1, policy_version 6810 (0.0010) -[2023-10-17 00:32:21,516][62373] Updated weights for policy 0, policy_version 6850 (0.0010) -[2023-10-17 00:32:21,886][62373] Updated weights for policy 0, policy_version 6860 (0.0009) -[2023-10-17 00:32:22,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 13991936. Throughput: 0: 1780.1, 1: 1749.2. Samples: 3506048. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-17 00:32:22,214][61453] Avg episode reward: [(0, '4.110'), (1, '3.950')] -[2023-10-17 00:32:22,271][62373] Updated weights for policy 0, policy_version 6870 (0.0010) -[2023-10-17 00:32:22,641][62373] Updated weights for policy 0, policy_version 6880 (0.0007) -[2023-10-17 00:32:23,308][62408] Updated weights for policy 1, policy_version 6820 (0.0008) -[2023-10-17 00:32:23,679][62408] Updated weights for policy 1, policy_version 6830 (0.0007) -[2023-10-17 00:32:24,060][62408] Updated weights for policy 1, policy_version 6840 (0.0008) -[2023-10-17 00:32:26,462][62373] Updated weights for policy 0, policy_version 6890 (0.0009) -[2023-10-17 00:32:26,827][62373] Updated weights for policy 0, policy_version 6900 (0.0009) -[2023-10-17 00:32:27,203][62373] Updated weights for policy 0, policy_version 6910 (0.0007) -[2023-10-17 00:32:27,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 14057472. Throughput: 0: 1793.2, 1: 1756.2. Samples: 3528300. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-17 00:32:27,215][61453] Avg episode reward: [(0, '4.020'), (1, '3.790')] -[2023-10-17 00:32:27,922][62408] Updated weights for policy 1, policy_version 6850 (0.0010) -[2023-10-17 00:32:28,288][62408] Updated weights for policy 1, policy_version 6860 (0.0008) -[2023-10-17 00:32:28,662][62408] Updated weights for policy 1, policy_version 6870 (0.0007) -[2023-10-17 00:32:29,027][62408] Updated weights for policy 1, policy_version 6880 (0.0011) -[2023-10-17 00:32:30,981][62373] Updated weights for policy 0, policy_version 6920 (0.0010) -[2023-10-17 00:32:31,345][62373] Updated weights for policy 0, policy_version 6930 (0.0008) -[2023-10-17 00:32:31,723][62373] Updated weights for policy 0, policy_version 6940 (0.0007) -[2023-10-17 00:32:32,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14106.9). Total num frames: 14155776. Throughput: 0: 1776.4, 1: 1771.9. Samples: 3549080. Policy #0 lag: (min: 24.0, avg: 51.2, max: 56.0) -[2023-10-17 00:32:32,214][61453] Avg episode reward: [(0, '3.890'), (1, '3.850')] -[2023-10-17 00:32:32,842][62408] Updated weights for policy 1, policy_version 6890 (0.0008) -[2023-10-17 00:32:33,211][62408] Updated weights for policy 1, policy_version 6900 (0.0007) -[2023-10-17 00:32:33,571][62408] Updated weights for policy 1, policy_version 6910 (0.0009) -[2023-10-17 00:32:35,389][62373] Updated weights for policy 0, policy_version 6950 (0.0009) -[2023-10-17 00:32:35,751][62373] Updated weights for policy 0, policy_version 6960 (0.0008) -[2023-10-17 00:32:36,126][62373] Updated weights for policy 0, policy_version 6970 (0.0008) -[2023-10-17 00:32:37,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 14221312. Throughput: 0: 1797.6, 1: 1753.6. Samples: 3560230. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:32:37,214][61453] Avg episode reward: [(0, '3.810'), (1, '4.190')] -[2023-10-17 00:32:37,424][62408] Updated weights for policy 1, policy_version 6920 (0.0009) -[2023-10-17 00:32:37,796][62408] Updated weights for policy 1, policy_version 6930 (0.0008) -[2023-10-17 00:32:38,158][62408] Updated weights for policy 1, policy_version 6940 (0.0008) -[2023-10-17 00:32:39,865][62373] Updated weights for policy 0, policy_version 6980 (0.0008) -[2023-10-17 00:32:40,232][62373] Updated weights for policy 0, policy_version 6990 (0.0010) -[2023-10-17 00:32:40,604][62373] Updated weights for policy 0, policy_version 7000 (0.0007) -[2023-10-17 00:32:41,956][62408] Updated weights for policy 1, policy_version 6950 (0.0007) -[2023-10-17 00:32:42,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 14286848. Throughput: 0: 1786.8, 1: 1762.1. Samples: 3581156. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:32:42,215][61453] Avg episode reward: [(0, '3.650'), (1, '4.160')] -[2023-10-17 00:32:42,323][62408] Updated weights for policy 1, policy_version 6960 (0.0008) -[2023-10-17 00:32:42,686][62408] Updated weights for policy 1, policy_version 6970 (0.0009) -[2023-10-17 00:32:44,355][62373] Updated weights for policy 0, policy_version 7010 (0.0007) -[2023-10-17 00:32:44,725][62373] Updated weights for policy 0, policy_version 7020 (0.0008) -[2023-10-17 00:32:45,098][62373] Updated weights for policy 0, policy_version 7030 (0.0008) -[2023-10-17 00:32:45,462][62373] Updated weights for policy 0, policy_version 7040 (0.0007) -[2023-10-17 00:32:46,580][62408] Updated weights for policy 1, policy_version 6980 (0.0010) -[2023-10-17 00:32:46,958][62408] Updated weights for policy 1, policy_version 6990 (0.0009) -[2023-10-17 00:32:47,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 14352384. Throughput: 0: 1793.2, 1: 1768.9. Samples: 3602872. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:32:47,215][61453] Avg episode reward: [(0, '3.660'), (1, '3.850')] -[2023-10-17 00:32:47,326][62408] Updated weights for policy 1, policy_version 7000 (0.0009) -[2023-10-17 00:32:49,216][62373] Updated weights for policy 0, policy_version 7050 (0.0009) -[2023-10-17 00:32:49,591][62373] Updated weights for policy 0, policy_version 7060 (0.0009) -[2023-10-17 00:32:49,954][62373] Updated weights for policy 0, policy_version 7070 (0.0008) -[2023-10-17 00:32:51,073][62408] Updated weights for policy 1, policy_version 7010 (0.0008) -[2023-10-17 00:32:51,448][62408] Updated weights for policy 1, policy_version 7020 (0.0008) -[2023-10-17 00:32:51,807][62408] Updated weights for policy 1, policy_version 7030 (0.0009) -[2023-10-17 00:32:52,178][62408] Updated weights for policy 1, policy_version 7040 (0.0009) -[2023-10-17 00:32:52,214][61453] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 14450688. Throughput: 0: 1797.2, 1: 1762.2. Samples: 3613094. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:32:52,214][61453] Avg episode reward: [(0, '3.990'), (1, '4.240')] -[2023-10-17 00:32:53,555][62373] Updated weights for policy 0, policy_version 7080 (0.0010) -[2023-10-17 00:32:53,926][62373] Updated weights for policy 0, policy_version 7090 (0.0010) -[2023-10-17 00:32:54,296][62373] Updated weights for policy 0, policy_version 7100 (0.0007) -[2023-10-17 00:32:55,985][62408] Updated weights for policy 1, policy_version 7050 (0.0007) -[2023-10-17 00:32:56,350][62408] Updated weights for policy 1, policy_version 7060 (0.0007) -[2023-10-17 00:32:56,721][62408] Updated weights for policy 1, policy_version 7070 (0.0009) -[2023-10-17 00:32:57,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 14516224. Throughput: 0: 1795.2, 1: 1780.7. Samples: 3634940. Policy #0 lag: (min: 31.0, avg: 33.1, max: 61.0) -[2023-10-17 00:32:57,215][61453] Avg episode reward: [(0, '4.110'), (1, '4.550')] -[2023-10-17 00:32:57,216][62252] Saving new best policy, reward=4.550! -[2023-10-17 00:32:58,165][62373] Updated weights for policy 0, policy_version 7110 (0.0009) -[2023-10-17 00:32:58,530][62373] Updated weights for policy 0, policy_version 7120 (0.0009) -[2023-10-17 00:32:58,902][62373] Updated weights for policy 0, policy_version 7130 (0.0009) -[2023-10-17 00:33:00,644][62408] Updated weights for policy 1, policy_version 7080 (0.0009) -[2023-10-17 00:33:01,030][62408] Updated weights for policy 1, policy_version 7090 (0.0010) -[2023-10-17 00:33:01,414][62408] Updated weights for policy 1, policy_version 7100 (0.0007) -[2023-10-17 00:33:02,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 14581760. Throughput: 0: 1790.1, 1: 1753.1. Samples: 3655804. Policy #0 lag: (min: 31.0, avg: 33.1, max: 61.0) -[2023-10-17 00:33:02,214][61453] Avg episode reward: [(0, '4.120'), (1, '4.550')] -[2023-10-17 00:33:02,596][62373] Updated weights for policy 0, policy_version 7140 (0.0007) -[2023-10-17 00:33:02,963][62373] Updated weights for policy 0, policy_version 7150 (0.0007) -[2023-10-17 00:33:03,332][62373] Updated weights for policy 0, policy_version 7160 (0.0007) -[2023-10-17 00:33:05,194][62408] Updated weights for policy 1, policy_version 7110 (0.0009) -[2023-10-17 00:33:05,552][62408] Updated weights for policy 1, policy_version 7120 (0.0007) -[2023-10-17 00:33:05,921][62408] Updated weights for policy 1, policy_version 7130 (0.0008) -[2023-10-17 00:33:07,213][62373] Updated weights for policy 0, policy_version 7170 (0.0008) -[2023-10-17 00:33:07,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 14647296. Throughput: 0: 1791.7, 1: 1782.7. Samples: 3666898. Policy #0 lag: (min: 31.0, avg: 31.7, max: 50.0) -[2023-10-17 00:33:07,215][61453] Avg episode reward: [(0, '3.800'), (1, '4.440')] -[2023-10-17 00:33:07,588][62373] Updated weights for policy 0, policy_version 7180 (0.0008) -[2023-10-17 00:33:07,953][62373] Updated weights for policy 0, policy_version 7190 (0.0007) -[2023-10-17 00:33:08,327][62373] Updated weights for policy 0, policy_version 7200 (0.0007) -[2023-10-17 00:33:09,788][62408] Updated weights for policy 1, policy_version 7140 (0.0009) -[2023-10-17 00:33:10,156][62408] Updated weights for policy 1, policy_version 7150 (0.0008) -[2023-10-17 00:33:10,522][62408] Updated weights for policy 1, policy_version 7160 (0.0009) -[2023-10-17 00:33:11,899][62373] Updated weights for policy 0, policy_version 7210 (0.0008) -[2023-10-17 00:33:12,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 14712832. Throughput: 0: 1794.0, 1: 1749.6. Samples: 3687764. Policy #0 lag: (min: 31.0, avg: 31.7, max: 50.0) -[2023-10-17 00:33:12,215][61453] Avg episode reward: [(0, '3.700'), (1, '4.410')] -[2023-10-17 00:33:12,267][62373] Updated weights for policy 0, policy_version 7220 (0.0007) -[2023-10-17 00:33:12,626][62373] Updated weights for policy 0, policy_version 7230 (0.0009) -[2023-10-17 00:33:14,385][62408] Updated weights for policy 1, policy_version 7170 (0.0010) -[2023-10-17 00:33:14,746][62408] Updated weights for policy 1, policy_version 7180 (0.0009) -[2023-10-17 00:33:15,123][62408] Updated weights for policy 1, policy_version 7190 (0.0010) -[2023-10-17 00:33:15,483][62408] Updated weights for policy 1, policy_version 7200 (0.0009) -[2023-10-17 00:33:16,469][62373] Updated weights for policy 0, policy_version 7240 (0.0007) -[2023-10-17 00:33:16,838][62373] Updated weights for policy 0, policy_version 7250 (0.0009) -[2023-10-17 00:33:17,211][62373] Updated weights for policy 0, policy_version 7260 (0.0010) -[2023-10-17 00:33:17,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 14778368. Throughput: 0: 1801.9, 1: 1750.0. Samples: 3708912. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-17 00:33:17,215][61453] Avg episode reward: [(0, '3.590'), (1, '4.150')] -[2023-10-17 00:33:19,307][62408] Updated weights for policy 1, policy_version 7210 (0.0010) -[2023-10-17 00:33:19,677][62408] Updated weights for policy 1, policy_version 7220 (0.0009) -[2023-10-17 00:33:20,052][62408] Updated weights for policy 1, policy_version 7230 (0.0010) -[2023-10-17 00:33:20,918][62373] Updated weights for policy 0, policy_version 7270 (0.0008) -[2023-10-17 00:33:21,292][62373] Updated weights for policy 0, policy_version 7280 (0.0007) -[2023-10-17 00:33:21,670][62373] Updated weights for policy 0, policy_version 7290 (0.0008) -[2023-10-17 00:33:22,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14106.9). Total num frames: 14876672. Throughput: 0: 1787.4, 1: 1764.2. Samples: 3720052. Policy #0 lag: (min: 1.0, avg: 11.6, max: 33.0) -[2023-10-17 00:33:22,214][61453] Avg episode reward: [(0, '3.670'), (1, '3.890')] -[2023-10-17 00:33:23,832][62408] Updated weights for policy 1, policy_version 7240 (0.0007) -[2023-10-17 00:33:24,197][62408] Updated weights for policy 1, policy_version 7250 (0.0008) -[2023-10-17 00:33:24,571][62408] Updated weights for policy 1, policy_version 7260 (0.0007) -[2023-10-17 00:33:25,402][62373] Updated weights for policy 0, policy_version 7300 (0.0009) -[2023-10-17 00:33:25,777][62373] Updated weights for policy 0, policy_version 7310 (0.0011) -[2023-10-17 00:33:26,152][62373] Updated weights for policy 0, policy_version 7320 (0.0007) -[2023-10-17 00:33:27,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14106.9). Total num frames: 14942208. Throughput: 0: 1799.0, 1: 1757.4. Samples: 3741194. Policy #0 lag: (min: 1.0, avg: 11.6, max: 33.0) -[2023-10-17 00:33:27,215][61453] Avg episode reward: [(0, '3.900'), (1, '3.920')] -[2023-10-17 00:33:28,399][62408] Updated weights for policy 1, policy_version 7270 (0.0009) -[2023-10-17 00:33:28,765][62408] Updated weights for policy 1, policy_version 7280 (0.0009) -[2023-10-17 00:33:29,140][62408] Updated weights for policy 1, policy_version 7290 (0.0009) -[2023-10-17 00:33:30,015][62373] Updated weights for policy 0, policy_version 7330 (0.0008) -[2023-10-17 00:33:30,385][62373] Updated weights for policy 0, policy_version 7340 (0.0007) -[2023-10-17 00:33:30,754][62373] Updated weights for policy 0, policy_version 7350 (0.0009) -[2023-10-17 00:33:31,128][62373] Updated weights for policy 0, policy_version 7360 (0.0007) -[2023-10-17 00:33:32,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 15007744. Throughput: 0: 1776.0, 1: 1772.5. Samples: 3762554. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-17 00:33:32,215][61453] Avg episode reward: [(0, '4.030'), (1, '4.240')] -[2023-10-17 00:33:32,224][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000007360_7536640.pth... -[2023-10-17 00:33:32,225][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000007296_7471104.pth... -[2023-10-17 00:33:32,258][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000005664_5799936.pth -[2023-10-17 00:33:32,265][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000005696_5832704.pth -[2023-10-17 00:33:33,072][62408] Updated weights for policy 1, policy_version 7300 (0.0007) -[2023-10-17 00:33:33,444][62408] Updated weights for policy 1, policy_version 7310 (0.0011) -[2023-10-17 00:33:33,806][62408] Updated weights for policy 1, policy_version 7320 (0.0011) -[2023-10-17 00:33:35,139][62373] Updated weights for policy 0, policy_version 7370 (0.0009) -[2023-10-17 00:33:35,515][62373] Updated weights for policy 0, policy_version 7380 (0.0009) -[2023-10-17 00:33:35,890][62373] Updated weights for policy 0, policy_version 7390 (0.0009) -[2023-10-17 00:33:37,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 15073280. Throughput: 0: 1801.6, 1: 1756.4. Samples: 3773206. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-17 00:33:37,215][61453] Avg episode reward: [(0, '4.320'), (1, '4.580')] -[2023-10-17 00:33:37,217][62252] Saving new best policy, reward=4.580! -[2023-10-17 00:33:37,534][62408] Updated weights for policy 1, policy_version 7330 (0.0008) -[2023-10-17 00:33:37,895][62408] Updated weights for policy 1, policy_version 7340 (0.0009) -[2023-10-17 00:33:38,257][62408] Updated weights for policy 1, policy_version 7350 (0.0007) -[2023-10-17 00:33:38,619][62408] Updated weights for policy 1, policy_version 7360 (0.0007) -[2023-10-17 00:33:39,778][62373] Updated weights for policy 0, policy_version 7400 (0.0009) -[2023-10-17 00:33:40,157][62373] Updated weights for policy 0, policy_version 7410 (0.0007) -[2023-10-17 00:33:40,536][62373] Updated weights for policy 0, policy_version 7420 (0.0011) -[2023-10-17 00:33:42,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 15138816. Throughput: 0: 1771.2, 1: 1766.1. Samples: 3794118. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:33:42,214][61453] Avg episode reward: [(0, '4.320'), (1, '4.480')] -[2023-10-17 00:33:42,483][62408] Updated weights for policy 1, policy_version 7370 (0.0009) -[2023-10-17 00:33:42,857][62408] Updated weights for policy 1, policy_version 7380 (0.0008) -[2023-10-17 00:33:43,224][62408] Updated weights for policy 1, policy_version 7390 (0.0008) -[2023-10-17 00:33:44,207][62373] Updated weights for policy 0, policy_version 7430 (0.0010) -[2023-10-17 00:33:44,573][62373] Updated weights for policy 0, policy_version 7440 (0.0007) -[2023-10-17 00:33:44,941][62373] Updated weights for policy 0, policy_version 7450 (0.0007) -[2023-10-17 00:33:47,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 15204352. Throughput: 0: 1771.5, 1: 1789.2. Samples: 3816036. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:33:47,215][61453] Avg episode reward: [(0, '4.230'), (1, '4.280')] -[2023-10-17 00:33:47,248][62408] Updated weights for policy 1, policy_version 7400 (0.0008) -[2023-10-17 00:33:47,615][62408] Updated weights for policy 1, policy_version 7410 (0.0007) -[2023-10-17 00:33:47,986][62408] Updated weights for policy 1, policy_version 7420 (0.0010) -[2023-10-17 00:33:48,693][62373] Updated weights for policy 0, policy_version 7460 (0.0008) -[2023-10-17 00:33:49,052][62373] Updated weights for policy 0, policy_version 7470 (0.0011) -[2023-10-17 00:33:49,425][62373] Updated weights for policy 0, policy_version 7480 (0.0007) -[2023-10-17 00:33:51,681][62408] Updated weights for policy 1, policy_version 7430 (0.0009) -[2023-10-17 00:33:52,054][62408] Updated weights for policy 1, policy_version 7440 (0.0008) -[2023-10-17 00:33:52,214][61453] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 15269888. Throughput: 0: 1768.5, 1: 1761.2. Samples: 3825736. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:33:52,215][61453] Avg episode reward: [(0, '4.020'), (1, '4.320')] -[2023-10-17 00:33:52,431][62408] Updated weights for policy 1, policy_version 7450 (0.0008) -[2023-10-17 00:33:53,204][62373] Updated weights for policy 0, policy_version 7490 (0.0007) -[2023-10-17 00:33:53,588][62373] Updated weights for policy 0, policy_version 7500 (0.0009) -[2023-10-17 00:33:53,964][62373] Updated weights for policy 0, policy_version 7510 (0.0008) -[2023-10-17 00:33:54,327][62373] Updated weights for policy 0, policy_version 7520 (0.0008) -[2023-10-17 00:33:56,301][62408] Updated weights for policy 1, policy_version 7460 (0.0010) -[2023-10-17 00:33:56,670][62408] Updated weights for policy 1, policy_version 7470 (0.0008) -[2023-10-17 00:33:57,046][62408] Updated weights for policy 1, policy_version 7480 (0.0009) -[2023-10-17 00:33:57,214][61453] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 15335424. Throughput: 0: 1765.8, 1: 1791.2. Samples: 3847828. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:33:57,214][61453] Avg episode reward: [(0, '4.010'), (1, '4.300')] -[2023-10-17 00:33:58,067][62373] Updated weights for policy 0, policy_version 7530 (0.0008) -[2023-10-17 00:33:58,447][62373] Updated weights for policy 0, policy_version 7540 (0.0008) -[2023-10-17 00:33:58,814][62373] Updated weights for policy 0, policy_version 7550 (0.0007) -[2023-10-17 00:34:00,949][62408] Updated weights for policy 1, policy_version 7490 (0.0008) -[2023-10-17 00:34:01,313][62408] Updated weights for policy 1, policy_version 7500 (0.0009) -[2023-10-17 00:34:01,691][62408] Updated weights for policy 1, policy_version 7510 (0.0009) -[2023-10-17 00:34:02,055][62408] Updated weights for policy 1, policy_version 7520 (0.0009) -[2023-10-17 00:34:02,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 15433728. Throughput: 0: 1790.3, 1: 1766.7. Samples: 3868976. Policy #0 lag: (min: 31.0, avg: 34.2, max: 63.0) -[2023-10-17 00:34:02,215][61453] Avg episode reward: [(0, '3.770'), (1, '4.190')] -[2023-10-17 00:34:02,639][62373] Updated weights for policy 0, policy_version 7560 (0.0007) -[2023-10-17 00:34:03,015][62373] Updated weights for policy 0, policy_version 7570 (0.0007) -[2023-10-17 00:34:03,377][62373] Updated weights for policy 0, policy_version 7580 (0.0007) -[2023-10-17 00:34:05,800][62408] Updated weights for policy 1, policy_version 7530 (0.0009) -[2023-10-17 00:34:06,167][62408] Updated weights for policy 1, policy_version 7540 (0.0009) -[2023-10-17 00:34:06,541][62408] Updated weights for policy 1, policy_version 7550 (0.0007) -[2023-10-17 00:34:07,036][62373] Updated weights for policy 0, policy_version 7590 (0.0009) -[2023-10-17 00:34:07,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 15499264. Throughput: 0: 1770.5, 1: 1781.2. Samples: 3879876. Policy #0 lag: (min: 31.0, avg: 34.2, max: 63.0) -[2023-10-17 00:34:07,214][61453] Avg episode reward: [(0, '4.240'), (1, '4.470')] -[2023-10-17 00:34:07,400][62373] Updated weights for policy 0, policy_version 7600 (0.0008) -[2023-10-17 00:34:07,773][62373] Updated weights for policy 0, policy_version 7610 (0.0009) -[2023-10-17 00:34:10,364][62408] Updated weights for policy 1, policy_version 7560 (0.0010) -[2023-10-17 00:34:10,728][62408] Updated weights for policy 1, policy_version 7570 (0.0011) -[2023-10-17 00:34:11,102][62408] Updated weights for policy 1, policy_version 7580 (0.0010) -[2023-10-17 00:34:11,585][62373] Updated weights for policy 0, policy_version 7620 (0.0008) -[2023-10-17 00:34:11,963][62373] Updated weights for policy 0, policy_version 7630 (0.0008) -[2023-10-17 00:34:12,214][61453] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 15564800. Throughput: 0: 1787.8, 1: 1763.6. Samples: 3901006. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-17 00:34:12,214][61453] Avg episode reward: [(0, '4.030'), (1, '4.300')] -[2023-10-17 00:34:12,349][62373] Updated weights for policy 0, policy_version 7640 (0.0007) -[2023-10-17 00:34:14,989][62408] Updated weights for policy 1, policy_version 7590 (0.0010) -[2023-10-17 00:34:15,357][62408] Updated weights for policy 1, policy_version 7600 (0.0009) -[2023-10-17 00:34:15,727][62408] Updated weights for policy 1, policy_version 7610 (0.0010) -[2023-10-17 00:34:16,169][62373] Updated weights for policy 0, policy_version 7650 (0.0007) -[2023-10-17 00:34:16,540][62373] Updated weights for policy 0, policy_version 7660 (0.0007) -[2023-10-17 00:34:16,911][62373] Updated weights for policy 0, policy_version 7670 (0.0008) -[2023-10-17 00:34:17,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 15630336. Throughput: 0: 1785.3, 1: 1745.6. Samples: 3921444. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-17 00:34:17,215][61453] Avg episode reward: [(0, '3.960'), (1, '4.600')] -[2023-10-17 00:34:17,226][62252] Saving new best policy, reward=4.600! -[2023-10-17 00:34:17,285][62373] Updated weights for policy 0, policy_version 7680 (0.0011) -[2023-10-17 00:34:19,739][62408] Updated weights for policy 1, policy_version 7620 (0.0010) -[2023-10-17 00:34:20,105][62408] Updated weights for policy 1, policy_version 7630 (0.0010) -[2023-10-17 00:34:20,470][62408] Updated weights for policy 1, policy_version 7640 (0.0008) -[2023-10-17 00:34:21,216][62373] Updated weights for policy 0, policy_version 7690 (0.0009) -[2023-10-17 00:34:21,602][62373] Updated weights for policy 0, policy_version 7700 (0.0009) -[2023-10-17 00:34:21,976][62373] Updated weights for policy 0, policy_version 7710 (0.0009) -[2023-10-17 00:34:22,214][61453] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 15728640. Throughput: 0: 1778.8, 1: 1773.6. Samples: 3933064. Policy #0 lag: (min: 25.0, avg: 39.8, max: 57.0) -[2023-10-17 00:34:22,215][61453] Avg episode reward: [(0, '4.100'), (1, '4.220')] -[2023-10-17 00:34:24,360][62408] Updated weights for policy 1, policy_version 7650 (0.0008) -[2023-10-17 00:34:24,730][62408] Updated weights for policy 1, policy_version 7660 (0.0012) -[2023-10-17 00:34:25,084][62408] Updated weights for policy 1, policy_version 7670 (0.0011) -[2023-10-17 00:34:25,454][62408] Updated weights for policy 1, policy_version 7680 (0.0010) -[2023-10-17 00:34:25,697][62373] Updated weights for policy 0, policy_version 7720 (0.0008) -[2023-10-17 00:34:26,057][62373] Updated weights for policy 0, policy_version 7730 (0.0009) -[2023-10-17 00:34:26,437][62373] Updated weights for policy 0, policy_version 7740 (0.0008) -[2023-10-17 00:34:27,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 15794176. Throughput: 0: 1797.4, 1: 1739.7. Samples: 3953286. Policy #0 lag: (min: 31.0, avg: 31.1, max: 36.0) -[2023-10-17 00:34:27,215][61453] Avg episode reward: [(0, '3.850'), (1, '4.570')] -[2023-10-17 00:34:29,356][62408] Updated weights for policy 1, policy_version 7690 (0.0008) -[2023-10-17 00:34:29,716][62408] Updated weights for policy 1, policy_version 7700 (0.0008) -[2023-10-17 00:34:30,086][62408] Updated weights for policy 1, policy_version 7710 (0.0007) -[2023-10-17 00:34:30,187][62373] Updated weights for policy 0, policy_version 7750 (0.0009) -[2023-10-17 00:34:30,553][62373] Updated weights for policy 0, policy_version 7760 (0.0010) -[2023-10-17 00:34:30,921][62373] Updated weights for policy 0, policy_version 7770 (0.0008) -[2023-10-17 00:34:32,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 15859712. Throughput: 0: 1782.0, 1: 1742.8. Samples: 3974648. Policy #0 lag: (min: 31.0, avg: 31.1, max: 36.0) -[2023-10-17 00:34:32,215][61453] Avg episode reward: [(0, '3.790'), (1, '4.540')] -[2023-10-17 00:34:33,903][62408] Updated weights for policy 1, policy_version 7720 (0.0008) -[2023-10-17 00:34:34,278][62408] Updated weights for policy 1, policy_version 7730 (0.0010) -[2023-10-17 00:34:34,649][62408] Updated weights for policy 1, policy_version 7740 (0.0008) -[2023-10-17 00:34:34,684][62373] Updated weights for policy 0, policy_version 7780 (0.0008) -[2023-10-17 00:34:35,050][62373] Updated weights for policy 0, policy_version 7790 (0.0009) -[2023-10-17 00:34:35,423][62373] Updated weights for policy 0, policy_version 7800 (0.0010) -[2023-10-17 00:34:37,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 15925248. Throughput: 0: 1802.4, 1: 1741.3. Samples: 3985200. Policy #0 lag: (min: 31.0, avg: 31.8, max: 50.0) -[2023-10-17 00:34:37,214][61453] Avg episode reward: [(0, '4.010'), (1, '4.580')] -[2023-10-17 00:34:38,179][62408] Updated weights for policy 1, policy_version 7750 (0.0007) -[2023-10-17 00:34:38,555][62408] Updated weights for policy 1, policy_version 7760 (0.0007) -[2023-10-17 00:34:38,921][62408] Updated weights for policy 1, policy_version 7770 (0.0007) -[2023-10-17 00:34:39,311][62373] Updated weights for policy 0, policy_version 7810 (0.0010) -[2023-10-17 00:34:39,685][62373] Updated weights for policy 0, policy_version 7820 (0.0007) -[2023-10-17 00:34:40,050][62373] Updated weights for policy 0, policy_version 7830 (0.0007) -[2023-10-17 00:34:40,421][62373] Updated weights for policy 0, policy_version 7840 (0.0007) -[2023-10-17 00:34:42,214][61453] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 15990784. Throughput: 0: 1778.0, 1: 1744.6. Samples: 4006344. Policy #0 lag: (min: 31.0, avg: 31.8, max: 50.0) -[2023-10-17 00:34:42,215][61453] Avg episode reward: [(0, '3.890'), (1, '4.510')] -[2023-10-17 00:34:42,725][62408] Updated weights for policy 1, policy_version 7780 (0.0009) -[2023-10-17 00:34:43,098][62408] Updated weights for policy 1, policy_version 7790 (0.0009) -[2023-10-17 00:34:43,469][62408] Updated weights for policy 1, policy_version 7800 (0.0010) -[2023-10-17 00:34:44,244][62373] Updated weights for policy 0, policy_version 7850 (0.0007) -[2023-10-17 00:34:44,611][62373] Updated weights for policy 0, policy_version 7860 (0.0008) -[2023-10-17 00:34:44,977][62373] Updated weights for policy 0, policy_version 7870 (0.0007) -[2023-10-17 00:34:47,214][61453] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 16056320. Throughput: 0: 1774.5, 1: 1769.2. Samples: 4028442. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) -[2023-10-17 00:34:47,215][61453] Avg episode reward: [(0, '4.110'), (1, '4.720')] -[2023-10-17 00:34:47,227][62252] Saving new best policy, reward=4.720! -[2023-10-17 00:34:47,449][62408] Updated weights for policy 1, policy_version 7810 (0.0009) -[2023-10-17 00:34:47,813][62408] Updated weights for policy 1, policy_version 7820 (0.0008) -[2023-10-17 00:34:48,182][62408] Updated weights for policy 1, policy_version 7830 (0.0007) -[2023-10-17 00:34:48,542][62408] Updated weights for policy 1, policy_version 7840 (0.0007) -[2023-10-17 00:34:48,646][62373] Updated weights for policy 0, policy_version 7880 (0.0009) -[2023-10-17 00:34:49,016][62373] Updated weights for policy 0, policy_version 7890 (0.0010) -[2023-10-17 00:34:49,390][62373] Updated weights for policy 0, policy_version 7900 (0.0009) -[2023-10-17 00:34:52,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 16121856. Throughput: 0: 1774.4, 1: 1743.6. Samples: 4038188. Policy #0 lag: (min: 31.0, avg: 33.2, max: 63.0) -[2023-10-17 00:34:52,214][61453] Avg episode reward: [(0, '4.520'), (1, '4.120')] -[2023-10-17 00:34:52,505][62408] Updated weights for policy 1, policy_version 7850 (0.0009) -[2023-10-17 00:34:52,871][62408] Updated weights for policy 1, policy_version 7860 (0.0008) -[2023-10-17 00:34:53,238][62408] Updated weights for policy 1, policy_version 7870 (0.0008) -[2023-10-17 00:34:53,285][62373] Updated weights for policy 0, policy_version 7910 (0.0010) -[2023-10-17 00:34:53,653][62373] Updated weights for policy 0, policy_version 7920 (0.0009) -[2023-10-17 00:34:54,025][62373] Updated weights for policy 0, policy_version 7930 (0.0009) -[2023-10-17 00:34:57,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 16187392. Throughput: 0: 1770.7, 1: 1766.1. Samples: 4060160. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-17 00:34:57,215][61453] Avg episode reward: [(0, '4.460'), (1, '4.150')] -[2023-10-17 00:34:57,256][62408] Updated weights for policy 1, policy_version 7880 (0.0010) -[2023-10-17 00:34:57,631][62408] Updated weights for policy 1, policy_version 7890 (0.0011) -[2023-10-17 00:34:57,769][62373] Updated weights for policy 0, policy_version 7940 (0.0007) -[2023-10-17 00:34:57,994][62408] Updated weights for policy 1, policy_version 7900 (0.0008) -[2023-10-17 00:34:58,143][62373] Updated weights for policy 0, policy_version 7950 (0.0007) -[2023-10-17 00:34:58,523][62373] Updated weights for policy 0, policy_version 7960 (0.0008) -[2023-10-17 00:35:01,670][62408] Updated weights for policy 1, policy_version 7910 (0.0008) -[2023-10-17 00:35:02,032][62408] Updated weights for policy 1, policy_version 7920 (0.0007) -[2023-10-17 00:35:02,194][62373] Updated weights for policy 0, policy_version 7970 (0.0009) -[2023-10-17 00:35:02,214][61453] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 16252928. Throughput: 0: 1796.1, 1: 1771.0. Samples: 4081962. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-17 00:35:02,215][61453] Avg episode reward: [(0, '4.220'), (1, '4.330')] -[2023-10-17 00:35:02,397][62408] Updated weights for policy 1, policy_version 7930 (0.0007) -[2023-10-17 00:35:02,553][62373] Updated weights for policy 0, policy_version 7980 (0.0008) -[2023-10-17 00:35:02,934][62373] Updated weights for policy 0, policy_version 7990 (0.0008) -[2023-10-17 00:35:03,296][62373] Updated weights for policy 0, policy_version 8000 (0.0008) -[2023-10-17 00:35:06,006][62408] Updated weights for policy 1, policy_version 7940 (0.0008) -[2023-10-17 00:35:06,378][62408] Updated weights for policy 1, policy_version 7950 (0.0008) -[2023-10-17 00:35:06,744][62408] Updated weights for policy 1, policy_version 7960 (0.0008) -[2023-10-17 00:35:07,182][62373] Updated weights for policy 0, policy_version 8010 (0.0008) -[2023-10-17 00:35:07,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 16351232. Throughput: 0: 1773.7, 1: 1757.7. Samples: 4091978. Policy #0 lag: (min: 1.0, avg: 11.4, max: 33.0) -[2023-10-17 00:35:07,215][61453] Avg episode reward: [(0, '4.370'), (1, '4.120')] -[2023-10-17 00:35:07,553][62373] Updated weights for policy 0, policy_version 8020 (0.0008) -[2023-10-17 00:35:07,933][62373] Updated weights for policy 0, policy_version 8030 (0.0007) -[2023-10-17 00:35:10,626][62408] Updated weights for policy 1, policy_version 7970 (0.0009) -[2023-10-17 00:35:10,999][62408] Updated weights for policy 1, policy_version 7980 (0.0009) -[2023-10-17 00:35:11,373][62408] Updated weights for policy 1, policy_version 7990 (0.0009) -[2023-10-17 00:35:11,708][62373] Updated weights for policy 0, policy_version 8040 (0.0007) -[2023-10-17 00:35:11,740][62408] Updated weights for policy 1, policy_version 8000 (0.0010) -[2023-10-17 00:35:12,082][62373] Updated weights for policy 0, policy_version 8050 (0.0007) -[2023-10-17 00:35:12,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 16416768. Throughput: 0: 1788.9, 1: 1775.2. Samples: 4113672. Policy #0 lag: (min: 1.0, avg: 11.4, max: 33.0) -[2023-10-17 00:35:12,215][61453] Avg episode reward: [(0, '4.380'), (1, '3.920')] -[2023-10-17 00:35:12,449][62373] Updated weights for policy 0, policy_version 8060 (0.0009) -[2023-10-17 00:35:15,539][62408] Updated weights for policy 1, policy_version 8010 (0.0009) -[2023-10-17 00:35:15,905][62408] Updated weights for policy 1, policy_version 8020 (0.0010) -[2023-10-17 00:35:16,205][62373] Updated weights for policy 0, policy_version 8070 (0.0008) -[2023-10-17 00:35:16,281][62408] Updated weights for policy 1, policy_version 8030 (0.0008) -[2023-10-17 00:35:16,581][62373] Updated weights for policy 0, policy_version 8080 (0.0009) -[2023-10-17 00:35:16,956][62373] Updated weights for policy 0, policy_version 8090 (0.0008) -[2023-10-17 00:35:17,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 16515072. Throughput: 0: 1775.6, 1: 1754.8. Samples: 4133514. Policy #0 lag: (min: 21.0, avg: 24.2, max: 53.0) -[2023-10-17 00:35:17,215][61453] Avg episode reward: [(0, '4.160'), (1, '4.240')] -[2023-10-17 00:35:20,277][62408] Updated weights for policy 1, policy_version 8040 (0.0010) -[2023-10-17 00:35:20,621][62373] Updated weights for policy 0, policy_version 8100 (0.0009) -[2023-10-17 00:35:20,662][62408] Updated weights for policy 1, policy_version 8050 (0.0009) -[2023-10-17 00:35:20,992][62373] Updated weights for policy 0, policy_version 8110 (0.0009) -[2023-10-17 00:35:21,031][62408] Updated weights for policy 1, policy_version 8060 (0.0009) -[2023-10-17 00:35:21,356][62373] Updated weights for policy 0, policy_version 8120 (0.0007) -[2023-10-17 00:35:22,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 16580608. Throughput: 0: 1779.0, 1: 1791.7. Samples: 4145882. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-17 00:35:22,215][61453] Avg episode reward: [(0, '4.150'), (1, '3.990')] -[2023-10-17 00:35:24,744][62408] Updated weights for policy 1, policy_version 8070 (0.0007) -[2023-10-17 00:35:25,117][62408] Updated weights for policy 1, policy_version 8080 (0.0008) -[2023-10-17 00:35:25,228][62373] Updated weights for policy 0, policy_version 8130 (0.0008) -[2023-10-17 00:35:25,482][62408] Updated weights for policy 1, policy_version 8090 (0.0007) -[2023-10-17 00:35:25,593][62373] Updated weights for policy 0, policy_version 8140 (0.0007) -[2023-10-17 00:35:25,957][62373] Updated weights for policy 0, policy_version 8150 (0.0007) -[2023-10-17 00:35:26,339][62373] Updated weights for policy 0, policy_version 8160 (0.0007) -[2023-10-17 00:35:27,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 16646144. Throughput: 0: 1784.1, 1: 1753.9. Samples: 4165554. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-17 00:35:27,215][61453] Avg episode reward: [(0, '4.250'), (1, '3.980')] -[2023-10-17 00:35:29,439][62408] Updated weights for policy 1, policy_version 8100 (0.0008) -[2023-10-17 00:35:29,812][62408] Updated weights for policy 1, policy_version 8110 (0.0007) -[2023-10-17 00:35:30,108][62373] Updated weights for policy 0, policy_version 8170 (0.0008) -[2023-10-17 00:35:30,189][62408] Updated weights for policy 1, policy_version 8120 (0.0007) -[2023-10-17 00:35:30,482][62373] Updated weights for policy 0, policy_version 8180 (0.0008) -[2023-10-17 00:35:30,845][62373] Updated weights for policy 0, policy_version 8190 (0.0010) -[2023-10-17 00:35:32,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 16711680. Throughput: 0: 1772.2, 1: 1752.2. Samples: 4187040. Policy #0 lag: (min: 15.0, avg: 18.0, max: 47.0) -[2023-10-17 00:35:32,214][61453] Avg episode reward: [(0, '4.160'), (1, '3.670')] -[2023-10-17 00:35:32,227][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000008128_8323072.pth... -[2023-10-17 00:35:32,227][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000008192_8388608.pth... -[2023-10-17 00:35:32,262][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000006528_6684672.pth -[2023-10-17 00:35:32,265][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000006496_6651904.pth -[2023-10-17 00:35:32,266][62094] Saving a milestone ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/milestones/checkpoint_000008192_8388608.pth -[2023-10-17 00:35:32,270][62252] Saving a milestone ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/milestones/checkpoint_000008128_8323072.pth -[2023-10-17 00:35:34,097][62408] Updated weights for policy 1, policy_version 8130 (0.0008) -[2023-10-17 00:35:34,457][62408] Updated weights for policy 1, policy_version 8140 (0.0009) -[2023-10-17 00:35:34,730][62373] Updated weights for policy 0, policy_version 8200 (0.0008) -[2023-10-17 00:35:34,831][62408] Updated weights for policy 1, policy_version 8150 (0.0008) -[2023-10-17 00:35:35,099][62373] Updated weights for policy 0, policy_version 8210 (0.0007) -[2023-10-17 00:35:35,199][62408] Updated weights for policy 1, policy_version 8160 (0.0008) -[2023-10-17 00:35:35,458][62373] Updated weights for policy 0, policy_version 8220 (0.0008) -[2023-10-17 00:35:37,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 16777216. Throughput: 0: 1787.2, 1: 1759.1. Samples: 4197774. Policy #0 lag: (min: 15.0, avg: 18.0, max: 47.0) -[2023-10-17 00:35:37,215][61453] Avg episode reward: [(0, '4.150'), (1, '3.650')] -[2023-10-17 00:35:39,106][62408] Updated weights for policy 1, policy_version 8170 (0.0010) -[2023-10-17 00:35:39,293][62373] Updated weights for policy 0, policy_version 8230 (0.0008) -[2023-10-17 00:35:39,477][62408] Updated weights for policy 1, policy_version 8180 (0.0008) -[2023-10-17 00:35:39,660][62373] Updated weights for policy 0, policy_version 8240 (0.0008) -[2023-10-17 00:35:39,842][62408] Updated weights for policy 1, policy_version 8190 (0.0008) -[2023-10-17 00:35:40,024][62373] Updated weights for policy 0, policy_version 8250 (0.0010) -[2023-10-17 00:35:42,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 16842752. Throughput: 0: 1771.2, 1: 1748.7. Samples: 4218554. Policy #0 lag: (min: 30.0, avg: 30.4, max: 44.0) -[2023-10-17 00:35:42,214][61453] Avg episode reward: [(0, '4.260'), (1, '3.710')] -[2023-10-17 00:35:43,567][62408] Updated weights for policy 1, policy_version 8200 (0.0010) -[2023-10-17 00:35:43,896][62373] Updated weights for policy 0, policy_version 8260 (0.0009) -[2023-10-17 00:35:43,938][62408] Updated weights for policy 1, policy_version 8210 (0.0008) -[2023-10-17 00:35:44,259][62373] Updated weights for policy 0, policy_version 8270 (0.0008) -[2023-10-17 00:35:44,307][62408] Updated weights for policy 1, policy_version 8220 (0.0008) -[2023-10-17 00:35:44,630][62373] Updated weights for policy 0, policy_version 8280 (0.0007) -[2023-10-17 00:35:47,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 16908288. Throughput: 0: 1769.6, 1: 1761.8. Samples: 4240878. Policy #0 lag: (min: 30.0, avg: 30.4, max: 44.0) -[2023-10-17 00:35:47,216][61453] Avg episode reward: [(0, '4.120'), (1, '4.130')] -[2023-10-17 00:35:48,070][62408] Updated weights for policy 1, policy_version 8230 (0.0007) -[2023-10-17 00:35:48,410][62373] Updated weights for policy 0, policy_version 8290 (0.0007) -[2023-10-17 00:35:48,437][62408] Updated weights for policy 1, policy_version 8240 (0.0008) -[2023-10-17 00:35:48,776][62373] Updated weights for policy 0, policy_version 8300 (0.0008) -[2023-10-17 00:35:48,800][62408] Updated weights for policy 1, policy_version 8250 (0.0009) -[2023-10-17 00:35:49,148][62373] Updated weights for policy 0, policy_version 8310 (0.0008) -[2023-10-17 00:35:49,520][62373] Updated weights for policy 0, policy_version 8320 (0.0007) -[2023-10-17 00:35:52,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 16973824. Throughput: 0: 1774.5, 1: 1751.0. Samples: 4250626. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:35:52,215][61453] Avg episode reward: [(0, '4.140'), (1, '4.010')] -[2023-10-17 00:35:52,621][62408] Updated weights for policy 1, policy_version 8260 (0.0008) -[2023-10-17 00:35:52,999][62408] Updated weights for policy 1, policy_version 8270 (0.0008) -[2023-10-17 00:35:53,183][62373] Updated weights for policy 0, policy_version 8330 (0.0008) -[2023-10-17 00:35:53,372][62408] Updated weights for policy 1, policy_version 8280 (0.0008) -[2023-10-17 00:35:53,548][62373] Updated weights for policy 0, policy_version 8340 (0.0010) -[2023-10-17 00:35:53,914][62373] Updated weights for policy 0, policy_version 8350 (0.0009) -[2023-10-17 00:35:57,214][61453] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 17039360. Throughput: 0: 1772.4, 1: 1758.2. Samples: 4272552. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:35:57,214][61453] Avg episode reward: [(0, '4.330'), (1, '4.370')] -[2023-10-17 00:35:57,374][62408] Updated weights for policy 1, policy_version 8290 (0.0008) -[2023-10-17 00:35:57,741][62408] Updated weights for policy 1, policy_version 8300 (0.0007) -[2023-10-17 00:35:57,808][62373] Updated weights for policy 0, policy_version 8360 (0.0008) -[2023-10-17 00:35:58,108][62408] Updated weights for policy 1, policy_version 8310 (0.0008) -[2023-10-17 00:35:58,180][62373] Updated weights for policy 0, policy_version 8370 (0.0009) -[2023-10-17 00:35:58,477][62408] Updated weights for policy 1, policy_version 8320 (0.0009) -[2023-10-17 00:35:58,562][62373] Updated weights for policy 0, policy_version 8380 (0.0008) -[2023-10-17 00:36:02,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 17104896. Throughput: 0: 1792.2, 1: 1777.2. Samples: 4294136. Policy #0 lag: (min: 31.0, avg: 33.1, max: 61.0) -[2023-10-17 00:36:02,215][61453] Avg episode reward: [(0, '4.320'), (1, '4.440')] -[2023-10-17 00:36:02,401][62408] Updated weights for policy 1, policy_version 8330 (0.0009) -[2023-10-17 00:36:02,409][62373] Updated weights for policy 0, policy_version 8390 (0.0010) -[2023-10-17 00:36:02,777][62408] Updated weights for policy 1, policy_version 8340 (0.0010) -[2023-10-17 00:36:02,782][62373] Updated weights for policy 0, policy_version 8400 (0.0008) -[2023-10-17 00:36:03,136][62408] Updated weights for policy 1, policy_version 8350 (0.0008) -[2023-10-17 00:36:03,146][62373] Updated weights for policy 0, policy_version 8410 (0.0008) -[2023-10-17 00:36:06,965][62373] Updated weights for policy 0, policy_version 8420 (0.0007) -[2023-10-17 00:36:07,188][62408] Updated weights for policy 1, policy_version 8360 (0.0009) -[2023-10-17 00:36:07,214][61453] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 17170432. Throughput: 0: 1765.9, 1: 1738.5. Samples: 4303576. Policy #0 lag: (min: 31.0, avg: 33.1, max: 61.0) -[2023-10-17 00:36:07,214][61453] Avg episode reward: [(0, '4.140'), (1, '4.450')] -[2023-10-17 00:36:07,343][62373] Updated weights for policy 0, policy_version 8430 (0.0009) -[2023-10-17 00:36:07,565][62408] Updated weights for policy 1, policy_version 8370 (0.0008) -[2023-10-17 00:36:07,722][62373] Updated weights for policy 0, policy_version 8440 (0.0009) -[2023-10-17 00:36:07,930][62408] Updated weights for policy 1, policy_version 8380 (0.0008) -[2023-10-17 00:36:11,542][62373] Updated weights for policy 0, policy_version 8450 (0.0008) -[2023-10-17 00:36:11,835][62408] Updated weights for policy 1, policy_version 8390 (0.0008) -[2023-10-17 00:36:11,909][62373] Updated weights for policy 0, policy_version 8460 (0.0007) -[2023-10-17 00:36:12,207][62408] Updated weights for policy 1, policy_version 8400 (0.0008) -[2023-10-17 00:36:12,214][61453] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 17235968. Throughput: 0: 1778.9, 1: 1762.7. Samples: 4324926. Policy #0 lag: (min: 21.0, avg: 28.0, max: 53.0) -[2023-10-17 00:36:12,216][61453] Avg episode reward: [(0, '4.360'), (1, '4.260')] -[2023-10-17 00:36:12,284][62373] Updated weights for policy 0, policy_version 8470 (0.0009) -[2023-10-17 00:36:12,580][62408] Updated weights for policy 1, policy_version 8410 (0.0008) -[2023-10-17 00:36:12,650][62373] Updated weights for policy 0, policy_version 8480 (0.0007) -[2023-10-17 00:36:16,292][62408] Updated weights for policy 1, policy_version 8420 (0.0007) -[2023-10-17 00:36:16,529][62373] Updated weights for policy 0, policy_version 8490 (0.0011) -[2023-10-17 00:36:16,661][62408] Updated weights for policy 1, policy_version 8430 (0.0008) -[2023-10-17 00:36:16,890][62373] Updated weights for policy 0, policy_version 8500 (0.0010) -[2023-10-17 00:36:17,032][62408] Updated weights for policy 1, policy_version 8440 (0.0007) -[2023-10-17 00:36:17,214][61453] Fps is (10 sec: 13107.0, 60 sec: 13107.2, 300 sec: 14106.9). Total num frames: 17301504. Throughput: 0: 1770.4, 1: 1748.6. Samples: 4345394. Policy #0 lag: (min: 21.0, avg: 28.0, max: 53.0) -[2023-10-17 00:36:17,215][61453] Avg episode reward: [(0, '4.020'), (1, '4.260')] -[2023-10-17 00:36:17,269][62373] Updated weights for policy 0, policy_version 8510 (0.0007) -[2023-10-17 00:36:20,727][62408] Updated weights for policy 1, policy_version 8450 (0.0008) -[2023-10-17 00:36:21,051][62373] Updated weights for policy 0, policy_version 8520 (0.0008) -[2023-10-17 00:36:21,093][62408] Updated weights for policy 1, policy_version 8460 (0.0008) -[2023-10-17 00:36:21,427][62373] Updated weights for policy 0, policy_version 8530 (0.0010) -[2023-10-17 00:36:21,467][62408] Updated weights for policy 1, policy_version 8470 (0.0009) -[2023-10-17 00:36:21,794][62373] Updated weights for policy 0, policy_version 8540 (0.0008) -[2023-10-17 00:36:21,831][62408] Updated weights for policy 1, policy_version 8480 (0.0007) -[2023-10-17 00:36:22,214][61453] Fps is (10 sec: 19661.4, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 17432576. Throughput: 0: 1775.4, 1: 1761.1. Samples: 4356916. Policy #0 lag: (min: 26.0, avg: 26.4, max: 39.0) -[2023-10-17 00:36:22,215][61453] Avg episode reward: [(0, '3.890'), (1, '3.960')] -[2023-10-17 00:36:25,555][62408] Updated weights for policy 1, policy_version 8490 (0.0008) -[2023-10-17 00:36:25,676][62373] Updated weights for policy 0, policy_version 8550 (0.0008) -[2023-10-17 00:36:25,917][62408] Updated weights for policy 1, policy_version 8500 (0.0008) -[2023-10-17 00:36:26,035][62373] Updated weights for policy 0, policy_version 8560 (0.0008) -[2023-10-17 00:36:26,293][62408] Updated weights for policy 1, policy_version 8510 (0.0008) -[2023-10-17 00:36:26,405][62373] Updated weights for policy 0, policy_version 8570 (0.0010) -[2023-10-17 00:36:27,214][61453] Fps is (10 sec: 19660.8, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 17498112. Throughput: 0: 1776.8, 1: 1758.2. Samples: 4377632. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-17 00:36:27,215][61453] Avg episode reward: [(0, '3.760'), (1, '4.240')] -[2023-10-17 00:36:30,293][62408] Updated weights for policy 1, policy_version 8520 (0.0008) -[2023-10-17 00:36:30,298][62373] Updated weights for policy 0, policy_version 8580 (0.0008) -[2023-10-17 00:36:30,660][62408] Updated weights for policy 1, policy_version 8530 (0.0007) -[2023-10-17 00:36:30,674][62373] Updated weights for policy 0, policy_version 8590 (0.0008) -[2023-10-17 00:36:31,026][62408] Updated weights for policy 1, policy_version 8540 (0.0009) -[2023-10-17 00:36:31,030][62373] Updated weights for policy 0, policy_version 8600 (0.0009) -[2023-10-17 00:36:32,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 17563648. Throughput: 0: 1749.8, 1: 1738.5. Samples: 4397848. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-17 00:36:32,215][61453] Avg episode reward: [(0, '4.030'), (1, '4.010')] -[2023-10-17 00:36:34,772][62408] Updated weights for policy 1, policy_version 8550 (0.0008) -[2023-10-17 00:36:34,858][62373] Updated weights for policy 0, policy_version 8610 (0.0008) -[2023-10-17 00:36:35,143][62408] Updated weights for policy 1, policy_version 8560 (0.0009) -[2023-10-17 00:36:35,223][62373] Updated weights for policy 0, policy_version 8620 (0.0008) -[2023-10-17 00:36:35,509][62408] Updated weights for policy 1, policy_version 8570 (0.0009) -[2023-10-17 00:36:35,591][62373] Updated weights for policy 0, policy_version 8630 (0.0007) -[2023-10-17 00:36:35,965][62373] Updated weights for policy 0, policy_version 8640 (0.0010) -[2023-10-17 00:36:37,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 17629184. Throughput: 0: 1772.4, 1: 1762.8. Samples: 4409710. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-17 00:36:37,215][61453] Avg episode reward: [(0, '3.750'), (1, '4.100')] -[2023-10-17 00:36:39,477][62408] Updated weights for policy 1, policy_version 8580 (0.0009) -[2023-10-17 00:36:39,854][62408] Updated weights for policy 1, policy_version 8590 (0.0008) -[2023-10-17 00:36:39,879][62373] Updated weights for policy 0, policy_version 8650 (0.0008) -[2023-10-17 00:36:40,225][62408] Updated weights for policy 1, policy_version 8600 (0.0009) -[2023-10-17 00:36:40,242][62373] Updated weights for policy 0, policy_version 8660 (0.0008) -[2023-10-17 00:36:40,614][62373] Updated weights for policy 0, policy_version 8670 (0.0009) -[2023-10-17 00:36:42,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 17694720. Throughput: 0: 1739.6, 1: 1736.4. Samples: 4428968. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-17 00:36:42,215][61453] Avg episode reward: [(0, '4.070'), (1, '4.290')] -[2023-10-17 00:36:44,188][62408] Updated weights for policy 1, policy_version 8610 (0.0008) -[2023-10-17 00:36:44,554][62408] Updated weights for policy 1, policy_version 8620 (0.0008) -[2023-10-17 00:36:44,604][62373] Updated weights for policy 0, policy_version 8680 (0.0008) -[2023-10-17 00:36:44,922][62408] Updated weights for policy 1, policy_version 8630 (0.0008) -[2023-10-17 00:36:44,982][62373] Updated weights for policy 0, policy_version 8690 (0.0010) -[2023-10-17 00:36:45,291][62408] Updated weights for policy 1, policy_version 8640 (0.0008) -[2023-10-17 00:36:45,339][62373] Updated weights for policy 0, policy_version 8700 (0.0008) -[2023-10-17 00:36:47,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 17760256. Throughput: 0: 1737.9, 1: 1733.3. Samples: 4450342. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-17 00:36:47,216][61453] Avg episode reward: [(0, '4.050'), (1, '4.250')] -[2023-10-17 00:36:49,206][62373] Updated weights for policy 0, policy_version 8710 (0.0008) -[2023-10-17 00:36:49,239][62408] Updated weights for policy 1, policy_version 8650 (0.0008) -[2023-10-17 00:36:49,572][62373] Updated weights for policy 0, policy_version 8720 (0.0009) -[2023-10-17 00:36:49,607][62408] Updated weights for policy 1, policy_version 8660 (0.0008) -[2023-10-17 00:36:49,948][62373] Updated weights for policy 0, policy_version 8730 (0.0008) -[2023-10-17 00:36:49,973][62408] Updated weights for policy 1, policy_version 8670 (0.0008) -[2023-10-17 00:36:52,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 17825792. Throughput: 0: 1745.1, 1: 1738.3. Samples: 4460332. Policy #0 lag: (min: 15.0, avg: 15.0, max: 15.0) -[2023-10-17 00:36:52,215][61453] Avg episode reward: [(0, '4.140'), (1, '4.070')] -[2023-10-17 00:36:53,752][62373] Updated weights for policy 0, policy_version 8740 (0.0007) -[2023-10-17 00:36:53,864][62408] Updated weights for policy 1, policy_version 8680 (0.0009) -[2023-10-17 00:36:54,122][62373] Updated weights for policy 0, policy_version 8750 (0.0007) -[2023-10-17 00:36:54,240][62408] Updated weights for policy 1, policy_version 8690 (0.0010) -[2023-10-17 00:36:54,498][62373] Updated weights for policy 0, policy_version 8760 (0.0007) -[2023-10-17 00:36:54,622][62408] Updated weights for policy 1, policy_version 8700 (0.0008) -[2023-10-17 00:36:57,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 17891328. Throughput: 0: 1742.2, 1: 1741.8. Samples: 4481704. Policy #0 lag: (min: 9.0, avg: 21.6, max: 41.0) -[2023-10-17 00:36:57,215][61453] Avg episode reward: [(0, '3.900'), (1, '4.530')] -[2023-10-17 00:36:58,193][62408] Updated weights for policy 1, policy_version 8710 (0.0007) -[2023-10-17 00:36:58,319][62373] Updated weights for policy 0, policy_version 8770 (0.0009) -[2023-10-17 00:36:58,556][62408] Updated weights for policy 1, policy_version 8720 (0.0008) -[2023-10-17 00:36:58,691][62373] Updated weights for policy 0, policy_version 8780 (0.0008) -[2023-10-17 00:36:58,929][62408] Updated weights for policy 1, policy_version 8730 (0.0007) -[2023-10-17 00:36:59,058][62373] Updated weights for policy 0, policy_version 8790 (0.0008) -[2023-10-17 00:36:59,419][62373] Updated weights for policy 0, policy_version 8800 (0.0008) -[2023-10-17 00:37:02,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 17956864. Throughput: 0: 1763.3, 1: 1754.8. Samples: 4503708. Policy #0 lag: (min: 9.0, avg: 21.6, max: 41.0) -[2023-10-17 00:37:02,216][61453] Avg episode reward: [(0, '4.120'), (1, '4.620')] -[2023-10-17 00:37:02,798][62408] Updated weights for policy 1, policy_version 8740 (0.0008) -[2023-10-17 00:37:03,179][62408] Updated weights for policy 1, policy_version 8750 (0.0007) -[2023-10-17 00:37:03,263][62373] Updated weights for policy 0, policy_version 8810 (0.0008) -[2023-10-17 00:37:03,542][62408] Updated weights for policy 1, policy_version 8760 (0.0008) -[2023-10-17 00:37:03,631][62373] Updated weights for policy 0, policy_version 8820 (0.0009) -[2023-10-17 00:37:04,001][62373] Updated weights for policy 0, policy_version 8830 (0.0010) -[2023-10-17 00:37:07,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 18022400. Throughput: 0: 1738.9, 1: 1734.5. Samples: 4513218. Policy #0 lag: (min: 31.0, avg: 32.4, max: 54.0) -[2023-10-17 00:37:07,215][61453] Avg episode reward: [(0, '4.230'), (1, '4.450')] -[2023-10-17 00:37:07,393][62408] Updated weights for policy 1, policy_version 8770 (0.0008) -[2023-10-17 00:37:07,753][62408] Updated weights for policy 1, policy_version 8780 (0.0009) -[2023-10-17 00:37:07,952][62373] Updated weights for policy 0, policy_version 8840 (0.0008) -[2023-10-17 00:37:08,120][62408] Updated weights for policy 1, policy_version 8790 (0.0008) -[2023-10-17 00:37:08,319][62373] Updated weights for policy 0, policy_version 8850 (0.0008) -[2023-10-17 00:37:08,486][62408] Updated weights for policy 1, policy_version 8800 (0.0008) -[2023-10-17 00:37:08,694][62373] Updated weights for policy 0, policy_version 8860 (0.0009) -[2023-10-17 00:37:12,214][61453] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 18087936. Throughput: 0: 1748.3, 1: 1753.7. Samples: 4535222. Policy #0 lag: (min: 31.0, avg: 32.4, max: 54.0) -[2023-10-17 00:37:12,215][61453] Avg episode reward: [(0, '4.160'), (1, '4.270')] -[2023-10-17 00:37:12,226][62408] Updated weights for policy 1, policy_version 8810 (0.0008) -[2023-10-17 00:37:12,442][62373] Updated weights for policy 0, policy_version 8870 (0.0008) -[2023-10-17 00:37:12,595][62408] Updated weights for policy 1, policy_version 8820 (0.0007) -[2023-10-17 00:37:12,817][62373] Updated weights for policy 0, policy_version 8880 (0.0008) -[2023-10-17 00:37:12,970][62408] Updated weights for policy 1, policy_version 8830 (0.0009) -[2023-10-17 00:37:13,185][62373] Updated weights for policy 0, policy_version 8890 (0.0007) -[2023-10-17 00:37:16,815][62408] Updated weights for policy 1, policy_version 8840 (0.0008) -[2023-10-17 00:37:17,040][62373] Updated weights for policy 0, policy_version 8900 (0.0008) -[2023-10-17 00:37:17,180][62408] Updated weights for policy 1, policy_version 8850 (0.0009) -[2023-10-17 00:37:17,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 18153472. Throughput: 0: 1774.1, 1: 1764.4. Samples: 4557082. Policy #0 lag: (min: 17.0, avg: 24.4, max: 49.0) -[2023-10-17 00:37:17,215][61453] Avg episode reward: [(0, '4.160'), (1, '4.420')] -[2023-10-17 00:37:17,410][62373] Updated weights for policy 0, policy_version 8910 (0.0008) -[2023-10-17 00:37:17,551][62408] Updated weights for policy 1, policy_version 8860 (0.0008) -[2023-10-17 00:37:17,779][62373] Updated weights for policy 0, policy_version 8920 (0.0008) -[2023-10-17 00:37:21,480][62408] Updated weights for policy 1, policy_version 8870 (0.0007) -[2023-10-17 00:37:21,594][62373] Updated weights for policy 0, policy_version 8930 (0.0008) -[2023-10-17 00:37:21,853][62408] Updated weights for policy 1, policy_version 8880 (0.0007) -[2023-10-17 00:37:21,969][62373] Updated weights for policy 0, policy_version 8940 (0.0008) -[2023-10-17 00:37:22,214][61453] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 14106.9). Total num frames: 18219008. Throughput: 0: 1752.1, 1: 1747.1. Samples: 4567172. Policy #0 lag: (min: 17.0, avg: 24.4, max: 49.0) -[2023-10-17 00:37:22,214][61453] Avg episode reward: [(0, '3.780'), (1, '4.200')] -[2023-10-17 00:37:22,220][62408] Updated weights for policy 1, policy_version 8890 (0.0009) -[2023-10-17 00:37:22,344][62373] Updated weights for policy 0, policy_version 8950 (0.0008) -[2023-10-17 00:37:22,713][62373] Updated weights for policy 0, policy_version 8960 (0.0008) -[2023-10-17 00:37:26,162][62408] Updated weights for policy 1, policy_version 8900 (0.0008) -[2023-10-17 00:37:26,376][62373] Updated weights for policy 0, policy_version 8970 (0.0007) -[2023-10-17 00:37:26,521][62408] Updated weights for policy 1, policy_version 8910 (0.0009) -[2023-10-17 00:37:26,752][62373] Updated weights for policy 0, policy_version 8980 (0.0008) -[2023-10-17 00:37:26,890][62408] Updated weights for policy 1, policy_version 8920 (0.0009) -[2023-10-17 00:37:27,123][62373] Updated weights for policy 0, policy_version 8990 (0.0008) -[2023-10-17 00:37:27,214][61453] Fps is (10 sec: 19661.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 18350080. Throughput: 0: 1785.7, 1: 1773.0. Samples: 4589112. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:37:27,214][61453] Avg episode reward: [(0, '3.800'), (1, '4.050')] -[2023-10-17 00:37:30,583][62408] Updated weights for policy 1, policy_version 8930 (0.0008) -[2023-10-17 00:37:30,931][62373] Updated weights for policy 0, policy_version 9000 (0.0008) -[2023-10-17 00:37:30,951][62408] Updated weights for policy 1, policy_version 8940 (0.0010) -[2023-10-17 00:37:31,306][62373] Updated weights for policy 0, policy_version 9010 (0.0007) -[2023-10-17 00:37:31,322][62408] Updated weights for policy 1, policy_version 8950 (0.0007) -[2023-10-17 00:37:31,677][62373] Updated weights for policy 0, policy_version 9020 (0.0008) -[2023-10-17 00:37:31,687][62408] Updated weights for policy 1, policy_version 8960 (0.0007) -[2023-10-17 00:37:32,214][61453] Fps is (10 sec: 19660.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 18415616. Throughput: 0: 1760.5, 1: 1749.2. Samples: 4608278. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-10-17 00:37:32,215][61453] Avg episode reward: [(0, '4.120'), (1, '4.500')] -[2023-10-17 00:37:32,224][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000008960_9175040.pth... -[2023-10-17 00:37:32,224][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000009024_9240576.pth... -[2023-10-17 00:37:32,262][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000007360_7536640.pth -[2023-10-17 00:37:32,265][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000007296_7471104.pth -[2023-10-17 00:37:35,589][62408] Updated weights for policy 1, policy_version 8970 (0.0010) -[2023-10-17 00:37:35,620][62373] Updated weights for policy 0, policy_version 9030 (0.0009) -[2023-10-17 00:37:35,958][62408] Updated weights for policy 1, policy_version 8980 (0.0008) -[2023-10-17 00:37:35,988][62373] Updated weights for policy 0, policy_version 9040 (0.0007) -[2023-10-17 00:37:36,323][62408] Updated weights for policy 1, policy_version 8990 (0.0009) -[2023-10-17 00:37:36,351][62373] Updated weights for policy 0, policy_version 9050 (0.0008) -[2023-10-17 00:37:37,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 18481152. Throughput: 0: 1784.4, 1: 1779.1. Samples: 4620686. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-10-17 00:37:37,214][61453] Avg episode reward: [(0, '4.070'), (1, '4.420')] -[2023-10-17 00:37:40,054][62373] Updated weights for policy 0, policy_version 9060 (0.0008) -[2023-10-17 00:37:40,345][62408] Updated weights for policy 1, policy_version 9000 (0.0007) -[2023-10-17 00:37:40,420][62373] Updated weights for policy 0, policy_version 9070 (0.0007) -[2023-10-17 00:37:40,723][62408] Updated weights for policy 1, policy_version 9010 (0.0008) -[2023-10-17 00:37:40,797][62373] Updated weights for policy 0, policy_version 9080 (0.0007) -[2023-10-17 00:37:41,091][62408] Updated weights for policy 1, policy_version 9020 (0.0008) -[2023-10-17 00:37:42,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 18546688. Throughput: 0: 1766.2, 1: 1757.5. Samples: 4640270. Policy #0 lag: (min: 26.0, avg: 38.8, max: 58.0) -[2023-10-17 00:37:42,214][61453] Avg episode reward: [(0, '4.590'), (1, '4.790')] -[2023-10-17 00:37:42,215][62252] Saving new best policy, reward=4.790! -[2023-10-17 00:37:44,735][62373] Updated weights for policy 0, policy_version 9090 (0.0007) -[2023-10-17 00:37:44,990][62408] Updated weights for policy 1, policy_version 9030 (0.0008) -[2023-10-17 00:37:45,099][62373] Updated weights for policy 0, policy_version 9100 (0.0007) -[2023-10-17 00:37:45,355][62408] Updated weights for policy 1, policy_version 9040 (0.0007) -[2023-10-17 00:37:45,476][62373] Updated weights for policy 0, policy_version 9110 (0.0007) -[2023-10-17 00:37:45,715][62408] Updated weights for policy 1, policy_version 9050 (0.0008) -[2023-10-17 00:37:45,835][62373] Updated weights for policy 0, policy_version 9120 (0.0008) -[2023-10-17 00:37:47,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 18612224. Throughput: 0: 1755.4, 1: 1746.0. Samples: 4661268. Policy #0 lag: (min: 26.0, avg: 38.8, max: 58.0) -[2023-10-17 00:37:47,214][61453] Avg episode reward: [(0, '4.340'), (1, '4.690')] -[2023-10-17 00:37:49,615][62408] Updated weights for policy 1, policy_version 9060 (0.0008) -[2023-10-17 00:37:49,682][62373] Updated weights for policy 0, policy_version 9130 (0.0008) -[2023-10-17 00:37:49,977][62408] Updated weights for policy 1, policy_version 9070 (0.0009) -[2023-10-17 00:37:50,047][62373] Updated weights for policy 0, policy_version 9140 (0.0009) -[2023-10-17 00:37:50,350][62408] Updated weights for policy 1, policy_version 9080 (0.0009) -[2023-10-17 00:37:50,415][62373] Updated weights for policy 0, policy_version 9150 (0.0009) -[2023-10-17 00:37:52,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 18677760. Throughput: 0: 1774.5, 1: 1766.7. Samples: 4672576. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:37:52,215][61453] Avg episode reward: [(0, '4.400'), (1, '4.500')] -[2023-10-17 00:37:54,102][62408] Updated weights for policy 1, policy_version 9090 (0.0009) -[2023-10-17 00:37:54,284][62373] Updated weights for policy 0, policy_version 9160 (0.0010) -[2023-10-17 00:37:54,478][62408] Updated weights for policy 1, policy_version 9100 (0.0009) -[2023-10-17 00:37:54,655][62373] Updated weights for policy 0, policy_version 9170 (0.0009) -[2023-10-17 00:37:54,846][62408] Updated weights for policy 1, policy_version 9110 (0.0008) -[2023-10-17 00:37:55,023][62373] Updated weights for policy 0, policy_version 9180 (0.0008) -[2023-10-17 00:37:55,208][62408] Updated weights for policy 1, policy_version 9120 (0.0008) -[2023-10-17 00:37:57,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 18743296. Throughput: 0: 1763.0, 1: 1742.8. Samples: 4692980. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:37:57,215][61453] Avg episode reward: [(0, '4.420'), (1, '4.130')] -[2023-10-17 00:37:58,706][62373] Updated weights for policy 0, policy_version 9190 (0.0008) -[2023-10-17 00:37:59,067][62373] Updated weights for policy 0, policy_version 9200 (0.0007) -[2023-10-17 00:37:59,129][62408] Updated weights for policy 1, policy_version 9130 (0.0009) -[2023-10-17 00:37:59,441][62373] Updated weights for policy 0, policy_version 9210 (0.0008) -[2023-10-17 00:37:59,494][62408] Updated weights for policy 1, policy_version 9140 (0.0009) -[2023-10-17 00:37:59,852][62408] Updated weights for policy 1, policy_version 9150 (0.0007) -[2023-10-17 00:38:02,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.6, 300 sec: 14106.9). Total num frames: 18808832. Throughput: 0: 1765.4, 1: 1742.1. Samples: 4714920. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:38:02,215][61453] Avg episode reward: [(0, '4.380'), (1, '4.360')] -[2023-10-17 00:38:03,115][62373] Updated weights for policy 0, policy_version 9220 (0.0008) -[2023-10-17 00:38:03,483][62373] Updated weights for policy 0, policy_version 9230 (0.0011) -[2023-10-17 00:38:03,738][62408] Updated weights for policy 1, policy_version 9160 (0.0007) -[2023-10-17 00:38:03,846][62373] Updated weights for policy 0, policy_version 9240 (0.0007) -[2023-10-17 00:38:04,098][62408] Updated weights for policy 1, policy_version 9170 (0.0007) -[2023-10-17 00:38:04,470][62408] Updated weights for policy 1, policy_version 9180 (0.0009) -[2023-10-17 00:38:07,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 18874368. Throughput: 0: 1766.5, 1: 1735.5. Samples: 4724762. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:38:07,215][61453] Avg episode reward: [(0, '4.450'), (1, '4.240')] -[2023-10-17 00:38:07,761][62373] Updated weights for policy 0, policy_version 9250 (0.0008) -[2023-10-17 00:38:08,132][62373] Updated weights for policy 0, policy_version 9260 (0.0008) -[2023-10-17 00:38:08,412][62408] Updated weights for policy 1, policy_version 9190 (0.0007) -[2023-10-17 00:38:08,503][62373] Updated weights for policy 0, policy_version 9270 (0.0007) -[2023-10-17 00:38:08,768][62408] Updated weights for policy 1, policy_version 9200 (0.0009) -[2023-10-17 00:38:08,873][62373] Updated weights for policy 0, policy_version 9280 (0.0007) -[2023-10-17 00:38:09,143][62408] Updated weights for policy 1, policy_version 9210 (0.0008) -[2023-10-17 00:38:12,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 18939904. Throughput: 0: 1762.4, 1: 1740.0. Samples: 4746722. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:38:12,214][61453] Avg episode reward: [(0, '4.240'), (1, '4.360')] -[2023-10-17 00:38:12,687][62373] Updated weights for policy 0, policy_version 9290 (0.0008) -[2023-10-17 00:38:13,002][62408] Updated weights for policy 1, policy_version 9220 (0.0008) -[2023-10-17 00:38:13,058][62373] Updated weights for policy 0, policy_version 9300 (0.0008) -[2023-10-17 00:38:13,371][62408] Updated weights for policy 1, policy_version 9230 (0.0007) -[2023-10-17 00:38:13,426][62373] Updated weights for policy 0, policy_version 9310 (0.0007) -[2023-10-17 00:38:13,735][62408] Updated weights for policy 1, policy_version 9240 (0.0008) -[2023-10-17 00:38:17,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 19005440. Throughput: 0: 1793.3, 1: 1775.4. Samples: 4768872. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:38:17,215][61453] Avg episode reward: [(0, '4.270'), (1, '4.460')] -[2023-10-17 00:38:17,351][62373] Updated weights for policy 0, policy_version 9320 (0.0007) -[2023-10-17 00:38:17,427][62408] Updated weights for policy 1, policy_version 9250 (0.0008) -[2023-10-17 00:38:17,727][62373] Updated weights for policy 0, policy_version 9330 (0.0007) -[2023-10-17 00:38:17,796][62408] Updated weights for policy 1, policy_version 9260 (0.0009) -[2023-10-17 00:38:18,101][62373] Updated weights for policy 0, policy_version 9340 (0.0007) -[2023-10-17 00:38:18,161][62408] Updated weights for policy 1, policy_version 9270 (0.0007) -[2023-10-17 00:38:18,529][62408] Updated weights for policy 1, policy_version 9280 (0.0007) -[2023-10-17 00:38:22,004][62373] Updated weights for policy 0, policy_version 9350 (0.0007) -[2023-10-17 00:38:22,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 19070976. Throughput: 0: 1758.8, 1: 1743.7. Samples: 4778298. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) -[2023-10-17 00:38:22,214][61453] Avg episode reward: [(0, '4.300'), (1, '4.690')] -[2023-10-17 00:38:22,374][62373] Updated weights for policy 0, policy_version 9360 (0.0007) -[2023-10-17 00:38:22,403][62408] Updated weights for policy 1, policy_version 9290 (0.0007) -[2023-10-17 00:38:22,734][62373] Updated weights for policy 0, policy_version 9370 (0.0007) -[2023-10-17 00:38:22,779][62408] Updated weights for policy 1, policy_version 9300 (0.0007) -[2023-10-17 00:38:23,146][62408] Updated weights for policy 1, policy_version 9310 (0.0010) -[2023-10-17 00:38:26,494][62373] Updated weights for policy 0, policy_version 9380 (0.0007) -[2023-10-17 00:38:26,863][62373] Updated weights for policy 0, policy_version 9390 (0.0008) -[2023-10-17 00:38:27,074][62408] Updated weights for policy 1, policy_version 9320 (0.0008) -[2023-10-17 00:38:27,214][61453] Fps is (10 sec: 13106.8, 60 sec: 13107.1, 300 sec: 13995.8). Total num frames: 19136512. Throughput: 0: 1783.8, 1: 1768.8. Samples: 4800140. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) -[2023-10-17 00:38:27,216][61453] Avg episode reward: [(0, '4.620'), (1, '4.450')] -[2023-10-17 00:38:27,236][62373] Updated weights for policy 0, policy_version 9400 (0.0007) -[2023-10-17 00:38:27,457][62408] Updated weights for policy 1, policy_version 9330 (0.0007) -[2023-10-17 00:38:27,825][62408] Updated weights for policy 1, policy_version 9340 (0.0007) -[2023-10-17 00:38:30,890][62373] Updated weights for policy 0, policy_version 9410 (0.0007) -[2023-10-17 00:38:31,252][62373] Updated weights for policy 0, policy_version 9420 (0.0009) -[2023-10-17 00:38:31,623][62373] Updated weights for policy 0, policy_version 9430 (0.0007) -[2023-10-17 00:38:31,629][62408] Updated weights for policy 1, policy_version 9350 (0.0009) -[2023-10-17 00:38:31,988][62373] Updated weights for policy 0, policy_version 9440 (0.0008) -[2023-10-17 00:38:31,997][62408] Updated weights for policy 1, policy_version 9360 (0.0010) -[2023-10-17 00:38:32,214][61453] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 19234816. Throughput: 0: 1768.8, 1: 1765.2. Samples: 4820296. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:38:32,214][61453] Avg episode reward: [(0, '4.160'), (1, '4.500')] -[2023-10-17 00:38:32,370][62408] Updated weights for policy 1, policy_version 9370 (0.0011) -[2023-10-17 00:38:35,840][62373] Updated weights for policy 0, policy_version 9450 (0.0008) -[2023-10-17 00:38:36,215][62373] Updated weights for policy 0, policy_version 9460 (0.0008) -[2023-10-17 00:38:36,285][62408] Updated weights for policy 1, policy_version 9380 (0.0008) -[2023-10-17 00:38:36,584][62373] Updated weights for policy 0, policy_version 9470 (0.0008) -[2023-10-17 00:38:36,655][62408] Updated weights for policy 1, policy_version 9390 (0.0009) -[2023-10-17 00:38:37,021][62408] Updated weights for policy 1, policy_version 9400 (0.0009) -[2023-10-17 00:38:37,214][61453] Fps is (10 sec: 16384.3, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 19300352. Throughput: 0: 1781.1, 1: 1752.6. Samples: 4831592. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) -[2023-10-17 00:38:37,215][61453] Avg episode reward: [(0, '4.150'), (1, '4.180')] -[2023-10-17 00:38:40,423][62373] Updated weights for policy 0, policy_version 9480 (0.0010) -[2023-10-17 00:38:40,788][62373] Updated weights for policy 0, policy_version 9490 (0.0008) -[2023-10-17 00:38:41,044][62408] Updated weights for policy 1, policy_version 9410 (0.0008) -[2023-10-17 00:38:41,166][62373] Updated weights for policy 0, policy_version 9500 (0.0007) -[2023-10-17 00:38:41,417][62408] Updated weights for policy 1, policy_version 9420 (0.0007) -[2023-10-17 00:38:41,782][62408] Updated weights for policy 1, policy_version 9430 (0.0010) -[2023-10-17 00:38:42,149][62408] Updated weights for policy 1, policy_version 9440 (0.0007) -[2023-10-17 00:38:42,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 19398656. Throughput: 0: 1776.9, 1: 1773.1. Samples: 4852730. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) -[2023-10-17 00:38:42,215][61453] Avg episode reward: [(0, '4.120'), (1, '4.230')] -[2023-10-17 00:38:45,041][62373] Updated weights for policy 0, policy_version 9510 (0.0007) -[2023-10-17 00:38:45,421][62373] Updated weights for policy 0, policy_version 9520 (0.0009) -[2023-10-17 00:38:45,790][62373] Updated weights for policy 0, policy_version 9530 (0.0008) -[2023-10-17 00:38:45,817][62408] Updated weights for policy 1, policy_version 9450 (0.0007) -[2023-10-17 00:38:46,179][62408] Updated weights for policy 1, policy_version 9460 (0.0008) -[2023-10-17 00:38:46,542][62408] Updated weights for policy 1, policy_version 9470 (0.0010) -[2023-10-17 00:38:47,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 19464192. Throughput: 0: 1758.8, 1: 1751.6. Samples: 4872888. Policy #0 lag: (min: 9.0, avg: 12.3, max: 38.0) -[2023-10-17 00:38:47,215][61453] Avg episode reward: [(0, '3.970'), (1, '4.400')] -[2023-10-17 00:38:49,487][62373] Updated weights for policy 0, policy_version 9540 (0.0008) -[2023-10-17 00:38:49,862][62373] Updated weights for policy 0, policy_version 9550 (0.0007) -[2023-10-17 00:38:50,230][62373] Updated weights for policy 0, policy_version 9560 (0.0007) -[2023-10-17 00:38:50,514][62408] Updated weights for policy 1, policy_version 9480 (0.0007) -[2023-10-17 00:38:50,887][62408] Updated weights for policy 1, policy_version 9490 (0.0007) -[2023-10-17 00:38:51,257][62408] Updated weights for policy 1, policy_version 9500 (0.0011) -[2023-10-17 00:38:52,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 19529728. Throughput: 0: 1774.0, 1: 1780.1. Samples: 4884700. Policy #0 lag: (min: 9.0, avg: 12.3, max: 38.0) -[2023-10-17 00:38:52,215][61453] Avg episode reward: [(0, '3.750'), (1, '4.640')] -[2023-10-17 00:38:54,019][62373] Updated weights for policy 0, policy_version 9570 (0.0008) -[2023-10-17 00:38:54,388][62373] Updated weights for policy 0, policy_version 9580 (0.0011) -[2023-10-17 00:38:54,768][62373] Updated weights for policy 0, policy_version 9590 (0.0009) -[2023-10-17 00:38:54,914][62408] Updated weights for policy 1, policy_version 9510 (0.0009) -[2023-10-17 00:38:55,150][62373] Updated weights for policy 0, policy_version 9600 (0.0009) -[2023-10-17 00:38:55,285][62408] Updated weights for policy 1, policy_version 9520 (0.0008) -[2023-10-17 00:38:55,650][62408] Updated weights for policy 1, policy_version 9530 (0.0008) -[2023-10-17 00:38:57,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 19595264. Throughput: 0: 1762.6, 1: 1756.9. Samples: 4905100. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-17 00:38:57,215][61453] Avg episode reward: [(0, '4.010'), (1, '4.630')] -[2023-10-17 00:38:58,659][62373] Updated weights for policy 0, policy_version 9610 (0.0008) -[2023-10-17 00:38:59,026][62373] Updated weights for policy 0, policy_version 9620 (0.0007) -[2023-10-17 00:38:59,397][62373] Updated weights for policy 0, policy_version 9630 (0.0008) -[2023-10-17 00:38:59,471][62408] Updated weights for policy 1, policy_version 9540 (0.0010) -[2023-10-17 00:38:59,839][62408] Updated weights for policy 1, policy_version 9550 (0.0007) -[2023-10-17 00:39:00,212][62408] Updated weights for policy 1, policy_version 9560 (0.0009) -[2023-10-17 00:39:02,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 19660800. Throughput: 0: 1772.2, 1: 1746.1. Samples: 4927196. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-17 00:39:02,215][61453] Avg episode reward: [(0, '4.110'), (1, '5.010')] -[2023-10-17 00:39:02,228][62252] Saving new best policy, reward=5.010! -[2023-10-17 00:39:03,385][62373] Updated weights for policy 0, policy_version 9640 (0.0007) -[2023-10-17 00:39:03,771][62373] Updated weights for policy 0, policy_version 9650 (0.0007) -[2023-10-17 00:39:04,057][62408] Updated weights for policy 1, policy_version 9570 (0.0008) -[2023-10-17 00:39:04,141][62373] Updated weights for policy 0, policy_version 9660 (0.0007) -[2023-10-17 00:39:04,423][62408] Updated weights for policy 1, policy_version 9580 (0.0009) -[2023-10-17 00:39:04,784][62408] Updated weights for policy 1, policy_version 9590 (0.0009) -[2023-10-17 00:39:05,160][62408] Updated weights for policy 1, policy_version 9600 (0.0010) -[2023-10-17 00:39:07,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 19726336. Throughput: 0: 1773.0, 1: 1756.8. Samples: 4937140. Policy #0 lag: (min: 25.0, avg: 39.3, max: 57.0) -[2023-10-17 00:39:07,216][61453] Avg episode reward: [(0, '4.080'), (1, '4.950')] -[2023-10-17 00:39:07,798][62373] Updated weights for policy 0, policy_version 9670 (0.0009) -[2023-10-17 00:39:08,163][62373] Updated weights for policy 0, policy_version 9680 (0.0007) -[2023-10-17 00:39:08,537][62373] Updated weights for policy 0, policy_version 9690 (0.0008) -[2023-10-17 00:39:08,972][62408] Updated weights for policy 1, policy_version 9610 (0.0008) -[2023-10-17 00:39:09,337][62408] Updated weights for policy 1, policy_version 9620 (0.0010) -[2023-10-17 00:39:09,716][62408] Updated weights for policy 1, policy_version 9630 (0.0009) -[2023-10-17 00:39:12,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 19791872. Throughput: 0: 1775.5, 1: 1750.1. Samples: 4958790. Policy #0 lag: (min: 25.0, avg: 39.3, max: 57.0) -[2023-10-17 00:39:12,215][61453] Avg episode reward: [(0, '4.290'), (1, '5.070')] -[2023-10-17 00:39:12,216][62252] Saving new best policy, reward=5.070! -[2023-10-17 00:39:12,442][62373] Updated weights for policy 0, policy_version 9700 (0.0007) -[2023-10-17 00:39:12,809][62373] Updated weights for policy 0, policy_version 9710 (0.0007) -[2023-10-17 00:39:13,189][62373] Updated weights for policy 0, policy_version 9720 (0.0008) -[2023-10-17 00:39:13,582][62408] Updated weights for policy 1, policy_version 9640 (0.0009) -[2023-10-17 00:39:13,961][62408] Updated weights for policy 1, policy_version 9650 (0.0007) -[2023-10-17 00:39:14,334][62408] Updated weights for policy 1, policy_version 9660 (0.0010) -[2023-10-17 00:39:16,907][62373] Updated weights for policy 0, policy_version 9730 (0.0008) -[2023-10-17 00:39:17,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 19857408. Throughput: 0: 1801.3, 1: 1766.5. Samples: 4980848. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:39:17,215][61453] Avg episode reward: [(0, '4.230'), (1, '4.730')] -[2023-10-17 00:39:17,284][62373] Updated weights for policy 0, policy_version 9740 (0.0007) -[2023-10-17 00:39:17,652][62373] Updated weights for policy 0, policy_version 9750 (0.0007) -[2023-10-17 00:39:18,037][62373] Updated weights for policy 0, policy_version 9760 (0.0009) -[2023-10-17 00:39:18,038][62408] Updated weights for policy 1, policy_version 9670 (0.0007) -[2023-10-17 00:39:18,411][62408] Updated weights for policy 1, policy_version 9680 (0.0007) -[2023-10-17 00:39:18,771][62408] Updated weights for policy 1, policy_version 9690 (0.0007) -[2023-10-17 00:39:21,806][62373] Updated weights for policy 0, policy_version 9770 (0.0010) -[2023-10-17 00:39:22,194][62373] Updated weights for policy 0, policy_version 9780 (0.0010) -[2023-10-17 00:39:22,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 19922944. Throughput: 0: 1776.0, 1: 1756.5. Samples: 4990550. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:39:22,214][61453] Avg episode reward: [(0, '4.440'), (1, '4.800')] -[2023-10-17 00:39:22,556][62373] Updated weights for policy 0, policy_version 9790 (0.0008) -[2023-10-17 00:39:22,700][62408] Updated weights for policy 1, policy_version 9700 (0.0008) -[2023-10-17 00:39:23,060][62408] Updated weights for policy 1, policy_version 9710 (0.0008) -[2023-10-17 00:39:23,427][62408] Updated weights for policy 1, policy_version 9720 (0.0007) -[2023-10-17 00:39:26,390][62373] Updated weights for policy 0, policy_version 9800 (0.0009) -[2023-10-17 00:39:26,758][62373] Updated weights for policy 0, policy_version 9810 (0.0007) -[2023-10-17 00:39:27,093][62408] Updated weights for policy 1, policy_version 9730 (0.0008) -[2023-10-17 00:39:27,128][62373] Updated weights for policy 0, policy_version 9820 (0.0009) -[2023-10-17 00:39:27,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 19988480. Throughput: 0: 1800.4, 1: 1758.9. Samples: 5012900. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-17 00:39:27,215][61453] Avg episode reward: [(0, '4.670'), (1, '4.740')] -[2023-10-17 00:39:27,277][62094] Saving new best policy, reward=4.670! -[2023-10-17 00:39:27,453][62408] Updated weights for policy 1, policy_version 9740 (0.0007) -[2023-10-17 00:39:27,823][62408] Updated weights for policy 1, policy_version 9750 (0.0008) -[2023-10-17 00:39:28,193][62408] Updated weights for policy 1, policy_version 9760 (0.0009) -[2023-10-17 00:39:30,837][62373] Updated weights for policy 0, policy_version 9830 (0.0010) -[2023-10-17 00:39:31,199][62373] Updated weights for policy 0, policy_version 9840 (0.0007) -[2023-10-17 00:39:31,571][62373] Updated weights for policy 0, policy_version 9850 (0.0010) -[2023-10-17 00:39:32,071][62408] Updated weights for policy 1, policy_version 9770 (0.0008) -[2023-10-17 00:39:32,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 20086784. Throughput: 0: 1787.2, 1: 1784.0. Samples: 5033594. Policy #0 lag: (min: 3.0, avg: 3.0, max: 4.0) -[2023-10-17 00:39:32,214][61453] Avg episode reward: [(0, '4.630'), (1, '4.930')] -[2023-10-17 00:39:32,226][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000009856_10092544.pth... -[2023-10-17 00:39:32,261][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000008192_8388608.pth -[2023-10-17 00:39:32,440][62408] Updated weights for policy 1, policy_version 9780 (0.0007) -[2023-10-17 00:39:32,803][62408] Updated weights for policy 1, policy_version 9790 (0.0008) -[2023-10-17 00:39:32,879][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000009792_10027008.pth... -[2023-10-17 00:39:32,910][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000008128_8323072.pth -[2023-10-17 00:39:35,227][62373] Updated weights for policy 0, policy_version 9860 (0.0008) -[2023-10-17 00:39:35,592][62373] Updated weights for policy 0, policy_version 9870 (0.0007) -[2023-10-17 00:39:35,969][62373] Updated weights for policy 0, policy_version 9880 (0.0009) -[2023-10-17 00:39:36,629][62408] Updated weights for policy 1, policy_version 9800 (0.0008) -[2023-10-17 00:39:36,995][62408] Updated weights for policy 1, policy_version 9810 (0.0007) -[2023-10-17 00:39:37,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 20152320. Throughput: 0: 1808.0, 1: 1759.1. Samples: 5045218. Policy #0 lag: (min: 3.0, avg: 3.0, max: 4.0) -[2023-10-17 00:39:37,215][61453] Avg episode reward: [(0, '4.780'), (1, '4.730')] -[2023-10-17 00:39:37,216][62094] Saving new best policy, reward=4.780! -[2023-10-17 00:39:37,370][62408] Updated weights for policy 1, policy_version 9820 (0.0008) -[2023-10-17 00:39:39,696][62373] Updated weights for policy 0, policy_version 9890 (0.0009) -[2023-10-17 00:39:40,076][62373] Updated weights for policy 0, policy_version 9900 (0.0008) -[2023-10-17 00:39:40,449][62373] Updated weights for policy 0, policy_version 9910 (0.0007) -[2023-10-17 00:39:40,816][62373] Updated weights for policy 0, policy_version 9920 (0.0008) -[2023-10-17 00:39:41,147][62408] Updated weights for policy 1, policy_version 9830 (0.0009) -[2023-10-17 00:39:41,524][62408] Updated weights for policy 1, policy_version 9840 (0.0008) -[2023-10-17 00:39:41,886][62408] Updated weights for policy 1, policy_version 9850 (0.0010) -[2023-10-17 00:39:42,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 20250624. Throughput: 0: 1788.8, 1: 1786.2. Samples: 5065974. Policy #0 lag: (min: 38.0, avg: 55.3, max: 56.0) -[2023-10-17 00:39:42,214][61453] Avg episode reward: [(0, '4.590'), (1, '5.070')] -[2023-10-17 00:39:44,633][62373] Updated weights for policy 0, policy_version 9930 (0.0008) -[2023-10-17 00:39:45,000][62373] Updated weights for policy 0, policy_version 9940 (0.0007) -[2023-10-17 00:39:45,370][62373] Updated weights for policy 0, policy_version 9950 (0.0008) -[2023-10-17 00:39:45,579][62408] Updated weights for policy 1, policy_version 9860 (0.0008) -[2023-10-17 00:39:45,951][62408] Updated weights for policy 1, policy_version 9870 (0.0008) -[2023-10-17 00:39:46,326][62408] Updated weights for policy 1, policy_version 9880 (0.0011) -[2023-10-17 00:39:47,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 20316160. Throughput: 0: 1786.7, 1: 1760.6. Samples: 5086826. Policy #0 lag: (min: 38.0, avg: 55.3, max: 56.0) -[2023-10-17 00:39:47,214][61453] Avg episode reward: [(0, '4.670'), (1, '5.090')] -[2023-10-17 00:39:47,224][62252] Saving new best policy, reward=5.090! -[2023-10-17 00:39:49,252][62373] Updated weights for policy 0, policy_version 9960 (0.0009) -[2023-10-17 00:39:49,626][62373] Updated weights for policy 0, policy_version 9970 (0.0009) -[2023-10-17 00:39:49,991][62373] Updated weights for policy 0, policy_version 9980 (0.0008) -[2023-10-17 00:39:50,203][62408] Updated weights for policy 1, policy_version 9890 (0.0010) -[2023-10-17 00:39:50,572][62408] Updated weights for policy 1, policy_version 9900 (0.0010) -[2023-10-17 00:39:50,938][62408] Updated weights for policy 1, policy_version 9910 (0.0008) -[2023-10-17 00:39:51,304][62408] Updated weights for policy 1, policy_version 9920 (0.0008) -[2023-10-17 00:39:52,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 20381696. Throughput: 0: 1790.5, 1: 1783.1. Samples: 5097952. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:39:52,215][61453] Avg episode reward: [(0, '4.440'), (1, '5.050')] -[2023-10-17 00:39:53,650][62373] Updated weights for policy 0, policy_version 9990 (0.0008) -[2023-10-17 00:39:54,033][62373] Updated weights for policy 0, policy_version 10000 (0.0008) -[2023-10-17 00:39:54,400][62373] Updated weights for policy 0, policy_version 10010 (0.0011) -[2023-10-17 00:39:55,057][62408] Updated weights for policy 1, policy_version 9930 (0.0008) -[2023-10-17 00:39:55,431][62408] Updated weights for policy 1, policy_version 9940 (0.0007) -[2023-10-17 00:39:55,808][62408] Updated weights for policy 1, policy_version 9950 (0.0008) -[2023-10-17 00:39:57,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 20447232. Throughput: 0: 1782.8, 1: 1764.5. Samples: 5118420. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:39:57,214][61453] Avg episode reward: [(0, '4.260'), (1, '4.730')] -[2023-10-17 00:39:58,227][62373] Updated weights for policy 0, policy_version 10020 (0.0009) -[2023-10-17 00:39:58,598][62373] Updated weights for policy 0, policy_version 10030 (0.0008) -[2023-10-17 00:39:58,971][62373] Updated weights for policy 0, policy_version 10040 (0.0008) -[2023-10-17 00:39:59,795][62408] Updated weights for policy 1, policy_version 9960 (0.0009) -[2023-10-17 00:40:00,172][62408] Updated weights for policy 1, policy_version 9970 (0.0011) -[2023-10-17 00:40:00,541][62408] Updated weights for policy 1, policy_version 9980 (0.0009) -[2023-10-17 00:40:02,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 20512768. Throughput: 0: 1784.8, 1: 1756.7. Samples: 5140214. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:40:02,215][61453] Avg episode reward: [(0, '3.860'), (1, '4.980')] -[2023-10-17 00:40:02,622][62373] Updated weights for policy 0, policy_version 10050 (0.0009) -[2023-10-17 00:40:02,993][62373] Updated weights for policy 0, policy_version 10060 (0.0008) -[2023-10-17 00:40:03,371][62373] Updated weights for policy 0, policy_version 10070 (0.0008) -[2023-10-17 00:40:03,739][62373] Updated weights for policy 0, policy_version 10080 (0.0008) -[2023-10-17 00:40:04,428][62408] Updated weights for policy 1, policy_version 9990 (0.0008) -[2023-10-17 00:40:04,792][62408] Updated weights for policy 1, policy_version 10000 (0.0010) -[2023-10-17 00:40:05,165][62408] Updated weights for policy 1, policy_version 10010 (0.0008) -[2023-10-17 00:40:07,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 20578304. Throughput: 0: 1778.0, 1: 1772.0. Samples: 5150302. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:40:07,215][61453] Avg episode reward: [(0, '4.130'), (1, '4.900')] -[2023-10-17 00:40:07,549][62373] Updated weights for policy 0, policy_version 10090 (0.0007) -[2023-10-17 00:40:07,922][62373] Updated weights for policy 0, policy_version 10100 (0.0007) -[2023-10-17 00:40:08,294][62373] Updated weights for policy 0, policy_version 10110 (0.0010) -[2023-10-17 00:40:09,060][62408] Updated weights for policy 1, policy_version 10020 (0.0009) -[2023-10-17 00:40:09,431][62408] Updated weights for policy 1, policy_version 10030 (0.0008) -[2023-10-17 00:40:09,802][62408] Updated weights for policy 1, policy_version 10040 (0.0008) -[2023-10-17 00:40:11,930][62373] Updated weights for policy 0, policy_version 10120 (0.0009) -[2023-10-17 00:40:12,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 20643840. Throughput: 0: 1775.4, 1: 1750.3. Samples: 5171558. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:40:12,214][61453] Avg episode reward: [(0, '4.140'), (1, '4.770')] -[2023-10-17 00:40:12,305][62373] Updated weights for policy 0, policy_version 10130 (0.0009) -[2023-10-17 00:40:12,668][62373] Updated weights for policy 0, policy_version 10140 (0.0011) -[2023-10-17 00:40:13,718][62408] Updated weights for policy 1, policy_version 10050 (0.0008) -[2023-10-17 00:40:14,100][62408] Updated weights for policy 1, policy_version 10060 (0.0009) -[2023-10-17 00:40:14,469][62408] Updated weights for policy 1, policy_version 10070 (0.0008) -[2023-10-17 00:40:14,838][62408] Updated weights for policy 1, policy_version 10080 (0.0007) -[2023-10-17 00:40:16,634][62373] Updated weights for policy 0, policy_version 10150 (0.0007) -[2023-10-17 00:40:17,012][62373] Updated weights for policy 0, policy_version 10160 (0.0008) -[2023-10-17 00:40:17,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 20709376. Throughput: 0: 1789.0, 1: 1752.8. Samples: 5192974. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:40:17,214][61453] Avg episode reward: [(0, '3.870'), (1, '4.980')] -[2023-10-17 00:40:17,381][62373] Updated weights for policy 0, policy_version 10170 (0.0007) -[2023-10-17 00:40:18,587][62408] Updated weights for policy 1, policy_version 10090 (0.0007) -[2023-10-17 00:40:18,955][62408] Updated weights for policy 1, policy_version 10100 (0.0007) -[2023-10-17 00:40:19,313][62408] Updated weights for policy 1, policy_version 10110 (0.0009) -[2023-10-17 00:40:21,226][62373] Updated weights for policy 0, policy_version 10180 (0.0008) -[2023-10-17 00:40:21,584][62373] Updated weights for policy 0, policy_version 10190 (0.0010) -[2023-10-17 00:40:21,964][62373] Updated weights for policy 0, policy_version 10200 (0.0010) -[2023-10-17 00:40:22,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 20774912. Throughput: 0: 1764.9, 1: 1748.8. Samples: 5203338. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:40:22,215][61453] Avg episode reward: [(0, '4.410'), (1, '5.010')] -[2023-10-17 00:40:23,333][62408] Updated weights for policy 1, policy_version 10120 (0.0010) -[2023-10-17 00:40:23,713][62408] Updated weights for policy 1, policy_version 10130 (0.0010) -[2023-10-17 00:40:24,078][62408] Updated weights for policy 1, policy_version 10140 (0.0010) -[2023-10-17 00:40:25,817][62373] Updated weights for policy 0, policy_version 10210 (0.0008) -[2023-10-17 00:40:26,189][62373] Updated weights for policy 0, policy_version 10220 (0.0010) -[2023-10-17 00:40:26,560][62373] Updated weights for policy 0, policy_version 10230 (0.0008) -[2023-10-17 00:40:26,923][62373] Updated weights for policy 0, policy_version 10240 (0.0009) -[2023-10-17 00:40:27,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14106.9). Total num frames: 20873216. Throughput: 0: 1789.5, 1: 1739.3. Samples: 5224770. Policy #0 lag: (min: 5.0, avg: 5.4, max: 19.0) -[2023-10-17 00:40:27,214][61453] Avg episode reward: [(0, '4.610'), (1, '4.810')] -[2023-10-17 00:40:27,926][62408] Updated weights for policy 1, policy_version 10150 (0.0010) -[2023-10-17 00:40:28,301][62408] Updated weights for policy 1, policy_version 10160 (0.0011) -[2023-10-17 00:40:28,671][62408] Updated weights for policy 1, policy_version 10170 (0.0011) -[2023-10-17 00:40:30,746][62373] Updated weights for policy 0, policy_version 10250 (0.0010) -[2023-10-17 00:40:31,118][62373] Updated weights for policy 0, policy_version 10260 (0.0008) -[2023-10-17 00:40:31,489][62373] Updated weights for policy 0, policy_version 10270 (0.0008) -[2023-10-17 00:40:32,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 20938752. Throughput: 0: 1760.4, 1: 1771.1. Samples: 5245742. Policy #0 lag: (min: 5.0, avg: 5.4, max: 19.0) -[2023-10-17 00:40:32,215][61453] Avg episode reward: [(0, '4.480'), (1, '4.600')] -[2023-10-17 00:40:32,545][62408] Updated weights for policy 1, policy_version 10180 (0.0011) -[2023-10-17 00:40:32,922][62408] Updated weights for policy 1, policy_version 10190 (0.0008) -[2023-10-17 00:40:33,291][62408] Updated weights for policy 1, policy_version 10200 (0.0010) -[2023-10-17 00:40:35,353][62373] Updated weights for policy 0, policy_version 10280 (0.0009) -[2023-10-17 00:40:35,723][62373] Updated weights for policy 0, policy_version 10290 (0.0009) -[2023-10-17 00:40:36,096][62373] Updated weights for policy 0, policy_version 10300 (0.0008) -[2023-10-17 00:40:37,070][62408] Updated weights for policy 1, policy_version 10210 (0.0010) -[2023-10-17 00:40:37,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 21004288. Throughput: 0: 1792.0, 1: 1738.8. Samples: 5256840. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-17 00:40:37,215][61453] Avg episode reward: [(0, '4.470'), (1, '4.730')] -[2023-10-17 00:40:37,437][62408] Updated weights for policy 1, policy_version 10220 (0.0009) -[2023-10-17 00:40:37,814][62408] Updated weights for policy 1, policy_version 10230 (0.0008) -[2023-10-17 00:40:38,186][62408] Updated weights for policy 1, policy_version 10240 (0.0009) -[2023-10-17 00:40:39,858][62373] Updated weights for policy 0, policy_version 10310 (0.0009) -[2023-10-17 00:40:40,227][62373] Updated weights for policy 0, policy_version 10320 (0.0007) -[2023-10-17 00:40:40,591][62373] Updated weights for policy 0, policy_version 10330 (0.0009) -[2023-10-17 00:40:41,890][62408] Updated weights for policy 1, policy_version 10250 (0.0008) -[2023-10-17 00:40:42,214][61453] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 21069824. Throughput: 0: 1766.4, 1: 1771.0. Samples: 5277606. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-17 00:40:42,215][61453] Avg episode reward: [(0, '4.670'), (1, '4.540')] -[2023-10-17 00:40:42,253][62408] Updated weights for policy 1, policy_version 10260 (0.0008) -[2023-10-17 00:40:42,628][62408] Updated weights for policy 1, policy_version 10270 (0.0009) -[2023-10-17 00:40:44,345][62373] Updated weights for policy 0, policy_version 10340 (0.0008) -[2023-10-17 00:40:44,717][62373] Updated weights for policy 0, policy_version 10350 (0.0007) -[2023-10-17 00:40:45,080][62373] Updated weights for policy 0, policy_version 10360 (0.0008) -[2023-10-17 00:40:46,574][62408] Updated weights for policy 1, policy_version 10280 (0.0009) -[2023-10-17 00:40:46,956][62408] Updated weights for policy 1, policy_version 10290 (0.0007) -[2023-10-17 00:40:47,214][61453] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 21135360. Throughput: 0: 1766.4, 1: 1757.6. Samples: 5298794. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-17 00:40:47,214][61453] Avg episode reward: [(0, '4.720'), (1, '4.630')] -[2023-10-17 00:40:47,324][62408] Updated weights for policy 1, policy_version 10300 (0.0009) -[2023-10-17 00:40:48,957][62373] Updated weights for policy 0, policy_version 10370 (0.0009) -[2023-10-17 00:40:49,326][62373] Updated weights for policy 0, policy_version 10380 (0.0008) -[2023-10-17 00:40:49,695][62373] Updated weights for policy 0, policy_version 10390 (0.0008) -[2023-10-17 00:40:50,066][62373] Updated weights for policy 0, policy_version 10400 (0.0010) -[2023-10-17 00:40:51,153][62408] Updated weights for policy 1, policy_version 10310 (0.0010) -[2023-10-17 00:40:51,519][62408] Updated weights for policy 1, policy_version 10320 (0.0008) -[2023-10-17 00:40:51,883][62408] Updated weights for policy 1, policy_version 10330 (0.0008) -[2023-10-17 00:40:52,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 21233664. Throughput: 0: 1769.9, 1: 1761.3. Samples: 5309204. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-17 00:40:52,215][61453] Avg episode reward: [(0, '4.410'), (1, '4.690')] -[2023-10-17 00:40:53,833][62373] Updated weights for policy 0, policy_version 10410 (0.0010) -[2023-10-17 00:40:54,197][62373] Updated weights for policy 0, policy_version 10420 (0.0010) -[2023-10-17 00:40:54,575][62373] Updated weights for policy 0, policy_version 10430 (0.0011) -[2023-10-17 00:40:55,716][62408] Updated weights for policy 1, policy_version 10340 (0.0007) -[2023-10-17 00:40:56,082][62408] Updated weights for policy 1, policy_version 10350 (0.0008) -[2023-10-17 00:40:56,458][62408] Updated weights for policy 1, policy_version 10360 (0.0007) -[2023-10-17 00:40:57,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 21299200. Throughput: 0: 1765.9, 1: 1772.3. Samples: 5330778. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:40:57,215][61453] Avg episode reward: [(0, '5.010'), (1, '4.800')] -[2023-10-17 00:40:57,216][62094] Saving new best policy, reward=5.010! -[2023-10-17 00:40:58,368][62373] Updated weights for policy 0, policy_version 10440 (0.0009) -[2023-10-17 00:40:58,745][62373] Updated weights for policy 0, policy_version 10450 (0.0008) -[2023-10-17 00:40:59,112][62373] Updated weights for policy 0, policy_version 10460 (0.0009) -[2023-10-17 00:41:00,149][62408] Updated weights for policy 1, policy_version 10370 (0.0007) -[2023-10-17 00:41:00,526][62408] Updated weights for policy 1, policy_version 10380 (0.0008) -[2023-10-17 00:41:00,892][62408] Updated weights for policy 1, policy_version 10390 (0.0008) -[2023-10-17 00:41:01,255][62408] Updated weights for policy 1, policy_version 10400 (0.0009) -[2023-10-17 00:41:02,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 21364736. Throughput: 0: 1780.7, 1: 1753.6. Samples: 5352020. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:41:02,215][61453] Avg episode reward: [(0, '4.630'), (1, '4.650')] -[2023-10-17 00:41:02,802][62373] Updated weights for policy 0, policy_version 10470 (0.0007) -[2023-10-17 00:41:03,171][62373] Updated weights for policy 0, policy_version 10480 (0.0009) -[2023-10-17 00:41:03,547][62373] Updated weights for policy 0, policy_version 10490 (0.0007) -[2023-10-17 00:41:04,981][62408] Updated weights for policy 1, policy_version 10410 (0.0008) -[2023-10-17 00:41:05,353][62408] Updated weights for policy 1, policy_version 10420 (0.0009) -[2023-10-17 00:41:05,710][62408] Updated weights for policy 1, policy_version 10430 (0.0010) -[2023-10-17 00:41:07,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 21430272. Throughput: 0: 1768.3, 1: 1778.6. Samples: 5362948. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:41:07,215][61453] Avg episode reward: [(0, '4.690'), (1, '4.840')] -[2023-10-17 00:41:07,258][62373] Updated weights for policy 0, policy_version 10500 (0.0008) -[2023-10-17 00:41:07,628][62373] Updated weights for policy 0, policy_version 10510 (0.0008) -[2023-10-17 00:41:08,002][62373] Updated weights for policy 0, policy_version 10520 (0.0007) -[2023-10-17 00:41:09,776][62408] Updated weights for policy 1, policy_version 10440 (0.0010) -[2023-10-17 00:41:10,150][62408] Updated weights for policy 1, policy_version 10450 (0.0009) -[2023-10-17 00:41:10,510][62408] Updated weights for policy 1, policy_version 10460 (0.0009) -[2023-10-17 00:41:11,813][62373] Updated weights for policy 0, policy_version 10530 (0.0008) -[2023-10-17 00:41:12,177][62373] Updated weights for policy 0, policy_version 10540 (0.0010) -[2023-10-17 00:41:12,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 21495808. Throughput: 0: 1781.1, 1: 1756.7. Samples: 5383968. Policy #0 lag: (min: 11.0, avg: 16.1, max: 43.0) -[2023-10-17 00:41:12,215][61453] Avg episode reward: [(0, '4.680'), (1, '4.520')] -[2023-10-17 00:41:12,541][62373] Updated weights for policy 0, policy_version 10550 (0.0010) -[2023-10-17 00:41:12,919][62373] Updated weights for policy 0, policy_version 10560 (0.0011) -[2023-10-17 00:41:14,170][62408] Updated weights for policy 1, policy_version 10470 (0.0009) -[2023-10-17 00:41:14,540][62408] Updated weights for policy 1, policy_version 10480 (0.0007) -[2023-10-17 00:41:14,907][62408] Updated weights for policy 1, policy_version 10490 (0.0008) -[2023-10-17 00:41:16,531][62373] Updated weights for policy 0, policy_version 10570 (0.0011) -[2023-10-17 00:41:16,899][62373] Updated weights for policy 0, policy_version 10580 (0.0010) -[2023-10-17 00:41:17,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 21561344. Throughput: 0: 1791.4, 1: 1757.7. Samples: 5405450. Policy #0 lag: (min: 11.0, avg: 16.1, max: 43.0) -[2023-10-17 00:41:17,215][61453] Avg episode reward: [(0, '4.510'), (1, '4.520')] -[2023-10-17 00:41:17,267][62373] Updated weights for policy 0, policy_version 10590 (0.0011) -[2023-10-17 00:41:18,692][62408] Updated weights for policy 1, policy_version 10500 (0.0008) -[2023-10-17 00:41:19,065][62408] Updated weights for policy 1, policy_version 10510 (0.0008) -[2023-10-17 00:41:19,425][62408] Updated weights for policy 1, policy_version 10520 (0.0008) -[2023-10-17 00:41:21,103][62373] Updated weights for policy 0, policy_version 10600 (0.0007) -[2023-10-17 00:41:21,481][62373] Updated weights for policy 0, policy_version 10610 (0.0010) -[2023-10-17 00:41:21,848][62373] Updated weights for policy 0, policy_version 10620 (0.0009) -[2023-10-17 00:41:22,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14106.9). Total num frames: 21659648. Throughput: 0: 1778.4, 1: 1760.4. Samples: 5416086. Policy #0 lag: (min: 25.0, avg: 31.2, max: 57.0) -[2023-10-17 00:41:22,215][61453] Avg episode reward: [(0, '4.320'), (1, '4.720')] -[2023-10-17 00:41:23,369][62408] Updated weights for policy 1, policy_version 10530 (0.0007) -[2023-10-17 00:41:23,744][62408] Updated weights for policy 1, policy_version 10540 (0.0007) -[2023-10-17 00:41:24,113][62408] Updated weights for policy 1, policy_version 10550 (0.0008) -[2023-10-17 00:41:24,477][62408] Updated weights for policy 1, policy_version 10560 (0.0009) -[2023-10-17 00:41:25,665][62373] Updated weights for policy 0, policy_version 10630 (0.0008) -[2023-10-17 00:41:26,034][62373] Updated weights for policy 0, policy_version 10640 (0.0008) -[2023-10-17 00:41:26,401][62373] Updated weights for policy 0, policy_version 10650 (0.0009) -[2023-10-17 00:41:27,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 21725184. Throughput: 0: 1798.5, 1: 1757.5. Samples: 5437624. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-17 00:41:27,215][61453] Avg episode reward: [(0, '4.380'), (1, '4.510')] -[2023-10-17 00:41:28,183][62408] Updated weights for policy 1, policy_version 10570 (0.0009) -[2023-10-17 00:41:28,551][62408] Updated weights for policy 1, policy_version 10580 (0.0011) -[2023-10-17 00:41:28,932][62408] Updated weights for policy 1, policy_version 10590 (0.0009) -[2023-10-17 00:41:30,142][62373] Updated weights for policy 0, policy_version 10660 (0.0009) -[2023-10-17 00:41:30,511][62373] Updated weights for policy 0, policy_version 10670 (0.0007) -[2023-10-17 00:41:30,878][62373] Updated weights for policy 0, policy_version 10680 (0.0008) -[2023-10-17 00:41:32,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 21790720. Throughput: 0: 1781.9, 1: 1780.9. Samples: 5459122. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-17 00:41:32,215][61453] Avg episode reward: [(0, '4.750'), (1, '4.570')] -[2023-10-17 00:41:32,228][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000010688_10944512.pth... -[2023-10-17 00:41:32,228][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000010592_10846208.pth... -[2023-10-17 00:41:32,258][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000009024_9240576.pth -[2023-10-17 00:41:32,266][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000008960_9175040.pth -[2023-10-17 00:41:32,790][62408] Updated weights for policy 1, policy_version 10600 (0.0010) -[2023-10-17 00:41:33,163][62408] Updated weights for policy 1, policy_version 10610 (0.0010) -[2023-10-17 00:41:33,540][62408] Updated weights for policy 1, policy_version 10620 (0.0010) -[2023-10-17 00:41:34,664][62373] Updated weights for policy 0, policy_version 10690 (0.0007) -[2023-10-17 00:41:35,040][62373] Updated weights for policy 0, policy_version 10700 (0.0008) -[2023-10-17 00:41:35,409][62373] Updated weights for policy 0, policy_version 10710 (0.0010) -[2023-10-17 00:41:35,781][62373] Updated weights for policy 0, policy_version 10720 (0.0009) -[2023-10-17 00:41:37,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 21856256. Throughput: 0: 1804.2, 1: 1758.5. Samples: 5469524. Policy #0 lag: (min: 16.0, avg: 39.6, max: 48.0) -[2023-10-17 00:41:37,214][61453] Avg episode reward: [(0, '4.500'), (1, '4.790')] -[2023-10-17 00:41:37,386][62408] Updated weights for policy 1, policy_version 10630 (0.0008) -[2023-10-17 00:41:37,744][62408] Updated weights for policy 1, policy_version 10640 (0.0008) -[2023-10-17 00:41:38,117][62408] Updated weights for policy 1, policy_version 10650 (0.0008) -[2023-10-17 00:41:39,754][62373] Updated weights for policy 0, policy_version 10730 (0.0007) -[2023-10-17 00:41:40,126][62373] Updated weights for policy 0, policy_version 10740 (0.0009) -[2023-10-17 00:41:40,501][62373] Updated weights for policy 0, policy_version 10750 (0.0008) -[2023-10-17 00:41:41,994][62408] Updated weights for policy 1, policy_version 10660 (0.0007) -[2023-10-17 00:41:42,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 21921792. Throughput: 0: 1784.3, 1: 1766.7. Samples: 5490572. Policy #0 lag: (min: 16.0, avg: 39.6, max: 48.0) -[2023-10-17 00:41:42,214][61453] Avg episode reward: [(0, '4.440'), (1, '4.930')] -[2023-10-17 00:41:42,367][62408] Updated weights for policy 1, policy_version 10670 (0.0010) -[2023-10-17 00:41:42,747][62408] Updated weights for policy 1, policy_version 10680 (0.0008) -[2023-10-17 00:41:44,319][62373] Updated weights for policy 0, policy_version 10760 (0.0008) -[2023-10-17 00:41:44,686][62373] Updated weights for policy 0, policy_version 10770 (0.0009) -[2023-10-17 00:41:45,065][62373] Updated weights for policy 0, policy_version 10780 (0.0008) -[2023-10-17 00:41:46,660][62408] Updated weights for policy 1, policy_version 10690 (0.0008) -[2023-10-17 00:41:47,028][62408] Updated weights for policy 1, policy_version 10700 (0.0010) -[2023-10-17 00:41:47,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 21987328. Throughput: 0: 1781.9, 1: 1780.4. Samples: 5512322. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-17 00:41:47,215][61453] Avg episode reward: [(0, '4.480'), (1, '4.760')] -[2023-10-17 00:41:47,403][62408] Updated weights for policy 1, policy_version 10710 (0.0009) -[2023-10-17 00:41:47,764][62408] Updated weights for policy 1, policy_version 10720 (0.0007) -[2023-10-17 00:41:48,787][62373] Updated weights for policy 0, policy_version 10790 (0.0009) -[2023-10-17 00:41:49,141][62373] Updated weights for policy 0, policy_version 10800 (0.0010) -[2023-10-17 00:41:49,508][62373] Updated weights for policy 0, policy_version 10810 (0.0008) -[2023-10-17 00:41:51,753][62408] Updated weights for policy 1, policy_version 10730 (0.0010) -[2023-10-17 00:41:52,124][62408] Updated weights for policy 1, policy_version 10740 (0.0007) -[2023-10-17 00:41:52,214][61453] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 22052864. Throughput: 0: 1778.8, 1: 1759.9. Samples: 5522188. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-17 00:41:52,214][61453] Avg episode reward: [(0, '4.590'), (1, '4.920')] -[2023-10-17 00:41:52,489][62408] Updated weights for policy 1, policy_version 10750 (0.0007) -[2023-10-17 00:41:53,256][62373] Updated weights for policy 0, policy_version 10820 (0.0010) -[2023-10-17 00:41:53,641][62373] Updated weights for policy 0, policy_version 10830 (0.0008) -[2023-10-17 00:41:54,002][62373] Updated weights for policy 0, policy_version 10840 (0.0009) -[2023-10-17 00:41:56,406][62408] Updated weights for policy 1, policy_version 10760 (0.0009) -[2023-10-17 00:41:56,779][62408] Updated weights for policy 1, policy_version 10770 (0.0008) -[2023-10-17 00:41:57,149][62408] Updated weights for policy 1, policy_version 10780 (0.0007) -[2023-10-17 00:41:57,214][61453] Fps is (10 sec: 13107.6, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 22118400. Throughput: 0: 1779.9, 1: 1783.9. Samples: 5544338. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-17 00:41:57,215][61453] Avg episode reward: [(0, '4.570'), (1, '4.960')] -[2023-10-17 00:41:57,893][62373] Updated weights for policy 0, policy_version 10850 (0.0008) -[2023-10-17 00:41:58,261][62373] Updated weights for policy 0, policy_version 10860 (0.0008) -[2023-10-17 00:41:58,635][62373] Updated weights for policy 0, policy_version 10870 (0.0009) -[2023-10-17 00:41:59,001][62373] Updated weights for policy 0, policy_version 10880 (0.0008) -[2023-10-17 00:42:00,941][62408] Updated weights for policy 1, policy_version 10790 (0.0010) -[2023-10-17 00:42:01,304][62408] Updated weights for policy 1, policy_version 10800 (0.0007) -[2023-10-17 00:42:01,673][62408] Updated weights for policy 1, policy_version 10810 (0.0008) -[2023-10-17 00:42:02,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 22216704. Throughput: 0: 1798.2, 1: 1752.8. Samples: 5565244. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-17 00:42:02,214][61453] Avg episode reward: [(0, '4.600'), (1, '4.720')] -[2023-10-17 00:42:02,649][62373] Updated weights for policy 0, policy_version 10890 (0.0007) -[2023-10-17 00:42:03,025][62373] Updated weights for policy 0, policy_version 10900 (0.0008) -[2023-10-17 00:42:03,392][62373] Updated weights for policy 0, policy_version 10910 (0.0009) -[2023-10-17 00:42:05,438][62408] Updated weights for policy 1, policy_version 10820 (0.0010) -[2023-10-17 00:42:05,805][62408] Updated weights for policy 1, policy_version 10830 (0.0011) -[2023-10-17 00:42:06,173][62408] Updated weights for policy 1, policy_version 10840 (0.0008) -[2023-10-17 00:42:07,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 22282240. Throughput: 0: 1777.0, 1: 1777.5. Samples: 5576036. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-17 00:42:07,214][61453] Avg episode reward: [(0, '4.590'), (1, '4.710')] -[2023-10-17 00:42:07,374][62373] Updated weights for policy 0, policy_version 10920 (0.0009) -[2023-10-17 00:42:07,744][62373] Updated weights for policy 0, policy_version 10930 (0.0007) -[2023-10-17 00:42:08,124][62373] Updated weights for policy 0, policy_version 10940 (0.0010) -[2023-10-17 00:42:09,992][62408] Updated weights for policy 1, policy_version 10850 (0.0010) -[2023-10-17 00:42:10,348][62408] Updated weights for policy 1, policy_version 10860 (0.0011) -[2023-10-17 00:42:10,727][62408] Updated weights for policy 1, policy_version 10870 (0.0010) -[2023-10-17 00:42:11,088][62408] Updated weights for policy 1, policy_version 10880 (0.0011) -[2023-10-17 00:42:11,855][62373] Updated weights for policy 0, policy_version 10950 (0.0008) -[2023-10-17 00:42:12,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 22347776. Throughput: 0: 1788.7, 1: 1753.8. Samples: 5597034. Policy #0 lag: (min: 31.0, avg: 32.1, max: 53.0) -[2023-10-17 00:42:12,215][61453] Avg episode reward: [(0, '4.570'), (1, '4.520')] -[2023-10-17 00:42:12,221][62373] Updated weights for policy 0, policy_version 10960 (0.0008) -[2023-10-17 00:42:12,592][62373] Updated weights for policy 0, policy_version 10970 (0.0009) -[2023-10-17 00:42:14,865][62408] Updated weights for policy 1, policy_version 10890 (0.0010) -[2023-10-17 00:42:15,235][62408] Updated weights for policy 1, policy_version 10900 (0.0007) -[2023-10-17 00:42:15,597][62408] Updated weights for policy 1, policy_version 10910 (0.0009) -[2023-10-17 00:42:16,508][62373] Updated weights for policy 0, policy_version 10980 (0.0008) -[2023-10-17 00:42:16,893][62373] Updated weights for policy 0, policy_version 10990 (0.0009) -[2023-10-17 00:42:17,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 22413312. Throughput: 0: 1784.3, 1: 1746.4. Samples: 5618000. Policy #0 lag: (min: 31.0, avg: 32.1, max: 53.0) -[2023-10-17 00:42:17,215][61453] Avg episode reward: [(0, '4.700'), (1, '4.890')] -[2023-10-17 00:42:17,260][62373] Updated weights for policy 0, policy_version 11000 (0.0008) -[2023-10-17 00:42:19,453][62408] Updated weights for policy 1, policy_version 10920 (0.0009) -[2023-10-17 00:42:19,823][62408] Updated weights for policy 1, policy_version 10930 (0.0008) -[2023-10-17 00:42:20,191][62408] Updated weights for policy 1, policy_version 10940 (0.0008) -[2023-10-17 00:42:20,968][62373] Updated weights for policy 0, policy_version 11010 (0.0009) -[2023-10-17 00:42:21,343][62373] Updated weights for policy 0, policy_version 11020 (0.0011) -[2023-10-17 00:42:21,707][62373] Updated weights for policy 0, policy_version 11030 (0.0008) -[2023-10-17 00:42:22,079][62373] Updated weights for policy 0, policy_version 11040 (0.0007) -[2023-10-17 00:42:22,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 22511616. Throughput: 0: 1775.5, 1: 1766.3. Samples: 5628902. Policy #0 lag: (min: 26.0, avg: 27.7, max: 47.0) -[2023-10-17 00:42:22,215][61453] Avg episode reward: [(0, '4.490'), (1, '4.640')] -[2023-10-17 00:42:23,988][62408] Updated weights for policy 1, policy_version 10950 (0.0009) -[2023-10-17 00:42:24,358][62408] Updated weights for policy 1, policy_version 10960 (0.0011) -[2023-10-17 00:42:24,726][62408] Updated weights for policy 1, policy_version 10970 (0.0009) -[2023-10-17 00:42:25,860][62373] Updated weights for policy 0, policy_version 11050 (0.0011) -[2023-10-17 00:42:26,225][62373] Updated weights for policy 0, policy_version 11060 (0.0009) -[2023-10-17 00:42:26,599][62373] Updated weights for policy 0, policy_version 11070 (0.0008) -[2023-10-17 00:42:27,214][61453] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 22577152. Throughput: 0: 1790.5, 1: 1750.7. Samples: 5649926. Policy #0 lag: (min: 26.0, avg: 27.7, max: 47.0) -[2023-10-17 00:42:27,214][61453] Avg episode reward: [(0, '4.480'), (1, '5.170')] -[2023-10-17 00:42:27,215][62252] Saving new best policy, reward=5.170! -[2023-10-17 00:42:28,718][62408] Updated weights for policy 1, policy_version 10980 (0.0008) -[2023-10-17 00:42:29,081][62408] Updated weights for policy 1, policy_version 10990 (0.0009) -[2023-10-17 00:42:29,446][62408] Updated weights for policy 1, policy_version 11000 (0.0011) -[2023-10-17 00:42:30,247][62373] Updated weights for policy 0, policy_version 11080 (0.0009) -[2023-10-17 00:42:30,617][62373] Updated weights for policy 0, policy_version 11090 (0.0008) -[2023-10-17 00:42:30,985][62373] Updated weights for policy 0, policy_version 11100 (0.0008) -[2023-10-17 00:42:32,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 22642688. Throughput: 0: 1775.1, 1: 1756.3. Samples: 5671234. Policy #0 lag: (min: 26.0, avg: 27.7, max: 47.0) -[2023-10-17 00:42:32,215][61453] Avg episode reward: [(0, '4.470'), (1, '5.200')] -[2023-10-17 00:42:32,228][62252] Saving new best policy, reward=5.200! -[2023-10-17 00:42:33,362][62408] Updated weights for policy 1, policy_version 11010 (0.0009) -[2023-10-17 00:42:33,733][62408] Updated weights for policy 1, policy_version 11020 (0.0007) -[2023-10-17 00:42:34,090][62408] Updated weights for policy 1, policy_version 11030 (0.0007) -[2023-10-17 00:42:34,454][62408] Updated weights for policy 1, policy_version 11040 (0.0007) -[2023-10-17 00:42:34,794][62373] Updated weights for policy 0, policy_version 11110 (0.0007) -[2023-10-17 00:42:35,167][62373] Updated weights for policy 0, policy_version 11120 (0.0007) -[2023-10-17 00:42:35,536][62373] Updated weights for policy 0, policy_version 11130 (0.0007) -[2023-10-17 00:42:37,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 22708224. Throughput: 0: 1796.7, 1: 1752.4. Samples: 5681900. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:42:37,215][61453] Avg episode reward: [(0, '4.450'), (1, '5.320')] -[2023-10-17 00:42:37,217][62252] Saving new best policy, reward=5.320! -[2023-10-17 00:42:38,227][62408] Updated weights for policy 1, policy_version 11050 (0.0007) -[2023-10-17 00:42:38,598][62408] Updated weights for policy 1, policy_version 11060 (0.0007) -[2023-10-17 00:42:38,968][62408] Updated weights for policy 1, policy_version 11070 (0.0008) -[2023-10-17 00:42:39,328][62373] Updated weights for policy 0, policy_version 11140 (0.0009) -[2023-10-17 00:42:39,697][62373] Updated weights for policy 0, policy_version 11150 (0.0008) -[2023-10-17 00:42:40,062][62373] Updated weights for policy 0, policy_version 11160 (0.0007) -[2023-10-17 00:42:42,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 22773760. Throughput: 0: 1772.5, 1: 1755.0. Samples: 5703076. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:42:42,215][61453] Avg episode reward: [(0, '4.300'), (1, '5.130')] -[2023-10-17 00:42:42,759][62408] Updated weights for policy 1, policy_version 11080 (0.0011) -[2023-10-17 00:42:43,131][62408] Updated weights for policy 1, policy_version 11090 (0.0010) -[2023-10-17 00:42:43,499][62408] Updated weights for policy 1, policy_version 11100 (0.0008) -[2023-10-17 00:42:43,825][62373] Updated weights for policy 0, policy_version 11170 (0.0007) -[2023-10-17 00:42:44,198][62373] Updated weights for policy 0, policy_version 11180 (0.0007) -[2023-10-17 00:42:44,565][62373] Updated weights for policy 0, policy_version 11190 (0.0009) -[2023-10-17 00:42:44,943][62373] Updated weights for policy 0, policy_version 11200 (0.0008) -[2023-10-17 00:42:47,169][62408] Updated weights for policy 1, policy_version 11110 (0.0009) -[2023-10-17 00:42:47,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 22839296. Throughput: 0: 1768.2, 1: 1784.8. Samples: 5725126. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:42:47,215][61453] Avg episode reward: [(0, '4.830'), (1, '5.160')] -[2023-10-17 00:42:47,537][62408] Updated weights for policy 1, policy_version 11120 (0.0010) -[2023-10-17 00:42:47,900][62408] Updated weights for policy 1, policy_version 11130 (0.0009) -[2023-10-17 00:42:48,675][62373] Updated weights for policy 0, policy_version 11210 (0.0010) -[2023-10-17 00:42:49,046][62373] Updated weights for policy 0, policy_version 11220 (0.0009) -[2023-10-17 00:42:49,421][62373] Updated weights for policy 0, policy_version 11230 (0.0008) -[2023-10-17 00:42:51,671][62408] Updated weights for policy 1, policy_version 11140 (0.0009) -[2023-10-17 00:42:52,038][62408] Updated weights for policy 1, policy_version 11150 (0.0008) -[2023-10-17 00:42:52,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 22904832. Throughput: 0: 1769.6, 1: 1757.6. Samples: 5734760. Policy #0 lag: (min: 17.0, avg: 32.2, max: 49.0) -[2023-10-17 00:42:52,215][61453] Avg episode reward: [(0, '4.920'), (1, '5.110')] -[2023-10-17 00:42:52,412][62408] Updated weights for policy 1, policy_version 11160 (0.0008) -[2023-10-17 00:42:53,089][62373] Updated weights for policy 0, policy_version 11240 (0.0008) -[2023-10-17 00:42:53,458][62373] Updated weights for policy 0, policy_version 11250 (0.0007) -[2023-10-17 00:42:53,825][62373] Updated weights for policy 0, policy_version 11260 (0.0007) -[2023-10-17 00:42:56,304][62408] Updated weights for policy 1, policy_version 11170 (0.0007) -[2023-10-17 00:42:56,667][62408] Updated weights for policy 1, policy_version 11180 (0.0008) -[2023-10-17 00:42:57,035][62408] Updated weights for policy 1, policy_version 11190 (0.0007) -[2023-10-17 00:42:57,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 22970368. Throughput: 0: 1777.6, 1: 1778.8. Samples: 5757072. Policy #0 lag: (min: 17.0, avg: 32.2, max: 49.0) -[2023-10-17 00:42:57,215][61453] Avg episode reward: [(0, '4.690'), (1, '4.690')] -[2023-10-17 00:42:57,404][62408] Updated weights for policy 1, policy_version 11200 (0.0008) -[2023-10-17 00:42:57,461][62373] Updated weights for policy 0, policy_version 11270 (0.0008) -[2023-10-17 00:42:57,835][62373] Updated weights for policy 0, policy_version 11280 (0.0009) -[2023-10-17 00:42:58,205][62373] Updated weights for policy 0, policy_version 11290 (0.0008) -[2023-10-17 00:43:01,211][62408] Updated weights for policy 1, policy_version 11210 (0.0008) -[2023-10-17 00:43:01,588][62408] Updated weights for policy 1, policy_version 11220 (0.0007) -[2023-10-17 00:43:01,958][62408] Updated weights for policy 1, policy_version 11230 (0.0010) -[2023-10-17 00:43:02,075][62373] Updated weights for policy 0, policy_version 11300 (0.0007) -[2023-10-17 00:43:02,214][61453] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 23068672. Throughput: 0: 1797.9, 1: 1758.9. Samples: 5778056. Policy #0 lag: (min: 17.0, avg: 32.2, max: 49.0) -[2023-10-17 00:43:02,215][61453] Avg episode reward: [(0, '5.040'), (1, '4.400')] -[2023-10-17 00:43:02,438][62373] Updated weights for policy 0, policy_version 11310 (0.0010) -[2023-10-17 00:43:02,807][62373] Updated weights for policy 0, policy_version 11320 (0.0007) -[2023-10-17 00:43:03,104][62094] Saving new best policy, reward=5.040! -[2023-10-17 00:43:05,892][62408] Updated weights for policy 1, policy_version 11240 (0.0009) -[2023-10-17 00:43:06,270][62408] Updated weights for policy 1, policy_version 11250 (0.0010) -[2023-10-17 00:43:06,631][62408] Updated weights for policy 1, policy_version 11260 (0.0008) -[2023-10-17 00:43:06,699][62373] Updated weights for policy 0, policy_version 11330 (0.0008) -[2023-10-17 00:43:07,067][62373] Updated weights for policy 0, policy_version 11340 (0.0008) -[2023-10-17 00:43:07,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 23134208. Throughput: 0: 1781.6, 1: 1774.8. Samples: 5788938. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:43:07,215][61453] Avg episode reward: [(0, '5.580'), (1, '4.740')] -[2023-10-17 00:43:07,435][62373] Updated weights for policy 0, policy_version 11350 (0.0010) -[2023-10-17 00:43:07,798][62094] Saving new best policy, reward=5.580! -[2023-10-17 00:43:07,801][62373] Updated weights for policy 0, policy_version 11360 (0.0008) -[2023-10-17 00:43:10,450][62408] Updated weights for policy 1, policy_version 11270 (0.0008) -[2023-10-17 00:43:10,812][62408] Updated weights for policy 1, policy_version 11280 (0.0008) -[2023-10-17 00:43:11,183][62408] Updated weights for policy 1, policy_version 11290 (0.0008) -[2023-10-17 00:43:11,685][62373] Updated weights for policy 0, policy_version 11370 (0.0009) -[2023-10-17 00:43:12,049][62373] Updated weights for policy 0, policy_version 11380 (0.0007) -[2023-10-17 00:43:12,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 23199744. Throughput: 0: 1792.0, 1: 1769.2. Samples: 5810182. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:43:12,214][61453] Avg episode reward: [(0, '5.080'), (1, '5.250')] -[2023-10-17 00:43:12,410][62373] Updated weights for policy 0, policy_version 11390 (0.0007) -[2023-10-17 00:43:15,251][62408] Updated weights for policy 1, policy_version 11300 (0.0010) -[2023-10-17 00:43:15,626][62408] Updated weights for policy 1, policy_version 11310 (0.0010) -[2023-10-17 00:43:15,990][62408] Updated weights for policy 1, policy_version 11320 (0.0009) -[2023-10-17 00:43:16,153][62373] Updated weights for policy 0, policy_version 11400 (0.0008) -[2023-10-17 00:43:16,530][62373] Updated weights for policy 0, policy_version 11410 (0.0007) -[2023-10-17 00:43:16,906][62373] Updated weights for policy 0, policy_version 11420 (0.0007) -[2023-10-17 00:43:17,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 23298048. Throughput: 0: 1781.1, 1: 1752.9. Samples: 5830262. Policy #0 lag: (min: 24.0, avg: 50.9, max: 56.0) -[2023-10-17 00:43:17,215][61453] Avg episode reward: [(0, '4.810'), (1, '4.920')] -[2023-10-17 00:43:19,835][62408] Updated weights for policy 1, policy_version 11330 (0.0008) -[2023-10-17 00:43:20,202][62408] Updated weights for policy 1, policy_version 11340 (0.0009) -[2023-10-17 00:43:20,574][62408] Updated weights for policy 1, policy_version 11350 (0.0009) -[2023-10-17 00:43:20,727][62373] Updated weights for policy 0, policy_version 11430 (0.0009) -[2023-10-17 00:43:20,943][62408] Updated weights for policy 1, policy_version 11360 (0.0009) -[2023-10-17 00:43:21,096][62373] Updated weights for policy 0, policy_version 11440 (0.0009) -[2023-10-17 00:43:21,471][62373] Updated weights for policy 0, policy_version 11450 (0.0009) -[2023-10-17 00:43:22,214][61453] Fps is (10 sec: 16383.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 23363584. Throughput: 0: 1786.4, 1: 1777.8. Samples: 5842290. Policy #0 lag: (min: 24.0, avg: 50.9, max: 56.0) -[2023-10-17 00:43:22,215][61453] Avg episode reward: [(0, '5.060'), (1, '4.930')] -[2023-10-17 00:43:24,764][62408] Updated weights for policy 1, policy_version 11370 (0.0007) -[2023-10-17 00:43:25,117][62373] Updated weights for policy 0, policy_version 11460 (0.0008) -[2023-10-17 00:43:25,130][62408] Updated weights for policy 1, policy_version 11380 (0.0007) -[2023-10-17 00:43:25,494][62373] Updated weights for policy 0, policy_version 11470 (0.0011) -[2023-10-17 00:43:25,506][62408] Updated weights for policy 1, policy_version 11390 (0.0007) -[2023-10-17 00:43:25,856][62373] Updated weights for policy 0, policy_version 11480 (0.0008) -[2023-10-17 00:43:27,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 23429120. Throughput: 0: 1784.0, 1: 1751.2. Samples: 5862158. Policy #0 lag: (min: 24.0, avg: 50.9, max: 56.0) -[2023-10-17 00:43:27,215][61453] Avg episode reward: [(0, '4.810'), (1, '5.200')] -[2023-10-17 00:43:29,084][62408] Updated weights for policy 1, policy_version 11400 (0.0008) -[2023-10-17 00:43:29,453][62408] Updated weights for policy 1, policy_version 11410 (0.0011) -[2023-10-17 00:43:29,518][62373] Updated weights for policy 0, policy_version 11490 (0.0008) -[2023-10-17 00:43:29,821][62408] Updated weights for policy 1, policy_version 11420 (0.0008) -[2023-10-17 00:43:29,884][62373] Updated weights for policy 0, policy_version 11500 (0.0007) -[2023-10-17 00:43:30,254][62373] Updated weights for policy 0, policy_version 11510 (0.0008) -[2023-10-17 00:43:30,620][62373] Updated weights for policy 0, policy_version 11520 (0.0009) -[2023-10-17 00:43:32,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 23494656. Throughput: 0: 1776.9, 1: 1758.2. Samples: 5884206. Policy #0 lag: (min: 4.0, avg: 10.6, max: 36.0) -[2023-10-17 00:43:32,215][61453] Avg episode reward: [(0, '4.600'), (1, '5.320')] -[2023-10-17 00:43:32,228][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000011520_11796480.pth... -[2023-10-17 00:43:32,228][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000011424_11698176.pth... -[2023-10-17 00:43:32,258][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000009792_10027008.pth -[2023-10-17 00:43:32,267][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000009856_10092544.pth -[2023-10-17 00:43:33,704][62408] Updated weights for policy 1, policy_version 11430 (0.0007) -[2023-10-17 00:43:34,074][62408] Updated weights for policy 1, policy_version 11440 (0.0007) -[2023-10-17 00:43:34,396][62373] Updated weights for policy 0, policy_version 11530 (0.0009) -[2023-10-17 00:43:34,439][62408] Updated weights for policy 1, policy_version 11450 (0.0008) -[2023-10-17 00:43:34,770][62373] Updated weights for policy 0, policy_version 11540 (0.0008) -[2023-10-17 00:43:35,138][62373] Updated weights for policy 0, policy_version 11550 (0.0009) -[2023-10-17 00:43:37,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 23560192. Throughput: 0: 1786.4, 1: 1754.9. Samples: 5894118. Policy #0 lag: (min: 4.0, avg: 10.6, max: 36.0) -[2023-10-17 00:43:37,215][61453] Avg episode reward: [(0, '4.730'), (1, '4.820')] -[2023-10-17 00:43:38,410][62408] Updated weights for policy 1, policy_version 11460 (0.0007) -[2023-10-17 00:43:38,782][62408] Updated weights for policy 1, policy_version 11470 (0.0007) -[2023-10-17 00:43:38,924][62373] Updated weights for policy 0, policy_version 11560 (0.0009) -[2023-10-17 00:43:39,141][62408] Updated weights for policy 1, policy_version 11480 (0.0009) -[2023-10-17 00:43:39,290][62373] Updated weights for policy 0, policy_version 11570 (0.0009) -[2023-10-17 00:43:39,662][62373] Updated weights for policy 0, policy_version 11580 (0.0010) -[2023-10-17 00:43:42,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 23625728. Throughput: 0: 1767.5, 1: 1751.5. Samples: 5915430. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:43:42,215][61453] Avg episode reward: [(0, '4.780'), (1, '4.940')] -[2023-10-17 00:43:43,195][62408] Updated weights for policy 1, policy_version 11490 (0.0008) -[2023-10-17 00:43:43,566][62408] Updated weights for policy 1, policy_version 11500 (0.0007) -[2023-10-17 00:43:43,616][62373] Updated weights for policy 0, policy_version 11590 (0.0009) -[2023-10-17 00:43:43,927][62408] Updated weights for policy 1, policy_version 11510 (0.0007) -[2023-10-17 00:43:43,994][62373] Updated weights for policy 0, policy_version 11600 (0.0008) -[2023-10-17 00:43:44,294][62408] Updated weights for policy 1, policy_version 11520 (0.0009) -[2023-10-17 00:43:44,358][62373] Updated weights for policy 0, policy_version 11610 (0.0008) -[2023-10-17 00:43:47,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 23691264. Throughput: 0: 1767.3, 1: 1773.0. Samples: 5937372. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:43:47,215][61453] Avg episode reward: [(0, '4.990'), (1, '4.600')] -[2023-10-17 00:43:48,105][62408] Updated weights for policy 1, policy_version 11530 (0.0009) -[2023-10-17 00:43:48,235][62373] Updated weights for policy 0, policy_version 11620 (0.0007) -[2023-10-17 00:43:48,479][62408] Updated weights for policy 1, policy_version 11540 (0.0009) -[2023-10-17 00:43:48,607][62373] Updated weights for policy 0, policy_version 11630 (0.0009) -[2023-10-17 00:43:48,846][62408] Updated weights for policy 1, policy_version 11550 (0.0009) -[2023-10-17 00:43:48,983][62373] Updated weights for policy 0, policy_version 11640 (0.0009) -[2023-10-17 00:43:52,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 23756800. Throughput: 0: 1766.9, 1: 1742.3. Samples: 5946854. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:43:52,214][61453] Avg episode reward: [(0, '5.010'), (1, '4.480')] -[2023-10-17 00:43:52,832][62373] Updated weights for policy 0, policy_version 11650 (0.0008) -[2023-10-17 00:43:52,843][62408] Updated weights for policy 1, policy_version 11560 (0.0008) -[2023-10-17 00:43:53,194][62373] Updated weights for policy 0, policy_version 11660 (0.0009) -[2023-10-17 00:43:53,218][62408] Updated weights for policy 1, policy_version 11570 (0.0009) -[2023-10-17 00:43:53,559][62373] Updated weights for policy 0, policy_version 11670 (0.0010) -[2023-10-17 00:43:53,592][62408] Updated weights for policy 1, policy_version 11580 (0.0009) -[2023-10-17 00:43:53,933][62373] Updated weights for policy 0, policy_version 11680 (0.0008) -[2023-10-17 00:43:57,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 23822336. Throughput: 0: 1764.0, 1: 1753.2. Samples: 5968454. Policy #0 lag: (min: 31.0, avg: 43.2, max: 63.0) -[2023-10-17 00:43:57,214][61453] Avg episode reward: [(0, '4.780'), (1, '4.470')] -[2023-10-17 00:43:57,511][62408] Updated weights for policy 1, policy_version 11590 (0.0008) -[2023-10-17 00:43:57,737][62373] Updated weights for policy 0, policy_version 11690 (0.0008) -[2023-10-17 00:43:57,877][62408] Updated weights for policy 1, policy_version 11600 (0.0007) -[2023-10-17 00:43:58,090][62373] Updated weights for policy 0, policy_version 11700 (0.0007) -[2023-10-17 00:43:58,239][62408] Updated weights for policy 1, policy_version 11610 (0.0007) -[2023-10-17 00:43:58,466][62373] Updated weights for policy 0, policy_version 11710 (0.0007) -[2023-10-17 00:44:02,055][62408] Updated weights for policy 1, policy_version 11620 (0.0007) -[2023-10-17 00:44:02,214][61453] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 23887872. Throughput: 0: 1792.1, 1: 1770.5. Samples: 5990580. Policy #0 lag: (min: 31.0, avg: 43.2, max: 63.0) -[2023-10-17 00:44:02,215][61453] Avg episode reward: [(0, '4.720'), (1, '4.390')] -[2023-10-17 00:44:02,253][62373] Updated weights for policy 0, policy_version 11720 (0.0008) -[2023-10-17 00:44:02,418][62408] Updated weights for policy 1, policy_version 11630 (0.0008) -[2023-10-17 00:44:02,616][62373] Updated weights for policy 0, policy_version 11730 (0.0009) -[2023-10-17 00:44:02,787][62408] Updated weights for policy 1, policy_version 11640 (0.0008) -[2023-10-17 00:44:02,990][62373] Updated weights for policy 0, policy_version 11740 (0.0009) -[2023-10-17 00:44:06,757][62408] Updated weights for policy 1, policy_version 11650 (0.0007) -[2023-10-17 00:44:06,784][62373] Updated weights for policy 0, policy_version 11750 (0.0008) -[2023-10-17 00:44:07,116][62408] Updated weights for policy 1, policy_version 11660 (0.0008) -[2023-10-17 00:44:07,152][62373] Updated weights for policy 0, policy_version 11760 (0.0008) -[2023-10-17 00:44:07,214][61453] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 23953408. Throughput: 0: 1763.1, 1: 1740.0. Samples: 5999930. Policy #0 lag: (min: 31.0, avg: 43.2, max: 63.0) -[2023-10-17 00:44:07,215][61453] Avg episode reward: [(0, '4.970'), (1, '4.700')] -[2023-10-17 00:44:07,484][62408] Updated weights for policy 1, policy_version 11670 (0.0007) -[2023-10-17 00:44:07,524][62373] Updated weights for policy 0, policy_version 11770 (0.0008) -[2023-10-17 00:44:07,854][62408] Updated weights for policy 1, policy_version 11680 (0.0008) -[2023-10-17 00:44:11,405][62373] Updated weights for policy 0, policy_version 11780 (0.0007) -[2023-10-17 00:44:11,615][62408] Updated weights for policy 1, policy_version 11690 (0.0007) -[2023-10-17 00:44:11,779][62373] Updated weights for policy 0, policy_version 11790 (0.0007) -[2023-10-17 00:44:11,983][62408] Updated weights for policy 1, policy_version 11700 (0.0007) -[2023-10-17 00:44:12,141][62373] Updated weights for policy 0, policy_version 11800 (0.0009) -[2023-10-17 00:44:12,214][61453] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 24018944. Throughput: 0: 1783.8, 1: 1767.3. Samples: 6021958. Policy #0 lag: (min: 9.0, avg: 10.6, max: 32.0) -[2023-10-17 00:44:12,215][61453] Avg episode reward: [(0, '4.640'), (1, '4.840')] -[2023-10-17 00:44:12,351][62408] Updated weights for policy 1, policy_version 11710 (0.0007) -[2023-10-17 00:44:16,144][62408] Updated weights for policy 1, policy_version 11720 (0.0008) -[2023-10-17 00:44:16,159][62373] Updated weights for policy 0, policy_version 11810 (0.0007) -[2023-10-17 00:44:16,504][62408] Updated weights for policy 1, policy_version 11730 (0.0008) -[2023-10-17 00:44:16,528][62373] Updated weights for policy 0, policy_version 11820 (0.0008) -[2023-10-17 00:44:16,861][62408] Updated weights for policy 1, policy_version 11740 (0.0008) -[2023-10-17 00:44:16,896][62373] Updated weights for policy 0, policy_version 11830 (0.0008) -[2023-10-17 00:44:17,214][61453] Fps is (10 sec: 16384.3, 60 sec: 13653.4, 300 sec: 14218.0). Total num frames: 24117248. Throughput: 0: 1765.3, 1: 1736.9. Samples: 6041802. Policy #0 lag: (min: 9.0, avg: 10.6, max: 32.0) -[2023-10-17 00:44:17,215][61453] Avg episode reward: [(0, '4.690'), (1, '5.200')] -[2023-10-17 00:44:17,265][62373] Updated weights for policy 0, policy_version 11840 (0.0010) -[2023-10-17 00:44:20,764][62408] Updated weights for policy 1, policy_version 11750 (0.0008) -[2023-10-17 00:44:21,045][62373] Updated weights for policy 0, policy_version 11850 (0.0007) -[2023-10-17 00:44:21,133][62408] Updated weights for policy 1, policy_version 11760 (0.0009) -[2023-10-17 00:44:21,426][62373] Updated weights for policy 0, policy_version 11860 (0.0007) -[2023-10-17 00:44:21,491][62408] Updated weights for policy 1, policy_version 11770 (0.0008) -[2023-10-17 00:44:21,799][62373] Updated weights for policy 0, policy_version 11870 (0.0008) -[2023-10-17 00:44:22,214][61453] Fps is (10 sec: 19661.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 24215552. Throughput: 0: 1781.3, 1: 1762.4. Samples: 6053586. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-17 00:44:22,215][61453] Avg episode reward: [(0, '4.580'), (1, '5.130')] -[2023-10-17 00:44:25,411][62408] Updated weights for policy 1, policy_version 11780 (0.0009) -[2023-10-17 00:44:25,715][62373] Updated weights for policy 0, policy_version 11880 (0.0007) -[2023-10-17 00:44:25,765][62408] Updated weights for policy 1, policy_version 11790 (0.0011) -[2023-10-17 00:44:26,091][62373] Updated weights for policy 0, policy_version 11890 (0.0009) -[2023-10-17 00:44:26,133][62408] Updated weights for policy 1, policy_version 11800 (0.0009) -[2023-10-17 00:44:26,468][62373] Updated weights for policy 0, policy_version 11900 (0.0009) -[2023-10-17 00:44:27,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 24281088. Throughput: 0: 1777.6, 1: 1741.1. Samples: 6073774. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-17 00:44:27,215][61453] Avg episode reward: [(0, '4.820'), (1, '4.790')] -[2023-10-17 00:44:29,836][62408] Updated weights for policy 1, policy_version 11810 (0.0010) -[2023-10-17 00:44:30,207][62408] Updated weights for policy 1, policy_version 11820 (0.0009) -[2023-10-17 00:44:30,305][62373] Updated weights for policy 0, policy_version 11910 (0.0009) -[2023-10-17 00:44:30,565][62408] Updated weights for policy 1, policy_version 11830 (0.0008) -[2023-10-17 00:44:30,684][62373] Updated weights for policy 0, policy_version 11920 (0.0010) -[2023-10-17 00:44:30,934][62408] Updated weights for policy 1, policy_version 11840 (0.0008) -[2023-10-17 00:44:31,047][62373] Updated weights for policy 0, policy_version 11930 (0.0011) -[2023-10-17 00:44:32,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 24346624. Throughput: 0: 1756.4, 1: 1727.9. Samples: 6094170. Policy #0 lag: (min: 1.0, avg: 12.8, max: 33.0) -[2023-10-17 00:44:32,215][61453] Avg episode reward: [(0, '4.810'), (1, '4.840')] -[2023-10-17 00:44:34,831][62373] Updated weights for policy 0, policy_version 11940 (0.0008) -[2023-10-17 00:44:34,963][62408] Updated weights for policy 1, policy_version 11850 (0.0009) -[2023-10-17 00:44:35,196][62373] Updated weights for policy 0, policy_version 11950 (0.0010) -[2023-10-17 00:44:35,336][62408] Updated weights for policy 1, policy_version 11860 (0.0008) -[2023-10-17 00:44:35,572][62373] Updated weights for policy 0, policy_version 11960 (0.0009) -[2023-10-17 00:44:35,701][62408] Updated weights for policy 1, policy_version 11870 (0.0007) -[2023-10-17 00:44:37,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 24412160. Throughput: 0: 1783.7, 1: 1754.6. Samples: 6106080. Policy #0 lag: (min: 1.0, avg: 12.8, max: 33.0) -[2023-10-17 00:44:37,215][61453] Avg episode reward: [(0, '4.860'), (1, '4.870')] -[2023-10-17 00:44:39,350][62373] Updated weights for policy 0, policy_version 11970 (0.0008) -[2023-10-17 00:44:39,549][62408] Updated weights for policy 1, policy_version 11880 (0.0009) -[2023-10-17 00:44:39,726][62373] Updated weights for policy 0, policy_version 11980 (0.0007) -[2023-10-17 00:44:39,920][62408] Updated weights for policy 1, policy_version 11890 (0.0007) -[2023-10-17 00:44:40,097][62373] Updated weights for policy 0, policy_version 11990 (0.0008) -[2023-10-17 00:44:40,279][62408] Updated weights for policy 1, policy_version 11900 (0.0008) -[2023-10-17 00:44:40,468][62373] Updated weights for policy 0, policy_version 12000 (0.0008) -[2023-10-17 00:44:42,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 24477696. Throughput: 0: 1757.1, 1: 1738.4. Samples: 6125752. Policy #0 lag: (min: 31.0, avg: 32.1, max: 54.0) -[2023-10-17 00:44:42,215][61453] Avg episode reward: [(0, '5.120'), (1, '5.150')] -[2023-10-17 00:44:44,108][62373] Updated weights for policy 0, policy_version 12010 (0.0008) -[2023-10-17 00:44:44,148][62408] Updated weights for policy 1, policy_version 11910 (0.0010) -[2023-10-17 00:44:44,470][62373] Updated weights for policy 0, policy_version 12020 (0.0007) -[2023-10-17 00:44:44,521][62408] Updated weights for policy 1, policy_version 11920 (0.0010) -[2023-10-17 00:44:44,839][62373] Updated weights for policy 0, policy_version 12030 (0.0007) -[2023-10-17 00:44:44,891][62408] Updated weights for policy 1, policy_version 11930 (0.0008) -[2023-10-17 00:44:47,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 24543232. Throughput: 0: 1757.2, 1: 1734.8. Samples: 6147716. Policy #0 lag: (min: 31.0, avg: 32.1, max: 54.0) -[2023-10-17 00:44:47,215][61453] Avg episode reward: [(0, '5.150'), (1, '5.090')] -[2023-10-17 00:44:48,658][62373] Updated weights for policy 0, policy_version 12040 (0.0009) -[2023-10-17 00:44:48,914][62408] Updated weights for policy 1, policy_version 11940 (0.0008) -[2023-10-17 00:44:49,036][62373] Updated weights for policy 0, policy_version 12050 (0.0009) -[2023-10-17 00:44:49,285][62408] Updated weights for policy 1, policy_version 11950 (0.0009) -[2023-10-17 00:44:49,399][62373] Updated weights for policy 0, policy_version 12060 (0.0008) -[2023-10-17 00:44:49,661][62408] Updated weights for policy 1, policy_version 11960 (0.0008) -[2023-10-17 00:44:52,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 24608768. Throughput: 0: 1758.8, 1: 1739.4. Samples: 6157352. Policy #0 lag: (min: 31.0, avg: 32.1, max: 54.0) -[2023-10-17 00:44:52,215][61453] Avg episode reward: [(0, '4.990'), (1, '4.910')] -[2023-10-17 00:44:53,208][62373] Updated weights for policy 0, policy_version 12070 (0.0007) -[2023-10-17 00:44:53,305][62408] Updated weights for policy 1, policy_version 11970 (0.0009) -[2023-10-17 00:44:53,572][62373] Updated weights for policy 0, policy_version 12080 (0.0009) -[2023-10-17 00:44:53,677][62408] Updated weights for policy 1, policy_version 11980 (0.0007) -[2023-10-17 00:44:53,950][62373] Updated weights for policy 0, policy_version 12090 (0.0008) -[2023-10-17 00:44:54,044][62408] Updated weights for policy 1, policy_version 11990 (0.0007) -[2023-10-17 00:44:54,407][62408] Updated weights for policy 1, policy_version 12000 (0.0008) -[2023-10-17 00:44:57,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 24674304. Throughput: 0: 1763.2, 1: 1739.1. Samples: 6179562. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-17 00:44:57,214][61453] Avg episode reward: [(0, '4.610'), (1, '4.660')] -[2023-10-17 00:44:57,787][62373] Updated weights for policy 0, policy_version 12100 (0.0009) -[2023-10-17 00:44:58,134][62408] Updated weights for policy 1, policy_version 12010 (0.0007) -[2023-10-17 00:44:58,156][62373] Updated weights for policy 0, policy_version 12110 (0.0007) -[2023-10-17 00:44:58,509][62408] Updated weights for policy 1, policy_version 12020 (0.0009) -[2023-10-17 00:44:58,537][62373] Updated weights for policy 0, policy_version 12120 (0.0007) -[2023-10-17 00:44:58,883][62408] Updated weights for policy 1, policy_version 12030 (0.0008) -[2023-10-17 00:45:02,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 24739840. Throughput: 0: 1787.2, 1: 1766.5. Samples: 6201720. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-17 00:45:02,215][61453] Avg episode reward: [(0, '4.790'), (1, '4.980')] -[2023-10-17 00:45:02,336][62373] Updated weights for policy 0, policy_version 12130 (0.0008) -[2023-10-17 00:45:02,679][62408] Updated weights for policy 1, policy_version 12040 (0.0008) -[2023-10-17 00:45:02,704][62373] Updated weights for policy 0, policy_version 12140 (0.0008) -[2023-10-17 00:45:03,052][62408] Updated weights for policy 1, policy_version 12050 (0.0009) -[2023-10-17 00:45:03,082][62373] Updated weights for policy 0, policy_version 12150 (0.0009) -[2023-10-17 00:45:03,424][62408] Updated weights for policy 1, policy_version 12060 (0.0008) -[2023-10-17 00:45:03,448][62373] Updated weights for policy 0, policy_version 12160 (0.0009) -[2023-10-17 00:45:07,139][62373] Updated weights for policy 0, policy_version 12170 (0.0007) -[2023-10-17 00:45:07,213][62408] Updated weights for policy 1, policy_version 12070 (0.0009) -[2023-10-17 00:45:07,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 24805376. Throughput: 0: 1762.6, 1: 1743.7. Samples: 6211370. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-17 00:45:07,214][61453] Avg episode reward: [(0, '5.000'), (1, '4.530')] -[2023-10-17 00:45:07,505][62373] Updated weights for policy 0, policy_version 12180 (0.0007) -[2023-10-17 00:45:07,587][62408] Updated weights for policy 1, policy_version 12080 (0.0008) -[2023-10-17 00:45:07,870][62373] Updated weights for policy 0, policy_version 12190 (0.0007) -[2023-10-17 00:45:07,957][62408] Updated weights for policy 1, policy_version 12090 (0.0009) -[2023-10-17 00:45:11,664][62373] Updated weights for policy 0, policy_version 12200 (0.0009) -[2023-10-17 00:45:11,881][62408] Updated weights for policy 1, policy_version 12100 (0.0009) -[2023-10-17 00:45:12,040][62373] Updated weights for policy 0, policy_version 12210 (0.0008) -[2023-10-17 00:45:12,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 24870912. Throughput: 0: 1780.8, 1: 1767.8. Samples: 6233464. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-17 00:45:12,215][61453] Avg episode reward: [(0, '4.620'), (1, '4.340')] -[2023-10-17 00:45:12,253][62408] Updated weights for policy 1, policy_version 12110 (0.0007) -[2023-10-17 00:45:12,416][62373] Updated weights for policy 0, policy_version 12220 (0.0008) -[2023-10-17 00:45:12,614][62408] Updated weights for policy 1, policy_version 12120 (0.0009) -[2023-10-17 00:45:16,286][62373] Updated weights for policy 0, policy_version 12230 (0.0009) -[2023-10-17 00:45:16,472][62408] Updated weights for policy 1, policy_version 12130 (0.0009) -[2023-10-17 00:45:16,673][62373] Updated weights for policy 0, policy_version 12240 (0.0008) -[2023-10-17 00:45:16,840][62408] Updated weights for policy 1, policy_version 12140 (0.0009) -[2023-10-17 00:45:17,031][62373] Updated weights for policy 0, policy_version 12250 (0.0010) -[2023-10-17 00:45:17,213][62408] Updated weights for policy 1, policy_version 12150 (0.0010) -[2023-10-17 00:45:17,214][61453] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 24936448. Throughput: 0: 1771.5, 1: 1771.9. Samples: 6253622. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-17 00:45:17,215][61453] Avg episode reward: [(0, '4.950'), (1, '4.410')] -[2023-10-17 00:45:17,590][62408] Updated weights for policy 1, policy_version 12160 (0.0007) -[2023-10-17 00:45:20,690][62373] Updated weights for policy 0, policy_version 12260 (0.0009) -[2023-10-17 00:45:21,056][62373] Updated weights for policy 0, policy_version 12270 (0.0010) -[2023-10-17 00:45:21,307][62408] Updated weights for policy 1, policy_version 12170 (0.0007) -[2023-10-17 00:45:21,431][62373] Updated weights for policy 0, policy_version 12280 (0.0008) -[2023-10-17 00:45:21,676][62408] Updated weights for policy 1, policy_version 12180 (0.0009) -[2023-10-17 00:45:22,040][62408] Updated weights for policy 1, policy_version 12190 (0.0010) -[2023-10-17 00:45:22,214][61453] Fps is (10 sec: 19660.7, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 25067520. Throughput: 0: 1772.0, 1: 1756.8. Samples: 6264876. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:45:22,215][61453] Avg episode reward: [(0, '4.950'), (1, '4.540')] -[2023-10-17 00:45:25,124][62373] Updated weights for policy 0, policy_version 12290 (0.0008) -[2023-10-17 00:45:25,485][62373] Updated weights for policy 0, policy_version 12300 (0.0008) -[2023-10-17 00:45:25,857][62373] Updated weights for policy 0, policy_version 12310 (0.0007) -[2023-10-17 00:45:25,990][62408] Updated weights for policy 1, policy_version 12200 (0.0008) -[2023-10-17 00:45:26,231][62373] Updated weights for policy 0, policy_version 12320 (0.0008) -[2023-10-17 00:45:26,365][62408] Updated weights for policy 1, policy_version 12210 (0.0010) -[2023-10-17 00:45:26,732][62408] Updated weights for policy 1, policy_version 12220 (0.0010) -[2023-10-17 00:45:27,214][61453] Fps is (10 sec: 19661.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 25133056. Throughput: 0: 1781.4, 1: 1778.8. Samples: 6285960. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:45:27,215][61453] Avg episode reward: [(0, '5.030'), (1, '4.730')] -[2023-10-17 00:45:30,235][62373] Updated weights for policy 0, policy_version 12330 (0.0009) -[2023-10-17 00:45:30,605][62373] Updated weights for policy 0, policy_version 12340 (0.0009) -[2023-10-17 00:45:30,651][62408] Updated weights for policy 1, policy_version 12230 (0.0009) -[2023-10-17 00:45:30,963][62373] Updated weights for policy 0, policy_version 12350 (0.0007) -[2023-10-17 00:45:31,015][62408] Updated weights for policy 1, policy_version 12240 (0.0009) -[2023-10-17 00:45:31,374][62408] Updated weights for policy 1, policy_version 12250 (0.0010) -[2023-10-17 00:45:32,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 25198592. Throughput: 0: 1766.9, 1: 1755.5. Samples: 6306226. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:45:32,215][61453] Avg episode reward: [(0, '4.920'), (1, '4.940')] -[2023-10-17 00:45:32,223][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000012256_12550144.pth... -[2023-10-17 00:45:32,223][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000012352_12648448.pth... -[2023-10-17 00:45:32,255][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000010592_10846208.pth -[2023-10-17 00:45:32,258][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000010688_10944512.pth -[2023-10-17 00:45:34,964][62373] Updated weights for policy 0, policy_version 12360 (0.0009) -[2023-10-17 00:45:35,330][62373] Updated weights for policy 0, policy_version 12370 (0.0007) -[2023-10-17 00:45:35,341][62408] Updated weights for policy 1, policy_version 12260 (0.0010) -[2023-10-17 00:45:35,699][62373] Updated weights for policy 0, policy_version 12380 (0.0007) -[2023-10-17 00:45:35,702][62408] Updated weights for policy 1, policy_version 12270 (0.0009) -[2023-10-17 00:45:36,068][62408] Updated weights for policy 1, policy_version 12280 (0.0009) -[2023-10-17 00:45:37,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 25264128. Throughput: 0: 1789.9, 1: 1781.4. Samples: 6318060. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-17 00:45:37,215][61453] Avg episode reward: [(0, '4.710'), (1, '4.980')] -[2023-10-17 00:45:39,450][62373] Updated weights for policy 0, policy_version 12390 (0.0009) -[2023-10-17 00:45:39,818][62373] Updated weights for policy 0, policy_version 12400 (0.0008) -[2023-10-17 00:45:40,087][62408] Updated weights for policy 1, policy_version 12290 (0.0010) -[2023-10-17 00:45:40,192][62373] Updated weights for policy 0, policy_version 12410 (0.0008) -[2023-10-17 00:45:40,443][62408] Updated weights for policy 1, policy_version 12300 (0.0011) -[2023-10-17 00:45:40,805][62408] Updated weights for policy 1, policy_version 12310 (0.0011) -[2023-10-17 00:45:41,168][62408] Updated weights for policy 1, policy_version 12320 (0.0008) -[2023-10-17 00:45:42,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 25329664. Throughput: 0: 1762.7, 1: 1755.4. Samples: 6337874. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-17 00:45:42,215][61453] Avg episode reward: [(0, '4.780'), (1, '5.420')] -[2023-10-17 00:45:42,217][62252] Saving new best policy, reward=5.420! -[2023-10-17 00:45:44,051][62373] Updated weights for policy 0, policy_version 12420 (0.0009) -[2023-10-17 00:45:44,414][62373] Updated weights for policy 0, policy_version 12430 (0.0009) -[2023-10-17 00:45:44,787][62373] Updated weights for policy 0, policy_version 12440 (0.0009) -[2023-10-17 00:45:44,791][62408] Updated weights for policy 1, policy_version 12330 (0.0008) -[2023-10-17 00:45:45,152][62408] Updated weights for policy 1, policy_version 12340 (0.0009) -[2023-10-17 00:45:45,518][62408] Updated weights for policy 1, policy_version 12350 (0.0007) -[2023-10-17 00:45:47,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 25395200. Throughput: 0: 1767.7, 1: 1737.6. Samples: 6359460. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-17 00:45:47,215][61453] Avg episode reward: [(0, '4.720'), (1, '5.170')] -[2023-10-17 00:45:48,388][62373] Updated weights for policy 0, policy_version 12450 (0.0008) -[2023-10-17 00:45:48,751][62373] Updated weights for policy 0, policy_version 12460 (0.0008) -[2023-10-17 00:45:49,119][62373] Updated weights for policy 0, policy_version 12470 (0.0010) -[2023-10-17 00:45:49,496][62373] Updated weights for policy 0, policy_version 12480 (0.0008) -[2023-10-17 00:45:49,562][62408] Updated weights for policy 1, policy_version 12360 (0.0009) -[2023-10-17 00:45:49,928][62408] Updated weights for policy 1, policy_version 12370 (0.0009) -[2023-10-17 00:45:50,294][62408] Updated weights for policy 1, policy_version 12380 (0.0008) -[2023-10-17 00:45:52,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 25460736. Throughput: 0: 1771.8, 1: 1749.2. Samples: 6369814. Policy #0 lag: (min: 31.0, avg: 33.0, max: 60.0) -[2023-10-17 00:45:52,215][61453] Avg episode reward: [(0, '4.660'), (1, '4.520')] -[2023-10-17 00:45:53,161][62373] Updated weights for policy 0, policy_version 12490 (0.0007) -[2023-10-17 00:45:53,531][62373] Updated weights for policy 0, policy_version 12500 (0.0007) -[2023-10-17 00:45:53,903][62373] Updated weights for policy 0, policy_version 12510 (0.0008) -[2023-10-17 00:45:54,292][62408] Updated weights for policy 1, policy_version 12390 (0.0009) -[2023-10-17 00:45:54,668][62408] Updated weights for policy 1, policy_version 12400 (0.0011) -[2023-10-17 00:45:55,032][62408] Updated weights for policy 1, policy_version 12410 (0.0009) -[2023-10-17 00:45:57,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 25526272. Throughput: 0: 1774.0, 1: 1730.2. Samples: 6391152. Policy #0 lag: (min: 31.0, avg: 33.0, max: 60.0) -[2023-10-17 00:45:57,215][61453] Avg episode reward: [(0, '4.810'), (1, '4.510')] -[2023-10-17 00:45:57,746][62373] Updated weights for policy 0, policy_version 12520 (0.0007) -[2023-10-17 00:45:58,115][62373] Updated weights for policy 0, policy_version 12530 (0.0007) -[2023-10-17 00:45:58,492][62373] Updated weights for policy 0, policy_version 12540 (0.0008) -[2023-10-17 00:45:58,954][62408] Updated weights for policy 1, policy_version 12420 (0.0008) -[2023-10-17 00:45:59,318][62408] Updated weights for policy 1, policy_version 12430 (0.0008) -[2023-10-17 00:45:59,680][62408] Updated weights for policy 1, policy_version 12440 (0.0008) -[2023-10-17 00:46:02,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 25591808. Throughput: 0: 1803.0, 1: 1742.5. Samples: 6413172. Policy #0 lag: (min: 31.0, avg: 33.0, max: 60.0) -[2023-10-17 00:46:02,214][61453] Avg episode reward: [(0, '4.790'), (1, '4.210')] -[2023-10-17 00:46:02,390][62373] Updated weights for policy 0, policy_version 12550 (0.0008) -[2023-10-17 00:46:02,772][62373] Updated weights for policy 0, policy_version 12560 (0.0007) -[2023-10-17 00:46:03,149][62373] Updated weights for policy 0, policy_version 12570 (0.0009) -[2023-10-17 00:46:03,557][62408] Updated weights for policy 1, policy_version 12450 (0.0009) -[2023-10-17 00:46:03,940][62408] Updated weights for policy 1, policy_version 12460 (0.0008) -[2023-10-17 00:46:04,304][62408] Updated weights for policy 1, policy_version 12470 (0.0007) -[2023-10-17 00:46:04,680][62408] Updated weights for policy 1, policy_version 12480 (0.0009) -[2023-10-17 00:46:06,874][62373] Updated weights for policy 0, policy_version 12580 (0.0010) -[2023-10-17 00:46:07,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 25657344. Throughput: 0: 1774.8, 1: 1733.5. Samples: 6422748. Policy #0 lag: (min: 12.0, avg: 16.2, max: 44.0) -[2023-10-17 00:46:07,214][61453] Avg episode reward: [(0, '4.760'), (1, '4.340')] -[2023-10-17 00:46:07,240][62373] Updated weights for policy 0, policy_version 12590 (0.0007) -[2023-10-17 00:46:07,624][62373] Updated weights for policy 0, policy_version 12600 (0.0008) -[2023-10-17 00:46:08,577][62408] Updated weights for policy 1, policy_version 12490 (0.0008) -[2023-10-17 00:46:08,951][62408] Updated weights for policy 1, policy_version 12500 (0.0008) -[2023-10-17 00:46:09,322][62408] Updated weights for policy 1, policy_version 12510 (0.0007) -[2023-10-17 00:46:11,386][62373] Updated weights for policy 0, policy_version 12610 (0.0009) -[2023-10-17 00:46:11,754][62373] Updated weights for policy 0, policy_version 12620 (0.0007) -[2023-10-17 00:46:12,119][62373] Updated weights for policy 0, policy_version 12630 (0.0008) -[2023-10-17 00:46:12,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 25722880. Throughput: 0: 1796.4, 1: 1735.2. Samples: 6444880. Policy #0 lag: (min: 12.0, avg: 16.2, max: 44.0) -[2023-10-17 00:46:12,215][61453] Avg episode reward: [(0, '4.420'), (1, '4.620')] -[2023-10-17 00:46:12,483][62373] Updated weights for policy 0, policy_version 12640 (0.0010) -[2023-10-17 00:46:13,227][62408] Updated weights for policy 1, policy_version 12520 (0.0009) -[2023-10-17 00:46:13,600][62408] Updated weights for policy 1, policy_version 12530 (0.0007) -[2023-10-17 00:46:13,965][62408] Updated weights for policy 1, policy_version 12540 (0.0007) -[2023-10-17 00:46:16,302][62373] Updated weights for policy 0, policy_version 12650 (0.0009) -[2023-10-17 00:46:16,669][62373] Updated weights for policy 0, policy_version 12660 (0.0008) -[2023-10-17 00:46:17,033][62373] Updated weights for policy 0, policy_version 12670 (0.0008) -[2023-10-17 00:46:17,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14106.9). Total num frames: 25821184. Throughput: 0: 1783.2, 1: 1760.7. Samples: 6465700. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-17 00:46:17,215][61453] Avg episode reward: [(0, '4.750'), (1, '5.050')] -[2023-10-17 00:46:17,892][62408] Updated weights for policy 1, policy_version 12550 (0.0009) -[2023-10-17 00:46:18,285][62408] Updated weights for policy 1, policy_version 12560 (0.0009) -[2023-10-17 00:46:18,660][62408] Updated weights for policy 1, policy_version 12570 (0.0009) -[2023-10-17 00:46:20,941][62373] Updated weights for policy 0, policy_version 12680 (0.0008) -[2023-10-17 00:46:21,318][62373] Updated weights for policy 0, policy_version 12690 (0.0009) -[2023-10-17 00:46:21,687][62373] Updated weights for policy 0, policy_version 12700 (0.0008) -[2023-10-17 00:46:22,214][61453] Fps is (10 sec: 16383.7, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 25886720. Throughput: 0: 1787.1, 1: 1731.0. Samples: 6476374. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-17 00:46:22,215][61453] Avg episode reward: [(0, '4.490'), (1, '4.870')] -[2023-10-17 00:46:22,387][62408] Updated weights for policy 1, policy_version 12580 (0.0009) -[2023-10-17 00:46:22,754][62408] Updated weights for policy 1, policy_version 12590 (0.0008) -[2023-10-17 00:46:23,124][62408] Updated weights for policy 1, policy_version 12600 (0.0007) -[2023-10-17 00:46:25,405][62373] Updated weights for policy 0, policy_version 12710 (0.0009) -[2023-10-17 00:46:25,774][62373] Updated weights for policy 0, policy_version 12720 (0.0008) -[2023-10-17 00:46:26,136][62373] Updated weights for policy 0, policy_version 12730 (0.0008) -[2023-10-17 00:46:26,676][62408] Updated weights for policy 1, policy_version 12610 (0.0010) -[2023-10-17 00:46:27,051][62408] Updated weights for policy 1, policy_version 12620 (0.0010) -[2023-10-17 00:46:27,214][61453] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 25952256. Throughput: 0: 1796.1, 1: 1761.2. Samples: 6497950. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-17 00:46:27,215][61453] Avg episode reward: [(0, '4.560'), (1, '5.000')] -[2023-10-17 00:46:27,421][62408] Updated weights for policy 1, policy_version 12630 (0.0007) -[2023-10-17 00:46:27,788][62408] Updated weights for policy 1, policy_version 12640 (0.0008) -[2023-10-17 00:46:29,899][62373] Updated weights for policy 0, policy_version 12740 (0.0010) -[2023-10-17 00:46:30,273][62373] Updated weights for policy 0, policy_version 12750 (0.0008) -[2023-10-17 00:46:30,642][62373] Updated weights for policy 0, policy_version 12760 (0.0008) -[2023-10-17 00:46:31,615][62408] Updated weights for policy 1, policy_version 12650 (0.0012) -[2023-10-17 00:46:31,980][62408] Updated weights for policy 1, policy_version 12660 (0.0011) -[2023-10-17 00:46:32,214][61453] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 26017792. Throughput: 0: 1783.2, 1: 1761.7. Samples: 6518982. Policy #0 lag: (min: 31.0, avg: 31.9, max: 52.0) -[2023-10-17 00:46:32,215][61453] Avg episode reward: [(0, '4.380'), (1, '4.610')] -[2023-10-17 00:46:32,349][62408] Updated weights for policy 1, policy_version 12670 (0.0008) -[2023-10-17 00:46:34,367][62373] Updated weights for policy 0, policy_version 12770 (0.0007) -[2023-10-17 00:46:34,743][62373] Updated weights for policy 0, policy_version 12780 (0.0007) -[2023-10-17 00:46:35,110][62373] Updated weights for policy 0, policy_version 12790 (0.0007) -[2023-10-17 00:46:35,478][62373] Updated weights for policy 0, policy_version 12800 (0.0008) -[2023-10-17 00:46:36,011][62408] Updated weights for policy 1, policy_version 12680 (0.0010) -[2023-10-17 00:46:36,377][62408] Updated weights for policy 1, policy_version 12690 (0.0009) -[2023-10-17 00:46:36,742][62408] Updated weights for policy 1, policy_version 12700 (0.0009) -[2023-10-17 00:46:37,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 26116096. Throughput: 0: 1794.7, 1: 1767.4. Samples: 6530108. Policy #0 lag: (min: 31.0, avg: 31.9, max: 52.0) -[2023-10-17 00:46:37,215][61453] Avg episode reward: [(0, '4.150'), (1, '4.740')] -[2023-10-17 00:46:39,256][62373] Updated weights for policy 0, policy_version 12810 (0.0009) -[2023-10-17 00:46:39,636][62373] Updated weights for policy 0, policy_version 12820 (0.0008) -[2023-10-17 00:46:40,001][62373] Updated weights for policy 0, policy_version 12830 (0.0008) -[2023-10-17 00:46:40,803][62408] Updated weights for policy 1, policy_version 12710 (0.0010) -[2023-10-17 00:46:41,165][62408] Updated weights for policy 1, policy_version 12720 (0.0009) -[2023-10-17 00:46:41,535][62408] Updated weights for policy 1, policy_version 12730 (0.0010) -[2023-10-17 00:46:42,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 26181632. Throughput: 0: 1772.6, 1: 1777.1. Samples: 6550888. Policy #0 lag: (min: 31.0, avg: 31.9, max: 52.0) -[2023-10-17 00:46:42,215][61453] Avg episode reward: [(0, '4.390'), (1, '4.590')] -[2023-10-17 00:46:43,636][62373] Updated weights for policy 0, policy_version 12840 (0.0007) -[2023-10-17 00:46:44,018][62373] Updated weights for policy 0, policy_version 12850 (0.0009) -[2023-10-17 00:46:44,395][62373] Updated weights for policy 0, policy_version 12860 (0.0009) -[2023-10-17 00:46:45,264][62408] Updated weights for policy 1, policy_version 12740 (0.0008) -[2023-10-17 00:46:45,624][62408] Updated weights for policy 1, policy_version 12750 (0.0009) -[2023-10-17 00:46:45,993][62408] Updated weights for policy 1, policy_version 12760 (0.0008) -[2023-10-17 00:46:47,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 26247168. Throughput: 0: 1774.6, 1: 1756.7. Samples: 6572082. Policy #0 lag: (min: 29.0, avg: 54.1, max: 56.0) -[2023-10-17 00:46:47,215][61453] Avg episode reward: [(0, '4.530'), (1, '4.920')] -[2023-10-17 00:46:48,427][62373] Updated weights for policy 0, policy_version 12870 (0.0009) -[2023-10-17 00:46:48,810][62373] Updated weights for policy 0, policy_version 12880 (0.0008) -[2023-10-17 00:46:49,176][62373] Updated weights for policy 0, policy_version 12890 (0.0010) -[2023-10-17 00:46:49,862][62408] Updated weights for policy 1, policy_version 12770 (0.0007) -[2023-10-17 00:46:50,237][62408] Updated weights for policy 1, policy_version 12780 (0.0007) -[2023-10-17 00:46:50,601][62408] Updated weights for policy 1, policy_version 12790 (0.0007) -[2023-10-17 00:46:50,970][62408] Updated weights for policy 1, policy_version 12800 (0.0008) -[2023-10-17 00:46:52,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 26312704. Throughput: 0: 1773.8, 1: 1785.1. Samples: 6582896. Policy #0 lag: (min: 29.0, avg: 54.1, max: 56.0) -[2023-10-17 00:46:52,214][61453] Avg episode reward: [(0, '4.560'), (1, '5.320')] -[2023-10-17 00:46:52,961][62373] Updated weights for policy 0, policy_version 12900 (0.0009) -[2023-10-17 00:46:53,327][62373] Updated weights for policy 0, policy_version 12910 (0.0008) -[2023-10-17 00:46:53,697][62373] Updated weights for policy 0, policy_version 12920 (0.0008) -[2023-10-17 00:46:54,649][62408] Updated weights for policy 1, policy_version 12810 (0.0009) -[2023-10-17 00:46:55,027][62408] Updated weights for policy 1, policy_version 12820 (0.0008) -[2023-10-17 00:46:55,404][62408] Updated weights for policy 1, policy_version 12830 (0.0010) -[2023-10-17 00:46:57,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 26378240. Throughput: 0: 1773.6, 1: 1760.7. Samples: 6603926. Policy #0 lag: (min: 29.0, avg: 54.1, max: 56.0) -[2023-10-17 00:46:57,215][61453] Avg episode reward: [(0, '5.060'), (1, '5.180')] -[2023-10-17 00:46:57,458][62373] Updated weights for policy 0, policy_version 12930 (0.0009) -[2023-10-17 00:46:57,825][62373] Updated weights for policy 0, policy_version 12940 (0.0009) -[2023-10-17 00:46:58,199][62373] Updated weights for policy 0, policy_version 12950 (0.0009) -[2023-10-17 00:46:58,567][62373] Updated weights for policy 0, policy_version 12960 (0.0010) -[2023-10-17 00:46:59,156][62408] Updated weights for policy 1, policy_version 12840 (0.0010) -[2023-10-17 00:46:59,528][62408] Updated weights for policy 1, policy_version 12850 (0.0008) -[2023-10-17 00:46:59,892][62408] Updated weights for policy 1, policy_version 12860 (0.0009) -[2023-10-17 00:47:02,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 26443776. Throughput: 0: 1797.6, 1: 1764.0. Samples: 6625970. Policy #0 lag: (min: 1.0, avg: 2.4, max: 27.0) -[2023-10-17 00:47:02,215][61453] Avg episode reward: [(0, '4.890'), (1, '5.380')] -[2023-10-17 00:47:02,380][62373] Updated weights for policy 0, policy_version 12970 (0.0008) -[2023-10-17 00:47:02,760][62373] Updated weights for policy 0, policy_version 12980 (0.0009) -[2023-10-17 00:47:03,124][62373] Updated weights for policy 0, policy_version 12990 (0.0010) -[2023-10-17 00:47:03,909][62408] Updated weights for policy 1, policy_version 12870 (0.0008) -[2023-10-17 00:47:04,298][62408] Updated weights for policy 1, policy_version 12880 (0.0007) -[2023-10-17 00:47:04,668][62408] Updated weights for policy 1, policy_version 12890 (0.0008) -[2023-10-17 00:47:06,843][62373] Updated weights for policy 0, policy_version 13000 (0.0009) -[2023-10-17 00:47:07,211][62373] Updated weights for policy 0, policy_version 13010 (0.0010) -[2023-10-17 00:47:07,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 26509312. Throughput: 0: 1772.4, 1: 1765.8. Samples: 6635596. Policy #0 lag: (min: 1.0, avg: 2.4, max: 27.0) -[2023-10-17 00:47:07,215][61453] Avg episode reward: [(0, '5.060'), (1, '5.460')] -[2023-10-17 00:47:07,216][62252] Saving new best policy, reward=5.460! -[2023-10-17 00:47:07,574][62373] Updated weights for policy 0, policy_version 13020 (0.0009) -[2023-10-17 00:47:08,404][62408] Updated weights for policy 1, policy_version 12900 (0.0007) -[2023-10-17 00:47:08,770][62408] Updated weights for policy 1, policy_version 12910 (0.0007) -[2023-10-17 00:47:09,141][62408] Updated weights for policy 1, policy_version 12920 (0.0007) -[2023-10-17 00:47:11,476][62373] Updated weights for policy 0, policy_version 13030 (0.0010) -[2023-10-17 00:47:11,849][62373] Updated weights for policy 0, policy_version 13040 (0.0010) -[2023-10-17 00:47:12,213][62373] Updated weights for policy 0, policy_version 13050 (0.0011) -[2023-10-17 00:47:12,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 26574848. Throughput: 0: 1787.6, 1: 1759.9. Samples: 6657588. Policy #0 lag: (min: 1.0, avg: 2.4, max: 27.0) -[2023-10-17 00:47:12,215][61453] Avg episode reward: [(0, '5.410'), (1, '5.380')] -[2023-10-17 00:47:12,812][62408] Updated weights for policy 1, policy_version 12930 (0.0010) -[2023-10-17 00:47:13,174][62408] Updated weights for policy 1, policy_version 12940 (0.0008) -[2023-10-17 00:47:13,545][62408] Updated weights for policy 1, policy_version 12950 (0.0010) -[2023-10-17 00:47:13,913][62408] Updated weights for policy 1, policy_version 12960 (0.0008) -[2023-10-17 00:47:16,070][62373] Updated weights for policy 0, policy_version 13060 (0.0009) -[2023-10-17 00:47:16,442][62373] Updated weights for policy 0, policy_version 13070 (0.0007) -[2023-10-17 00:47:16,814][62373] Updated weights for policy 0, policy_version 13080 (0.0007) -[2023-10-17 00:47:17,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 26673152. Throughput: 0: 1765.6, 1: 1778.7. Samples: 6678476. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:47:17,215][61453] Avg episode reward: [(0, '5.320'), (1, '4.910')] -[2023-10-17 00:47:17,770][62408] Updated weights for policy 1, policy_version 12970 (0.0011) -[2023-10-17 00:47:18,140][62408] Updated weights for policy 1, policy_version 12980 (0.0008) -[2023-10-17 00:47:18,505][62408] Updated weights for policy 1, policy_version 12990 (0.0007) -[2023-10-17 00:47:20,607][62373] Updated weights for policy 0, policy_version 13090 (0.0009) -[2023-10-17 00:47:20,979][62373] Updated weights for policy 0, policy_version 13100 (0.0011) -[2023-10-17 00:47:21,345][62373] Updated weights for policy 0, policy_version 13110 (0.0009) -[2023-10-17 00:47:21,716][62373] Updated weights for policy 0, policy_version 13120 (0.0010) -[2023-10-17 00:47:22,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 26738688. Throughput: 0: 1777.3, 1: 1760.3. Samples: 6689298. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:47:22,214][61453] Avg episode reward: [(0, '5.460'), (1, '5.030')] -[2023-10-17 00:47:22,336][62408] Updated weights for policy 1, policy_version 13000 (0.0008) -[2023-10-17 00:47:22,695][62408] Updated weights for policy 1, policy_version 13010 (0.0008) -[2023-10-17 00:47:23,065][62408] Updated weights for policy 1, policy_version 13020 (0.0010) -[2023-10-17 00:47:25,439][62373] Updated weights for policy 0, policy_version 13130 (0.0007) -[2023-10-17 00:47:25,827][62373] Updated weights for policy 0, policy_version 13140 (0.0008) -[2023-10-17 00:47:26,187][62373] Updated weights for policy 0, policy_version 13150 (0.0008) -[2023-10-17 00:47:26,943][62408] Updated weights for policy 1, policy_version 13030 (0.0008) -[2023-10-17 00:47:27,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 26804224. Throughput: 0: 1774.7, 1: 1770.3. Samples: 6710412. Policy #0 lag: (min: 13.0, avg: 22.7, max: 45.0) -[2023-10-17 00:47:27,214][61453] Avg episode reward: [(0, '5.470'), (1, '4.650')] -[2023-10-17 00:47:27,314][62408] Updated weights for policy 1, policy_version 13040 (0.0007) -[2023-10-17 00:47:27,683][62408] Updated weights for policy 1, policy_version 13050 (0.0009) -[2023-10-17 00:47:29,936][62373] Updated weights for policy 0, policy_version 13160 (0.0007) -[2023-10-17 00:47:30,312][62373] Updated weights for policy 0, policy_version 13170 (0.0007) -[2023-10-17 00:47:30,683][62373] Updated weights for policy 0, policy_version 13180 (0.0007) -[2023-10-17 00:47:31,556][62408] Updated weights for policy 1, policy_version 13060 (0.0009) -[2023-10-17 00:47:31,930][62408] Updated weights for policy 1, policy_version 13070 (0.0008) -[2023-10-17 00:47:32,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 26869760. Throughput: 0: 1766.8, 1: 1783.6. Samples: 6731846. Policy #0 lag: (min: 13.0, avg: 22.7, max: 45.0) -[2023-10-17 00:47:32,214][61453] Avg episode reward: [(0, '5.510'), (1, '4.570')] -[2023-10-17 00:47:32,223][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000013184_13500416.pth... -[2023-10-17 00:47:32,262][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000011520_11796480.pth -[2023-10-17 00:47:32,296][62408] Updated weights for policy 1, policy_version 13080 (0.0008) -[2023-10-17 00:47:32,598][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000013088_13402112.pth... -[2023-10-17 00:47:32,635][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000011424_11698176.pth -[2023-10-17 00:47:34,454][62373] Updated weights for policy 0, policy_version 13190 (0.0009) -[2023-10-17 00:47:34,837][62373] Updated weights for policy 0, policy_version 13200 (0.0010) -[2023-10-17 00:47:35,203][62373] Updated weights for policy 0, policy_version 13210 (0.0009) -[2023-10-17 00:47:36,352][62408] Updated weights for policy 1, policy_version 13090 (0.0010) -[2023-10-17 00:47:36,714][62408] Updated weights for policy 1, policy_version 13100 (0.0007) -[2023-10-17 00:47:37,089][62408] Updated weights for policy 1, policy_version 13110 (0.0008) -[2023-10-17 00:47:37,214][61453] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 26935296. Throughput: 0: 1782.4, 1: 1762.8. Samples: 6742430. Policy #0 lag: (min: 13.0, avg: 22.7, max: 45.0) -[2023-10-17 00:47:37,215][61453] Avg episode reward: [(0, '5.570'), (1, '4.740')] -[2023-10-17 00:47:37,460][62408] Updated weights for policy 1, policy_version 13120 (0.0010) -[2023-10-17 00:47:38,843][62373] Updated weights for policy 0, policy_version 13220 (0.0009) -[2023-10-17 00:47:39,222][62373] Updated weights for policy 0, policy_version 13230 (0.0008) -[2023-10-17 00:47:39,587][62373] Updated weights for policy 0, policy_version 13240 (0.0010) -[2023-10-17 00:47:41,143][62408] Updated weights for policy 1, policy_version 13130 (0.0009) -[2023-10-17 00:47:41,516][62408] Updated weights for policy 1, policy_version 13140 (0.0008) -[2023-10-17 00:47:41,894][62408] Updated weights for policy 1, policy_version 13150 (0.0011) -[2023-10-17 00:47:42,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 27033600. Throughput: 0: 1768.2, 1: 1788.6. Samples: 6763984. Policy #0 lag: (min: 8.0, avg: 36.3, max: 40.0) -[2023-10-17 00:47:42,215][61453] Avg episode reward: [(0, '4.970'), (1, '4.960')] -[2023-10-17 00:47:43,346][62373] Updated weights for policy 0, policy_version 13250 (0.0008) -[2023-10-17 00:47:43,719][62373] Updated weights for policy 0, policy_version 13260 (0.0010) -[2023-10-17 00:47:44,103][62373] Updated weights for policy 0, policy_version 13270 (0.0008) -[2023-10-17 00:47:44,474][62373] Updated weights for policy 0, policy_version 13280 (0.0007) -[2023-10-17 00:47:45,728][62408] Updated weights for policy 1, policy_version 13160 (0.0009) -[2023-10-17 00:47:46,098][62408] Updated weights for policy 1, policy_version 13170 (0.0009) -[2023-10-17 00:47:46,458][62408] Updated weights for policy 1, policy_version 13180 (0.0009) -[2023-10-17 00:47:47,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 27099136. Throughput: 0: 1773.9, 1: 1755.9. Samples: 6784810. Policy #0 lag: (min: 8.0, avg: 36.3, max: 40.0) -[2023-10-17 00:47:47,215][61453] Avg episode reward: [(0, '5.050'), (1, '5.510')] -[2023-10-17 00:47:47,225][62252] Saving new best policy, reward=5.510! -[2023-10-17 00:47:48,272][62373] Updated weights for policy 0, policy_version 13290 (0.0009) -[2023-10-17 00:47:48,647][62373] Updated weights for policy 0, policy_version 13300 (0.0008) -[2023-10-17 00:47:49,006][62373] Updated weights for policy 0, policy_version 13310 (0.0009) -[2023-10-17 00:47:50,416][62408] Updated weights for policy 1, policy_version 13190 (0.0007) -[2023-10-17 00:47:50,804][62408] Updated weights for policy 1, policy_version 13200 (0.0007) -[2023-10-17 00:47:51,167][62408] Updated weights for policy 1, policy_version 13210 (0.0009) -[2023-10-17 00:47:52,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 27164672. Throughput: 0: 1768.8, 1: 1788.4. Samples: 6795670. Policy #0 lag: (min: 8.0, avg: 36.3, max: 40.0) -[2023-10-17 00:47:52,215][61453] Avg episode reward: [(0, '4.800'), (1, '5.560')] -[2023-10-17 00:47:52,217][62252] Saving new best policy, reward=5.560! -[2023-10-17 00:47:52,785][62373] Updated weights for policy 0, policy_version 13320 (0.0007) -[2023-10-17 00:47:53,160][62373] Updated weights for policy 0, policy_version 13330 (0.0008) -[2023-10-17 00:47:53,527][62373] Updated weights for policy 0, policy_version 13340 (0.0011) -[2023-10-17 00:47:54,886][62408] Updated weights for policy 1, policy_version 13220 (0.0009) -[2023-10-17 00:47:55,248][62408] Updated weights for policy 1, policy_version 13230 (0.0009) -[2023-10-17 00:47:55,618][62408] Updated weights for policy 1, policy_version 13240 (0.0010) -[2023-10-17 00:47:57,214][61453] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 27230208. Throughput: 0: 1772.0, 1: 1760.7. Samples: 6816560. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:47:57,214][61453] Avg episode reward: [(0, '4.900'), (1, '5.510')] -[2023-10-17 00:47:57,327][62373] Updated weights for policy 0, policy_version 13350 (0.0009) -[2023-10-17 00:47:57,698][62373] Updated weights for policy 0, policy_version 13360 (0.0007) -[2023-10-17 00:47:58,069][62373] Updated weights for policy 0, policy_version 13370 (0.0007) -[2023-10-17 00:47:59,379][62408] Updated weights for policy 1, policy_version 13250 (0.0009) -[2023-10-17 00:47:59,750][62408] Updated weights for policy 1, policy_version 13260 (0.0011) -[2023-10-17 00:48:00,121][62408] Updated weights for policy 1, policy_version 13270 (0.0007) -[2023-10-17 00:48:00,493][62408] Updated weights for policy 1, policy_version 13280 (0.0007) -[2023-10-17 00:48:01,874][62373] Updated weights for policy 0, policy_version 13380 (0.0010) -[2023-10-17 00:48:02,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 27295744. Throughput: 0: 1795.3, 1: 1757.0. Samples: 6838330. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:48:02,215][61453] Avg episode reward: [(0, '5.060'), (1, '5.410')] -[2023-10-17 00:48:02,251][62373] Updated weights for policy 0, policy_version 13390 (0.0008) -[2023-10-17 00:48:02,617][62373] Updated weights for policy 0, policy_version 13400 (0.0008) -[2023-10-17 00:48:04,327][62408] Updated weights for policy 1, policy_version 13290 (0.0007) -[2023-10-17 00:48:04,694][62408] Updated weights for policy 1, policy_version 13300 (0.0008) -[2023-10-17 00:48:05,065][62408] Updated weights for policy 1, policy_version 13310 (0.0010) -[2023-10-17 00:48:06,398][62373] Updated weights for policy 0, policy_version 13410 (0.0007) -[2023-10-17 00:48:06,769][62373] Updated weights for policy 0, policy_version 13420 (0.0008) -[2023-10-17 00:48:07,137][62373] Updated weights for policy 0, policy_version 13430 (0.0009) -[2023-10-17 00:48:07,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 27361280. Throughput: 0: 1775.1, 1: 1767.3. Samples: 6848706. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:48:07,215][61453] Avg episode reward: [(0, '4.950'), (1, '5.020')] -[2023-10-17 00:48:07,504][62373] Updated weights for policy 0, policy_version 13440 (0.0008) -[2023-10-17 00:48:08,866][62408] Updated weights for policy 1, policy_version 13320 (0.0007) -[2023-10-17 00:48:09,242][62408] Updated weights for policy 1, policy_version 13330 (0.0008) -[2023-10-17 00:48:09,617][62408] Updated weights for policy 1, policy_version 13340 (0.0007) -[2023-10-17 00:48:11,370][62373] Updated weights for policy 0, policy_version 13450 (0.0008) -[2023-10-17 00:48:11,734][62373] Updated weights for policy 0, policy_version 13460 (0.0008) -[2023-10-17 00:48:12,115][62373] Updated weights for policy 0, policy_version 13470 (0.0010) -[2023-10-17 00:48:12,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14106.9). Total num frames: 27459584. Throughput: 0: 1791.6, 1: 1759.8. Samples: 6870226. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:48:12,215][61453] Avg episode reward: [(0, '5.020'), (1, '4.820')] -[2023-10-17 00:48:13,393][62408] Updated weights for policy 1, policy_version 13350 (0.0008) -[2023-10-17 00:48:13,772][62408] Updated weights for policy 1, policy_version 13360 (0.0007) -[2023-10-17 00:48:14,143][62408] Updated weights for policy 1, policy_version 13370 (0.0007) -[2023-10-17 00:48:15,914][62373] Updated weights for policy 0, policy_version 13480 (0.0008) -[2023-10-17 00:48:16,279][62373] Updated weights for policy 0, policy_version 13490 (0.0010) -[2023-10-17 00:48:16,657][62373] Updated weights for policy 0, policy_version 13500 (0.0009) -[2023-10-17 00:48:17,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 27525120. Throughput: 0: 1767.9, 1: 1771.8. Samples: 6891134. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:48:17,215][61453] Avg episode reward: [(0, '4.820'), (1, '4.690')] -[2023-10-17 00:48:17,995][62408] Updated weights for policy 1, policy_version 13380 (0.0009) -[2023-10-17 00:48:18,358][62408] Updated weights for policy 1, policy_version 13390 (0.0007) -[2023-10-17 00:48:18,728][62408] Updated weights for policy 1, policy_version 13400 (0.0008) -[2023-10-17 00:48:20,465][62373] Updated weights for policy 0, policy_version 13510 (0.0008) -[2023-10-17 00:48:20,849][62373] Updated weights for policy 0, policy_version 13520 (0.0010) -[2023-10-17 00:48:21,213][62373] Updated weights for policy 0, policy_version 13530 (0.0009) -[2023-10-17 00:48:22,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 27590656. Throughput: 0: 1791.2, 1: 1762.8. Samples: 6902360. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:48:22,215][61453] Avg episode reward: [(0, '5.430'), (1, '4.620')] -[2023-10-17 00:48:22,530][62408] Updated weights for policy 1, policy_version 13410 (0.0007) -[2023-10-17 00:48:22,905][62408] Updated weights for policy 1, policy_version 13420 (0.0008) -[2023-10-17 00:48:23,266][62408] Updated weights for policy 1, policy_version 13430 (0.0008) -[2023-10-17 00:48:23,640][62408] Updated weights for policy 1, policy_version 13440 (0.0007) -[2023-10-17 00:48:24,975][62373] Updated weights for policy 0, policy_version 13540 (0.0008) -[2023-10-17 00:48:25,336][62373] Updated weights for policy 0, policy_version 13550 (0.0010) -[2023-10-17 00:48:25,703][62373] Updated weights for policy 0, policy_version 13560 (0.0010) -[2023-10-17 00:48:27,214][62408] Updated weights for policy 1, policy_version 13450 (0.0009) -[2023-10-17 00:48:27,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 27656192. Throughput: 0: 1771.5, 1: 1767.2. Samples: 6923224. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:48:27,214][61453] Avg episode reward: [(0, '5.360'), (1, '5.560')] -[2023-10-17 00:48:27,577][62408] Updated weights for policy 1, policy_version 13460 (0.0008) -[2023-10-17 00:48:27,947][62408] Updated weights for policy 1, policy_version 13470 (0.0009) -[2023-10-17 00:48:29,572][62373] Updated weights for policy 0, policy_version 13570 (0.0009) -[2023-10-17 00:48:29,940][62373] Updated weights for policy 0, policy_version 13580 (0.0007) -[2023-10-17 00:48:30,317][62373] Updated weights for policy 0, policy_version 13590 (0.0007) -[2023-10-17 00:48:30,689][62373] Updated weights for policy 0, policy_version 13600 (0.0010) -[2023-10-17 00:48:31,791][62408] Updated weights for policy 1, policy_version 13480 (0.0007) -[2023-10-17 00:48:32,170][62408] Updated weights for policy 1, policy_version 13490 (0.0009) -[2023-10-17 00:48:32,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 27721728. Throughput: 0: 1761.8, 1: 1792.5. Samples: 6944754. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:48:32,215][61453] Avg episode reward: [(0, '5.580'), (1, '5.170')] -[2023-10-17 00:48:32,532][62408] Updated weights for policy 1, policy_version 13500 (0.0008) -[2023-10-17 00:48:34,492][62373] Updated weights for policy 0, policy_version 13610 (0.0007) -[2023-10-17 00:48:34,869][62373] Updated weights for policy 0, policy_version 13620 (0.0008) -[2023-10-17 00:48:35,251][62373] Updated weights for policy 0, policy_version 13630 (0.0007) -[2023-10-17 00:48:36,460][62408] Updated weights for policy 1, policy_version 13510 (0.0007) -[2023-10-17 00:48:36,853][62408] Updated weights for policy 1, policy_version 13520 (0.0008) -[2023-10-17 00:48:37,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 27787264. Throughput: 0: 1777.2, 1: 1768.4. Samples: 6955222. Policy #0 lag: (min: 13.0, avg: 21.0, max: 45.0) -[2023-10-17 00:48:37,214][61453] Avg episode reward: [(0, '5.500'), (1, '5.440')] -[2023-10-17 00:48:37,229][62408] Updated weights for policy 1, policy_version 13530 (0.0007) -[2023-10-17 00:48:39,226][62373] Updated weights for policy 0, policy_version 13640 (0.0007) -[2023-10-17 00:48:39,592][62373] Updated weights for policy 0, policy_version 13650 (0.0010) -[2023-10-17 00:48:39,973][62373] Updated weights for policy 0, policy_version 13660 (0.0009) -[2023-10-17 00:48:40,802][62408] Updated weights for policy 1, policy_version 13540 (0.0008) -[2023-10-17 00:48:41,161][62408] Updated weights for policy 1, policy_version 13550 (0.0007) -[2023-10-17 00:48:41,534][62408] Updated weights for policy 1, policy_version 13560 (0.0009) -[2023-10-17 00:48:42,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 27885568. Throughput: 0: 1760.5, 1: 1792.0. Samples: 6976422. Policy #0 lag: (min: 13.0, avg: 21.0, max: 45.0) -[2023-10-17 00:48:42,215][61453] Avg episode reward: [(0, '5.800'), (1, '5.550')] -[2023-10-17 00:48:42,216][62094] Saving new best policy, reward=5.800! -[2023-10-17 00:48:43,733][62373] Updated weights for policy 0, policy_version 13670 (0.0009) -[2023-10-17 00:48:44,104][62373] Updated weights for policy 0, policy_version 13680 (0.0007) -[2023-10-17 00:48:44,477][62373] Updated weights for policy 0, policy_version 13690 (0.0008) -[2023-10-17 00:48:45,340][62408] Updated weights for policy 1, policy_version 13570 (0.0008) -[2023-10-17 00:48:45,712][62408] Updated weights for policy 1, policy_version 13580 (0.0009) -[2023-10-17 00:48:46,075][62408] Updated weights for policy 1, policy_version 13590 (0.0010) -[2023-10-17 00:48:46,441][62408] Updated weights for policy 1, policy_version 13600 (0.0010) -[2023-10-17 00:48:47,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 27951104. Throughput: 0: 1772.7, 1: 1770.0. Samples: 6997748. Policy #0 lag: (min: 13.0, avg: 21.0, max: 45.0) -[2023-10-17 00:48:47,214][61453] Avg episode reward: [(0, '5.620'), (1, '5.660')] -[2023-10-17 00:48:47,225][62252] Saving new best policy, reward=5.660! -[2023-10-17 00:48:48,056][62373] Updated weights for policy 0, policy_version 13700 (0.0010) -[2023-10-17 00:48:48,421][62373] Updated weights for policy 0, policy_version 13710 (0.0009) -[2023-10-17 00:48:48,788][62373] Updated weights for policy 0, policy_version 13720 (0.0010) -[2023-10-17 00:48:50,341][62408] Updated weights for policy 1, policy_version 13610 (0.0009) -[2023-10-17 00:48:50,709][62408] Updated weights for policy 1, policy_version 13620 (0.0008) -[2023-10-17 00:48:51,077][62408] Updated weights for policy 1, policy_version 13630 (0.0009) -[2023-10-17 00:48:52,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 28016640. Throughput: 0: 1762.2, 1: 1792.1. Samples: 7008650. Policy #0 lag: (min: 2.0, avg: 2.2, max: 12.0) -[2023-10-17 00:48:52,215][61453] Avg episode reward: [(0, '5.170'), (1, '5.270')] -[2023-10-17 00:48:52,578][62373] Updated weights for policy 0, policy_version 13730 (0.0009) -[2023-10-17 00:48:52,946][62373] Updated weights for policy 0, policy_version 13740 (0.0009) -[2023-10-17 00:48:53,322][62373] Updated weights for policy 0, policy_version 13750 (0.0008) -[2023-10-17 00:48:53,689][62373] Updated weights for policy 0, policy_version 13760 (0.0008) -[2023-10-17 00:48:54,898][62408] Updated weights for policy 1, policy_version 13640 (0.0008) -[2023-10-17 00:48:55,271][62408] Updated weights for policy 1, policy_version 13650 (0.0008) -[2023-10-17 00:48:55,640][62408] Updated weights for policy 1, policy_version 13660 (0.0010) -[2023-10-17 00:48:57,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 28082176. Throughput: 0: 1770.1, 1: 1770.0. Samples: 7029528. Policy #0 lag: (min: 2.0, avg: 2.2, max: 12.0) -[2023-10-17 00:48:57,215][61453] Avg episode reward: [(0, '5.290'), (1, '5.090')] -[2023-10-17 00:48:57,664][62373] Updated weights for policy 0, policy_version 13770 (0.0010) -[2023-10-17 00:48:58,032][62373] Updated weights for policy 0, policy_version 13780 (0.0008) -[2023-10-17 00:48:58,391][62373] Updated weights for policy 0, policy_version 13790 (0.0007) -[2023-10-17 00:48:59,458][62408] Updated weights for policy 1, policy_version 13670 (0.0009) -[2023-10-17 00:48:59,823][62408] Updated weights for policy 1, policy_version 13680 (0.0008) -[2023-10-17 00:49:00,195][62408] Updated weights for policy 1, policy_version 13690 (0.0008) -[2023-10-17 00:49:02,096][62373] Updated weights for policy 0, policy_version 13800 (0.0008) -[2023-10-17 00:49:02,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 28147712. Throughput: 0: 1794.7, 1: 1770.1. Samples: 7051550. Policy #0 lag: (min: 2.0, avg: 2.2, max: 12.0) -[2023-10-17 00:49:02,214][61453] Avg episode reward: [(0, '5.330'), (1, '4.980')] -[2023-10-17 00:49:02,463][62373] Updated weights for policy 0, policy_version 13810 (0.0008) -[2023-10-17 00:49:02,847][62373] Updated weights for policy 0, policy_version 13820 (0.0007) -[2023-10-17 00:49:04,005][62408] Updated weights for policy 1, policy_version 13700 (0.0008) -[2023-10-17 00:49:04,371][62408] Updated weights for policy 1, policy_version 13710 (0.0008) -[2023-10-17 00:49:04,736][62408] Updated weights for policy 1, policy_version 13720 (0.0007) -[2023-10-17 00:49:06,750][62373] Updated weights for policy 0, policy_version 13830 (0.0007) -[2023-10-17 00:49:07,127][62373] Updated weights for policy 0, policy_version 13840 (0.0009) -[2023-10-17 00:49:07,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 28213248. Throughput: 0: 1762.9, 1: 1778.3. Samples: 7061716. Policy #0 lag: (min: 11.0, avg: 11.0, max: 12.0) -[2023-10-17 00:49:07,215][61453] Avg episode reward: [(0, '5.140'), (1, '4.920')] -[2023-10-17 00:49:07,506][62373] Updated weights for policy 0, policy_version 13850 (0.0007) -[2023-10-17 00:49:08,598][62408] Updated weights for policy 1, policy_version 13730 (0.0009) -[2023-10-17 00:49:08,967][62408] Updated weights for policy 1, policy_version 13740 (0.0007) -[2023-10-17 00:49:09,341][62408] Updated weights for policy 1, policy_version 13750 (0.0009) -[2023-10-17 00:49:09,709][62408] Updated weights for policy 1, policy_version 13760 (0.0009) -[2023-10-17 00:49:11,094][62373] Updated weights for policy 0, policy_version 13860 (0.0009) -[2023-10-17 00:49:11,474][62373] Updated weights for policy 0, policy_version 13870 (0.0010) -[2023-10-17 00:49:11,847][62373] Updated weights for policy 0, policy_version 13880 (0.0009) -[2023-10-17 00:49:12,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 28311552. Throughput: 0: 1797.4, 1: 1762.8. Samples: 7083436. Policy #0 lag: (min: 11.0, avg: 11.0, max: 12.0) -[2023-10-17 00:49:12,215][61453] Avg episode reward: [(0, '5.060'), (1, '5.060')] -[2023-10-17 00:49:13,366][62408] Updated weights for policy 1, policy_version 13770 (0.0008) -[2023-10-17 00:49:13,725][62408] Updated weights for policy 1, policy_version 13780 (0.0008) -[2023-10-17 00:49:14,096][62408] Updated weights for policy 1, policy_version 13790 (0.0009) -[2023-10-17 00:49:15,584][62373] Updated weights for policy 0, policy_version 13890 (0.0008) -[2023-10-17 00:49:15,958][62373] Updated weights for policy 0, policy_version 13900 (0.0009) -[2023-10-17 00:49:16,325][62373] Updated weights for policy 0, policy_version 13910 (0.0009) -[2023-10-17 00:49:16,692][62373] Updated weights for policy 0, policy_version 13920 (0.0010) -[2023-10-17 00:49:17,214][61453] Fps is (10 sec: 16383.6, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 28377088. Throughput: 0: 1774.2, 1: 1778.5. Samples: 7104624. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:49:17,215][61453] Avg episode reward: [(0, '4.980'), (1, '4.980')] -[2023-10-17 00:49:17,879][62408] Updated weights for policy 1, policy_version 13800 (0.0009) -[2023-10-17 00:49:18,244][62408] Updated weights for policy 1, policy_version 13810 (0.0007) -[2023-10-17 00:49:18,616][62408] Updated weights for policy 1, policy_version 13820 (0.0007) -[2023-10-17 00:49:20,422][62373] Updated weights for policy 0, policy_version 13930 (0.0007) -[2023-10-17 00:49:20,793][62373] Updated weights for policy 0, policy_version 13940 (0.0010) -[2023-10-17 00:49:21,171][62373] Updated weights for policy 0, policy_version 13950 (0.0009) -[2023-10-17 00:49:22,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 28442624. Throughput: 0: 1796.8, 1: 1770.2. Samples: 7115740. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:49:22,215][61453] Avg episode reward: [(0, '4.750'), (1, '5.040')] -[2023-10-17 00:49:22,364][62408] Updated weights for policy 1, policy_version 13830 (0.0007) -[2023-10-17 00:49:22,750][62408] Updated weights for policy 1, policy_version 13840 (0.0008) -[2023-10-17 00:49:23,123][62408] Updated weights for policy 1, policy_version 13850 (0.0007) -[2023-10-17 00:49:24,742][62373] Updated weights for policy 0, policy_version 13960 (0.0008) -[2023-10-17 00:49:25,114][62373] Updated weights for policy 0, policy_version 13970 (0.0007) -[2023-10-17 00:49:25,485][62373] Updated weights for policy 0, policy_version 13980 (0.0008) -[2023-10-17 00:49:26,916][62408] Updated weights for policy 1, policy_version 13860 (0.0009) -[2023-10-17 00:49:27,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 28508160. Throughput: 0: 1783.6, 1: 1780.4. Samples: 7136802. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:49:27,215][61453] Avg episode reward: [(0, '5.010'), (1, '5.170')] -[2023-10-17 00:49:27,295][62408] Updated weights for policy 1, policy_version 13870 (0.0009) -[2023-10-17 00:49:27,651][62408] Updated weights for policy 1, policy_version 13880 (0.0010) -[2023-10-17 00:49:29,218][62373] Updated weights for policy 0, policy_version 13990 (0.0009) -[2023-10-17 00:49:29,587][62373] Updated weights for policy 0, policy_version 14000 (0.0007) -[2023-10-17 00:49:29,970][62373] Updated weights for policy 0, policy_version 14010 (0.0007) -[2023-10-17 00:49:31,400][62408] Updated weights for policy 1, policy_version 13890 (0.0007) -[2023-10-17 00:49:31,766][62408] Updated weights for policy 1, policy_version 13900 (0.0009) -[2023-10-17 00:49:32,141][62408] Updated weights for policy 1, policy_version 13910 (0.0007) -[2023-10-17 00:49:32,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 28573696. Throughput: 0: 1783.4, 1: 1788.8. Samples: 7158498. Policy #0 lag: (min: 20.0, avg: 20.0, max: 22.0) -[2023-10-17 00:49:32,215][61453] Avg episode reward: [(0, '4.960'), (1, '5.370')] -[2023-10-17 00:49:32,223][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000014016_14352384.pth... -[2023-10-17 00:49:32,263][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000012352_12648448.pth -[2023-10-17 00:49:32,518][62408] Updated weights for policy 1, policy_version 13920 (0.0008) -[2023-10-17 00:49:32,519][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000013920_14254080.pth... -[2023-10-17 00:49:32,555][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000012256_12550144.pth -[2023-10-17 00:49:33,814][62373] Updated weights for policy 0, policy_version 14020 (0.0008) -[2023-10-17 00:49:34,188][62373] Updated weights for policy 0, policy_version 14030 (0.0010) -[2023-10-17 00:49:34,567][62373] Updated weights for policy 0, policy_version 14040 (0.0010) -[2023-10-17 00:49:36,259][62408] Updated weights for policy 1, policy_version 13930 (0.0009) -[2023-10-17 00:49:36,632][62408] Updated weights for policy 1, policy_version 13940 (0.0008) -[2023-10-17 00:49:36,997][62408] Updated weights for policy 1, policy_version 13950 (0.0009) -[2023-10-17 00:49:37,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14745.5, 300 sec: 14218.0). Total num frames: 28672000. Throughput: 0: 1785.1, 1: 1774.4. Samples: 7168828. Policy #0 lag: (min: 20.0, avg: 20.0, max: 22.0) -[2023-10-17 00:49:37,215][61453] Avg episode reward: [(0, '4.550'), (1, '5.530')] -[2023-10-17 00:49:38,353][62373] Updated weights for policy 0, policy_version 14050 (0.0008) -[2023-10-17 00:49:38,720][62373] Updated weights for policy 0, policy_version 14060 (0.0007) -[2023-10-17 00:49:39,098][62373] Updated weights for policy 0, policy_version 14070 (0.0008) -[2023-10-17 00:49:39,458][62373] Updated weights for policy 0, policy_version 14080 (0.0008) -[2023-10-17 00:49:40,929][62408] Updated weights for policy 1, policy_version 13960 (0.0008) -[2023-10-17 00:49:41,301][62408] Updated weights for policy 1, policy_version 13970 (0.0007) -[2023-10-17 00:49:41,668][62408] Updated weights for policy 1, policy_version 13980 (0.0009) -[2023-10-17 00:49:42,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 28737536. Throughput: 0: 1781.8, 1: 1797.6. Samples: 7190598. Policy #0 lag: (min: 20.0, avg: 20.0, max: 22.0) -[2023-10-17 00:49:42,215][61453] Avg episode reward: [(0, '4.820'), (1, '5.380')] -[2023-10-17 00:49:43,161][62373] Updated weights for policy 0, policy_version 14090 (0.0007) -[2023-10-17 00:49:43,539][62373] Updated weights for policy 0, policy_version 14100 (0.0007) -[2023-10-17 00:49:43,901][62373] Updated weights for policy 0, policy_version 14110 (0.0008) -[2023-10-17 00:49:45,546][62408] Updated weights for policy 1, policy_version 13990 (0.0009) -[2023-10-17 00:49:45,915][62408] Updated weights for policy 1, policy_version 14000 (0.0010) -[2023-10-17 00:49:46,286][62408] Updated weights for policy 1, policy_version 14010 (0.0007) -[2023-10-17 00:49:47,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 28803072. Throughput: 0: 1793.0, 1: 1769.7. Samples: 7211872. Policy #0 lag: (min: 17.0, avg: 19.4, max: 49.0) -[2023-10-17 00:49:47,215][61453] Avg episode reward: [(0, '4.770'), (1, '5.420')] -[2023-10-17 00:49:47,617][62373] Updated weights for policy 0, policy_version 14120 (0.0009) -[2023-10-17 00:49:47,996][62373] Updated weights for policy 0, policy_version 14130 (0.0007) -[2023-10-17 00:49:48,365][62373] Updated weights for policy 0, policy_version 14140 (0.0007) -[2023-10-17 00:49:49,859][62408] Updated weights for policy 1, policy_version 14020 (0.0008) -[2023-10-17 00:49:50,227][62408] Updated weights for policy 1, policy_version 14030 (0.0010) -[2023-10-17 00:49:50,607][62408] Updated weights for policy 1, policy_version 14040 (0.0011) -[2023-10-17 00:49:52,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 28868608. Throughput: 0: 1785.9, 1: 1794.9. Samples: 7222850. Policy #0 lag: (min: 17.0, avg: 19.4, max: 49.0) -[2023-10-17 00:49:52,215][61453] Avg episode reward: [(0, '5.080'), (1, '5.220')] -[2023-10-17 00:49:52,330][62373] Updated weights for policy 0, policy_version 14150 (0.0008) -[2023-10-17 00:49:52,714][62373] Updated weights for policy 0, policy_version 14160 (0.0007) -[2023-10-17 00:49:53,085][62373] Updated weights for policy 0, policy_version 14170 (0.0009) -[2023-10-17 00:49:54,478][62408] Updated weights for policy 1, policy_version 14050 (0.0009) -[2023-10-17 00:49:54,848][62408] Updated weights for policy 1, policy_version 14060 (0.0009) -[2023-10-17 00:49:55,210][62408] Updated weights for policy 1, policy_version 14070 (0.0010) -[2023-10-17 00:49:55,572][62408] Updated weights for policy 1, policy_version 14080 (0.0010) -[2023-10-17 00:49:56,979][62373] Updated weights for policy 0, policy_version 14180 (0.0010) -[2023-10-17 00:49:57,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 28934144. Throughput: 0: 1783.1, 1: 1776.2. Samples: 7243604. Policy #0 lag: (min: 17.0, avg: 19.4, max: 49.0) -[2023-10-17 00:49:57,214][61453] Avg episode reward: [(0, '4.690'), (1, '5.140')] -[2023-10-17 00:49:57,352][62373] Updated weights for policy 0, policy_version 14190 (0.0010) -[2023-10-17 00:49:57,719][62373] Updated weights for policy 0, policy_version 14200 (0.0009) -[2023-10-17 00:49:59,249][62408] Updated weights for policy 1, policy_version 14090 (0.0010) -[2023-10-17 00:49:59,617][62408] Updated weights for policy 1, policy_version 14100 (0.0007) -[2023-10-17 00:49:59,992][62408] Updated weights for policy 1, policy_version 14110 (0.0007) -[2023-10-17 00:50:01,477][62373] Updated weights for policy 0, policy_version 14210 (0.0010) -[2023-10-17 00:50:01,848][62373] Updated weights for policy 0, policy_version 14220 (0.0007) -[2023-10-17 00:50:02,213][62373] Updated weights for policy 0, policy_version 14230 (0.0009) -[2023-10-17 00:50:02,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 28999680. Throughput: 0: 1794.5, 1: 1771.3. Samples: 7265088. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:50:02,215][61453] Avg episode reward: [(0, '5.080'), (1, '5.030')] -[2023-10-17 00:50:02,583][62373] Updated weights for policy 0, policy_version 14240 (0.0007) -[2023-10-17 00:50:03,907][62408] Updated weights for policy 1, policy_version 14120 (0.0008) -[2023-10-17 00:50:04,272][62408] Updated weights for policy 1, policy_version 14130 (0.0007) -[2023-10-17 00:50:04,646][62408] Updated weights for policy 1, policy_version 14140 (0.0009) -[2023-10-17 00:50:06,320][62373] Updated weights for policy 0, policy_version 14250 (0.0008) -[2023-10-17 00:50:06,676][62373] Updated weights for policy 0, policy_version 14260 (0.0007) -[2023-10-17 00:50:07,046][62373] Updated weights for policy 0, policy_version 14270 (0.0008) -[2023-10-17 00:50:07,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 29097984. Throughput: 0: 1776.5, 1: 1767.9. Samples: 7275236. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:50:07,215][61453] Avg episode reward: [(0, '5.310'), (1, '4.830')] -[2023-10-17 00:50:08,411][62408] Updated weights for policy 1, policy_version 14150 (0.0011) -[2023-10-17 00:50:08,776][62408] Updated weights for policy 1, policy_version 14160 (0.0010) -[2023-10-17 00:50:09,142][62408] Updated weights for policy 1, policy_version 14170 (0.0008) -[2023-10-17 00:50:10,873][62373] Updated weights for policy 0, policy_version 14280 (0.0009) -[2023-10-17 00:50:11,244][62373] Updated weights for policy 0, policy_version 14290 (0.0008) -[2023-10-17 00:50:11,615][62373] Updated weights for policy 0, policy_version 14300 (0.0008) -[2023-10-17 00:50:12,214][61453] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 29163520. Throughput: 0: 1795.2, 1: 1765.0. Samples: 7297010. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-17 00:50:12,215][61453] Avg episode reward: [(0, '5.100'), (1, '4.790')] -[2023-10-17 00:50:13,015][62408] Updated weights for policy 1, policy_version 14180 (0.0008) -[2023-10-17 00:50:13,413][62408] Updated weights for policy 1, policy_version 14190 (0.0009) -[2023-10-17 00:50:13,787][62408] Updated weights for policy 1, policy_version 14200 (0.0009) -[2023-10-17 00:50:15,459][62373] Updated weights for policy 0, policy_version 14310 (0.0009) -[2023-10-17 00:50:15,832][62373] Updated weights for policy 0, policy_version 14320 (0.0008) -[2023-10-17 00:50:16,207][62373] Updated weights for policy 0, policy_version 14330 (0.0010) -[2023-10-17 00:50:17,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 29229056. Throughput: 0: 1769.6, 1: 1775.3. Samples: 7318014. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-17 00:50:17,214][61453] Avg episode reward: [(0, '4.940'), (1, '5.050')] -[2023-10-17 00:50:17,668][62408] Updated weights for policy 1, policy_version 14210 (0.0008) -[2023-10-17 00:50:18,033][62408] Updated weights for policy 1, policy_version 14220 (0.0008) -[2023-10-17 00:50:18,405][62408] Updated weights for policy 1, policy_version 14230 (0.0009) -[2023-10-17 00:50:18,773][62408] Updated weights for policy 1, policy_version 14240 (0.0009) -[2023-10-17 00:50:19,884][62373] Updated weights for policy 0, policy_version 14340 (0.0008) -[2023-10-17 00:50:20,258][62373] Updated weights for policy 0, policy_version 14350 (0.0009) -[2023-10-17 00:50:20,626][62373] Updated weights for policy 0, policy_version 14360 (0.0008) -[2023-10-17 00:50:22,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 29294592. Throughput: 0: 1802.0, 1: 1757.2. Samples: 7328988. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-17 00:50:22,214][61453] Avg episode reward: [(0, '4.990'), (1, '5.220')] -[2023-10-17 00:50:22,615][62408] Updated weights for policy 1, policy_version 14250 (0.0009) -[2023-10-17 00:50:22,984][62408] Updated weights for policy 1, policy_version 14260 (0.0007) -[2023-10-17 00:50:23,357][62408] Updated weights for policy 1, policy_version 14270 (0.0007) -[2023-10-17 00:50:24,440][62373] Updated weights for policy 0, policy_version 14370 (0.0009) -[2023-10-17 00:50:24,819][62373] Updated weights for policy 0, policy_version 14380 (0.0007) -[2023-10-17 00:50:25,192][62373] Updated weights for policy 0, policy_version 14390 (0.0010) -[2023-10-17 00:50:25,561][62373] Updated weights for policy 0, policy_version 14400 (0.0007) -[2023-10-17 00:50:27,211][62408] Updated weights for policy 1, policy_version 14280 (0.0010) -[2023-10-17 00:50:27,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 29360128. Throughput: 0: 1776.1, 1: 1765.3. Samples: 7349962. Policy #0 lag: (min: 8.0, avg: 31.6, max: 40.0) -[2023-10-17 00:50:27,215][61453] Avg episode reward: [(0, '5.110'), (1, '4.990')] -[2023-10-17 00:50:27,586][62408] Updated weights for policy 1, policy_version 14290 (0.0011) -[2023-10-17 00:50:27,953][62408] Updated weights for policy 1, policy_version 14300 (0.0008) -[2023-10-17 00:50:29,205][62373] Updated weights for policy 0, policy_version 14410 (0.0007) -[2023-10-17 00:50:29,579][62373] Updated weights for policy 0, policy_version 14420 (0.0007) -[2023-10-17 00:50:29,956][62373] Updated weights for policy 0, policy_version 14430 (0.0007) -[2023-10-17 00:50:31,756][62408] Updated weights for policy 1, policy_version 14310 (0.0011) -[2023-10-17 00:50:32,126][62408] Updated weights for policy 1, policy_version 14320 (0.0009) -[2023-10-17 00:50:32,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 29425664. Throughput: 0: 1776.0, 1: 1779.7. Samples: 7371878. Policy #0 lag: (min: 8.0, avg: 31.6, max: 40.0) -[2023-10-17 00:50:32,215][61453] Avg episode reward: [(0, '4.960'), (1, '5.040')] -[2023-10-17 00:50:32,495][62408] Updated weights for policy 1, policy_version 14330 (0.0007) -[2023-10-17 00:50:33,617][62373] Updated weights for policy 0, policy_version 14440 (0.0010) -[2023-10-17 00:50:33,991][62373] Updated weights for policy 0, policy_version 14450 (0.0010) -[2023-10-17 00:50:34,353][62373] Updated weights for policy 0, policy_version 14460 (0.0009) -[2023-10-17 00:50:36,313][62408] Updated weights for policy 1, policy_version 14340 (0.0007) -[2023-10-17 00:50:36,673][62408] Updated weights for policy 1, policy_version 14350 (0.0008) -[2023-10-17 00:50:37,043][62408] Updated weights for policy 1, policy_version 14360 (0.0009) -[2023-10-17 00:50:37,214][61453] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 29491200. Throughput: 0: 1778.3, 1: 1758.1. Samples: 7381988. Policy #0 lag: (min: 8.0, avg: 31.6, max: 40.0) -[2023-10-17 00:50:37,214][61453] Avg episode reward: [(0, '4.620'), (1, '5.420')] -[2023-10-17 00:50:38,247][62373] Updated weights for policy 0, policy_version 14470 (0.0008) -[2023-10-17 00:50:38,614][62373] Updated weights for policy 0, policy_version 14480 (0.0007) -[2023-10-17 00:50:38,981][62373] Updated weights for policy 0, policy_version 14490 (0.0008) -[2023-10-17 00:50:40,922][62408] Updated weights for policy 1, policy_version 14370 (0.0010) -[2023-10-17 00:50:41,293][62408] Updated weights for policy 1, policy_version 14380 (0.0009) -[2023-10-17 00:50:41,668][62408] Updated weights for policy 1, policy_version 14390 (0.0011) -[2023-10-17 00:50:42,021][62408] Updated weights for policy 1, policy_version 14400 (0.0008) -[2023-10-17 00:50:42,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 29589504. Throughput: 0: 1779.6, 1: 1782.4. Samples: 7403894. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-17 00:50:42,215][61453] Avg episode reward: [(0, '4.970'), (1, '5.290')] -[2023-10-17 00:50:42,687][62373] Updated weights for policy 0, policy_version 14500 (0.0008) -[2023-10-17 00:50:43,089][62373] Updated weights for policy 0, policy_version 14510 (0.0008) -[2023-10-17 00:50:43,456][62373] Updated weights for policy 0, policy_version 14520 (0.0009) -[2023-10-17 00:50:46,006][62408] Updated weights for policy 1, policy_version 14410 (0.0010) -[2023-10-17 00:50:46,376][62408] Updated weights for policy 1, policy_version 14420 (0.0008) -[2023-10-17 00:50:46,747][62408] Updated weights for policy 1, policy_version 14430 (0.0007) -[2023-10-17 00:50:47,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 29655040. Throughput: 0: 1795.0, 1: 1745.4. Samples: 7424404. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-17 00:50:47,214][61453] Avg episode reward: [(0, '5.250'), (1, '4.960')] -[2023-10-17 00:50:47,345][62373] Updated weights for policy 0, policy_version 14530 (0.0008) -[2023-10-17 00:50:47,714][62373] Updated weights for policy 0, policy_version 14540 (0.0009) -[2023-10-17 00:50:48,091][62373] Updated weights for policy 0, policy_version 14550 (0.0008) -[2023-10-17 00:50:48,455][62373] Updated weights for policy 0, policy_version 14560 (0.0008) -[2023-10-17 00:50:50,401][62408] Updated weights for policy 1, policy_version 14440 (0.0007) -[2023-10-17 00:50:50,766][62408] Updated weights for policy 1, policy_version 14450 (0.0010) -[2023-10-17 00:50:51,142][62408] Updated weights for policy 1, policy_version 14460 (0.0009) -[2023-10-17 00:50:52,123][62373] Updated weights for policy 0, policy_version 14570 (0.0008) -[2023-10-17 00:50:52,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 29720576. Throughput: 0: 1781.5, 1: 1786.7. Samples: 7435804. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-10-17 00:50:52,214][61453] Avg episode reward: [(0, '4.750'), (1, '5.060')] -[2023-10-17 00:50:52,492][62373] Updated weights for policy 0, policy_version 14580 (0.0008) -[2023-10-17 00:50:52,856][62373] Updated weights for policy 0, policy_version 14590 (0.0008) -[2023-10-17 00:50:54,892][62408] Updated weights for policy 1, policy_version 14470 (0.0010) -[2023-10-17 00:50:55,248][62408] Updated weights for policy 1, policy_version 14480 (0.0010) -[2023-10-17 00:50:55,617][62408] Updated weights for policy 1, policy_version 14490 (0.0011) -[2023-10-17 00:50:56,651][62373] Updated weights for policy 0, policy_version 14600 (0.0008) -[2023-10-17 00:50:57,023][62373] Updated weights for policy 0, policy_version 14610 (0.0010) -[2023-10-17 00:50:57,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 29786112. Throughput: 0: 1792.9, 1: 1758.4. Samples: 7456822. Policy #0 lag: (min: 23.0, avg: 27.1, max: 55.0) -[2023-10-17 00:50:57,215][61453] Avg episode reward: [(0, '4.490'), (1, '5.590')] -[2023-10-17 00:50:57,386][62373] Updated weights for policy 0, policy_version 14620 (0.0007) -[2023-10-17 00:50:59,477][62408] Updated weights for policy 1, policy_version 14500 (0.0008) -[2023-10-17 00:50:59,851][62408] Updated weights for policy 1, policy_version 14510 (0.0009) -[2023-10-17 00:51:00,215][62408] Updated weights for policy 1, policy_version 14520 (0.0009) -[2023-10-17 00:51:01,230][62373] Updated weights for policy 0, policy_version 14630 (0.0011) -[2023-10-17 00:51:01,598][62373] Updated weights for policy 0, policy_version 14640 (0.0010) -[2023-10-17 00:51:01,977][62373] Updated weights for policy 0, policy_version 14650 (0.0007) -[2023-10-17 00:51:02,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14745.7, 300 sec: 14329.1). Total num frames: 29884416. Throughput: 0: 1789.8, 1: 1760.9. Samples: 7477796. Policy #0 lag: (min: 23.0, avg: 27.1, max: 55.0) -[2023-10-17 00:51:02,214][61453] Avg episode reward: [(0, '5.150'), (1, '5.460')] -[2023-10-17 00:51:04,034][62408] Updated weights for policy 1, policy_version 14530 (0.0008) -[2023-10-17 00:51:04,399][62408] Updated weights for policy 1, policy_version 14540 (0.0009) -[2023-10-17 00:51:04,767][62408] Updated weights for policy 1, policy_version 14550 (0.0007) -[2023-10-17 00:51:05,133][62408] Updated weights for policy 1, policy_version 14560 (0.0007) -[2023-10-17 00:51:05,766][62373] Updated weights for policy 0, policy_version 14660 (0.0009) -[2023-10-17 00:51:06,137][62373] Updated weights for policy 0, policy_version 14670 (0.0009) -[2023-10-17 00:51:06,502][62373] Updated weights for policy 0, policy_version 14680 (0.0010) -[2023-10-17 00:51:07,214][61453] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 29949952. Throughput: 0: 1785.3, 1: 1770.4. Samples: 7488994. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:51:07,215][61453] Avg episode reward: [(0, '5.400'), (1, '5.230')] -[2023-10-17 00:51:08,952][62408] Updated weights for policy 1, policy_version 14570 (0.0008) -[2023-10-17 00:51:09,317][62408] Updated weights for policy 1, policy_version 14580 (0.0008) -[2023-10-17 00:51:09,685][62408] Updated weights for policy 1, policy_version 14590 (0.0008) -[2023-10-17 00:51:10,361][62373] Updated weights for policy 0, policy_version 14690 (0.0007) -[2023-10-17 00:51:10,740][62373] Updated weights for policy 0, policy_version 14700 (0.0010) -[2023-10-17 00:51:11,111][62373] Updated weights for policy 0, policy_version 14710 (0.0011) -[2023-10-17 00:51:11,478][62373] Updated weights for policy 0, policy_version 14720 (0.0008) -[2023-10-17 00:51:12,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 30015488. Throughput: 0: 1791.8, 1: 1759.6. Samples: 7509774. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:51:12,215][61453] Avg episode reward: [(0, '5.090'), (1, '5.210')] -[2023-10-17 00:51:13,512][62408] Updated weights for policy 1, policy_version 14600 (0.0008) -[2023-10-17 00:51:13,883][62408] Updated weights for policy 1, policy_version 14610 (0.0011) -[2023-10-17 00:51:14,254][62408] Updated weights for policy 1, policy_version 14620 (0.0008) -[2023-10-17 00:51:15,284][62373] Updated weights for policy 0, policy_version 14730 (0.0008) -[2023-10-17 00:51:15,661][62373] Updated weights for policy 0, policy_version 14740 (0.0009) -[2023-10-17 00:51:16,024][62373] Updated weights for policy 0, policy_version 14750 (0.0011) -[2023-10-17 00:51:17,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 30081024. Throughput: 0: 1773.2, 1: 1768.0. Samples: 7531228. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:51:17,215][61453] Avg episode reward: [(0, '5.050'), (1, '5.110')] -[2023-10-17 00:51:18,121][62408] Updated weights for policy 1, policy_version 14630 (0.0010) -[2023-10-17 00:51:18,491][62408] Updated weights for policy 1, policy_version 14640 (0.0012) -[2023-10-17 00:51:18,857][62408] Updated weights for policy 1, policy_version 14650 (0.0009) -[2023-10-17 00:51:19,792][62373] Updated weights for policy 0, policy_version 14760 (0.0010) -[2023-10-17 00:51:20,169][62373] Updated weights for policy 0, policy_version 14770 (0.0008) -[2023-10-17 00:51:20,547][62373] Updated weights for policy 0, policy_version 14780 (0.0008) -[2023-10-17 00:51:22,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 30146560. Throughput: 0: 1794.2, 1: 1759.2. Samples: 7541894. Policy #0 lag: (min: 14.0, avg: 21.0, max: 46.0) -[2023-10-17 00:51:22,214][61453] Avg episode reward: [(0, '5.390'), (1, '5.100')] -[2023-10-17 00:51:22,865][62408] Updated weights for policy 1, policy_version 14660 (0.0010) -[2023-10-17 00:51:23,236][62408] Updated weights for policy 1, policy_version 14670 (0.0012) -[2023-10-17 00:51:23,607][62408] Updated weights for policy 1, policy_version 14680 (0.0010) -[2023-10-17 00:51:24,329][62373] Updated weights for policy 0, policy_version 14790 (0.0010) -[2023-10-17 00:51:24,693][62373] Updated weights for policy 0, policy_version 14800 (0.0009) -[2023-10-17 00:51:25,068][62373] Updated weights for policy 0, policy_version 14810 (0.0009) -[2023-10-17 00:51:27,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 30212096. Throughput: 0: 1772.5, 1: 1762.4. Samples: 7562962. Policy #0 lag: (min: 14.0, avg: 21.0, max: 46.0) -[2023-10-17 00:51:27,215][61453] Avg episode reward: [(0, '5.220'), (1, '5.320')] -[2023-10-17 00:51:27,495][62408] Updated weights for policy 1, policy_version 14690 (0.0010) -[2023-10-17 00:51:27,863][62408] Updated weights for policy 1, policy_version 14700 (0.0010) -[2023-10-17 00:51:28,233][62408] Updated weights for policy 1, policy_version 14710 (0.0010) -[2023-10-17 00:51:28,603][62408] Updated weights for policy 1, policy_version 14720 (0.0011) -[2023-10-17 00:51:28,975][62373] Updated weights for policy 0, policy_version 14820 (0.0009) -[2023-10-17 00:51:29,360][62373] Updated weights for policy 0, policy_version 14830 (0.0008) -[2023-10-17 00:51:29,728][62373] Updated weights for policy 0, policy_version 14840 (0.0007) -[2023-10-17 00:51:32,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 30277632. Throughput: 0: 1772.9, 1: 1792.4. Samples: 7584844. Policy #0 lag: (min: 14.0, avg: 21.0, max: 46.0) -[2023-10-17 00:51:32,214][61453] Avg episode reward: [(0, '5.050'), (1, '5.070')] -[2023-10-17 00:51:32,224][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000014848_15204352.pth... -[2023-10-17 00:51:32,264][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000013184_13500416.pth -[2023-10-17 00:51:32,384][62408] Updated weights for policy 1, policy_version 14730 (0.0008) -[2023-10-17 00:51:32,747][62408] Updated weights for policy 1, policy_version 14740 (0.0007) -[2023-10-17 00:51:33,121][62408] Updated weights for policy 1, policy_version 14750 (0.0010) -[2023-10-17 00:51:33,189][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000014752_15106048.pth... -[2023-10-17 00:51:33,232][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000013088_13402112.pth -[2023-10-17 00:51:33,525][62373] Updated weights for policy 0, policy_version 14850 (0.0007) -[2023-10-17 00:51:33,898][62373] Updated weights for policy 0, policy_version 14860 (0.0007) -[2023-10-17 00:51:34,268][62373] Updated weights for policy 0, policy_version 14870 (0.0007) -[2023-10-17 00:51:34,643][62373] Updated weights for policy 0, policy_version 14880 (0.0008) -[2023-10-17 00:51:36,903][62408] Updated weights for policy 1, policy_version 14760 (0.0008) -[2023-10-17 00:51:37,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 30343168. Throughput: 0: 1772.6, 1: 1756.8. Samples: 7594626. Policy #0 lag: (min: 31.0, avg: 40.2, max: 63.0) -[2023-10-17 00:51:37,215][61453] Avg episode reward: [(0, '4.820'), (1, '5.180')] -[2023-10-17 00:51:37,277][62408] Updated weights for policy 1, policy_version 14770 (0.0009) -[2023-10-17 00:51:37,653][62408] Updated weights for policy 1, policy_version 14780 (0.0007) -[2023-10-17 00:51:38,461][62373] Updated weights for policy 0, policy_version 14890 (0.0007) -[2023-10-17 00:51:38,835][62373] Updated weights for policy 0, policy_version 14900 (0.0007) -[2023-10-17 00:51:39,211][62373] Updated weights for policy 0, policy_version 14910 (0.0008) -[2023-10-17 00:51:41,499][62408] Updated weights for policy 1, policy_version 14790 (0.0010) -[2023-10-17 00:51:41,871][62408] Updated weights for policy 1, policy_version 14800 (0.0009) -[2023-10-17 00:51:42,214][61453] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 30408704. Throughput: 0: 1771.2, 1: 1785.8. Samples: 7616888. Policy #0 lag: (min: 31.0, avg: 40.2, max: 63.0) -[2023-10-17 00:51:42,214][61453] Avg episode reward: [(0, '4.770'), (1, '5.180')] -[2023-10-17 00:51:42,242][62408] Updated weights for policy 1, policy_version 14810 (0.0010) -[2023-10-17 00:51:42,924][62373] Updated weights for policy 0, policy_version 14920 (0.0008) -[2023-10-17 00:51:43,290][62373] Updated weights for policy 0, policy_version 14930 (0.0010) -[2023-10-17 00:51:43,661][62373] Updated weights for policy 0, policy_version 14940 (0.0008) -[2023-10-17 00:51:46,040][62408] Updated weights for policy 1, policy_version 14820 (0.0010) -[2023-10-17 00:51:46,442][62408] Updated weights for policy 1, policy_version 14830 (0.0007) -[2023-10-17 00:51:46,819][62408] Updated weights for policy 1, policy_version 14840 (0.0009) -[2023-10-17 00:51:47,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 30507008. Throughput: 0: 1796.8, 1: 1758.4. Samples: 7637782. Policy #0 lag: (min: 31.0, avg: 40.2, max: 63.0) -[2023-10-17 00:51:47,215][61453] Avg episode reward: [(0, '4.640'), (1, '5.210')] -[2023-10-17 00:51:47,394][62373] Updated weights for policy 0, policy_version 14950 (0.0007) -[2023-10-17 00:51:47,763][62373] Updated weights for policy 0, policy_version 14960 (0.0007) -[2023-10-17 00:51:48,126][62373] Updated weights for policy 0, policy_version 14970 (0.0008) -[2023-10-17 00:51:50,557][62408] Updated weights for policy 1, policy_version 14850 (0.0009) -[2023-10-17 00:51:50,930][62408] Updated weights for policy 1, policy_version 14860 (0.0008) -[2023-10-17 00:51:51,299][62408] Updated weights for policy 1, policy_version 14870 (0.0008) -[2023-10-17 00:51:51,668][62408] Updated weights for policy 1, policy_version 14880 (0.0008) -[2023-10-17 00:51:51,877][62373] Updated weights for policy 0, policy_version 14980 (0.0009) -[2023-10-17 00:51:52,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 30572544. Throughput: 0: 1767.2, 1: 1774.0. Samples: 7648352. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-17 00:51:52,215][61453] Avg episode reward: [(0, '5.130'), (1, '5.140')] -[2023-10-17 00:51:52,244][62373] Updated weights for policy 0, policy_version 14990 (0.0008) -[2023-10-17 00:51:52,622][62373] Updated weights for policy 0, policy_version 15000 (0.0007) -[2023-10-17 00:51:55,390][62408] Updated weights for policy 1, policy_version 14890 (0.0008) -[2023-10-17 00:51:55,757][62408] Updated weights for policy 1, policy_version 14900 (0.0008) -[2023-10-17 00:51:56,136][62408] Updated weights for policy 1, policy_version 14910 (0.0008) -[2023-10-17 00:51:56,413][62373] Updated weights for policy 0, policy_version 15010 (0.0008) -[2023-10-17 00:51:56,785][62373] Updated weights for policy 0, policy_version 15020 (0.0009) -[2023-10-17 00:51:57,145][62373] Updated weights for policy 0, policy_version 15030 (0.0010) -[2023-10-17 00:51:57,214][61453] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 30638080. Throughput: 0: 1785.8, 1: 1767.8. Samples: 7669688. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-17 00:51:57,214][61453] Avg episode reward: [(0, '5.120'), (1, '4.960')] -[2023-10-17 00:51:57,515][62373] Updated weights for policy 0, policy_version 15040 (0.0009) -[2023-10-17 00:51:59,898][62408] Updated weights for policy 1, policy_version 14920 (0.0010) -[2023-10-17 00:52:00,265][62408] Updated weights for policy 1, policy_version 14930 (0.0009) -[2023-10-17 00:52:00,634][62408] Updated weights for policy 1, policy_version 14940 (0.0007) -[2023-10-17 00:52:01,546][62373] Updated weights for policy 0, policy_version 15050 (0.0010) -[2023-10-17 00:52:01,908][62373] Updated weights for policy 0, policy_version 15060 (0.0008) -[2023-10-17 00:52:02,214][61453] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 14218.0). Total num frames: 30703616. Throughput: 0: 1771.6, 1: 1759.5. Samples: 7690128. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-10-17 00:52:02,214][61453] Avg episode reward: [(0, '4.840'), (1, '4.890')] -[2023-10-17 00:52:02,288][62373] Updated weights for policy 0, policy_version 15070 (0.0008) -[2023-10-17 00:52:04,574][62408] Updated weights for policy 1, policy_version 14950 (0.0009) -[2023-10-17 00:52:04,937][62408] Updated weights for policy 1, policy_version 14960 (0.0010) -[2023-10-17 00:52:05,298][62408] Updated weights for policy 1, policy_version 14970 (0.0011) -[2023-10-17 00:52:05,959][62373] Updated weights for policy 0, policy_version 15080 (0.0008) -[2023-10-17 00:52:06,337][62373] Updated weights for policy 0, policy_version 15090 (0.0009) -[2023-10-17 00:52:06,721][62373] Updated weights for policy 0, policy_version 15100 (0.0010) -[2023-10-17 00:52:07,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 30801920. Throughput: 0: 1774.3, 1: 1768.4. Samples: 7701318. Policy #0 lag: (min: 23.0, avg: 27.2, max: 55.0) -[2023-10-17 00:52:07,215][61453] Avg episode reward: [(0, '5.040'), (1, '5.260')] -[2023-10-17 00:52:09,269][62408] Updated weights for policy 1, policy_version 14980 (0.0009) -[2023-10-17 00:52:09,636][62408] Updated weights for policy 1, policy_version 14990 (0.0008) -[2023-10-17 00:52:09,997][62408] Updated weights for policy 1, policy_version 15000 (0.0008) -[2023-10-17 00:52:10,512][62373] Updated weights for policy 0, policy_version 15110 (0.0007) -[2023-10-17 00:52:10,879][62373] Updated weights for policy 0, policy_version 15120 (0.0009) -[2023-10-17 00:52:11,246][62373] Updated weights for policy 0, policy_version 15130 (0.0008) -[2023-10-17 00:52:12,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 30867456. Throughput: 0: 1781.7, 1: 1752.2. Samples: 7721986. Policy #0 lag: (min: 23.0, avg: 27.2, max: 55.0) -[2023-10-17 00:52:12,214][61453] Avg episode reward: [(0, '4.850'), (1, '5.010')] -[2023-10-17 00:52:13,764][62408] Updated weights for policy 1, policy_version 15010 (0.0008) -[2023-10-17 00:52:14,132][62408] Updated weights for policy 1, policy_version 15020 (0.0009) -[2023-10-17 00:52:14,492][62408] Updated weights for policy 1, policy_version 15030 (0.0007) -[2023-10-17 00:52:14,861][62408] Updated weights for policy 1, policy_version 15040 (0.0009) -[2023-10-17 00:52:14,897][62373] Updated weights for policy 0, policy_version 15140 (0.0009) -[2023-10-17 00:52:15,282][62373] Updated weights for policy 0, policy_version 15150 (0.0008) -[2023-10-17 00:52:15,650][62373] Updated weights for policy 0, policy_version 15160 (0.0008) -[2023-10-17 00:52:17,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 30932992. Throughput: 0: 1767.6, 1: 1761.1. Samples: 7743638. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:52:17,215][61453] Avg episode reward: [(0, '4.740'), (1, '5.090')] -[2023-10-17 00:52:18,621][62408] Updated weights for policy 1, policy_version 15050 (0.0007) -[2023-10-17 00:52:18,994][62408] Updated weights for policy 1, policy_version 15060 (0.0008) -[2023-10-17 00:52:19,355][62408] Updated weights for policy 1, policy_version 15070 (0.0009) -[2023-10-17 00:52:19,386][62373] Updated weights for policy 0, policy_version 15170 (0.0009) -[2023-10-17 00:52:19,756][62373] Updated weights for policy 0, policy_version 15180 (0.0007) -[2023-10-17 00:52:20,124][62373] Updated weights for policy 0, policy_version 15190 (0.0009) -[2023-10-17 00:52:20,496][62373] Updated weights for policy 0, policy_version 15200 (0.0008) -[2023-10-17 00:52:22,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 30998528. Throughput: 0: 1785.7, 1: 1762.4. Samples: 7754288. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:52:22,215][61453] Avg episode reward: [(0, '4.620'), (1, '5.610')] -[2023-10-17 00:52:23,255][62408] Updated weights for policy 1, policy_version 15080 (0.0011) -[2023-10-17 00:52:23,621][62408] Updated weights for policy 1, policy_version 15090 (0.0010) -[2023-10-17 00:52:23,990][62408] Updated weights for policy 1, policy_version 15100 (0.0009) -[2023-10-17 00:52:24,502][62373] Updated weights for policy 0, policy_version 15210 (0.0010) -[2023-10-17 00:52:24,878][62373] Updated weights for policy 0, policy_version 15220 (0.0009) -[2023-10-17 00:52:25,244][62373] Updated weights for policy 0, policy_version 15230 (0.0007) -[2023-10-17 00:52:27,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 31064064. Throughput: 0: 1764.4, 1: 1762.8. Samples: 7775610. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:52:27,215][61453] Avg episode reward: [(0, '4.990'), (1, '5.330')] -[2023-10-17 00:52:27,779][62408] Updated weights for policy 1, policy_version 15110 (0.0009) -[2023-10-17 00:52:28,147][62408] Updated weights for policy 1, policy_version 15120 (0.0008) -[2023-10-17 00:52:28,511][62408] Updated weights for policy 1, policy_version 15130 (0.0009) -[2023-10-17 00:52:29,206][62373] Updated weights for policy 0, policy_version 15240 (0.0007) -[2023-10-17 00:52:29,583][62373] Updated weights for policy 0, policy_version 15250 (0.0007) -[2023-10-17 00:52:29,953][62373] Updated weights for policy 0, policy_version 15260 (0.0009) -[2023-10-17 00:52:32,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 31129600. Throughput: 0: 1760.8, 1: 1786.3. Samples: 7797400. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:52:32,215][61453] Avg episode reward: [(0, '4.870'), (1, '5.270')] -[2023-10-17 00:52:32,419][62408] Updated weights for policy 1, policy_version 15140 (0.0009) -[2023-10-17 00:52:32,818][62408] Updated weights for policy 1, policy_version 15150 (0.0009) -[2023-10-17 00:52:33,185][62408] Updated weights for policy 1, policy_version 15160 (0.0010) -[2023-10-17 00:52:33,626][62373] Updated weights for policy 0, policy_version 15270 (0.0009) -[2023-10-17 00:52:33,997][62373] Updated weights for policy 0, policy_version 15280 (0.0008) -[2023-10-17 00:52:34,367][62373] Updated weights for policy 0, policy_version 15290 (0.0007) -[2023-10-17 00:52:36,927][62408] Updated weights for policy 1, policy_version 15170 (0.0009) -[2023-10-17 00:52:37,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 31195136. Throughput: 0: 1762.7, 1: 1756.9. Samples: 7806734. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:52:37,215][61453] Avg episode reward: [(0, '5.110'), (1, '5.510')] -[2023-10-17 00:52:37,299][62408] Updated weights for policy 1, policy_version 15180 (0.0007) -[2023-10-17 00:52:37,670][62408] Updated weights for policy 1, policy_version 15190 (0.0008) -[2023-10-17 00:52:38,029][62408] Updated weights for policy 1, policy_version 15200 (0.0010) -[2023-10-17 00:52:38,256][62373] Updated weights for policy 0, policy_version 15300 (0.0008) -[2023-10-17 00:52:38,626][62373] Updated weights for policy 0, policy_version 15310 (0.0011) -[2023-10-17 00:52:38,994][62373] Updated weights for policy 0, policy_version 15320 (0.0010) -[2023-10-17 00:52:41,818][62408] Updated weights for policy 1, policy_version 15210 (0.0010) -[2023-10-17 00:52:42,188][62408] Updated weights for policy 1, policy_version 15220 (0.0008) -[2023-10-17 00:52:42,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 31260672. Throughput: 0: 1757.0, 1: 1773.5. Samples: 7828560. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:52:42,215][61453] Avg episode reward: [(0, '4.820'), (1, '5.480')] -[2023-10-17 00:52:42,551][62408] Updated weights for policy 1, policy_version 15230 (0.0010) -[2023-10-17 00:52:42,773][62373] Updated weights for policy 0, policy_version 15330 (0.0008) -[2023-10-17 00:52:43,148][62373] Updated weights for policy 0, policy_version 15340 (0.0010) -[2023-10-17 00:52:43,529][62373] Updated weights for policy 0, policy_version 15350 (0.0009) -[2023-10-17 00:52:43,898][62373] Updated weights for policy 0, policy_version 15360 (0.0007) -[2023-10-17 00:52:46,372][62408] Updated weights for policy 1, policy_version 15240 (0.0007) -[2023-10-17 00:52:46,743][62408] Updated weights for policy 1, policy_version 15250 (0.0007) -[2023-10-17 00:52:47,112][62408] Updated weights for policy 1, policy_version 15260 (0.0007) -[2023-10-17 00:52:47,214][61453] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 31326208. Throughput: 0: 1783.5, 1: 1762.0. Samples: 7849672. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) -[2023-10-17 00:52:47,214][61453] Avg episode reward: [(0, '4.750'), (1, '5.770')] -[2023-10-17 00:52:47,258][62252] Saving new best policy, reward=5.770! -[2023-10-17 00:52:47,815][62373] Updated weights for policy 0, policy_version 15370 (0.0010) -[2023-10-17 00:52:48,181][62373] Updated weights for policy 0, policy_version 15380 (0.0008) -[2023-10-17 00:52:48,556][62373] Updated weights for policy 0, policy_version 15390 (0.0007) -[2023-10-17 00:52:50,926][62408] Updated weights for policy 1, policy_version 15270 (0.0009) -[2023-10-17 00:52:51,290][62408] Updated weights for policy 1, policy_version 15280 (0.0007) -[2023-10-17 00:52:51,652][62408] Updated weights for policy 1, policy_version 15290 (0.0011) -[2023-10-17 00:52:52,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 31424512. Throughput: 0: 1759.0, 1: 1770.0. Samples: 7860120. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) -[2023-10-17 00:52:52,215][61453] Avg episode reward: [(0, '5.210'), (1, '5.440')] -[2023-10-17 00:52:52,377][62373] Updated weights for policy 0, policy_version 15400 (0.0007) -[2023-10-17 00:52:52,747][62373] Updated weights for policy 0, policy_version 15410 (0.0008) -[2023-10-17 00:52:53,109][62373] Updated weights for policy 0, policy_version 15420 (0.0009) -[2023-10-17 00:52:55,544][62408] Updated weights for policy 1, policy_version 15300 (0.0010) -[2023-10-17 00:52:55,916][62408] Updated weights for policy 1, policy_version 15310 (0.0009) -[2023-10-17 00:52:56,278][62408] Updated weights for policy 1, policy_version 15320 (0.0007) -[2023-10-17 00:52:56,968][62373] Updated weights for policy 0, policy_version 15430 (0.0007) -[2023-10-17 00:52:57,214][61453] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 31490048. Throughput: 0: 1776.7, 1: 1772.5. Samples: 7881702. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) -[2023-10-17 00:52:57,215][61453] Avg episode reward: [(0, '5.230'), (1, '5.270')] -[2023-10-17 00:52:57,334][62373] Updated weights for policy 0, policy_version 15440 (0.0007) -[2023-10-17 00:52:57,709][62373] Updated weights for policy 0, policy_version 15450 (0.0007) -[2023-10-17 00:53:00,138][62408] Updated weights for policy 1, policy_version 15330 (0.0008) -[2023-10-17 00:53:00,503][62408] Updated weights for policy 1, policy_version 15340 (0.0007) -[2023-10-17 00:53:00,875][62408] Updated weights for policy 1, policy_version 15350 (0.0008) -[2023-10-17 00:53:01,234][62408] Updated weights for policy 1, policy_version 15360 (0.0009) -[2023-10-17 00:53:01,408][62373] Updated weights for policy 0, policy_version 15460 (0.0008) -[2023-10-17 00:53:01,803][62373] Updated weights for policy 0, policy_version 15470 (0.0009) -[2023-10-17 00:53:02,167][62373] Updated weights for policy 0, policy_version 15480 (0.0009) -[2023-10-17 00:53:02,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 31555584. Throughput: 0: 1775.9, 1: 1742.4. Samples: 7901958. Policy #0 lag: (min: 30.0, avg: 37.9, max: 62.0) -[2023-10-17 00:53:02,215][61453] Avg episode reward: [(0, '5.530'), (1, '4.880')] -[2023-10-17 00:53:05,059][62408] Updated weights for policy 1, policy_version 15370 (0.0009) -[2023-10-17 00:53:05,426][62408] Updated weights for policy 1, policy_version 15380 (0.0008) -[2023-10-17 00:53:05,801][62408] Updated weights for policy 1, policy_version 15390 (0.0008) -[2023-10-17 00:53:05,944][62373] Updated weights for policy 0, policy_version 15490 (0.0008) -[2023-10-17 00:53:06,314][62373] Updated weights for policy 0, policy_version 15500 (0.0010) -[2023-10-17 00:53:06,682][62373] Updated weights for policy 0, policy_version 15510 (0.0009) -[2023-10-17 00:53:07,055][62373] Updated weights for policy 0, policy_version 15520 (0.0008) -[2023-10-17 00:53:07,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 31653888. Throughput: 0: 1774.1, 1: 1768.6. Samples: 7913710. Policy #0 lag: (min: 30.0, avg: 37.9, max: 62.0) -[2023-10-17 00:53:07,215][61453] Avg episode reward: [(0, '5.520'), (1, '5.260')] -[2023-10-17 00:53:09,544][62408] Updated weights for policy 1, policy_version 15400 (0.0008) -[2023-10-17 00:53:09,910][62408] Updated weights for policy 1, policy_version 15410 (0.0009) -[2023-10-17 00:53:10,275][62408] Updated weights for policy 1, policy_version 15420 (0.0007) -[2023-10-17 00:53:10,960][62373] Updated weights for policy 0, policy_version 15530 (0.0009) -[2023-10-17 00:53:11,333][62373] Updated weights for policy 0, policy_version 15540 (0.0010) -[2023-10-17 00:53:11,711][62373] Updated weights for policy 0, policy_version 15550 (0.0008) -[2023-10-17 00:53:12,214][61453] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 31719424. Throughput: 0: 1785.0, 1: 1742.8. Samples: 7934358. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-17 00:53:12,215][61453] Avg episode reward: [(0, '5.660'), (1, '4.910')] -[2023-10-17 00:53:14,089][62408] Updated weights for policy 1, policy_version 15430 (0.0007) -[2023-10-17 00:53:14,462][62408] Updated weights for policy 1, policy_version 15440 (0.0009) -[2023-10-17 00:53:14,840][62408] Updated weights for policy 1, policy_version 15450 (0.0011) -[2023-10-17 00:53:15,403][62373] Updated weights for policy 0, policy_version 15560 (0.0008) -[2023-10-17 00:53:15,775][62373] Updated weights for policy 0, policy_version 15570 (0.0007) -[2023-10-17 00:53:16,147][62373] Updated weights for policy 0, policy_version 15580 (0.0009) -[2023-10-17 00:53:17,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 31784960. Throughput: 0: 1765.7, 1: 1748.2. Samples: 7955526. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-17 00:53:17,215][61453] Avg episode reward: [(0, '5.600'), (1, '4.950')] -[2023-10-17 00:53:18,703][62408] Updated weights for policy 1, policy_version 15460 (0.0010) -[2023-10-17 00:53:19,076][62408] Updated weights for policy 1, policy_version 15470 (0.0008) -[2023-10-17 00:53:19,449][62408] Updated weights for policy 1, policy_version 15480 (0.0008) -[2023-10-17 00:53:19,731][62373] Updated weights for policy 0, policy_version 15590 (0.0009) -[2023-10-17 00:53:20,109][62373] Updated weights for policy 0, policy_version 15600 (0.0007) -[2023-10-17 00:53:20,478][62373] Updated weights for policy 0, policy_version 15610 (0.0009) -[2023-10-17 00:53:22,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 31850496. Throughput: 0: 1796.5, 1: 1750.8. Samples: 7966362. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-17 00:53:22,215][61453] Avg episode reward: [(0, '5.630'), (1, '5.310')] -[2023-10-17 00:53:23,371][62408] Updated weights for policy 1, policy_version 15490 (0.0008) -[2023-10-17 00:53:23,739][62408] Updated weights for policy 1, policy_version 15500 (0.0008) -[2023-10-17 00:53:24,103][62408] Updated weights for policy 1, policy_version 15510 (0.0008) -[2023-10-17 00:53:24,317][62373] Updated weights for policy 0, policy_version 15620 (0.0010) -[2023-10-17 00:53:24,470][62408] Updated weights for policy 1, policy_version 15520 (0.0009) -[2023-10-17 00:53:24,690][62373] Updated weights for policy 0, policy_version 15630 (0.0009) -[2023-10-17 00:53:25,059][62373] Updated weights for policy 0, policy_version 15640 (0.0009) -[2023-10-17 00:53:27,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 31916032. Throughput: 0: 1778.6, 1: 1748.7. Samples: 7987288. Policy #0 lag: (min: 15.0, avg: 25.2, max: 47.0) -[2023-10-17 00:53:27,214][61453] Avg episode reward: [(0, '5.480'), (1, '5.500')] -[2023-10-17 00:53:28,343][62408] Updated weights for policy 1, policy_version 15530 (0.0009) -[2023-10-17 00:53:28,717][62408] Updated weights for policy 1, policy_version 15540 (0.0009) -[2023-10-17 00:53:28,847][62373] Updated weights for policy 0, policy_version 15650 (0.0010) -[2023-10-17 00:53:29,083][62408] Updated weights for policy 1, policy_version 15550 (0.0010) -[2023-10-17 00:53:29,216][62373] Updated weights for policy 0, policy_version 15660 (0.0009) -[2023-10-17 00:53:29,587][62373] Updated weights for policy 0, policy_version 15670 (0.0009) -[2023-10-17 00:53:29,949][62373] Updated weights for policy 0, policy_version 15680 (0.0009) -[2023-10-17 00:53:32,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 31981568. Throughput: 0: 1781.2, 1: 1766.7. Samples: 8009326. Policy #0 lag: (min: 15.0, avg: 25.2, max: 47.0) -[2023-10-17 00:53:32,215][61453] Avg episode reward: [(0, '5.130'), (1, '5.010')] -[2023-10-17 00:53:32,227][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000015552_15925248.pth... -[2023-10-17 00:53:32,227][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000015680_16056320.pth... -[2023-10-17 00:53:32,265][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000014016_14352384.pth -[2023-10-17 00:53:32,266][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000013920_14254080.pth -[2023-10-17 00:53:32,991][62408] Updated weights for policy 1, policy_version 15560 (0.0009) -[2023-10-17 00:53:33,358][62408] Updated weights for policy 1, policy_version 15570 (0.0010) -[2023-10-17 00:53:33,716][62373] Updated weights for policy 0, policy_version 15690 (0.0008) -[2023-10-17 00:53:33,726][62408] Updated weights for policy 1, policy_version 15580 (0.0008) -[2023-10-17 00:53:34,073][62373] Updated weights for policy 0, policy_version 15700 (0.0009) -[2023-10-17 00:53:34,439][62373] Updated weights for policy 0, policy_version 15710 (0.0011) -[2023-10-17 00:53:37,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 32047104. Throughput: 0: 1780.3, 1: 1749.7. Samples: 8018970. Policy #0 lag: (min: 15.0, avg: 25.2, max: 47.0) -[2023-10-17 00:53:37,215][61453] Avg episode reward: [(0, '5.460'), (1, '5.080')] -[2023-10-17 00:53:37,554][62408] Updated weights for policy 1, policy_version 15590 (0.0009) -[2023-10-17 00:53:37,913][62408] Updated weights for policy 1, policy_version 15600 (0.0009) -[2023-10-17 00:53:38,282][62408] Updated weights for policy 1, policy_version 15610 (0.0008) -[2023-10-17 00:53:38,292][62373] Updated weights for policy 0, policy_version 15720 (0.0008) -[2023-10-17 00:53:38,670][62373] Updated weights for policy 0, policy_version 15730 (0.0007) -[2023-10-17 00:53:39,032][62373] Updated weights for policy 0, policy_version 15740 (0.0009) -[2023-10-17 00:53:42,157][62408] Updated weights for policy 1, policy_version 15620 (0.0008) -[2023-10-17 00:53:42,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 32112640. Throughput: 0: 1776.8, 1: 1765.4. Samples: 8041102. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-10-17 00:53:42,215][61453] Avg episode reward: [(0, '5.830'), (1, '5.370')] -[2023-10-17 00:53:42,216][62094] Saving new best policy, reward=5.830! -[2023-10-17 00:53:42,523][62408] Updated weights for policy 1, policy_version 15630 (0.0008) -[2023-10-17 00:53:42,789][62373] Updated weights for policy 0, policy_version 15750 (0.0008) -[2023-10-17 00:53:42,887][62408] Updated weights for policy 1, policy_version 15640 (0.0007) -[2023-10-17 00:53:43,157][62373] Updated weights for policy 0, policy_version 15760 (0.0008) -[2023-10-17 00:53:43,520][62373] Updated weights for policy 0, policy_version 15770 (0.0011) -[2023-10-17 00:53:46,772][62408] Updated weights for policy 1, policy_version 15650 (0.0008) -[2023-10-17 00:53:47,140][62408] Updated weights for policy 1, policy_version 15660 (0.0007) -[2023-10-17 00:53:47,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 32178176. Throughput: 0: 1795.6, 1: 1780.6. Samples: 8062886. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-10-17 00:53:47,214][61453] Avg episode reward: [(0, '5.710'), (1, '5.170')] -[2023-10-17 00:53:47,352][62373] Updated weights for policy 0, policy_version 15780 (0.0009) -[2023-10-17 00:53:47,501][62408] Updated weights for policy 1, policy_version 15670 (0.0008) -[2023-10-17 00:53:47,741][62373] Updated weights for policy 0, policy_version 15790 (0.0007) -[2023-10-17 00:53:47,867][62408] Updated weights for policy 1, policy_version 15680 (0.0007) -[2023-10-17 00:53:48,101][62373] Updated weights for policy 0, policy_version 15800 (0.0009) -[2023-10-17 00:53:51,639][62408] Updated weights for policy 1, policy_version 15690 (0.0007) -[2023-10-17 00:53:51,909][62373] Updated weights for policy 0, policy_version 15810 (0.0011) -[2023-10-17 00:53:52,017][62408] Updated weights for policy 1, policy_version 15700 (0.0007) -[2023-10-17 00:53:52,214][61453] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 32243712. Throughput: 0: 1776.1, 1: 1756.0. Samples: 8072650. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-10-17 00:53:52,214][61453] Avg episode reward: [(0, '6.080'), (1, '5.470')] -[2023-10-17 00:53:52,277][62373] Updated weights for policy 0, policy_version 15820 (0.0007) -[2023-10-17 00:53:52,379][62408] Updated weights for policy 1, policy_version 15710 (0.0007) -[2023-10-17 00:53:52,643][62373] Updated weights for policy 0, policy_version 15830 (0.0009) -[2023-10-17 00:53:53,016][62373] Updated weights for policy 0, policy_version 15840 (0.0008) -[2023-10-17 00:53:53,015][62094] Saving new best policy, reward=6.080! -[2023-10-17 00:53:56,361][62408] Updated weights for policy 1, policy_version 15720 (0.0010) -[2023-10-17 00:53:56,741][62408] Updated weights for policy 1, policy_version 15730 (0.0007) -[2023-10-17 00:53:56,836][62373] Updated weights for policy 0, policy_version 15850 (0.0008) -[2023-10-17 00:53:57,098][62408] Updated weights for policy 1, policy_version 15740 (0.0008) -[2023-10-17 00:53:57,199][62373] Updated weights for policy 0, policy_version 15860 (0.0008) -[2023-10-17 00:53:57,214][61453] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 32309248. Throughput: 0: 1784.4, 1: 1774.7. Samples: 8094518. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:53:57,214][61453] Avg episode reward: [(0, '5.740'), (1, '5.480')] -[2023-10-17 00:53:57,578][62373] Updated weights for policy 0, policy_version 15870 (0.0009) -[2023-10-17 00:54:01,047][62408] Updated weights for policy 1, policy_version 15750 (0.0008) -[2023-10-17 00:54:01,328][62373] Updated weights for policy 0, policy_version 15880 (0.0009) -[2023-10-17 00:54:01,419][62408] Updated weights for policy 1, policy_version 15760 (0.0007) -[2023-10-17 00:54:01,703][62373] Updated weights for policy 0, policy_version 15890 (0.0010) -[2023-10-17 00:54:01,782][62408] Updated weights for policy 1, policy_version 15770 (0.0008) -[2023-10-17 00:54:02,083][62373] Updated weights for policy 0, policy_version 15900 (0.0009) -[2023-10-17 00:54:02,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 32407552. Throughput: 0: 1781.4, 1: 1741.7. Samples: 8114064. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:54:02,214][61453] Avg episode reward: [(0, '5.910'), (1, '5.900')] -[2023-10-17 00:54:02,223][62252] Saving new best policy, reward=5.900! -[2023-10-17 00:54:05,760][62373] Updated weights for policy 0, policy_version 15910 (0.0008) -[2023-10-17 00:54:05,784][62408] Updated weights for policy 1, policy_version 15780 (0.0008) -[2023-10-17 00:54:06,120][62373] Updated weights for policy 0, policy_version 15920 (0.0008) -[2023-10-17 00:54:06,173][62408] Updated weights for policy 1, policy_version 15790 (0.0008) -[2023-10-17 00:54:06,491][62373] Updated weights for policy 0, policy_version 15930 (0.0008) -[2023-10-17 00:54:06,541][62408] Updated weights for policy 1, policy_version 15800 (0.0007) -[2023-10-17 00:54:07,214][61453] Fps is (10 sec: 19660.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 32505856. Throughput: 0: 1780.4, 1: 1766.9. Samples: 8125990. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-10-17 00:54:07,215][61453] Avg episode reward: [(0, '5.950'), (1, '5.940')] -[2023-10-17 00:54:07,217][62252] Saving new best policy, reward=5.940! -[2023-10-17 00:54:10,285][62373] Updated weights for policy 0, policy_version 15940 (0.0007) -[2023-10-17 00:54:10,342][62408] Updated weights for policy 1, policy_version 15810 (0.0007) -[2023-10-17 00:54:10,657][62373] Updated weights for policy 0, policy_version 15950 (0.0009) -[2023-10-17 00:54:10,717][62408] Updated weights for policy 1, policy_version 15820 (0.0008) -[2023-10-17 00:54:11,020][62373] Updated weights for policy 0, policy_version 15960 (0.0008) -[2023-10-17 00:54:11,080][62408] Updated weights for policy 1, policy_version 15830 (0.0007) -[2023-10-17 00:54:11,441][62408] Updated weights for policy 1, policy_version 15840 (0.0007) -[2023-10-17 00:54:12,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 32571392. Throughput: 0: 1783.6, 1: 1750.0. Samples: 8146298. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-10-17 00:54:12,214][61453] Avg episode reward: [(0, '5.530'), (1, '5.800')] -[2023-10-17 00:54:14,796][62373] Updated weights for policy 0, policy_version 15970 (0.0008) -[2023-10-17 00:54:15,172][62373] Updated weights for policy 0, policy_version 15980 (0.0008) -[2023-10-17 00:54:15,386][62408] Updated weights for policy 1, policy_version 15850 (0.0009) -[2023-10-17 00:54:15,541][62373] Updated weights for policy 0, policy_version 15990 (0.0008) -[2023-10-17 00:54:15,754][62408] Updated weights for policy 1, policy_version 15860 (0.0008) -[2023-10-17 00:54:15,903][62373] Updated weights for policy 0, policy_version 16000 (0.0008) -[2023-10-17 00:54:16,115][62408] Updated weights for policy 1, policy_version 15870 (0.0009) -[2023-10-17 00:54:17,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 32636928. Throughput: 0: 1772.0, 1: 1735.7. Samples: 8167172. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-10-17 00:54:17,215][61453] Avg episode reward: [(0, '5.660'), (1, '5.920')] -[2023-10-17 00:54:19,780][62373] Updated weights for policy 0, policy_version 16010 (0.0008) -[2023-10-17 00:54:19,978][62408] Updated weights for policy 1, policy_version 15880 (0.0007) -[2023-10-17 00:54:20,142][62373] Updated weights for policy 0, policy_version 16020 (0.0007) -[2023-10-17 00:54:20,346][62408] Updated weights for policy 1, policy_version 15890 (0.0007) -[2023-10-17 00:54:20,510][62373] Updated weights for policy 0, policy_version 16030 (0.0007) -[2023-10-17 00:54:20,711][62408] Updated weights for policy 1, policy_version 15900 (0.0010) -[2023-10-17 00:54:22,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 32702464. Throughput: 0: 1791.0, 1: 1756.7. Samples: 8178614. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-17 00:54:22,215][61453] Avg episode reward: [(0, '5.820'), (1, '5.330')] -[2023-10-17 00:54:24,159][62373] Updated weights for policy 0, policy_version 16040 (0.0007) -[2023-10-17 00:54:24,533][62373] Updated weights for policy 0, policy_version 16050 (0.0008) -[2023-10-17 00:54:24,590][62408] Updated weights for policy 1, policy_version 15910 (0.0008) -[2023-10-17 00:54:24,903][62373] Updated weights for policy 0, policy_version 16060 (0.0008) -[2023-10-17 00:54:24,954][62408] Updated weights for policy 1, policy_version 15920 (0.0010) -[2023-10-17 00:54:25,321][62408] Updated weights for policy 1, policy_version 15930 (0.0007) -[2023-10-17 00:54:27,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 32768000. Throughput: 0: 1778.4, 1: 1727.1. Samples: 8198850. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-17 00:54:27,214][61453] Avg episode reward: [(0, '5.610'), (1, '5.160')] -[2023-10-17 00:54:28,719][62373] Updated weights for policy 0, policy_version 16070 (0.0007) -[2023-10-17 00:54:29,024][62408] Updated weights for policy 1, policy_version 15940 (0.0008) -[2023-10-17 00:54:29,089][62373] Updated weights for policy 0, policy_version 16080 (0.0009) -[2023-10-17 00:54:29,389][62408] Updated weights for policy 1, policy_version 15950 (0.0007) -[2023-10-17 00:54:29,456][62373] Updated weights for policy 0, policy_version 16090 (0.0008) -[2023-10-17 00:54:29,758][62408] Updated weights for policy 1, policy_version 15960 (0.0008) -[2023-10-17 00:54:32,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 32833536. Throughput: 0: 1775.5, 1: 1732.5. Samples: 8220744. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-17 00:54:32,214][61453] Avg episode reward: [(0, '5.570'), (1, '5.070')] -[2023-10-17 00:54:33,299][62373] Updated weights for policy 0, policy_version 16100 (0.0009) -[2023-10-17 00:54:33,691][62373] Updated weights for policy 0, policy_version 16110 (0.0009) -[2023-10-17 00:54:33,770][62408] Updated weights for policy 1, policy_version 15970 (0.0008) -[2023-10-17 00:54:34,050][62373] Updated weights for policy 0, policy_version 16120 (0.0008) -[2023-10-17 00:54:34,139][62408] Updated weights for policy 1, policy_version 15980 (0.0008) -[2023-10-17 00:54:34,504][62408] Updated weights for policy 1, policy_version 15990 (0.0007) -[2023-10-17 00:54:34,870][62408] Updated weights for policy 1, policy_version 16000 (0.0009) -[2023-10-17 00:54:37,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 32899072. Throughput: 0: 1774.1, 1: 1728.4. Samples: 8230262. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:54:37,214][61453] Avg episode reward: [(0, '5.640'), (1, '4.740')] -[2023-10-17 00:54:37,869][62373] Updated weights for policy 0, policy_version 16130 (0.0008) -[2023-10-17 00:54:38,242][62373] Updated weights for policy 0, policy_version 16140 (0.0009) -[2023-10-17 00:54:38,608][62373] Updated weights for policy 0, policy_version 16150 (0.0007) -[2023-10-17 00:54:38,778][62408] Updated weights for policy 1, policy_version 16010 (0.0007) -[2023-10-17 00:54:38,975][62373] Updated weights for policy 0, policy_version 16160 (0.0008) -[2023-10-17 00:54:39,152][62408] Updated weights for policy 1, policy_version 16020 (0.0009) -[2023-10-17 00:54:39,516][62408] Updated weights for policy 1, policy_version 16030 (0.0010) -[2023-10-17 00:54:42,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 32964608. Throughput: 0: 1771.6, 1: 1726.3. Samples: 8251924. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:54:42,215][61453] Avg episode reward: [(0, '5.510'), (1, '4.910')] -[2023-10-17 00:54:42,812][62373] Updated weights for policy 0, policy_version 16170 (0.0011) -[2023-10-17 00:54:43,179][62373] Updated weights for policy 0, policy_version 16180 (0.0008) -[2023-10-17 00:54:43,334][62408] Updated weights for policy 1, policy_version 16040 (0.0008) -[2023-10-17 00:54:43,552][62373] Updated weights for policy 0, policy_version 16190 (0.0008) -[2023-10-17 00:54:43,695][62408] Updated weights for policy 1, policy_version 16050 (0.0009) -[2023-10-17 00:54:44,060][62408] Updated weights for policy 1, policy_version 16060 (0.0010) -[2023-10-17 00:54:47,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 33030144. Throughput: 0: 1798.7, 1: 1755.7. Samples: 8274010. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:54:47,214][61453] Avg episode reward: [(0, '5.710'), (1, '5.090')] -[2023-10-17 00:54:47,309][62373] Updated weights for policy 0, policy_version 16200 (0.0008) -[2023-10-17 00:54:47,675][62373] Updated weights for policy 0, policy_version 16210 (0.0007) -[2023-10-17 00:54:47,966][62408] Updated weights for policy 1, policy_version 16070 (0.0009) -[2023-10-17 00:54:48,047][62373] Updated weights for policy 0, policy_version 16220 (0.0007) -[2023-10-17 00:54:48,332][62408] Updated weights for policy 1, policy_version 16080 (0.0009) -[2023-10-17 00:54:48,709][62408] Updated weights for policy 1, policy_version 16090 (0.0009) -[2023-10-17 00:54:51,928][62373] Updated weights for policy 0, policy_version 16230 (0.0008) -[2023-10-17 00:54:52,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 33095680. Throughput: 0: 1768.0, 1: 1732.0. Samples: 8283494. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:54:52,215][61453] Avg episode reward: [(0, '5.470'), (1, '5.470')] -[2023-10-17 00:54:52,302][62373] Updated weights for policy 0, policy_version 16240 (0.0008) -[2023-10-17 00:54:52,471][62408] Updated weights for policy 1, policy_version 16100 (0.0007) -[2023-10-17 00:54:52,673][62373] Updated weights for policy 0, policy_version 16250 (0.0009) -[2023-10-17 00:54:52,844][62408] Updated weights for policy 1, policy_version 16110 (0.0007) -[2023-10-17 00:54:53,209][62408] Updated weights for policy 1, policy_version 16120 (0.0009) -[2023-10-17 00:54:56,475][62373] Updated weights for policy 0, policy_version 16260 (0.0009) -[2023-10-17 00:54:56,843][62373] Updated weights for policy 0, policy_version 16270 (0.0007) -[2023-10-17 00:54:56,937][62408] Updated weights for policy 1, policy_version 16130 (0.0009) -[2023-10-17 00:54:57,214][62373] Updated weights for policy 0, policy_version 16280 (0.0007) -[2023-10-17 00:54:57,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 33161216. Throughput: 0: 1786.6, 1: 1752.9. Samples: 8305576. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:54:57,215][61453] Avg episode reward: [(0, '5.530'), (1, '5.230')] -[2023-10-17 00:54:57,308][62408] Updated weights for policy 1, policy_version 16140 (0.0009) -[2023-10-17 00:54:57,669][62408] Updated weights for policy 1, policy_version 16150 (0.0007) -[2023-10-17 00:54:58,039][62408] Updated weights for policy 1, policy_version 16160 (0.0008) -[2023-10-17 00:55:00,993][62373] Updated weights for policy 0, policy_version 16290 (0.0008) -[2023-10-17 00:55:01,372][62373] Updated weights for policy 0, policy_version 16300 (0.0010) -[2023-10-17 00:55:01,738][62373] Updated weights for policy 0, policy_version 16310 (0.0010) -[2023-10-17 00:55:01,770][62408] Updated weights for policy 1, policy_version 16170 (0.0007) -[2023-10-17 00:55:02,109][62373] Updated weights for policy 0, policy_version 16320 (0.0008) -[2023-10-17 00:55:02,140][62408] Updated weights for policy 1, policy_version 16180 (0.0008) -[2023-10-17 00:55:02,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 33259520. Throughput: 0: 1768.6, 1: 1761.2. Samples: 8326014. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) -[2023-10-17 00:55:02,215][61453] Avg episode reward: [(0, '5.350'), (1, '5.430')] -[2023-10-17 00:55:02,518][62408] Updated weights for policy 1, policy_version 16190 (0.0008) -[2023-10-17 00:55:05,868][62373] Updated weights for policy 0, policy_version 16330 (0.0009) -[2023-10-17 00:55:06,234][62373] Updated weights for policy 0, policy_version 16340 (0.0008) -[2023-10-17 00:55:06,325][62408] Updated weights for policy 1, policy_version 16200 (0.0007) -[2023-10-17 00:55:06,596][62373] Updated weights for policy 0, policy_version 16350 (0.0009) -[2023-10-17 00:55:06,685][62408] Updated weights for policy 1, policy_version 16210 (0.0008) -[2023-10-17 00:55:07,057][62408] Updated weights for policy 1, policy_version 16220 (0.0008) -[2023-10-17 00:55:07,214][61453] Fps is (10 sec: 19661.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 33357824. Throughput: 0: 1778.1, 1: 1748.4. Samples: 8337304. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) -[2023-10-17 00:55:07,214][61453] Avg episode reward: [(0, '5.800'), (1, '5.830')] -[2023-10-17 00:55:10,294][62373] Updated weights for policy 0, policy_version 16360 (0.0008) -[2023-10-17 00:55:10,662][62373] Updated weights for policy 0, policy_version 16370 (0.0009) -[2023-10-17 00:55:11,019][62408] Updated weights for policy 1, policy_version 16230 (0.0008) -[2023-10-17 00:55:11,026][62373] Updated weights for policy 0, policy_version 16380 (0.0008) -[2023-10-17 00:55:11,393][62408] Updated weights for policy 1, policy_version 16240 (0.0009) -[2023-10-17 00:55:11,769][62408] Updated weights for policy 1, policy_version 16250 (0.0009) -[2023-10-17 00:55:12,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 33423360. Throughput: 0: 1765.5, 1: 1775.9. Samples: 8358214. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) -[2023-10-17 00:55:12,215][61453] Avg episode reward: [(0, '5.720'), (1, '6.050')] -[2023-10-17 00:55:12,216][62252] Saving new best policy, reward=6.050! -[2023-10-17 00:55:14,905][62373] Updated weights for policy 0, policy_version 16390 (0.0008) -[2023-10-17 00:55:15,284][62373] Updated weights for policy 0, policy_version 16400 (0.0008) -[2023-10-17 00:55:15,604][62408] Updated weights for policy 1, policy_version 16260 (0.0009) -[2023-10-17 00:55:15,655][62373] Updated weights for policy 0, policy_version 16410 (0.0009) -[2023-10-17 00:55:15,973][62408] Updated weights for policy 1, policy_version 16270 (0.0009) -[2023-10-17 00:55:16,349][62408] Updated weights for policy 1, policy_version 16280 (0.0009) -[2023-10-17 00:55:17,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 33488896. Throughput: 0: 1759.1, 1: 1750.5. Samples: 8378676. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) -[2023-10-17 00:55:17,215][61453] Avg episode reward: [(0, '5.690'), (1, '5.820')] -[2023-10-17 00:55:19,609][62373] Updated weights for policy 0, policy_version 16420 (0.0009) -[2023-10-17 00:55:20,014][62373] Updated weights for policy 0, policy_version 16430 (0.0007) -[2023-10-17 00:55:20,086][62408] Updated weights for policy 1, policy_version 16290 (0.0008) -[2023-10-17 00:55:20,372][62373] Updated weights for policy 0, policy_version 16440 (0.0008) -[2023-10-17 00:55:20,456][62408] Updated weights for policy 1, policy_version 16300 (0.0007) -[2023-10-17 00:55:20,821][62408] Updated weights for policy 1, policy_version 16310 (0.0008) -[2023-10-17 00:55:21,190][62408] Updated weights for policy 1, policy_version 16320 (0.0007) -[2023-10-17 00:55:22,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 33554432. Throughput: 0: 1779.2, 1: 1782.2. Samples: 8390526. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) -[2023-10-17 00:55:22,215][61453] Avg episode reward: [(0, '5.500'), (1, '6.110')] -[2023-10-17 00:55:22,217][62252] Saving new best policy, reward=6.110! -[2023-10-17 00:55:24,207][62373] Updated weights for policy 0, policy_version 16450 (0.0007) -[2023-10-17 00:55:24,570][62373] Updated weights for policy 0, policy_version 16460 (0.0007) -[2023-10-17 00:55:24,953][62373] Updated weights for policy 0, policy_version 16470 (0.0008) -[2023-10-17 00:55:25,090][62408] Updated weights for policy 1, policy_version 16330 (0.0008) -[2023-10-17 00:55:25,326][62373] Updated weights for policy 0, policy_version 16480 (0.0007) -[2023-10-17 00:55:25,463][62408] Updated weights for policy 1, policy_version 16340 (0.0007) -[2023-10-17 00:55:25,824][62408] Updated weights for policy 1, policy_version 16350 (0.0008) -[2023-10-17 00:55:27,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 33619968. Throughput: 0: 1758.7, 1: 1759.5. Samples: 8410244. Policy #0 lag: (min: 31.0, avg: 31.0, max: 35.0) -[2023-10-17 00:55:27,215][61453] Avg episode reward: [(0, '5.690'), (1, '5.880')] -[2023-10-17 00:55:29,152][62373] Updated weights for policy 0, policy_version 16490 (0.0008) -[2023-10-17 00:55:29,519][62373] Updated weights for policy 0, policy_version 16500 (0.0007) -[2023-10-17 00:55:29,710][62408] Updated weights for policy 1, policy_version 16360 (0.0008) -[2023-10-17 00:55:29,887][62373] Updated weights for policy 0, policy_version 16510 (0.0009) -[2023-10-17 00:55:30,068][62408] Updated weights for policy 1, policy_version 16370 (0.0007) -[2023-10-17 00:55:30,438][62408] Updated weights for policy 1, policy_version 16380 (0.0008) -[2023-10-17 00:55:32,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 33685504. Throughput: 0: 1755.0, 1: 1760.0. Samples: 8432188. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:55:32,215][61453] Avg episode reward: [(0, '5.570'), (1, '5.590')] -[2023-10-17 00:55:32,227][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000016384_16777216.pth... -[2023-10-17 00:55:32,227][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000016512_16908288.pth... -[2023-10-17 00:55:32,264][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000014752_15106048.pth -[2023-10-17 00:55:32,265][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000014848_15204352.pth -[2023-10-17 00:55:32,268][62252] Saving a milestone ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/milestones/checkpoint_000016384_16777216.pth -[2023-10-17 00:55:32,269][62094] Saving a milestone ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/milestones/checkpoint_000016512_16908288.pth -[2023-10-17 00:55:33,681][62373] Updated weights for policy 0, policy_version 16520 (0.0009) -[2023-10-17 00:55:34,054][62373] Updated weights for policy 0, policy_version 16530 (0.0007) -[2023-10-17 00:55:34,385][62408] Updated weights for policy 1, policy_version 16390 (0.0009) -[2023-10-17 00:55:34,427][62373] Updated weights for policy 0, policy_version 16540 (0.0009) -[2023-10-17 00:55:34,759][62408] Updated weights for policy 1, policy_version 16400 (0.0010) -[2023-10-17 00:55:35,124][62408] Updated weights for policy 1, policy_version 16410 (0.0010) -[2023-10-17 00:55:37,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 33751040. Throughput: 0: 1756.9, 1: 1770.5. Samples: 8442226. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:55:37,214][61453] Avg episode reward: [(0, '5.210'), (1, '5.340')] -[2023-10-17 00:55:38,237][62373] Updated weights for policy 0, policy_version 16550 (0.0009) -[2023-10-17 00:55:38,599][62373] Updated weights for policy 0, policy_version 16560 (0.0007) -[2023-10-17 00:55:38,784][62408] Updated weights for policy 1, policy_version 16420 (0.0008) -[2023-10-17 00:55:38,971][62373] Updated weights for policy 0, policy_version 16570 (0.0008) -[2023-10-17 00:55:39,161][62408] Updated weights for policy 1, policy_version 16430 (0.0007) -[2023-10-17 00:55:39,519][62408] Updated weights for policy 1, policy_version 16440 (0.0011) -[2023-10-17 00:55:42,214][61453] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 33816576. Throughput: 0: 1759.3, 1: 1757.5. Samples: 8463832. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:55:42,215][61453] Avg episode reward: [(0, '5.320'), (1, '5.100')] -[2023-10-17 00:55:42,754][62373] Updated weights for policy 0, policy_version 16580 (0.0008) -[2023-10-17 00:55:43,132][62373] Updated weights for policy 0, policy_version 16590 (0.0009) -[2023-10-17 00:55:43,440][62408] Updated weights for policy 1, policy_version 16450 (0.0010) -[2023-10-17 00:55:43,500][62373] Updated weights for policy 0, policy_version 16600 (0.0008) -[2023-10-17 00:55:43,834][62408] Updated weights for policy 1, policy_version 16460 (0.0007) -[2023-10-17 00:55:44,208][62408] Updated weights for policy 1, policy_version 16470 (0.0009) -[2023-10-17 00:55:44,574][62408] Updated weights for policy 1, policy_version 16480 (0.0010) -[2023-10-17 00:55:47,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 33882112. Throughput: 0: 1788.7, 1: 1767.7. Samples: 8486052. Policy #0 lag: (min: 31.0, avg: 32.5, max: 57.0) -[2023-10-17 00:55:47,215][61453] Avg episode reward: [(0, '5.050'), (1, '4.730')] -[2023-10-17 00:55:47,295][62373] Updated weights for policy 0, policy_version 16610 (0.0009) -[2023-10-17 00:55:47,667][62373] Updated weights for policy 0, policy_version 16620 (0.0009) -[2023-10-17 00:55:48,033][62373] Updated weights for policy 0, policy_version 16630 (0.0009) -[2023-10-17 00:55:48,413][62373] Updated weights for policy 0, policy_version 16640 (0.0009) -[2023-10-17 00:55:48,430][62408] Updated weights for policy 1, policy_version 16490 (0.0009) -[2023-10-17 00:55:48,796][62408] Updated weights for policy 1, policy_version 16500 (0.0009) -[2023-10-17 00:55:49,167][62408] Updated weights for policy 1, policy_version 16510 (0.0009) -[2023-10-17 00:55:52,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 33947648. Throughput: 0: 1760.4, 1: 1758.3. Samples: 8495644. Policy #0 lag: (min: 31.0, avg: 32.5, max: 57.0) -[2023-10-17 00:55:52,215][61453] Avg episode reward: [(0, '5.130'), (1, '5.100')] -[2023-10-17 00:55:52,340][62373] Updated weights for policy 0, policy_version 16650 (0.0009) -[2023-10-17 00:55:52,715][62373] Updated weights for policy 0, policy_version 16660 (0.0011) -[2023-10-17 00:55:52,977][62408] Updated weights for policy 1, policy_version 16520 (0.0008) -[2023-10-17 00:55:53,084][62373] Updated weights for policy 0, policy_version 16670 (0.0007) -[2023-10-17 00:55:53,354][62408] Updated weights for policy 1, policy_version 16530 (0.0008) -[2023-10-17 00:55:53,728][62408] Updated weights for policy 1, policy_version 16540 (0.0009) -[2023-10-17 00:55:56,796][62373] Updated weights for policy 0, policy_version 16680 (0.0008) -[2023-10-17 00:55:57,157][62373] Updated weights for policy 0, policy_version 16690 (0.0007) -[2023-10-17 00:55:57,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 34013184. Throughput: 0: 1783.7, 1: 1761.1. Samples: 8517726. Policy #0 lag: (min: 31.0, avg: 32.5, max: 57.0) -[2023-10-17 00:55:57,215][61453] Avg episode reward: [(0, '5.570'), (1, '5.150')] -[2023-10-17 00:55:57,522][62373] Updated weights for policy 0, policy_version 16700 (0.0007) -[2023-10-17 00:55:57,537][62408] Updated weights for policy 1, policy_version 16550 (0.0007) -[2023-10-17 00:55:57,893][62408] Updated weights for policy 1, policy_version 16560 (0.0009) -[2023-10-17 00:55:58,263][62408] Updated weights for policy 1, policy_version 16570 (0.0007) -[2023-10-17 00:56:01,197][62373] Updated weights for policy 0, policy_version 16710 (0.0008) -[2023-10-17 00:56:01,565][62373] Updated weights for policy 0, policy_version 16720 (0.0011) -[2023-10-17 00:56:01,944][62373] Updated weights for policy 0, policy_version 16730 (0.0010) -[2023-10-17 00:56:02,013][62408] Updated weights for policy 1, policy_version 16580 (0.0007) -[2023-10-17 00:56:02,214][61453] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 34111488. Throughput: 0: 1772.7, 1: 1790.1. Samples: 8539000. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-17 00:56:02,214][61453] Avg episode reward: [(0, '5.570'), (1, '5.390')] -[2023-10-17 00:56:02,390][62408] Updated weights for policy 1, policy_version 16590 (0.0007) -[2023-10-17 00:56:02,757][62408] Updated weights for policy 1, policy_version 16600 (0.0009) -[2023-10-17 00:56:05,728][62373] Updated weights for policy 0, policy_version 16740 (0.0008) -[2023-10-17 00:56:06,115][62373] Updated weights for policy 0, policy_version 16750 (0.0008) -[2023-10-17 00:56:06,491][62373] Updated weights for policy 0, policy_version 16760 (0.0007) -[2023-10-17 00:56:06,641][62408] Updated weights for policy 1, policy_version 16610 (0.0008) -[2023-10-17 00:56:07,006][62408] Updated weights for policy 1, policy_version 16620 (0.0008) -[2023-10-17 00:56:07,214][61453] Fps is (10 sec: 16384.1, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 34177024. Throughput: 0: 1779.4, 1: 1754.9. Samples: 8549572. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-17 00:56:07,214][61453] Avg episode reward: [(0, '5.050'), (1, '5.830')] -[2023-10-17 00:56:07,367][62408] Updated weights for policy 1, policy_version 16630 (0.0007) -[2023-10-17 00:56:07,739][62408] Updated weights for policy 1, policy_version 16640 (0.0008) -[2023-10-17 00:56:10,476][62373] Updated weights for policy 0, policy_version 16770 (0.0008) -[2023-10-17 00:56:10,842][62373] Updated weights for policy 0, policy_version 16780 (0.0008) -[2023-10-17 00:56:11,216][62373] Updated weights for policy 0, policy_version 16790 (0.0008) -[2023-10-17 00:56:11,559][62408] Updated weights for policy 1, policy_version 16650 (0.0008) -[2023-10-17 00:56:11,587][62373] Updated weights for policy 0, policy_version 16800 (0.0008) -[2023-10-17 00:56:11,922][62408] Updated weights for policy 1, policy_version 16660 (0.0007) -[2023-10-17 00:56:12,214][61453] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 34242560. Throughput: 0: 1782.0, 1: 1781.7. Samples: 8570610. Policy #0 lag: (min: 29.0, avg: 35.5, max: 61.0) -[2023-10-17 00:56:12,215][61453] Avg episode reward: [(0, '5.190'), (1, '6.230')] -[2023-10-17 00:56:12,276][62408] Updated weights for policy 1, policy_version 16670 (0.0009) -[2023-10-17 00:56:12,349][62252] Saving new best policy, reward=6.230! -[2023-10-17 00:56:15,328][62373] Updated weights for policy 0, policy_version 16810 (0.0009) -[2023-10-17 00:56:15,701][62373] Updated weights for policy 0, policy_version 16820 (0.0008) -[2023-10-17 00:56:16,066][62373] Updated weights for policy 0, policy_version 16830 (0.0007) -[2023-10-17 00:56:16,171][62408] Updated weights for policy 1, policy_version 16680 (0.0009) -[2023-10-17 00:56:16,532][62408] Updated weights for policy 1, policy_version 16690 (0.0011) -[2023-10-17 00:56:16,896][62408] Updated weights for policy 1, policy_version 16700 (0.0010) -[2023-10-17 00:56:17,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 34340864. Throughput: 0: 1766.6, 1: 1757.4. Samples: 8590768. Policy #0 lag: (min: 29.0, avg: 35.5, max: 61.0) -[2023-10-17 00:56:17,214][61453] Avg episode reward: [(0, '5.290'), (1, '6.100')] -[2023-10-17 00:56:19,751][62373] Updated weights for policy 0, policy_version 16840 (0.0007) -[2023-10-17 00:56:20,126][62373] Updated weights for policy 0, policy_version 16850 (0.0008) -[2023-10-17 00:56:20,495][62373] Updated weights for policy 0, policy_version 16860 (0.0009) -[2023-10-17 00:56:20,767][62408] Updated weights for policy 1, policy_version 16710 (0.0009) -[2023-10-17 00:56:21,137][62408] Updated weights for policy 1, policy_version 16720 (0.0007) -[2023-10-17 00:56:21,494][62408] Updated weights for policy 1, policy_version 16730 (0.0007) -[2023-10-17 00:56:22,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 34406400. Throughput: 0: 1787.2, 1: 1770.0. Samples: 8602302. Policy #0 lag: (min: 29.0, avg: 35.5, max: 61.0) -[2023-10-17 00:56:22,215][61453] Avg episode reward: [(0, '5.070'), (1, '5.670')] -[2023-10-17 00:56:24,176][62373] Updated weights for policy 0, policy_version 16870 (0.0010) -[2023-10-17 00:56:24,542][62373] Updated weights for policy 0, policy_version 16880 (0.0008) -[2023-10-17 00:56:24,911][62373] Updated weights for policy 0, policy_version 16890 (0.0011) -[2023-10-17 00:56:25,373][62408] Updated weights for policy 1, policy_version 16740 (0.0007) -[2023-10-17 00:56:25,742][62408] Updated weights for policy 1, policy_version 16750 (0.0008) -[2023-10-17 00:56:26,106][62408] Updated weights for policy 1, policy_version 16760 (0.0009) -[2023-10-17 00:56:27,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 34471936. Throughput: 0: 1769.1, 1: 1767.2. Samples: 8622970. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:56:27,215][61453] Avg episode reward: [(0, '5.130'), (1, '5.580')] -[2023-10-17 00:56:28,830][62373] Updated weights for policy 0, policy_version 16900 (0.0009) -[2023-10-17 00:56:29,201][62373] Updated weights for policy 0, policy_version 16910 (0.0010) -[2023-10-17 00:56:29,580][62373] Updated weights for policy 0, policy_version 16920 (0.0009) -[2023-10-17 00:56:29,907][62408] Updated weights for policy 1, policy_version 16770 (0.0009) -[2023-10-17 00:56:30,323][62408] Updated weights for policy 1, policy_version 16780 (0.0009) -[2023-10-17 00:56:30,692][62408] Updated weights for policy 1, policy_version 16790 (0.0009) -[2023-10-17 00:56:31,056][62408] Updated weights for policy 1, policy_version 16800 (0.0007) -[2023-10-17 00:56:32,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 34537472. Throughput: 0: 1767.2, 1: 1749.3. Samples: 8644294. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:56:32,214][61453] Avg episode reward: [(0, '5.310'), (1, '5.600')] -[2023-10-17 00:56:33,356][62373] Updated weights for policy 0, policy_version 16930 (0.0009) -[2023-10-17 00:56:33,725][62373] Updated weights for policy 0, policy_version 16940 (0.0007) -[2023-10-17 00:56:34,096][62373] Updated weights for policy 0, policy_version 16950 (0.0008) -[2023-10-17 00:56:34,462][62373] Updated weights for policy 0, policy_version 16960 (0.0011) -[2023-10-17 00:56:34,784][62408] Updated weights for policy 1, policy_version 16810 (0.0008) -[2023-10-17 00:56:35,153][62408] Updated weights for policy 1, policy_version 16820 (0.0007) -[2023-10-17 00:56:35,530][62408] Updated weights for policy 1, policy_version 16830 (0.0008) -[2023-10-17 00:56:37,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 34603008. Throughput: 0: 1766.3, 1: 1764.8. Samples: 8654542. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:56:37,215][61453] Avg episode reward: [(0, '5.920'), (1, '5.610')] -[2023-10-17 00:56:38,254][62373] Updated weights for policy 0, policy_version 16970 (0.0008) -[2023-10-17 00:56:38,628][62373] Updated weights for policy 0, policy_version 16980 (0.0007) -[2023-10-17 00:56:38,998][62373] Updated weights for policy 0, policy_version 16990 (0.0010) -[2023-10-17 00:56:39,450][62408] Updated weights for policy 1, policy_version 16840 (0.0009) -[2023-10-17 00:56:39,826][62408] Updated weights for policy 1, policy_version 16850 (0.0008) -[2023-10-17 00:56:40,197][62408] Updated weights for policy 1, policy_version 16860 (0.0009) -[2023-10-17 00:56:42,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 34668544. Throughput: 0: 1765.6, 1: 1741.6. Samples: 8675546. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:56:42,215][61453] Avg episode reward: [(0, '6.200'), (1, '5.620')] -[2023-10-17 00:56:42,216][62094] Saving new best policy, reward=6.200! -[2023-10-17 00:56:42,768][62373] Updated weights for policy 0, policy_version 17000 (0.0009) -[2023-10-17 00:56:43,137][62373] Updated weights for policy 0, policy_version 17010 (0.0009) -[2023-10-17 00:56:43,511][62373] Updated weights for policy 0, policy_version 17020 (0.0009) -[2023-10-17 00:56:44,023][62408] Updated weights for policy 1, policy_version 16870 (0.0008) -[2023-10-17 00:56:44,397][62408] Updated weights for policy 1, policy_version 16880 (0.0011) -[2023-10-17 00:56:44,775][62408] Updated weights for policy 1, policy_version 16890 (0.0011) -[2023-10-17 00:56:47,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 34734080. Throughput: 0: 1789.4, 1: 1736.5. Samples: 8697666. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:56:47,215][61453] Avg episode reward: [(0, '6.130'), (1, '5.870')] -[2023-10-17 00:56:47,358][62373] Updated weights for policy 0, policy_version 17030 (0.0009) -[2023-10-17 00:56:47,732][62373] Updated weights for policy 0, policy_version 17040 (0.0010) -[2023-10-17 00:56:48,109][62373] Updated weights for policy 0, policy_version 17050 (0.0009) -[2023-10-17 00:56:48,758][62408] Updated weights for policy 1, policy_version 16900 (0.0010) -[2023-10-17 00:56:49,133][62408] Updated weights for policy 1, policy_version 16910 (0.0011) -[2023-10-17 00:56:49,510][62408] Updated weights for policy 1, policy_version 16920 (0.0010) -[2023-10-17 00:56:52,057][62373] Updated weights for policy 0, policy_version 17060 (0.0008) -[2023-10-17 00:56:52,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 34799616. Throughput: 0: 1762.7, 1: 1742.6. Samples: 8707312. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:56:52,215][61453] Avg episode reward: [(0, '6.130'), (1, '5.860')] -[2023-10-17 00:56:52,445][62373] Updated weights for policy 0, policy_version 17070 (0.0008) -[2023-10-17 00:56:52,815][62373] Updated weights for policy 0, policy_version 17080 (0.0010) -[2023-10-17 00:56:53,267][62408] Updated weights for policy 1, policy_version 16930 (0.0008) -[2023-10-17 00:56:53,633][62408] Updated weights for policy 1, policy_version 16940 (0.0008) -[2023-10-17 00:56:53,997][62408] Updated weights for policy 1, policy_version 16950 (0.0009) -[2023-10-17 00:56:54,366][62408] Updated weights for policy 1, policy_version 16960 (0.0010) -[2023-10-17 00:56:56,478][62373] Updated weights for policy 0, policy_version 17090 (0.0010) -[2023-10-17 00:56:56,848][62373] Updated weights for policy 0, policy_version 17100 (0.0009) -[2023-10-17 00:56:57,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 34865152. Throughput: 0: 1782.3, 1: 1745.7. Samples: 8729370. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:56:57,214][61453] Avg episode reward: [(0, '5.910'), (1, '5.860')] -[2023-10-17 00:56:57,226][62373] Updated weights for policy 0, policy_version 17110 (0.0008) -[2023-10-17 00:56:57,589][62373] Updated weights for policy 0, policy_version 17120 (0.0008) -[2023-10-17 00:56:58,151][62408] Updated weights for policy 1, policy_version 16970 (0.0008) -[2023-10-17 00:56:58,528][62408] Updated weights for policy 1, policy_version 16980 (0.0007) -[2023-10-17 00:56:58,885][62408] Updated weights for policy 1, policy_version 16990 (0.0007) -[2023-10-17 00:57:01,387][62373] Updated weights for policy 0, policy_version 17130 (0.0010) -[2023-10-17 00:57:01,758][62373] Updated weights for policy 0, policy_version 17140 (0.0010) -[2023-10-17 00:57:02,123][62373] Updated weights for policy 0, policy_version 17150 (0.0009) -[2023-10-17 00:57:02,214][61453] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 34963456. Throughput: 0: 1776.4, 1: 1772.6. Samples: 8750474. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:57:02,214][61453] Avg episode reward: [(0, '5.720'), (1, '6.170')] -[2023-10-17 00:57:02,834][62408] Updated weights for policy 1, policy_version 17000 (0.0008) -[2023-10-17 00:57:03,203][62408] Updated weights for policy 1, policy_version 17010 (0.0007) -[2023-10-17 00:57:03,569][62408] Updated weights for policy 1, policy_version 17020 (0.0009) -[2023-10-17 00:57:05,889][62373] Updated weights for policy 0, policy_version 17160 (0.0010) -[2023-10-17 00:57:06,257][62373] Updated weights for policy 0, policy_version 17170 (0.0011) -[2023-10-17 00:57:06,638][62373] Updated weights for policy 0, policy_version 17180 (0.0010) -[2023-10-17 00:57:07,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 35028992. Throughput: 0: 1782.8, 1: 1750.4. Samples: 8761294. Policy #0 lag: (min: 3.0, avg: 4.1, max: 26.0) -[2023-10-17 00:57:07,214][61453] Avg episode reward: [(0, '5.680'), (1, '6.260')] -[2023-10-17 00:57:07,215][62252] Saving new best policy, reward=6.260! -[2023-10-17 00:57:07,633][62408] Updated weights for policy 1, policy_version 17030 (0.0008) -[2023-10-17 00:57:07,994][62408] Updated weights for policy 1, policy_version 17040 (0.0008) -[2023-10-17 00:57:08,365][62408] Updated weights for policy 1, policy_version 17050 (0.0009) -[2023-10-17 00:57:10,367][62373] Updated weights for policy 0, policy_version 17190 (0.0008) -[2023-10-17 00:57:10,745][62373] Updated weights for policy 0, policy_version 17200 (0.0008) -[2023-10-17 00:57:11,117][62373] Updated weights for policy 0, policy_version 17210 (0.0007) -[2023-10-17 00:57:12,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 35094528. Throughput: 0: 1783.2, 1: 1755.5. Samples: 8782212. Policy #0 lag: (min: 3.0, avg: 4.1, max: 26.0) -[2023-10-17 00:57:12,215][61453] Avg episode reward: [(0, '5.950'), (1, '6.060')] -[2023-10-17 00:57:12,224][62408] Updated weights for policy 1, policy_version 17060 (0.0009) -[2023-10-17 00:57:12,599][62408] Updated weights for policy 1, policy_version 17070 (0.0008) -[2023-10-17 00:57:12,969][62408] Updated weights for policy 1, policy_version 17080 (0.0008) -[2023-10-17 00:57:15,004][62373] Updated weights for policy 0, policy_version 17220 (0.0010) -[2023-10-17 00:57:15,375][62373] Updated weights for policy 0, policy_version 17230 (0.0011) -[2023-10-17 00:57:15,749][62373] Updated weights for policy 0, policy_version 17240 (0.0010) -[2023-10-17 00:57:16,838][62408] Updated weights for policy 1, policy_version 17090 (0.0009) -[2023-10-17 00:57:17,214][61453] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 35160064. Throughput: 0: 1770.9, 1: 1771.2. Samples: 8803686. Policy #0 lag: (min: 3.0, avg: 4.1, max: 26.0) -[2023-10-17 00:57:17,215][61453] Avg episode reward: [(0, '5.570'), (1, '5.960')] -[2023-10-17 00:57:17,237][62408] Updated weights for policy 1, policy_version 17100 (0.0009) -[2023-10-17 00:57:17,607][62408] Updated weights for policy 1, policy_version 17110 (0.0011) -[2023-10-17 00:57:17,975][62408] Updated weights for policy 1, policy_version 17120 (0.0009) -[2023-10-17 00:57:19,445][62373] Updated weights for policy 0, policy_version 17250 (0.0009) -[2023-10-17 00:57:19,815][62373] Updated weights for policy 0, policy_version 17260 (0.0009) -[2023-10-17 00:57:20,189][62373] Updated weights for policy 0, policy_version 17270 (0.0007) -[2023-10-17 00:57:20,558][62373] Updated weights for policy 0, policy_version 17280 (0.0008) -[2023-10-17 00:57:21,648][62408] Updated weights for policy 1, policy_version 17130 (0.0007) -[2023-10-17 00:57:22,025][62408] Updated weights for policy 1, policy_version 17140 (0.0007) -[2023-10-17 00:57:22,214][61453] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 35225600. Throughput: 0: 1790.6, 1: 1758.6. Samples: 8814254. Policy #0 lag: (min: 31.0, avg: 33.3, max: 63.0) -[2023-10-17 00:57:22,215][61453] Avg episode reward: [(0, '5.640'), (1, '6.000')] -[2023-10-17 00:57:22,403][62408] Updated weights for policy 1, policy_version 17150 (0.0007) -[2023-10-17 00:57:24,351][62373] Updated weights for policy 0, policy_version 17290 (0.0007) -[2023-10-17 00:57:24,715][62373] Updated weights for policy 0, policy_version 17300 (0.0007) -[2023-10-17 00:57:25,089][62373] Updated weights for policy 0, policy_version 17310 (0.0007) -[2023-10-17 00:57:26,082][62408] Updated weights for policy 1, policy_version 17160 (0.0011) -[2023-10-17 00:57:26,450][62408] Updated weights for policy 1, policy_version 17170 (0.0009) -[2023-10-17 00:57:26,819][62408] Updated weights for policy 1, policy_version 17180 (0.0008) -[2023-10-17 00:57:27,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 35323904. Throughput: 0: 1774.2, 1: 1784.3. Samples: 8835678. Policy #0 lag: (min: 31.0, avg: 33.3, max: 63.0) -[2023-10-17 00:57:27,215][61453] Avg episode reward: [(0, '6.110'), (1, '5.690')] -[2023-10-17 00:57:28,835][62373] Updated weights for policy 0, policy_version 17320 (0.0007) -[2023-10-17 00:57:29,201][62373] Updated weights for policy 0, policy_version 17330 (0.0010) -[2023-10-17 00:57:29,573][62373] Updated weights for policy 0, policy_version 17340 (0.0008) -[2023-10-17 00:57:30,615][62408] Updated weights for policy 1, policy_version 17190 (0.0009) -[2023-10-17 00:57:30,987][62408] Updated weights for policy 1, policy_version 17200 (0.0010) -[2023-10-17 00:57:31,351][62408] Updated weights for policy 1, policy_version 17210 (0.0008) -[2023-10-17 00:57:32,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 35389440. Throughput: 0: 1778.0, 1: 1760.4. Samples: 8856894. Policy #0 lag: (min: 31.0, avg: 33.3, max: 63.0) -[2023-10-17 00:57:32,215][61453] Avg episode reward: [(0, '5.540'), (1, '5.490')] -[2023-10-17 00:57:32,223][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000017216_17629184.pth... -[2023-10-17 00:57:32,223][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000017344_17760256.pth... -[2023-10-17 00:57:32,259][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000015680_16056320.pth -[2023-10-17 00:57:32,264][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000015552_15925248.pth -[2023-10-17 00:57:33,280][62373] Updated weights for policy 0, policy_version 17350 (0.0009) -[2023-10-17 00:57:33,661][62373] Updated weights for policy 0, policy_version 17360 (0.0007) -[2023-10-17 00:57:34,037][62373] Updated weights for policy 0, policy_version 17370 (0.0009) -[2023-10-17 00:57:35,169][62408] Updated weights for policy 1, policy_version 17220 (0.0011) -[2023-10-17 00:57:35,538][62408] Updated weights for policy 1, policy_version 17230 (0.0011) -[2023-10-17 00:57:35,906][62408] Updated weights for policy 1, policy_version 17240 (0.0007) -[2023-10-17 00:57:37,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 35454976. Throughput: 0: 1779.4, 1: 1793.0. Samples: 8868070. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:57:37,215][61453] Avg episode reward: [(0, '5.340'), (1, '5.600')] -[2023-10-17 00:57:37,789][62373] Updated weights for policy 0, policy_version 17380 (0.0009) -[2023-10-17 00:57:38,163][62373] Updated weights for policy 0, policy_version 17390 (0.0009) -[2023-10-17 00:57:38,522][62373] Updated weights for policy 0, policy_version 17400 (0.0008) -[2023-10-17 00:57:39,762][62408] Updated weights for policy 1, policy_version 17250 (0.0009) -[2023-10-17 00:57:40,145][62408] Updated weights for policy 1, policy_version 17260 (0.0009) -[2023-10-17 00:57:40,510][62408] Updated weights for policy 1, policy_version 17270 (0.0008) -[2023-10-17 00:57:40,870][62408] Updated weights for policy 1, policy_version 17280 (0.0007) -[2023-10-17 00:57:42,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 35520512. Throughput: 0: 1779.6, 1: 1763.1. Samples: 8888792. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:57:42,214][61453] Avg episode reward: [(0, '5.850'), (1, '5.370')] -[2023-10-17 00:57:42,389][62373] Updated weights for policy 0, policy_version 17410 (0.0007) -[2023-10-17 00:57:42,787][62373] Updated weights for policy 0, policy_version 17420 (0.0009) -[2023-10-17 00:57:43,157][62373] Updated weights for policy 0, policy_version 17430 (0.0007) -[2023-10-17 00:57:43,533][62373] Updated weights for policy 0, policy_version 17440 (0.0011) -[2023-10-17 00:57:44,649][62408] Updated weights for policy 1, policy_version 17290 (0.0008) -[2023-10-17 00:57:45,006][62408] Updated weights for policy 1, policy_version 17300 (0.0008) -[2023-10-17 00:57:45,366][62408] Updated weights for policy 1, policy_version 17310 (0.0007) -[2023-10-17 00:57:47,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 35586048. Throughput: 0: 1798.3, 1: 1760.8. Samples: 8910636. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:57:47,215][61453] Avg episode reward: [(0, '5.760'), (1, '5.680')] -[2023-10-17 00:57:47,227][62373] Updated weights for policy 0, policy_version 17450 (0.0009) -[2023-10-17 00:57:47,596][62373] Updated weights for policy 0, policy_version 17460 (0.0009) -[2023-10-17 00:57:47,966][62373] Updated weights for policy 0, policy_version 17470 (0.0009) -[2023-10-17 00:57:49,176][62408] Updated weights for policy 1, policy_version 17320 (0.0008) -[2023-10-17 00:57:49,538][62408] Updated weights for policy 1, policy_version 17330 (0.0009) -[2023-10-17 00:57:49,916][62408] Updated weights for policy 1, policy_version 17340 (0.0009) -[2023-10-17 00:57:51,837][62373] Updated weights for policy 0, policy_version 17480 (0.0007) -[2023-10-17 00:57:52,201][62373] Updated weights for policy 0, policy_version 17490 (0.0010) -[2023-10-17 00:57:52,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 35651584. Throughput: 0: 1772.7, 1: 1767.7. Samples: 8920616. Policy #0 lag: (min: 3.0, avg: 3.0, max: 4.0) -[2023-10-17 00:57:52,215][61453] Avg episode reward: [(0, '5.260'), (1, '5.560')] -[2023-10-17 00:57:52,568][62373] Updated weights for policy 0, policy_version 17500 (0.0011) -[2023-10-17 00:57:53,582][62408] Updated weights for policy 1, policy_version 17350 (0.0010) -[2023-10-17 00:57:53,955][62408] Updated weights for policy 1, policy_version 17360 (0.0009) -[2023-10-17 00:57:54,330][62408] Updated weights for policy 1, policy_version 17370 (0.0008) -[2023-10-17 00:57:56,376][62373] Updated weights for policy 0, policy_version 17510 (0.0008) -[2023-10-17 00:57:56,757][62373] Updated weights for policy 0, policy_version 17520 (0.0007) -[2023-10-17 00:57:57,130][62373] Updated weights for policy 0, policy_version 17530 (0.0008) -[2023-10-17 00:57:57,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 35717120. Throughput: 0: 1791.6, 1: 1769.2. Samples: 8942448. Policy #0 lag: (min: 3.0, avg: 3.0, max: 4.0) -[2023-10-17 00:57:57,215][61453] Avg episode reward: [(0, '5.530'), (1, '5.840')] -[2023-10-17 00:57:58,149][62408] Updated weights for policy 1, policy_version 17380 (0.0010) -[2023-10-17 00:57:58,521][62408] Updated weights for policy 1, policy_version 17390 (0.0008) -[2023-10-17 00:57:58,893][62408] Updated weights for policy 1, policy_version 17400 (0.0010) -[2023-10-17 00:58:00,893][62373] Updated weights for policy 0, policy_version 17540 (0.0007) -[2023-10-17 00:58:01,263][62373] Updated weights for policy 0, policy_version 17550 (0.0009) -[2023-10-17 00:58:01,637][62373] Updated weights for policy 0, policy_version 17560 (0.0010) -[2023-10-17 00:58:02,214][61453] Fps is (10 sec: 16383.5, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 35815424. Throughput: 0: 1776.4, 1: 1777.6. Samples: 8963618. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:58:02,215][61453] Avg episode reward: [(0, '5.710'), (1, '6.020')] -[2023-10-17 00:58:02,674][62408] Updated weights for policy 1, policy_version 17410 (0.0009) -[2023-10-17 00:58:03,085][62408] Updated weights for policy 1, policy_version 17420 (0.0008) -[2023-10-17 00:58:03,452][62408] Updated weights for policy 1, policy_version 17430 (0.0010) -[2023-10-17 00:58:03,821][62408] Updated weights for policy 1, policy_version 17440 (0.0007) -[2023-10-17 00:58:05,409][62373] Updated weights for policy 0, policy_version 17570 (0.0009) -[2023-10-17 00:58:05,776][62373] Updated weights for policy 0, policy_version 17580 (0.0007) -[2023-10-17 00:58:06,141][62373] Updated weights for policy 0, policy_version 17590 (0.0009) -[2023-10-17 00:58:06,517][62373] Updated weights for policy 0, policy_version 17600 (0.0009) -[2023-10-17 00:58:07,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 35880960. Throughput: 0: 1793.0, 1: 1768.2. Samples: 8974508. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:58:07,215][61453] Avg episode reward: [(0, '5.930'), (1, '5.670')] -[2023-10-17 00:58:07,790][62408] Updated weights for policy 1, policy_version 17450 (0.0009) -[2023-10-17 00:58:08,160][62408] Updated weights for policy 1, policy_version 17460 (0.0008) -[2023-10-17 00:58:08,534][62408] Updated weights for policy 1, policy_version 17470 (0.0010) -[2023-10-17 00:58:10,307][62373] Updated weights for policy 0, policy_version 17610 (0.0009) -[2023-10-17 00:58:10,675][62373] Updated weights for policy 0, policy_version 17620 (0.0010) -[2023-10-17 00:58:11,051][62373] Updated weights for policy 0, policy_version 17630 (0.0010) -[2023-10-17 00:58:12,209][62408] Updated weights for policy 1, policy_version 17480 (0.0010) -[2023-10-17 00:58:12,214][61453] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 35946496. Throughput: 0: 1781.2, 1: 1763.9. Samples: 8995204. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:58:12,215][61453] Avg episode reward: [(0, '5.520'), (1, '5.590')] -[2023-10-17 00:58:12,578][62408] Updated weights for policy 1, policy_version 17490 (0.0009) -[2023-10-17 00:58:12,944][62408] Updated weights for policy 1, policy_version 17500 (0.0009) -[2023-10-17 00:58:14,892][62373] Updated weights for policy 0, policy_version 17640 (0.0008) -[2023-10-17 00:58:15,258][62373] Updated weights for policy 0, policy_version 17650 (0.0008) -[2023-10-17 00:58:15,630][62373] Updated weights for policy 0, policy_version 17660 (0.0009) -[2023-10-17 00:58:16,641][62408] Updated weights for policy 1, policy_version 17510 (0.0010) -[2023-10-17 00:58:17,015][62408] Updated weights for policy 1, policy_version 17520 (0.0010) -[2023-10-17 00:58:17,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 36012032. Throughput: 0: 1767.5, 1: 1788.2. Samples: 9016900. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:58:17,215][61453] Avg episode reward: [(0, '6.020'), (1, '5.820')] -[2023-10-17 00:58:17,392][62408] Updated weights for policy 1, policy_version 17530 (0.0008) -[2023-10-17 00:58:19,349][62373] Updated weights for policy 0, policy_version 17670 (0.0009) -[2023-10-17 00:58:19,720][62373] Updated weights for policy 0, policy_version 17680 (0.0008) -[2023-10-17 00:58:20,092][62373] Updated weights for policy 0, policy_version 17690 (0.0010) -[2023-10-17 00:58:21,228][62408] Updated weights for policy 1, policy_version 17540 (0.0009) -[2023-10-17 00:58:21,600][62408] Updated weights for policy 1, policy_version 17550 (0.0009) -[2023-10-17 00:58:21,970][62408] Updated weights for policy 1, policy_version 17560 (0.0011) -[2023-10-17 00:58:22,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 36077568. Throughput: 0: 1778.6, 1: 1761.2. Samples: 9027360. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:58:22,214][61453] Avg episode reward: [(0, '6.080'), (1, '6.030')] -[2023-10-17 00:58:23,970][62373] Updated weights for policy 0, policy_version 17700 (0.0010) -[2023-10-17 00:58:24,341][62373] Updated weights for policy 0, policy_version 17710 (0.0010) -[2023-10-17 00:58:24,708][62373] Updated weights for policy 0, policy_version 17720 (0.0011) -[2023-10-17 00:58:25,963][62408] Updated weights for policy 1, policy_version 17570 (0.0008) -[2023-10-17 00:58:26,340][62408] Updated weights for policy 1, policy_version 17580 (0.0011) -[2023-10-17 00:58:26,699][62408] Updated weights for policy 1, policy_version 17590 (0.0008) -[2023-10-17 00:58:27,065][62408] Updated weights for policy 1, policy_version 17600 (0.0008) -[2023-10-17 00:58:27,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 36175872. Throughput: 0: 1765.3, 1: 1783.3. Samples: 9048480. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:58:27,214][61453] Avg episode reward: [(0, '5.940'), (1, '5.770')] -[2023-10-17 00:58:28,610][62373] Updated weights for policy 0, policy_version 17730 (0.0009) -[2023-10-17 00:58:28,978][62373] Updated weights for policy 0, policy_version 17740 (0.0009) -[2023-10-17 00:58:29,352][62373] Updated weights for policy 0, policy_version 17750 (0.0011) -[2023-10-17 00:58:29,728][62373] Updated weights for policy 0, policy_version 17760 (0.0009) -[2023-10-17 00:58:30,833][62408] Updated weights for policy 1, policy_version 17610 (0.0010) -[2023-10-17 00:58:31,188][62408] Updated weights for policy 1, policy_version 17620 (0.0011) -[2023-10-17 00:58:31,555][62408] Updated weights for policy 1, policy_version 17630 (0.0009) -[2023-10-17 00:58:32,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 36241408. Throughput: 0: 1765.2, 1: 1755.6. Samples: 9069072. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:58:32,214][61453] Avg episode reward: [(0, '5.980'), (1, '5.560')] -[2023-10-17 00:58:33,723][62373] Updated weights for policy 0, policy_version 17770 (0.0008) -[2023-10-17 00:58:34,095][62373] Updated weights for policy 0, policy_version 17780 (0.0009) -[2023-10-17 00:58:34,461][62373] Updated weights for policy 0, policy_version 17790 (0.0008) -[2023-10-17 00:58:35,379][62408] Updated weights for policy 1, policy_version 17640 (0.0009) -[2023-10-17 00:58:35,741][62408] Updated weights for policy 1, policy_version 17650 (0.0010) -[2023-10-17 00:58:36,104][62408] Updated weights for policy 1, policy_version 17660 (0.0008) -[2023-10-17 00:58:37,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 36306944. Throughput: 0: 1759.2, 1: 1783.0. Samples: 9080016. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:58:37,214][61453] Avg episode reward: [(0, '5.740'), (1, '5.800')] -[2023-10-17 00:58:38,308][62373] Updated weights for policy 0, policy_version 17800 (0.0011) -[2023-10-17 00:58:38,676][62373] Updated weights for policy 0, policy_version 17810 (0.0008) -[2023-10-17 00:58:39,043][62373] Updated weights for policy 0, policy_version 17820 (0.0008) -[2023-10-17 00:58:40,120][62408] Updated weights for policy 1, policy_version 17670 (0.0010) -[2023-10-17 00:58:40,489][62408] Updated weights for policy 1, policy_version 17680 (0.0009) -[2023-10-17 00:58:40,863][62408] Updated weights for policy 1, policy_version 17690 (0.0008) -[2023-10-17 00:58:42,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 36372480. Throughput: 0: 1755.0, 1: 1762.1. Samples: 9100718. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:58:42,214][61453] Avg episode reward: [(0, '6.000'), (1, '5.460')] -[2023-10-17 00:58:42,866][62373] Updated weights for policy 0, policy_version 17830 (0.0010) -[2023-10-17 00:58:43,237][62373] Updated weights for policy 0, policy_version 17840 (0.0010) -[2023-10-17 00:58:43,606][62373] Updated weights for policy 0, policy_version 17850 (0.0009) -[2023-10-17 00:58:44,771][62408] Updated weights for policy 1, policy_version 17700 (0.0008) -[2023-10-17 00:58:45,143][62408] Updated weights for policy 1, policy_version 17710 (0.0007) -[2023-10-17 00:58:45,502][62408] Updated weights for policy 1, policy_version 17720 (0.0008) -[2023-10-17 00:58:47,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 36438016. Throughput: 0: 1785.3, 1: 1744.3. Samples: 9122448. Policy #0 lag: (min: 1.0, avg: 15.0, max: 33.0) -[2023-10-17 00:58:47,214][61453] Avg episode reward: [(0, '5.620'), (1, '4.910')] -[2023-10-17 00:58:47,291][62373] Updated weights for policy 0, policy_version 17860 (0.0010) -[2023-10-17 00:58:47,665][62373] Updated weights for policy 0, policy_version 17870 (0.0008) -[2023-10-17 00:58:48,036][62373] Updated weights for policy 0, policy_version 17880 (0.0007) -[2023-10-17 00:58:49,364][62408] Updated weights for policy 1, policy_version 17730 (0.0009) -[2023-10-17 00:58:49,780][62408] Updated weights for policy 1, policy_version 17740 (0.0007) -[2023-10-17 00:58:50,145][62408] Updated weights for policy 1, policy_version 17750 (0.0007) -[2023-10-17 00:58:50,512][62408] Updated weights for policy 1, policy_version 17760 (0.0009) -[2023-10-17 00:58:51,800][62373] Updated weights for policy 0, policy_version 17890 (0.0008) -[2023-10-17 00:58:52,169][62373] Updated weights for policy 0, policy_version 17900 (0.0007) -[2023-10-17 00:58:52,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 36503552. Throughput: 0: 1749.5, 1: 1766.3. Samples: 9132718. Policy #0 lag: (min: 1.0, avg: 15.0, max: 33.0) -[2023-10-17 00:58:52,214][61453] Avg episode reward: [(0, '5.920'), (1, '5.300')] -[2023-10-17 00:58:52,545][62373] Updated weights for policy 0, policy_version 17910 (0.0007) -[2023-10-17 00:58:52,919][62373] Updated weights for policy 0, policy_version 17920 (0.0008) -[2023-10-17 00:58:54,402][62408] Updated weights for policy 1, policy_version 17770 (0.0009) -[2023-10-17 00:58:54,764][62408] Updated weights for policy 1, policy_version 17780 (0.0007) -[2023-10-17 00:58:55,133][62408] Updated weights for policy 1, policy_version 17790 (0.0008) -[2023-10-17 00:58:56,832][62373] Updated weights for policy 0, policy_version 17930 (0.0009) -[2023-10-17 00:58:57,203][62373] Updated weights for policy 0, policy_version 17940 (0.0008) -[2023-10-17 00:58:57,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 36569088. Throughput: 0: 1783.2, 1: 1745.8. Samples: 9154010. Policy #0 lag: (min: 1.0, avg: 15.0, max: 33.0) -[2023-10-17 00:58:57,214][61453] Avg episode reward: [(0, '5.580'), (1, '5.750')] -[2023-10-17 00:58:57,580][62373] Updated weights for policy 0, policy_version 17950 (0.0010) -[2023-10-17 00:58:59,019][62408] Updated weights for policy 1, policy_version 17800 (0.0008) -[2023-10-17 00:58:59,400][62408] Updated weights for policy 1, policy_version 17810 (0.0009) -[2023-10-17 00:58:59,764][62408] Updated weights for policy 1, policy_version 17820 (0.0007) -[2023-10-17 00:59:01,360][62373] Updated weights for policy 0, policy_version 17960 (0.0010) -[2023-10-17 00:59:01,730][62373] Updated weights for policy 0, policy_version 17970 (0.0007) -[2023-10-17 00:59:02,107][62373] Updated weights for policy 0, policy_version 17980 (0.0010) -[2023-10-17 00:59:02,214][61453] Fps is (10 sec: 13106.8, 60 sec: 13653.4, 300 sec: 13995.8). Total num frames: 36634624. Throughput: 0: 1765.1, 1: 1751.6. Samples: 9175150. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-17 00:59:02,215][61453] Avg episode reward: [(0, '5.610'), (1, '5.600')] -[2023-10-17 00:59:03,401][62408] Updated weights for policy 1, policy_version 17830 (0.0009) -[2023-10-17 00:59:03,761][62408] Updated weights for policy 1, policy_version 17840 (0.0009) -[2023-10-17 00:59:04,127][62408] Updated weights for policy 1, policy_version 17850 (0.0007) -[2023-10-17 00:59:05,960][62373] Updated weights for policy 0, policy_version 17990 (0.0008) -[2023-10-17 00:59:06,339][62373] Updated weights for policy 0, policy_version 18000 (0.0009) -[2023-10-17 00:59:06,698][62373] Updated weights for policy 0, policy_version 18010 (0.0010) -[2023-10-17 00:59:07,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 36732928. Throughput: 0: 1775.6, 1: 1745.4. Samples: 9185804. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-17 00:59:07,214][61453] Avg episode reward: [(0, '5.560'), (1, '5.800')] -[2023-10-17 00:59:07,933][62408] Updated weights for policy 1, policy_version 17860 (0.0008) -[2023-10-17 00:59:08,306][62408] Updated weights for policy 1, policy_version 17870 (0.0008) -[2023-10-17 00:59:08,670][62408] Updated weights for policy 1, policy_version 17880 (0.0007) -[2023-10-17 00:59:10,531][62373] Updated weights for policy 0, policy_version 18020 (0.0009) -[2023-10-17 00:59:10,914][62373] Updated weights for policy 0, policy_version 18030 (0.0008) -[2023-10-17 00:59:11,287][62373] Updated weights for policy 0, policy_version 18040 (0.0007) -[2023-10-17 00:59:12,214][61453] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 36798464. Throughput: 0: 1771.5, 1: 1754.6. Samples: 9207154. Policy #0 lag: (min: 9.0, avg: 18.8, max: 41.0) -[2023-10-17 00:59:12,214][61453] Avg episode reward: [(0, '5.810'), (1, '5.910')] -[2023-10-17 00:59:12,529][62408] Updated weights for policy 1, policy_version 17890 (0.0008) -[2023-10-17 00:59:12,902][62408] Updated weights for policy 1, policy_version 17900 (0.0009) -[2023-10-17 00:59:13,286][62408] Updated weights for policy 1, policy_version 17910 (0.0008) -[2023-10-17 00:59:13,653][62408] Updated weights for policy 1, policy_version 17920 (0.0008) -[2023-10-17 00:59:15,181][62373] Updated weights for policy 0, policy_version 18050 (0.0008) -[2023-10-17 00:59:15,556][62373] Updated weights for policy 0, policy_version 18060 (0.0009) -[2023-10-17 00:59:15,930][62373] Updated weights for policy 0, policy_version 18070 (0.0007) -[2023-10-17 00:59:16,301][62373] Updated weights for policy 0, policy_version 18080 (0.0008) -[2023-10-17 00:59:17,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 36864000. Throughput: 0: 1754.4, 1: 1785.6. Samples: 9228374. Policy #0 lag: (min: 9.0, avg: 18.8, max: 41.0) -[2023-10-17 00:59:17,215][61453] Avg episode reward: [(0, '5.800'), (1, '5.960')] -[2023-10-17 00:59:17,436][62408] Updated weights for policy 1, policy_version 17930 (0.0007) -[2023-10-17 00:59:17,813][62408] Updated weights for policy 1, policy_version 17940 (0.0009) -[2023-10-17 00:59:18,183][62408] Updated weights for policy 1, policy_version 17950 (0.0007) -[2023-10-17 00:59:20,031][62373] Updated weights for policy 0, policy_version 18090 (0.0008) -[2023-10-17 00:59:20,392][62373] Updated weights for policy 0, policy_version 18100 (0.0010) -[2023-10-17 00:59:20,748][62373] Updated weights for policy 0, policy_version 18110 (0.0010) -[2023-10-17 00:59:21,871][62408] Updated weights for policy 1, policy_version 17960 (0.0008) -[2023-10-17 00:59:22,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 36929536. Throughput: 0: 1784.0, 1: 1751.8. Samples: 9239126. Policy #0 lag: (min: 9.0, avg: 18.8, max: 41.0) -[2023-10-17 00:59:22,214][61453] Avg episode reward: [(0, '5.790'), (1, '6.310')] -[2023-10-17 00:59:22,229][62408] Updated weights for policy 1, policy_version 17970 (0.0007) -[2023-10-17 00:59:22,587][62408] Updated weights for policy 1, policy_version 17980 (0.0007) -[2023-10-17 00:59:22,716][62252] Saving new best policy, reward=6.310! -[2023-10-17 00:59:24,409][62373] Updated weights for policy 0, policy_version 18120 (0.0008) -[2023-10-17 00:59:24,765][62373] Updated weights for policy 0, policy_version 18130 (0.0009) -[2023-10-17 00:59:25,122][62373] Updated weights for policy 0, policy_version 18140 (0.0009) -[2023-10-17 00:59:26,201][62408] Updated weights for policy 1, policy_version 17990 (0.0008) -[2023-10-17 00:59:26,568][62408] Updated weights for policy 1, policy_version 18000 (0.0008) -[2023-10-17 00:59:26,920][62408] Updated weights for policy 1, policy_version 18010 (0.0009) -[2023-10-17 00:59:27,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 37027840. Throughput: 0: 1766.3, 1: 1792.3. Samples: 9260860. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:59:27,215][61453] Avg episode reward: [(0, '5.790'), (1, '6.050')] -[2023-10-17 00:59:28,815][62373] Updated weights for policy 0, policy_version 18150 (0.0010) -[2023-10-17 00:59:29,186][62373] Updated weights for policy 0, policy_version 18160 (0.0008) -[2023-10-17 00:59:29,558][62373] Updated weights for policy 0, policy_version 18170 (0.0009) -[2023-10-17 00:59:30,705][62408] Updated weights for policy 1, policy_version 18020 (0.0008) -[2023-10-17 00:59:31,071][62408] Updated weights for policy 1, policy_version 18030 (0.0009) -[2023-10-17 00:59:31,438][62408] Updated weights for policy 1, policy_version 18040 (0.0009) -[2023-10-17 00:59:32,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 37093376. Throughput: 0: 1776.3, 1: 1775.9. Samples: 9282298. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:59:32,214][61453] Avg episode reward: [(0, '6.270'), (1, '6.050')] -[2023-10-17 00:59:32,223][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000018176_18612224.pth... -[2023-10-17 00:59:32,223][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000018048_18481152.pth... -[2023-10-17 00:59:32,253][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000016512_16908288.pth -[2023-10-17 00:59:32,254][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000016384_16777216.pth -[2023-10-17 00:59:32,257][62094] Saving new best policy, reward=6.270! -[2023-10-17 00:59:33,305][62373] Updated weights for policy 0, policy_version 18180 (0.0007) -[2023-10-17 00:59:33,679][62373] Updated weights for policy 0, policy_version 18190 (0.0007) -[2023-10-17 00:59:34,044][62373] Updated weights for policy 0, policy_version 18200 (0.0007) -[2023-10-17 00:59:35,324][62408] Updated weights for policy 1, policy_version 18050 (0.0007) -[2023-10-17 00:59:35,720][62408] Updated weights for policy 1, policy_version 18060 (0.0007) -[2023-10-17 00:59:36,093][62408] Updated weights for policy 1, policy_version 18070 (0.0009) -[2023-10-17 00:59:36,459][62408] Updated weights for policy 1, policy_version 18080 (0.0008) -[2023-10-17 00:59:37,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 37158912. Throughput: 0: 1779.3, 1: 1795.7. Samples: 9293596. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:59:37,215][61453] Avg episode reward: [(0, '6.060'), (1, '6.320')] -[2023-10-17 00:59:37,216][62252] Saving new best policy, reward=6.320! -[2023-10-17 00:59:37,883][62373] Updated weights for policy 0, policy_version 18210 (0.0007) -[2023-10-17 00:59:38,261][62373] Updated weights for policy 0, policy_version 18220 (0.0007) -[2023-10-17 00:59:38,624][62373] Updated weights for policy 0, policy_version 18230 (0.0007) -[2023-10-17 00:59:38,993][62373] Updated weights for policy 0, policy_version 18240 (0.0007) -[2023-10-17 00:59:40,232][62408] Updated weights for policy 1, policy_version 18090 (0.0008) -[2023-10-17 00:59:40,601][62408] Updated weights for policy 1, policy_version 18100 (0.0009) -[2023-10-17 00:59:40,971][62408] Updated weights for policy 1, policy_version 18110 (0.0009) -[2023-10-17 00:59:42,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 37224448. Throughput: 0: 1781.7, 1: 1788.2. Samples: 9314654. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:59:42,215][61453] Avg episode reward: [(0, '5.960'), (1, '6.400')] -[2023-10-17 00:59:42,216][62252] Saving new best policy, reward=6.400! -[2023-10-17 00:59:42,745][62373] Updated weights for policy 0, policy_version 18250 (0.0007) -[2023-10-17 00:59:43,120][62373] Updated weights for policy 0, policy_version 18260 (0.0009) -[2023-10-17 00:59:43,492][62373] Updated weights for policy 0, policy_version 18270 (0.0011) -[2023-10-17 00:59:44,648][62408] Updated weights for policy 1, policy_version 18120 (0.0008) -[2023-10-17 00:59:45,013][62408] Updated weights for policy 1, policy_version 18130 (0.0007) -[2023-10-17 00:59:45,386][62408] Updated weights for policy 1, policy_version 18140 (0.0008) -[2023-10-17 00:59:47,062][62373] Updated weights for policy 0, policy_version 18280 (0.0009) -[2023-10-17 00:59:47,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 37289984. Throughput: 0: 1803.0, 1: 1781.4. Samples: 9336448. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:59:47,215][61453] Avg episode reward: [(0, '6.010'), (1, '5.840')] -[2023-10-17 00:59:47,430][62373] Updated weights for policy 0, policy_version 18290 (0.0010) -[2023-10-17 00:59:47,795][62373] Updated weights for policy 0, policy_version 18300 (0.0008) -[2023-10-17 00:59:49,288][62408] Updated weights for policy 1, policy_version 18150 (0.0008) -[2023-10-17 00:59:49,649][62408] Updated weights for policy 1, policy_version 18160 (0.0009) -[2023-10-17 00:59:50,016][62408] Updated weights for policy 1, policy_version 18170 (0.0007) -[2023-10-17 00:59:51,636][62373] Updated weights for policy 0, policy_version 18310 (0.0009) -[2023-10-17 00:59:51,996][62373] Updated weights for policy 0, policy_version 18320 (0.0008) -[2023-10-17 00:59:52,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 37355520. Throughput: 0: 1787.5, 1: 1789.7. Samples: 9346780. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:59:52,215][61453] Avg episode reward: [(0, '6.270'), (1, '5.890')] -[2023-10-17 00:59:52,373][62373] Updated weights for policy 0, policy_version 18330 (0.0009) -[2023-10-17 00:59:53,700][62408] Updated weights for policy 1, policy_version 18180 (0.0009) -[2023-10-17 00:59:54,074][62408] Updated weights for policy 1, policy_version 18190 (0.0010) -[2023-10-17 00:59:54,444][62408] Updated weights for policy 1, policy_version 18200 (0.0008) -[2023-10-17 00:59:56,291][62373] Updated weights for policy 0, policy_version 18340 (0.0008) -[2023-10-17 00:59:56,667][62373] Updated weights for policy 0, policy_version 18350 (0.0007) -[2023-10-17 00:59:57,027][62373] Updated weights for policy 0, policy_version 18360 (0.0007) -[2023-10-17 00:59:57,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 37421056. Throughput: 0: 1806.7, 1: 1779.0. Samples: 9368510. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 00:59:57,215][61453] Avg episode reward: [(0, '6.360'), (1, '5.800')] -[2023-10-17 00:59:57,325][62094] Saving new best policy, reward=6.360! -[2023-10-17 00:59:58,319][62408] Updated weights for policy 1, policy_version 18210 (0.0011) -[2023-10-17 00:59:58,690][62408] Updated weights for policy 1, policy_version 18220 (0.0011) -[2023-10-17 00:59:59,060][62408] Updated weights for policy 1, policy_version 18230 (0.0007) -[2023-10-17 00:59:59,427][62408] Updated weights for policy 1, policy_version 18240 (0.0008) -[2023-10-17 01:00:00,923][62373] Updated weights for policy 0, policy_version 18370 (0.0008) -[2023-10-17 01:00:01,315][62373] Updated weights for policy 0, policy_version 18380 (0.0008) -[2023-10-17 01:00:01,688][62373] Updated weights for policy 0, policy_version 18390 (0.0011) -[2023-10-17 01:00:02,061][62373] Updated weights for policy 0, policy_version 18400 (0.0007) -[2023-10-17 01:00:02,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14106.9). Total num frames: 37519360. Throughput: 0: 1800.2, 1: 1773.2. Samples: 9389176. Policy #0 lag: (min: 31.0, avg: 32.6, max: 59.0) -[2023-10-17 01:00:02,215][61453] Avg episode reward: [(0, '6.220'), (1, '6.120')] -[2023-10-17 01:00:03,352][62408] Updated weights for policy 1, policy_version 18250 (0.0007) -[2023-10-17 01:00:03,719][62408] Updated weights for policy 1, policy_version 18260 (0.0008) -[2023-10-17 01:00:04,095][62408] Updated weights for policy 1, policy_version 18270 (0.0009) -[2023-10-17 01:00:05,708][62373] Updated weights for policy 0, policy_version 18410 (0.0008) -[2023-10-17 01:00:06,068][62373] Updated weights for policy 0, policy_version 18420 (0.0008) -[2023-10-17 01:00:06,446][62373] Updated weights for policy 0, policy_version 18430 (0.0009) -[2023-10-17 01:00:07,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 37584896. Throughput: 0: 1806.0, 1: 1771.0. Samples: 9400090. Policy #0 lag: (min: 31.0, avg: 32.6, max: 59.0) -[2023-10-17 01:00:07,215][61453] Avg episode reward: [(0, '6.520'), (1, '5.970')] -[2023-10-17 01:00:07,215][62094] Saving new best policy, reward=6.520! -[2023-10-17 01:00:07,965][62408] Updated weights for policy 1, policy_version 18280 (0.0009) -[2023-10-17 01:00:08,326][62408] Updated weights for policy 1, policy_version 18290 (0.0008) -[2023-10-17 01:00:08,694][62408] Updated weights for policy 1, policy_version 18300 (0.0007) -[2023-10-17 01:00:10,067][62373] Updated weights for policy 0, policy_version 18440 (0.0009) -[2023-10-17 01:00:10,435][62373] Updated weights for policy 0, policy_version 18450 (0.0010) -[2023-10-17 01:00:10,811][62373] Updated weights for policy 0, policy_version 18460 (0.0010) -[2023-10-17 01:00:12,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 37650432. Throughput: 0: 1792.5, 1: 1763.1. Samples: 9420862. Policy #0 lag: (min: 31.0, avg: 32.6, max: 59.0) -[2023-10-17 01:00:12,215][61453] Avg episode reward: [(0, '6.690'), (1, '5.960')] -[2023-10-17 01:00:12,216][62094] Saving new best policy, reward=6.690! -[2023-10-17 01:00:12,487][62408] Updated weights for policy 1, policy_version 18310 (0.0007) -[2023-10-17 01:00:12,850][62408] Updated weights for policy 1, policy_version 18320 (0.0007) -[2023-10-17 01:00:13,225][62408] Updated weights for policy 1, policy_version 18330 (0.0008) -[2023-10-17 01:00:14,726][62373] Updated weights for policy 0, policy_version 18470 (0.0008) -[2023-10-17 01:00:15,093][62373] Updated weights for policy 0, policy_version 18480 (0.0007) -[2023-10-17 01:00:15,470][62373] Updated weights for policy 0, policy_version 18490 (0.0007) -[2023-10-17 01:00:17,042][62408] Updated weights for policy 1, policy_version 18340 (0.0008) -[2023-10-17 01:00:17,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 37715968. Throughput: 0: 1773.7, 1: 1795.6. Samples: 9442914. Policy #0 lag: (min: 31.0, avg: 32.6, max: 59.0) -[2023-10-17 01:00:17,214][61453] Avg episode reward: [(0, '6.020'), (1, '5.950')] -[2023-10-17 01:00:17,420][62408] Updated weights for policy 1, policy_version 18350 (0.0008) -[2023-10-17 01:00:17,785][62408] Updated weights for policy 1, policy_version 18360 (0.0008) -[2023-10-17 01:00:19,366][62373] Updated weights for policy 0, policy_version 18500 (0.0009) -[2023-10-17 01:00:19,735][62373] Updated weights for policy 0, policy_version 18510 (0.0007) -[2023-10-17 01:00:20,108][62373] Updated weights for policy 0, policy_version 18520 (0.0007) -[2023-10-17 01:00:21,803][62408] Updated weights for policy 1, policy_version 18370 (0.0008) -[2023-10-17 01:00:22,214][62408] Updated weights for policy 1, policy_version 18380 (0.0009) -[2023-10-17 01:00:22,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 37781504. Throughput: 0: 1787.8, 1: 1755.7. Samples: 9453054. Policy #0 lag: (min: 24.0, avg: 51.9, max: 56.0) -[2023-10-17 01:00:22,215][61453] Avg episode reward: [(0, '6.030'), (1, '6.170')] -[2023-10-17 01:00:22,588][62408] Updated weights for policy 1, policy_version 18390 (0.0007) -[2023-10-17 01:00:22,952][62408] Updated weights for policy 1, policy_version 18400 (0.0010) -[2023-10-17 01:00:23,861][62373] Updated weights for policy 0, policy_version 18530 (0.0008) -[2023-10-17 01:00:24,224][62373] Updated weights for policy 0, policy_version 18540 (0.0007) -[2023-10-17 01:00:24,596][62373] Updated weights for policy 0, policy_version 18550 (0.0008) -[2023-10-17 01:00:24,971][62373] Updated weights for policy 0, policy_version 18560 (0.0007) -[2023-10-17 01:00:26,583][62408] Updated weights for policy 1, policy_version 18410 (0.0009) -[2023-10-17 01:00:26,956][62408] Updated weights for policy 1, policy_version 18420 (0.0007) -[2023-10-17 01:00:27,214][61453] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 37847040. Throughput: 0: 1772.1, 1: 1783.6. Samples: 9474664. Policy #0 lag: (min: 24.0, avg: 51.9, max: 56.0) -[2023-10-17 01:00:27,215][61453] Avg episode reward: [(0, '6.550'), (1, '6.140')] -[2023-10-17 01:00:27,323][62408] Updated weights for policy 1, policy_version 18430 (0.0008) -[2023-10-17 01:00:28,458][62373] Updated weights for policy 0, policy_version 18570 (0.0010) -[2023-10-17 01:00:28,833][62373] Updated weights for policy 0, policy_version 18580 (0.0007) -[2023-10-17 01:00:29,200][62373] Updated weights for policy 0, policy_version 18590 (0.0009) -[2023-10-17 01:00:31,310][62408] Updated weights for policy 1, policy_version 18440 (0.0010) -[2023-10-17 01:00:31,678][62408] Updated weights for policy 1, policy_version 18450 (0.0009) -[2023-10-17 01:00:32,045][62408] Updated weights for policy 1, policy_version 18460 (0.0007) -[2023-10-17 01:00:32,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 37945344. Throughput: 0: 1773.6, 1: 1762.8. Samples: 9495588. Policy #0 lag: (min: 24.0, avg: 51.9, max: 56.0) -[2023-10-17 01:00:32,215][61453] Avg episode reward: [(0, '6.000'), (1, '6.160')] -[2023-10-17 01:00:32,993][62373] Updated weights for policy 0, policy_version 18600 (0.0009) -[2023-10-17 01:00:33,367][62373] Updated weights for policy 0, policy_version 18610 (0.0008) -[2023-10-17 01:00:33,739][62373] Updated weights for policy 0, policy_version 18620 (0.0008) -[2023-10-17 01:00:35,893][62408] Updated weights for policy 1, policy_version 18470 (0.0008) -[2023-10-17 01:00:36,262][62408] Updated weights for policy 1, policy_version 18480 (0.0008) -[2023-10-17 01:00:36,631][62408] Updated weights for policy 1, policy_version 18490 (0.0008) -[2023-10-17 01:00:37,214][61453] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 38010880. Throughput: 0: 1767.0, 1: 1775.0. Samples: 9506170. Policy #0 lag: (min: 24.0, avg: 51.9, max: 56.0) -[2023-10-17 01:00:37,214][61453] Avg episode reward: [(0, '5.620'), (1, '6.150')] -[2023-10-17 01:00:37,672][62373] Updated weights for policy 0, policy_version 18630 (0.0007) -[2023-10-17 01:00:38,043][62373] Updated weights for policy 0, policy_version 18640 (0.0007) -[2023-10-17 01:00:38,406][62373] Updated weights for policy 0, policy_version 18650 (0.0007) -[2023-10-17 01:00:40,317][62408] Updated weights for policy 1, policy_version 18500 (0.0010) -[2023-10-17 01:00:40,688][62408] Updated weights for policy 1, policy_version 18510 (0.0008) -[2023-10-17 01:00:41,049][62408] Updated weights for policy 1, policy_version 18520 (0.0009) -[2023-10-17 01:00:42,152][62373] Updated weights for policy 0, policy_version 18660 (0.0008) -[2023-10-17 01:00:42,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 38076416. Throughput: 0: 1764.7, 1: 1765.9. Samples: 9527386. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:00:42,215][61453] Avg episode reward: [(0, '6.210'), (1, '6.010')] -[2023-10-17 01:00:42,519][62373] Updated weights for policy 0, policy_version 18670 (0.0008) -[2023-10-17 01:00:42,894][62373] Updated weights for policy 0, policy_version 18680 (0.0007) -[2023-10-17 01:00:44,980][62408] Updated weights for policy 1, policy_version 18530 (0.0009) -[2023-10-17 01:00:45,343][62408] Updated weights for policy 1, policy_version 18540 (0.0009) -[2023-10-17 01:00:45,716][62408] Updated weights for policy 1, policy_version 18550 (0.0010) -[2023-10-17 01:00:46,084][62408] Updated weights for policy 1, policy_version 18560 (0.0009) -[2023-10-17 01:00:46,654][62373] Updated weights for policy 0, policy_version 18690 (0.0008) -[2023-10-17 01:00:47,061][62373] Updated weights for policy 0, policy_version 18700 (0.0009) -[2023-10-17 01:00:47,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 38141952. Throughput: 0: 1783.0, 1: 1756.5. Samples: 9548450. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:00:47,215][61453] Avg episode reward: [(0, '5.830'), (1, '5.730')] -[2023-10-17 01:00:47,440][62373] Updated weights for policy 0, policy_version 18710 (0.0010) -[2023-10-17 01:00:47,811][62373] Updated weights for policy 0, policy_version 18720 (0.0009) -[2023-10-17 01:00:49,789][62408] Updated weights for policy 1, policy_version 18570 (0.0011) -[2023-10-17 01:00:50,153][62408] Updated weights for policy 1, policy_version 18580 (0.0008) -[2023-10-17 01:00:50,518][62408] Updated weights for policy 1, policy_version 18590 (0.0008) -[2023-10-17 01:00:51,595][62373] Updated weights for policy 0, policy_version 18730 (0.0007) -[2023-10-17 01:00:51,971][62373] Updated weights for policy 0, policy_version 18740 (0.0007) -[2023-10-17 01:00:52,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 38207488. Throughput: 0: 1757.1, 1: 1782.1. Samples: 9559356. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:00:52,214][61453] Avg episode reward: [(0, '5.490'), (1, '5.960')] -[2023-10-17 01:00:52,331][62373] Updated weights for policy 0, policy_version 18750 (0.0007) -[2023-10-17 01:00:54,249][62408] Updated weights for policy 1, policy_version 18600 (0.0007) -[2023-10-17 01:00:54,611][62408] Updated weights for policy 1, policy_version 18610 (0.0008) -[2023-10-17 01:00:54,977][62408] Updated weights for policy 1, policy_version 18620 (0.0007) -[2023-10-17 01:00:56,157][62373] Updated weights for policy 0, policy_version 18760 (0.0008) -[2023-10-17 01:00:56,521][62373] Updated weights for policy 0, policy_version 18770 (0.0007) -[2023-10-17 01:00:56,896][62373] Updated weights for policy 0, policy_version 18780 (0.0009) -[2023-10-17 01:00:57,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14218.0). Total num frames: 38305792. Throughput: 0: 1790.5, 1: 1762.4. Samples: 9580742. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:00:57,215][61453] Avg episode reward: [(0, '5.580'), (1, '5.890')] -[2023-10-17 01:00:58,798][62408] Updated weights for policy 1, policy_version 18630 (0.0009) -[2023-10-17 01:00:59,167][62408] Updated weights for policy 1, policy_version 18640 (0.0008) -[2023-10-17 01:00:59,540][62408] Updated weights for policy 1, policy_version 18650 (0.0007) -[2023-10-17 01:01:00,759][62373] Updated weights for policy 0, policy_version 18790 (0.0009) -[2023-10-17 01:01:01,129][62373] Updated weights for policy 0, policy_version 18800 (0.0009) -[2023-10-17 01:01:01,490][62373] Updated weights for policy 0, policy_version 18810 (0.0008) -[2023-10-17 01:01:02,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 38371328. Throughput: 0: 1766.1, 1: 1758.8. Samples: 9601536. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:01:02,214][61453] Avg episode reward: [(0, '5.940'), (1, '5.860')] -[2023-10-17 01:01:03,260][62408] Updated weights for policy 1, policy_version 18660 (0.0010) -[2023-10-17 01:01:03,631][62408] Updated weights for policy 1, policy_version 18670 (0.0011) -[2023-10-17 01:01:03,989][62408] Updated weights for policy 1, policy_version 18680 (0.0008) -[2023-10-17 01:01:05,287][62373] Updated weights for policy 0, policy_version 18820 (0.0009) -[2023-10-17 01:01:05,648][62373] Updated weights for policy 0, policy_version 18830 (0.0010) -[2023-10-17 01:01:06,021][62373] Updated weights for policy 0, policy_version 18840 (0.0009) -[2023-10-17 01:01:07,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 38436864. Throughput: 0: 1783.9, 1: 1757.2. Samples: 9612406. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:01:07,215][61453] Avg episode reward: [(0, '5.400'), (1, '5.960')] -[2023-10-17 01:01:07,841][62408] Updated weights for policy 1, policy_version 18690 (0.0008) -[2023-10-17 01:01:08,212][62408] Updated weights for policy 1, policy_version 18700 (0.0008) -[2023-10-17 01:01:08,585][62408] Updated weights for policy 1, policy_version 18710 (0.0008) -[2023-10-17 01:01:08,950][62408] Updated weights for policy 1, policy_version 18720 (0.0008) -[2023-10-17 01:01:09,735][62373] Updated weights for policy 0, policy_version 18850 (0.0007) -[2023-10-17 01:01:10,106][62373] Updated weights for policy 0, policy_version 18860 (0.0009) -[2023-10-17 01:01:10,480][62373] Updated weights for policy 0, policy_version 18870 (0.0008) -[2023-10-17 01:01:10,847][62373] Updated weights for policy 0, policy_version 18880 (0.0009) -[2023-10-17 01:01:12,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 38502400. Throughput: 0: 1766.7, 1: 1758.1. Samples: 9633280. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:01:12,215][61453] Avg episode reward: [(0, '5.200'), (1, '5.350')] -[2023-10-17 01:01:12,868][62408] Updated weights for policy 1, policy_version 18730 (0.0007) -[2023-10-17 01:01:13,233][62408] Updated weights for policy 1, policy_version 18740 (0.0007) -[2023-10-17 01:01:13,614][62408] Updated weights for policy 1, policy_version 18750 (0.0010) -[2023-10-17 01:01:14,753][62373] Updated weights for policy 0, policy_version 18890 (0.0008) -[2023-10-17 01:01:15,121][62373] Updated weights for policy 0, policy_version 18900 (0.0008) -[2023-10-17 01:01:15,503][62373] Updated weights for policy 0, policy_version 18910 (0.0009) -[2023-10-17 01:01:17,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 38567936. Throughput: 0: 1764.4, 1: 1778.5. Samples: 9655016. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:01:17,214][61453] Avg episode reward: [(0, '5.230'), (1, '5.950')] -[2023-10-17 01:01:17,553][62408] Updated weights for policy 1, policy_version 18760 (0.0008) -[2023-10-17 01:01:17,928][62408] Updated weights for policy 1, policy_version 18770 (0.0009) -[2023-10-17 01:01:18,288][62408] Updated weights for policy 1, policy_version 18780 (0.0008) -[2023-10-17 01:01:19,350][62373] Updated weights for policy 0, policy_version 18920 (0.0008) -[2023-10-17 01:01:19,713][62373] Updated weights for policy 0, policy_version 18930 (0.0007) -[2023-10-17 01:01:20,081][62373] Updated weights for policy 0, policy_version 18940 (0.0009) -[2023-10-17 01:01:21,963][62408] Updated weights for policy 1, policy_version 18790 (0.0008) -[2023-10-17 01:01:22,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 38633472. Throughput: 0: 1775.4, 1: 1757.2. Samples: 9665138. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:01:22,214][61453] Avg episode reward: [(0, '5.360'), (1, '6.040')] -[2023-10-17 01:01:22,342][62408] Updated weights for policy 1, policy_version 18800 (0.0008) -[2023-10-17 01:01:22,709][62408] Updated weights for policy 1, policy_version 18810 (0.0010) -[2023-10-17 01:01:23,778][62373] Updated weights for policy 0, policy_version 18950 (0.0007) -[2023-10-17 01:01:24,144][62373] Updated weights for policy 0, policy_version 18960 (0.0008) -[2023-10-17 01:01:24,510][62373] Updated weights for policy 0, policy_version 18970 (0.0007) -[2023-10-17 01:01:26,769][62408] Updated weights for policy 1, policy_version 18820 (0.0009) -[2023-10-17 01:01:27,130][62408] Updated weights for policy 1, policy_version 18830 (0.0009) -[2023-10-17 01:01:27,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 38699008. Throughput: 0: 1770.8, 1: 1772.2. Samples: 9686820. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:01:27,214][61453] Avg episode reward: [(0, '5.590'), (1, '5.620')] -[2023-10-17 01:01:27,500][62408] Updated weights for policy 1, policy_version 18840 (0.0010) -[2023-10-17 01:01:28,291][62373] Updated weights for policy 0, policy_version 18980 (0.0007) -[2023-10-17 01:01:28,660][62373] Updated weights for policy 0, policy_version 18990 (0.0007) -[2023-10-17 01:01:29,020][62373] Updated weights for policy 0, policy_version 19000 (0.0010) -[2023-10-17 01:01:31,542][62408] Updated weights for policy 1, policy_version 18850 (0.0010) -[2023-10-17 01:01:31,911][62408] Updated weights for policy 1, policy_version 18860 (0.0008) -[2023-10-17 01:01:32,214][61453] Fps is (10 sec: 13106.6, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 38764544. Throughput: 0: 1784.8, 1: 1776.0. Samples: 9708688. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:01:32,215][61453] Avg episode reward: [(0, '5.810'), (1, '5.700')] -[2023-10-17 01:01:32,227][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000019008_19464192.pth... -[2023-10-17 01:01:32,269][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000017344_17760256.pth -[2023-10-17 01:01:32,283][62408] Updated weights for policy 1, policy_version 18870 (0.0010) -[2023-10-17 01:01:32,648][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000018880_19333120.pth... -[2023-10-17 01:01:32,649][62408] Updated weights for policy 1, policy_version 18880 (0.0010) -[2023-10-17 01:01:32,676][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000017216_17629184.pth -[2023-10-17 01:01:32,843][62373] Updated weights for policy 0, policy_version 19010 (0.0009) -[2023-10-17 01:01:33,222][62373] Updated weights for policy 0, policy_version 19020 (0.0009) -[2023-10-17 01:01:33,594][62373] Updated weights for policy 0, policy_version 19030 (0.0007) -[2023-10-17 01:01:33,961][62373] Updated weights for policy 0, policy_version 19040 (0.0008) -[2023-10-17 01:01:36,487][62408] Updated weights for policy 1, policy_version 18890 (0.0007) -[2023-10-17 01:01:36,863][62408] Updated weights for policy 1, policy_version 18900 (0.0008) -[2023-10-17 01:01:37,214][61453] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 38830080. Throughput: 0: 1776.4, 1: 1762.2. Samples: 9718592. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:01:37,215][61453] Avg episode reward: [(0, '5.910'), (1, '6.020')] -[2023-10-17 01:01:37,230][62408] Updated weights for policy 1, policy_version 18910 (0.0009) -[2023-10-17 01:01:37,747][62373] Updated weights for policy 0, policy_version 19050 (0.0008) -[2023-10-17 01:01:38,111][62373] Updated weights for policy 0, policy_version 19060 (0.0008) -[2023-10-17 01:01:38,477][62373] Updated weights for policy 0, policy_version 19070 (0.0010) -[2023-10-17 01:01:41,050][62408] Updated weights for policy 1, policy_version 18920 (0.0010) -[2023-10-17 01:01:41,420][62408] Updated weights for policy 1, policy_version 18930 (0.0009) -[2023-10-17 01:01:41,790][62408] Updated weights for policy 1, policy_version 18940 (0.0008) -[2023-10-17 01:01:42,214][61453] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 38928384. Throughput: 0: 1778.4, 1: 1770.0. Samples: 9740418. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:01:42,215][61453] Avg episode reward: [(0, '5.970'), (1, '5.610')] -[2023-10-17 01:01:42,229][62373] Updated weights for policy 0, policy_version 19080 (0.0008) -[2023-10-17 01:01:42,593][62373] Updated weights for policy 0, policy_version 19090 (0.0008) -[2023-10-17 01:01:42,960][62373] Updated weights for policy 0, policy_version 19100 (0.0007) -[2023-10-17 01:01:45,745][62408] Updated weights for policy 1, policy_version 18950 (0.0008) -[2023-10-17 01:01:46,117][62408] Updated weights for policy 1, policy_version 18960 (0.0009) -[2023-10-17 01:01:46,479][62408] Updated weights for policy 1, policy_version 18970 (0.0009) -[2023-10-17 01:01:46,668][62373] Updated weights for policy 0, policy_version 19110 (0.0008) -[2023-10-17 01:01:47,040][62373] Updated weights for policy 0, policy_version 19120 (0.0007) -[2023-10-17 01:01:47,214][61453] Fps is (10 sec: 16383.5, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 38993920. Throughput: 0: 1800.2, 1: 1736.6. Samples: 9760690. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:01:47,216][61453] Avg episode reward: [(0, '5.860'), (1, '5.840')] -[2023-10-17 01:01:47,411][62373] Updated weights for policy 0, policy_version 19130 (0.0010) -[2023-10-17 01:01:50,229][62408] Updated weights for policy 1, policy_version 18980 (0.0008) -[2023-10-17 01:01:50,598][62408] Updated weights for policy 1, policy_version 18990 (0.0007) -[2023-10-17 01:01:50,956][62408] Updated weights for policy 1, policy_version 19000 (0.0008) -[2023-10-17 01:01:51,189][62373] Updated weights for policy 0, policy_version 19140 (0.0009) -[2023-10-17 01:01:51,566][62373] Updated weights for policy 0, policy_version 19150 (0.0010) -[2023-10-17 01:01:51,943][62373] Updated weights for policy 0, policy_version 19160 (0.0008) -[2023-10-17 01:01:52,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 39059456. Throughput: 0: 1779.3, 1: 1773.7. Samples: 9772286. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:01:52,215][61453] Avg episode reward: [(0, '6.200'), (1, '5.640')] -[2023-10-17 01:01:54,788][62408] Updated weights for policy 1, policy_version 19010 (0.0010) -[2023-10-17 01:01:55,164][62408] Updated weights for policy 1, policy_version 19020 (0.0009) -[2023-10-17 01:01:55,532][62408] Updated weights for policy 1, policy_version 19030 (0.0009) -[2023-10-17 01:01:55,764][62373] Updated weights for policy 0, policy_version 19170 (0.0010) -[2023-10-17 01:01:55,898][62408] Updated weights for policy 1, policy_version 19040 (0.0010) -[2023-10-17 01:01:56,132][62373] Updated weights for policy 0, policy_version 19180 (0.0010) -[2023-10-17 01:01:56,498][62373] Updated weights for policy 0, policy_version 19190 (0.0009) -[2023-10-17 01:01:56,873][62373] Updated weights for policy 0, policy_version 19200 (0.0010) -[2023-10-17 01:01:57,214][61453] Fps is (10 sec: 16384.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 39157760. Throughput: 0: 1804.1, 1: 1744.6. Samples: 9792972. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:01:57,214][61453] Avg episode reward: [(0, '6.340'), (1, '6.120')] -[2023-10-17 01:01:59,753][62408] Updated weights for policy 1, policy_version 19050 (0.0010) -[2023-10-17 01:02:00,121][62408] Updated weights for policy 1, policy_version 19060 (0.0007) -[2023-10-17 01:02:00,488][62408] Updated weights for policy 1, policy_version 19070 (0.0007) -[2023-10-17 01:02:00,764][62373] Updated weights for policy 0, policy_version 19210 (0.0008) -[2023-10-17 01:02:01,132][62373] Updated weights for policy 0, policy_version 19220 (0.0011) -[2023-10-17 01:02:01,495][62373] Updated weights for policy 0, policy_version 19230 (0.0008) -[2023-10-17 01:02:02,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 39223296. Throughput: 0: 1776.8, 1: 1745.3. Samples: 9813510. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:02:02,215][61453] Avg episode reward: [(0, '6.410'), (1, '5.600')] -[2023-10-17 01:02:04,200][62408] Updated weights for policy 1, policy_version 19080 (0.0009) -[2023-10-17 01:02:04,580][62408] Updated weights for policy 1, policy_version 19090 (0.0010) -[2023-10-17 01:02:04,948][62408] Updated weights for policy 1, policy_version 19100 (0.0010) -[2023-10-17 01:02:05,419][62373] Updated weights for policy 0, policy_version 19240 (0.0008) -[2023-10-17 01:02:05,787][62373] Updated weights for policy 0, policy_version 19250 (0.0007) -[2023-10-17 01:02:06,160][62373] Updated weights for policy 0, policy_version 19260 (0.0010) -[2023-10-17 01:02:07,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 39288832. Throughput: 0: 1794.4, 1: 1749.5. Samples: 9824612. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:02:07,215][61453] Avg episode reward: [(0, '6.450'), (1, '5.930')] -[2023-10-17 01:02:08,771][62408] Updated weights for policy 1, policy_version 19110 (0.0009) -[2023-10-17 01:02:09,144][62408] Updated weights for policy 1, policy_version 19120 (0.0007) -[2023-10-17 01:02:09,510][62408] Updated weights for policy 1, policy_version 19130 (0.0009) -[2023-10-17 01:02:09,906][62373] Updated weights for policy 0, policy_version 19270 (0.0008) -[2023-10-17 01:02:10,273][62373] Updated weights for policy 0, policy_version 19280 (0.0007) -[2023-10-17 01:02:10,638][62373] Updated weights for policy 0, policy_version 19290 (0.0008) -[2023-10-17 01:02:12,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 39354368. Throughput: 0: 1772.3, 1: 1748.9. Samples: 9845272. Policy #0 lag: (min: 31.0, avg: 35.8, max: 63.0) -[2023-10-17 01:02:12,214][61453] Avg episode reward: [(0, '6.280'), (1, '5.640')] -[2023-10-17 01:02:13,312][62408] Updated weights for policy 1, policy_version 19140 (0.0008) -[2023-10-17 01:02:13,685][62408] Updated weights for policy 1, policy_version 19150 (0.0009) -[2023-10-17 01:02:14,064][62408] Updated weights for policy 1, policy_version 19160 (0.0007) -[2023-10-17 01:02:14,417][62373] Updated weights for policy 0, policy_version 19300 (0.0009) -[2023-10-17 01:02:14,794][62373] Updated weights for policy 0, policy_version 19310 (0.0008) -[2023-10-17 01:02:15,160][62373] Updated weights for policy 0, policy_version 19320 (0.0011) -[2023-10-17 01:02:17,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 39419904. Throughput: 0: 1772.5, 1: 1751.7. Samples: 9867276. Policy #0 lag: (min: 31.0, avg: 35.8, max: 63.0) -[2023-10-17 01:02:17,214][61453] Avg episode reward: [(0, '6.090'), (1, '5.740')] -[2023-10-17 01:02:17,914][62408] Updated weights for policy 1, policy_version 19170 (0.0010) -[2023-10-17 01:02:18,283][62408] Updated weights for policy 1, policy_version 19180 (0.0010) -[2023-10-17 01:02:18,657][62408] Updated weights for policy 1, policy_version 19190 (0.0011) -[2023-10-17 01:02:18,860][62373] Updated weights for policy 0, policy_version 19330 (0.0010) -[2023-10-17 01:02:19,013][62408] Updated weights for policy 1, policy_version 19200 (0.0008) -[2023-10-17 01:02:19,253][62373] Updated weights for policy 0, policy_version 19340 (0.0007) -[2023-10-17 01:02:19,617][62373] Updated weights for policy 0, policy_version 19350 (0.0007) -[2023-10-17 01:02:19,985][62373] Updated weights for policy 0, policy_version 19360 (0.0009) -[2023-10-17 01:02:22,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 39485440. Throughput: 0: 1778.7, 1: 1746.9. Samples: 9877244. Policy #0 lag: (min: 31.0, avg: 35.8, max: 63.0) -[2023-10-17 01:02:22,215][61453] Avg episode reward: [(0, '5.710'), (1, '5.320')] -[2023-10-17 01:02:22,707][62408] Updated weights for policy 1, policy_version 19210 (0.0008) -[2023-10-17 01:02:23,081][62408] Updated weights for policy 1, policy_version 19220 (0.0010) -[2023-10-17 01:02:23,438][62408] Updated weights for policy 1, policy_version 19230 (0.0009) -[2023-10-17 01:02:23,844][62373] Updated weights for policy 0, policy_version 19370 (0.0007) -[2023-10-17 01:02:24,212][62373] Updated weights for policy 0, policy_version 19380 (0.0007) -[2023-10-17 01:02:24,586][62373] Updated weights for policy 0, policy_version 19390 (0.0008) -[2023-10-17 01:02:27,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 39550976. Throughput: 0: 1776.3, 1: 1760.0. Samples: 9899550. Policy #0 lag: (min: 31.0, avg: 35.8, max: 63.0) -[2023-10-17 01:02:27,215][61453] Avg episode reward: [(0, '5.840'), (1, '5.940')] -[2023-10-17 01:02:27,364][62408] Updated weights for policy 1, policy_version 19240 (0.0009) -[2023-10-17 01:02:27,723][62408] Updated weights for policy 1, policy_version 19250 (0.0009) -[2023-10-17 01:02:28,090][62408] Updated weights for policy 1, policy_version 19260 (0.0008) -[2023-10-17 01:02:28,368][62373] Updated weights for policy 0, policy_version 19400 (0.0010) -[2023-10-17 01:02:28,742][62373] Updated weights for policy 0, policy_version 19410 (0.0011) -[2023-10-17 01:02:29,108][62373] Updated weights for policy 0, policy_version 19420 (0.0007) -[2023-10-17 01:02:31,964][62408] Updated weights for policy 1, policy_version 19270 (0.0007) -[2023-10-17 01:02:32,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 39616512. Throughput: 0: 1785.2, 1: 1786.9. Samples: 9921432. Policy #0 lag: (min: 31.0, avg: 32.4, max: 55.0) -[2023-10-17 01:02:32,215][61453] Avg episode reward: [(0, '6.210'), (1, '5.570')] -[2023-10-17 01:02:32,339][62408] Updated weights for policy 1, policy_version 19280 (0.0008) -[2023-10-17 01:02:32,707][62408] Updated weights for policy 1, policy_version 19290 (0.0007) -[2023-10-17 01:02:32,872][62373] Updated weights for policy 0, policy_version 19430 (0.0007) -[2023-10-17 01:02:33,241][62373] Updated weights for policy 0, policy_version 19440 (0.0009) -[2023-10-17 01:02:33,607][62373] Updated weights for policy 0, policy_version 19450 (0.0011) -[2023-10-17 01:02:36,482][62408] Updated weights for policy 1, policy_version 19300 (0.0009) -[2023-10-17 01:02:36,843][62408] Updated weights for policy 1, policy_version 19310 (0.0008) -[2023-10-17 01:02:37,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 39682048. Throughput: 0: 1772.3, 1: 1760.8. Samples: 9931272. Policy #0 lag: (min: 31.0, avg: 32.4, max: 55.0) -[2023-10-17 01:02:37,215][62408] Updated weights for policy 1, policy_version 19320 (0.0009) -[2023-10-17 01:02:37,215][61453] Avg episode reward: [(0, '6.660'), (1, '5.850')] -[2023-10-17 01:02:37,326][62373] Updated weights for policy 0, policy_version 19460 (0.0009) -[2023-10-17 01:02:37,691][62373] Updated weights for policy 0, policy_version 19470 (0.0008) -[2023-10-17 01:02:38,068][62373] Updated weights for policy 0, policy_version 19480 (0.0007) -[2023-10-17 01:02:40,920][62408] Updated weights for policy 1, policy_version 19330 (0.0007) -[2023-10-17 01:02:41,294][62408] Updated weights for policy 1, policy_version 19340 (0.0008) -[2023-10-17 01:02:41,658][62408] Updated weights for policy 1, policy_version 19350 (0.0007) -[2023-10-17 01:02:41,953][62373] Updated weights for policy 0, policy_version 19490 (0.0008) -[2023-10-17 01:02:42,022][62408] Updated weights for policy 1, policy_version 19360 (0.0009) -[2023-10-17 01:02:42,214][61453] Fps is (10 sec: 16384.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 39780352. Throughput: 0: 1770.3, 1: 1789.7. Samples: 9953170. Policy #0 lag: (min: 31.0, avg: 32.4, max: 55.0) -[2023-10-17 01:02:42,214][61453] Avg episode reward: [(0, '6.550'), (1, '6.170')] -[2023-10-17 01:02:42,307][62373] Updated weights for policy 0, policy_version 19500 (0.0009) -[2023-10-17 01:02:42,671][62373] Updated weights for policy 0, policy_version 19510 (0.0009) -[2023-10-17 01:02:43,039][62373] Updated weights for policy 0, policy_version 19520 (0.0010) -[2023-10-17 01:02:45,944][62408] Updated weights for policy 1, policy_version 19370 (0.0008) -[2023-10-17 01:02:46,312][62408] Updated weights for policy 1, policy_version 19380 (0.0008) -[2023-10-17 01:02:46,687][62408] Updated weights for policy 1, policy_version 19390 (0.0009) -[2023-10-17 01:02:47,063][62373] Updated weights for policy 0, policy_version 19530 (0.0008) -[2023-10-17 01:02:47,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 39845888. Throughput: 0: 1790.4, 1: 1758.5. Samples: 9973210. Policy #0 lag: (min: 31.0, avg: 32.4, max: 55.0) -[2023-10-17 01:02:47,215][61453] Avg episode reward: [(0, '7.130'), (1, '6.270')] -[2023-10-17 01:02:47,428][62373] Updated weights for policy 0, policy_version 19540 (0.0009) -[2023-10-17 01:02:47,800][62373] Updated weights for policy 0, policy_version 19550 (0.0009) -[2023-10-17 01:02:47,874][62094] Saving new best policy, reward=7.130! -[2023-10-17 01:02:50,552][62408] Updated weights for policy 1, policy_version 19400 (0.0010) -[2023-10-17 01:02:50,916][62408] Updated weights for policy 1, policy_version 19410 (0.0011) -[2023-10-17 01:02:51,282][62408] Updated weights for policy 1, policy_version 19420 (0.0008) -[2023-10-17 01:02:51,530][62373] Updated weights for policy 0, policy_version 19560 (0.0008) -[2023-10-17 01:02:51,908][62373] Updated weights for policy 0, policy_version 19570 (0.0010) -[2023-10-17 01:02:52,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 39911424. Throughput: 0: 1770.3, 1: 1784.6. Samples: 9984582. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-17 01:02:52,215][61453] Avg episode reward: [(0, '7.010'), (1, '6.290')] -[2023-10-17 01:02:52,284][62373] Updated weights for policy 0, policy_version 19580 (0.0010) -[2023-10-17 01:02:55,204][62408] Updated weights for policy 1, policy_version 19430 (0.0008) -[2023-10-17 01:02:55,579][62408] Updated weights for policy 1, policy_version 19440 (0.0008) -[2023-10-17 01:02:55,943][62408] Updated weights for policy 1, policy_version 19450 (0.0009) -[2023-10-17 01:02:55,970][62373] Updated weights for policy 0, policy_version 19590 (0.0008) -[2023-10-17 01:02:56,339][62373] Updated weights for policy 0, policy_version 19600 (0.0010) -[2023-10-17 01:02:56,711][62373] Updated weights for policy 0, policy_version 19610 (0.0008) -[2023-10-17 01:02:57,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 40009728. Throughput: 0: 1793.8, 1: 1760.4. Samples: 10005208. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-17 01:02:57,215][61453] Avg episode reward: [(0, '6.420'), (1, '6.050')] -[2023-10-17 01:02:59,843][62408] Updated weights for policy 1, policy_version 19460 (0.0010) -[2023-10-17 01:03:00,200][62408] Updated weights for policy 1, policy_version 19470 (0.0009) -[2023-10-17 01:03:00,567][62408] Updated weights for policy 1, policy_version 19480 (0.0009) -[2023-10-17 01:03:00,641][62373] Updated weights for policy 0, policy_version 19620 (0.0010) -[2023-10-17 01:03:01,015][62373] Updated weights for policy 0, policy_version 19630 (0.0009) -[2023-10-17 01:03:01,384][62373] Updated weights for policy 0, policy_version 19640 (0.0008) -[2023-10-17 01:03:02,214][61453] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 40075264. Throughput: 0: 1760.8, 1: 1757.7. Samples: 10025608. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-17 01:03:02,214][61453] Avg episode reward: [(0, '5.890'), (1, '5.950')] -[2023-10-17 01:03:04,390][62408] Updated weights for policy 1, policy_version 19490 (0.0008) -[2023-10-17 01:03:04,765][62408] Updated weights for policy 1, policy_version 19500 (0.0010) -[2023-10-17 01:03:05,129][62408] Updated weights for policy 1, policy_version 19510 (0.0007) -[2023-10-17 01:03:05,220][62373] Updated weights for policy 0, policy_version 19650 (0.0008) -[2023-10-17 01:03:05,500][62408] Updated weights for policy 1, policy_version 19520 (0.0008) -[2023-10-17 01:03:05,608][62373] Updated weights for policy 0, policy_version 19660 (0.0008) -[2023-10-17 01:03:05,985][62373] Updated weights for policy 0, policy_version 19670 (0.0009) -[2023-10-17 01:03:06,347][62373] Updated weights for policy 0, policy_version 19680 (0.0007) -[2023-10-17 01:03:07,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 40140800. Throughput: 0: 1790.6, 1: 1770.5. Samples: 10037492. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:03:07,215][61453] Avg episode reward: [(0, '6.010'), (1, '6.080')] -[2023-10-17 01:03:09,422][62408] Updated weights for policy 1, policy_version 19530 (0.0008) -[2023-10-17 01:03:09,797][62408] Updated weights for policy 1, policy_version 19540 (0.0008) -[2023-10-17 01:03:10,165][62408] Updated weights for policy 1, policy_version 19550 (0.0008) -[2023-10-17 01:03:10,224][62373] Updated weights for policy 0, policy_version 19690 (0.0007) -[2023-10-17 01:03:10,595][62373] Updated weights for policy 0, policy_version 19700 (0.0007) -[2023-10-17 01:03:10,957][62373] Updated weights for policy 0, policy_version 19710 (0.0007) -[2023-10-17 01:03:12,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 40206336. Throughput: 0: 1756.1, 1: 1745.1. Samples: 10057108. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:03:12,215][61453] Avg episode reward: [(0, '5.950'), (1, '5.640')] -[2023-10-17 01:03:13,916][62408] Updated weights for policy 1, policy_version 19560 (0.0011) -[2023-10-17 01:03:14,273][62408] Updated weights for policy 1, policy_version 19570 (0.0010) -[2023-10-17 01:03:14,651][62408] Updated weights for policy 1, policy_version 19580 (0.0010) -[2023-10-17 01:03:14,839][62373] Updated weights for policy 0, policy_version 19720 (0.0008) -[2023-10-17 01:03:15,214][62373] Updated weights for policy 0, policy_version 19730 (0.0009) -[2023-10-17 01:03:15,581][62373] Updated weights for policy 0, policy_version 19740 (0.0009) -[2023-10-17 01:03:17,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 40271872. Throughput: 0: 1749.1, 1: 1753.6. Samples: 10079056. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:03:17,215][61453] Avg episode reward: [(0, '5.600'), (1, '5.490')] -[2023-10-17 01:03:18,491][62408] Updated weights for policy 1, policy_version 19590 (0.0008) -[2023-10-17 01:03:18,864][62408] Updated weights for policy 1, policy_version 19600 (0.0007) -[2023-10-17 01:03:19,227][62408] Updated weights for policy 1, policy_version 19610 (0.0009) -[2023-10-17 01:03:19,357][62373] Updated weights for policy 0, policy_version 19750 (0.0007) -[2023-10-17 01:03:19,727][62373] Updated weights for policy 0, policy_version 19760 (0.0007) -[2023-10-17 01:03:20,098][62373] Updated weights for policy 0, policy_version 19770 (0.0009) -[2023-10-17 01:03:22,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 40337408. Throughput: 0: 1763.2, 1: 1749.4. Samples: 10089340. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:03:22,215][61453] Avg episode reward: [(0, '5.650'), (1, '5.610')] -[2023-10-17 01:03:23,004][62408] Updated weights for policy 1, policy_version 19620 (0.0007) -[2023-10-17 01:03:23,373][62408] Updated weights for policy 1, policy_version 19630 (0.0010) -[2023-10-17 01:03:23,739][62408] Updated weights for policy 1, policy_version 19640 (0.0008) -[2023-10-17 01:03:23,882][62373] Updated weights for policy 0, policy_version 19780 (0.0008) -[2023-10-17 01:03:24,253][62373] Updated weights for policy 0, policy_version 19790 (0.0011) -[2023-10-17 01:03:24,629][62373] Updated weights for policy 0, policy_version 19800 (0.0008) -[2023-10-17 01:03:27,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 40402944. Throughput: 0: 1752.3, 1: 1748.3. Samples: 10110694. Policy #0 lag: (min: 29.0, avg: 33.9, max: 61.0) -[2023-10-17 01:03:27,215][61453] Avg episode reward: [(0, '6.040'), (1, '5.780')] -[2023-10-17 01:03:27,450][62408] Updated weights for policy 1, policy_version 19650 (0.0009) -[2023-10-17 01:03:27,819][62408] Updated weights for policy 1, policy_version 19660 (0.0009) -[2023-10-17 01:03:28,183][62408] Updated weights for policy 1, policy_version 19670 (0.0008) -[2023-10-17 01:03:28,444][62373] Updated weights for policy 0, policy_version 19810 (0.0009) -[2023-10-17 01:03:28,549][62408] Updated weights for policy 1, policy_version 19680 (0.0009) -[2023-10-17 01:03:28,812][62373] Updated weights for policy 0, policy_version 19820 (0.0010) -[2023-10-17 01:03:29,186][62373] Updated weights for policy 0, policy_version 19830 (0.0009) -[2023-10-17 01:03:29,556][62373] Updated weights for policy 0, policy_version 19840 (0.0007) -[2023-10-17 01:03:32,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 40468480. Throughput: 0: 1761.0, 1: 1779.7. Samples: 10132542. Policy #0 lag: (min: 29.0, avg: 33.9, max: 61.0) -[2023-10-17 01:03:32,215][61453] Avg episode reward: [(0, '5.800'), (1, '6.060')] -[2023-10-17 01:03:32,225][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000019840_20316160.pth... -[2023-10-17 01:03:32,258][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000018176_18612224.pth -[2023-10-17 01:03:32,520][62408] Updated weights for policy 1, policy_version 19690 (0.0009) -[2023-10-17 01:03:32,891][62408] Updated weights for policy 1, policy_version 19700 (0.0008) -[2023-10-17 01:03:33,262][62408] Updated weights for policy 1, policy_version 19710 (0.0008) -[2023-10-17 01:03:33,329][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000019712_20185088.pth... -[2023-10-17 01:03:33,357][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000018048_18481152.pth -[2023-10-17 01:03:33,404][62373] Updated weights for policy 0, policy_version 19850 (0.0007) -[2023-10-17 01:03:33,775][62373] Updated weights for policy 0, policy_version 19860 (0.0009) -[2023-10-17 01:03:34,151][62373] Updated weights for policy 0, policy_version 19870 (0.0009) -[2023-10-17 01:03:37,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 40534016. Throughput: 0: 1754.0, 1: 1743.4. Samples: 10141966. Policy #0 lag: (min: 29.0, avg: 33.9, max: 61.0) -[2023-10-17 01:03:37,215][61453] Avg episode reward: [(0, '6.110'), (1, '5.950')] -[2023-10-17 01:03:37,293][62408] Updated weights for policy 1, policy_version 19720 (0.0010) -[2023-10-17 01:03:37,664][62408] Updated weights for policy 1, policy_version 19730 (0.0009) -[2023-10-17 01:03:37,779][62373] Updated weights for policy 0, policy_version 19880 (0.0009) -[2023-10-17 01:03:38,041][62408] Updated weights for policy 1, policy_version 19740 (0.0008) -[2023-10-17 01:03:38,153][62373] Updated weights for policy 0, policy_version 19890 (0.0009) -[2023-10-17 01:03:38,518][62373] Updated weights for policy 0, policy_version 19900 (0.0010) -[2023-10-17 01:03:41,778][62408] Updated weights for policy 1, policy_version 19750 (0.0009) -[2023-10-17 01:03:42,143][62408] Updated weights for policy 1, policy_version 19760 (0.0008) -[2023-10-17 01:03:42,214][61453] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 40599552. Throughput: 0: 1760.8, 1: 1767.2. Samples: 10163970. Policy #0 lag: (min: 29.0, avg: 33.9, max: 61.0) -[2023-10-17 01:03:42,215][61453] Avg episode reward: [(0, '6.340'), (1, '5.900')] -[2023-10-17 01:03:42,306][62373] Updated weights for policy 0, policy_version 19910 (0.0007) -[2023-10-17 01:03:42,512][62408] Updated weights for policy 1, policy_version 19770 (0.0009) -[2023-10-17 01:03:42,676][62373] Updated weights for policy 0, policy_version 19920 (0.0007) -[2023-10-17 01:03:43,041][62373] Updated weights for policy 0, policy_version 19930 (0.0007) -[2023-10-17 01:03:46,506][62408] Updated weights for policy 1, policy_version 19780 (0.0008) -[2023-10-17 01:03:46,871][62408] Updated weights for policy 1, policy_version 19790 (0.0009) -[2023-10-17 01:03:46,985][62373] Updated weights for policy 0, policy_version 19940 (0.0007) -[2023-10-17 01:03:47,214][61453] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 40665088. Throughput: 0: 1782.7, 1: 1758.9. Samples: 10184984. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:03:47,215][61453] Avg episode reward: [(0, '6.210'), (1, '6.170')] -[2023-10-17 01:03:47,231][62408] Updated weights for policy 1, policy_version 19800 (0.0007) -[2023-10-17 01:03:47,346][62373] Updated weights for policy 0, policy_version 19950 (0.0008) -[2023-10-17 01:03:47,721][62373] Updated weights for policy 0, policy_version 19960 (0.0008) -[2023-10-17 01:03:51,288][62408] Updated weights for policy 1, policy_version 19810 (0.0008) -[2023-10-17 01:03:51,627][62373] Updated weights for policy 0, policy_version 19970 (0.0007) -[2023-10-17 01:03:51,655][62408] Updated weights for policy 1, policy_version 19820 (0.0007) -[2023-10-17 01:03:52,014][62373] Updated weights for policy 0, policy_version 19980 (0.0009) -[2023-10-17 01:03:52,026][62408] Updated weights for policy 1, policy_version 19830 (0.0007) -[2023-10-17 01:03:52,214][61453] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 40730624. Throughput: 0: 1751.8, 1: 1751.3. Samples: 10195134. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:03:52,214][61453] Avg episode reward: [(0, '6.310'), (1, '5.640')] -[2023-10-17 01:03:52,382][62408] Updated weights for policy 1, policy_version 19840 (0.0008) -[2023-10-17 01:03:52,384][62373] Updated weights for policy 0, policy_version 19990 (0.0007) -[2023-10-17 01:03:52,756][62373] Updated weights for policy 0, policy_version 20000 (0.0007) -[2023-10-17 01:03:56,291][62408] Updated weights for policy 1, policy_version 19850 (0.0008) -[2023-10-17 01:03:56,531][62373] Updated weights for policy 0, policy_version 20010 (0.0007) -[2023-10-17 01:03:56,646][62408] Updated weights for policy 1, policy_version 19860 (0.0007) -[2023-10-17 01:03:56,889][62373] Updated weights for policy 0, policy_version 20020 (0.0010) -[2023-10-17 01:03:57,014][62408] Updated weights for policy 1, policy_version 19870 (0.0008) -[2023-10-17 01:03:57,214][61453] Fps is (10 sec: 16384.3, 60 sec: 13653.3, 300 sec: 14218.0). Total num frames: 40828928. Throughput: 0: 1781.7, 1: 1771.2. Samples: 10216986. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:03:57,215][61453] Avg episode reward: [(0, '6.510'), (1, '5.790')] -[2023-10-17 01:03:57,261][62373] Updated weights for policy 0, policy_version 20030 (0.0009) -[2023-10-17 01:04:00,736][62408] Updated weights for policy 1, policy_version 19880 (0.0008) -[2023-10-17 01:04:01,107][62408] Updated weights for policy 1, policy_version 19890 (0.0008) -[2023-10-17 01:04:01,124][62373] Updated weights for policy 0, policy_version 20040 (0.0008) -[2023-10-17 01:04:01,474][62408] Updated weights for policy 1, policy_version 19900 (0.0008) -[2023-10-17 01:04:01,496][62373] Updated weights for policy 0, policy_version 20050 (0.0009) -[2023-10-17 01:04:01,856][62373] Updated weights for policy 0, policy_version 20060 (0.0010) -[2023-10-17 01:04:02,214][61453] Fps is (10 sec: 19660.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 40927232. Throughput: 0: 1756.5, 1: 1738.1. Samples: 10236314. Policy #0 lag: (min: 31.0, avg: 31.1, max: 38.0) -[2023-10-17 01:04:02,215][61453] Avg episode reward: [(0, '6.620'), (1, '5.780')] -[2023-10-17 01:04:05,331][62408] Updated weights for policy 1, policy_version 19910 (0.0009) -[2023-10-17 01:04:05,695][62408] Updated weights for policy 1, policy_version 19920 (0.0007) -[2023-10-17 01:04:05,698][62373] Updated weights for policy 0, policy_version 20070 (0.0008) -[2023-10-17 01:04:06,060][62373] Updated weights for policy 0, policy_version 20080 (0.0010) -[2023-10-17 01:04:06,063][62408] Updated weights for policy 1, policy_version 19930 (0.0009) -[2023-10-17 01:04:06,426][62373] Updated weights for policy 0, policy_version 20090 (0.0009) -[2023-10-17 01:04:07,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 40992768. Throughput: 0: 1772.4, 1: 1770.8. Samples: 10248784. Policy #0 lag: (min: 31.0, avg: 31.1, max: 38.0) -[2023-10-17 01:04:07,214][61453] Avg episode reward: [(0, '6.550'), (1, '5.930')] -[2023-10-17 01:04:09,830][62408] Updated weights for policy 1, policy_version 19940 (0.0009) -[2023-10-17 01:04:10,196][62408] Updated weights for policy 1, policy_version 19950 (0.0008) -[2023-10-17 01:04:10,201][62373] Updated weights for policy 0, policy_version 20100 (0.0009) -[2023-10-17 01:04:10,556][62373] Updated weights for policy 0, policy_version 20110 (0.0008) -[2023-10-17 01:04:10,560][62408] Updated weights for policy 1, policy_version 19960 (0.0008) -[2023-10-17 01:04:10,933][62373] Updated weights for policy 0, policy_version 20120 (0.0009) -[2023-10-17 01:04:12,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 41058304. Throughput: 0: 1767.3, 1: 1745.2. Samples: 10268756. Policy #0 lag: (min: 31.0, avg: 31.1, max: 38.0) -[2023-10-17 01:04:12,215][61453] Avg episode reward: [(0, '6.350'), (1, '5.920')] -[2023-10-17 01:04:14,202][62408] Updated weights for policy 1, policy_version 19970 (0.0009) -[2023-10-17 01:04:14,580][62408] Updated weights for policy 1, policy_version 19980 (0.0008) -[2023-10-17 01:04:14,756][62373] Updated weights for policy 0, policy_version 20130 (0.0008) -[2023-10-17 01:04:14,939][62408] Updated weights for policy 1, policy_version 19990 (0.0008) -[2023-10-17 01:04:15,127][62373] Updated weights for policy 0, policy_version 20140 (0.0010) -[2023-10-17 01:04:15,310][62408] Updated weights for policy 1, policy_version 20000 (0.0007) -[2023-10-17 01:04:15,489][62373] Updated weights for policy 0, policy_version 20150 (0.0007) -[2023-10-17 01:04:15,859][62373] Updated weights for policy 0, policy_version 20160 (0.0009) -[2023-10-17 01:04:17,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 41123840. Throughput: 0: 1758.7, 1: 1755.8. Samples: 10290692. Policy #0 lag: (min: 31.0, avg: 31.1, max: 38.0) -[2023-10-17 01:04:17,215][61453] Avg episode reward: [(0, '6.440'), (1, '6.340')] -[2023-10-17 01:04:19,233][62408] Updated weights for policy 1, policy_version 20010 (0.0011) -[2023-10-17 01:04:19,605][62408] Updated weights for policy 1, policy_version 20020 (0.0007) -[2023-10-17 01:04:19,633][62373] Updated weights for policy 0, policy_version 20170 (0.0008) -[2023-10-17 01:04:19,975][62408] Updated weights for policy 1, policy_version 20030 (0.0007) -[2023-10-17 01:04:20,015][62373] Updated weights for policy 0, policy_version 20180 (0.0009) -[2023-10-17 01:04:20,394][62373] Updated weights for policy 0, policy_version 20190 (0.0008) -[2023-10-17 01:04:22,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 41189376. Throughput: 0: 1770.1, 1: 1760.5. Samples: 10300844. Policy #0 lag: (min: 10.0, avg: 10.1, max: 18.0) -[2023-10-17 01:04:22,215][61453] Avg episode reward: [(0, '6.190'), (1, '6.370')] -[2023-10-17 01:04:23,754][62408] Updated weights for policy 1, policy_version 20040 (0.0007) -[2023-10-17 01:04:24,119][62408] Updated weights for policy 1, policy_version 20050 (0.0007) -[2023-10-17 01:04:24,273][62373] Updated weights for policy 0, policy_version 20200 (0.0009) -[2023-10-17 01:04:24,489][62408] Updated weights for policy 1, policy_version 20060 (0.0007) -[2023-10-17 01:04:24,633][62373] Updated weights for policy 0, policy_version 20210 (0.0008) -[2023-10-17 01:04:25,011][62373] Updated weights for policy 0, policy_version 20220 (0.0008) -[2023-10-17 01:04:27,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 41254912. Throughput: 0: 1751.3, 1: 1757.8. Samples: 10321880. Policy #0 lag: (min: 10.0, avg: 10.1, max: 18.0) -[2023-10-17 01:04:27,215][61453] Avg episode reward: [(0, '6.340'), (1, '6.170')] -[2023-10-17 01:04:28,395][62408] Updated weights for policy 1, policy_version 20070 (0.0008) -[2023-10-17 01:04:28,765][62408] Updated weights for policy 1, policy_version 20080 (0.0007) -[2023-10-17 01:04:28,924][62373] Updated weights for policy 0, policy_version 20230 (0.0007) -[2023-10-17 01:04:29,140][62408] Updated weights for policy 1, policy_version 20090 (0.0009) -[2023-10-17 01:04:29,301][62373] Updated weights for policy 0, policy_version 20240 (0.0009) -[2023-10-17 01:04:29,677][62373] Updated weights for policy 0, policy_version 20250 (0.0008) -[2023-10-17 01:04:32,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 41320448. Throughput: 0: 1759.4, 1: 1777.9. Samples: 10344162. Policy #0 lag: (min: 10.0, avg: 10.1, max: 18.0) -[2023-10-17 01:04:32,215][61453] Avg episode reward: [(0, '6.080'), (1, '6.610')] -[2023-10-17 01:04:32,227][62252] Saving new best policy, reward=6.610! -[2023-10-17 01:04:32,978][62408] Updated weights for policy 1, policy_version 20100 (0.0007) -[2023-10-17 01:04:33,347][62408] Updated weights for policy 1, policy_version 20110 (0.0008) -[2023-10-17 01:04:33,468][62373] Updated weights for policy 0, policy_version 20260 (0.0009) -[2023-10-17 01:04:33,715][62408] Updated weights for policy 1, policy_version 20120 (0.0007) -[2023-10-17 01:04:33,832][62373] Updated weights for policy 0, policy_version 20270 (0.0008) -[2023-10-17 01:04:34,204][62373] Updated weights for policy 0, policy_version 20280 (0.0009) -[2023-10-17 01:04:37,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 41385984. Throughput: 0: 1756.1, 1: 1765.6. Samples: 10353612. Policy #0 lag: (min: 10.0, avg: 10.1, max: 18.0) -[2023-10-17 01:04:37,215][61453] Avg episode reward: [(0, '6.210'), (1, '6.500')] -[2023-10-17 01:04:37,594][62408] Updated weights for policy 1, policy_version 20130 (0.0008) -[2023-10-17 01:04:37,963][62408] Updated weights for policy 1, policy_version 20140 (0.0007) -[2023-10-17 01:04:38,116][62373] Updated weights for policy 0, policy_version 20290 (0.0009) -[2023-10-17 01:04:38,332][62408] Updated weights for policy 1, policy_version 20150 (0.0007) -[2023-10-17 01:04:38,492][62373] Updated weights for policy 0, policy_version 20300 (0.0008) -[2023-10-17 01:04:38,701][62408] Updated weights for policy 1, policy_version 20160 (0.0008) -[2023-10-17 01:04:38,856][62373] Updated weights for policy 0, policy_version 20310 (0.0008) -[2023-10-17 01:04:39,232][62373] Updated weights for policy 0, policy_version 20320 (0.0009) -[2023-10-17 01:04:42,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 41451520. Throughput: 0: 1757.4, 1: 1767.8. Samples: 10375620. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:04:42,215][61453] Avg episode reward: [(0, '6.360'), (1, '6.220')] -[2023-10-17 01:04:42,559][62408] Updated weights for policy 1, policy_version 20170 (0.0008) -[2023-10-17 01:04:42,924][62408] Updated weights for policy 1, policy_version 20180 (0.0008) -[2023-10-17 01:04:43,058][62373] Updated weights for policy 0, policy_version 20330 (0.0007) -[2023-10-17 01:04:43,294][62408] Updated weights for policy 1, policy_version 20190 (0.0007) -[2023-10-17 01:04:43,436][62373] Updated weights for policy 0, policy_version 20340 (0.0008) -[2023-10-17 01:04:43,804][62373] Updated weights for policy 0, policy_version 20350 (0.0010) -[2023-10-17 01:04:47,126][62408] Updated weights for policy 1, policy_version 20200 (0.0010) -[2023-10-17 01:04:47,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 41517056. Throughput: 0: 1787.9, 1: 1793.6. Samples: 10397478. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:04:47,215][61453] Avg episode reward: [(0, '6.340'), (1, '6.200')] -[2023-10-17 01:04:47,489][62408] Updated weights for policy 1, policy_version 20210 (0.0008) -[2023-10-17 01:04:47,640][62373] Updated weights for policy 0, policy_version 20360 (0.0008) -[2023-10-17 01:04:47,850][62408] Updated weights for policy 1, policy_version 20220 (0.0008) -[2023-10-17 01:04:48,006][62373] Updated weights for policy 0, policy_version 20370 (0.0008) -[2023-10-17 01:04:48,378][62373] Updated weights for policy 0, policy_version 20380 (0.0007) -[2023-10-17 01:04:51,609][62408] Updated weights for policy 1, policy_version 20230 (0.0007) -[2023-10-17 01:04:51,974][62408] Updated weights for policy 1, policy_version 20240 (0.0010) -[2023-10-17 01:04:52,118][62373] Updated weights for policy 0, policy_version 20390 (0.0008) -[2023-10-17 01:04:52,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 41582592. Throughput: 0: 1756.6, 1: 1761.3. Samples: 10407090. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:04:52,215][61453] Avg episode reward: [(0, '6.440'), (1, '6.050')] -[2023-10-17 01:04:52,337][62408] Updated weights for policy 1, policy_version 20250 (0.0009) -[2023-10-17 01:04:52,489][62373] Updated weights for policy 0, policy_version 20400 (0.0008) -[2023-10-17 01:04:52,848][62373] Updated weights for policy 0, policy_version 20410 (0.0008) -[2023-10-17 01:04:56,263][62408] Updated weights for policy 1, policy_version 20260 (0.0008) -[2023-10-17 01:04:56,586][62373] Updated weights for policy 0, policy_version 20420 (0.0007) -[2023-10-17 01:04:56,627][62408] Updated weights for policy 1, policy_version 20270 (0.0008) -[2023-10-17 01:04:56,951][62373] Updated weights for policy 0, policy_version 20430 (0.0008) -[2023-10-17 01:04:56,999][62408] Updated weights for policy 1, policy_version 20280 (0.0008) -[2023-10-17 01:04:57,214][61453] Fps is (10 sec: 13107.6, 60 sec: 13653.3, 300 sec: 13995.8). Total num frames: 41648128. Throughput: 0: 1778.7, 1: 1786.5. Samples: 10429190. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:04:57,214][61453] Avg episode reward: [(0, '6.700'), (1, '6.630')] -[2023-10-17 01:04:57,281][62252] Saving new best policy, reward=6.630! -[2023-10-17 01:04:57,321][62373] Updated weights for policy 0, policy_version 20440 (0.0010) -[2023-10-17 01:05:00,805][62408] Updated weights for policy 1, policy_version 20290 (0.0007) -[2023-10-17 01:05:01,168][62373] Updated weights for policy 0, policy_version 20450 (0.0009) -[2023-10-17 01:05:01,176][62408] Updated weights for policy 1, policy_version 20300 (0.0009) -[2023-10-17 01:05:01,537][62373] Updated weights for policy 0, policy_version 20460 (0.0007) -[2023-10-17 01:05:01,543][62408] Updated weights for policy 1, policy_version 20310 (0.0008) -[2023-10-17 01:05:01,911][62408] Updated weights for policy 1, policy_version 20320 (0.0007) -[2023-10-17 01:05:01,912][62373] Updated weights for policy 0, policy_version 20470 (0.0009) -[2023-10-17 01:05:02,214][61453] Fps is (10 sec: 16384.3, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 41746432. Throughput: 0: 1761.9, 1: 1751.3. Samples: 10448786. Policy #0 lag: (min: 3.0, avg: 28.7, max: 32.0) -[2023-10-17 01:05:02,214][61453] Avg episode reward: [(0, '7.030'), (1, '6.010')] -[2023-10-17 01:05:02,274][62373] Updated weights for policy 0, policy_version 20480 (0.0009) -[2023-10-17 01:05:05,715][62408] Updated weights for policy 1, policy_version 20330 (0.0007) -[2023-10-17 01:05:06,090][62408] Updated weights for policy 1, policy_version 20340 (0.0009) -[2023-10-17 01:05:06,122][62373] Updated weights for policy 0, policy_version 20490 (0.0008) -[2023-10-17 01:05:06,446][62408] Updated weights for policy 1, policy_version 20350 (0.0009) -[2023-10-17 01:05:06,488][62373] Updated weights for policy 0, policy_version 20500 (0.0008) -[2023-10-17 01:05:06,863][62373] Updated weights for policy 0, policy_version 20510 (0.0010) -[2023-10-17 01:05:07,214][61453] Fps is (10 sec: 19660.6, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 41844736. Throughput: 0: 1770.5, 1: 1784.0. Samples: 10460796. Policy #0 lag: (min: 3.0, avg: 28.7, max: 32.0) -[2023-10-17 01:05:07,215][61453] Avg episode reward: [(0, '6.950'), (1, '6.170')] -[2023-10-17 01:05:10,157][62408] Updated weights for policy 1, policy_version 20360 (0.0008) -[2023-10-17 01:05:10,531][62408] Updated weights for policy 1, policy_version 20370 (0.0008) -[2023-10-17 01:05:10,760][62373] Updated weights for policy 0, policy_version 20520 (0.0008) -[2023-10-17 01:05:10,895][62408] Updated weights for policy 1, policy_version 20380 (0.0008) -[2023-10-17 01:05:11,129][62373] Updated weights for policy 0, policy_version 20530 (0.0009) -[2023-10-17 01:05:11,505][62373] Updated weights for policy 0, policy_version 20540 (0.0008) -[2023-10-17 01:05:12,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 41910272. Throughput: 0: 1775.5, 1: 1767.7. Samples: 10481324. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:05:12,214][61453] Avg episode reward: [(0, '6.600'), (1, '6.280')] -[2023-10-17 01:05:14,654][62408] Updated weights for policy 1, policy_version 20390 (0.0007) -[2023-10-17 01:05:15,025][62408] Updated weights for policy 1, policy_version 20400 (0.0008) -[2023-10-17 01:05:15,282][62373] Updated weights for policy 0, policy_version 20550 (0.0008) -[2023-10-17 01:05:15,389][62408] Updated weights for policy 1, policy_version 20410 (0.0007) -[2023-10-17 01:05:15,649][62373] Updated weights for policy 0, policy_version 20560 (0.0007) -[2023-10-17 01:05:16,024][62373] Updated weights for policy 0, policy_version 20570 (0.0009) -[2023-10-17 01:05:17,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 41975808. Throughput: 0: 1753.5, 1: 1758.4. Samples: 10502196. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:05:17,215][61453] Avg episode reward: [(0, '7.170'), (1, '6.270')] -[2023-10-17 01:05:17,227][62094] Saving new best policy, reward=7.170! -[2023-10-17 01:05:19,378][62408] Updated weights for policy 1, policy_version 20420 (0.0007) -[2023-10-17 01:05:19,743][62408] Updated weights for policy 1, policy_version 20430 (0.0009) -[2023-10-17 01:05:19,825][62373] Updated weights for policy 0, policy_version 20580 (0.0009) -[2023-10-17 01:05:20,114][62408] Updated weights for policy 1, policy_version 20440 (0.0008) -[2023-10-17 01:05:20,185][62373] Updated weights for policy 0, policy_version 20590 (0.0008) -[2023-10-17 01:05:20,558][62373] Updated weights for policy 0, policy_version 20600 (0.0008) -[2023-10-17 01:05:22,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 42041344. Throughput: 0: 1782.6, 1: 1771.2. Samples: 10513536. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:05:22,215][61453] Avg episode reward: [(0, '6.730'), (1, '6.050')] -[2023-10-17 01:05:23,869][62408] Updated weights for policy 1, policy_version 20450 (0.0008) -[2023-10-17 01:05:24,210][62373] Updated weights for policy 0, policy_version 20610 (0.0009) -[2023-10-17 01:05:24,232][62408] Updated weights for policy 1, policy_version 20460 (0.0010) -[2023-10-17 01:05:24,578][62373] Updated weights for policy 0, policy_version 20620 (0.0010) -[2023-10-17 01:05:24,601][62408] Updated weights for policy 1, policy_version 20470 (0.0007) -[2023-10-17 01:05:24,955][62373] Updated weights for policy 0, policy_version 20630 (0.0008) -[2023-10-17 01:05:24,965][62408] Updated weights for policy 1, policy_version 20480 (0.0008) -[2023-10-17 01:05:25,322][62373] Updated weights for policy 0, policy_version 20640 (0.0011) -[2023-10-17 01:05:27,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 42106880. Throughput: 0: 1762.2, 1: 1757.0. Samples: 10533984. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:05:27,215][61453] Avg episode reward: [(0, '6.620'), (1, '5.850')] -[2023-10-17 01:05:28,651][62408] Updated weights for policy 1, policy_version 20490 (0.0010) -[2023-10-17 01:05:29,023][62408] Updated weights for policy 1, policy_version 20500 (0.0008) -[2023-10-17 01:05:29,154][62373] Updated weights for policy 0, policy_version 20650 (0.0009) -[2023-10-17 01:05:29,389][62408] Updated weights for policy 1, policy_version 20510 (0.0009) -[2023-10-17 01:05:29,524][62373] Updated weights for policy 0, policy_version 20660 (0.0008) -[2023-10-17 01:05:29,890][62373] Updated weights for policy 0, policy_version 20670 (0.0008) -[2023-10-17 01:05:32,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 42172416. Throughput: 0: 1763.3, 1: 1757.7. Samples: 10555922. Policy #0 lag: (min: 27.0, avg: 33.3, max: 59.0) -[2023-10-17 01:05:32,215][61453] Avg episode reward: [(0, '6.350'), (1, '6.050')] -[2023-10-17 01:05:32,225][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000020512_21004288.pth... -[2023-10-17 01:05:32,226][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000020672_21168128.pth... -[2023-10-17 01:05:32,259][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000018880_19333120.pth -[2023-10-17 01:05:32,268][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000019008_19464192.pth -[2023-10-17 01:05:33,293][62408] Updated weights for policy 1, policy_version 20520 (0.0007) -[2023-10-17 01:05:33,666][62408] Updated weights for policy 1, policy_version 20530 (0.0008) -[2023-10-17 01:05:33,688][62373] Updated weights for policy 0, policy_version 20680 (0.0007) -[2023-10-17 01:05:34,034][62408] Updated weights for policy 1, policy_version 20540 (0.0009) -[2023-10-17 01:05:34,068][62373] Updated weights for policy 0, policy_version 20690 (0.0009) -[2023-10-17 01:05:34,438][62373] Updated weights for policy 0, policy_version 20700 (0.0009) -[2023-10-17 01:05:37,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 42237952. Throughput: 0: 1764.6, 1: 1755.2. Samples: 10565480. Policy #0 lag: (min: 27.0, avg: 33.3, max: 59.0) -[2023-10-17 01:05:37,215][61453] Avg episode reward: [(0, '6.320'), (1, '5.960')] -[2023-10-17 01:05:37,920][62408] Updated weights for policy 1, policy_version 20550 (0.0008) -[2023-10-17 01:05:38,289][62408] Updated weights for policy 1, policy_version 20560 (0.0007) -[2023-10-17 01:05:38,340][62373] Updated weights for policy 0, policy_version 20710 (0.0008) -[2023-10-17 01:05:38,655][62408] Updated weights for policy 1, policy_version 20570 (0.0009) -[2023-10-17 01:05:38,709][62373] Updated weights for policy 0, policy_version 20720 (0.0008) -[2023-10-17 01:05:39,081][62373] Updated weights for policy 0, policy_version 20730 (0.0008) -[2023-10-17 01:05:42,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 42303488. Throughput: 0: 1761.3, 1: 1755.3. Samples: 10587436. Policy #0 lag: (min: 27.0, avg: 33.3, max: 59.0) -[2023-10-17 01:05:42,214][61453] Avg episode reward: [(0, '6.310'), (1, '5.680')] -[2023-10-17 01:05:42,488][62408] Updated weights for policy 1, policy_version 20580 (0.0008) -[2023-10-17 01:05:42,791][62373] Updated weights for policy 0, policy_version 20740 (0.0008) -[2023-10-17 01:05:42,852][62408] Updated weights for policy 1, policy_version 20590 (0.0007) -[2023-10-17 01:05:43,166][62373] Updated weights for policy 0, policy_version 20750 (0.0008) -[2023-10-17 01:05:43,220][62408] Updated weights for policy 1, policy_version 20600 (0.0008) -[2023-10-17 01:05:43,533][62373] Updated weights for policy 0, policy_version 20760 (0.0007) -[2023-10-17 01:05:47,068][62408] Updated weights for policy 1, policy_version 20610 (0.0009) -[2023-10-17 01:05:47,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 42369024. Throughput: 0: 1787.6, 1: 1784.1. Samples: 10609514. Policy #0 lag: (min: 27.0, avg: 33.3, max: 59.0) -[2023-10-17 01:05:47,215][61453] Avg episode reward: [(0, '5.850'), (1, '5.760')] -[2023-10-17 01:05:47,261][62373] Updated weights for policy 0, policy_version 20770 (0.0007) -[2023-10-17 01:05:47,431][62408] Updated weights for policy 1, policy_version 20620 (0.0007) -[2023-10-17 01:05:47,629][62373] Updated weights for policy 0, policy_version 20780 (0.0007) -[2023-10-17 01:05:47,799][62408] Updated weights for policy 1, policy_version 20630 (0.0008) -[2023-10-17 01:05:48,004][62373] Updated weights for policy 0, policy_version 20790 (0.0009) -[2023-10-17 01:05:48,167][62408] Updated weights for policy 1, policy_version 20640 (0.0009) -[2023-10-17 01:05:48,370][62373] Updated weights for policy 0, policy_version 20800 (0.0009) -[2023-10-17 01:05:52,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 42434560. Throughput: 0: 1768.8, 1: 1748.2. Samples: 10619060. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-10-17 01:05:52,214][61453] Avg episode reward: [(0, '6.310'), (1, '6.510')] -[2023-10-17 01:05:52,254][62373] Updated weights for policy 0, policy_version 20810 (0.0009) -[2023-10-17 01:05:52,258][62408] Updated weights for policy 1, policy_version 20650 (0.0007) -[2023-10-17 01:05:52,612][62373] Updated weights for policy 0, policy_version 20820 (0.0007) -[2023-10-17 01:05:52,637][62408] Updated weights for policy 1, policy_version 20660 (0.0008) -[2023-10-17 01:05:52,991][62373] Updated weights for policy 0, policy_version 20830 (0.0007) -[2023-10-17 01:05:52,995][62408] Updated weights for policy 1, policy_version 20670 (0.0007) -[2023-10-17 01:05:56,792][62408] Updated weights for policy 1, policy_version 20680 (0.0010) -[2023-10-17 01:05:56,965][62373] Updated weights for policy 0, policy_version 20840 (0.0009) -[2023-10-17 01:05:57,158][62408] Updated weights for policy 1, policy_version 20690 (0.0007) -[2023-10-17 01:05:57,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 42500096. Throughput: 0: 1777.3, 1: 1764.9. Samples: 10640724. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-10-17 01:05:57,215][61453] Avg episode reward: [(0, '6.170'), (1, '5.940')] -[2023-10-17 01:05:57,337][62373] Updated weights for policy 0, policy_version 20850 (0.0007) -[2023-10-17 01:05:57,524][62408] Updated weights for policy 1, policy_version 20700 (0.0007) -[2023-10-17 01:05:57,702][62373] Updated weights for policy 0, policy_version 20860 (0.0007) -[2023-10-17 01:06:01,373][62408] Updated weights for policy 1, policy_version 20710 (0.0009) -[2023-10-17 01:06:01,492][62373] Updated weights for policy 0, policy_version 20870 (0.0008) -[2023-10-17 01:06:01,744][62408] Updated weights for policy 1, policy_version 20720 (0.0008) -[2023-10-17 01:06:01,854][62373] Updated weights for policy 0, policy_version 20880 (0.0009) -[2023-10-17 01:06:02,104][62408] Updated weights for policy 1, policy_version 20730 (0.0007) -[2023-10-17 01:06:02,214][61453] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13995.8). Total num frames: 42565632. Throughput: 0: 1778.5, 1: 1751.9. Samples: 10661064. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-10-17 01:06:02,214][61453] Avg episode reward: [(0, '6.480'), (1, '5.910')] -[2023-10-17 01:06:02,233][62373] Updated weights for policy 0, policy_version 20890 (0.0008) -[2023-10-17 01:06:06,076][62408] Updated weights for policy 1, policy_version 20740 (0.0008) -[2023-10-17 01:06:06,210][62373] Updated weights for policy 0, policy_version 20900 (0.0008) -[2023-10-17 01:06:06,442][62408] Updated weights for policy 1, policy_version 20750 (0.0008) -[2023-10-17 01:06:06,578][62373] Updated weights for policy 0, policy_version 20910 (0.0009) -[2023-10-17 01:06:06,807][62408] Updated weights for policy 1, policy_version 20760 (0.0007) -[2023-10-17 01:06:06,956][62373] Updated weights for policy 0, policy_version 20920 (0.0008) -[2023-10-17 01:06:07,214][61453] Fps is (10 sec: 16383.8, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 42663936. Throughput: 0: 1767.2, 1: 1758.4. Samples: 10672186. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-10-17 01:06:07,215][61453] Avg episode reward: [(0, '6.650'), (1, '6.280')] -[2023-10-17 01:06:10,695][62408] Updated weights for policy 1, policy_version 20770 (0.0008) -[2023-10-17 01:06:10,721][62373] Updated weights for policy 0, policy_version 20930 (0.0008) -[2023-10-17 01:06:11,069][62408] Updated weights for policy 1, policy_version 20780 (0.0008) -[2023-10-17 01:06:11,097][62373] Updated weights for policy 0, policy_version 20940 (0.0010) -[2023-10-17 01:06:11,435][62408] Updated weights for policy 1, policy_version 20790 (0.0008) -[2023-10-17 01:06:11,472][62373] Updated weights for policy 0, policy_version 20950 (0.0008) -[2023-10-17 01:06:11,800][62408] Updated weights for policy 1, policy_version 20800 (0.0009) -[2023-10-17 01:06:11,833][62373] Updated weights for policy 0, policy_version 20960 (0.0010) -[2023-10-17 01:06:12,214][61453] Fps is (10 sec: 19660.5, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 42762240. Throughput: 0: 1784.1, 1: 1757.1. Samples: 10693338. Policy #0 lag: (min: 9.0, avg: 18.2, max: 41.0) -[2023-10-17 01:06:12,215][61453] Avg episode reward: [(0, '6.730'), (1, '5.720')] -[2023-10-17 01:06:15,521][62408] Updated weights for policy 1, policy_version 20810 (0.0007) -[2023-10-17 01:06:15,838][62373] Updated weights for policy 0, policy_version 20970 (0.0008) -[2023-10-17 01:06:15,880][62408] Updated weights for policy 1, policy_version 20820 (0.0008) -[2023-10-17 01:06:16,210][62373] Updated weights for policy 0, policy_version 20980 (0.0007) -[2023-10-17 01:06:16,243][62408] Updated weights for policy 1, policy_version 20830 (0.0008) -[2023-10-17 01:06:16,581][62373] Updated weights for policy 0, policy_version 20990 (0.0008) -[2023-10-17 01:06:17,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 42827776. Throughput: 0: 1752.7, 1: 1737.4. Samples: 10712974. Policy #0 lag: (min: 9.0, avg: 18.2, max: 41.0) -[2023-10-17 01:06:17,215][61453] Avg episode reward: [(0, '6.660'), (1, '5.690')] -[2023-10-17 01:06:20,222][62373] Updated weights for policy 0, policy_version 21000 (0.0008) -[2023-10-17 01:06:20,242][62408] Updated weights for policy 1, policy_version 20840 (0.0007) -[2023-10-17 01:06:20,587][62373] Updated weights for policy 0, policy_version 21010 (0.0009) -[2023-10-17 01:06:20,604][62408] Updated weights for policy 1, policy_version 20850 (0.0007) -[2023-10-17 01:06:20,944][62373] Updated weights for policy 0, policy_version 21020 (0.0009) -[2023-10-17 01:06:20,969][62408] Updated weights for policy 1, policy_version 20860 (0.0008) -[2023-10-17 01:06:22,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 42893312. Throughput: 0: 1788.4, 1: 1765.0. Samples: 10725384. Policy #0 lag: (min: 9.0, avg: 18.2, max: 41.0) -[2023-10-17 01:06:22,215][61453] Avg episode reward: [(0, '6.520'), (1, '5.980')] -[2023-10-17 01:06:24,600][62373] Updated weights for policy 0, policy_version 21030 (0.0008) -[2023-10-17 01:06:24,833][62408] Updated weights for policy 1, policy_version 20870 (0.0009) -[2023-10-17 01:06:24,962][62373] Updated weights for policy 0, policy_version 21040 (0.0007) -[2023-10-17 01:06:25,197][62408] Updated weights for policy 1, policy_version 20880 (0.0008) -[2023-10-17 01:06:25,335][62373] Updated weights for policy 0, policy_version 21050 (0.0008) -[2023-10-17 01:06:25,572][62408] Updated weights for policy 1, policy_version 20890 (0.0008) -[2023-10-17 01:06:27,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 42958848. Throughput: 0: 1761.6, 1: 1735.5. Samples: 10744810. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-17 01:06:27,215][61453] Avg episode reward: [(0, '6.800'), (1, '5.750')] -[2023-10-17 01:06:29,028][62373] Updated weights for policy 0, policy_version 21060 (0.0008) -[2023-10-17 01:06:29,395][62373] Updated weights for policy 0, policy_version 21070 (0.0009) -[2023-10-17 01:06:29,559][62408] Updated weights for policy 1, policy_version 20900 (0.0009) -[2023-10-17 01:06:29,765][62373] Updated weights for policy 0, policy_version 21080 (0.0007) -[2023-10-17 01:06:29,922][62408] Updated weights for policy 1, policy_version 20910 (0.0009) -[2023-10-17 01:06:30,297][62408] Updated weights for policy 1, policy_version 20920 (0.0009) -[2023-10-17 01:06:32,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 43024384. Throughput: 0: 1761.8, 1: 1734.3. Samples: 10766838. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-17 01:06:32,215][61453] Avg episode reward: [(0, '6.470'), (1, '5.690')] -[2023-10-17 01:06:33,587][62373] Updated weights for policy 0, policy_version 21090 (0.0007) -[2023-10-17 01:06:33,953][62373] Updated weights for policy 0, policy_version 21100 (0.0007) -[2023-10-17 01:06:34,109][62408] Updated weights for policy 1, policy_version 20930 (0.0009) -[2023-10-17 01:06:34,324][62373] Updated weights for policy 0, policy_version 21110 (0.0007) -[2023-10-17 01:06:34,471][62408] Updated weights for policy 1, policy_version 20940 (0.0008) -[2023-10-17 01:06:34,694][62373] Updated weights for policy 0, policy_version 21120 (0.0009) -[2023-10-17 01:06:34,837][62408] Updated weights for policy 1, policy_version 20950 (0.0009) -[2023-10-17 01:06:35,211][62408] Updated weights for policy 1, policy_version 20960 (0.0007) -[2023-10-17 01:06:37,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 43089920. Throughput: 0: 1760.2, 1: 1745.1. Samples: 10776800. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-17 01:06:37,215][61453] Avg episode reward: [(0, '6.530'), (1, '5.820')] -[2023-10-17 01:06:38,602][62373] Updated weights for policy 0, policy_version 21130 (0.0008) -[2023-10-17 01:06:38,961][62408] Updated weights for policy 1, policy_version 20970 (0.0008) -[2023-10-17 01:06:38,975][62373] Updated weights for policy 0, policy_version 21140 (0.0007) -[2023-10-17 01:06:39,332][62408] Updated weights for policy 1, policy_version 20980 (0.0007) -[2023-10-17 01:06:39,343][62373] Updated weights for policy 0, policy_version 21150 (0.0007) -[2023-10-17 01:06:39,700][62408] Updated weights for policy 1, policy_version 20990 (0.0007) -[2023-10-17 01:06:42,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 43155456. Throughput: 0: 1766.3, 1: 1738.2. Samples: 10798426. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-17 01:06:42,215][61453] Avg episode reward: [(0, '6.530'), (1, '6.180')] -[2023-10-17 01:06:43,025][62373] Updated weights for policy 0, policy_version 21160 (0.0007) -[2023-10-17 01:06:43,391][62373] Updated weights for policy 0, policy_version 21170 (0.0007) -[2023-10-17 01:06:43,447][62408] Updated weights for policy 1, policy_version 21000 (0.0007) -[2023-10-17 01:06:43,757][62373] Updated weights for policy 0, policy_version 21180 (0.0009) -[2023-10-17 01:06:43,812][62408] Updated weights for policy 1, policy_version 21010 (0.0008) -[2023-10-17 01:06:44,187][62408] Updated weights for policy 1, policy_version 21020 (0.0008) -[2023-10-17 01:06:47,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 43220992. Throughput: 0: 1787.1, 1: 1753.9. Samples: 10820410. Policy #0 lag: (min: 14.0, avg: 14.4, max: 27.0) -[2023-10-17 01:06:47,214][61453] Avg episode reward: [(0, '6.190'), (1, '6.360')] -[2023-10-17 01:06:47,566][62373] Updated weights for policy 0, policy_version 21190 (0.0008) -[2023-10-17 01:06:47,926][62373] Updated weights for policy 0, policy_version 21200 (0.0009) -[2023-10-17 01:06:48,037][62408] Updated weights for policy 1, policy_version 21030 (0.0009) -[2023-10-17 01:06:48,298][62373] Updated weights for policy 0, policy_version 21210 (0.0008) -[2023-10-17 01:06:48,407][62408] Updated weights for policy 1, policy_version 21040 (0.0008) -[2023-10-17 01:06:48,772][62408] Updated weights for policy 1, policy_version 21050 (0.0010) -[2023-10-17 01:06:52,084][62373] Updated weights for policy 0, policy_version 21220 (0.0007) -[2023-10-17 01:06:52,214][61453] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 43286528. Throughput: 0: 1770.3, 1: 1737.1. Samples: 10830020. Policy #0 lag: (min: 14.0, avg: 14.4, max: 27.0) -[2023-10-17 01:06:52,214][61453] Avg episode reward: [(0, '6.080'), (1, '6.750')] -[2023-10-17 01:06:52,215][62252] Saving new best policy, reward=6.750! -[2023-10-17 01:06:52,453][62373] Updated weights for policy 0, policy_version 21230 (0.0007) -[2023-10-17 01:06:52,608][62408] Updated weights for policy 1, policy_version 21060 (0.0009) -[2023-10-17 01:06:52,826][62373] Updated weights for policy 0, policy_version 21240 (0.0009) -[2023-10-17 01:06:52,975][62408] Updated weights for policy 1, policy_version 21070 (0.0007) -[2023-10-17 01:06:53,339][62408] Updated weights for policy 1, policy_version 21080 (0.0007) -[2023-10-17 01:06:56,657][62373] Updated weights for policy 0, policy_version 21250 (0.0009) -[2023-10-17 01:06:57,031][62373] Updated weights for policy 0, policy_version 21260 (0.0007) -[2023-10-17 01:06:57,162][62408] Updated weights for policy 1, policy_version 21090 (0.0007) -[2023-10-17 01:06:57,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 43352064. Throughput: 0: 1778.7, 1: 1756.1. Samples: 10852404. Policy #0 lag: (min: 14.0, avg: 14.4, max: 27.0) -[2023-10-17 01:06:57,214][61453] Avg episode reward: [(0, '6.000'), (1, '6.950')] -[2023-10-17 01:06:57,397][62373] Updated weights for policy 0, policy_version 21270 (0.0008) -[2023-10-17 01:06:57,521][62408] Updated weights for policy 1, policy_version 21100 (0.0008) -[2023-10-17 01:06:57,771][62373] Updated weights for policy 0, policy_version 21280 (0.0007) -[2023-10-17 01:06:57,891][62408] Updated weights for policy 1, policy_version 21110 (0.0008) -[2023-10-17 01:06:58,253][62252] Saving new best policy, reward=6.950! -[2023-10-17 01:06:58,257][62408] Updated weights for policy 1, policy_version 21120 (0.0007) -[2023-10-17 01:07:01,725][62373] Updated weights for policy 0, policy_version 21290 (0.0009) -[2023-10-17 01:07:02,002][62408] Updated weights for policy 1, policy_version 21130 (0.0007) -[2023-10-17 01:07:02,089][62373] Updated weights for policy 0, policy_version 21300 (0.0008) -[2023-10-17 01:07:02,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 43417600. Throughput: 0: 1784.7, 1: 1778.8. Samples: 10873332. Policy #0 lag: (min: 14.0, avg: 14.4, max: 27.0) -[2023-10-17 01:07:02,215][61453] Avg episode reward: [(0, '6.420'), (1, '6.960')] -[2023-10-17 01:07:02,371][62408] Updated weights for policy 1, policy_version 21140 (0.0009) -[2023-10-17 01:07:02,462][62373] Updated weights for policy 0, policy_version 21310 (0.0007) -[2023-10-17 01:07:02,728][62408] Updated weights for policy 1, policy_version 21150 (0.0007) -[2023-10-17 01:07:02,804][62252] Saving new best policy, reward=6.960! -[2023-10-17 01:07:06,312][62373] Updated weights for policy 0, policy_version 21320 (0.0008) -[2023-10-17 01:07:06,677][62408] Updated weights for policy 1, policy_version 21160 (0.0007) -[2023-10-17 01:07:06,686][62373] Updated weights for policy 0, policy_version 21330 (0.0008) -[2023-10-17 01:07:07,047][62408] Updated weights for policy 1, policy_version 21170 (0.0007) -[2023-10-17 01:07:07,056][62373] Updated weights for policy 0, policy_version 21340 (0.0008) -[2023-10-17 01:07:07,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 43515904. Throughput: 0: 1766.2, 1: 1755.1. Samples: 10883844. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:07:07,214][61453] Avg episode reward: [(0, '6.380'), (1, '7.380')] -[2023-10-17 01:07:07,413][62408] Updated weights for policy 1, policy_version 21180 (0.0007) -[2023-10-17 01:07:07,552][62252] Saving new best policy, reward=7.380! -[2023-10-17 01:07:10,821][62373] Updated weights for policy 0, policy_version 21350 (0.0009) -[2023-10-17 01:07:11,199][62373] Updated weights for policy 0, policy_version 21360 (0.0008) -[2023-10-17 01:07:11,427][62408] Updated weights for policy 1, policy_version 21190 (0.0010) -[2023-10-17 01:07:11,566][62373] Updated weights for policy 0, policy_version 21370 (0.0008) -[2023-10-17 01:07:11,791][62408] Updated weights for policy 1, policy_version 21200 (0.0009) -[2023-10-17 01:07:12,156][62408] Updated weights for policy 1, policy_version 21210 (0.0008) -[2023-10-17 01:07:12,214][61453] Fps is (10 sec: 16384.2, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 43581440. Throughput: 0: 1786.2, 1: 1779.2. Samples: 10905252. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:07:12,215][61453] Avg episode reward: [(0, '6.340'), (1, '6.730')] -[2023-10-17 01:07:15,168][62373] Updated weights for policy 0, policy_version 21380 (0.0008) -[2023-10-17 01:07:15,539][62373] Updated weights for policy 0, policy_version 21390 (0.0007) -[2023-10-17 01:07:15,915][62373] Updated weights for policy 0, policy_version 21400 (0.0010) -[2023-10-17 01:07:16,126][62408] Updated weights for policy 1, policy_version 21220 (0.0007) -[2023-10-17 01:07:16,486][62408] Updated weights for policy 1, policy_version 21230 (0.0007) -[2023-10-17 01:07:16,849][62408] Updated weights for policy 1, policy_version 21240 (0.0008) -[2023-10-17 01:07:17,214][61453] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 43679744. Throughput: 0: 1768.1, 1: 1753.1. Samples: 10925290. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:07:17,215][61453] Avg episode reward: [(0, '6.860'), (1, '6.570')] -[2023-10-17 01:07:19,743][62373] Updated weights for policy 0, policy_version 21410 (0.0008) -[2023-10-17 01:07:20,114][62373] Updated weights for policy 0, policy_version 21420 (0.0009) -[2023-10-17 01:07:20,491][62373] Updated weights for policy 0, policy_version 21430 (0.0011) -[2023-10-17 01:07:20,762][62408] Updated weights for policy 1, policy_version 21250 (0.0010) -[2023-10-17 01:07:20,851][62373] Updated weights for policy 0, policy_version 21440 (0.0010) -[2023-10-17 01:07:21,122][62408] Updated weights for policy 1, policy_version 21260 (0.0009) -[2023-10-17 01:07:21,495][62408] Updated weights for policy 1, policy_version 21270 (0.0011) -[2023-10-17 01:07:21,869][62408] Updated weights for policy 1, policy_version 21280 (0.0011) -[2023-10-17 01:07:22,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 43745280. Throughput: 0: 1793.2, 1: 1768.8. Samples: 10937092. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:07:22,215][61453] Avg episode reward: [(0, '6.490'), (1, '6.180')] -[2023-10-17 01:07:24,564][62373] Updated weights for policy 0, policy_version 21450 (0.0008) -[2023-10-17 01:07:24,929][62373] Updated weights for policy 0, policy_version 21460 (0.0009) -[2023-10-17 01:07:25,299][62373] Updated weights for policy 0, policy_version 21470 (0.0007) -[2023-10-17 01:07:25,733][62408] Updated weights for policy 1, policy_version 21290 (0.0010) -[2023-10-17 01:07:26,096][62408] Updated weights for policy 1, policy_version 21300 (0.0007) -[2023-10-17 01:07:26,462][62408] Updated weights for policy 1, policy_version 21310 (0.0007) -[2023-10-17 01:07:27,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 43810816. Throughput: 0: 1770.6, 1: 1762.5. Samples: 10957412. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:07:27,215][61453] Avg episode reward: [(0, '6.660'), (1, '6.600')] -[2023-10-17 01:07:29,218][62373] Updated weights for policy 0, policy_version 21480 (0.0008) -[2023-10-17 01:07:29,582][62373] Updated weights for policy 0, policy_version 21490 (0.0009) -[2023-10-17 01:07:29,960][62373] Updated weights for policy 0, policy_version 21500 (0.0008) -[2023-10-17 01:07:30,316][62408] Updated weights for policy 1, policy_version 21320 (0.0008) -[2023-10-17 01:07:30,688][62408] Updated weights for policy 1, policy_version 21330 (0.0011) -[2023-10-17 01:07:31,069][62408] Updated weights for policy 1, policy_version 21340 (0.0010) -[2023-10-17 01:07:32,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 43876352. Throughput: 0: 1772.3, 1: 1737.0. Samples: 10978326. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:07:32,215][61453] Avg episode reward: [(0, '6.620'), (1, '5.650')] -[2023-10-17 01:07:32,230][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000021344_21856256.pth... -[2023-10-17 01:07:32,230][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000021504_22020096.pth... -[2023-10-17 01:07:32,267][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000019712_20185088.pth -[2023-10-17 01:07:32,267][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000019840_20316160.pth -[2023-10-17 01:07:33,818][62373] Updated weights for policy 0, policy_version 21510 (0.0007) -[2023-10-17 01:07:34,189][62373] Updated weights for policy 0, policy_version 21520 (0.0008) -[2023-10-17 01:07:34,561][62373] Updated weights for policy 0, policy_version 21530 (0.0010) -[2023-10-17 01:07:34,947][62408] Updated weights for policy 1, policy_version 21350 (0.0009) -[2023-10-17 01:07:35,315][62408] Updated weights for policy 1, policy_version 21360 (0.0010) -[2023-10-17 01:07:35,683][62408] Updated weights for policy 1, policy_version 21370 (0.0010) -[2023-10-17 01:07:37,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 43941888. Throughput: 0: 1769.2, 1: 1765.5. Samples: 10989082. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:07:37,214][61453] Avg episode reward: [(0, '6.570'), (1, '6.080')] -[2023-10-17 01:07:38,329][62373] Updated weights for policy 0, policy_version 21540 (0.0007) -[2023-10-17 01:07:38,699][62373] Updated weights for policy 0, policy_version 21550 (0.0008) -[2023-10-17 01:07:39,058][62373] Updated weights for policy 0, policy_version 21560 (0.0010) -[2023-10-17 01:07:39,691][62408] Updated weights for policy 1, policy_version 21380 (0.0008) -[2023-10-17 01:07:40,059][62408] Updated weights for policy 1, policy_version 21390 (0.0007) -[2023-10-17 01:07:40,422][62408] Updated weights for policy 1, policy_version 21400 (0.0008) -[2023-10-17 01:07:42,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 44007424. Throughput: 0: 1765.9, 1: 1732.1. Samples: 11009814. Policy #0 lag: (min: 3.0, avg: 3.2, max: 13.0) -[2023-10-17 01:07:42,215][61453] Avg episode reward: [(0, '6.740'), (1, '6.880')] -[2023-10-17 01:07:42,809][62373] Updated weights for policy 0, policy_version 21570 (0.0008) -[2023-10-17 01:07:43,181][62373] Updated weights for policy 0, policy_version 21580 (0.0009) -[2023-10-17 01:07:43,552][62373] Updated weights for policy 0, policy_version 21590 (0.0008) -[2023-10-17 01:07:43,920][62373] Updated weights for policy 0, policy_version 21600 (0.0009) -[2023-10-17 01:07:44,077][62408] Updated weights for policy 1, policy_version 21410 (0.0010) -[2023-10-17 01:07:44,453][62408] Updated weights for policy 1, policy_version 21420 (0.0008) -[2023-10-17 01:07:44,816][62408] Updated weights for policy 1, policy_version 21430 (0.0007) -[2023-10-17 01:07:45,190][62408] Updated weights for policy 1, policy_version 21440 (0.0008) -[2023-10-17 01:07:47,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 44072960. Throughput: 0: 1798.7, 1: 1737.7. Samples: 11032472. Policy #0 lag: (min: 3.0, avg: 3.2, max: 13.0) -[2023-10-17 01:07:47,215][61453] Avg episode reward: [(0, '6.760'), (1, '7.020')] -[2023-10-17 01:07:47,645][62373] Updated weights for policy 0, policy_version 21610 (0.0007) -[2023-10-17 01:07:48,010][62373] Updated weights for policy 0, policy_version 21620 (0.0008) -[2023-10-17 01:07:48,394][62373] Updated weights for policy 0, policy_version 21630 (0.0010) -[2023-10-17 01:07:48,946][62408] Updated weights for policy 1, policy_version 21450 (0.0009) -[2023-10-17 01:07:49,313][62408] Updated weights for policy 1, policy_version 21460 (0.0007) -[2023-10-17 01:07:49,679][62408] Updated weights for policy 1, policy_version 21470 (0.0007) -[2023-10-17 01:07:52,149][62373] Updated weights for policy 0, policy_version 21640 (0.0008) -[2023-10-17 01:07:52,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 44138496. Throughput: 0: 1783.2, 1: 1733.4. Samples: 11042094. Policy #0 lag: (min: 3.0, avg: 3.2, max: 13.0) -[2023-10-17 01:07:52,215][61453] Avg episode reward: [(0, '6.830'), (1, '6.630')] -[2023-10-17 01:07:52,517][62373] Updated weights for policy 0, policy_version 21650 (0.0009) -[2023-10-17 01:07:52,896][62373] Updated weights for policy 0, policy_version 21660 (0.0010) -[2023-10-17 01:07:53,562][62408] Updated weights for policy 1, policy_version 21480 (0.0008) -[2023-10-17 01:07:53,925][62408] Updated weights for policy 1, policy_version 21490 (0.0010) -[2023-10-17 01:07:54,289][62408] Updated weights for policy 1, policy_version 21500 (0.0008) -[2023-10-17 01:07:56,668][62373] Updated weights for policy 0, policy_version 21670 (0.0009) -[2023-10-17 01:07:57,045][62373] Updated weights for policy 0, policy_version 21680 (0.0008) -[2023-10-17 01:07:57,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 44204032. Throughput: 0: 1793.7, 1: 1737.7. Samples: 11064166. Policy #0 lag: (min: 3.0, avg: 3.2, max: 13.0) -[2023-10-17 01:07:57,215][61453] Avg episode reward: [(0, '6.950'), (1, '6.590')] -[2023-10-17 01:07:57,414][62373] Updated weights for policy 0, policy_version 21690 (0.0008) -[2023-10-17 01:07:58,067][62408] Updated weights for policy 1, policy_version 21510 (0.0008) -[2023-10-17 01:07:58,438][62408] Updated weights for policy 1, policy_version 21520 (0.0011) -[2023-10-17 01:07:58,793][62408] Updated weights for policy 1, policy_version 21530 (0.0007) -[2023-10-17 01:08:01,277][62373] Updated weights for policy 0, policy_version 21700 (0.0009) -[2023-10-17 01:08:01,657][62373] Updated weights for policy 0, policy_version 21710 (0.0008) -[2023-10-17 01:08:02,030][62373] Updated weights for policy 0, policy_version 21720 (0.0009) -[2023-10-17 01:08:02,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 44269568. Throughput: 0: 1789.6, 1: 1765.2. Samples: 11085254. Policy #0 lag: (min: 31.0, avg: 33.0, max: 62.0) -[2023-10-17 01:08:02,215][61453] Avg episode reward: [(0, '6.550'), (1, '6.540')] -[2023-10-17 01:08:02,678][62408] Updated weights for policy 1, policy_version 21540 (0.0008) -[2023-10-17 01:08:03,040][62408] Updated weights for policy 1, policy_version 21550 (0.0009) -[2023-10-17 01:08:03,412][62408] Updated weights for policy 1, policy_version 21560 (0.0010) -[2023-10-17 01:08:05,869][62373] Updated weights for policy 0, policy_version 21730 (0.0010) -[2023-10-17 01:08:06,241][62373] Updated weights for policy 0, policy_version 21740 (0.0010) -[2023-10-17 01:08:06,613][62373] Updated weights for policy 0, policy_version 21750 (0.0010) -[2023-10-17 01:08:06,986][62373] Updated weights for policy 0, policy_version 21760 (0.0009) -[2023-10-17 01:08:07,179][62408] Updated weights for policy 1, policy_version 21570 (0.0010) -[2023-10-17 01:08:07,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 44367872. Throughput: 0: 1781.7, 1: 1742.0. Samples: 11095662. Policy #0 lag: (min: 31.0, avg: 33.0, max: 62.0) -[2023-10-17 01:08:07,215][61453] Avg episode reward: [(0, '6.830'), (1, '5.880')] -[2023-10-17 01:08:07,540][62408] Updated weights for policy 1, policy_version 21580 (0.0008) -[2023-10-17 01:08:07,904][62408] Updated weights for policy 1, policy_version 21590 (0.0009) -[2023-10-17 01:08:08,275][62408] Updated weights for policy 1, policy_version 21600 (0.0007) -[2023-10-17 01:08:10,736][62373] Updated weights for policy 0, policy_version 21770 (0.0009) -[2023-10-17 01:08:11,099][62373] Updated weights for policy 0, policy_version 21780 (0.0010) -[2023-10-17 01:08:11,477][62373] Updated weights for policy 0, policy_version 21790 (0.0008) -[2023-10-17 01:08:12,054][62408] Updated weights for policy 1, policy_version 21610 (0.0010) -[2023-10-17 01:08:12,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 44433408. Throughput: 0: 1788.4, 1: 1760.9. Samples: 11117132. Policy #0 lag: (min: 31.0, avg: 33.0, max: 62.0) -[2023-10-17 01:08:12,215][61453] Avg episode reward: [(0, '6.780'), (1, '5.840')] -[2023-10-17 01:08:12,429][62408] Updated weights for policy 1, policy_version 21620 (0.0009) -[2023-10-17 01:08:12,795][62408] Updated weights for policy 1, policy_version 21630 (0.0009) -[2023-10-17 01:08:15,243][62373] Updated weights for policy 0, policy_version 21800 (0.0009) -[2023-10-17 01:08:15,616][62373] Updated weights for policy 0, policy_version 21810 (0.0008) -[2023-10-17 01:08:15,977][62373] Updated weights for policy 0, policy_version 21820 (0.0008) -[2023-10-17 01:08:16,649][62408] Updated weights for policy 1, policy_version 21640 (0.0009) -[2023-10-17 01:08:17,011][62408] Updated weights for policy 1, policy_version 21650 (0.0008) -[2023-10-17 01:08:17,214][61453] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 44498944. Throughput: 0: 1772.6, 1: 1777.7. Samples: 11138088. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:08:17,214][61453] Avg episode reward: [(0, '6.670'), (1, '6.020')] -[2023-10-17 01:08:17,388][62408] Updated weights for policy 1, policy_version 21660 (0.0008) -[2023-10-17 01:08:19,797][62373] Updated weights for policy 0, policy_version 21830 (0.0008) -[2023-10-17 01:08:20,165][62373] Updated weights for policy 0, policy_version 21840 (0.0007) -[2023-10-17 01:08:20,549][62373] Updated weights for policy 0, policy_version 21850 (0.0010) -[2023-10-17 01:08:21,371][62408] Updated weights for policy 1, policy_version 21670 (0.0009) -[2023-10-17 01:08:21,739][62408] Updated weights for policy 1, policy_version 21680 (0.0007) -[2023-10-17 01:08:22,119][62408] Updated weights for policy 1, policy_version 21690 (0.0008) -[2023-10-17 01:08:22,214][61453] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 44564480. Throughput: 0: 1799.9, 1: 1760.2. Samples: 11149286. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:08:22,215][61453] Avg episode reward: [(0, '6.610'), (1, '6.410')] -[2023-10-17 01:08:24,296][62373] Updated weights for policy 0, policy_version 21860 (0.0011) -[2023-10-17 01:08:24,672][62373] Updated weights for policy 0, policy_version 21870 (0.0008) -[2023-10-17 01:08:25,050][62373] Updated weights for policy 0, policy_version 21880 (0.0010) -[2023-10-17 01:08:25,880][62408] Updated weights for policy 1, policy_version 21700 (0.0008) -[2023-10-17 01:08:26,254][62408] Updated weights for policy 1, policy_version 21710 (0.0011) -[2023-10-17 01:08:26,627][62408] Updated weights for policy 1, policy_version 21720 (0.0008) -[2023-10-17 01:08:27,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 44662784. Throughput: 0: 1776.7, 1: 1783.4. Samples: 11170018. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:08:27,215][61453] Avg episode reward: [(0, '6.860'), (1, '6.710')] -[2023-10-17 01:08:28,811][62373] Updated weights for policy 0, policy_version 21890 (0.0010) -[2023-10-17 01:08:29,179][62373] Updated weights for policy 0, policy_version 21900 (0.0009) -[2023-10-17 01:08:29,548][62373] Updated weights for policy 0, policy_version 21910 (0.0008) -[2023-10-17 01:08:29,910][62373] Updated weights for policy 0, policy_version 21920 (0.0009) -[2023-10-17 01:08:30,332][62408] Updated weights for policy 1, policy_version 21730 (0.0008) -[2023-10-17 01:08:30,692][62408] Updated weights for policy 1, policy_version 21740 (0.0009) -[2023-10-17 01:08:31,055][62408] Updated weights for policy 1, policy_version 21750 (0.0009) -[2023-10-17 01:08:31,423][62408] Updated weights for policy 1, policy_version 21760 (0.0008) -[2023-10-17 01:08:32,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 44728320. Throughput: 0: 1772.3, 1: 1754.6. Samples: 11191182. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:08:32,215][61453] Avg episode reward: [(0, '6.770'), (1, '6.600')] -[2023-10-17 01:08:33,872][62373] Updated weights for policy 0, policy_version 21930 (0.0007) -[2023-10-17 01:08:34,244][62373] Updated weights for policy 0, policy_version 21940 (0.0009) -[2023-10-17 01:08:34,616][62373] Updated weights for policy 0, policy_version 21950 (0.0008) -[2023-10-17 01:08:35,212][62408] Updated weights for policy 1, policy_version 21770 (0.0008) -[2023-10-17 01:08:35,575][62408] Updated weights for policy 1, policy_version 21780 (0.0008) -[2023-10-17 01:08:35,943][62408] Updated weights for policy 1, policy_version 21790 (0.0010) -[2023-10-17 01:08:37,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 44793856. Throughput: 0: 1766.2, 1: 1788.0. Samples: 11202034. Policy #0 lag: (min: 1.0, avg: 13.9, max: 33.0) -[2023-10-17 01:08:37,215][61453] Avg episode reward: [(0, '6.710'), (1, '6.630')] -[2023-10-17 01:08:38,515][62373] Updated weights for policy 0, policy_version 21960 (0.0007) -[2023-10-17 01:08:38,878][62373] Updated weights for policy 0, policy_version 21970 (0.0008) -[2023-10-17 01:08:39,249][62373] Updated weights for policy 0, policy_version 21980 (0.0007) -[2023-10-17 01:08:39,842][62408] Updated weights for policy 1, policy_version 21800 (0.0008) -[2023-10-17 01:08:40,212][62408] Updated weights for policy 1, policy_version 21810 (0.0008) -[2023-10-17 01:08:40,578][62408] Updated weights for policy 1, policy_version 21820 (0.0009) -[2023-10-17 01:08:42,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 44859392. Throughput: 0: 1762.0, 1: 1758.7. Samples: 11222598. Policy #0 lag: (min: 1.0, avg: 13.9, max: 33.0) -[2023-10-17 01:08:42,215][61453] Avg episode reward: [(0, '6.730'), (1, '6.340')] -[2023-10-17 01:08:42,993][62373] Updated weights for policy 0, policy_version 21990 (0.0007) -[2023-10-17 01:08:43,356][62373] Updated weights for policy 0, policy_version 22000 (0.0007) -[2023-10-17 01:08:43,729][62373] Updated weights for policy 0, policy_version 22010 (0.0009) -[2023-10-17 01:08:44,243][62408] Updated weights for policy 1, policy_version 21830 (0.0008) -[2023-10-17 01:08:44,605][62408] Updated weights for policy 1, policy_version 21840 (0.0008) -[2023-10-17 01:08:44,980][62408] Updated weights for policy 1, policy_version 21850 (0.0010) -[2023-10-17 01:08:47,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 44924928. Throughput: 0: 1786.8, 1: 1761.2. Samples: 11244914. Policy #0 lag: (min: 1.0, avg: 13.9, max: 33.0) -[2023-10-17 01:08:47,214][61453] Avg episode reward: [(0, '6.940'), (1, '6.450')] -[2023-10-17 01:08:47,478][62373] Updated weights for policy 0, policy_version 22020 (0.0008) -[2023-10-17 01:08:47,843][62373] Updated weights for policy 0, policy_version 22030 (0.0008) -[2023-10-17 01:08:48,213][62373] Updated weights for policy 0, policy_version 22040 (0.0009) -[2023-10-17 01:08:48,963][62408] Updated weights for policy 1, policy_version 21860 (0.0008) -[2023-10-17 01:08:49,325][62408] Updated weights for policy 1, policy_version 21870 (0.0008) -[2023-10-17 01:08:49,692][62408] Updated weights for policy 1, policy_version 21880 (0.0008) -[2023-10-17 01:08:51,930][62373] Updated weights for policy 0, policy_version 22050 (0.0009) -[2023-10-17 01:08:52,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 44990464. Throughput: 0: 1768.4, 1: 1765.3. Samples: 11254676. Policy #0 lag: (min: 1.0, avg: 13.9, max: 33.0) -[2023-10-17 01:08:52,215][61453] Avg episode reward: [(0, '6.840'), (1, '6.080')] -[2023-10-17 01:08:52,315][62373] Updated weights for policy 0, policy_version 22060 (0.0007) -[2023-10-17 01:08:52,686][62373] Updated weights for policy 0, policy_version 22070 (0.0011) -[2023-10-17 01:08:53,050][62373] Updated weights for policy 0, policy_version 22080 (0.0009) -[2023-10-17 01:08:53,606][62408] Updated weights for policy 1, policy_version 21890 (0.0009) -[2023-10-17 01:08:53,974][62408] Updated weights for policy 1, policy_version 21900 (0.0011) -[2023-10-17 01:08:54,341][62408] Updated weights for policy 1, policy_version 21910 (0.0010) -[2023-10-17 01:08:54,709][62408] Updated weights for policy 1, policy_version 21920 (0.0008) -[2023-10-17 01:08:57,055][62373] Updated weights for policy 0, policy_version 22090 (0.0008) -[2023-10-17 01:08:57,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 45056000. Throughput: 0: 1779.9, 1: 1760.6. Samples: 11276456. Policy #0 lag: (min: 11.0, avg: 11.1, max: 16.0) -[2023-10-17 01:08:57,215][61453] Avg episode reward: [(0, '6.360'), (1, '6.120')] -[2023-10-17 01:08:57,427][62373] Updated weights for policy 0, policy_version 22100 (0.0009) -[2023-10-17 01:08:57,799][62373] Updated weights for policy 0, policy_version 22110 (0.0007) -[2023-10-17 01:08:58,509][62408] Updated weights for policy 1, policy_version 21930 (0.0009) -[2023-10-17 01:08:58,873][62408] Updated weights for policy 1, policy_version 21940 (0.0007) -[2023-10-17 01:08:59,245][62408] Updated weights for policy 1, policy_version 21950 (0.0009) -[2023-10-17 01:09:01,630][62373] Updated weights for policy 0, policy_version 22120 (0.0008) -[2023-10-17 01:09:01,992][62373] Updated weights for policy 0, policy_version 22130 (0.0007) -[2023-10-17 01:09:02,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 45121536. Throughput: 0: 1771.9, 1: 1771.6. Samples: 11297546. Policy #0 lag: (min: 11.0, avg: 11.1, max: 16.0) -[2023-10-17 01:09:02,215][61453] Avg episode reward: [(0, '6.580'), (1, '6.160')] -[2023-10-17 01:09:02,365][62373] Updated weights for policy 0, policy_version 22140 (0.0007) -[2023-10-17 01:09:03,113][62408] Updated weights for policy 1, policy_version 21960 (0.0010) -[2023-10-17 01:09:03,475][62408] Updated weights for policy 1, policy_version 21970 (0.0011) -[2023-10-17 01:09:03,850][62408] Updated weights for policy 1, policy_version 21980 (0.0009) -[2023-10-17 01:09:06,103][62373] Updated weights for policy 0, policy_version 22150 (0.0009) -[2023-10-17 01:09:06,483][62373] Updated weights for policy 0, policy_version 22160 (0.0009) -[2023-10-17 01:09:06,842][62373] Updated weights for policy 0, policy_version 22170 (0.0011) -[2023-10-17 01:09:07,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 45219840. Throughput: 0: 1768.2, 1: 1757.0. Samples: 11307918. Policy #0 lag: (min: 11.0, avg: 11.1, max: 16.0) -[2023-10-17 01:09:07,215][61453] Avg episode reward: [(0, '6.500'), (1, '5.960')] -[2023-10-17 01:09:07,740][62408] Updated weights for policy 1, policy_version 21990 (0.0008) -[2023-10-17 01:09:08,097][62408] Updated weights for policy 1, policy_version 22000 (0.0011) -[2023-10-17 01:09:08,475][62408] Updated weights for policy 1, policy_version 22010 (0.0007) -[2023-10-17 01:09:10,595][62373] Updated weights for policy 0, policy_version 22180 (0.0008) -[2023-10-17 01:09:10,969][62373] Updated weights for policy 0, policy_version 22190 (0.0008) -[2023-10-17 01:09:11,338][62373] Updated weights for policy 0, policy_version 22200 (0.0009) -[2023-10-17 01:09:12,130][62408] Updated weights for policy 1, policy_version 22020 (0.0008) -[2023-10-17 01:09:12,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 45285376. Throughput: 0: 1781.2, 1: 1764.6. Samples: 11329576. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:09:12,214][61453] Avg episode reward: [(0, '6.650'), (1, '6.290')] -[2023-10-17 01:09:12,505][62408] Updated weights for policy 1, policy_version 22030 (0.0008) -[2023-10-17 01:09:12,865][62408] Updated weights for policy 1, policy_version 22040 (0.0009) -[2023-10-17 01:09:15,090][62373] Updated weights for policy 0, policy_version 22210 (0.0008) -[2023-10-17 01:09:15,457][62373] Updated weights for policy 0, policy_version 22220 (0.0009) -[2023-10-17 01:09:15,831][62373] Updated weights for policy 0, policy_version 22230 (0.0009) -[2023-10-17 01:09:16,190][62373] Updated weights for policy 0, policy_version 22240 (0.0009) -[2023-10-17 01:09:16,727][62408] Updated weights for policy 1, policy_version 22050 (0.0008) -[2023-10-17 01:09:17,096][62408] Updated weights for policy 1, policy_version 22060 (0.0011) -[2023-10-17 01:09:17,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 45350912. Throughput: 0: 1757.3, 1: 1786.0. Samples: 11350634. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:09:17,215][61453] Avg episode reward: [(0, '6.140'), (1, '5.720')] -[2023-10-17 01:09:17,461][62408] Updated weights for policy 1, policy_version 22070 (0.0008) -[2023-10-17 01:09:17,833][62408] Updated weights for policy 1, policy_version 22080 (0.0007) -[2023-10-17 01:09:20,078][62373] Updated weights for policy 0, policy_version 22250 (0.0009) -[2023-10-17 01:09:20,445][62373] Updated weights for policy 0, policy_version 22260 (0.0010) -[2023-10-17 01:09:20,816][62373] Updated weights for policy 0, policy_version 22270 (0.0008) -[2023-10-17 01:09:21,690][62408] Updated weights for policy 1, policy_version 22090 (0.0008) -[2023-10-17 01:09:22,064][62408] Updated weights for policy 1, policy_version 22100 (0.0009) -[2023-10-17 01:09:22,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 45416448. Throughput: 0: 1785.3, 1: 1759.5. Samples: 11361548. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:09:22,214][61453] Avg episode reward: [(0, '6.710'), (1, '5.700')] -[2023-10-17 01:09:22,431][62408] Updated weights for policy 1, policy_version 22110 (0.0007) -[2023-10-17 01:09:24,687][62373] Updated weights for policy 0, policy_version 22280 (0.0008) -[2023-10-17 01:09:25,068][62373] Updated weights for policy 0, policy_version 22290 (0.0007) -[2023-10-17 01:09:25,429][62373] Updated weights for policy 0, policy_version 22300 (0.0007) -[2023-10-17 01:09:26,170][62408] Updated weights for policy 1, policy_version 22120 (0.0010) -[2023-10-17 01:09:26,541][62408] Updated weights for policy 1, policy_version 22130 (0.0010) -[2023-10-17 01:09:26,916][62408] Updated weights for policy 1, policy_version 22140 (0.0009) -[2023-10-17 01:09:27,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 45514752. Throughput: 0: 1760.1, 1: 1793.7. Samples: 11382518. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:09:27,215][61453] Avg episode reward: [(0, '7.090'), (1, '5.940')] -[2023-10-17 01:09:29,156][62373] Updated weights for policy 0, policy_version 22310 (0.0008) -[2023-10-17 01:09:29,528][62373] Updated weights for policy 0, policy_version 22320 (0.0008) -[2023-10-17 01:09:29,900][62373] Updated weights for policy 0, policy_version 22330 (0.0009) -[2023-10-17 01:09:30,731][62408] Updated weights for policy 1, policy_version 22150 (0.0009) -[2023-10-17 01:09:31,092][62408] Updated weights for policy 1, policy_version 22160 (0.0011) -[2023-10-17 01:09:31,456][62408] Updated weights for policy 1, policy_version 22170 (0.0009) -[2023-10-17 01:09:32,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 45580288. Throughput: 0: 1761.9, 1: 1763.5. Samples: 11403554. Policy #0 lag: (min: 26.0, avg: 29.8, max: 58.0) -[2023-10-17 01:09:32,215][61453] Avg episode reward: [(0, '7.000'), (1, '6.300')] -[2023-10-17 01:09:32,225][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000022336_22872064.pth... -[2023-10-17 01:09:32,225][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000022176_22708224.pth... -[2023-10-17 01:09:32,262][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000020672_21168128.pth -[2023-10-17 01:09:32,263][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000020512_21004288.pth -[2023-10-17 01:09:33,853][62373] Updated weights for policy 0, policy_version 22340 (0.0009) -[2023-10-17 01:09:34,209][62373] Updated weights for policy 0, policy_version 22350 (0.0010) -[2023-10-17 01:09:34,581][62373] Updated weights for policy 0, policy_version 22360 (0.0008) -[2023-10-17 01:09:35,253][62408] Updated weights for policy 1, policy_version 22180 (0.0007) -[2023-10-17 01:09:35,623][62408] Updated weights for policy 1, policy_version 22190 (0.0007) -[2023-10-17 01:09:35,986][62408] Updated weights for policy 1, policy_version 22200 (0.0010) -[2023-10-17 01:09:37,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 45645824. Throughput: 0: 1758.2, 1: 1791.9. Samples: 11414430. Policy #0 lag: (min: 26.0, avg: 29.8, max: 58.0) -[2023-10-17 01:09:37,214][61453] Avg episode reward: [(0, '7.030'), (1, '5.890')] -[2023-10-17 01:09:38,338][62373] Updated weights for policy 0, policy_version 22370 (0.0007) -[2023-10-17 01:09:38,713][62373] Updated weights for policy 0, policy_version 22380 (0.0008) -[2023-10-17 01:09:39,088][62373] Updated weights for policy 0, policy_version 22390 (0.0009) -[2023-10-17 01:09:39,454][62373] Updated weights for policy 0, policy_version 22400 (0.0007) -[2023-10-17 01:09:39,709][62408] Updated weights for policy 1, policy_version 22210 (0.0011) -[2023-10-17 01:09:40,076][62408] Updated weights for policy 1, policy_version 22220 (0.0009) -[2023-10-17 01:09:40,450][62408] Updated weights for policy 1, policy_version 22230 (0.0011) -[2023-10-17 01:09:40,820][62408] Updated weights for policy 1, policy_version 22240 (0.0009) -[2023-10-17 01:09:42,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 45711360. Throughput: 0: 1767.1, 1: 1769.6. Samples: 11435608. Policy #0 lag: (min: 26.0, avg: 29.8, max: 58.0) -[2023-10-17 01:09:42,215][61453] Avg episode reward: [(0, '7.330'), (1, '6.080')] -[2023-10-17 01:09:42,215][62094] Saving new best policy, reward=7.330! -[2023-10-17 01:09:43,182][62373] Updated weights for policy 0, policy_version 22410 (0.0007) -[2023-10-17 01:09:43,559][62373] Updated weights for policy 0, policy_version 22420 (0.0009) -[2023-10-17 01:09:43,926][62373] Updated weights for policy 0, policy_version 22430 (0.0009) -[2023-10-17 01:09:44,560][62408] Updated weights for policy 1, policy_version 22250 (0.0008) -[2023-10-17 01:09:44,940][62408] Updated weights for policy 1, policy_version 22260 (0.0010) -[2023-10-17 01:09:45,312][62408] Updated weights for policy 1, policy_version 22270 (0.0007) -[2023-10-17 01:09:47,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 45776896. Throughput: 0: 1787.0, 1: 1773.7. Samples: 11457776. Policy #0 lag: (min: 26.0, avg: 29.8, max: 58.0) -[2023-10-17 01:09:47,215][61453] Avg episode reward: [(0, '7.450'), (1, '6.790')] -[2023-10-17 01:09:47,226][62094] Saving new best policy, reward=7.450! -[2023-10-17 01:09:47,770][62373] Updated weights for policy 0, policy_version 22440 (0.0008) -[2023-10-17 01:09:48,135][62373] Updated weights for policy 0, policy_version 22450 (0.0007) -[2023-10-17 01:09:48,506][62373] Updated weights for policy 0, policy_version 22460 (0.0010) -[2023-10-17 01:09:49,170][62408] Updated weights for policy 1, policy_version 22280 (0.0007) -[2023-10-17 01:09:49,540][62408] Updated weights for policy 1, policy_version 22290 (0.0008) -[2023-10-17 01:09:49,903][62408] Updated weights for policy 1, policy_version 22300 (0.0011) -[2023-10-17 01:09:52,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 45842432. Throughput: 0: 1768.2, 1: 1781.1. Samples: 11467636. Policy #0 lag: (min: 31.0, avg: 32.8, max: 60.0) -[2023-10-17 01:09:52,215][61453] Avg episode reward: [(0, '7.490'), (1, '6.160')] -[2023-10-17 01:09:52,303][62373] Updated weights for policy 0, policy_version 22470 (0.0010) -[2023-10-17 01:09:52,677][62373] Updated weights for policy 0, policy_version 22480 (0.0011) -[2023-10-17 01:09:53,052][62373] Updated weights for policy 0, policy_version 22490 (0.0011) -[2023-10-17 01:09:53,270][62094] Saving new best policy, reward=7.490! -[2023-10-17 01:09:53,814][62408] Updated weights for policy 1, policy_version 22310 (0.0011) -[2023-10-17 01:09:54,178][62408] Updated weights for policy 1, policy_version 22320 (0.0010) -[2023-10-17 01:09:54,551][62408] Updated weights for policy 1, policy_version 22330 (0.0010) -[2023-10-17 01:09:56,782][62373] Updated weights for policy 0, policy_version 22500 (0.0009) -[2023-10-17 01:09:57,156][62373] Updated weights for policy 0, policy_version 22510 (0.0009) -[2023-10-17 01:09:57,214][61453] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 45907968. Throughput: 0: 1781.6, 1: 1772.3. Samples: 11489500. Policy #0 lag: (min: 31.0, avg: 32.8, max: 60.0) -[2023-10-17 01:09:57,214][61453] Avg episode reward: [(0, '7.370'), (1, '6.470')] -[2023-10-17 01:09:57,519][62373] Updated weights for policy 0, policy_version 22520 (0.0009) -[2023-10-17 01:09:58,354][62408] Updated weights for policy 1, policy_version 22340 (0.0008) -[2023-10-17 01:09:58,728][62408] Updated weights for policy 1, policy_version 22350 (0.0011) -[2023-10-17 01:09:59,097][62408] Updated weights for policy 1, policy_version 22360 (0.0010) -[2023-10-17 01:10:01,209][62373] Updated weights for policy 0, policy_version 22530 (0.0008) -[2023-10-17 01:10:01,586][62373] Updated weights for policy 0, policy_version 22540 (0.0007) -[2023-10-17 01:10:01,962][62373] Updated weights for policy 0, policy_version 22550 (0.0008) -[2023-10-17 01:10:02,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 45973504. Throughput: 0: 1783.8, 1: 1783.2. Samples: 11511150. Policy #0 lag: (min: 31.0, avg: 32.8, max: 60.0) -[2023-10-17 01:10:02,215][61453] Avg episode reward: [(0, '7.180'), (1, '6.110')] -[2023-10-17 01:10:02,337][62373] Updated weights for policy 0, policy_version 22560 (0.0007) -[2023-10-17 01:10:02,704][62408] Updated weights for policy 1, policy_version 22370 (0.0009) -[2023-10-17 01:10:03,078][62408] Updated weights for policy 1, policy_version 22380 (0.0010) -[2023-10-17 01:10:03,442][62408] Updated weights for policy 1, policy_version 22390 (0.0011) -[2023-10-17 01:10:03,819][62408] Updated weights for policy 1, policy_version 22400 (0.0011) -[2023-10-17 01:10:06,115][62373] Updated weights for policy 0, policy_version 22570 (0.0009) -[2023-10-17 01:10:06,494][62373] Updated weights for policy 0, policy_version 22580 (0.0008) -[2023-10-17 01:10:06,868][62373] Updated weights for policy 0, policy_version 22590 (0.0011) -[2023-10-17 01:10:07,214][61453] Fps is (10 sec: 16383.6, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 46071808. Throughput: 0: 1784.4, 1: 1777.7. Samples: 11521844. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-17 01:10:07,215][61453] Avg episode reward: [(0, '7.160'), (1, '6.070')] -[2023-10-17 01:10:07,590][62408] Updated weights for policy 1, policy_version 22410 (0.0007) -[2023-10-17 01:10:07,953][62408] Updated weights for policy 1, policy_version 22420 (0.0009) -[2023-10-17 01:10:08,324][62408] Updated weights for policy 1, policy_version 22430 (0.0008) -[2023-10-17 01:10:10,654][62373] Updated weights for policy 0, policy_version 22600 (0.0008) -[2023-10-17 01:10:11,038][62373] Updated weights for policy 0, policy_version 22610 (0.0010) -[2023-10-17 01:10:11,410][62373] Updated weights for policy 0, policy_version 22620 (0.0008) -[2023-10-17 01:10:11,982][62408] Updated weights for policy 1, policy_version 22440 (0.0008) -[2023-10-17 01:10:12,214][61453] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 46137344. Throughput: 0: 1789.2, 1: 1776.8. Samples: 11542986. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-17 01:10:12,215][61453] Avg episode reward: [(0, '6.840'), (1, '6.180')] -[2023-10-17 01:10:12,346][62408] Updated weights for policy 1, policy_version 22450 (0.0008) -[2023-10-17 01:10:12,725][62408] Updated weights for policy 1, policy_version 22460 (0.0008) -[2023-10-17 01:10:15,188][62373] Updated weights for policy 0, policy_version 22630 (0.0009) -[2023-10-17 01:10:15,558][62373] Updated weights for policy 0, policy_version 22640 (0.0008) -[2023-10-17 01:10:15,929][62373] Updated weights for policy 0, policy_version 22650 (0.0009) -[2023-10-17 01:10:16,576][62408] Updated weights for policy 1, policy_version 22470 (0.0008) -[2023-10-17 01:10:16,947][62408] Updated weights for policy 1, policy_version 22480 (0.0008) -[2023-10-17 01:10:17,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 46202880. Throughput: 0: 1770.0, 1: 1790.8. Samples: 11563792. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-17 01:10:17,215][61453] Avg episode reward: [(0, '7.220'), (1, '6.480')] -[2023-10-17 01:10:17,310][62408] Updated weights for policy 1, policy_version 22490 (0.0008) -[2023-10-17 01:10:19,794][62373] Updated weights for policy 0, policy_version 22660 (0.0009) -[2023-10-17 01:10:20,171][62373] Updated weights for policy 0, policy_version 22670 (0.0009) -[2023-10-17 01:10:20,543][62373] Updated weights for policy 0, policy_version 22680 (0.0008) -[2023-10-17 01:10:21,038][62408] Updated weights for policy 1, policy_version 22500 (0.0008) -[2023-10-17 01:10:21,396][62408] Updated weights for policy 1, policy_version 22510 (0.0010) -[2023-10-17 01:10:21,763][62408] Updated weights for policy 1, policy_version 22520 (0.0010) -[2023-10-17 01:10:22,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14218.0). Total num frames: 46301184. Throughput: 0: 1796.8, 1: 1772.4. Samples: 11575044. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-17 01:10:22,215][61453] Avg episode reward: [(0, '6.770'), (1, '6.710')] -[2023-10-17 01:10:24,356][62373] Updated weights for policy 0, policy_version 22690 (0.0008) -[2023-10-17 01:10:24,722][62373] Updated weights for policy 0, policy_version 22700 (0.0009) -[2023-10-17 01:10:25,091][62373] Updated weights for policy 0, policy_version 22710 (0.0010) -[2023-10-17 01:10:25,467][62373] Updated weights for policy 0, policy_version 22720 (0.0012) -[2023-10-17 01:10:25,669][62408] Updated weights for policy 1, policy_version 22530 (0.0008) -[2023-10-17 01:10:26,038][62408] Updated weights for policy 1, policy_version 22540 (0.0008) -[2023-10-17 01:10:26,414][62408] Updated weights for policy 1, policy_version 22550 (0.0010) -[2023-10-17 01:10:26,785][62408] Updated weights for policy 1, policy_version 22560 (0.0010) -[2023-10-17 01:10:27,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 46366720. Throughput: 0: 1763.9, 1: 1794.0. Samples: 11595712. Policy #0 lag: (min: 31.0, avg: 40.4, max: 63.0) -[2023-10-17 01:10:27,215][61453] Avg episode reward: [(0, '6.990'), (1, '6.440')] -[2023-10-17 01:10:29,268][62373] Updated weights for policy 0, policy_version 22730 (0.0007) -[2023-10-17 01:10:29,645][62373] Updated weights for policy 0, policy_version 22740 (0.0007) -[2023-10-17 01:10:30,027][62373] Updated weights for policy 0, policy_version 22750 (0.0010) -[2023-10-17 01:10:30,561][62408] Updated weights for policy 1, policy_version 22570 (0.0008) -[2023-10-17 01:10:30,930][62408] Updated weights for policy 1, policy_version 22580 (0.0010) -[2023-10-17 01:10:31,310][62408] Updated weights for policy 1, policy_version 22590 (0.0010) -[2023-10-17 01:10:32,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 46432256. Throughput: 0: 1762.6, 1: 1767.3. Samples: 11616622. Policy #0 lag: (min: 31.0, avg: 40.4, max: 63.0) -[2023-10-17 01:10:32,214][61453] Avg episode reward: [(0, '6.630'), (1, '6.850')] -[2023-10-17 01:10:33,914][62373] Updated weights for policy 0, policy_version 22760 (0.0008) -[2023-10-17 01:10:34,278][62373] Updated weights for policy 0, policy_version 22770 (0.0009) -[2023-10-17 01:10:34,651][62373] Updated weights for policy 0, policy_version 22780 (0.0008) -[2023-10-17 01:10:35,386][62408] Updated weights for policy 1, policy_version 22600 (0.0010) -[2023-10-17 01:10:35,759][62408] Updated weights for policy 1, policy_version 22610 (0.0010) -[2023-10-17 01:10:36,127][62408] Updated weights for policy 1, policy_version 22620 (0.0008) -[2023-10-17 01:10:37,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 46497792. Throughput: 0: 1758.5, 1: 1791.2. Samples: 11627372. Policy #0 lag: (min: 31.0, avg: 40.4, max: 63.0) -[2023-10-17 01:10:37,215][61453] Avg episode reward: [(0, '6.840'), (1, '6.480')] -[2023-10-17 01:10:38,312][62373] Updated weights for policy 0, policy_version 22790 (0.0009) -[2023-10-17 01:10:38,678][62373] Updated weights for policy 0, policy_version 22800 (0.0009) -[2023-10-17 01:10:39,046][62373] Updated weights for policy 0, policy_version 22810 (0.0008) -[2023-10-17 01:10:39,993][62408] Updated weights for policy 1, policy_version 22630 (0.0008) -[2023-10-17 01:10:40,360][62408] Updated weights for policy 1, policy_version 22640 (0.0007) -[2023-10-17 01:10:40,728][62408] Updated weights for policy 1, policy_version 22650 (0.0009) -[2023-10-17 01:10:42,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 46563328. Throughput: 0: 1757.8, 1: 1767.1. Samples: 11648122. Policy #0 lag: (min: 31.0, avg: 40.4, max: 63.0) -[2023-10-17 01:10:42,215][61453] Avg episode reward: [(0, '6.710'), (1, '6.680')] -[2023-10-17 01:10:42,865][62373] Updated weights for policy 0, policy_version 22820 (0.0008) -[2023-10-17 01:10:43,231][62373] Updated weights for policy 0, policy_version 22830 (0.0008) -[2023-10-17 01:10:43,601][62373] Updated weights for policy 0, policy_version 22840 (0.0009) -[2023-10-17 01:10:44,439][62408] Updated weights for policy 1, policy_version 22660 (0.0009) -[2023-10-17 01:10:44,801][62408] Updated weights for policy 1, policy_version 22670 (0.0010) -[2023-10-17 01:10:45,172][62408] Updated weights for policy 1, policy_version 22680 (0.0007) -[2023-10-17 01:10:47,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 46628864. Throughput: 0: 1778.9, 1: 1762.8. Samples: 11670524. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-17 01:10:47,215][61453] Avg episode reward: [(0, '6.750'), (1, '6.700')] -[2023-10-17 01:10:47,453][62373] Updated weights for policy 0, policy_version 22850 (0.0009) -[2023-10-17 01:10:47,826][62373] Updated weights for policy 0, policy_version 22860 (0.0007) -[2023-10-17 01:10:48,202][62373] Updated weights for policy 0, policy_version 22870 (0.0008) -[2023-10-17 01:10:48,564][62373] Updated weights for policy 0, policy_version 22880 (0.0008) -[2023-10-17 01:10:48,937][62408] Updated weights for policy 1, policy_version 22690 (0.0007) -[2023-10-17 01:10:49,296][62408] Updated weights for policy 1, policy_version 22700 (0.0011) -[2023-10-17 01:10:49,668][62408] Updated weights for policy 1, policy_version 22710 (0.0010) -[2023-10-17 01:10:50,037][62408] Updated weights for policy 1, policy_version 22720 (0.0008) -[2023-10-17 01:10:52,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 46694400. Throughput: 0: 1753.9, 1: 1769.3. Samples: 11680386. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-17 01:10:52,215][61453] Avg episode reward: [(0, '7.060'), (1, '6.620')] -[2023-10-17 01:10:52,428][62373] Updated weights for policy 0, policy_version 22890 (0.0007) -[2023-10-17 01:10:52,797][62373] Updated weights for policy 0, policy_version 22900 (0.0010) -[2023-10-17 01:10:53,160][62373] Updated weights for policy 0, policy_version 22910 (0.0010) -[2023-10-17 01:10:53,816][62408] Updated weights for policy 1, policy_version 22730 (0.0009) -[2023-10-17 01:10:54,189][62408] Updated weights for policy 1, policy_version 22740 (0.0009) -[2023-10-17 01:10:54,547][62408] Updated weights for policy 1, policy_version 22750 (0.0009) -[2023-10-17 01:10:57,009][62373] Updated weights for policy 0, policy_version 22920 (0.0008) -[2023-10-17 01:10:57,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 46759936. Throughput: 0: 1775.1, 1: 1763.0. Samples: 11702198. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-17 01:10:57,214][61453] Avg episode reward: [(0, '6.660'), (1, '6.510')] -[2023-10-17 01:10:57,390][62373] Updated weights for policy 0, policy_version 22930 (0.0009) -[2023-10-17 01:10:57,759][62373] Updated weights for policy 0, policy_version 22940 (0.0008) -[2023-10-17 01:10:58,496][62408] Updated weights for policy 1, policy_version 22760 (0.0009) -[2023-10-17 01:10:58,862][62408] Updated weights for policy 1, policy_version 22770 (0.0008) -[2023-10-17 01:10:59,231][62408] Updated weights for policy 1, policy_version 22780 (0.0008) -[2023-10-17 01:11:01,523][62373] Updated weights for policy 0, policy_version 22950 (0.0008) -[2023-10-17 01:11:01,896][62373] Updated weights for policy 0, policy_version 22960 (0.0007) -[2023-10-17 01:11:02,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 46825472. Throughput: 0: 1774.7, 1: 1776.3. Samples: 11723586. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-17 01:11:02,215][61453] Avg episode reward: [(0, '7.200'), (1, '6.500')] -[2023-10-17 01:11:02,258][62373] Updated weights for policy 0, policy_version 22970 (0.0009) -[2023-10-17 01:11:02,925][62408] Updated weights for policy 1, policy_version 22790 (0.0009) -[2023-10-17 01:11:03,288][62408] Updated weights for policy 1, policy_version 22800 (0.0007) -[2023-10-17 01:11:03,658][62408] Updated weights for policy 1, policy_version 22810 (0.0008) -[2023-10-17 01:11:05,893][62373] Updated weights for policy 0, policy_version 22980 (0.0009) -[2023-10-17 01:11:06,259][62373] Updated weights for policy 0, policy_version 22990 (0.0009) -[2023-10-17 01:11:06,638][62373] Updated weights for policy 0, policy_version 23000 (0.0009) -[2023-10-17 01:11:07,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 46923776. Throughput: 0: 1770.9, 1: 1764.8. Samples: 11734148. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:11:07,215][61453] Avg episode reward: [(0, '6.700'), (1, '6.130')] -[2023-10-17 01:11:07,523][62408] Updated weights for policy 1, policy_version 22820 (0.0010) -[2023-10-17 01:11:07,891][62408] Updated weights for policy 1, policy_version 22830 (0.0010) -[2023-10-17 01:11:08,255][62408] Updated weights for policy 1, policy_version 22840 (0.0010) -[2023-10-17 01:11:10,444][62373] Updated weights for policy 0, policy_version 23010 (0.0009) -[2023-10-17 01:11:10,809][62373] Updated weights for policy 0, policy_version 23020 (0.0008) -[2023-10-17 01:11:11,180][62373] Updated weights for policy 0, policy_version 23030 (0.0007) -[2023-10-17 01:11:11,549][62373] Updated weights for policy 0, policy_version 23040 (0.0009) -[2023-10-17 01:11:12,104][62408] Updated weights for policy 1, policy_version 22850 (0.0011) -[2023-10-17 01:11:12,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 46989312. Throughput: 0: 1786.5, 1: 1772.1. Samples: 11755848. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:11:12,215][61453] Avg episode reward: [(0, '7.350'), (1, '5.970')] -[2023-10-17 01:11:12,465][62408] Updated weights for policy 1, policy_version 22860 (0.0007) -[2023-10-17 01:11:12,837][62408] Updated weights for policy 1, policy_version 22870 (0.0009) -[2023-10-17 01:11:13,207][62408] Updated weights for policy 1, policy_version 22880 (0.0010) -[2023-10-17 01:11:15,290][62373] Updated weights for policy 0, policy_version 23050 (0.0008) -[2023-10-17 01:11:15,659][62373] Updated weights for policy 0, policy_version 23060 (0.0007) -[2023-10-17 01:11:16,032][62373] Updated weights for policy 0, policy_version 23070 (0.0008) -[2023-10-17 01:11:17,120][62408] Updated weights for policy 1, policy_version 22890 (0.0010) -[2023-10-17 01:11:17,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 47054848. Throughput: 0: 1775.3, 1: 1787.8. Samples: 11776964. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:11:17,215][61453] Avg episode reward: [(0, '6.990'), (1, '6.150')] -[2023-10-17 01:11:17,486][62408] Updated weights for policy 1, policy_version 22900 (0.0009) -[2023-10-17 01:11:17,853][62408] Updated weights for policy 1, policy_version 22910 (0.0008) -[2023-10-17 01:11:19,647][62373] Updated weights for policy 0, policy_version 23080 (0.0009) -[2023-10-17 01:11:20,021][62373] Updated weights for policy 0, policy_version 23090 (0.0009) -[2023-10-17 01:11:20,388][62373] Updated weights for policy 0, policy_version 23100 (0.0009) -[2023-10-17 01:11:21,731][62408] Updated weights for policy 1, policy_version 22920 (0.0010) -[2023-10-17 01:11:22,109][62408] Updated weights for policy 1, policy_version 22930 (0.0007) -[2023-10-17 01:11:22,214][61453] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 47120384. Throughput: 0: 1797.7, 1: 1762.5. Samples: 11787582. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-17 01:11:22,214][61453] Avg episode reward: [(0, '6.920'), (1, '5.930')] -[2023-10-17 01:11:22,485][62408] Updated weights for policy 1, policy_version 22940 (0.0007) -[2023-10-17 01:11:24,192][62373] Updated weights for policy 0, policy_version 23110 (0.0007) -[2023-10-17 01:11:24,556][62373] Updated weights for policy 0, policy_version 23120 (0.0007) -[2023-10-17 01:11:24,930][62373] Updated weights for policy 0, policy_version 23130 (0.0008) -[2023-10-17 01:11:26,454][62408] Updated weights for policy 1, policy_version 22950 (0.0009) -[2023-10-17 01:11:26,817][62408] Updated weights for policy 1, policy_version 22960 (0.0009) -[2023-10-17 01:11:27,194][62408] Updated weights for policy 1, policy_version 22970 (0.0009) -[2023-10-17 01:11:27,214][61453] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 47185920. Throughput: 0: 1784.4, 1: 1786.5. Samples: 11808812. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-17 01:11:27,215][61453] Avg episode reward: [(0, '7.140'), (1, '6.940')] -[2023-10-17 01:11:28,795][62373] Updated weights for policy 0, policy_version 23140 (0.0009) -[2023-10-17 01:11:29,169][62373] Updated weights for policy 0, policy_version 23150 (0.0008) -[2023-10-17 01:11:29,531][62373] Updated weights for policy 0, policy_version 23160 (0.0009) -[2023-10-17 01:11:30,938][62408] Updated weights for policy 1, policy_version 22980 (0.0009) -[2023-10-17 01:11:31,317][62408] Updated weights for policy 1, policy_version 22990 (0.0008) -[2023-10-17 01:11:31,688][62408] Updated weights for policy 1, policy_version 23000 (0.0007) -[2023-10-17 01:11:32,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 47284224. Throughput: 0: 1780.4, 1: 1754.9. Samples: 11829612. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-17 01:11:32,215][61453] Avg episode reward: [(0, '7.590'), (1, '6.710')] -[2023-10-17 01:11:32,225][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000023008_23560192.pth... -[2023-10-17 01:11:32,225][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000023168_23724032.pth... -[2023-10-17 01:11:32,262][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000021504_22020096.pth -[2023-10-17 01:11:32,266][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000021344_21856256.pth -[2023-10-17 01:11:32,266][62094] Saving new best policy, reward=7.590! -[2023-10-17 01:11:33,337][62373] Updated weights for policy 0, policy_version 23170 (0.0009) -[2023-10-17 01:11:33,699][62373] Updated weights for policy 0, policy_version 23180 (0.0010) -[2023-10-17 01:11:34,079][62373] Updated weights for policy 0, policy_version 23190 (0.0009) -[2023-10-17 01:11:34,447][62373] Updated weights for policy 0, policy_version 23200 (0.0009) -[2023-10-17 01:11:35,621][62408] Updated weights for policy 1, policy_version 23010 (0.0008) -[2023-10-17 01:11:35,993][62408] Updated weights for policy 1, policy_version 23020 (0.0011) -[2023-10-17 01:11:36,361][62408] Updated weights for policy 1, policy_version 23030 (0.0011) -[2023-10-17 01:11:36,735][62408] Updated weights for policy 1, policy_version 23040 (0.0010) -[2023-10-17 01:11:37,214][61453] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 47349760. Throughput: 0: 1781.3, 1: 1772.5. Samples: 11840308. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-17 01:11:37,214][61453] Avg episode reward: [(0, '7.700'), (1, '6.720')] -[2023-10-17 01:11:37,215][62094] Saving new best policy, reward=7.700! -[2023-10-17 01:11:38,330][62373] Updated weights for policy 0, policy_version 23210 (0.0008) -[2023-10-17 01:11:38,696][62373] Updated weights for policy 0, policy_version 23220 (0.0010) -[2023-10-17 01:11:39,066][62373] Updated weights for policy 0, policy_version 23230 (0.0010) -[2023-10-17 01:11:40,444][62408] Updated weights for policy 1, policy_version 23050 (0.0009) -[2023-10-17 01:11:40,816][62408] Updated weights for policy 1, policy_version 23060 (0.0008) -[2023-10-17 01:11:41,190][62408] Updated weights for policy 1, policy_version 23070 (0.0007) -[2023-10-17 01:11:42,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 47415296. Throughput: 0: 1784.3, 1: 1759.2. Samples: 11861658. Policy #0 lag: (min: 31.0, avg: 35.5, max: 63.0) -[2023-10-17 01:11:42,215][61453] Avg episode reward: [(0, '7.300'), (1, '7.330')] -[2023-10-17 01:11:43,018][62373] Updated weights for policy 0, policy_version 23240 (0.0009) -[2023-10-17 01:11:43,398][62373] Updated weights for policy 0, policy_version 23250 (0.0008) -[2023-10-17 01:11:43,769][62373] Updated weights for policy 0, policy_version 23260 (0.0008) -[2023-10-17 01:11:44,960][62408] Updated weights for policy 1, policy_version 23080 (0.0007) -[2023-10-17 01:11:45,321][62408] Updated weights for policy 1, policy_version 23090 (0.0007) -[2023-10-17 01:11:45,692][62408] Updated weights for policy 1, policy_version 23100 (0.0008) -[2023-10-17 01:11:47,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 47480832. Throughput: 0: 1796.7, 1: 1748.6. Samples: 11883126. Policy #0 lag: (min: 31.0, avg: 35.5, max: 63.0) -[2023-10-17 01:11:47,215][61453] Avg episode reward: [(0, '7.180'), (1, '6.930')] -[2023-10-17 01:11:47,515][62373] Updated weights for policy 0, policy_version 23270 (0.0007) -[2023-10-17 01:11:47,888][62373] Updated weights for policy 0, policy_version 23280 (0.0008) -[2023-10-17 01:11:48,252][62373] Updated weights for policy 0, policy_version 23290 (0.0009) -[2023-10-17 01:11:49,561][62408] Updated weights for policy 1, policy_version 23110 (0.0008) -[2023-10-17 01:11:49,928][62408] Updated weights for policy 1, policy_version 23120 (0.0010) -[2023-10-17 01:11:50,304][62408] Updated weights for policy 1, policy_version 23130 (0.0010) -[2023-10-17 01:11:52,081][62373] Updated weights for policy 0, policy_version 23300 (0.0008) -[2023-10-17 01:11:52,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 47546368. Throughput: 0: 1778.6, 1: 1760.8. Samples: 11893418. Policy #0 lag: (min: 31.0, avg: 35.5, max: 63.0) -[2023-10-17 01:11:52,215][61453] Avg episode reward: [(0, '7.670'), (1, '6.680')] -[2023-10-17 01:11:52,443][62373] Updated weights for policy 0, policy_version 23310 (0.0008) -[2023-10-17 01:11:52,812][62373] Updated weights for policy 0, policy_version 23320 (0.0008) -[2023-10-17 01:11:54,125][62408] Updated weights for policy 1, policy_version 23140 (0.0009) -[2023-10-17 01:11:54,481][62408] Updated weights for policy 1, policy_version 23150 (0.0007) -[2023-10-17 01:11:54,853][62408] Updated weights for policy 1, policy_version 23160 (0.0008) -[2023-10-17 01:11:56,586][62373] Updated weights for policy 0, policy_version 23330 (0.0007) -[2023-10-17 01:11:56,955][62373] Updated weights for policy 0, policy_version 23340 (0.0007) -[2023-10-17 01:11:57,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 47611904. Throughput: 0: 1793.7, 1: 1733.9. Samples: 11914590. Policy #0 lag: (min: 31.0, avg: 35.5, max: 63.0) -[2023-10-17 01:11:57,215][61453] Avg episode reward: [(0, '7.420'), (1, '6.640')] -[2023-10-17 01:11:57,324][62373] Updated weights for policy 0, policy_version 23350 (0.0008) -[2023-10-17 01:11:57,696][62373] Updated weights for policy 0, policy_version 23360 (0.0007) -[2023-10-17 01:11:58,846][62408] Updated weights for policy 1, policy_version 23170 (0.0010) -[2023-10-17 01:11:59,219][62408] Updated weights for policy 1, policy_version 23180 (0.0010) -[2023-10-17 01:11:59,579][62408] Updated weights for policy 1, policy_version 23190 (0.0008) -[2023-10-17 01:11:59,944][62408] Updated weights for policy 1, policy_version 23200 (0.0007) -[2023-10-17 01:12:01,333][62373] Updated weights for policy 0, policy_version 23370 (0.0007) -[2023-10-17 01:12:01,702][62373] Updated weights for policy 0, policy_version 23380 (0.0008) -[2023-10-17 01:12:02,068][62373] Updated weights for policy 0, policy_version 23390 (0.0008) -[2023-10-17 01:12:02,214][61453] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14218.0). Total num frames: 47710208. Throughput: 0: 1786.8, 1: 1747.5. Samples: 11936006. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-17 01:12:02,214][61453] Avg episode reward: [(0, '7.580'), (1, '6.410')] -[2023-10-17 01:12:03,847][62408] Updated weights for policy 1, policy_version 23210 (0.0008) -[2023-10-17 01:12:04,215][62408] Updated weights for policy 1, policy_version 23220 (0.0007) -[2023-10-17 01:12:04,576][62408] Updated weights for policy 1, policy_version 23230 (0.0008) -[2023-10-17 01:12:05,837][62373] Updated weights for policy 0, policy_version 23400 (0.0010) -[2023-10-17 01:12:06,202][62373] Updated weights for policy 0, policy_version 23410 (0.0009) -[2023-10-17 01:12:06,574][62373] Updated weights for policy 0, policy_version 23420 (0.0009) -[2023-10-17 01:12:07,214][61453] Fps is (10 sec: 16383.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 47775744. Throughput: 0: 1793.1, 1: 1742.2. Samples: 11946668. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-17 01:12:07,215][61453] Avg episode reward: [(0, '7.590'), (1, '5.860')] -[2023-10-17 01:12:08,459][62408] Updated weights for policy 1, policy_version 23240 (0.0010) -[2023-10-17 01:12:08,828][62408] Updated weights for policy 1, policy_version 23250 (0.0010) -[2023-10-17 01:12:09,205][62408] Updated weights for policy 1, policy_version 23260 (0.0008) -[2023-10-17 01:12:10,492][62373] Updated weights for policy 0, policy_version 23430 (0.0010) -[2023-10-17 01:12:10,862][62373] Updated weights for policy 0, policy_version 23440 (0.0008) -[2023-10-17 01:12:11,232][62373] Updated weights for policy 0, policy_version 23450 (0.0007) -[2023-10-17 01:12:12,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 47841280. Throughput: 0: 1786.1, 1: 1746.4. Samples: 11967772. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-17 01:12:12,214][61453] Avg episode reward: [(0, '7.500'), (1, '6.260')] -[2023-10-17 01:12:13,037][62408] Updated weights for policy 1, policy_version 23270 (0.0008) -[2023-10-17 01:12:13,433][62408] Updated weights for policy 1, policy_version 23280 (0.0009) -[2023-10-17 01:12:13,805][62408] Updated weights for policy 1, policy_version 23290 (0.0007) -[2023-10-17 01:12:14,988][62373] Updated weights for policy 0, policy_version 23460 (0.0007) -[2023-10-17 01:12:15,363][62373] Updated weights for policy 0, policy_version 23470 (0.0009) -[2023-10-17 01:12:15,744][62373] Updated weights for policy 0, policy_version 23480 (0.0009) -[2023-10-17 01:12:17,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 47906816. Throughput: 0: 1774.6, 1: 1773.5. Samples: 11989276. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:12:17,214][61453] Avg episode reward: [(0, '8.170'), (1, '5.680')] -[2023-10-17 01:12:17,223][62094] Saving new best policy, reward=8.170! -[2023-10-17 01:12:17,684][62408] Updated weights for policy 1, policy_version 23300 (0.0010) -[2023-10-17 01:12:18,055][62408] Updated weights for policy 1, policy_version 23310 (0.0009) -[2023-10-17 01:12:18,435][62408] Updated weights for policy 1, policy_version 23320 (0.0008) -[2023-10-17 01:12:19,413][62373] Updated weights for policy 0, policy_version 23490 (0.0009) -[2023-10-17 01:12:19,786][62373] Updated weights for policy 0, policy_version 23500 (0.0009) -[2023-10-17 01:12:20,158][62373] Updated weights for policy 0, policy_version 23510 (0.0008) -[2023-10-17 01:12:20,527][62373] Updated weights for policy 0, policy_version 23520 (0.0008) -[2023-10-17 01:12:22,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 47972352. Throughput: 0: 1794.3, 1: 1746.0. Samples: 11999622. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:12:22,215][61453] Avg episode reward: [(0, '7.430'), (1, '5.650')] -[2023-10-17 01:12:22,290][62408] Updated weights for policy 1, policy_version 23330 (0.0007) -[2023-10-17 01:12:22,657][62408] Updated weights for policy 1, policy_version 23340 (0.0007) -[2023-10-17 01:12:23,033][62408] Updated weights for policy 1, policy_version 23350 (0.0008) -[2023-10-17 01:12:23,390][62408] Updated weights for policy 1, policy_version 23360 (0.0007) -[2023-10-17 01:12:24,384][62373] Updated weights for policy 0, policy_version 23530 (0.0008) -[2023-10-17 01:12:24,750][62373] Updated weights for policy 0, policy_version 23540 (0.0009) -[2023-10-17 01:12:25,124][62373] Updated weights for policy 0, policy_version 23550 (0.0009) -[2023-10-17 01:12:26,990][62408] Updated weights for policy 1, policy_version 23370 (0.0007) -[2023-10-17 01:12:27,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 48037888. Throughput: 0: 1771.7, 1: 1773.3. Samples: 12021182. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:12:27,215][61453] Avg episode reward: [(0, '7.140'), (1, '6.130')] -[2023-10-17 01:12:27,363][62408] Updated weights for policy 1, policy_version 23380 (0.0007) -[2023-10-17 01:12:27,741][62408] Updated weights for policy 1, policy_version 23390 (0.0008) -[2023-10-17 01:12:29,075][62373] Updated weights for policy 0, policy_version 23560 (0.0010) -[2023-10-17 01:12:29,451][62373] Updated weights for policy 0, policy_version 23570 (0.0009) -[2023-10-17 01:12:29,819][62373] Updated weights for policy 0, policy_version 23580 (0.0008) -[2023-10-17 01:12:31,439][62408] Updated weights for policy 1, policy_version 23400 (0.0011) -[2023-10-17 01:12:31,803][62408] Updated weights for policy 1, policy_version 23410 (0.0010) -[2023-10-17 01:12:32,167][62408] Updated weights for policy 1, policy_version 23420 (0.0011) -[2023-10-17 01:12:32,214][61453] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 48103424. Throughput: 0: 1771.8, 1: 1770.4. Samples: 12042522. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:12:32,214][61453] Avg episode reward: [(0, '6.830'), (1, '6.020')] -[2023-10-17 01:12:33,361][62373] Updated weights for policy 0, policy_version 23590 (0.0009) -[2023-10-17 01:12:33,734][62373] Updated weights for policy 0, policy_version 23600 (0.0010) -[2023-10-17 01:12:34,107][62373] Updated weights for policy 0, policy_version 23610 (0.0009) -[2023-10-17 01:12:36,051][62408] Updated weights for policy 1, policy_version 23430 (0.0009) -[2023-10-17 01:12:36,408][62408] Updated weights for policy 1, policy_version 23440 (0.0008) -[2023-10-17 01:12:36,786][62408] Updated weights for policy 1, policy_version 23450 (0.0009) -[2023-10-17 01:12:37,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 48201728. Throughput: 0: 1774.7, 1: 1772.4. Samples: 12053036. Policy #0 lag: (min: 0.0, avg: 22.4, max: 32.0) -[2023-10-17 01:12:37,215][61453] Avg episode reward: [(0, '7.110'), (1, '5.750')] -[2023-10-17 01:12:37,990][62373] Updated weights for policy 0, policy_version 23620 (0.0009) -[2023-10-17 01:12:38,354][62373] Updated weights for policy 0, policy_version 23630 (0.0007) -[2023-10-17 01:12:38,721][62373] Updated weights for policy 0, policy_version 23640 (0.0009) -[2023-10-17 01:12:40,647][62408] Updated weights for policy 1, policy_version 23460 (0.0009) -[2023-10-17 01:12:41,016][62408] Updated weights for policy 1, policy_version 23470 (0.0010) -[2023-10-17 01:12:41,374][62408] Updated weights for policy 1, policy_version 23480 (0.0010) -[2023-10-17 01:12:42,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 48267264. Throughput: 0: 1768.4, 1: 1789.0. Samples: 12074672. Policy #0 lag: (min: 0.0, avg: 22.4, max: 32.0) -[2023-10-17 01:12:42,215][61453] Avg episode reward: [(0, '7.030'), (1, '5.730')] -[2023-10-17 01:12:42,537][62373] Updated weights for policy 0, policy_version 23650 (0.0010) -[2023-10-17 01:12:42,906][62373] Updated weights for policy 0, policy_version 23660 (0.0009) -[2023-10-17 01:12:43,281][62373] Updated weights for policy 0, policy_version 23670 (0.0008) -[2023-10-17 01:12:43,654][62373] Updated weights for policy 0, policy_version 23680 (0.0008) -[2023-10-17 01:12:45,172][62408] Updated weights for policy 1, policy_version 23490 (0.0008) -[2023-10-17 01:12:45,539][62408] Updated weights for policy 1, policy_version 23500 (0.0009) -[2023-10-17 01:12:45,920][62408] Updated weights for policy 1, policy_version 23510 (0.0010) -[2023-10-17 01:12:46,286][62408] Updated weights for policy 1, policy_version 23520 (0.0009) -[2023-10-17 01:12:47,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 48332800. Throughput: 0: 1791.8, 1: 1759.7. Samples: 12095824. Policy #0 lag: (min: 0.0, avg: 22.4, max: 32.0) -[2023-10-17 01:12:47,215][61453] Avg episode reward: [(0, '6.800'), (1, '6.070')] -[2023-10-17 01:12:47,412][62373] Updated weights for policy 0, policy_version 23690 (0.0008) -[2023-10-17 01:12:47,793][62373] Updated weights for policy 0, policy_version 23700 (0.0009) -[2023-10-17 01:12:48,172][62373] Updated weights for policy 0, policy_version 23710 (0.0010) -[2023-10-17 01:12:50,217][62408] Updated weights for policy 1, policy_version 23530 (0.0007) -[2023-10-17 01:12:50,584][62408] Updated weights for policy 1, policy_version 23540 (0.0008) -[2023-10-17 01:12:50,955][62408] Updated weights for policy 1, policy_version 23550 (0.0011) -[2023-10-17 01:12:52,019][62373] Updated weights for policy 0, policy_version 23720 (0.0011) -[2023-10-17 01:12:52,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 48398336. Throughput: 0: 1759.9, 1: 1789.2. Samples: 12106378. Policy #0 lag: (min: 0.0, avg: 22.4, max: 32.0) -[2023-10-17 01:12:52,214][61453] Avg episode reward: [(0, '6.850'), (1, '6.520')] -[2023-10-17 01:12:52,378][62373] Updated weights for policy 0, policy_version 23730 (0.0009) -[2023-10-17 01:12:52,745][62373] Updated weights for policy 0, policy_version 23740 (0.0009) -[2023-10-17 01:12:54,675][62408] Updated weights for policy 1, policy_version 23560 (0.0008) -[2023-10-17 01:12:55,042][62408] Updated weights for policy 1, policy_version 23570 (0.0007) -[2023-10-17 01:12:55,417][62408] Updated weights for policy 1, policy_version 23580 (0.0007) -[2023-10-17 01:12:56,533][62373] Updated weights for policy 0, policy_version 23750 (0.0007) -[2023-10-17 01:12:56,903][62373] Updated weights for policy 0, policy_version 23760 (0.0009) -[2023-10-17 01:12:57,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 48463872. Throughput: 0: 1783.2, 1: 1766.1. Samples: 12127490. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-17 01:12:57,214][61453] Avg episode reward: [(0, '7.140'), (1, '6.480')] -[2023-10-17 01:12:57,272][62373] Updated weights for policy 0, policy_version 23770 (0.0010) -[2023-10-17 01:12:59,312][62408] Updated weights for policy 1, policy_version 23590 (0.0007) -[2023-10-17 01:12:59,698][62408] Updated weights for policy 1, policy_version 23600 (0.0008) -[2023-10-17 01:13:00,073][62408] Updated weights for policy 1, policy_version 23610 (0.0008) -[2023-10-17 01:13:01,115][62373] Updated weights for policy 0, policy_version 23780 (0.0010) -[2023-10-17 01:13:01,484][62373] Updated weights for policy 0, policy_version 23790 (0.0011) -[2023-10-17 01:13:01,856][62373] Updated weights for policy 0, policy_version 23800 (0.0008) -[2023-10-17 01:13:02,214][61453] Fps is (10 sec: 16383.5, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 48562176. Throughput: 0: 1767.4, 1: 1763.5. Samples: 12148168. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-17 01:13:02,215][61453] Avg episode reward: [(0, '7.640'), (1, '7.030')] -[2023-10-17 01:13:03,785][62408] Updated weights for policy 1, policy_version 23620 (0.0010) -[2023-10-17 01:13:04,156][62408] Updated weights for policy 1, policy_version 23630 (0.0009) -[2023-10-17 01:13:04,521][62408] Updated weights for policy 1, policy_version 23640 (0.0010) -[2023-10-17 01:13:05,563][62373] Updated weights for policy 0, policy_version 23810 (0.0008) -[2023-10-17 01:13:05,928][62373] Updated weights for policy 0, policy_version 23820 (0.0010) -[2023-10-17 01:13:06,296][62373] Updated weights for policy 0, policy_version 23830 (0.0011) -[2023-10-17 01:13:06,666][62373] Updated weights for policy 0, policy_version 23840 (0.0010) -[2023-10-17 01:13:07,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 48627712. Throughput: 0: 1776.8, 1: 1763.6. Samples: 12158936. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-17 01:13:07,215][61453] Avg episode reward: [(0, '7.960'), (1, '7.450')] -[2023-10-17 01:13:07,216][62252] Saving new best policy, reward=7.450! -[2023-10-17 01:13:08,182][62408] Updated weights for policy 1, policy_version 23650 (0.0010) -[2023-10-17 01:13:08,550][62408] Updated weights for policy 1, policy_version 23660 (0.0010) -[2023-10-17 01:13:08,915][62408] Updated weights for policy 1, policy_version 23670 (0.0010) -[2023-10-17 01:13:09,285][62408] Updated weights for policy 1, policy_version 23680 (0.0009) -[2023-10-17 01:13:10,541][62373] Updated weights for policy 0, policy_version 23850 (0.0007) -[2023-10-17 01:13:10,901][62373] Updated weights for policy 0, policy_version 23860 (0.0008) -[2023-10-17 01:13:11,269][62373] Updated weights for policy 0, policy_version 23870 (0.0007) -[2023-10-17 01:13:12,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 48693248. Throughput: 0: 1777.1, 1: 1757.4. Samples: 12180234. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:13:12,215][61453] Avg episode reward: [(0, '7.240'), (1, '6.700')] -[2023-10-17 01:13:13,196][62408] Updated weights for policy 1, policy_version 23690 (0.0010) -[2023-10-17 01:13:13,565][62408] Updated weights for policy 1, policy_version 23700 (0.0010) -[2023-10-17 01:13:13,939][62408] Updated weights for policy 1, policy_version 23710 (0.0009) -[2023-10-17 01:13:15,162][62373] Updated weights for policy 0, policy_version 23880 (0.0010) -[2023-10-17 01:13:15,541][62373] Updated weights for policy 0, policy_version 23890 (0.0007) -[2023-10-17 01:13:15,905][62373] Updated weights for policy 0, policy_version 23900 (0.0010) -[2023-10-17 01:13:17,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 48758784. Throughput: 0: 1763.9, 1: 1773.4. Samples: 12201698. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:13:17,214][61453] Avg episode reward: [(0, '7.190'), (1, '6.720')] -[2023-10-17 01:13:17,779][62408] Updated weights for policy 1, policy_version 23720 (0.0007) -[2023-10-17 01:13:18,158][62408] Updated weights for policy 1, policy_version 23730 (0.0007) -[2023-10-17 01:13:18,518][62408] Updated weights for policy 1, policy_version 23740 (0.0007) -[2023-10-17 01:13:19,573][62373] Updated weights for policy 0, policy_version 23910 (0.0008) -[2023-10-17 01:13:19,947][62373] Updated weights for policy 0, policy_version 23920 (0.0007) -[2023-10-17 01:13:20,309][62373] Updated weights for policy 0, policy_version 23930 (0.0007) -[2023-10-17 01:13:22,166][62408] Updated weights for policy 1, policy_version 23750 (0.0009) -[2023-10-17 01:13:22,214][61453] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 48824320. Throughput: 0: 1779.1, 1: 1756.5. Samples: 12212134. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:13:22,214][61453] Avg episode reward: [(0, '7.060'), (1, '6.650')] -[2023-10-17 01:13:22,534][62408] Updated weights for policy 1, policy_version 23760 (0.0011) -[2023-10-17 01:13:22,907][62408] Updated weights for policy 1, policy_version 23770 (0.0011) -[2023-10-17 01:13:24,260][62373] Updated weights for policy 0, policy_version 23940 (0.0009) -[2023-10-17 01:13:24,623][62373] Updated weights for policy 0, policy_version 23950 (0.0009) -[2023-10-17 01:13:25,001][62373] Updated weights for policy 0, policy_version 23960 (0.0007) -[2023-10-17 01:13:26,730][62408] Updated weights for policy 1, policy_version 23780 (0.0009) -[2023-10-17 01:13:27,103][62408] Updated weights for policy 1, policy_version 23790 (0.0010) -[2023-10-17 01:13:27,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 48889856. Throughput: 0: 1763.6, 1: 1771.2. Samples: 12233736. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:13:27,215][61453] Avg episode reward: [(0, '6.960'), (1, '6.660')] -[2023-10-17 01:13:27,476][62408] Updated weights for policy 1, policy_version 23800 (0.0008) -[2023-10-17 01:13:28,970][62373] Updated weights for policy 0, policy_version 23970 (0.0007) -[2023-10-17 01:13:29,341][62373] Updated weights for policy 0, policy_version 23980 (0.0009) -[2023-10-17 01:13:29,709][62373] Updated weights for policy 0, policy_version 23990 (0.0009) -[2023-10-17 01:13:30,076][62373] Updated weights for policy 0, policy_version 24000 (0.0008) -[2023-10-17 01:13:31,130][62408] Updated weights for policy 1, policy_version 23810 (0.0007) -[2023-10-17 01:13:31,498][62408] Updated weights for policy 1, policy_version 23820 (0.0007) -[2023-10-17 01:13:31,868][62408] Updated weights for policy 1, policy_version 23830 (0.0007) -[2023-10-17 01:13:32,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 48955392. Throughput: 0: 1759.0, 1: 1778.1. Samples: 12254994. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:13:32,215][61453] Avg episode reward: [(0, '6.390'), (1, '6.370')] -[2023-10-17 01:13:32,224][62408] Updated weights for policy 1, policy_version 23840 (0.0007) -[2023-10-17 01:13:32,224][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000024000_24576000.pth... -[2023-10-17 01:13:32,225][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000023840_24412160.pth... -[2023-10-17 01:13:32,271][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000022336_22872064.pth -[2023-10-17 01:13:32,271][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000022176_22708224.pth -[2023-10-17 01:13:33,728][62373] Updated weights for policy 0, policy_version 24010 (0.0009) -[2023-10-17 01:13:34,091][62373] Updated weights for policy 0, policy_version 24020 (0.0009) -[2023-10-17 01:13:34,460][62373] Updated weights for policy 0, policy_version 24030 (0.0009) -[2023-10-17 01:13:36,035][62408] Updated weights for policy 1, policy_version 23850 (0.0009) -[2023-10-17 01:13:36,413][62408] Updated weights for policy 1, policy_version 23860 (0.0012) -[2023-10-17 01:13:36,776][62408] Updated weights for policy 1, policy_version 23870 (0.0007) -[2023-10-17 01:13:37,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 49053696. Throughput: 0: 1769.9, 1: 1774.3. Samples: 12265870. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:13:37,215][61453] Avg episode reward: [(0, '6.090'), (1, '6.100')] -[2023-10-17 01:13:38,147][62373] Updated weights for policy 0, policy_version 24040 (0.0008) -[2023-10-17 01:13:38,522][62373] Updated weights for policy 0, policy_version 24050 (0.0008) -[2023-10-17 01:13:38,895][62373] Updated weights for policy 0, policy_version 24060 (0.0008) -[2023-10-17 01:13:40,535][62408] Updated weights for policy 1, policy_version 23880 (0.0008) -[2023-10-17 01:13:40,901][62408] Updated weights for policy 1, policy_version 23890 (0.0010) -[2023-10-17 01:13:41,280][62408] Updated weights for policy 1, policy_version 23900 (0.0010) -[2023-10-17 01:13:42,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 49119232. Throughput: 0: 1772.1, 1: 1788.6. Samples: 12287722. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:13:42,215][61453] Avg episode reward: [(0, '6.580'), (1, '6.490')] -[2023-10-17 01:13:42,598][62373] Updated weights for policy 0, policy_version 24070 (0.0008) -[2023-10-17 01:13:42,972][62373] Updated weights for policy 0, policy_version 24080 (0.0010) -[2023-10-17 01:13:43,347][62373] Updated weights for policy 0, policy_version 24090 (0.0010) -[2023-10-17 01:13:45,256][62408] Updated weights for policy 1, policy_version 23910 (0.0009) -[2023-10-17 01:13:45,648][62408] Updated weights for policy 1, policy_version 23920 (0.0009) -[2023-10-17 01:13:46,013][62408] Updated weights for policy 1, policy_version 23930 (0.0008) -[2023-10-17 01:13:47,056][62373] Updated weights for policy 0, policy_version 24100 (0.0007) -[2023-10-17 01:13:47,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 49184768. Throughput: 0: 1800.7, 1: 1770.2. Samples: 12308856. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:13:47,214][61453] Avg episode reward: [(0, '7.090'), (1, '7.060')] -[2023-10-17 01:13:47,439][62373] Updated weights for policy 0, policy_version 24110 (0.0008) -[2023-10-17 01:13:47,815][62373] Updated weights for policy 0, policy_version 24120 (0.0008) -[2023-10-17 01:13:49,916][62408] Updated weights for policy 1, policy_version 23940 (0.0008) -[2023-10-17 01:13:50,279][62408] Updated weights for policy 1, policy_version 23950 (0.0008) -[2023-10-17 01:13:50,648][62408] Updated weights for policy 1, policy_version 23960 (0.0008) -[2023-10-17 01:13:51,499][62373] Updated weights for policy 0, policy_version 24130 (0.0008) -[2023-10-17 01:13:51,877][62373] Updated weights for policy 0, policy_version 24140 (0.0008) -[2023-10-17 01:13:52,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 49250304. Throughput: 0: 1775.8, 1: 1798.4. Samples: 12319774. Policy #0 lag: (min: 7.0, avg: 7.2, max: 16.0) -[2023-10-17 01:13:52,214][61453] Avg episode reward: [(0, '7.720'), (1, '7.140')] -[2023-10-17 01:13:52,243][62373] Updated weights for policy 0, policy_version 24150 (0.0008) -[2023-10-17 01:13:52,623][62373] Updated weights for policy 0, policy_version 24160 (0.0007) -[2023-10-17 01:13:54,380][62408] Updated weights for policy 1, policy_version 23970 (0.0008) -[2023-10-17 01:13:54,757][62408] Updated weights for policy 1, policy_version 23980 (0.0010) -[2023-10-17 01:13:55,129][62408] Updated weights for policy 1, policy_version 23990 (0.0009) -[2023-10-17 01:13:55,495][62408] Updated weights for policy 1, policy_version 24000 (0.0011) -[2023-10-17 01:13:56,337][62373] Updated weights for policy 0, policy_version 24170 (0.0008) -[2023-10-17 01:13:56,706][62373] Updated weights for policy 0, policy_version 24180 (0.0008) -[2023-10-17 01:13:57,082][62373] Updated weights for policy 0, policy_version 24190 (0.0010) -[2023-10-17 01:13:57,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 49348608. Throughput: 0: 1799.1, 1: 1770.7. Samples: 12340872. Policy #0 lag: (min: 7.0, avg: 7.2, max: 16.0) -[2023-10-17 01:13:57,215][61453] Avg episode reward: [(0, '8.160'), (1, '7.270')] -[2023-10-17 01:13:59,433][62408] Updated weights for policy 1, policy_version 24010 (0.0008) -[2023-10-17 01:13:59,798][62408] Updated weights for policy 1, policy_version 24020 (0.0010) -[2023-10-17 01:14:00,173][62408] Updated weights for policy 1, policy_version 24030 (0.0010) -[2023-10-17 01:14:00,851][62373] Updated weights for policy 0, policy_version 24200 (0.0010) -[2023-10-17 01:14:01,218][62373] Updated weights for policy 0, policy_version 24210 (0.0010) -[2023-10-17 01:14:01,590][62373] Updated weights for policy 0, policy_version 24220 (0.0011) -[2023-10-17 01:14:02,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 49414144. Throughput: 0: 1782.4, 1: 1771.2. Samples: 12361614. Policy #0 lag: (min: 7.0, avg: 7.2, max: 16.0) -[2023-10-17 01:14:02,215][61453] Avg episode reward: [(0, '7.790'), (1, '7.170')] -[2023-10-17 01:14:04,049][62408] Updated weights for policy 1, policy_version 24040 (0.0008) -[2023-10-17 01:14:04,412][62408] Updated weights for policy 1, policy_version 24050 (0.0007) -[2023-10-17 01:14:04,781][62408] Updated weights for policy 1, policy_version 24060 (0.0008) -[2023-10-17 01:14:05,322][62373] Updated weights for policy 0, policy_version 24230 (0.0009) -[2023-10-17 01:14:05,694][62373] Updated weights for policy 0, policy_version 24240 (0.0008) -[2023-10-17 01:14:06,070][62373] Updated weights for policy 0, policy_version 24250 (0.0011) -[2023-10-17 01:14:07,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 49479680. Throughput: 0: 1798.9, 1: 1773.2. Samples: 12372878. Policy #0 lag: (min: 31.0, avg: 33.0, max: 61.0) -[2023-10-17 01:14:07,214][61453] Avg episode reward: [(0, '8.180'), (1, '7.440')] -[2023-10-17 01:14:07,215][62094] Saving new best policy, reward=8.180! -[2023-10-17 01:14:08,585][62408] Updated weights for policy 1, policy_version 24070 (0.0007) -[2023-10-17 01:14:08,951][62408] Updated weights for policy 1, policy_version 24080 (0.0007) -[2023-10-17 01:14:09,332][62408] Updated weights for policy 1, policy_version 24090 (0.0010) -[2023-10-17 01:14:09,942][62373] Updated weights for policy 0, policy_version 24260 (0.0008) -[2023-10-17 01:14:10,313][62373] Updated weights for policy 0, policy_version 24270 (0.0009) -[2023-10-17 01:14:10,681][62373] Updated weights for policy 0, policy_version 24280 (0.0008) -[2023-10-17 01:14:12,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 49545216. Throughput: 0: 1781.7, 1: 1767.1. Samples: 12393432. Policy #0 lag: (min: 31.0, avg: 33.0, max: 61.0) -[2023-10-17 01:14:12,215][61453] Avg episode reward: [(0, '7.890'), (1, '6.940')] -[2023-10-17 01:14:13,137][62408] Updated weights for policy 1, policy_version 24100 (0.0007) -[2023-10-17 01:14:13,491][62408] Updated weights for policy 1, policy_version 24110 (0.0008) -[2023-10-17 01:14:13,870][62408] Updated weights for policy 1, policy_version 24120 (0.0009) -[2023-10-17 01:14:14,422][62373] Updated weights for policy 0, policy_version 24290 (0.0008) -[2023-10-17 01:14:14,805][62373] Updated weights for policy 0, policy_version 24300 (0.0008) -[2023-10-17 01:14:15,173][62373] Updated weights for policy 0, policy_version 24310 (0.0008) -[2023-10-17 01:14:15,543][62373] Updated weights for policy 0, policy_version 24320 (0.0009) -[2023-10-17 01:14:17,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 49610752. Throughput: 0: 1782.1, 1: 1786.8. Samples: 12415594. Policy #0 lag: (min: 31.0, avg: 33.0, max: 61.0) -[2023-10-17 01:14:17,215][61453] Avg episode reward: [(0, '8.280'), (1, '6.920')] -[2023-10-17 01:14:17,225][62094] Saving new best policy, reward=8.280! -[2023-10-17 01:14:17,633][62408] Updated weights for policy 1, policy_version 24130 (0.0010) -[2023-10-17 01:14:18,001][62408] Updated weights for policy 1, policy_version 24140 (0.0007) -[2023-10-17 01:14:18,379][62408] Updated weights for policy 1, policy_version 24150 (0.0008) -[2023-10-17 01:14:18,742][62408] Updated weights for policy 1, policy_version 24160 (0.0008) -[2023-10-17 01:14:19,236][62373] Updated weights for policy 0, policy_version 24330 (0.0009) -[2023-10-17 01:14:19,611][62373] Updated weights for policy 0, policy_version 24340 (0.0008) -[2023-10-17 01:14:19,967][62373] Updated weights for policy 0, policy_version 24350 (0.0007) -[2023-10-17 01:14:22,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 49676288. Throughput: 0: 1787.9, 1: 1764.4. Samples: 12425724. Policy #0 lag: (min: 31.0, avg: 33.0, max: 61.0) -[2023-10-17 01:14:22,214][61453] Avg episode reward: [(0, '7.420'), (1, '6.560')] -[2023-10-17 01:14:22,359][62408] Updated weights for policy 1, policy_version 24170 (0.0007) -[2023-10-17 01:14:22,734][62408] Updated weights for policy 1, policy_version 24180 (0.0009) -[2023-10-17 01:14:23,096][62408] Updated weights for policy 1, policy_version 24190 (0.0009) -[2023-10-17 01:14:23,815][62373] Updated weights for policy 0, policy_version 24360 (0.0007) -[2023-10-17 01:14:24,195][62373] Updated weights for policy 0, policy_version 24370 (0.0009) -[2023-10-17 01:14:24,562][62373] Updated weights for policy 0, policy_version 24380 (0.0007) -[2023-10-17 01:14:26,822][62408] Updated weights for policy 1, policy_version 24200 (0.0009) -[2023-10-17 01:14:27,202][62408] Updated weights for policy 1, policy_version 24210 (0.0008) -[2023-10-17 01:14:27,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 49741824. Throughput: 0: 1775.8, 1: 1781.0. Samples: 12447776. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) -[2023-10-17 01:14:27,215][61453] Avg episode reward: [(0, '6.790'), (1, '6.230')] -[2023-10-17 01:14:27,566][62408] Updated weights for policy 1, policy_version 24220 (0.0009) -[2023-10-17 01:14:28,437][62373] Updated weights for policy 0, policy_version 24390 (0.0007) -[2023-10-17 01:14:28,804][62373] Updated weights for policy 0, policy_version 24400 (0.0007) -[2023-10-17 01:14:29,167][62373] Updated weights for policy 0, policy_version 24410 (0.0007) -[2023-10-17 01:14:31,480][62408] Updated weights for policy 1, policy_version 24230 (0.0009) -[2023-10-17 01:14:31,870][62408] Updated weights for policy 1, policy_version 24240 (0.0010) -[2023-10-17 01:14:32,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 49807360. Throughput: 0: 1780.8, 1: 1775.5. Samples: 12468890. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) -[2023-10-17 01:14:32,215][61453] Avg episode reward: [(0, '7.250'), (1, '6.490')] -[2023-10-17 01:14:32,241][62408] Updated weights for policy 1, policy_version 24250 (0.0011) -[2023-10-17 01:14:32,881][62373] Updated weights for policy 0, policy_version 24420 (0.0008) -[2023-10-17 01:14:33,257][62373] Updated weights for policy 0, policy_version 24430 (0.0008) -[2023-10-17 01:14:33,623][62373] Updated weights for policy 0, policy_version 24440 (0.0008) -[2023-10-17 01:14:36,016][62408] Updated weights for policy 1, policy_version 24260 (0.0011) -[2023-10-17 01:14:36,385][62408] Updated weights for policy 1, policy_version 24270 (0.0007) -[2023-10-17 01:14:36,758][62408] Updated weights for policy 1, policy_version 24280 (0.0008) -[2023-10-17 01:14:37,214][61453] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 49905664. Throughput: 0: 1777.0, 1: 1766.8. Samples: 12479246. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) -[2023-10-17 01:14:37,214][61453] Avg episode reward: [(0, '6.870'), (1, '6.660')] -[2023-10-17 01:14:37,357][62373] Updated weights for policy 0, policy_version 24450 (0.0008) -[2023-10-17 01:14:37,724][62373] Updated weights for policy 0, policy_version 24460 (0.0008) -[2023-10-17 01:14:38,102][62373] Updated weights for policy 0, policy_version 24470 (0.0007) -[2023-10-17 01:14:38,464][62373] Updated weights for policy 0, policy_version 24480 (0.0009) -[2023-10-17 01:14:40,641][62408] Updated weights for policy 1, policy_version 24290 (0.0008) -[2023-10-17 01:14:41,017][62408] Updated weights for policy 1, policy_version 24300 (0.0007) -[2023-10-17 01:14:41,380][62408] Updated weights for policy 1, policy_version 24310 (0.0007) -[2023-10-17 01:14:41,744][62408] Updated weights for policy 1, policy_version 24320 (0.0009) -[2023-10-17 01:14:42,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 49971200. Throughput: 0: 1773.2, 1: 1784.2. Samples: 12500952. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) -[2023-10-17 01:14:42,214][61453] Avg episode reward: [(0, '6.660'), (1, '6.840')] -[2023-10-17 01:14:42,332][62373] Updated weights for policy 0, policy_version 24490 (0.0010) -[2023-10-17 01:14:42,702][62373] Updated weights for policy 0, policy_version 24500 (0.0010) -[2023-10-17 01:14:43,069][62373] Updated weights for policy 0, policy_version 24510 (0.0012) -[2023-10-17 01:14:45,413][62408] Updated weights for policy 1, policy_version 24330 (0.0009) -[2023-10-17 01:14:45,790][62408] Updated weights for policy 1, policy_version 24340 (0.0010) -[2023-10-17 01:14:46,161][62408] Updated weights for policy 1, policy_version 24350 (0.0008) -[2023-10-17 01:14:46,905][62373] Updated weights for policy 0, policy_version 24520 (0.0010) -[2023-10-17 01:14:47,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 50036736. Throughput: 0: 1798.3, 1: 1761.4. Samples: 12521802. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-17 01:14:47,215][61453] Avg episode reward: [(0, '6.700'), (1, '6.950')] -[2023-10-17 01:14:47,287][62373] Updated weights for policy 0, policy_version 24530 (0.0010) -[2023-10-17 01:14:47,665][62373] Updated weights for policy 0, policy_version 24540 (0.0009) -[2023-10-17 01:14:50,006][62408] Updated weights for policy 1, policy_version 24360 (0.0008) -[2023-10-17 01:14:50,382][62408] Updated weights for policy 1, policy_version 24370 (0.0008) -[2023-10-17 01:14:50,753][62408] Updated weights for policy 1, policy_version 24380 (0.0010) -[2023-10-17 01:14:51,306][62373] Updated weights for policy 0, policy_version 24550 (0.0009) -[2023-10-17 01:14:51,688][62373] Updated weights for policy 0, policy_version 24560 (0.0009) -[2023-10-17 01:14:52,060][62373] Updated weights for policy 0, policy_version 24570 (0.0007) -[2023-10-17 01:14:52,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 50102272. Throughput: 0: 1775.0, 1: 1786.1. Samples: 12533130. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-17 01:14:52,214][61453] Avg episode reward: [(0, '6.350'), (1, '6.980')] -[2023-10-17 01:14:54,624][62408] Updated weights for policy 1, policy_version 24390 (0.0008) -[2023-10-17 01:14:54,996][62408] Updated weights for policy 1, policy_version 24400 (0.0009) -[2023-10-17 01:14:55,379][62408] Updated weights for policy 1, policy_version 24410 (0.0008) -[2023-10-17 01:14:55,850][62373] Updated weights for policy 0, policy_version 24580 (0.0007) -[2023-10-17 01:14:56,220][62373] Updated weights for policy 0, policy_version 24590 (0.0009) -[2023-10-17 01:14:56,584][62373] Updated weights for policy 0, policy_version 24600 (0.0008) -[2023-10-17 01:14:57,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 50200576. Throughput: 0: 1805.6, 1: 1757.0. Samples: 12553750. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-17 01:14:57,215][61453] Avg episode reward: [(0, '6.860'), (1, '7.290')] -[2023-10-17 01:14:59,263][62408] Updated weights for policy 1, policy_version 24420 (0.0010) -[2023-10-17 01:14:59,627][62408] Updated weights for policy 1, policy_version 24430 (0.0008) -[2023-10-17 01:15:00,002][62408] Updated weights for policy 1, policy_version 24440 (0.0007) -[2023-10-17 01:15:00,275][62373] Updated weights for policy 0, policy_version 24610 (0.0008) -[2023-10-17 01:15:00,647][62373] Updated weights for policy 0, policy_version 24620 (0.0009) -[2023-10-17 01:15:01,020][62373] Updated weights for policy 0, policy_version 24630 (0.0010) -[2023-10-17 01:15:01,383][62373] Updated weights for policy 0, policy_version 24640 (0.0008) -[2023-10-17 01:15:02,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 50266112. Throughput: 0: 1788.0, 1: 1753.3. Samples: 12574952. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:15:02,215][61453] Avg episode reward: [(0, '7.190'), (1, '7.320')] -[2023-10-17 01:15:03,857][62408] Updated weights for policy 1, policy_version 24450 (0.0007) -[2023-10-17 01:15:04,225][62408] Updated weights for policy 1, policy_version 24460 (0.0008) -[2023-10-17 01:15:04,586][62408] Updated weights for policy 1, policy_version 24470 (0.0008) -[2023-10-17 01:15:04,953][62408] Updated weights for policy 1, policy_version 24480 (0.0008) -[2023-10-17 01:15:05,314][62373] Updated weights for policy 0, policy_version 24650 (0.0009) -[2023-10-17 01:15:05,692][62373] Updated weights for policy 0, policy_version 24660 (0.0008) -[2023-10-17 01:15:06,061][62373] Updated weights for policy 0, policy_version 24670 (0.0007) -[2023-10-17 01:15:07,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 50331648. Throughput: 0: 1808.1, 1: 1757.6. Samples: 12586178. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:15:07,214][61453] Avg episode reward: [(0, '7.260'), (1, '6.960')] -[2023-10-17 01:15:08,818][62408] Updated weights for policy 1, policy_version 24490 (0.0009) -[2023-10-17 01:15:09,184][62408] Updated weights for policy 1, policy_version 24500 (0.0007) -[2023-10-17 01:15:09,551][62408] Updated weights for policy 1, policy_version 24510 (0.0010) -[2023-10-17 01:15:09,790][62373] Updated weights for policy 0, policy_version 24680 (0.0007) -[2023-10-17 01:15:10,150][62373] Updated weights for policy 0, policy_version 24690 (0.0007) -[2023-10-17 01:15:10,530][62373] Updated weights for policy 0, policy_version 24700 (0.0007) -[2023-10-17 01:15:12,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 50397184. Throughput: 0: 1783.4, 1: 1747.5. Samples: 12606664. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:15:12,215][61453] Avg episode reward: [(0, '7.070'), (1, '7.480')] -[2023-10-17 01:15:12,215][62252] Saving new best policy, reward=7.480! -[2023-10-17 01:15:13,518][62408] Updated weights for policy 1, policy_version 24520 (0.0008) -[2023-10-17 01:15:13,891][62408] Updated weights for policy 1, policy_version 24530 (0.0007) -[2023-10-17 01:15:14,252][62408] Updated weights for policy 1, policy_version 24540 (0.0007) -[2023-10-17 01:15:14,435][62373] Updated weights for policy 0, policy_version 24710 (0.0008) -[2023-10-17 01:15:14,804][62373] Updated weights for policy 0, policy_version 24720 (0.0008) -[2023-10-17 01:15:15,170][62373] Updated weights for policy 0, policy_version 24730 (0.0010) -[2023-10-17 01:15:17,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 50462720. Throughput: 0: 1772.4, 1: 1769.4. Samples: 12628272. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:15:17,214][61453] Avg episode reward: [(0, '7.730'), (1, '7.300')] -[2023-10-17 01:15:18,276][62408] Updated weights for policy 1, policy_version 24550 (0.0008) -[2023-10-17 01:15:18,658][62408] Updated weights for policy 1, policy_version 24560 (0.0011) -[2023-10-17 01:15:18,901][62373] Updated weights for policy 0, policy_version 24740 (0.0009) -[2023-10-17 01:15:19,039][62408] Updated weights for policy 1, policy_version 24570 (0.0009) -[2023-10-17 01:15:19,267][62373] Updated weights for policy 0, policy_version 24750 (0.0007) -[2023-10-17 01:15:19,643][62373] Updated weights for policy 0, policy_version 24760 (0.0007) -[2023-10-17 01:15:22,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 50528256. Throughput: 0: 1779.4, 1: 1746.7. Samples: 12637922. Policy #0 lag: (min: 2.0, avg: 11.3, max: 34.0) -[2023-10-17 01:15:22,215][61453] Avg episode reward: [(0, '7.240'), (1, '7.260')] -[2023-10-17 01:15:22,928][62408] Updated weights for policy 1, policy_version 24580 (0.0009) -[2023-10-17 01:15:23,298][62408] Updated weights for policy 1, policy_version 24590 (0.0009) -[2023-10-17 01:15:23,308][62373] Updated weights for policy 0, policy_version 24770 (0.0009) -[2023-10-17 01:15:23,672][62408] Updated weights for policy 1, policy_version 24600 (0.0009) -[2023-10-17 01:15:23,682][62373] Updated weights for policy 0, policy_version 24780 (0.0009) -[2023-10-17 01:15:24,052][62373] Updated weights for policy 0, policy_version 24790 (0.0008) -[2023-10-17 01:15:24,428][62373] Updated weights for policy 0, policy_version 24800 (0.0007) -[2023-10-17 01:15:27,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 50593792. Throughput: 0: 1780.3, 1: 1750.0. Samples: 12659816. Policy #0 lag: (min: 2.0, avg: 11.3, max: 34.0) -[2023-10-17 01:15:27,215][61453] Avg episode reward: [(0, '7.620'), (1, '6.940')] -[2023-10-17 01:15:27,500][62408] Updated weights for policy 1, policy_version 24610 (0.0008) -[2023-10-17 01:15:27,872][62408] Updated weights for policy 1, policy_version 24620 (0.0009) -[2023-10-17 01:15:28,176][62373] Updated weights for policy 0, policy_version 24810 (0.0008) -[2023-10-17 01:15:28,246][62408] Updated weights for policy 1, policy_version 24630 (0.0008) -[2023-10-17 01:15:28,559][62373] Updated weights for policy 0, policy_version 24820 (0.0008) -[2023-10-17 01:15:28,618][62408] Updated weights for policy 1, policy_version 24640 (0.0008) -[2023-10-17 01:15:28,936][62373] Updated weights for policy 0, policy_version 24830 (0.0008) -[2023-10-17 01:15:32,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 50659328. Throughput: 0: 1781.0, 1: 1768.0. Samples: 12681510. Policy #0 lag: (min: 2.0, avg: 11.3, max: 34.0) -[2023-10-17 01:15:32,215][61453] Avg episode reward: [(0, '7.190'), (1, '7.370')] -[2023-10-17 01:15:32,222][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000024832_25427968.pth... -[2023-10-17 01:15:32,256][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000023168_23724032.pth -[2023-10-17 01:15:32,260][62094] Saving a milestone ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/milestones/checkpoint_000024832_25427968.pth -[2023-10-17 01:15:32,382][62408] Updated weights for policy 1, policy_version 24650 (0.0007) -[2023-10-17 01:15:32,752][62408] Updated weights for policy 1, policy_version 24660 (0.0007) -[2023-10-17 01:15:32,924][62373] Updated weights for policy 0, policy_version 24840 (0.0008) -[2023-10-17 01:15:33,111][62408] Updated weights for policy 1, policy_version 24670 (0.0008) -[2023-10-17 01:15:33,185][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000024672_25264128.pth... -[2023-10-17 01:15:33,224][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000023008_23560192.pth -[2023-10-17 01:15:33,230][62252] Saving a milestone ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/milestones/checkpoint_000024672_25264128.pth -[2023-10-17 01:15:33,300][62373] Updated weights for policy 0, policy_version 24850 (0.0009) -[2023-10-17 01:15:33,666][62373] Updated weights for policy 0, policy_version 24860 (0.0010) -[2023-10-17 01:15:36,812][62408] Updated weights for policy 1, policy_version 24680 (0.0009) -[2023-10-17 01:15:37,183][62408] Updated weights for policy 1, policy_version 24690 (0.0008) -[2023-10-17 01:15:37,214][61453] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 50724864. Throughput: 0: 1764.9, 1: 1742.5. Samples: 12690966. Policy #0 lag: (min: 2.0, avg: 11.3, max: 34.0) -[2023-10-17 01:15:37,215][61453] Avg episode reward: [(0, '6.940'), (1, '7.550')] -[2023-10-17 01:15:37,528][62373] Updated weights for policy 0, policy_version 24870 (0.0010) -[2023-10-17 01:15:37,546][62408] Updated weights for policy 1, policy_version 24700 (0.0008) -[2023-10-17 01:15:37,678][62252] Saving new best policy, reward=7.550! -[2023-10-17 01:15:37,904][62373] Updated weights for policy 0, policy_version 24880 (0.0007) -[2023-10-17 01:15:38,271][62373] Updated weights for policy 0, policy_version 24890 (0.0008) -[2023-10-17 01:15:41,398][62408] Updated weights for policy 1, policy_version 24710 (0.0010) -[2023-10-17 01:15:41,761][62408] Updated weights for policy 1, policy_version 24720 (0.0009) -[2023-10-17 01:15:42,121][62408] Updated weights for policy 1, policy_version 24730 (0.0009) -[2023-10-17 01:15:42,135][62373] Updated weights for policy 0, policy_version 24900 (0.0007) -[2023-10-17 01:15:42,214][61453] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 50790400. Throughput: 0: 1763.4, 1: 1769.8. Samples: 12712742. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-17 01:15:42,214][61453] Avg episode reward: [(0, '6.770'), (1, '7.080')] -[2023-10-17 01:15:42,498][62373] Updated weights for policy 0, policy_version 24910 (0.0008) -[2023-10-17 01:15:42,869][62373] Updated weights for policy 0, policy_version 24920 (0.0009) -[2023-10-17 01:15:46,060][62408] Updated weights for policy 1, policy_version 24740 (0.0008) -[2023-10-17 01:15:46,430][62408] Updated weights for policy 1, policy_version 24750 (0.0009) -[2023-10-17 01:15:46,634][62373] Updated weights for policy 0, policy_version 24930 (0.0007) -[2023-10-17 01:15:46,795][62408] Updated weights for policy 1, policy_version 24760 (0.0008) -[2023-10-17 01:15:47,010][62373] Updated weights for policy 0, policy_version 24940 (0.0008) -[2023-10-17 01:15:47,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 50888704. Throughput: 0: 1774.3, 1: 1742.5. Samples: 12733208. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-17 01:15:47,215][61453] Avg episode reward: [(0, '6.770'), (1, '7.190')] -[2023-10-17 01:15:47,373][62373] Updated weights for policy 0, policy_version 24950 (0.0010) -[2023-10-17 01:15:47,747][62373] Updated weights for policy 0, policy_version 24960 (0.0009) -[2023-10-17 01:15:50,529][62408] Updated weights for policy 1, policy_version 24770 (0.0009) -[2023-10-17 01:15:50,903][62408] Updated weights for policy 1, policy_version 24780 (0.0008) -[2023-10-17 01:15:51,264][62408] Updated weights for policy 1, policy_version 24790 (0.0008) -[2023-10-17 01:15:51,638][62408] Updated weights for policy 1, policy_version 24800 (0.0008) -[2023-10-17 01:15:51,667][62373] Updated weights for policy 0, policy_version 24970 (0.0009) -[2023-10-17 01:15:52,035][62373] Updated weights for policy 0, policy_version 24980 (0.0009) -[2023-10-17 01:15:52,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 50954240. Throughput: 0: 1750.5, 1: 1763.2. Samples: 12744296. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-17 01:15:52,214][61453] Avg episode reward: [(0, '6.760'), (1, '7.360')] -[2023-10-17 01:15:52,400][62373] Updated weights for policy 0, policy_version 24990 (0.0007) -[2023-10-17 01:15:55,484][62408] Updated weights for policy 1, policy_version 24810 (0.0008) -[2023-10-17 01:15:55,857][62408] Updated weights for policy 1, policy_version 24820 (0.0009) -[2023-10-17 01:15:56,218][62408] Updated weights for policy 1, policy_version 24830 (0.0007) -[2023-10-17 01:15:56,229][62373] Updated weights for policy 0, policy_version 25000 (0.0008) -[2023-10-17 01:15:56,591][62373] Updated weights for policy 0, policy_version 25010 (0.0010) -[2023-10-17 01:15:56,971][62373] Updated weights for policy 0, policy_version 25020 (0.0010) -[2023-10-17 01:15:57,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 51052544. Throughput: 0: 1784.4, 1: 1750.6. Samples: 12765738. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-17 01:15:57,215][61453] Avg episode reward: [(0, '6.870'), (1, '7.130')] -[2023-10-17 01:16:00,077][62408] Updated weights for policy 1, policy_version 24840 (0.0007) -[2023-10-17 01:16:00,453][62408] Updated weights for policy 1, policy_version 24850 (0.0009) -[2023-10-17 01:16:00,726][62373] Updated weights for policy 0, policy_version 25030 (0.0010) -[2023-10-17 01:16:00,823][62408] Updated weights for policy 1, policy_version 24860 (0.0010) -[2023-10-17 01:16:01,099][62373] Updated weights for policy 0, policy_version 25040 (0.0008) -[2023-10-17 01:16:01,467][62373] Updated weights for policy 0, policy_version 25050 (0.0007) -[2023-10-17 01:16:02,214][61453] Fps is (10 sec: 16383.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 51118080. Throughput: 0: 1756.9, 1: 1747.3. Samples: 12785962. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-17 01:16:02,215][61453] Avg episode reward: [(0, '6.950'), (1, '7.070')] -[2023-10-17 01:16:04,634][62408] Updated weights for policy 1, policy_version 24870 (0.0008) -[2023-10-17 01:16:05,023][62408] Updated weights for policy 1, policy_version 24880 (0.0010) -[2023-10-17 01:16:05,367][62373] Updated weights for policy 0, policy_version 25060 (0.0008) -[2023-10-17 01:16:05,393][62408] Updated weights for policy 1, policy_version 24890 (0.0009) -[2023-10-17 01:16:05,728][62373] Updated weights for policy 0, policy_version 25070 (0.0009) -[2023-10-17 01:16:06,101][62373] Updated weights for policy 0, policy_version 25080 (0.0009) -[2023-10-17 01:16:07,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 51183616. Throughput: 0: 1783.1, 1: 1769.8. Samples: 12797802. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-17 01:16:07,215][61453] Avg episode reward: [(0, '6.850'), (1, '7.350')] -[2023-10-17 01:16:09,107][62408] Updated weights for policy 1, policy_version 24900 (0.0009) -[2023-10-17 01:16:09,476][62408] Updated weights for policy 1, policy_version 24910 (0.0007) -[2023-10-17 01:16:09,839][62408] Updated weights for policy 1, policy_version 24920 (0.0007) -[2023-10-17 01:16:09,847][62373] Updated weights for policy 0, policy_version 25090 (0.0010) -[2023-10-17 01:16:10,210][62373] Updated weights for policy 0, policy_version 25100 (0.0007) -[2023-10-17 01:16:10,585][62373] Updated weights for policy 0, policy_version 25110 (0.0007) -[2023-10-17 01:16:10,955][62373] Updated weights for policy 0, policy_version 25120 (0.0008) -[2023-10-17 01:16:12,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 51249152. Throughput: 0: 1752.3, 1: 1755.4. Samples: 12817660. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-17 01:16:12,214][61453] Avg episode reward: [(0, '6.830'), (1, '7.390')] -[2023-10-17 01:16:13,849][62408] Updated weights for policy 1, policy_version 24930 (0.0007) -[2023-10-17 01:16:14,217][62408] Updated weights for policy 1, policy_version 24940 (0.0008) -[2023-10-17 01:16:14,590][62408] Updated weights for policy 1, policy_version 24950 (0.0007) -[2023-10-17 01:16:14,621][62373] Updated weights for policy 0, policy_version 25130 (0.0008) -[2023-10-17 01:16:14,945][62408] Updated weights for policy 1, policy_version 24960 (0.0008) -[2023-10-17 01:16:14,988][62373] Updated weights for policy 0, policy_version 25140 (0.0007) -[2023-10-17 01:16:15,364][62373] Updated weights for policy 0, policy_version 25150 (0.0008) -[2023-10-17 01:16:17,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 51314688. Throughput: 0: 1761.1, 1: 1751.9. Samples: 12839594. Policy #0 lag: (min: 12.0, avg: 19.6, max: 44.0) -[2023-10-17 01:16:17,215][61453] Avg episode reward: [(0, '7.030'), (1, '6.750')] -[2023-10-17 01:16:18,844][62408] Updated weights for policy 1, policy_version 24970 (0.0007) -[2023-10-17 01:16:19,214][62408] Updated weights for policy 1, policy_version 24980 (0.0007) -[2023-10-17 01:16:19,324][62373] Updated weights for policy 0, policy_version 25160 (0.0008) -[2023-10-17 01:16:19,582][62408] Updated weights for policy 1, policy_version 24990 (0.0008) -[2023-10-17 01:16:19,696][62373] Updated weights for policy 0, policy_version 25170 (0.0010) -[2023-10-17 01:16:20,061][62373] Updated weights for policy 0, policy_version 25180 (0.0008) -[2023-10-17 01:16:22,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 51380224. Throughput: 0: 1774.2, 1: 1749.2. Samples: 12849516. Policy #0 lag: (min: 12.0, avg: 19.6, max: 44.0) -[2023-10-17 01:16:22,215][61453] Avg episode reward: [(0, '7.230'), (1, '7.280')] -[2023-10-17 01:16:23,546][62408] Updated weights for policy 1, policy_version 25000 (0.0010) -[2023-10-17 01:16:23,911][62408] Updated weights for policy 1, policy_version 25010 (0.0010) -[2023-10-17 01:16:23,959][62373] Updated weights for policy 0, policy_version 25190 (0.0008) -[2023-10-17 01:16:24,272][62408] Updated weights for policy 1, policy_version 25020 (0.0008) -[2023-10-17 01:16:24,335][62373] Updated weights for policy 0, policy_version 25200 (0.0008) -[2023-10-17 01:16:24,706][62373] Updated weights for policy 0, policy_version 25210 (0.0008) -[2023-10-17 01:16:27,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 51445760. Throughput: 0: 1768.1, 1: 1750.5. Samples: 12871078. Policy #0 lag: (min: 12.0, avg: 19.6, max: 44.0) -[2023-10-17 01:16:27,215][61453] Avg episode reward: [(0, '7.110'), (1, '7.240')] -[2023-10-17 01:16:28,049][62408] Updated weights for policy 1, policy_version 25030 (0.0007) -[2023-10-17 01:16:28,415][62408] Updated weights for policy 1, policy_version 25040 (0.0009) -[2023-10-17 01:16:28,448][62373] Updated weights for policy 0, policy_version 25220 (0.0009) -[2023-10-17 01:16:28,795][62408] Updated weights for policy 1, policy_version 25050 (0.0008) -[2023-10-17 01:16:28,814][62373] Updated weights for policy 0, policy_version 25230 (0.0008) -[2023-10-17 01:16:29,187][62373] Updated weights for policy 0, policy_version 25240 (0.0007) -[2023-10-17 01:16:32,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 51511296. Throughput: 0: 1781.4, 1: 1774.1. Samples: 12893206. Policy #0 lag: (min: 12.0, avg: 19.6, max: 44.0) -[2023-10-17 01:16:32,214][61453] Avg episode reward: [(0, '7.530'), (1, '7.120')] -[2023-10-17 01:16:32,829][62408] Updated weights for policy 1, policy_version 25060 (0.0008) -[2023-10-17 01:16:32,840][62373] Updated weights for policy 0, policy_version 25250 (0.0010) -[2023-10-17 01:16:33,196][62408] Updated weights for policy 1, policy_version 25070 (0.0008) -[2023-10-17 01:16:33,209][62373] Updated weights for policy 0, policy_version 25260 (0.0009) -[2023-10-17 01:16:33,570][62408] Updated weights for policy 1, policy_version 25080 (0.0008) -[2023-10-17 01:16:33,583][62373] Updated weights for policy 0, policy_version 25270 (0.0008) -[2023-10-17 01:16:33,940][62373] Updated weights for policy 0, policy_version 25280 (0.0008) -[2023-10-17 01:16:37,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 51576832. Throughput: 0: 1769.6, 1: 1747.6. Samples: 12902570. Policy #0 lag: (min: 6.0, avg: 14.0, max: 38.0) -[2023-10-17 01:16:37,214][61453] Avg episode reward: [(0, '7.770'), (1, '6.870')] -[2023-10-17 01:16:37,350][62408] Updated weights for policy 1, policy_version 25090 (0.0009) -[2023-10-17 01:16:37,715][62408] Updated weights for policy 1, policy_version 25100 (0.0008) -[2023-10-17 01:16:37,924][62373] Updated weights for policy 0, policy_version 25290 (0.0007) -[2023-10-17 01:16:38,078][62408] Updated weights for policy 1, policy_version 25110 (0.0007) -[2023-10-17 01:16:38,281][62373] Updated weights for policy 0, policy_version 25300 (0.0008) -[2023-10-17 01:16:38,445][62408] Updated weights for policy 1, policy_version 25120 (0.0009) -[2023-10-17 01:16:38,645][62373] Updated weights for policy 0, policy_version 25310 (0.0009) -[2023-10-17 01:16:42,061][62408] Updated weights for policy 1, policy_version 25130 (0.0009) -[2023-10-17 01:16:42,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 51642368. Throughput: 0: 1764.9, 1: 1766.2. Samples: 12924638. Policy #0 lag: (min: 6.0, avg: 14.0, max: 38.0) -[2023-10-17 01:16:42,216][61453] Avg episode reward: [(0, '8.320'), (1, '7.630')] -[2023-10-17 01:16:42,369][62373] Updated weights for policy 0, policy_version 25320 (0.0007) -[2023-10-17 01:16:42,429][62408] Updated weights for policy 1, policy_version 25140 (0.0009) -[2023-10-17 01:16:42,749][62373] Updated weights for policy 0, policy_version 25330 (0.0007) -[2023-10-17 01:16:42,803][62408] Updated weights for policy 1, policy_version 25150 (0.0007) -[2023-10-17 01:16:42,876][62252] Saving new best policy, reward=7.630! -[2023-10-17 01:16:43,110][62373] Updated weights for policy 0, policy_version 25340 (0.0009) -[2023-10-17 01:16:43,255][62094] Saving new best policy, reward=8.320! -[2023-10-17 01:16:46,764][62408] Updated weights for policy 1, policy_version 25160 (0.0008) -[2023-10-17 01:16:46,854][62373] Updated weights for policy 0, policy_version 25350 (0.0008) -[2023-10-17 01:16:47,136][62408] Updated weights for policy 1, policy_version 25170 (0.0008) -[2023-10-17 01:16:47,214][61453] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 51707904. Throughput: 0: 1794.0, 1: 1758.5. Samples: 12945826. Policy #0 lag: (min: 6.0, avg: 14.0, max: 38.0) -[2023-10-17 01:16:47,215][61453] Avg episode reward: [(0, '7.990'), (1, '7.680')] -[2023-10-17 01:16:47,216][62373] Updated weights for policy 0, policy_version 25360 (0.0009) -[2023-10-17 01:16:47,496][62408] Updated weights for policy 1, policy_version 25180 (0.0007) -[2023-10-17 01:16:47,586][62373] Updated weights for policy 0, policy_version 25370 (0.0007) -[2023-10-17 01:16:47,642][62252] Saving new best policy, reward=7.680! -[2023-10-17 01:16:51,477][62408] Updated weights for policy 1, policy_version 25190 (0.0007) -[2023-10-17 01:16:51,501][62373] Updated weights for policy 0, policy_version 25380 (0.0007) -[2023-10-17 01:16:51,873][62373] Updated weights for policy 0, policy_version 25390 (0.0009) -[2023-10-17 01:16:51,877][62408] Updated weights for policy 1, policy_version 25200 (0.0009) -[2023-10-17 01:16:52,214][61453] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 51773440. Throughput: 0: 1764.1, 1: 1751.2. Samples: 12955994. Policy #0 lag: (min: 6.0, avg: 14.0, max: 38.0) -[2023-10-17 01:16:52,215][61453] Avg episode reward: [(0, '7.710'), (1, '7.010')] -[2023-10-17 01:16:52,238][62373] Updated weights for policy 0, policy_version 25400 (0.0007) -[2023-10-17 01:16:52,254][62408] Updated weights for policy 1, policy_version 25210 (0.0008) -[2023-10-17 01:16:56,026][62373] Updated weights for policy 0, policy_version 25410 (0.0007) -[2023-10-17 01:16:56,053][62408] Updated weights for policy 1, policy_version 25220 (0.0010) -[2023-10-17 01:16:56,390][62373] Updated weights for policy 0, policy_version 25420 (0.0008) -[2023-10-17 01:16:56,420][62408] Updated weights for policy 1, policy_version 25230 (0.0007) -[2023-10-17 01:16:56,755][62373] Updated weights for policy 0, policy_version 25430 (0.0010) -[2023-10-17 01:16:56,792][62408] Updated weights for policy 1, policy_version 25240 (0.0009) -[2023-10-17 01:16:57,129][62373] Updated weights for policy 0, policy_version 25440 (0.0009) -[2023-10-17 01:16:57,214][61453] Fps is (10 sec: 19661.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 51904512. Throughput: 0: 1794.4, 1: 1761.2. Samples: 12977662. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) -[2023-10-17 01:16:57,215][61453] Avg episode reward: [(0, '7.530'), (1, '6.710')] -[2023-10-17 01:17:00,574][62408] Updated weights for policy 1, policy_version 25250 (0.0009) -[2023-10-17 01:17:00,927][62373] Updated weights for policy 0, policy_version 25450 (0.0009) -[2023-10-17 01:17:00,951][62408] Updated weights for policy 1, policy_version 25260 (0.0008) -[2023-10-17 01:17:01,291][62373] Updated weights for policy 0, policy_version 25460 (0.0008) -[2023-10-17 01:17:01,316][62408] Updated weights for policy 1, policy_version 25270 (0.0007) -[2023-10-17 01:17:01,665][62373] Updated weights for policy 0, policy_version 25470 (0.0007) -[2023-10-17 01:17:01,676][62408] Updated weights for policy 1, policy_version 25280 (0.0007) -[2023-10-17 01:17:02,214][61453] Fps is (10 sec: 19661.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 51970048. Throughput: 0: 1761.7, 1: 1732.8. Samples: 12996844. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) -[2023-10-17 01:17:02,214][61453] Avg episode reward: [(0, '8.030'), (1, '6.650')] -[2023-10-17 01:17:05,407][62408] Updated weights for policy 1, policy_version 25290 (0.0008) -[2023-10-17 01:17:05,577][62373] Updated weights for policy 0, policy_version 25480 (0.0009) -[2023-10-17 01:17:05,778][62408] Updated weights for policy 1, policy_version 25300 (0.0010) -[2023-10-17 01:17:05,959][62373] Updated weights for policy 0, policy_version 25490 (0.0009) -[2023-10-17 01:17:06,148][62408] Updated weights for policy 1, policy_version 25310 (0.0008) -[2023-10-17 01:17:06,322][62373] Updated weights for policy 0, policy_version 25500 (0.0007) -[2023-10-17 01:17:07,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 52035584. Throughput: 0: 1787.3, 1: 1770.2. Samples: 13009604. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) -[2023-10-17 01:17:07,214][61453] Avg episode reward: [(0, '8.280'), (1, '6.640')] -[2023-10-17 01:17:10,086][62408] Updated weights for policy 1, policy_version 25320 (0.0008) -[2023-10-17 01:17:10,194][62373] Updated weights for policy 0, policy_version 25510 (0.0007) -[2023-10-17 01:17:10,445][62408] Updated weights for policy 1, policy_version 25330 (0.0007) -[2023-10-17 01:17:10,562][62373] Updated weights for policy 0, policy_version 25520 (0.0008) -[2023-10-17 01:17:10,821][62408] Updated weights for policy 1, policy_version 25340 (0.0008) -[2023-10-17 01:17:10,935][62373] Updated weights for policy 0, policy_version 25530 (0.0008) -[2023-10-17 01:17:12,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 52101120. Throughput: 0: 1766.3, 1: 1746.8. Samples: 13029164. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:17:12,215][61453] Avg episode reward: [(0, '7.330'), (1, '6.810')] -[2023-10-17 01:17:14,613][62373] Updated weights for policy 0, policy_version 25540 (0.0008) -[2023-10-17 01:17:14,923][62408] Updated weights for policy 1, policy_version 25350 (0.0009) -[2023-10-17 01:17:14,987][62373] Updated weights for policy 0, policy_version 25550 (0.0007) -[2023-10-17 01:17:15,297][62408] Updated weights for policy 1, policy_version 25360 (0.0008) -[2023-10-17 01:17:15,351][62373] Updated weights for policy 0, policy_version 25560 (0.0009) -[2023-10-17 01:17:15,665][62408] Updated weights for policy 1, policy_version 25370 (0.0009) -[2023-10-17 01:17:17,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 52166656. Throughput: 0: 1759.0, 1: 1739.6. Samples: 13050642. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:17:17,214][61453] Avg episode reward: [(0, '7.510'), (1, '6.800')] -[2023-10-17 01:17:19,206][62373] Updated weights for policy 0, policy_version 25570 (0.0008) -[2023-10-17 01:17:19,522][62408] Updated weights for policy 1, policy_version 25380 (0.0009) -[2023-10-17 01:17:19,578][62373] Updated weights for policy 0, policy_version 25580 (0.0009) -[2023-10-17 01:17:19,888][62408] Updated weights for policy 1, policy_version 25390 (0.0008) -[2023-10-17 01:17:19,946][62373] Updated weights for policy 0, policy_version 25590 (0.0009) -[2023-10-17 01:17:20,248][62408] Updated weights for policy 1, policy_version 25400 (0.0007) -[2023-10-17 01:17:20,316][62373] Updated weights for policy 0, policy_version 25600 (0.0007) -[2023-10-17 01:17:22,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 52232192. Throughput: 0: 1773.1, 1: 1762.7. Samples: 13061682. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:17:22,215][61453] Avg episode reward: [(0, '8.300'), (1, '7.410')] -[2023-10-17 01:17:24,088][62373] Updated weights for policy 0, policy_version 25610 (0.0007) -[2023-10-17 01:17:24,128][62408] Updated weights for policy 1, policy_version 25410 (0.0008) -[2023-10-17 01:17:24,455][62373] Updated weights for policy 0, policy_version 25620 (0.0007) -[2023-10-17 01:17:24,499][62408] Updated weights for policy 1, policy_version 25420 (0.0007) -[2023-10-17 01:17:24,828][62373] Updated weights for policy 0, policy_version 25630 (0.0008) -[2023-10-17 01:17:24,870][62408] Updated weights for policy 1, policy_version 25430 (0.0008) -[2023-10-17 01:17:25,238][62408] Updated weights for policy 1, policy_version 25440 (0.0009) -[2023-10-17 01:17:27,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 52297728. Throughput: 0: 1765.2, 1: 1739.5. Samples: 13082352. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:17:27,216][61453] Avg episode reward: [(0, '8.070'), (1, '7.800')] -[2023-10-17 01:17:27,218][62252] Saving new best policy, reward=7.800! -[2023-10-17 01:17:28,580][62373] Updated weights for policy 0, policy_version 25640 (0.0008) -[2023-10-17 01:17:28,947][62373] Updated weights for policy 0, policy_version 25650 (0.0008) -[2023-10-17 01:17:29,042][62408] Updated weights for policy 1, policy_version 25450 (0.0009) -[2023-10-17 01:17:29,314][62373] Updated weights for policy 0, policy_version 25660 (0.0008) -[2023-10-17 01:17:29,403][62408] Updated weights for policy 1, policy_version 25460 (0.0008) -[2023-10-17 01:17:29,764][62408] Updated weights for policy 1, policy_version 25470 (0.0008) -[2023-10-17 01:17:32,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 52363264. Throughput: 0: 1768.6, 1: 1753.3. Samples: 13104310. Policy #0 lag: (min: 9.0, avg: 17.3, max: 41.0) -[2023-10-17 01:17:32,214][61453] Avg episode reward: [(0, '8.100'), (1, '8.070')] -[2023-10-17 01:17:32,223][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000025472_26083328.pth... -[2023-10-17 01:17:32,223][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000025664_26279936.pth... -[2023-10-17 01:17:32,260][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000024000_24576000.pth -[2023-10-17 01:17:32,264][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000023840_24412160.pth -[2023-10-17 01:17:32,268][62252] Saving new best policy, reward=8.070! -[2023-10-17 01:17:33,211][62373] Updated weights for policy 0, policy_version 25670 (0.0009) -[2023-10-17 01:17:33,586][62373] Updated weights for policy 0, policy_version 25680 (0.0009) -[2023-10-17 01:17:33,639][62408] Updated weights for policy 1, policy_version 25480 (0.0009) -[2023-10-17 01:17:33,957][62373] Updated weights for policy 0, policy_version 25690 (0.0007) -[2023-10-17 01:17:34,000][62408] Updated weights for policy 1, policy_version 25490 (0.0008) -[2023-10-17 01:17:34,365][62408] Updated weights for policy 1, policy_version 25500 (0.0009) -[2023-10-17 01:17:37,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 52428800. Throughput: 0: 1763.5, 1: 1740.9. Samples: 13113692. Policy #0 lag: (min: 9.0, avg: 17.3, max: 41.0) -[2023-10-17 01:17:37,215][61453] Avg episode reward: [(0, '7.780'), (1, '7.830')] -[2023-10-17 01:17:37,890][62373] Updated weights for policy 0, policy_version 25700 (0.0008) -[2023-10-17 01:17:38,252][62373] Updated weights for policy 0, policy_version 25710 (0.0007) -[2023-10-17 01:17:38,347][62408] Updated weights for policy 1, policy_version 25510 (0.0009) -[2023-10-17 01:17:38,628][62373] Updated weights for policy 0, policy_version 25720 (0.0009) -[2023-10-17 01:17:38,704][62408] Updated weights for policy 1, policy_version 25520 (0.0007) -[2023-10-17 01:17:39,079][62408] Updated weights for policy 1, policy_version 25530 (0.0008) -[2023-10-17 01:17:42,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 52494336. Throughput: 0: 1759.9, 1: 1741.3. Samples: 13135218. Policy #0 lag: (min: 9.0, avg: 17.3, max: 41.0) -[2023-10-17 01:17:42,215][61453] Avg episode reward: [(0, '8.010'), (1, '7.630')] -[2023-10-17 01:17:42,362][62373] Updated weights for policy 0, policy_version 25730 (0.0009) -[2023-10-17 01:17:42,735][62373] Updated weights for policy 0, policy_version 25740 (0.0008) -[2023-10-17 01:17:42,998][62408] Updated weights for policy 1, policy_version 25540 (0.0008) -[2023-10-17 01:17:43,106][62373] Updated weights for policy 0, policy_version 25750 (0.0007) -[2023-10-17 01:17:43,393][62408] Updated weights for policy 1, policy_version 25550 (0.0008) -[2023-10-17 01:17:43,479][62373] Updated weights for policy 0, policy_version 25760 (0.0008) -[2023-10-17 01:17:43,763][62408] Updated weights for policy 1, policy_version 25560 (0.0008) -[2023-10-17 01:17:47,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 52559872. Throughput: 0: 1792.5, 1: 1772.8. Samples: 13157284. Policy #0 lag: (min: 9.0, avg: 17.3, max: 41.0) -[2023-10-17 01:17:47,215][61453] Avg episode reward: [(0, '8.420'), (1, '8.290')] -[2023-10-17 01:17:47,225][62252] Saving new best policy, reward=8.290! -[2023-10-17 01:17:47,306][62373] Updated weights for policy 0, policy_version 25770 (0.0008) -[2023-10-17 01:17:47,513][62408] Updated weights for policy 1, policy_version 25570 (0.0009) -[2023-10-17 01:17:47,674][62373] Updated weights for policy 0, policy_version 25780 (0.0008) -[2023-10-17 01:17:47,884][62408] Updated weights for policy 1, policy_version 25580 (0.0008) -[2023-10-17 01:17:48,033][62373] Updated weights for policy 0, policy_version 25790 (0.0009) -[2023-10-17 01:17:48,109][62094] Saving new best policy, reward=8.420! -[2023-10-17 01:17:48,244][62408] Updated weights for policy 1, policy_version 25590 (0.0008) -[2023-10-17 01:17:48,615][62408] Updated weights for policy 1, policy_version 25600 (0.0007) -[2023-10-17 01:17:51,818][62373] Updated weights for policy 0, policy_version 25800 (0.0007) -[2023-10-17 01:17:52,191][62373] Updated weights for policy 0, policy_version 25810 (0.0009) -[2023-10-17 01:17:52,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 52625408. Throughput: 0: 1761.7, 1: 1734.9. Samples: 13166952. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) -[2023-10-17 01:17:52,214][61453] Avg episode reward: [(0, '8.180'), (1, '7.940')] -[2023-10-17 01:17:52,424][62408] Updated weights for policy 1, policy_version 25610 (0.0008) -[2023-10-17 01:17:52,561][62373] Updated weights for policy 0, policy_version 25820 (0.0007) -[2023-10-17 01:17:52,791][62408] Updated weights for policy 1, policy_version 25620 (0.0008) -[2023-10-17 01:17:53,161][62408] Updated weights for policy 1, policy_version 25630 (0.0008) -[2023-10-17 01:17:56,395][62373] Updated weights for policy 0, policy_version 25830 (0.0007) -[2023-10-17 01:17:56,760][62373] Updated weights for policy 0, policy_version 25840 (0.0009) -[2023-10-17 01:17:57,025][62408] Updated weights for policy 1, policy_version 25640 (0.0007) -[2023-10-17 01:17:57,130][62373] Updated weights for policy 0, policy_version 25850 (0.0007) -[2023-10-17 01:17:57,214][61453] Fps is (10 sec: 13107.6, 60 sec: 13107.2, 300 sec: 13995.8). Total num frames: 52690944. Throughput: 0: 1793.3, 1: 1756.9. Samples: 13188918. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) -[2023-10-17 01:17:57,214][61453] Avg episode reward: [(0, '7.950'), (1, '7.560')] -[2023-10-17 01:17:57,400][62408] Updated weights for policy 1, policy_version 25650 (0.0009) -[2023-10-17 01:17:57,779][62408] Updated weights for policy 1, policy_version 25660 (0.0011) -[2023-10-17 01:18:00,878][62373] Updated weights for policy 0, policy_version 25860 (0.0010) -[2023-10-17 01:18:01,254][62373] Updated weights for policy 0, policy_version 25870 (0.0009) -[2023-10-17 01:18:01,625][62373] Updated weights for policy 0, policy_version 25880 (0.0009) -[2023-10-17 01:18:01,636][62408] Updated weights for policy 1, policy_version 25670 (0.0009) -[2023-10-17 01:18:02,019][62408] Updated weights for policy 1, policy_version 25680 (0.0008) -[2023-10-17 01:18:02,214][61453] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 52789248. Throughput: 0: 1762.4, 1: 1757.8. Samples: 13209052. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) -[2023-10-17 01:18:02,214][61453] Avg episode reward: [(0, '8.160'), (1, '7.440')] -[2023-10-17 01:18:02,380][62408] Updated weights for policy 1, policy_version 25690 (0.0008) -[2023-10-17 01:18:05,427][62373] Updated weights for policy 0, policy_version 25890 (0.0008) -[2023-10-17 01:18:05,799][62373] Updated weights for policy 0, policy_version 25900 (0.0007) -[2023-10-17 01:18:06,158][62408] Updated weights for policy 1, policy_version 25700 (0.0008) -[2023-10-17 01:18:06,170][62373] Updated weights for policy 0, policy_version 25910 (0.0007) -[2023-10-17 01:18:06,523][62408] Updated weights for policy 1, policy_version 25710 (0.0008) -[2023-10-17 01:18:06,535][62373] Updated weights for policy 0, policy_version 25920 (0.0009) -[2023-10-17 01:18:06,896][62408] Updated weights for policy 1, policy_version 25720 (0.0007) -[2023-10-17 01:18:07,214][61453] Fps is (10 sec: 19660.8, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 52887552. Throughput: 0: 1784.9, 1: 1747.5. Samples: 13220642. Policy #0 lag: (min: 9.0, avg: 23.1, max: 41.0) -[2023-10-17 01:18:07,214][61453] Avg episode reward: [(0, '8.160'), (1, '8.120')] -[2023-10-17 01:18:10,418][62373] Updated weights for policy 0, policy_version 25930 (0.0009) -[2023-10-17 01:18:10,795][62373] Updated weights for policy 0, policy_version 25940 (0.0009) -[2023-10-17 01:18:10,873][62408] Updated weights for policy 1, policy_version 25730 (0.0010) -[2023-10-17 01:18:11,170][62373] Updated weights for policy 0, policy_version 25950 (0.0009) -[2023-10-17 01:18:11,239][62408] Updated weights for policy 1, policy_version 25740 (0.0007) -[2023-10-17 01:18:11,599][62408] Updated weights for policy 1, policy_version 25750 (0.0008) -[2023-10-17 01:18:11,966][62408] Updated weights for policy 1, policy_version 25760 (0.0007) -[2023-10-17 01:18:12,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 52953088. Throughput: 0: 1768.3, 1: 1769.6. Samples: 13241558. Policy #0 lag: (min: 9.0, avg: 23.1, max: 41.0) -[2023-10-17 01:18:12,215][61453] Avg episode reward: [(0, '8.160'), (1, '7.670')] -[2023-10-17 01:18:14,848][62373] Updated weights for policy 0, policy_version 25960 (0.0009) -[2023-10-17 01:18:15,217][62373] Updated weights for policy 0, policy_version 25970 (0.0009) -[2023-10-17 01:18:15,587][62373] Updated weights for policy 0, policy_version 25980 (0.0007) -[2023-10-17 01:18:15,590][62408] Updated weights for policy 1, policy_version 25770 (0.0007) -[2023-10-17 01:18:15,958][62408] Updated weights for policy 1, policy_version 25780 (0.0009) -[2023-10-17 01:18:16,333][62408] Updated weights for policy 1, policy_version 25790 (0.0010) -[2023-10-17 01:18:17,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 53018624. Throughput: 0: 1761.4, 1: 1741.4. Samples: 13261936. Policy #0 lag: (min: 9.0, avg: 23.1, max: 41.0) -[2023-10-17 01:18:17,215][61453] Avg episode reward: [(0, '7.980'), (1, '7.730')] -[2023-10-17 01:18:19,249][62373] Updated weights for policy 0, policy_version 25990 (0.0009) -[2023-10-17 01:18:19,615][62373] Updated weights for policy 0, policy_version 26000 (0.0008) -[2023-10-17 01:18:19,989][62373] Updated weights for policy 0, policy_version 26010 (0.0008) -[2023-10-17 01:18:20,173][62408] Updated weights for policy 1, policy_version 25800 (0.0007) -[2023-10-17 01:18:20,541][62408] Updated weights for policy 1, policy_version 25810 (0.0007) -[2023-10-17 01:18:20,911][62408] Updated weights for policy 1, policy_version 25820 (0.0009) -[2023-10-17 01:18:22,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 53084160. Throughput: 0: 1774.6, 1: 1776.4. Samples: 13273488. Policy #0 lag: (min: 9.0, avg: 23.1, max: 41.0) -[2023-10-17 01:18:22,215][61453] Avg episode reward: [(0, '7.530'), (1, '7.780')] -[2023-10-17 01:18:23,838][62373] Updated weights for policy 0, policy_version 26020 (0.0008) -[2023-10-17 01:18:24,208][62373] Updated weights for policy 0, policy_version 26030 (0.0010) -[2023-10-17 01:18:24,583][62373] Updated weights for policy 0, policy_version 26040 (0.0008) -[2023-10-17 01:18:24,746][62408] Updated weights for policy 1, policy_version 25830 (0.0007) -[2023-10-17 01:18:25,117][62408] Updated weights for policy 1, policy_version 25840 (0.0007) -[2023-10-17 01:18:25,483][62408] Updated weights for policy 1, policy_version 25850 (0.0009) -[2023-10-17 01:18:27,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 53149696. Throughput: 0: 1766.7, 1: 1754.2. Samples: 13293656. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:18:27,215][61453] Avg episode reward: [(0, '7.770'), (1, '7.250')] -[2023-10-17 01:18:28,405][62373] Updated weights for policy 0, policy_version 26050 (0.0008) -[2023-10-17 01:18:28,781][62373] Updated weights for policy 0, policy_version 26060 (0.0008) -[2023-10-17 01:18:29,153][62373] Updated weights for policy 0, policy_version 26070 (0.0008) -[2023-10-17 01:18:29,504][62408] Updated weights for policy 1, policy_version 25860 (0.0008) -[2023-10-17 01:18:29,522][62373] Updated weights for policy 0, policy_version 26080 (0.0008) -[2023-10-17 01:18:29,903][62408] Updated weights for policy 1, policy_version 25870 (0.0008) -[2023-10-17 01:18:30,275][62408] Updated weights for policy 1, policy_version 25880 (0.0007) -[2023-10-17 01:18:32,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 53215232. Throughput: 0: 1771.8, 1: 1754.0. Samples: 13315942. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:18:32,215][61453] Avg episode reward: [(0, '7.770'), (1, '6.960')] -[2023-10-17 01:18:33,341][62373] Updated weights for policy 0, policy_version 26090 (0.0007) -[2023-10-17 01:18:33,712][62373] Updated weights for policy 0, policy_version 26100 (0.0008) -[2023-10-17 01:18:34,087][62373] Updated weights for policy 0, policy_version 26110 (0.0008) -[2023-10-17 01:18:34,120][62408] Updated weights for policy 1, policy_version 25890 (0.0009) -[2023-10-17 01:18:34,483][62408] Updated weights for policy 1, policy_version 25900 (0.0008) -[2023-10-17 01:18:34,860][62408] Updated weights for policy 1, policy_version 25910 (0.0008) -[2023-10-17 01:18:35,221][62408] Updated weights for policy 1, policy_version 25920 (0.0009) -[2023-10-17 01:18:37,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 53280768. Throughput: 0: 1772.1, 1: 1765.8. Samples: 13326158. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:18:37,215][61453] Avg episode reward: [(0, '7.720'), (1, '7.340')] -[2023-10-17 01:18:37,825][62373] Updated weights for policy 0, policy_version 26120 (0.0008) -[2023-10-17 01:18:38,194][62373] Updated weights for policy 0, policy_version 26130 (0.0007) -[2023-10-17 01:18:38,566][62373] Updated weights for policy 0, policy_version 26140 (0.0007) -[2023-10-17 01:18:39,100][62408] Updated weights for policy 1, policy_version 25930 (0.0010) -[2023-10-17 01:18:39,476][62408] Updated weights for policy 1, policy_version 25940 (0.0010) -[2023-10-17 01:18:39,844][62408] Updated weights for policy 1, policy_version 25950 (0.0011) -[2023-10-17 01:18:42,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 53346304. Throughput: 0: 1776.4, 1: 1755.6. Samples: 13347858. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:18:42,215][61453] Avg episode reward: [(0, '7.000'), (1, '6.880')] -[2023-10-17 01:18:42,362][62373] Updated weights for policy 0, policy_version 26150 (0.0007) -[2023-10-17 01:18:42,728][62373] Updated weights for policy 0, policy_version 26160 (0.0009) -[2023-10-17 01:18:43,097][62373] Updated weights for policy 0, policy_version 26170 (0.0009) -[2023-10-17 01:18:43,426][62408] Updated weights for policy 1, policy_version 25960 (0.0011) -[2023-10-17 01:18:43,801][62408] Updated weights for policy 1, policy_version 25970 (0.0011) -[2023-10-17 01:18:44,176][62408] Updated weights for policy 1, policy_version 25980 (0.0009) -[2023-10-17 01:18:46,896][62373] Updated weights for policy 0, policy_version 26180 (0.0008) -[2023-10-17 01:18:47,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 53411840. Throughput: 0: 1805.4, 1: 1771.7. Samples: 13370024. Policy #0 lag: (min: 31.0, avg: 32.3, max: 55.0) -[2023-10-17 01:18:47,215][61453] Avg episode reward: [(0, '6.660'), (1, '6.500')] -[2023-10-17 01:18:47,270][62373] Updated weights for policy 0, policy_version 26190 (0.0007) -[2023-10-17 01:18:47,644][62373] Updated weights for policy 0, policy_version 26200 (0.0007) -[2023-10-17 01:18:48,007][62408] Updated weights for policy 1, policy_version 25990 (0.0009) -[2023-10-17 01:18:48,376][62408] Updated weights for policy 1, policy_version 26000 (0.0007) -[2023-10-17 01:18:48,746][62408] Updated weights for policy 1, policy_version 26010 (0.0009) -[2023-10-17 01:18:51,360][62373] Updated weights for policy 0, policy_version 26210 (0.0009) -[2023-10-17 01:18:51,730][62373] Updated weights for policy 0, policy_version 26220 (0.0008) -[2023-10-17 01:18:52,097][62373] Updated weights for policy 0, policy_version 26230 (0.0008) -[2023-10-17 01:18:52,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 53477376. Throughput: 0: 1779.8, 1: 1760.8. Samples: 13379970. Policy #0 lag: (min: 31.0, avg: 32.3, max: 55.0) -[2023-10-17 01:18:52,215][61453] Avg episode reward: [(0, '7.060'), (1, '6.790')] -[2023-10-17 01:18:52,470][62373] Updated weights for policy 0, policy_version 26240 (0.0010) -[2023-10-17 01:18:52,500][62408] Updated weights for policy 1, policy_version 26020 (0.0009) -[2023-10-17 01:18:52,878][62408] Updated weights for policy 1, policy_version 26030 (0.0008) -[2023-10-17 01:18:53,238][62408] Updated weights for policy 1, policy_version 26040 (0.0009) -[2023-10-17 01:18:56,358][62373] Updated weights for policy 0, policy_version 26250 (0.0009) -[2023-10-17 01:18:56,728][62373] Updated weights for policy 0, policy_version 26260 (0.0010) -[2023-10-17 01:18:56,907][62408] Updated weights for policy 1, policy_version 26050 (0.0008) -[2023-10-17 01:18:57,102][62373] Updated weights for policy 0, policy_version 26270 (0.0008) -[2023-10-17 01:18:57,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14745.5, 300 sec: 14106.9). Total num frames: 53575680. Throughput: 0: 1802.8, 1: 1763.6. Samples: 13402048. Policy #0 lag: (min: 31.0, avg: 32.3, max: 55.0) -[2023-10-17 01:18:57,215][61453] Avg episode reward: [(0, '7.170'), (1, '7.170')] -[2023-10-17 01:18:57,278][62408] Updated weights for policy 1, policy_version 26060 (0.0007) -[2023-10-17 01:18:57,652][62408] Updated weights for policy 1, policy_version 26070 (0.0007) -[2023-10-17 01:18:58,029][62408] Updated weights for policy 1, policy_version 26080 (0.0008) -[2023-10-17 01:19:00,860][62373] Updated weights for policy 0, policy_version 26280 (0.0010) -[2023-10-17 01:19:01,241][62373] Updated weights for policy 0, policy_version 26290 (0.0010) -[2023-10-17 01:19:01,610][62373] Updated weights for policy 0, policy_version 26300 (0.0008) -[2023-10-17 01:19:01,748][62408] Updated weights for policy 1, policy_version 26090 (0.0007) -[2023-10-17 01:19:02,117][62408] Updated weights for policy 1, policy_version 26100 (0.0007) -[2023-10-17 01:19:02,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 53641216. Throughput: 0: 1779.8, 1: 1782.3. Samples: 13422232. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:19:02,215][61453] Avg episode reward: [(0, '6.690'), (1, '7.270')] -[2023-10-17 01:19:02,480][62408] Updated weights for policy 1, policy_version 26110 (0.0008) -[2023-10-17 01:19:05,294][62373] Updated weights for policy 0, policy_version 26310 (0.0008) -[2023-10-17 01:19:05,664][62373] Updated weights for policy 0, policy_version 26320 (0.0007) -[2023-10-17 01:19:06,036][62373] Updated weights for policy 0, policy_version 26330 (0.0008) -[2023-10-17 01:19:06,453][62408] Updated weights for policy 1, policy_version 26120 (0.0008) -[2023-10-17 01:19:06,818][62408] Updated weights for policy 1, policy_version 26130 (0.0009) -[2023-10-17 01:19:07,193][62408] Updated weights for policy 1, policy_version 26140 (0.0008) -[2023-10-17 01:19:07,214][61453] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 53706752. Throughput: 0: 1802.9, 1: 1763.5. Samples: 13433974. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:19:07,214][61453] Avg episode reward: [(0, '6.750'), (1, '6.790')] -[2023-10-17 01:19:09,824][62373] Updated weights for policy 0, policy_version 26340 (0.0008) -[2023-10-17 01:19:10,187][62373] Updated weights for policy 0, policy_version 26350 (0.0010) -[2023-10-17 01:19:10,549][62373] Updated weights for policy 0, policy_version 26360 (0.0009) -[2023-10-17 01:19:10,996][62408] Updated weights for policy 1, policy_version 26150 (0.0010) -[2023-10-17 01:19:11,365][62408] Updated weights for policy 1, policy_version 26160 (0.0008) -[2023-10-17 01:19:11,733][62408] Updated weights for policy 1, policy_version 26170 (0.0009) -[2023-10-17 01:19:12,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 53805056. Throughput: 0: 1781.8, 1: 1795.0. Samples: 13454612. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:19:12,214][61453] Avg episode reward: [(0, '7.110'), (1, '7.030')] -[2023-10-17 01:19:14,431][62373] Updated weights for policy 0, policy_version 26370 (0.0007) -[2023-10-17 01:19:14,799][62373] Updated weights for policy 0, policy_version 26380 (0.0008) -[2023-10-17 01:19:15,165][62373] Updated weights for policy 0, policy_version 26390 (0.0008) -[2023-10-17 01:19:15,537][62373] Updated weights for policy 0, policy_version 26400 (0.0008) -[2023-10-17 01:19:15,699][62408] Updated weights for policy 1, policy_version 26180 (0.0009) -[2023-10-17 01:19:16,106][62408] Updated weights for policy 1, policy_version 26190 (0.0008) -[2023-10-17 01:19:16,483][62408] Updated weights for policy 1, policy_version 26200 (0.0008) -[2023-10-17 01:19:17,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 53870592. Throughput: 0: 1772.6, 1: 1765.6. Samples: 13475160. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:19:17,214][61453] Avg episode reward: [(0, '7.350'), (1, '7.070')] -[2023-10-17 01:19:19,308][62373] Updated weights for policy 0, policy_version 26410 (0.0011) -[2023-10-17 01:19:19,668][62373] Updated weights for policy 0, policy_version 26420 (0.0009) -[2023-10-17 01:19:20,039][62373] Updated weights for policy 0, policy_version 26430 (0.0008) -[2023-10-17 01:19:20,503][62408] Updated weights for policy 1, policy_version 26210 (0.0008) -[2023-10-17 01:19:20,876][62408] Updated weights for policy 1, policy_version 26220 (0.0008) -[2023-10-17 01:19:21,238][62408] Updated weights for policy 1, policy_version 26230 (0.0007) -[2023-10-17 01:19:21,609][62408] Updated weights for policy 1, policy_version 26240 (0.0010) -[2023-10-17 01:19:22,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 53936128. Throughput: 0: 1775.2, 1: 1784.6. Samples: 13486348. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:19:22,214][61453] Avg episode reward: [(0, '7.760'), (1, '6.760')] -[2023-10-17 01:19:23,838][62373] Updated weights for policy 0, policy_version 26440 (0.0007) -[2023-10-17 01:19:24,221][62373] Updated weights for policy 0, policy_version 26450 (0.0008) -[2023-10-17 01:19:24,580][62373] Updated weights for policy 0, policy_version 26460 (0.0010) -[2023-10-17 01:19:25,359][62408] Updated weights for policy 1, policy_version 26250 (0.0007) -[2023-10-17 01:19:25,721][62408] Updated weights for policy 1, policy_version 26260 (0.0008) -[2023-10-17 01:19:26,096][62408] Updated weights for policy 1, policy_version 26270 (0.0010) -[2023-10-17 01:19:27,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 54001664. Throughput: 0: 1767.6, 1: 1771.4. Samples: 13507112. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:19:27,214][61453] Avg episode reward: [(0, '7.760'), (1, '6.780')] -[2023-10-17 01:19:28,261][62373] Updated weights for policy 0, policy_version 26470 (0.0009) -[2023-10-17 01:19:28,644][62373] Updated weights for policy 0, policy_version 26480 (0.0008) -[2023-10-17 01:19:29,001][62373] Updated weights for policy 0, policy_version 26490 (0.0010) -[2023-10-17 01:19:29,687][62408] Updated weights for policy 1, policy_version 26280 (0.0011) -[2023-10-17 01:19:30,055][62408] Updated weights for policy 1, policy_version 26290 (0.0008) -[2023-10-17 01:19:30,415][62408] Updated weights for policy 1, policy_version 26300 (0.0008) -[2023-10-17 01:19:32,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 54067200. Throughput: 0: 1773.7, 1: 1756.8. Samples: 13528898. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:19:32,215][61453] Avg episode reward: [(0, '7.630'), (1, '6.640')] -[2023-10-17 01:19:32,225][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000026496_27131904.pth... -[2023-10-17 01:19:32,225][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000026304_26935296.pth... -[2023-10-17 01:19:32,265][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000024672_25264128.pth -[2023-10-17 01:19:32,266][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000024832_25427968.pth -[2023-10-17 01:19:32,856][62373] Updated weights for policy 0, policy_version 26500 (0.0009) -[2023-10-17 01:19:33,217][62373] Updated weights for policy 0, policy_version 26510 (0.0009) -[2023-10-17 01:19:33,595][62373] Updated weights for policy 0, policy_version 26520 (0.0008) -[2023-10-17 01:19:34,368][62408] Updated weights for policy 1, policy_version 26310 (0.0008) -[2023-10-17 01:19:34,734][62408] Updated weights for policy 1, policy_version 26320 (0.0008) -[2023-10-17 01:19:35,105][62408] Updated weights for policy 1, policy_version 26330 (0.0009) -[2023-10-17 01:19:37,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 54132736. Throughput: 0: 1769.6, 1: 1770.0. Samples: 13539254. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:19:37,215][61453] Avg episode reward: [(0, '7.540'), (1, '7.310')] -[2023-10-17 01:19:37,367][62373] Updated weights for policy 0, policy_version 26530 (0.0007) -[2023-10-17 01:19:37,739][62373] Updated weights for policy 0, policy_version 26540 (0.0007) -[2023-10-17 01:19:38,114][62373] Updated weights for policy 0, policy_version 26550 (0.0007) -[2023-10-17 01:19:38,484][62373] Updated weights for policy 0, policy_version 26560 (0.0007) -[2023-10-17 01:19:38,993][62408] Updated weights for policy 1, policy_version 26340 (0.0008) -[2023-10-17 01:19:39,353][62408] Updated weights for policy 1, policy_version 26350 (0.0009) -[2023-10-17 01:19:39,724][62408] Updated weights for policy 1, policy_version 26360 (0.0007) -[2023-10-17 01:19:42,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 54198272. Throughput: 0: 1772.1, 1: 1751.2. Samples: 13560600. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:19:42,215][61453] Avg episode reward: [(0, '7.530'), (1, '8.000')] -[2023-10-17 01:19:42,493][62373] Updated weights for policy 0, policy_version 26570 (0.0010) -[2023-10-17 01:19:42,858][62373] Updated weights for policy 0, policy_version 26580 (0.0008) -[2023-10-17 01:19:43,229][62373] Updated weights for policy 0, policy_version 26590 (0.0008) -[2023-10-17 01:19:43,448][62408] Updated weights for policy 1, policy_version 26370 (0.0009) -[2023-10-17 01:19:43,820][62408] Updated weights for policy 1, policy_version 26380 (0.0008) -[2023-10-17 01:19:44,190][62408] Updated weights for policy 1, policy_version 26390 (0.0008) -[2023-10-17 01:19:44,559][62408] Updated weights for policy 1, policy_version 26400 (0.0008) -[2023-10-17 01:19:46,967][62373] Updated weights for policy 0, policy_version 26600 (0.0009) -[2023-10-17 01:19:47,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 54263808. Throughput: 0: 1799.4, 1: 1763.5. Samples: 13582562. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-17 01:19:47,214][61453] Avg episode reward: [(0, '7.430'), (1, '7.580')] -[2023-10-17 01:19:47,340][62373] Updated weights for policy 0, policy_version 26610 (0.0009) -[2023-10-17 01:19:47,700][62373] Updated weights for policy 0, policy_version 26620 (0.0009) -[2023-10-17 01:19:48,485][62408] Updated weights for policy 1, policy_version 26410 (0.0009) -[2023-10-17 01:19:48,851][62408] Updated weights for policy 1, policy_version 26420 (0.0009) -[2023-10-17 01:19:49,222][62408] Updated weights for policy 1, policy_version 26430 (0.0010) -[2023-10-17 01:19:51,597][62373] Updated weights for policy 0, policy_version 26630 (0.0010) -[2023-10-17 01:19:51,967][62373] Updated weights for policy 0, policy_version 26640 (0.0008) -[2023-10-17 01:19:52,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 54329344. Throughput: 0: 1772.5, 1: 1752.8. Samples: 13592616. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-17 01:19:52,215][61453] Avg episode reward: [(0, '7.410'), (1, '7.820')] -[2023-10-17 01:19:52,329][62373] Updated weights for policy 0, policy_version 26650 (0.0007) -[2023-10-17 01:19:52,957][62408] Updated weights for policy 1, policy_version 26440 (0.0009) -[2023-10-17 01:19:53,322][62408] Updated weights for policy 1, policy_version 26450 (0.0010) -[2023-10-17 01:19:53,689][62408] Updated weights for policy 1, policy_version 26460 (0.0010) -[2023-10-17 01:19:56,121][62373] Updated weights for policy 0, policy_version 26660 (0.0010) -[2023-10-17 01:19:56,498][62373] Updated weights for policy 0, policy_version 26670 (0.0009) -[2023-10-17 01:19:56,870][62373] Updated weights for policy 0, policy_version 26680 (0.0009) -[2023-10-17 01:19:57,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 54427648. Throughput: 0: 1803.5, 1: 1754.9. Samples: 13614740. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-17 01:19:57,215][61453] Avg episode reward: [(0, '6.890'), (1, '7.960')] -[2023-10-17 01:19:57,553][62408] Updated weights for policy 1, policy_version 26470 (0.0007) -[2023-10-17 01:19:57,921][62408] Updated weights for policy 1, policy_version 26480 (0.0008) -[2023-10-17 01:19:58,290][62408] Updated weights for policy 1, policy_version 26490 (0.0007) -[2023-10-17 01:20:00,573][62373] Updated weights for policy 0, policy_version 26690 (0.0007) -[2023-10-17 01:20:00,944][62373] Updated weights for policy 0, policy_version 26700 (0.0007) -[2023-10-17 01:20:01,309][62373] Updated weights for policy 0, policy_version 26710 (0.0010) -[2023-10-17 01:20:01,681][62373] Updated weights for policy 0, policy_version 26720 (0.0007) -[2023-10-17 01:20:02,113][62408] Updated weights for policy 1, policy_version 26500 (0.0007) -[2023-10-17 01:20:02,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 54493184. Throughput: 0: 1778.7, 1: 1790.8. Samples: 13635788. Policy #0 lag: (min: 47.0, avg: 55.8, max: 56.0) -[2023-10-17 01:20:02,215][61453] Avg episode reward: [(0, '6.950'), (1, '7.850')] -[2023-10-17 01:20:02,520][62408] Updated weights for policy 1, policy_version 26510 (0.0007) -[2023-10-17 01:20:02,880][62408] Updated weights for policy 1, policy_version 26520 (0.0009) -[2023-10-17 01:20:05,334][62373] Updated weights for policy 0, policy_version 26730 (0.0008) -[2023-10-17 01:20:05,697][62373] Updated weights for policy 0, policy_version 26740 (0.0007) -[2023-10-17 01:20:06,063][62373] Updated weights for policy 0, policy_version 26750 (0.0008) -[2023-10-17 01:20:06,577][62408] Updated weights for policy 1, policy_version 26530 (0.0008) -[2023-10-17 01:20:06,949][62408] Updated weights for policy 1, policy_version 26540 (0.0007) -[2023-10-17 01:20:07,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 54558720. Throughput: 0: 1806.6, 1: 1759.2. Samples: 13646810. Policy #0 lag: (min: 47.0, avg: 55.8, max: 56.0) -[2023-10-17 01:20:07,215][61453] Avg episode reward: [(0, '7.020'), (1, '7.250')] -[2023-10-17 01:20:07,318][62408] Updated weights for policy 1, policy_version 26550 (0.0007) -[2023-10-17 01:20:07,685][62408] Updated weights for policy 1, policy_version 26560 (0.0007) -[2023-10-17 01:20:09,820][62373] Updated weights for policy 0, policy_version 26760 (0.0010) -[2023-10-17 01:20:10,193][62373] Updated weights for policy 0, policy_version 26770 (0.0012) -[2023-10-17 01:20:10,564][62373] Updated weights for policy 0, policy_version 26780 (0.0008) -[2023-10-17 01:20:11,537][62408] Updated weights for policy 1, policy_version 26570 (0.0007) -[2023-10-17 01:20:11,911][62408] Updated weights for policy 1, policy_version 26580 (0.0008) -[2023-10-17 01:20:12,214][61453] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 54624256. Throughput: 0: 1777.7, 1: 1783.2. Samples: 13667350. Policy #0 lag: (min: 47.0, avg: 55.8, max: 56.0) -[2023-10-17 01:20:12,214][61453] Avg episode reward: [(0, '7.150'), (1, '7.140')] -[2023-10-17 01:20:12,278][62408] Updated weights for policy 1, policy_version 26590 (0.0009) -[2023-10-17 01:20:14,576][62373] Updated weights for policy 0, policy_version 26790 (0.0008) -[2023-10-17 01:20:14,966][62373] Updated weights for policy 0, policy_version 26800 (0.0010) -[2023-10-17 01:20:15,341][62373] Updated weights for policy 0, policy_version 26810 (0.0010) -[2023-10-17 01:20:16,129][62408] Updated weights for policy 1, policy_version 26600 (0.0009) -[2023-10-17 01:20:16,510][62408] Updated weights for policy 1, policy_version 26610 (0.0008) -[2023-10-17 01:20:16,881][62408] Updated weights for policy 1, policy_version 26620 (0.0007) -[2023-10-17 01:20:17,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 54722560. Throughput: 0: 1773.6, 1: 1761.9. Samples: 13687994. Policy #0 lag: (min: 47.0, avg: 55.8, max: 56.0) -[2023-10-17 01:20:17,215][61453] Avg episode reward: [(0, '6.970'), (1, '7.290')] -[2023-10-17 01:20:19,167][62373] Updated weights for policy 0, policy_version 26820 (0.0009) -[2023-10-17 01:20:19,525][62373] Updated weights for policy 0, policy_version 26830 (0.0010) -[2023-10-17 01:20:19,890][62373] Updated weights for policy 0, policy_version 26840 (0.0008) -[2023-10-17 01:20:20,657][62408] Updated weights for policy 1, policy_version 26630 (0.0010) -[2023-10-17 01:20:21,027][62408] Updated weights for policy 1, policy_version 26640 (0.0008) -[2023-10-17 01:20:21,394][62408] Updated weights for policy 1, policy_version 26650 (0.0010) -[2023-10-17 01:20:22,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 54788096. Throughput: 0: 1776.4, 1: 1775.0. Samples: 13699068. Policy #0 lag: (min: 31.0, avg: 32.2, max: 55.0) -[2023-10-17 01:20:22,215][61453] Avg episode reward: [(0, '6.660'), (1, '7.390')] -[2023-10-17 01:20:23,708][62373] Updated weights for policy 0, policy_version 26850 (0.0010) -[2023-10-17 01:20:24,083][62373] Updated weights for policy 0, policy_version 26860 (0.0007) -[2023-10-17 01:20:24,455][62373] Updated weights for policy 0, policy_version 26870 (0.0009) -[2023-10-17 01:20:24,814][62373] Updated weights for policy 0, policy_version 26880 (0.0008) -[2023-10-17 01:20:25,221][62408] Updated weights for policy 1, policy_version 26660 (0.0011) -[2023-10-17 01:20:25,591][62408] Updated weights for policy 1, policy_version 26670 (0.0011) -[2023-10-17 01:20:25,950][62408] Updated weights for policy 1, policy_version 26680 (0.0010) -[2023-10-17 01:20:27,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 54853632. Throughput: 0: 1770.0, 1: 1768.6. Samples: 13719838. Policy #0 lag: (min: 31.0, avg: 32.2, max: 55.0) -[2023-10-17 01:20:27,214][61453] Avg episode reward: [(0, '6.840'), (1, '6.880')] -[2023-10-17 01:20:28,582][62373] Updated weights for policy 0, policy_version 26890 (0.0009) -[2023-10-17 01:20:28,958][62373] Updated weights for policy 0, policy_version 26900 (0.0009) -[2023-10-17 01:20:29,325][62373] Updated weights for policy 0, policy_version 26910 (0.0008) -[2023-10-17 01:20:29,832][62408] Updated weights for policy 1, policy_version 26690 (0.0010) -[2023-10-17 01:20:30,199][62408] Updated weights for policy 1, policy_version 26700 (0.0008) -[2023-10-17 01:20:30,566][62408] Updated weights for policy 1, policy_version 26710 (0.0007) -[2023-10-17 01:20:30,933][62408] Updated weights for policy 1, policy_version 26720 (0.0010) -[2023-10-17 01:20:32,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 54919168. Throughput: 0: 1777.2, 1: 1755.7. Samples: 13741546. Policy #0 lag: (min: 31.0, avg: 32.2, max: 55.0) -[2023-10-17 01:20:32,215][61453] Avg episode reward: [(0, '7.190'), (1, '7.370')] -[2023-10-17 01:20:33,011][62373] Updated weights for policy 0, policy_version 26920 (0.0007) -[2023-10-17 01:20:33,384][62373] Updated weights for policy 0, policy_version 26930 (0.0009) -[2023-10-17 01:20:33,749][62373] Updated weights for policy 0, policy_version 26940 (0.0010) -[2023-10-17 01:20:34,843][62408] Updated weights for policy 1, policy_version 26730 (0.0011) -[2023-10-17 01:20:35,208][62408] Updated weights for policy 1, policy_version 26740 (0.0008) -[2023-10-17 01:20:35,575][62408] Updated weights for policy 1, policy_version 26750 (0.0007) -[2023-10-17 01:20:37,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 54984704. Throughput: 0: 1766.5, 1: 1772.9. Samples: 13751886. Policy #0 lag: (min: 31.0, avg: 32.2, max: 55.0) -[2023-10-17 01:20:37,214][61453] Avg episode reward: [(0, '7.160'), (1, '7.250')] -[2023-10-17 01:20:37,670][62373] Updated weights for policy 0, policy_version 26950 (0.0008) -[2023-10-17 01:20:38,038][62373] Updated weights for policy 0, policy_version 26960 (0.0008) -[2023-10-17 01:20:38,415][62373] Updated weights for policy 0, policy_version 26970 (0.0007) -[2023-10-17 01:20:39,315][62408] Updated weights for policy 1, policy_version 26760 (0.0008) -[2023-10-17 01:20:39,667][62408] Updated weights for policy 1, policy_version 26770 (0.0007) -[2023-10-17 01:20:40,029][62408] Updated weights for policy 1, policy_version 26780 (0.0007) -[2023-10-17 01:20:42,123][62373] Updated weights for policy 0, policy_version 26980 (0.0007) -[2023-10-17 01:20:42,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 55050240. Throughput: 0: 1767.8, 1: 1750.0. Samples: 13773038. Policy #0 lag: (min: 31.0, avg: 32.2, max: 55.0) -[2023-10-17 01:20:42,214][61453] Avg episode reward: [(0, '6.680'), (1, '7.380')] -[2023-10-17 01:20:42,486][62373] Updated weights for policy 0, policy_version 26990 (0.0007) -[2023-10-17 01:20:42,850][62373] Updated weights for policy 0, policy_version 27000 (0.0008) -[2023-10-17 01:20:43,913][62408] Updated weights for policy 1, policy_version 26790 (0.0008) -[2023-10-17 01:20:44,283][62408] Updated weights for policy 1, policy_version 26800 (0.0009) -[2023-10-17 01:20:44,662][62408] Updated weights for policy 1, policy_version 26810 (0.0008) -[2023-10-17 01:20:46,584][62373] Updated weights for policy 0, policy_version 27010 (0.0009) -[2023-10-17 01:20:46,960][62373] Updated weights for policy 0, policy_version 27020 (0.0010) -[2023-10-17 01:20:47,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 55115776. Throughput: 0: 1784.2, 1: 1748.8. Samples: 13794772. Policy #0 lag: (min: 31.0, avg: 32.4, max: 56.0) -[2023-10-17 01:20:47,214][61453] Avg episode reward: [(0, '7.320'), (1, '8.050')] -[2023-10-17 01:20:47,332][62373] Updated weights for policy 0, policy_version 27030 (0.0008) -[2023-10-17 01:20:47,703][62373] Updated weights for policy 0, policy_version 27040 (0.0008) -[2023-10-17 01:20:48,522][62408] Updated weights for policy 1, policy_version 26820 (0.0008) -[2023-10-17 01:20:48,929][62408] Updated weights for policy 1, policy_version 26830 (0.0009) -[2023-10-17 01:20:49,285][62408] Updated weights for policy 1, policy_version 26840 (0.0007) -[2023-10-17 01:20:51,430][62373] Updated weights for policy 0, policy_version 27050 (0.0008) -[2023-10-17 01:20:51,793][62373] Updated weights for policy 0, policy_version 27060 (0.0010) -[2023-10-17 01:20:52,162][62373] Updated weights for policy 0, policy_version 27070 (0.0010) -[2023-10-17 01:20:52,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 55181312. Throughput: 0: 1762.6, 1: 1748.0. Samples: 13804786. Policy #0 lag: (min: 31.0, avg: 32.4, max: 56.0) -[2023-10-17 01:20:52,215][61453] Avg episode reward: [(0, '7.690'), (1, '7.780')] -[2023-10-17 01:20:53,035][62408] Updated weights for policy 1, policy_version 26850 (0.0010) -[2023-10-17 01:20:53,405][62408] Updated weights for policy 1, policy_version 26860 (0.0008) -[2023-10-17 01:20:53,772][62408] Updated weights for policy 1, policy_version 26870 (0.0009) -[2023-10-17 01:20:54,136][62408] Updated weights for policy 1, policy_version 26880 (0.0011) -[2023-10-17 01:20:55,944][62373] Updated weights for policy 0, policy_version 27080 (0.0008) -[2023-10-17 01:20:56,316][62373] Updated weights for policy 0, policy_version 27090 (0.0009) -[2023-10-17 01:20:56,688][62373] Updated weights for policy 0, policy_version 27100 (0.0010) -[2023-10-17 01:20:57,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 55279616. Throughput: 0: 1786.3, 1: 1752.6. Samples: 13826598. Policy #0 lag: (min: 31.0, avg: 32.4, max: 56.0) -[2023-10-17 01:20:57,215][61453] Avg episode reward: [(0, '8.110'), (1, '8.420')] -[2023-10-17 01:20:57,217][62252] Saving new best policy, reward=8.420! -[2023-10-17 01:20:58,081][62408] Updated weights for policy 1, policy_version 26890 (0.0010) -[2023-10-17 01:20:58,443][62408] Updated weights for policy 1, policy_version 26900 (0.0008) -[2023-10-17 01:20:58,818][62408] Updated weights for policy 1, policy_version 26910 (0.0010) -[2023-10-17 01:21:00,509][62373] Updated weights for policy 0, policy_version 27110 (0.0009) -[2023-10-17 01:21:00,884][62373] Updated weights for policy 0, policy_version 27120 (0.0007) -[2023-10-17 01:21:01,256][62373] Updated weights for policy 0, policy_version 27130 (0.0007) -[2023-10-17 01:21:02,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 55345152. Throughput: 0: 1765.7, 1: 1783.2. Samples: 13847696. Policy #0 lag: (min: 31.0, avg: 32.4, max: 56.0) -[2023-10-17 01:21:02,215][61453] Avg episode reward: [(0, '7.590'), (1, '8.370')] -[2023-10-17 01:21:02,701][62408] Updated weights for policy 1, policy_version 26920 (0.0008) -[2023-10-17 01:21:03,074][62408] Updated weights for policy 1, policy_version 26930 (0.0009) -[2023-10-17 01:21:03,438][62408] Updated weights for policy 1, policy_version 26940 (0.0008) -[2023-10-17 01:21:05,055][62373] Updated weights for policy 0, policy_version 27140 (0.0008) -[2023-10-17 01:21:05,427][62373] Updated weights for policy 0, policy_version 27150 (0.0008) -[2023-10-17 01:21:05,802][62373] Updated weights for policy 0, policy_version 27160 (0.0009) -[2023-10-17 01:21:07,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 55410688. Throughput: 0: 1792.3, 1: 1754.8. Samples: 13858686. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:21:07,215][61453] Avg episode reward: [(0, '7.570'), (1, '8.320')] -[2023-10-17 01:21:07,325][62408] Updated weights for policy 1, policy_version 26950 (0.0009) -[2023-10-17 01:21:07,700][62408] Updated weights for policy 1, policy_version 26960 (0.0007) -[2023-10-17 01:21:08,082][62408] Updated weights for policy 1, policy_version 26970 (0.0008) -[2023-10-17 01:21:09,483][62373] Updated weights for policy 0, policy_version 27170 (0.0010) -[2023-10-17 01:21:09,867][62373] Updated weights for policy 0, policy_version 27180 (0.0009) -[2023-10-17 01:21:10,229][62373] Updated weights for policy 0, policy_version 27190 (0.0008) -[2023-10-17 01:21:10,599][62373] Updated weights for policy 0, policy_version 27200 (0.0008) -[2023-10-17 01:21:11,916][62408] Updated weights for policy 1, policy_version 26980 (0.0008) -[2023-10-17 01:21:12,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 55476224. Throughput: 0: 1769.6, 1: 1774.8. Samples: 13879336. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:21:12,215][61453] Avg episode reward: [(0, '8.200'), (1, '7.970')] -[2023-10-17 01:21:12,289][62408] Updated weights for policy 1, policy_version 26990 (0.0007) -[2023-10-17 01:21:12,647][62408] Updated weights for policy 1, policy_version 27000 (0.0009) -[2023-10-17 01:21:14,411][62373] Updated weights for policy 0, policy_version 27210 (0.0008) -[2023-10-17 01:21:14,776][62373] Updated weights for policy 0, policy_version 27220 (0.0009) -[2023-10-17 01:21:15,155][62373] Updated weights for policy 0, policy_version 27230 (0.0009) -[2023-10-17 01:21:16,394][62408] Updated weights for policy 1, policy_version 27010 (0.0009) -[2023-10-17 01:21:16,755][62408] Updated weights for policy 1, policy_version 27020 (0.0007) -[2023-10-17 01:21:17,119][62408] Updated weights for policy 1, policy_version 27030 (0.0009) -[2023-10-17 01:21:17,214][61453] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 55541760. Throughput: 0: 1766.1, 1: 1772.3. Samples: 13900776. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:21:17,214][61453] Avg episode reward: [(0, '8.170'), (1, '7.510')] -[2023-10-17 01:21:17,488][62408] Updated weights for policy 1, policy_version 27040 (0.0009) -[2023-10-17 01:21:18,986][62373] Updated weights for policy 0, policy_version 27240 (0.0008) -[2023-10-17 01:21:19,352][62373] Updated weights for policy 0, policy_version 27250 (0.0009) -[2023-10-17 01:21:19,718][62373] Updated weights for policy 0, policy_version 27260 (0.0009) -[2023-10-17 01:21:21,367][62408] Updated weights for policy 1, policy_version 27050 (0.0010) -[2023-10-17 01:21:21,734][62408] Updated weights for policy 1, policy_version 27060 (0.0011) -[2023-10-17 01:21:22,110][62408] Updated weights for policy 1, policy_version 27070 (0.0009) -[2023-10-17 01:21:22,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 55640064. Throughput: 0: 1767.3, 1: 1766.9. Samples: 13910928. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:21:22,215][61453] Avg episode reward: [(0, '7.770'), (1, '7.930')] -[2023-10-17 01:21:23,688][62373] Updated weights for policy 0, policy_version 27270 (0.0010) -[2023-10-17 01:21:24,063][62373] Updated weights for policy 0, policy_version 27280 (0.0010) -[2023-10-17 01:21:24,429][62373] Updated weights for policy 0, policy_version 27290 (0.0009) -[2023-10-17 01:21:25,948][62408] Updated weights for policy 1, policy_version 27080 (0.0010) -[2023-10-17 01:21:26,329][62408] Updated weights for policy 1, policy_version 27090 (0.0009) -[2023-10-17 01:21:26,695][62408] Updated weights for policy 1, policy_version 27100 (0.0008) -[2023-10-17 01:21:27,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 55705600. Throughput: 0: 1763.0, 1: 1782.1. Samples: 13932570. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:21:27,215][61453] Avg episode reward: [(0, '7.440'), (1, '7.390')] -[2023-10-17 01:21:28,213][62373] Updated weights for policy 0, policy_version 27300 (0.0008) -[2023-10-17 01:21:28,577][62373] Updated weights for policy 0, policy_version 27310 (0.0007) -[2023-10-17 01:21:28,947][62373] Updated weights for policy 0, policy_version 27320 (0.0010) -[2023-10-17 01:21:30,535][62408] Updated weights for policy 1, policy_version 27110 (0.0008) -[2023-10-17 01:21:30,904][62408] Updated weights for policy 1, policy_version 27120 (0.0010) -[2023-10-17 01:21:31,272][62408] Updated weights for policy 1, policy_version 27130 (0.0008) -[2023-10-17 01:21:32,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 55771136. Throughput: 0: 1774.7, 1: 1751.5. Samples: 13953456. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:21:32,215][61453] Avg episode reward: [(0, '7.940'), (1, '7.100')] -[2023-10-17 01:21:32,223][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000027328_27983872.pth... -[2023-10-17 01:21:32,223][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000027136_27787264.pth... -[2023-10-17 01:21:32,260][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000025472_26083328.pth -[2023-10-17 01:21:32,260][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000025664_26279936.pth -[2023-10-17 01:21:32,728][62373] Updated weights for policy 0, policy_version 27330 (0.0008) -[2023-10-17 01:21:33,098][62373] Updated weights for policy 0, policy_version 27340 (0.0009) -[2023-10-17 01:21:33,459][62373] Updated weights for policy 0, policy_version 27350 (0.0007) -[2023-10-17 01:21:33,828][62373] Updated weights for policy 0, policy_version 27360 (0.0007) -[2023-10-17 01:21:35,141][62408] Updated weights for policy 1, policy_version 27140 (0.0009) -[2023-10-17 01:21:35,530][62408] Updated weights for policy 1, policy_version 27150 (0.0010) -[2023-10-17 01:21:35,896][62408] Updated weights for policy 1, policy_version 27160 (0.0010) -[2023-10-17 01:21:37,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 55836672. Throughput: 0: 1760.7, 1: 1787.5. Samples: 13964454. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:21:37,215][61453] Avg episode reward: [(0, '8.130'), (1, '6.810')] -[2023-10-17 01:21:37,655][62373] Updated weights for policy 0, policy_version 27370 (0.0009) -[2023-10-17 01:21:38,014][62373] Updated weights for policy 0, policy_version 27380 (0.0009) -[2023-10-17 01:21:38,371][62373] Updated weights for policy 0, policy_version 27390 (0.0009) -[2023-10-17 01:21:39,669][62408] Updated weights for policy 1, policy_version 27170 (0.0008) -[2023-10-17 01:21:40,047][62408] Updated weights for policy 1, policy_version 27180 (0.0007) -[2023-10-17 01:21:40,418][62408] Updated weights for policy 1, policy_version 27190 (0.0007) -[2023-10-17 01:21:40,780][62408] Updated weights for policy 1, policy_version 27200 (0.0008) -[2023-10-17 01:21:42,184][62373] Updated weights for policy 0, policy_version 27400 (0.0008) -[2023-10-17 01:21:42,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 55902208. Throughput: 0: 1767.9, 1: 1753.7. Samples: 13985068. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:21:42,214][61453] Avg episode reward: [(0, '7.960'), (1, '7.290')] -[2023-10-17 01:21:42,550][62373] Updated weights for policy 0, policy_version 27410 (0.0007) -[2023-10-17 01:21:42,925][62373] Updated weights for policy 0, policy_version 27420 (0.0008) -[2023-10-17 01:21:44,709][62408] Updated weights for policy 1, policy_version 27210 (0.0008) -[2023-10-17 01:21:45,068][62408] Updated weights for policy 1, policy_version 27220 (0.0007) -[2023-10-17 01:21:45,439][62408] Updated weights for policy 1, policy_version 27230 (0.0007) -[2023-10-17 01:21:46,655][62373] Updated weights for policy 0, policy_version 27430 (0.0007) -[2023-10-17 01:21:47,036][62373] Updated weights for policy 0, policy_version 27440 (0.0009) -[2023-10-17 01:21:47,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 55967744. Throughput: 0: 1781.8, 1: 1754.4. Samples: 14006826. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:21:47,214][61453] Avg episode reward: [(0, '7.890'), (1, '6.980')] -[2023-10-17 01:21:47,392][62373] Updated weights for policy 0, policy_version 27450 (0.0008) -[2023-10-17 01:21:49,181][62408] Updated weights for policy 1, policy_version 27240 (0.0009) -[2023-10-17 01:21:49,545][62408] Updated weights for policy 1, policy_version 27250 (0.0011) -[2023-10-17 01:21:49,922][62408] Updated weights for policy 1, policy_version 27260 (0.0010) -[2023-10-17 01:21:51,180][62373] Updated weights for policy 0, policy_version 27460 (0.0008) -[2023-10-17 01:21:51,547][62373] Updated weights for policy 0, policy_version 27470 (0.0008) -[2023-10-17 01:21:51,912][62373] Updated weights for policy 0, policy_version 27480 (0.0010) -[2023-10-17 01:21:52,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14106.9). Total num frames: 56066048. Throughput: 0: 1764.4, 1: 1760.6. Samples: 14017310. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:21:52,215][61453] Avg episode reward: [(0, '8.030'), (1, '6.990')] -[2023-10-17 01:21:53,672][62408] Updated weights for policy 1, policy_version 27270 (0.0008) -[2023-10-17 01:21:54,035][62408] Updated weights for policy 1, policy_version 27280 (0.0011) -[2023-10-17 01:21:54,400][62408] Updated weights for policy 1, policy_version 27290 (0.0010) -[2023-10-17 01:21:55,785][62373] Updated weights for policy 0, policy_version 27490 (0.0007) -[2023-10-17 01:21:56,161][62373] Updated weights for policy 0, policy_version 27500 (0.0009) -[2023-10-17 01:21:56,530][62373] Updated weights for policy 0, policy_version 27510 (0.0007) -[2023-10-17 01:21:56,904][62373] Updated weights for policy 0, policy_version 27520 (0.0008) -[2023-10-17 01:21:57,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 56131584. Throughput: 0: 1788.4, 1: 1760.5. Samples: 14039038. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:21:57,215][61453] Avg episode reward: [(0, '7.750'), (1, '7.220')] -[2023-10-17 01:21:58,095][62408] Updated weights for policy 1, policy_version 27300 (0.0007) -[2023-10-17 01:21:58,468][62408] Updated weights for policy 1, policy_version 27310 (0.0008) -[2023-10-17 01:21:58,832][62408] Updated weights for policy 1, policy_version 27320 (0.0008) -[2023-10-17 01:22:00,629][62373] Updated weights for policy 0, policy_version 27530 (0.0010) -[2023-10-17 01:22:01,001][62373] Updated weights for policy 0, policy_version 27540 (0.0007) -[2023-10-17 01:22:01,368][62373] Updated weights for policy 0, policy_version 27550 (0.0009) -[2023-10-17 01:22:02,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 56197120. Throughput: 0: 1759.1, 1: 1777.3. Samples: 14059914. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:22:02,215][61453] Avg episode reward: [(0, '7.560'), (1, '7.410')] -[2023-10-17 01:22:02,631][62408] Updated weights for policy 1, policy_version 27330 (0.0008) -[2023-10-17 01:22:03,001][62408] Updated weights for policy 1, policy_version 27340 (0.0009) -[2023-10-17 01:22:03,374][62408] Updated weights for policy 1, policy_version 27350 (0.0011) -[2023-10-17 01:22:03,732][62408] Updated weights for policy 1, policy_version 27360 (0.0010) -[2023-10-17 01:22:05,311][62373] Updated weights for policy 0, policy_version 27560 (0.0007) -[2023-10-17 01:22:05,681][62373] Updated weights for policy 0, policy_version 27570 (0.0008) -[2023-10-17 01:22:06,052][62373] Updated weights for policy 0, policy_version 27580 (0.0008) -[2023-10-17 01:22:07,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 56262656. Throughput: 0: 1791.7, 1: 1761.5. Samples: 14070820. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:22:07,215][61453] Avg episode reward: [(0, '7.530'), (1, '7.550')] -[2023-10-17 01:22:07,594][62408] Updated weights for policy 1, policy_version 27370 (0.0009) -[2023-10-17 01:22:07,962][62408] Updated weights for policy 1, policy_version 27380 (0.0008) -[2023-10-17 01:22:08,334][62408] Updated weights for policy 1, policy_version 27390 (0.0007) -[2023-10-17 01:22:09,852][62373] Updated weights for policy 0, policy_version 27590 (0.0009) -[2023-10-17 01:22:10,225][62373] Updated weights for policy 0, policy_version 27600 (0.0008) -[2023-10-17 01:22:10,602][62373] Updated weights for policy 0, policy_version 27610 (0.0008) -[2023-10-17 01:22:12,129][62408] Updated weights for policy 1, policy_version 27400 (0.0007) -[2023-10-17 01:22:12,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 56328192. Throughput: 0: 1764.4, 1: 1764.5. Samples: 14091370. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:22:12,215][61453] Avg episode reward: [(0, '7.160'), (1, '7.270')] -[2023-10-17 01:22:12,503][62408] Updated weights for policy 1, policy_version 27410 (0.0009) -[2023-10-17 01:22:12,868][62408] Updated weights for policy 1, policy_version 27420 (0.0009) -[2023-10-17 01:22:14,465][62373] Updated weights for policy 0, policy_version 27620 (0.0010) -[2023-10-17 01:22:14,830][62373] Updated weights for policy 0, policy_version 27630 (0.0011) -[2023-10-17 01:22:15,204][62373] Updated weights for policy 0, policy_version 27640 (0.0010) -[2023-10-17 01:22:16,605][62408] Updated weights for policy 1, policy_version 27430 (0.0007) -[2023-10-17 01:22:16,974][62408] Updated weights for policy 1, policy_version 27440 (0.0009) -[2023-10-17 01:22:17,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 56393728. Throughput: 0: 1763.2, 1: 1782.6. Samples: 14113016. Policy #0 lag: (min: 18.0, avg: 18.2, max: 28.0) -[2023-10-17 01:22:17,214][61453] Avg episode reward: [(0, '7.200'), (1, '8.090')] -[2023-10-17 01:22:17,339][62408] Updated weights for policy 1, policy_version 27450 (0.0008) -[2023-10-17 01:22:18,928][62373] Updated weights for policy 0, policy_version 27650 (0.0009) -[2023-10-17 01:22:19,299][62373] Updated weights for policy 0, policy_version 27660 (0.0009) -[2023-10-17 01:22:19,674][62373] Updated weights for policy 0, policy_version 27670 (0.0008) -[2023-10-17 01:22:20,038][62373] Updated weights for policy 0, policy_version 27680 (0.0008) -[2023-10-17 01:22:21,333][62408] Updated weights for policy 1, policy_version 27460 (0.0007) -[2023-10-17 01:22:21,724][62408] Updated weights for policy 1, policy_version 27470 (0.0007) -[2023-10-17 01:22:22,095][62408] Updated weights for policy 1, policy_version 27480 (0.0007) -[2023-10-17 01:22:22,214][61453] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 56459264. Throughput: 0: 1771.5, 1: 1758.6. Samples: 14123310. Policy #0 lag: (min: 18.0, avg: 18.2, max: 28.0) -[2023-10-17 01:22:22,215][61453] Avg episode reward: [(0, '6.560'), (1, '8.250')] -[2023-10-17 01:22:23,844][62373] Updated weights for policy 0, policy_version 27690 (0.0010) -[2023-10-17 01:22:24,210][62373] Updated weights for policy 0, policy_version 27700 (0.0009) -[2023-10-17 01:22:24,582][62373] Updated weights for policy 0, policy_version 27710 (0.0011) -[2023-10-17 01:22:25,858][62408] Updated weights for policy 1, policy_version 27490 (0.0007) -[2023-10-17 01:22:26,214][62408] Updated weights for policy 1, policy_version 27500 (0.0009) -[2023-10-17 01:22:26,580][62408] Updated weights for policy 1, policy_version 27510 (0.0011) -[2023-10-17 01:22:26,950][62408] Updated weights for policy 1, policy_version 27520 (0.0010) -[2023-10-17 01:22:27,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 56557568. Throughput: 0: 1768.4, 1: 1786.5. Samples: 14145038. Policy #0 lag: (min: 18.0, avg: 18.2, max: 28.0) -[2023-10-17 01:22:27,215][61453] Avg episode reward: [(0, '6.680'), (1, '8.240')] -[2023-10-17 01:22:28,327][62373] Updated weights for policy 0, policy_version 27720 (0.0007) -[2023-10-17 01:22:28,696][62373] Updated weights for policy 0, policy_version 27730 (0.0008) -[2023-10-17 01:22:29,060][62373] Updated weights for policy 0, policy_version 27740 (0.0009) -[2023-10-17 01:22:31,006][62408] Updated weights for policy 1, policy_version 27530 (0.0008) -[2023-10-17 01:22:31,378][62408] Updated weights for policy 1, policy_version 27540 (0.0007) -[2023-10-17 01:22:31,752][62408] Updated weights for policy 1, policy_version 27550 (0.0007) -[2023-10-17 01:22:32,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 56623104. Throughput: 0: 1781.4, 1: 1757.4. Samples: 14166070. Policy #0 lag: (min: 18.0, avg: 18.2, max: 28.0) -[2023-10-17 01:22:32,215][61453] Avg episode reward: [(0, '7.360'), (1, '8.370')] -[2023-10-17 01:22:32,902][62373] Updated weights for policy 0, policy_version 27750 (0.0009) -[2023-10-17 01:22:33,283][62373] Updated weights for policy 0, policy_version 27760 (0.0009) -[2023-10-17 01:22:33,652][62373] Updated weights for policy 0, policy_version 27770 (0.0010) -[2023-10-17 01:22:35,678][62408] Updated weights for policy 1, policy_version 27560 (0.0010) -[2023-10-17 01:22:36,043][62408] Updated weights for policy 1, policy_version 27570 (0.0010) -[2023-10-17 01:22:36,412][62408] Updated weights for policy 1, policy_version 27580 (0.0010) -[2023-10-17 01:22:37,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 56688640. Throughput: 0: 1763.6, 1: 1784.1. Samples: 14176956. Policy #0 lag: (min: 18.0, avg: 18.2, max: 28.0) -[2023-10-17 01:22:37,214][61453] Avg episode reward: [(0, '7.380'), (1, '8.140')] -[2023-10-17 01:22:37,552][62373] Updated weights for policy 0, policy_version 27780 (0.0009) -[2023-10-17 01:22:37,927][62373] Updated weights for policy 0, policy_version 27790 (0.0008) -[2023-10-17 01:22:38,300][62373] Updated weights for policy 0, policy_version 27800 (0.0009) -[2023-10-17 01:22:40,276][62408] Updated weights for policy 1, policy_version 27590 (0.0008) -[2023-10-17 01:22:40,646][62408] Updated weights for policy 1, policy_version 27600 (0.0007) -[2023-10-17 01:22:41,010][62408] Updated weights for policy 1, policy_version 27610 (0.0009) -[2023-10-17 01:22:42,096][62373] Updated weights for policy 0, policy_version 27810 (0.0009) -[2023-10-17 01:22:42,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 56754176. Throughput: 0: 1765.4, 1: 1761.7. Samples: 14197758. Policy #0 lag: (min: 9.0, avg: 23.8, max: 41.0) -[2023-10-17 01:22:42,214][61453] Avg episode reward: [(0, '7.760'), (1, '8.040')] -[2023-10-17 01:22:42,473][62373] Updated weights for policy 0, policy_version 27820 (0.0010) -[2023-10-17 01:22:42,838][62373] Updated weights for policy 0, policy_version 27830 (0.0008) -[2023-10-17 01:22:43,205][62373] Updated weights for policy 0, policy_version 27840 (0.0011) -[2023-10-17 01:22:44,780][62408] Updated weights for policy 1, policy_version 27620 (0.0009) -[2023-10-17 01:22:45,147][62408] Updated weights for policy 1, policy_version 27630 (0.0009) -[2023-10-17 01:22:45,520][62408] Updated weights for policy 1, policy_version 27640 (0.0008) -[2023-10-17 01:22:47,015][62373] Updated weights for policy 0, policy_version 27850 (0.0007) -[2023-10-17 01:22:47,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 56819712. Throughput: 0: 1790.2, 1: 1745.8. Samples: 14219034. Policy #0 lag: (min: 9.0, avg: 23.8, max: 41.0) -[2023-10-17 01:22:47,214][61453] Avg episode reward: [(0, '7.800'), (1, '7.490')] -[2023-10-17 01:22:47,391][62373] Updated weights for policy 0, policy_version 27860 (0.0010) -[2023-10-17 01:22:47,754][62373] Updated weights for policy 0, policy_version 27870 (0.0009) -[2023-10-17 01:22:49,172][62408] Updated weights for policy 1, policy_version 27650 (0.0008) -[2023-10-17 01:22:49,540][62408] Updated weights for policy 1, policy_version 27660 (0.0007) -[2023-10-17 01:22:49,916][62408] Updated weights for policy 1, policy_version 27670 (0.0007) -[2023-10-17 01:22:50,284][62408] Updated weights for policy 1, policy_version 27680 (0.0008) -[2023-10-17 01:22:51,510][62373] Updated weights for policy 0, policy_version 27880 (0.0009) -[2023-10-17 01:22:51,878][62373] Updated weights for policy 0, policy_version 27890 (0.0007) -[2023-10-17 01:22:52,214][61453] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 14218.0). Total num frames: 56885248. Throughput: 0: 1770.5, 1: 1759.9. Samples: 14229690. Policy #0 lag: (min: 9.0, avg: 23.8, max: 41.0) -[2023-10-17 01:22:52,214][61453] Avg episode reward: [(0, '7.220'), (1, '7.240')] -[2023-10-17 01:22:52,243][62373] Updated weights for policy 0, policy_version 27900 (0.0008) -[2023-10-17 01:22:53,998][62408] Updated weights for policy 1, policy_version 27690 (0.0011) -[2023-10-17 01:22:54,380][62408] Updated weights for policy 1, policy_version 27700 (0.0011) -[2023-10-17 01:22:54,756][62408] Updated weights for policy 1, policy_version 27710 (0.0010) -[2023-10-17 01:22:55,968][62373] Updated weights for policy 0, policy_version 27910 (0.0009) -[2023-10-17 01:22:56,347][62373] Updated weights for policy 0, policy_version 27920 (0.0011) -[2023-10-17 01:22:56,716][62373] Updated weights for policy 0, policy_version 27930 (0.0007) -[2023-10-17 01:22:57,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 56983552. Throughput: 0: 1799.2, 1: 1752.0. Samples: 14251178. Policy #0 lag: (min: 9.0, avg: 23.8, max: 41.0) -[2023-10-17 01:22:57,215][61453] Avg episode reward: [(0, '7.810'), (1, '7.060')] -[2023-10-17 01:22:58,742][62408] Updated weights for policy 1, policy_version 27720 (0.0010) -[2023-10-17 01:22:59,108][62408] Updated weights for policy 1, policy_version 27730 (0.0009) -[2023-10-17 01:22:59,488][62408] Updated weights for policy 1, policy_version 27740 (0.0010) -[2023-10-17 01:23:00,508][62373] Updated weights for policy 0, policy_version 27940 (0.0009) -[2023-10-17 01:23:00,872][62373] Updated weights for policy 0, policy_version 27950 (0.0008) -[2023-10-17 01:23:01,244][62373] Updated weights for policy 0, policy_version 27960 (0.0007) -[2023-10-17 01:23:02,214][61453] Fps is (10 sec: 16383.6, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 57049088. Throughput: 0: 1775.1, 1: 1765.8. Samples: 14272358. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:23:02,215][61453] Avg episode reward: [(0, '7.410'), (1, '7.030')] -[2023-10-17 01:23:03,204][62408] Updated weights for policy 1, policy_version 27750 (0.0011) -[2023-10-17 01:23:03,575][62408] Updated weights for policy 1, policy_version 27760 (0.0009) -[2023-10-17 01:23:03,942][62408] Updated weights for policy 1, policy_version 27770 (0.0009) -[2023-10-17 01:23:04,952][62373] Updated weights for policy 0, policy_version 27970 (0.0007) -[2023-10-17 01:23:05,318][62373] Updated weights for policy 0, policy_version 27980 (0.0007) -[2023-10-17 01:23:05,692][62373] Updated weights for policy 0, policy_version 27990 (0.0009) -[2023-10-17 01:23:06,066][62373] Updated weights for policy 0, policy_version 28000 (0.0009) -[2023-10-17 01:23:07,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 57114624. Throughput: 0: 1799.2, 1: 1758.0. Samples: 14283388. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:23:07,215][61453] Avg episode reward: [(0, '7.680'), (1, '7.120')] -[2023-10-17 01:23:07,760][62408] Updated weights for policy 1, policy_version 27780 (0.0008) -[2023-10-17 01:23:08,134][62408] Updated weights for policy 1, policy_version 27790 (0.0009) -[2023-10-17 01:23:08,498][62408] Updated weights for policy 1, policy_version 27800 (0.0009) -[2023-10-17 01:23:09,884][62373] Updated weights for policy 0, policy_version 28010 (0.0007) -[2023-10-17 01:23:10,255][62373] Updated weights for policy 0, policy_version 28020 (0.0010) -[2023-10-17 01:23:10,627][62373] Updated weights for policy 0, policy_version 28030 (0.0008) -[2023-10-17 01:23:12,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 57180160. Throughput: 0: 1772.8, 1: 1761.9. Samples: 14304098. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:23:12,215][61453] Avg episode reward: [(0, '7.780'), (1, '7.220')] -[2023-10-17 01:23:12,283][62408] Updated weights for policy 1, policy_version 27810 (0.0009) -[2023-10-17 01:23:12,680][62408] Updated weights for policy 1, policy_version 27820 (0.0008) -[2023-10-17 01:23:13,049][62408] Updated weights for policy 1, policy_version 27830 (0.0008) -[2023-10-17 01:23:13,410][62408] Updated weights for policy 1, policy_version 27840 (0.0010) -[2023-10-17 01:23:14,488][62373] Updated weights for policy 0, policy_version 28040 (0.0007) -[2023-10-17 01:23:14,868][62373] Updated weights for policy 0, policy_version 28050 (0.0008) -[2023-10-17 01:23:15,242][62373] Updated weights for policy 0, policy_version 28060 (0.0008) -[2023-10-17 01:23:17,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 57245696. Throughput: 0: 1768.9, 1: 1789.6. Samples: 14326206. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:23:17,215][61453] Avg episode reward: [(0, '7.700'), (1, '7.600')] -[2023-10-17 01:23:17,419][62408] Updated weights for policy 1, policy_version 27850 (0.0008) -[2023-10-17 01:23:17,790][62408] Updated weights for policy 1, policy_version 27860 (0.0009) -[2023-10-17 01:23:18,160][62408] Updated weights for policy 1, policy_version 27870 (0.0009) -[2023-10-17 01:23:19,072][62373] Updated weights for policy 0, policy_version 28070 (0.0010) -[2023-10-17 01:23:19,434][62373] Updated weights for policy 0, policy_version 28080 (0.0011) -[2023-10-17 01:23:19,804][62373] Updated weights for policy 0, policy_version 28090 (0.0011) -[2023-10-17 01:23:21,919][62408] Updated weights for policy 1, policy_version 27880 (0.0009) -[2023-10-17 01:23:22,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 57311232. Throughput: 0: 1778.6, 1: 1759.2. Samples: 14336158. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:23:22,214][61453] Avg episode reward: [(0, '8.230'), (1, '7.750')] -[2023-10-17 01:23:22,303][62408] Updated weights for policy 1, policy_version 27890 (0.0009) -[2023-10-17 01:23:22,666][62408] Updated weights for policy 1, policy_version 27900 (0.0008) -[2023-10-17 01:23:23,615][62373] Updated weights for policy 0, policy_version 28100 (0.0010) -[2023-10-17 01:23:23,986][62373] Updated weights for policy 0, policy_version 28110 (0.0009) -[2023-10-17 01:23:24,350][62373] Updated weights for policy 0, policy_version 28120 (0.0010) -[2023-10-17 01:23:26,239][62408] Updated weights for policy 1, policy_version 27910 (0.0007) -[2023-10-17 01:23:26,602][62408] Updated weights for policy 1, policy_version 27920 (0.0010) -[2023-10-17 01:23:26,971][62408] Updated weights for policy 1, policy_version 27930 (0.0009) -[2023-10-17 01:23:27,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 57409536. Throughput: 0: 1773.0, 1: 1787.0. Samples: 14357960. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-17 01:23:27,215][61453] Avg episode reward: [(0, '8.380'), (1, '8.360')] -[2023-10-17 01:23:28,244][62373] Updated weights for policy 0, policy_version 28130 (0.0010) -[2023-10-17 01:23:28,609][62373] Updated weights for policy 0, policy_version 28140 (0.0008) -[2023-10-17 01:23:28,981][62373] Updated weights for policy 0, policy_version 28150 (0.0008) -[2023-10-17 01:23:29,353][62373] Updated weights for policy 0, policy_version 28160 (0.0010) -[2023-10-17 01:23:30,715][62408] Updated weights for policy 1, policy_version 27940 (0.0009) -[2023-10-17 01:23:31,077][62408] Updated weights for policy 1, policy_version 27950 (0.0007) -[2023-10-17 01:23:31,451][62408] Updated weights for policy 1, policy_version 27960 (0.0007) -[2023-10-17 01:23:32,214][61453] Fps is (10 sec: 16383.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 57475072. Throughput: 0: 1777.2, 1: 1771.6. Samples: 14378730. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-17 01:23:32,215][61453] Avg episode reward: [(0, '7.530'), (1, '7.950')] -[2023-10-17 01:23:32,226][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000027968_28639232.pth... -[2023-10-17 01:23:32,227][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000028160_28835840.pth... -[2023-10-17 01:23:32,258][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000026304_26935296.pth -[2023-10-17 01:23:32,263][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000026496_27131904.pth -[2023-10-17 01:23:33,012][62373] Updated weights for policy 0, policy_version 28170 (0.0008) -[2023-10-17 01:23:33,388][62373] Updated weights for policy 0, policy_version 28180 (0.0009) -[2023-10-17 01:23:33,752][62373] Updated weights for policy 0, policy_version 28190 (0.0010) -[2023-10-17 01:23:35,287][62408] Updated weights for policy 1, policy_version 27970 (0.0008) -[2023-10-17 01:23:35,662][62408] Updated weights for policy 1, policy_version 27980 (0.0011) -[2023-10-17 01:23:36,020][62408] Updated weights for policy 1, policy_version 27990 (0.0012) -[2023-10-17 01:23:36,387][62408] Updated weights for policy 1, policy_version 28000 (0.0010) -[2023-10-17 01:23:37,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 57540608. Throughput: 0: 1766.2, 1: 1794.0. Samples: 14389898. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-17 01:23:37,215][61453] Avg episode reward: [(0, '7.330'), (1, '7.890')] -[2023-10-17 01:23:37,547][62373] Updated weights for policy 0, policy_version 28200 (0.0008) -[2023-10-17 01:23:37,918][62373] Updated weights for policy 0, policy_version 28210 (0.0008) -[2023-10-17 01:23:38,284][62373] Updated weights for policy 0, policy_version 28220 (0.0008) -[2023-10-17 01:23:40,278][62408] Updated weights for policy 1, policy_version 28010 (0.0009) -[2023-10-17 01:23:40,650][62408] Updated weights for policy 1, policy_version 28020 (0.0009) -[2023-10-17 01:23:41,022][62408] Updated weights for policy 1, policy_version 28030 (0.0008) -[2023-10-17 01:23:42,104][62373] Updated weights for policy 0, policy_version 28230 (0.0008) -[2023-10-17 01:23:42,214][61453] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 57606144. Throughput: 0: 1770.5, 1: 1777.4. Samples: 14410830. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-17 01:23:42,215][61453] Avg episode reward: [(0, '7.250'), (1, '7.890')] -[2023-10-17 01:23:42,482][62373] Updated weights for policy 0, policy_version 28240 (0.0008) -[2023-10-17 01:23:42,859][62373] Updated weights for policy 0, policy_version 28250 (0.0008) -[2023-10-17 01:23:44,646][62408] Updated weights for policy 1, policy_version 28040 (0.0008) -[2023-10-17 01:23:45,023][62408] Updated weights for policy 1, policy_version 28050 (0.0008) -[2023-10-17 01:23:45,394][62408] Updated weights for policy 1, policy_version 28060 (0.0009) -[2023-10-17 01:23:46,698][62373] Updated weights for policy 0, policy_version 28260 (0.0008) -[2023-10-17 01:23:47,065][62373] Updated weights for policy 0, policy_version 28270 (0.0009) -[2023-10-17 01:23:47,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 57671680. Throughput: 0: 1782.7, 1: 1767.6. Samples: 14432120. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-17 01:23:47,214][61453] Avg episode reward: [(0, '7.170'), (1, '7.420')] -[2023-10-17 01:23:47,438][62373] Updated weights for policy 0, policy_version 28280 (0.0007) -[2023-10-17 01:23:49,263][62408] Updated weights for policy 1, policy_version 28070 (0.0010) -[2023-10-17 01:23:49,632][62408] Updated weights for policy 1, policy_version 28080 (0.0009) -[2023-10-17 01:23:50,002][62408] Updated weights for policy 1, policy_version 28090 (0.0008) -[2023-10-17 01:23:51,201][62373] Updated weights for policy 0, policy_version 28290 (0.0007) -[2023-10-17 01:23:51,584][62373] Updated weights for policy 0, policy_version 28300 (0.0008) -[2023-10-17 01:23:51,949][62373] Updated weights for policy 0, policy_version 28310 (0.0008) -[2023-10-17 01:23:52,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 57737216. Throughput: 0: 1765.7, 1: 1777.9. Samples: 14442852. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:23:52,214][61453] Avg episode reward: [(0, '6.820'), (1, '7.640')] -[2023-10-17 01:23:52,321][62373] Updated weights for policy 0, policy_version 28320 (0.0009) -[2023-10-17 01:23:53,734][62408] Updated weights for policy 1, policy_version 28100 (0.0008) -[2023-10-17 01:23:54,107][62408] Updated weights for policy 1, policy_version 28110 (0.0008) -[2023-10-17 01:23:54,473][62408] Updated weights for policy 1, policy_version 28120 (0.0008) -[2023-10-17 01:23:56,224][62373] Updated weights for policy 0, policy_version 28330 (0.0008) -[2023-10-17 01:23:56,583][62373] Updated weights for policy 0, policy_version 28340 (0.0008) -[2023-10-17 01:23:56,959][62373] Updated weights for policy 0, policy_version 28350 (0.0010) -[2023-10-17 01:23:57,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 57835520. Throughput: 0: 1793.1, 1: 1767.3. Samples: 14464316. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:23:57,215][61453] Avg episode reward: [(0, '7.400'), (1, '7.560')] -[2023-10-17 01:23:58,360][62408] Updated weights for policy 1, policy_version 28130 (0.0008) -[2023-10-17 01:23:58,750][62408] Updated weights for policy 1, policy_version 28140 (0.0007) -[2023-10-17 01:23:59,107][62408] Updated weights for policy 1, policy_version 28150 (0.0007) -[2023-10-17 01:23:59,468][62408] Updated weights for policy 1, policy_version 28160 (0.0007) -[2023-10-17 01:24:00,863][62373] Updated weights for policy 0, policy_version 28360 (0.0010) -[2023-10-17 01:24:01,239][62373] Updated weights for policy 0, policy_version 28370 (0.0007) -[2023-10-17 01:24:01,601][62373] Updated weights for policy 0, policy_version 28380 (0.0007) -[2023-10-17 01:24:02,214][61453] Fps is (10 sec: 16383.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 57901056. Throughput: 0: 1758.3, 1: 1767.8. Samples: 14484880. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:24:02,215][61453] Avg episode reward: [(0, '7.810'), (1, '7.300')] -[2023-10-17 01:24:03,254][62408] Updated weights for policy 1, policy_version 28170 (0.0010) -[2023-10-17 01:24:03,624][62408] Updated weights for policy 1, policy_version 28180 (0.0009) -[2023-10-17 01:24:03,997][62408] Updated weights for policy 1, policy_version 28190 (0.0007) -[2023-10-17 01:24:05,538][62373] Updated weights for policy 0, policy_version 28390 (0.0010) -[2023-10-17 01:24:05,908][62373] Updated weights for policy 0, policy_version 28400 (0.0011) -[2023-10-17 01:24:06,276][62373] Updated weights for policy 0, policy_version 28410 (0.0011) -[2023-10-17 01:24:07,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 57966592. Throughput: 0: 1783.1, 1: 1768.4. Samples: 14495976. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:24:07,215][61453] Avg episode reward: [(0, '8.240'), (1, '7.320')] -[2023-10-17 01:24:07,756][62408] Updated weights for policy 1, policy_version 28200 (0.0007) -[2023-10-17 01:24:08,129][62408] Updated weights for policy 1, policy_version 28210 (0.0008) -[2023-10-17 01:24:08,495][62408] Updated weights for policy 1, policy_version 28220 (0.0009) -[2023-10-17 01:24:10,128][62373] Updated weights for policy 0, policy_version 28420 (0.0009) -[2023-10-17 01:24:10,491][62373] Updated weights for policy 0, policy_version 28430 (0.0008) -[2023-10-17 01:24:10,868][62373] Updated weights for policy 0, policy_version 28440 (0.0008) -[2023-10-17 01:24:12,214][61453] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 58032128. Throughput: 0: 1763.2, 1: 1766.8. Samples: 14516808. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:24:12,215][61453] Avg episode reward: [(0, '7.810'), (1, '8.010')] -[2023-10-17 01:24:12,392][62408] Updated weights for policy 1, policy_version 28230 (0.0010) -[2023-10-17 01:24:12,763][62408] Updated weights for policy 1, policy_version 28240 (0.0009) -[2023-10-17 01:24:13,135][62408] Updated weights for policy 1, policy_version 28250 (0.0009) -[2023-10-17 01:24:14,601][62373] Updated weights for policy 0, policy_version 28450 (0.0007) -[2023-10-17 01:24:14,967][62373] Updated weights for policy 0, policy_version 28460 (0.0008) -[2023-10-17 01:24:15,348][62373] Updated weights for policy 0, policy_version 28470 (0.0008) -[2023-10-17 01:24:15,719][62373] Updated weights for policy 0, policy_version 28480 (0.0008) -[2023-10-17 01:24:16,944][62408] Updated weights for policy 1, policy_version 28260 (0.0009) -[2023-10-17 01:24:17,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 58097664. Throughput: 0: 1760.8, 1: 1788.6. Samples: 14538454. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:24:17,215][61453] Avg episode reward: [(0, '7.590'), (1, '7.960')] -[2023-10-17 01:24:17,314][62408] Updated weights for policy 1, policy_version 28270 (0.0008) -[2023-10-17 01:24:17,683][62408] Updated weights for policy 1, policy_version 28280 (0.0009) -[2023-10-17 01:24:19,514][62373] Updated weights for policy 0, policy_version 28490 (0.0011) -[2023-10-17 01:24:19,880][62373] Updated weights for policy 0, policy_version 28500 (0.0008) -[2023-10-17 01:24:20,251][62373] Updated weights for policy 0, policy_version 28510 (0.0009) -[2023-10-17 01:24:21,497][62408] Updated weights for policy 1, policy_version 28290 (0.0010) -[2023-10-17 01:24:21,878][62408] Updated weights for policy 1, policy_version 28300 (0.0009) -[2023-10-17 01:24:22,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 58163200. Throughput: 0: 1771.1, 1: 1756.9. Samples: 14548658. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:24:22,215][61453] Avg episode reward: [(0, '7.870'), (1, '8.200')] -[2023-10-17 01:24:22,249][62408] Updated weights for policy 1, policy_version 28310 (0.0012) -[2023-10-17 01:24:22,616][62408] Updated weights for policy 1, policy_version 28320 (0.0010) -[2023-10-17 01:24:24,012][62373] Updated weights for policy 0, policy_version 28520 (0.0007) -[2023-10-17 01:24:24,387][62373] Updated weights for policy 0, policy_version 28530 (0.0008) -[2023-10-17 01:24:24,750][62373] Updated weights for policy 0, policy_version 28540 (0.0008) -[2023-10-17 01:24:26,499][62408] Updated weights for policy 1, policy_version 28330 (0.0008) -[2023-10-17 01:24:26,865][62408] Updated weights for policy 1, policy_version 28340 (0.0009) -[2023-10-17 01:24:27,214][61453] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 58228736. Throughput: 0: 1760.5, 1: 1786.5. Samples: 14570446. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:24:27,215][61453] Avg episode reward: [(0, '7.100'), (1, '7.960')] -[2023-10-17 01:24:27,225][62408] Updated weights for policy 1, policy_version 28350 (0.0008) -[2023-10-17 01:24:28,535][62373] Updated weights for policy 0, policy_version 28550 (0.0008) -[2023-10-17 01:24:28,906][62373] Updated weights for policy 0, policy_version 28560 (0.0008) -[2023-10-17 01:24:29,275][62373] Updated weights for policy 0, policy_version 28570 (0.0008) -[2023-10-17 01:24:30,978][62408] Updated weights for policy 1, policy_version 28360 (0.0009) -[2023-10-17 01:24:31,352][62408] Updated weights for policy 1, policy_version 28370 (0.0011) -[2023-10-17 01:24:31,726][62408] Updated weights for policy 1, policy_version 28380 (0.0008) -[2023-10-17 01:24:32,214][61453] Fps is (10 sec: 16383.4, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 58327040. Throughput: 0: 1772.8, 1: 1766.1. Samples: 14591374. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:24:32,216][61453] Avg episode reward: [(0, '7.230'), (1, '8.230')] -[2023-10-17 01:24:33,004][62373] Updated weights for policy 0, policy_version 28580 (0.0008) -[2023-10-17 01:24:33,369][62373] Updated weights for policy 0, policy_version 28590 (0.0008) -[2023-10-17 01:24:33,752][62373] Updated weights for policy 0, policy_version 28600 (0.0008) -[2023-10-17 01:24:35,521][62408] Updated weights for policy 1, policy_version 28390 (0.0008) -[2023-10-17 01:24:35,884][62408] Updated weights for policy 1, policy_version 28400 (0.0011) -[2023-10-17 01:24:36,258][62408] Updated weights for policy 1, policy_version 28410 (0.0009) -[2023-10-17 01:24:37,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 58392576. Throughput: 0: 1761.6, 1: 1783.4. Samples: 14602376. Policy #0 lag: (min: 17.0, avg: 21.3, max: 49.0) -[2023-10-17 01:24:37,214][61453] Avg episode reward: [(0, '7.340'), (1, '8.020')] -[2023-10-17 01:24:37,533][62373] Updated weights for policy 0, policy_version 28610 (0.0009) -[2023-10-17 01:24:37,898][62373] Updated weights for policy 0, policy_version 28620 (0.0010) -[2023-10-17 01:24:38,283][62373] Updated weights for policy 0, policy_version 28630 (0.0010) -[2023-10-17 01:24:38,651][62373] Updated weights for policy 0, policy_version 28640 (0.0007) -[2023-10-17 01:24:40,277][62408] Updated weights for policy 1, policy_version 28420 (0.0009) -[2023-10-17 01:24:40,632][62408] Updated weights for policy 1, policy_version 28430 (0.0008) -[2023-10-17 01:24:41,006][62408] Updated weights for policy 1, policy_version 28440 (0.0008) -[2023-10-17 01:24:42,214][61453] Fps is (10 sec: 13107.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 58458112. Throughput: 0: 1766.4, 1: 1769.0. Samples: 14623410. Policy #0 lag: (min: 17.0, avg: 21.3, max: 49.0) -[2023-10-17 01:24:42,215][61453] Avg episode reward: [(0, '7.670'), (1, '7.440')] -[2023-10-17 01:24:42,346][62373] Updated weights for policy 0, policy_version 28650 (0.0008) -[2023-10-17 01:24:42,712][62373] Updated weights for policy 0, policy_version 28660 (0.0008) -[2023-10-17 01:24:43,080][62373] Updated weights for policy 0, policy_version 28670 (0.0007) -[2023-10-17 01:24:44,927][62408] Updated weights for policy 1, policy_version 28450 (0.0011) -[2023-10-17 01:24:45,348][62408] Updated weights for policy 1, policy_version 28460 (0.0010) -[2023-10-17 01:24:45,726][62408] Updated weights for policy 1, policy_version 28470 (0.0010) -[2023-10-17 01:24:46,082][62408] Updated weights for policy 1, policy_version 28480 (0.0011) -[2023-10-17 01:24:46,929][62373] Updated weights for policy 0, policy_version 28680 (0.0008) -[2023-10-17 01:24:47,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 58523648. Throughput: 0: 1792.4, 1: 1752.4. Samples: 14644394. Policy #0 lag: (min: 17.0, avg: 21.3, max: 49.0) -[2023-10-17 01:24:47,214][61453] Avg episode reward: [(0, '7.870'), (1, '7.950')] -[2023-10-17 01:24:47,295][62373] Updated weights for policy 0, policy_version 28690 (0.0007) -[2023-10-17 01:24:47,665][62373] Updated weights for policy 0, policy_version 28700 (0.0007) -[2023-10-17 01:24:49,880][62408] Updated weights for policy 1, policy_version 28490 (0.0007) -[2023-10-17 01:24:50,241][62408] Updated weights for policy 1, policy_version 28500 (0.0007) -[2023-10-17 01:24:50,607][62408] Updated weights for policy 1, policy_version 28510 (0.0009) -[2023-10-17 01:24:51,578][62373] Updated weights for policy 0, policy_version 28710 (0.0008) -[2023-10-17 01:24:51,948][62373] Updated weights for policy 0, policy_version 28720 (0.0010) -[2023-10-17 01:24:52,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 58589184. Throughput: 0: 1769.5, 1: 1772.4. Samples: 14655360. Policy #0 lag: (min: 17.0, avg: 21.3, max: 49.0) -[2023-10-17 01:24:52,215][61453] Avg episode reward: [(0, '7.580'), (1, '8.110')] -[2023-10-17 01:24:52,316][62373] Updated weights for policy 0, policy_version 28730 (0.0007) -[2023-10-17 01:24:54,411][62408] Updated weights for policy 1, policy_version 28520 (0.0010) -[2023-10-17 01:24:54,781][62408] Updated weights for policy 1, policy_version 28530 (0.0009) -[2023-10-17 01:24:55,143][62408] Updated weights for policy 1, policy_version 28540 (0.0009) -[2023-10-17 01:24:55,964][62373] Updated weights for policy 0, policy_version 28740 (0.0009) -[2023-10-17 01:24:56,328][62373] Updated weights for policy 0, policy_version 28750 (0.0007) -[2023-10-17 01:24:56,696][62373] Updated weights for policy 0, policy_version 28760 (0.0009) -[2023-10-17 01:24:57,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 58687488. Throughput: 0: 1799.3, 1: 1752.9. Samples: 14676656. Policy #0 lag: (min: 3.0, avg: 10.0, max: 35.0) -[2023-10-17 01:24:57,215][61453] Avg episode reward: [(0, '8.100'), (1, '8.620')] -[2023-10-17 01:24:57,217][62252] Saving new best policy, reward=8.620! -[2023-10-17 01:24:59,006][62408] Updated weights for policy 1, policy_version 28550 (0.0010) -[2023-10-17 01:24:59,384][62408] Updated weights for policy 1, policy_version 28560 (0.0010) -[2023-10-17 01:24:59,750][62408] Updated weights for policy 1, policy_version 28570 (0.0008) -[2023-10-17 01:25:00,512][62373] Updated weights for policy 0, policy_version 28770 (0.0009) -[2023-10-17 01:25:00,876][62373] Updated weights for policy 0, policy_version 28780 (0.0008) -[2023-10-17 01:25:01,251][62373] Updated weights for policy 0, policy_version 28790 (0.0007) -[2023-10-17 01:25:01,619][62373] Updated weights for policy 0, policy_version 28800 (0.0007) -[2023-10-17 01:25:02,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 58753024. Throughput: 0: 1776.2, 1: 1761.0. Samples: 14697628. Policy #0 lag: (min: 3.0, avg: 10.0, max: 35.0) -[2023-10-17 01:25:02,215][61453] Avg episode reward: [(0, '7.640'), (1, '7.790')] -[2023-10-17 01:25:03,353][62408] Updated weights for policy 1, policy_version 28580 (0.0008) -[2023-10-17 01:25:03,715][62408] Updated weights for policy 1, policy_version 28590 (0.0007) -[2023-10-17 01:25:04,093][62408] Updated weights for policy 1, policy_version 28600 (0.0009) -[2023-10-17 01:25:05,377][62373] Updated weights for policy 0, policy_version 28810 (0.0008) -[2023-10-17 01:25:05,735][62373] Updated weights for policy 0, policy_version 28820 (0.0008) -[2023-10-17 01:25:06,114][62373] Updated weights for policy 0, policy_version 28830 (0.0008) -[2023-10-17 01:25:07,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 58818560. Throughput: 0: 1800.6, 1: 1758.9. Samples: 14708836. Policy #0 lag: (min: 3.0, avg: 10.0, max: 35.0) -[2023-10-17 01:25:07,215][61453] Avg episode reward: [(0, '7.680'), (1, '8.190')] -[2023-10-17 01:25:07,871][62408] Updated weights for policy 1, policy_version 28610 (0.0010) -[2023-10-17 01:25:08,228][62408] Updated weights for policy 1, policy_version 28620 (0.0009) -[2023-10-17 01:25:08,602][62408] Updated weights for policy 1, policy_version 28630 (0.0007) -[2023-10-17 01:25:08,963][62408] Updated weights for policy 1, policy_version 28640 (0.0008) -[2023-10-17 01:25:09,778][62373] Updated weights for policy 0, policy_version 28840 (0.0010) -[2023-10-17 01:25:10,142][62373] Updated weights for policy 0, policy_version 28850 (0.0010) -[2023-10-17 01:25:10,522][62373] Updated weights for policy 0, policy_version 28860 (0.0008) -[2023-10-17 01:25:12,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 58884096. Throughput: 0: 1774.8, 1: 1759.1. Samples: 14729468. Policy #0 lag: (min: 3.0, avg: 10.0, max: 35.0) -[2023-10-17 01:25:12,214][61453] Avg episode reward: [(0, '7.430'), (1, '8.180')] -[2023-10-17 01:25:12,747][62408] Updated weights for policy 1, policy_version 28650 (0.0010) -[2023-10-17 01:25:13,109][62408] Updated weights for policy 1, policy_version 28660 (0.0010) -[2023-10-17 01:25:13,478][62408] Updated weights for policy 1, policy_version 28670 (0.0007) -[2023-10-17 01:25:14,187][62373] Updated weights for policy 0, policy_version 28870 (0.0011) -[2023-10-17 01:25:14,555][62373] Updated weights for policy 0, policy_version 28880 (0.0008) -[2023-10-17 01:25:14,931][62373] Updated weights for policy 0, policy_version 28890 (0.0008) -[2023-10-17 01:25:17,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 58949632. Throughput: 0: 1777.6, 1: 1786.1. Samples: 14751738. Policy #0 lag: (min: 3.0, avg: 10.0, max: 35.0) -[2023-10-17 01:25:17,214][61453] Avg episode reward: [(0, '7.810'), (1, '7.950')] -[2023-10-17 01:25:17,321][62408] Updated weights for policy 1, policy_version 28680 (0.0007) -[2023-10-17 01:25:17,691][62408] Updated weights for policy 1, policy_version 28690 (0.0008) -[2023-10-17 01:25:18,061][62408] Updated weights for policy 1, policy_version 28700 (0.0007) -[2023-10-17 01:25:18,662][62373] Updated weights for policy 0, policy_version 28900 (0.0008) -[2023-10-17 01:25:19,042][62373] Updated weights for policy 0, policy_version 28910 (0.0009) -[2023-10-17 01:25:19,416][62373] Updated weights for policy 0, policy_version 28920 (0.0008) -[2023-10-17 01:25:21,821][62408] Updated weights for policy 1, policy_version 28710 (0.0010) -[2023-10-17 01:25:22,190][62408] Updated weights for policy 1, policy_version 28720 (0.0010) -[2023-10-17 01:25:22,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 59015168. Throughput: 0: 1777.8, 1: 1754.6. Samples: 14761332. Policy #0 lag: (min: 31.0, avg: 35.8, max: 63.0) -[2023-10-17 01:25:22,215][61453] Avg episode reward: [(0, '8.170'), (1, '7.410')] -[2023-10-17 01:25:22,553][62408] Updated weights for policy 1, policy_version 28730 (0.0008) -[2023-10-17 01:25:23,209][62373] Updated weights for policy 0, policy_version 28930 (0.0008) -[2023-10-17 01:25:23,571][62373] Updated weights for policy 0, policy_version 28940 (0.0010) -[2023-10-17 01:25:23,935][62373] Updated weights for policy 0, policy_version 28950 (0.0008) -[2023-10-17 01:25:24,310][62373] Updated weights for policy 0, policy_version 28960 (0.0007) -[2023-10-17 01:25:26,501][62408] Updated weights for policy 1, policy_version 28740 (0.0008) -[2023-10-17 01:25:26,865][62408] Updated weights for policy 1, policy_version 28750 (0.0010) -[2023-10-17 01:25:27,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 59080704. Throughput: 0: 1783.1, 1: 1778.3. Samples: 14783678. Policy #0 lag: (min: 31.0, avg: 35.8, max: 63.0) -[2023-10-17 01:25:27,215][61453] Avg episode reward: [(0, '7.980'), (1, '7.220')] -[2023-10-17 01:25:27,230][62408] Updated weights for policy 1, policy_version 28760 (0.0010) -[2023-10-17 01:25:28,136][62373] Updated weights for policy 0, policy_version 28970 (0.0008) -[2023-10-17 01:25:28,502][62373] Updated weights for policy 0, policy_version 28980 (0.0007) -[2023-10-17 01:25:28,877][62373] Updated weights for policy 0, policy_version 28990 (0.0008) -[2023-10-17 01:25:31,238][62408] Updated weights for policy 1, policy_version 28770 (0.0010) -[2023-10-17 01:25:31,643][62408] Updated weights for policy 1, policy_version 28780 (0.0009) -[2023-10-17 01:25:32,016][62408] Updated weights for policy 1, policy_version 28790 (0.0008) -[2023-10-17 01:25:32,214][61453] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 59146240. Throughput: 0: 1792.6, 1: 1776.3. Samples: 14804994. Policy #0 lag: (min: 31.0, avg: 35.8, max: 63.0) -[2023-10-17 01:25:32,214][61453] Avg episode reward: [(0, '8.440'), (1, '7.830')] -[2023-10-17 01:25:32,379][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000028800_29491200.pth... -[2023-10-17 01:25:32,384][62408] Updated weights for policy 1, policy_version 28800 (0.0008) -[2023-10-17 01:25:32,412][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000027136_27787264.pth -[2023-10-17 01:25:32,575][62373] Updated weights for policy 0, policy_version 29000 (0.0007) -[2023-10-17 01:25:32,948][62373] Updated weights for policy 0, policy_version 29010 (0.0007) -[2023-10-17 01:25:33,310][62373] Updated weights for policy 0, policy_version 29020 (0.0007) -[2023-10-17 01:25:33,455][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000029024_29720576.pth... -[2023-10-17 01:25:33,484][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000027328_27983872.pth -[2023-10-17 01:25:33,488][62094] Saving new best policy, reward=8.440! -[2023-10-17 01:25:36,217][62408] Updated weights for policy 1, policy_version 28810 (0.0011) -[2023-10-17 01:25:36,583][62408] Updated weights for policy 1, policy_version 28820 (0.0008) -[2023-10-17 01:25:36,951][62408] Updated weights for policy 1, policy_version 28830 (0.0007) -[2023-10-17 01:25:37,109][62373] Updated weights for policy 0, policy_version 29030 (0.0008) -[2023-10-17 01:25:37,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 59244544. Throughput: 0: 1787.6, 1: 1771.3. Samples: 14815512. Policy #0 lag: (min: 31.0, avg: 35.8, max: 63.0) -[2023-10-17 01:25:37,215][61453] Avg episode reward: [(0, '7.740'), (1, '7.190')] -[2023-10-17 01:25:37,491][62373] Updated weights for policy 0, policy_version 29040 (0.0008) -[2023-10-17 01:25:37,862][62373] Updated weights for policy 0, policy_version 29050 (0.0009) -[2023-10-17 01:25:40,815][62408] Updated weights for policy 1, policy_version 28840 (0.0008) -[2023-10-17 01:25:41,175][62408] Updated weights for policy 1, policy_version 28850 (0.0011) -[2023-10-17 01:25:41,542][62408] Updated weights for policy 1, policy_version 28860 (0.0009) -[2023-10-17 01:25:41,711][62373] Updated weights for policy 0, policy_version 29060 (0.0008) -[2023-10-17 01:25:42,080][62373] Updated weights for policy 0, policy_version 29070 (0.0007) -[2023-10-17 01:25:42,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 59310080. Throughput: 0: 1782.8, 1: 1779.6. Samples: 14836962. Policy #0 lag: (min: 31.0, avg: 35.8, max: 63.0) -[2023-10-17 01:25:42,214][61453] Avg episode reward: [(0, '7.580'), (1, '7.480')] -[2023-10-17 01:25:42,457][62373] Updated weights for policy 0, policy_version 29080 (0.0008) -[2023-10-17 01:25:45,373][62408] Updated weights for policy 1, policy_version 28870 (0.0008) -[2023-10-17 01:25:45,743][62408] Updated weights for policy 1, policy_version 28880 (0.0007) -[2023-10-17 01:25:46,114][62408] Updated weights for policy 1, policy_version 28890 (0.0008) -[2023-10-17 01:25:46,126][62373] Updated weights for policy 0, policy_version 29090 (0.0008) -[2023-10-17 01:25:46,502][62373] Updated weights for policy 0, policy_version 29100 (0.0007) -[2023-10-17 01:25:46,875][62373] Updated weights for policy 0, policy_version 29110 (0.0007) -[2023-10-17 01:25:47,214][61453] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 59375616. Throughput: 0: 1792.9, 1: 1757.3. Samples: 14857386. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-17 01:25:47,214][61453] Avg episode reward: [(0, '7.490'), (1, '7.690')] -[2023-10-17 01:25:47,236][62373] Updated weights for policy 0, policy_version 29120 (0.0008) -[2023-10-17 01:25:49,921][62408] Updated weights for policy 1, policy_version 28900 (0.0008) -[2023-10-17 01:25:50,294][62408] Updated weights for policy 1, policy_version 28910 (0.0009) -[2023-10-17 01:25:50,674][62408] Updated weights for policy 1, policy_version 28920 (0.0008) -[2023-10-17 01:25:51,232][62373] Updated weights for policy 0, policy_version 29130 (0.0008) -[2023-10-17 01:25:51,597][62373] Updated weights for policy 0, policy_version 29140 (0.0007) -[2023-10-17 01:25:51,966][62373] Updated weights for policy 0, policy_version 29150 (0.0008) -[2023-10-17 01:25:52,214][61453] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14218.0). Total num frames: 59473920. Throughput: 0: 1777.7, 1: 1786.8. Samples: 14869240. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-17 01:25:52,215][61453] Avg episode reward: [(0, '7.590'), (1, '7.870')] -[2023-10-17 01:25:54,316][62408] Updated weights for policy 1, policy_version 28930 (0.0008) -[2023-10-17 01:25:54,691][62408] Updated weights for policy 1, policy_version 28940 (0.0007) -[2023-10-17 01:25:55,074][62408] Updated weights for policy 1, policy_version 28950 (0.0011) -[2023-10-17 01:25:55,439][62408] Updated weights for policy 1, policy_version 28960 (0.0009) -[2023-10-17 01:25:55,692][62373] Updated weights for policy 0, policy_version 29160 (0.0007) -[2023-10-17 01:25:56,062][62373] Updated weights for policy 0, policy_version 29170 (0.0008) -[2023-10-17 01:25:56,433][62373] Updated weights for policy 0, policy_version 29180 (0.0009) -[2023-10-17 01:25:57,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 59539456. Throughput: 0: 1805.4, 1: 1754.7. Samples: 14889674. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-17 01:25:57,215][61453] Avg episode reward: [(0, '7.440'), (1, '7.530')] -[2023-10-17 01:25:59,128][62408] Updated weights for policy 1, policy_version 28970 (0.0011) -[2023-10-17 01:25:59,505][62408] Updated weights for policy 1, policy_version 28980 (0.0007) -[2023-10-17 01:25:59,878][62408] Updated weights for policy 1, policy_version 28990 (0.0009) -[2023-10-17 01:26:00,302][62373] Updated weights for policy 0, policy_version 29190 (0.0008) -[2023-10-17 01:26:00,661][62373] Updated weights for policy 0, policy_version 29200 (0.0011) -[2023-10-17 01:26:01,027][62373] Updated weights for policy 0, policy_version 29210 (0.0010) -[2023-10-17 01:26:02,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 59604992. Throughput: 0: 1781.2, 1: 1755.0. Samples: 14910868. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-17 01:26:02,215][61453] Avg episode reward: [(0, '7.530'), (1, '7.500')] -[2023-10-17 01:26:03,711][62408] Updated weights for policy 1, policy_version 29000 (0.0009) -[2023-10-17 01:26:04,078][62408] Updated weights for policy 1, policy_version 29010 (0.0007) -[2023-10-17 01:26:04,451][62408] Updated weights for policy 1, policy_version 29020 (0.0007) -[2023-10-17 01:26:04,879][62373] Updated weights for policy 0, policy_version 29220 (0.0007) -[2023-10-17 01:26:05,260][62373] Updated weights for policy 0, policy_version 29230 (0.0008) -[2023-10-17 01:26:05,626][62373] Updated weights for policy 0, policy_version 29240 (0.0009) -[2023-10-17 01:26:07,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 59670528. Throughput: 0: 1805.1, 1: 1758.6. Samples: 14921700. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-17 01:26:07,215][61453] Avg episode reward: [(0, '8.220'), (1, '7.530')] -[2023-10-17 01:26:08,272][62408] Updated weights for policy 1, policy_version 29030 (0.0009) -[2023-10-17 01:26:08,634][62408] Updated weights for policy 1, policy_version 29040 (0.0008) -[2023-10-17 01:26:09,010][62408] Updated weights for policy 1, policy_version 29050 (0.0010) -[2023-10-17 01:26:09,342][62373] Updated weights for policy 0, policy_version 29250 (0.0008) -[2023-10-17 01:26:09,706][62373] Updated weights for policy 0, policy_version 29260 (0.0007) -[2023-10-17 01:26:10,083][62373] Updated weights for policy 0, policy_version 29270 (0.0009) -[2023-10-17 01:26:10,456][62373] Updated weights for policy 0, policy_version 29280 (0.0008) -[2023-10-17 01:26:12,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 59736064. Throughput: 0: 1771.7, 1: 1763.5. Samples: 14942762. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-17 01:26:12,215][61453] Avg episode reward: [(0, '7.970'), (1, '7.000')] -[2023-10-17 01:26:12,808][62408] Updated weights for policy 1, policy_version 29060 (0.0008) -[2023-10-17 01:26:13,176][62408] Updated weights for policy 1, policy_version 29070 (0.0008) -[2023-10-17 01:26:13,536][62408] Updated weights for policy 1, policy_version 29080 (0.0010) -[2023-10-17 01:26:14,212][62373] Updated weights for policy 0, policy_version 29290 (0.0011) -[2023-10-17 01:26:14,571][62373] Updated weights for policy 0, policy_version 29300 (0.0007) -[2023-10-17 01:26:14,949][62373] Updated weights for policy 0, policy_version 29310 (0.0008) -[2023-10-17 01:26:17,214][61453] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 59801600. Throughput: 0: 1773.1, 1: 1791.0. Samples: 14965378. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-17 01:26:17,214][61453] Avg episode reward: [(0, '7.910'), (1, '7.200')] -[2023-10-17 01:26:17,303][62408] Updated weights for policy 1, policy_version 29090 (0.0009) -[2023-10-17 01:26:17,684][62408] Updated weights for policy 1, policy_version 29100 (0.0007) -[2023-10-17 01:26:18,060][62408] Updated weights for policy 1, policy_version 29110 (0.0007) -[2023-10-17 01:26:18,431][62408] Updated weights for policy 1, policy_version 29120 (0.0007) -[2023-10-17 01:26:18,696][62373] Updated weights for policy 0, policy_version 29320 (0.0009) -[2023-10-17 01:26:19,066][62373] Updated weights for policy 0, policy_version 29330 (0.0009) -[2023-10-17 01:26:19,442][62373] Updated weights for policy 0, policy_version 29340 (0.0009) -[2023-10-17 01:26:22,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 59867136. Throughput: 0: 1771.2, 1: 1774.3. Samples: 14975060. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-17 01:26:22,215][61453] Avg episode reward: [(0, '8.100'), (1, '7.080')] -[2023-10-17 01:26:22,260][62408] Updated weights for policy 1, policy_version 29130 (0.0007) -[2023-10-17 01:26:22,630][62408] Updated weights for policy 1, policy_version 29140 (0.0008) -[2023-10-17 01:26:23,002][62408] Updated weights for policy 1, policy_version 29150 (0.0009) -[2023-10-17 01:26:23,180][62373] Updated weights for policy 0, policy_version 29350 (0.0009) -[2023-10-17 01:26:23,552][62373] Updated weights for policy 0, policy_version 29360 (0.0011) -[2023-10-17 01:26:23,934][62373] Updated weights for policy 0, policy_version 29370 (0.0011) -[2023-10-17 01:26:26,772][62408] Updated weights for policy 1, policy_version 29160 (0.0007) -[2023-10-17 01:26:27,140][62408] Updated weights for policy 1, policy_version 29170 (0.0007) -[2023-10-17 01:26:27,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 59932672. Throughput: 0: 1771.3, 1: 1781.1. Samples: 14996820. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-17 01:26:27,214][61453] Avg episode reward: [(0, '8.010'), (1, '7.410')] -[2023-10-17 01:26:27,503][62408] Updated weights for policy 1, policy_version 29180 (0.0007) -[2023-10-17 01:26:27,739][62373] Updated weights for policy 0, policy_version 29380 (0.0009) -[2023-10-17 01:26:28,111][62373] Updated weights for policy 0, policy_version 29390 (0.0008) -[2023-10-17 01:26:28,476][62373] Updated weights for policy 0, policy_version 29400 (0.0007) -[2023-10-17 01:26:31,382][62408] Updated weights for policy 1, policy_version 29190 (0.0007) -[2023-10-17 01:26:31,751][62408] Updated weights for policy 1, policy_version 29200 (0.0008) -[2023-10-17 01:26:32,117][62408] Updated weights for policy 1, policy_version 29210 (0.0008) -[2023-10-17 01:26:32,190][62373] Updated weights for policy 0, policy_version 29410 (0.0008) -[2023-10-17 01:26:32,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 59998208. Throughput: 0: 1791.5, 1: 1779.8. Samples: 15018094. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) -[2023-10-17 01:26:32,214][61453] Avg episode reward: [(0, '8.150'), (1, '7.260')] -[2023-10-17 01:26:32,560][62373] Updated weights for policy 0, policy_version 29420 (0.0009) -[2023-10-17 01:26:32,922][62373] Updated weights for policy 0, policy_version 29430 (0.0010) -[2023-10-17 01:26:33,276][62373] Updated weights for policy 0, policy_version 29440 (0.0009) -[2023-10-17 01:26:35,908][62408] Updated weights for policy 1, policy_version 29220 (0.0009) -[2023-10-17 01:26:36,274][62408] Updated weights for policy 1, policy_version 29230 (0.0011) -[2023-10-17 01:26:36,642][62408] Updated weights for policy 1, policy_version 29240 (0.0007) -[2023-10-17 01:26:37,171][62373] Updated weights for policy 0, policy_version 29450 (0.0008) -[2023-10-17 01:26:37,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 60096512. Throughput: 0: 1773.0, 1: 1768.4. Samples: 15028602. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) -[2023-10-17 01:26:37,215][61453] Avg episode reward: [(0, '7.970'), (1, '7.100')] -[2023-10-17 01:26:37,555][62373] Updated weights for policy 0, policy_version 29460 (0.0009) -[2023-10-17 01:26:37,923][62373] Updated weights for policy 0, policy_version 29470 (0.0011) -[2023-10-17 01:26:40,470][62408] Updated weights for policy 1, policy_version 29250 (0.0008) -[2023-10-17 01:26:40,836][62408] Updated weights for policy 1, policy_version 29260 (0.0008) -[2023-10-17 01:26:41,214][62408] Updated weights for policy 1, policy_version 29270 (0.0009) -[2023-10-17 01:26:41,574][62408] Updated weights for policy 1, policy_version 29280 (0.0007) -[2023-10-17 01:26:41,791][62373] Updated weights for policy 0, policy_version 29480 (0.0007) -[2023-10-17 01:26:42,158][62373] Updated weights for policy 0, policy_version 29490 (0.0007) -[2023-10-17 01:26:42,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 60162048. Throughput: 0: 1775.7, 1: 1784.2. Samples: 15049866. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) -[2023-10-17 01:26:42,215][61453] Avg episode reward: [(0, '8.750'), (1, '8.250')] -[2023-10-17 01:26:42,518][62373] Updated weights for policy 0, policy_version 29500 (0.0008) -[2023-10-17 01:26:42,665][62094] Saving new best policy, reward=8.750! -[2023-10-17 01:26:45,374][62408] Updated weights for policy 1, policy_version 29290 (0.0008) -[2023-10-17 01:26:45,741][62408] Updated weights for policy 1, policy_version 29300 (0.0007) -[2023-10-17 01:26:46,103][62408] Updated weights for policy 1, policy_version 29310 (0.0008) -[2023-10-17 01:26:46,299][62373] Updated weights for policy 0, policy_version 29510 (0.0008) -[2023-10-17 01:26:46,675][62373] Updated weights for policy 0, policy_version 29520 (0.0009) -[2023-10-17 01:26:47,041][62373] Updated weights for policy 0, policy_version 29530 (0.0007) -[2023-10-17 01:26:47,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 60227584. Throughput: 0: 1778.0, 1: 1767.1. Samples: 15070396. Policy #0 lag: (min: 31.0, avg: 34.9, max: 63.0) -[2023-10-17 01:26:47,214][61453] Avg episode reward: [(0, '8.320'), (1, '7.540')] -[2023-10-17 01:26:49,890][62408] Updated weights for policy 1, policy_version 29320 (0.0008) -[2023-10-17 01:26:50,260][62408] Updated weights for policy 1, policy_version 29330 (0.0009) -[2023-10-17 01:26:50,621][62408] Updated weights for policy 1, policy_version 29340 (0.0009) -[2023-10-17 01:26:51,081][62373] Updated weights for policy 0, policy_version 29540 (0.0010) -[2023-10-17 01:26:51,455][62373] Updated weights for policy 0, policy_version 29550 (0.0008) -[2023-10-17 01:26:51,826][62373] Updated weights for policy 0, policy_version 29560 (0.0009) -[2023-10-17 01:26:52,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 60325888. Throughput: 0: 1768.9, 1: 1791.5. Samples: 15081918. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:26:52,215][61453] Avg episode reward: [(0, '7.940'), (1, '7.560')] -[2023-10-17 01:26:54,649][62408] Updated weights for policy 1, policy_version 29350 (0.0009) -[2023-10-17 01:26:55,020][62408] Updated weights for policy 1, policy_version 29360 (0.0008) -[2023-10-17 01:26:55,391][62408] Updated weights for policy 1, policy_version 29370 (0.0011) -[2023-10-17 01:26:55,504][62373] Updated weights for policy 0, policy_version 29570 (0.0009) -[2023-10-17 01:26:55,866][62373] Updated weights for policy 0, policy_version 29580 (0.0009) -[2023-10-17 01:26:56,230][62373] Updated weights for policy 0, policy_version 29590 (0.0009) -[2023-10-17 01:26:56,599][62373] Updated weights for policy 0, policy_version 29600 (0.0010) -[2023-10-17 01:26:57,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 60391424. Throughput: 0: 1782.2, 1: 1760.8. Samples: 15102200. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:26:57,215][61453] Avg episode reward: [(0, '7.500'), (1, '7.720')] -[2023-10-17 01:26:59,344][62408] Updated weights for policy 1, policy_version 29380 (0.0008) -[2023-10-17 01:26:59,712][62408] Updated weights for policy 1, policy_version 29390 (0.0007) -[2023-10-17 01:27:00,079][62408] Updated weights for policy 1, policy_version 29400 (0.0008) -[2023-10-17 01:27:00,347][62373] Updated weights for policy 0, policy_version 29610 (0.0008) -[2023-10-17 01:27:00,712][62373] Updated weights for policy 0, policy_version 29620 (0.0009) -[2023-10-17 01:27:01,091][62373] Updated weights for policy 0, policy_version 29630 (0.0008) -[2023-10-17 01:27:02,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 60456960. Throughput: 0: 1759.9, 1: 1749.2. Samples: 15123292. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:27:02,215][61453] Avg episode reward: [(0, '7.550'), (1, '7.830')] -[2023-10-17 01:27:03,947][62408] Updated weights for policy 1, policy_version 29410 (0.0008) -[2023-10-17 01:27:04,354][62408] Updated weights for policy 1, policy_version 29420 (0.0009) -[2023-10-17 01:27:04,719][62408] Updated weights for policy 1, policy_version 29430 (0.0010) -[2023-10-17 01:27:04,987][62373] Updated weights for policy 0, policy_version 29640 (0.0008) -[2023-10-17 01:27:05,089][62408] Updated weights for policy 1, policy_version 29440 (0.0009) -[2023-10-17 01:27:05,359][62373] Updated weights for policy 0, policy_version 29650 (0.0008) -[2023-10-17 01:27:05,736][62373] Updated weights for policy 0, policy_version 29660 (0.0010) -[2023-10-17 01:27:07,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 60522496. Throughput: 0: 1783.2, 1: 1751.3. Samples: 15134112. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:27:07,215][61453] Avg episode reward: [(0, '7.670'), (1, '7.950')] -[2023-10-17 01:27:09,015][62408] Updated weights for policy 1, policy_version 29450 (0.0008) -[2023-10-17 01:27:09,390][62408] Updated weights for policy 1, policy_version 29460 (0.0009) -[2023-10-17 01:27:09,612][62373] Updated weights for policy 0, policy_version 29670 (0.0008) -[2023-10-17 01:27:09,751][62408] Updated weights for policy 1, policy_version 29470 (0.0008) -[2023-10-17 01:27:09,979][62373] Updated weights for policy 0, policy_version 29680 (0.0010) -[2023-10-17 01:27:10,347][62373] Updated weights for policy 0, policy_version 29690 (0.0010) -[2023-10-17 01:27:12,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 60588032. Throughput: 0: 1760.5, 1: 1739.6. Samples: 15154326. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:27:12,215][61453] Avg episode reward: [(0, '7.050'), (1, '7.230')] -[2023-10-17 01:27:13,653][62408] Updated weights for policy 1, policy_version 29480 (0.0011) -[2023-10-17 01:27:14,026][62408] Updated weights for policy 1, policy_version 29490 (0.0010) -[2023-10-17 01:27:14,142][62373] Updated weights for policy 0, policy_version 29700 (0.0008) -[2023-10-17 01:27:14,401][62408] Updated weights for policy 1, policy_version 29500 (0.0008) -[2023-10-17 01:27:14,524][62373] Updated weights for policy 0, policy_version 29710 (0.0008) -[2023-10-17 01:27:14,898][62373] Updated weights for policy 0, policy_version 29720 (0.0007) -[2023-10-17 01:27:17,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 60653568. Throughput: 0: 1757.0, 1: 1763.7. Samples: 15176528. Policy #0 lag: (min: 31.0, avg: 42.0, max: 63.0) -[2023-10-17 01:27:17,214][61453] Avg episode reward: [(0, '7.740'), (1, '7.560')] -[2023-10-17 01:27:18,172][62408] Updated weights for policy 1, policy_version 29510 (0.0008) -[2023-10-17 01:27:18,544][62408] Updated weights for policy 1, policy_version 29520 (0.0007) -[2023-10-17 01:27:18,670][62373] Updated weights for policy 0, policy_version 29730 (0.0008) -[2023-10-17 01:27:18,913][62408] Updated weights for policy 1, policy_version 29530 (0.0008) -[2023-10-17 01:27:19,032][62373] Updated weights for policy 0, policy_version 29740 (0.0009) -[2023-10-17 01:27:19,395][62373] Updated weights for policy 0, policy_version 29750 (0.0008) -[2023-10-17 01:27:19,763][62373] Updated weights for policy 0, policy_version 29760 (0.0008) -[2023-10-17 01:27:22,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 60719104. Throughput: 0: 1755.5, 1: 1743.3. Samples: 15186048. Policy #0 lag: (min: 31.0, avg: 42.0, max: 63.0) -[2023-10-17 01:27:22,215][61453] Avg episode reward: [(0, '7.830'), (1, '7.500')] -[2023-10-17 01:27:22,664][62408] Updated weights for policy 1, policy_version 29540 (0.0008) -[2023-10-17 01:27:23,030][62408] Updated weights for policy 1, policy_version 29550 (0.0008) -[2023-10-17 01:27:23,403][62408] Updated weights for policy 1, policy_version 29560 (0.0009) -[2023-10-17 01:27:23,668][62373] Updated weights for policy 0, policy_version 29770 (0.0007) -[2023-10-17 01:27:24,032][62373] Updated weights for policy 0, policy_version 29780 (0.0007) -[2023-10-17 01:27:24,397][62373] Updated weights for policy 0, policy_version 29790 (0.0010) -[2023-10-17 01:27:27,010][62408] Updated weights for policy 1, policy_version 29570 (0.0010) -[2023-10-17 01:27:27,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 60784640. Throughput: 0: 1759.6, 1: 1759.6. Samples: 15208226. Policy #0 lag: (min: 31.0, avg: 42.0, max: 63.0) -[2023-10-17 01:27:27,215][61453] Avg episode reward: [(0, '7.560'), (1, '7.460')] -[2023-10-17 01:27:27,389][62408] Updated weights for policy 1, policy_version 29580 (0.0009) -[2023-10-17 01:27:27,756][62408] Updated weights for policy 1, policy_version 29590 (0.0011) -[2023-10-17 01:27:28,121][62408] Updated weights for policy 1, policy_version 29600 (0.0007) -[2023-10-17 01:27:28,165][62373] Updated weights for policy 0, policy_version 29800 (0.0007) -[2023-10-17 01:27:28,546][62373] Updated weights for policy 0, policy_version 29810 (0.0009) -[2023-10-17 01:27:28,917][62373] Updated weights for policy 0, policy_version 29820 (0.0010) -[2023-10-17 01:27:31,895][62408] Updated weights for policy 1, policy_version 29610 (0.0008) -[2023-10-17 01:27:32,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 60850176. Throughput: 0: 1774.0, 1: 1766.0. Samples: 15229696. Policy #0 lag: (min: 31.0, avg: 42.0, max: 63.0) -[2023-10-17 01:27:32,215][61453] Avg episode reward: [(0, '8.130'), (1, '7.470')] -[2023-10-17 01:27:32,226][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000029824_30539776.pth... -[2023-10-17 01:27:32,262][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000028160_28835840.pth -[2023-10-17 01:27:32,266][62408] Updated weights for policy 1, policy_version 29620 (0.0009) -[2023-10-17 01:27:32,634][62408] Updated weights for policy 1, policy_version 29630 (0.0009) -[2023-10-17 01:27:32,706][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000029632_30343168.pth... -[2023-10-17 01:27:32,744][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000027968_28639232.pth -[2023-10-17 01:27:32,805][62373] Updated weights for policy 0, policy_version 29830 (0.0009) -[2023-10-17 01:27:33,181][62373] Updated weights for policy 0, policy_version 29840 (0.0009) -[2023-10-17 01:27:33,552][62373] Updated weights for policy 0, policy_version 29850 (0.0007) -[2023-10-17 01:27:36,467][62408] Updated weights for policy 1, policy_version 29640 (0.0008) -[2023-10-17 01:27:36,835][62408] Updated weights for policy 1, policy_version 29650 (0.0010) -[2023-10-17 01:27:37,205][62408] Updated weights for policy 1, policy_version 29660 (0.0008) -[2023-10-17 01:27:37,214][61453] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 60915712. Throughput: 0: 1762.2, 1: 1752.8. Samples: 15240094. Policy #0 lag: (min: 31.0, avg: 42.0, max: 63.0) -[2023-10-17 01:27:37,215][61453] Avg episode reward: [(0, '8.050'), (1, '7.410')] -[2023-10-17 01:27:37,308][62373] Updated weights for policy 0, policy_version 29860 (0.0008) -[2023-10-17 01:27:37,685][62373] Updated weights for policy 0, policy_version 29870 (0.0010) -[2023-10-17 01:27:38,051][62373] Updated weights for policy 0, policy_version 29880 (0.0009) -[2023-10-17 01:27:41,141][62408] Updated weights for policy 1, policy_version 29670 (0.0010) -[2023-10-17 01:27:41,513][62408] Updated weights for policy 1, policy_version 29680 (0.0011) -[2023-10-17 01:27:41,716][62373] Updated weights for policy 0, policy_version 29890 (0.0008) -[2023-10-17 01:27:41,880][62408] Updated weights for policy 1, policy_version 29690 (0.0008) -[2023-10-17 01:27:42,074][62373] Updated weights for policy 0, policy_version 29900 (0.0009) -[2023-10-17 01:27:42,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 61014016. Throughput: 0: 1775.2, 1: 1774.3. Samples: 15261926. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:27:42,215][61453] Avg episode reward: [(0, '7.780'), (1, '7.860')] -[2023-10-17 01:27:42,444][62373] Updated weights for policy 0, policy_version 29910 (0.0011) -[2023-10-17 01:27:42,805][62373] Updated weights for policy 0, policy_version 29920 (0.0010) -[2023-10-17 01:27:45,724][62408] Updated weights for policy 1, policy_version 29700 (0.0008) -[2023-10-17 01:27:46,090][62408] Updated weights for policy 1, policy_version 29710 (0.0010) -[2023-10-17 01:27:46,459][62408] Updated weights for policy 1, policy_version 29720 (0.0007) -[2023-10-17 01:27:46,692][62373] Updated weights for policy 0, policy_version 29930 (0.0007) -[2023-10-17 01:27:47,067][62373] Updated weights for policy 0, policy_version 29940 (0.0008) -[2023-10-17 01:27:47,214][61453] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 61079552. Throughput: 0: 1776.2, 1: 1740.8. Samples: 15281554. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:27:47,215][61453] Avg episode reward: [(0, '8.200'), (1, '7.400')] -[2023-10-17 01:27:47,442][62373] Updated weights for policy 0, policy_version 29950 (0.0009) -[2023-10-17 01:27:50,357][62408] Updated weights for policy 1, policy_version 29730 (0.0008) -[2023-10-17 01:27:50,769][62408] Updated weights for policy 1, policy_version 29740 (0.0008) -[2023-10-17 01:27:51,141][62408] Updated weights for policy 1, policy_version 29750 (0.0007) -[2023-10-17 01:27:51,238][62373] Updated weights for policy 0, policy_version 29960 (0.0007) -[2023-10-17 01:27:51,506][62408] Updated weights for policy 1, policy_version 29760 (0.0007) -[2023-10-17 01:27:51,602][62373] Updated weights for policy 0, policy_version 29970 (0.0007) -[2023-10-17 01:27:51,972][62373] Updated weights for policy 0, policy_version 29980 (0.0009) -[2023-10-17 01:27:52,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 61177856. Throughput: 0: 1767.9, 1: 1770.8. Samples: 15293356. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:27:52,215][61453] Avg episode reward: [(0, '8.140'), (1, '7.400')] -[2023-10-17 01:27:55,253][62408] Updated weights for policy 1, policy_version 29770 (0.0008) -[2023-10-17 01:27:55,623][62408] Updated weights for policy 1, policy_version 29780 (0.0007) -[2023-10-17 01:27:55,742][62373] Updated weights for policy 0, policy_version 29990 (0.0008) -[2023-10-17 01:27:55,983][62408] Updated weights for policy 1, policy_version 29790 (0.0008) -[2023-10-17 01:27:56,108][62373] Updated weights for policy 0, policy_version 30000 (0.0010) -[2023-10-17 01:27:56,477][62373] Updated weights for policy 0, policy_version 30010 (0.0009) -[2023-10-17 01:27:57,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 61243392. Throughput: 0: 1786.5, 1: 1757.1. Samples: 15313790. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:27:57,215][61453] Avg episode reward: [(0, '8.500'), (1, '7.250')] -[2023-10-17 01:27:59,900][62408] Updated weights for policy 1, policy_version 29800 (0.0009) -[2023-10-17 01:28:00,265][62408] Updated weights for policy 1, policy_version 29810 (0.0008) -[2023-10-17 01:28:00,486][62373] Updated weights for policy 0, policy_version 30020 (0.0008) -[2023-10-17 01:28:00,626][62408] Updated weights for policy 1, policy_version 29820 (0.0009) -[2023-10-17 01:28:00,868][62373] Updated weights for policy 0, policy_version 30030 (0.0009) -[2023-10-17 01:28:01,244][62373] Updated weights for policy 0, policy_version 30040 (0.0009) -[2023-10-17 01:28:02,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 61308928. Throughput: 0: 1755.4, 1: 1752.2. Samples: 15334372. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-17 01:28:02,215][61453] Avg episode reward: [(0, '8.850'), (1, '7.270')] -[2023-10-17 01:28:02,228][62094] Saving new best policy, reward=8.850! -[2023-10-17 01:28:04,406][62408] Updated weights for policy 1, policy_version 29830 (0.0007) -[2023-10-17 01:28:04,786][62408] Updated weights for policy 1, policy_version 29840 (0.0008) -[2023-10-17 01:28:04,955][62373] Updated weights for policy 0, policy_version 30050 (0.0009) -[2023-10-17 01:28:05,152][62408] Updated weights for policy 1, policy_version 29850 (0.0007) -[2023-10-17 01:28:05,326][62373] Updated weights for policy 0, policy_version 30060 (0.0008) -[2023-10-17 01:28:05,689][62373] Updated weights for policy 0, policy_version 30070 (0.0010) -[2023-10-17 01:28:06,052][62373] Updated weights for policy 0, policy_version 30080 (0.0009) -[2023-10-17 01:28:07,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 61374464. Throughput: 0: 1789.4, 1: 1767.0. Samples: 15346086. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-17 01:28:07,215][61453] Avg episode reward: [(0, '9.290'), (1, '7.690')] -[2023-10-17 01:28:07,216][62094] Saving new best policy, reward=9.290! -[2023-10-17 01:28:09,012][62408] Updated weights for policy 1, policy_version 29860 (0.0008) -[2023-10-17 01:28:09,389][62408] Updated weights for policy 1, policy_version 29870 (0.0008) -[2023-10-17 01:28:09,759][62408] Updated weights for policy 1, policy_version 29880 (0.0008) -[2023-10-17 01:28:10,048][62373] Updated weights for policy 0, policy_version 30090 (0.0009) -[2023-10-17 01:28:10,419][62373] Updated weights for policy 0, policy_version 30100 (0.0010) -[2023-10-17 01:28:10,790][62373] Updated weights for policy 0, policy_version 30110 (0.0007) -[2023-10-17 01:28:12,214][61453] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 61440000. Throughput: 0: 1751.7, 1: 1749.6. Samples: 15365788. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-17 01:28:12,214][61453] Avg episode reward: [(0, '9.110'), (1, '7.630')] -[2023-10-17 01:28:13,485][62408] Updated weights for policy 1, policy_version 29890 (0.0009) -[2023-10-17 01:28:13,857][62408] Updated weights for policy 1, policy_version 29900 (0.0007) -[2023-10-17 01:28:14,221][62408] Updated weights for policy 1, policy_version 29910 (0.0007) -[2023-10-17 01:28:14,544][62373] Updated weights for policy 0, policy_version 30120 (0.0007) -[2023-10-17 01:28:14,583][62408] Updated weights for policy 1, policy_version 29920 (0.0007) -[2023-10-17 01:28:14,924][62373] Updated weights for policy 0, policy_version 30130 (0.0007) -[2023-10-17 01:28:15,292][62373] Updated weights for policy 0, policy_version 30140 (0.0008) -[2023-10-17 01:28:17,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 61505536. Throughput: 0: 1756.2, 1: 1760.4. Samples: 15387944. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-17 01:28:17,215][61453] Avg episode reward: [(0, '9.470'), (1, '7.650')] -[2023-10-17 01:28:17,225][62094] Saving new best policy, reward=9.470! -[2023-10-17 01:28:18,486][62408] Updated weights for policy 1, policy_version 29930 (0.0007) -[2023-10-17 01:28:18,849][62408] Updated weights for policy 1, policy_version 29940 (0.0007) -[2023-10-17 01:28:19,137][62373] Updated weights for policy 0, policy_version 30150 (0.0007) -[2023-10-17 01:28:19,216][62408] Updated weights for policy 1, policy_version 29950 (0.0007) -[2023-10-17 01:28:19,516][62373] Updated weights for policy 0, policy_version 30160 (0.0009) -[2023-10-17 01:28:19,884][62373] Updated weights for policy 0, policy_version 30170 (0.0008) -[2023-10-17 01:28:22,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 61571072. Throughput: 0: 1758.6, 1: 1749.9. Samples: 15397976. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-17 01:28:22,215][61453] Avg episode reward: [(0, '8.790'), (1, '7.600')] -[2023-10-17 01:28:22,964][62408] Updated weights for policy 1, policy_version 29960 (0.0011) -[2023-10-17 01:28:23,331][62408] Updated weights for policy 1, policy_version 29970 (0.0011) -[2023-10-17 01:28:23,694][62408] Updated weights for policy 1, policy_version 29980 (0.0010) -[2023-10-17 01:28:23,730][62373] Updated weights for policy 0, policy_version 30180 (0.0008) -[2023-10-17 01:28:24,097][62373] Updated weights for policy 0, policy_version 30190 (0.0008) -[2023-10-17 01:28:24,467][62373] Updated weights for policy 0, policy_version 30200 (0.0007) -[2023-10-17 01:28:27,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 61636608. Throughput: 0: 1748.4, 1: 1753.1. Samples: 15419494. Policy #0 lag: (min: 26.0, avg: 26.0, max: 31.0) -[2023-10-17 01:28:27,215][61453] Avg episode reward: [(0, '8.810'), (1, '8.060')] -[2023-10-17 01:28:27,507][62408] Updated weights for policy 1, policy_version 29990 (0.0009) -[2023-10-17 01:28:27,871][62408] Updated weights for policy 1, policy_version 30000 (0.0008) -[2023-10-17 01:28:28,240][62408] Updated weights for policy 1, policy_version 30010 (0.0008) -[2023-10-17 01:28:28,400][62373] Updated weights for policy 0, policy_version 30210 (0.0007) -[2023-10-17 01:28:28,776][62373] Updated weights for policy 0, policy_version 30220 (0.0007) -[2023-10-17 01:28:29,132][62373] Updated weights for policy 0, policy_version 30230 (0.0009) -[2023-10-17 01:28:29,504][62373] Updated weights for policy 0, policy_version 30240 (0.0008) -[2023-10-17 01:28:32,161][62408] Updated weights for policy 1, policy_version 30020 (0.0007) -[2023-10-17 01:28:32,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 61702144. Throughput: 0: 1762.8, 1: 1789.0. Samples: 15441384. Policy #0 lag: (min: 26.0, avg: 26.0, max: 31.0) -[2023-10-17 01:28:32,215][61453] Avg episode reward: [(0, '9.480'), (1, '7.750')] -[2023-10-17 01:28:32,227][62094] Saving new best policy, reward=9.480! -[2023-10-17 01:28:32,532][62408] Updated weights for policy 1, policy_version 30030 (0.0007) -[2023-10-17 01:28:32,898][62408] Updated weights for policy 1, policy_version 30040 (0.0008) -[2023-10-17 01:28:33,234][62373] Updated weights for policy 0, policy_version 30250 (0.0008) -[2023-10-17 01:28:33,598][62373] Updated weights for policy 0, policy_version 30260 (0.0010) -[2023-10-17 01:28:33,965][62373] Updated weights for policy 0, policy_version 30270 (0.0010) -[2023-10-17 01:28:36,755][62408] Updated weights for policy 1, policy_version 30050 (0.0008) -[2023-10-17 01:28:37,159][62408] Updated weights for policy 1, policy_version 30060 (0.0009) -[2023-10-17 01:28:37,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 61767680. Throughput: 0: 1747.1, 1: 1758.1. Samples: 15451092. Policy #0 lag: (min: 26.0, avg: 26.0, max: 31.0) -[2023-10-17 01:28:37,215][61453] Avg episode reward: [(0, '8.410'), (1, '7.720')] -[2023-10-17 01:28:37,528][62408] Updated weights for policy 1, policy_version 30070 (0.0008) -[2023-10-17 01:28:37,855][62373] Updated weights for policy 0, policy_version 30280 (0.0007) -[2023-10-17 01:28:37,887][62408] Updated weights for policy 1, policy_version 30080 (0.0009) -[2023-10-17 01:28:38,218][62373] Updated weights for policy 0, policy_version 30290 (0.0007) -[2023-10-17 01:28:38,584][62373] Updated weights for policy 0, policy_version 30300 (0.0007) -[2023-10-17 01:28:41,786][62408] Updated weights for policy 1, policy_version 30090 (0.0007) -[2023-10-17 01:28:42,151][62408] Updated weights for policy 1, policy_version 30100 (0.0007) -[2023-10-17 01:28:42,214][61453] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 61833216. Throughput: 0: 1756.2, 1: 1777.2. Samples: 15472792. Policy #0 lag: (min: 26.0, avg: 26.0, max: 31.0) -[2023-10-17 01:28:42,215][61453] Avg episode reward: [(0, '8.740'), (1, '7.670')] -[2023-10-17 01:28:42,397][62373] Updated weights for policy 0, policy_version 30310 (0.0007) -[2023-10-17 01:28:42,516][62408] Updated weights for policy 1, policy_version 30110 (0.0008) -[2023-10-17 01:28:42,763][62373] Updated weights for policy 0, policy_version 30320 (0.0007) -[2023-10-17 01:28:43,137][62373] Updated weights for policy 0, policy_version 30330 (0.0009) -[2023-10-17 01:28:46,350][62408] Updated weights for policy 1, policy_version 30120 (0.0008) -[2023-10-17 01:28:46,723][62408] Updated weights for policy 1, policy_version 30130 (0.0010) -[2023-10-17 01:28:47,011][62373] Updated weights for policy 0, policy_version 30340 (0.0008) -[2023-10-17 01:28:47,093][62408] Updated weights for policy 1, policy_version 30140 (0.0008) -[2023-10-17 01:28:47,214][61453] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 61898752. Throughput: 0: 1786.4, 1: 1760.9. Samples: 15493998. Policy #0 lag: (min: 26.0, avg: 26.0, max: 31.0) -[2023-10-17 01:28:47,215][61453] Avg episode reward: [(0, '8.320'), (1, '8.110')] -[2023-10-17 01:28:47,405][62373] Updated weights for policy 0, policy_version 30350 (0.0007) -[2023-10-17 01:28:47,775][62373] Updated weights for policy 0, policy_version 30360 (0.0007) -[2023-10-17 01:28:50,895][62408] Updated weights for policy 1, policy_version 30150 (0.0007) -[2023-10-17 01:28:51,264][62408] Updated weights for policy 1, policy_version 30160 (0.0008) -[2023-10-17 01:28:51,608][62373] Updated weights for policy 0, policy_version 30370 (0.0009) -[2023-10-17 01:28:51,640][62408] Updated weights for policy 1, policy_version 30170 (0.0009) -[2023-10-17 01:28:51,976][62373] Updated weights for policy 0, policy_version 30380 (0.0009) -[2023-10-17 01:28:52,214][61453] Fps is (10 sec: 16384.4, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 61997056. Throughput: 0: 1751.9, 1: 1769.1. Samples: 15504528. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:28:52,214][61453] Avg episode reward: [(0, '8.540'), (1, '7.370')] -[2023-10-17 01:28:52,346][62373] Updated weights for policy 0, policy_version 30390 (0.0008) -[2023-10-17 01:28:52,721][62373] Updated weights for policy 0, policy_version 30400 (0.0007) -[2023-10-17 01:28:55,450][62408] Updated weights for policy 1, policy_version 30180 (0.0009) -[2023-10-17 01:28:55,820][62408] Updated weights for policy 1, policy_version 30190 (0.0009) -[2023-10-17 01:28:56,188][62408] Updated weights for policy 1, policy_version 30200 (0.0010) -[2023-10-17 01:28:56,613][62373] Updated weights for policy 0, policy_version 30410 (0.0009) -[2023-10-17 01:28:56,981][62373] Updated weights for policy 0, policy_version 30420 (0.0008) -[2023-10-17 01:28:57,214][61453] Fps is (10 sec: 16384.0, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 62062592. Throughput: 0: 1791.5, 1: 1771.5. Samples: 15526122. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:28:57,215][61453] Avg episode reward: [(0, '8.730'), (1, '7.320')] -[2023-10-17 01:28:57,351][62373] Updated weights for policy 0, policy_version 30430 (0.0007) -[2023-10-17 01:28:59,862][62408] Updated weights for policy 1, policy_version 30210 (0.0007) -[2023-10-17 01:29:00,235][62408] Updated weights for policy 1, policy_version 30220 (0.0009) -[2023-10-17 01:29:00,594][62408] Updated weights for policy 1, policy_version 30230 (0.0009) -[2023-10-17 01:29:00,959][62408] Updated weights for policy 1, policy_version 30240 (0.0008) -[2023-10-17 01:29:01,092][62373] Updated weights for policy 0, policy_version 30440 (0.0009) -[2023-10-17 01:29:01,453][62373] Updated weights for policy 0, policy_version 30450 (0.0011) -[2023-10-17 01:29:01,829][62373] Updated weights for policy 0, policy_version 30460 (0.0010) -[2023-10-17 01:29:02,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 62160896. Throughput: 0: 1760.4, 1: 1758.5. Samples: 15546294. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:29:02,215][61453] Avg episode reward: [(0, '7.970'), (1, '7.170')] -[2023-10-17 01:29:04,740][62408] Updated weights for policy 1, policy_version 30250 (0.0007) -[2023-10-17 01:29:05,114][62408] Updated weights for policy 1, policy_version 30260 (0.0007) -[2023-10-17 01:29:05,473][62408] Updated weights for policy 1, policy_version 30270 (0.0008) -[2023-10-17 01:29:05,552][62373] Updated weights for policy 0, policy_version 30470 (0.0008) -[2023-10-17 01:29:05,923][62373] Updated weights for policy 0, policy_version 30480 (0.0008) -[2023-10-17 01:29:06,289][62373] Updated weights for policy 0, policy_version 30490 (0.0011) -[2023-10-17 01:29:07,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 62226432. Throughput: 0: 1783.1, 1: 1778.0. Samples: 15558224. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:29:07,215][61453] Avg episode reward: [(0, '8.160'), (1, '6.830')] -[2023-10-17 01:29:09,397][62408] Updated weights for policy 1, policy_version 30280 (0.0007) -[2023-10-17 01:29:09,768][62408] Updated weights for policy 1, policy_version 30290 (0.0007) -[2023-10-17 01:29:10,135][62408] Updated weights for policy 1, policy_version 30300 (0.0007) -[2023-10-17 01:29:10,177][62373] Updated weights for policy 0, policy_version 30500 (0.0008) -[2023-10-17 01:29:10,546][62373] Updated weights for policy 0, policy_version 30510 (0.0007) -[2023-10-17 01:29:10,913][62373] Updated weights for policy 0, policy_version 30520 (0.0009) -[2023-10-17 01:29:12,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 62291968. Throughput: 0: 1769.6, 1: 1757.9. Samples: 15578230. Policy #0 lag: (min: 16.0, avg: 44.6, max: 48.0) -[2023-10-17 01:29:12,215][61453] Avg episode reward: [(0, '8.830'), (1, '6.390')] -[2023-10-17 01:29:14,007][62408] Updated weights for policy 1, policy_version 30310 (0.0008) -[2023-10-17 01:29:14,369][62408] Updated weights for policy 1, policy_version 30320 (0.0007) -[2023-10-17 01:29:14,711][62373] Updated weights for policy 0, policy_version 30530 (0.0010) -[2023-10-17 01:29:14,738][62408] Updated weights for policy 1, policy_version 30330 (0.0009) -[2023-10-17 01:29:15,074][62373] Updated weights for policy 0, policy_version 30540 (0.0009) -[2023-10-17 01:29:15,446][62373] Updated weights for policy 0, policy_version 30550 (0.0010) -[2023-10-17 01:29:15,818][62373] Updated weights for policy 0, policy_version 30560 (0.0010) -[2023-10-17 01:29:17,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 62357504. Throughput: 0: 1761.2, 1: 1754.9. Samples: 15599612. Policy #0 lag: (min: 16.0, avg: 44.6, max: 48.0) -[2023-10-17 01:29:17,215][61453] Avg episode reward: [(0, '8.960'), (1, '6.460')] -[2023-10-17 01:29:18,509][62408] Updated weights for policy 1, policy_version 30340 (0.0009) -[2023-10-17 01:29:18,878][62408] Updated weights for policy 1, policy_version 30350 (0.0008) -[2023-10-17 01:29:19,245][62408] Updated weights for policy 1, policy_version 30360 (0.0009) -[2023-10-17 01:29:19,674][62373] Updated weights for policy 0, policy_version 30570 (0.0007) -[2023-10-17 01:29:20,046][62373] Updated weights for policy 0, policy_version 30580 (0.0007) -[2023-10-17 01:29:20,409][62373] Updated weights for policy 0, policy_version 30590 (0.0007) -[2023-10-17 01:29:22,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 62423040. Throughput: 0: 1776.7, 1: 1751.8. Samples: 15609874. Policy #0 lag: (min: 16.0, avg: 44.6, max: 48.0) -[2023-10-17 01:29:22,215][61453] Avg episode reward: [(0, '9.400'), (1, '7.280')] -[2023-10-17 01:29:23,195][62408] Updated weights for policy 1, policy_version 30370 (0.0009) -[2023-10-17 01:29:23,617][62408] Updated weights for policy 1, policy_version 30380 (0.0008) -[2023-10-17 01:29:23,986][62408] Updated weights for policy 1, policy_version 30390 (0.0008) -[2023-10-17 01:29:24,271][62373] Updated weights for policy 0, policy_version 30600 (0.0011) -[2023-10-17 01:29:24,353][62408] Updated weights for policy 1, policy_version 30400 (0.0008) -[2023-10-17 01:29:24,632][62373] Updated weights for policy 0, policy_version 30610 (0.0011) -[2023-10-17 01:29:25,010][62373] Updated weights for policy 0, policy_version 30620 (0.0009) -[2023-10-17 01:29:27,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 62488576. Throughput: 0: 1760.0, 1: 1757.3. Samples: 15631072. Policy #0 lag: (min: 16.0, avg: 44.6, max: 48.0) -[2023-10-17 01:29:27,215][61453] Avg episode reward: [(0, '8.710'), (1, '7.330')] -[2023-10-17 01:29:28,188][62408] Updated weights for policy 1, policy_version 30410 (0.0010) -[2023-10-17 01:29:28,560][62408] Updated weights for policy 1, policy_version 30420 (0.0010) -[2023-10-17 01:29:28,888][62373] Updated weights for policy 0, policy_version 30630 (0.0009) -[2023-10-17 01:29:28,928][62408] Updated weights for policy 1, policy_version 30430 (0.0008) -[2023-10-17 01:29:29,254][62373] Updated weights for policy 0, policy_version 30640 (0.0010) -[2023-10-17 01:29:29,629][62373] Updated weights for policy 0, policy_version 30650 (0.0011) -[2023-10-17 01:29:32,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 62554112. Throughput: 0: 1759.3, 1: 1777.8. Samples: 15653170. Policy #0 lag: (min: 16.0, avg: 44.6, max: 48.0) -[2023-10-17 01:29:32,215][61453] Avg episode reward: [(0, '8.670'), (1, '7.800')] -[2023-10-17 01:29:32,227][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000030656_31391744.pth... -[2023-10-17 01:29:32,227][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000030432_31162368.pth... -[2023-10-17 01:29:32,260][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000029024_29720576.pth -[2023-10-17 01:29:32,265][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000028800_29491200.pth -[2023-10-17 01:29:32,704][62408] Updated weights for policy 1, policy_version 30440 (0.0007) -[2023-10-17 01:29:33,077][62408] Updated weights for policy 1, policy_version 30450 (0.0007) -[2023-10-17 01:29:33,430][62373] Updated weights for policy 0, policy_version 30660 (0.0010) -[2023-10-17 01:29:33,441][62408] Updated weights for policy 1, policy_version 30460 (0.0009) -[2023-10-17 01:29:33,822][62373] Updated weights for policy 0, policy_version 30670 (0.0009) -[2023-10-17 01:29:34,181][62373] Updated weights for policy 0, policy_version 30680 (0.0008) -[2023-10-17 01:29:37,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 62619648. Throughput: 0: 1759.2, 1: 1757.3. Samples: 15662774. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-17 01:29:37,214][61453] Avg episode reward: [(0, '8.120'), (1, '7.750')] -[2023-10-17 01:29:37,314][62408] Updated weights for policy 1, policy_version 30470 (0.0009) -[2023-10-17 01:29:37,681][62408] Updated weights for policy 1, policy_version 30480 (0.0008) -[2023-10-17 01:29:37,801][62373] Updated weights for policy 0, policy_version 30690 (0.0008) -[2023-10-17 01:29:38,041][62408] Updated weights for policy 1, policy_version 30490 (0.0008) -[2023-10-17 01:29:38,172][62373] Updated weights for policy 0, policy_version 30700 (0.0007) -[2023-10-17 01:29:38,544][62373] Updated weights for policy 0, policy_version 30710 (0.0010) -[2023-10-17 01:29:38,922][62373] Updated weights for policy 0, policy_version 30720 (0.0010) -[2023-10-17 01:29:41,891][62408] Updated weights for policy 1, policy_version 30500 (0.0008) -[2023-10-17 01:29:42,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 62685184. Throughput: 0: 1763.4, 1: 1763.8. Samples: 15684848. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-17 01:29:42,215][61453] Avg episode reward: [(0, '7.990'), (1, '7.820')] -[2023-10-17 01:29:42,259][62408] Updated weights for policy 1, policy_version 30510 (0.0007) -[2023-10-17 01:29:42,632][62408] Updated weights for policy 1, policy_version 30520 (0.0007) -[2023-10-17 01:29:42,703][62373] Updated weights for policy 0, policy_version 30730 (0.0008) -[2023-10-17 01:29:43,058][62373] Updated weights for policy 0, policy_version 30740 (0.0007) -[2023-10-17 01:29:43,436][62373] Updated weights for policy 0, policy_version 30750 (0.0008) -[2023-10-17 01:29:46,425][62408] Updated weights for policy 1, policy_version 30530 (0.0008) -[2023-10-17 01:29:46,793][62408] Updated weights for policy 1, policy_version 30540 (0.0010) -[2023-10-17 01:29:47,165][62408] Updated weights for policy 1, policy_version 30550 (0.0008) -[2023-10-17 01:29:47,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 62750720. Throughput: 0: 1795.2, 1: 1762.7. Samples: 15706400. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-17 01:29:47,215][61453] Avg episode reward: [(0, '8.200'), (1, '7.660')] -[2023-10-17 01:29:47,316][62373] Updated weights for policy 0, policy_version 30760 (0.0008) -[2023-10-17 01:29:47,533][62408] Updated weights for policy 1, policy_version 30560 (0.0007) -[2023-10-17 01:29:47,693][62373] Updated weights for policy 0, policy_version 30770 (0.0007) -[2023-10-17 01:29:48,072][62373] Updated weights for policy 0, policy_version 30780 (0.0011) -[2023-10-17 01:29:51,354][62408] Updated weights for policy 1, policy_version 30570 (0.0011) -[2023-10-17 01:29:51,728][62408] Updated weights for policy 1, policy_version 30580 (0.0009) -[2023-10-17 01:29:51,867][62373] Updated weights for policy 0, policy_version 30790 (0.0008) -[2023-10-17 01:29:52,095][62408] Updated weights for policy 1, policy_version 30590 (0.0008) -[2023-10-17 01:29:52,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 62849024. Throughput: 0: 1761.3, 1: 1757.1. Samples: 15716554. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-17 01:29:52,214][61453] Avg episode reward: [(0, '7.490'), (1, '7.490')] -[2023-10-17 01:29:52,240][62373] Updated weights for policy 0, policy_version 30800 (0.0009) -[2023-10-17 01:29:52,611][62373] Updated weights for policy 0, policy_version 30810 (0.0008) -[2023-10-17 01:29:55,891][62408] Updated weights for policy 1, policy_version 30600 (0.0008) -[2023-10-17 01:29:56,253][62408] Updated weights for policy 1, policy_version 30610 (0.0010) -[2023-10-17 01:29:56,298][62373] Updated weights for policy 0, policy_version 30820 (0.0007) -[2023-10-17 01:29:56,618][62408] Updated weights for policy 1, policy_version 30620 (0.0009) -[2023-10-17 01:29:56,663][62373] Updated weights for policy 0, policy_version 30830 (0.0008) -[2023-10-17 01:29:57,036][62373] Updated weights for policy 0, policy_version 30840 (0.0008) -[2023-10-17 01:29:57,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 62914560. Throughput: 0: 1786.6, 1: 1772.4. Samples: 15738386. Policy #0 lag: (min: 31.0, avg: 33.5, max: 63.0) -[2023-10-17 01:29:57,215][61453] Avg episode reward: [(0, '7.830'), (1, '7.310')] -[2023-10-17 01:30:00,484][62408] Updated weights for policy 1, policy_version 30630 (0.0009) -[2023-10-17 01:30:00,820][62373] Updated weights for policy 0, policy_version 30850 (0.0010) -[2023-10-17 01:30:00,850][62408] Updated weights for policy 1, policy_version 30640 (0.0009) -[2023-10-17 01:30:01,190][62373] Updated weights for policy 0, policy_version 30860 (0.0010) -[2023-10-17 01:30:01,207][62408] Updated weights for policy 1, policy_version 30650 (0.0007) -[2023-10-17 01:30:01,563][62373] Updated weights for policy 0, policy_version 30870 (0.0008) -[2023-10-17 01:30:01,933][62373] Updated weights for policy 0, policy_version 30880 (0.0007) -[2023-10-17 01:30:02,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 63012864. Throughput: 0: 1768.7, 1: 1756.2. Samples: 15758230. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-17 01:30:02,214][61453] Avg episode reward: [(0, '7.910'), (1, '7.260')] -[2023-10-17 01:30:05,026][62408] Updated weights for policy 1, policy_version 30660 (0.0008) -[2023-10-17 01:30:05,393][62408] Updated weights for policy 1, policy_version 30670 (0.0008) -[2023-10-17 01:30:05,567][62373] Updated weights for policy 0, policy_version 30890 (0.0010) -[2023-10-17 01:30:05,751][62408] Updated weights for policy 1, policy_version 30680 (0.0009) -[2023-10-17 01:30:05,936][62373] Updated weights for policy 0, policy_version 30900 (0.0009) -[2023-10-17 01:30:06,306][62373] Updated weights for policy 0, policy_version 30910 (0.0010) -[2023-10-17 01:30:07,214][61453] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 63078400. Throughput: 0: 1789.1, 1: 1793.1. Samples: 15771072. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-17 01:30:07,215][61453] Avg episode reward: [(0, '8.160'), (1, '7.310')] -[2023-10-17 01:30:09,504][62408] Updated weights for policy 1, policy_version 30690 (0.0008) -[2023-10-17 01:30:09,879][62408] Updated weights for policy 1, policy_version 30700 (0.0009) -[2023-10-17 01:30:10,070][62373] Updated weights for policy 0, policy_version 30920 (0.0009) -[2023-10-17 01:30:10,259][62408] Updated weights for policy 1, policy_version 30710 (0.0008) -[2023-10-17 01:30:10,440][62373] Updated weights for policy 0, policy_version 30930 (0.0010) -[2023-10-17 01:30:10,623][62408] Updated weights for policy 1, policy_version 30720 (0.0007) -[2023-10-17 01:30:10,806][62373] Updated weights for policy 0, policy_version 30940 (0.0009) -[2023-10-17 01:30:12,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 63143936. Throughput: 0: 1773.4, 1: 1765.3. Samples: 15790316. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-17 01:30:12,214][61453] Avg episode reward: [(0, '7.700'), (1, '7.480')] -[2023-10-17 01:30:14,519][62408] Updated weights for policy 1, policy_version 30730 (0.0008) -[2023-10-17 01:30:14,640][62373] Updated weights for policy 0, policy_version 30950 (0.0009) -[2023-10-17 01:30:14,884][62408] Updated weights for policy 1, policy_version 30740 (0.0007) -[2023-10-17 01:30:15,005][62373] Updated weights for policy 0, policy_version 30960 (0.0008) -[2023-10-17 01:30:15,254][62408] Updated weights for policy 1, policy_version 30750 (0.0007) -[2023-10-17 01:30:15,376][62373] Updated weights for policy 0, policy_version 30970 (0.0007) -[2023-10-17 01:30:17,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 63209472. Throughput: 0: 1770.1, 1: 1765.0. Samples: 15812250. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-17 01:30:17,215][61453] Avg episode reward: [(0, '7.610'), (1, '7.900')] -[2023-10-17 01:30:19,078][62408] Updated weights for policy 1, policy_version 30760 (0.0008) -[2023-10-17 01:30:19,334][62373] Updated weights for policy 0, policy_version 30980 (0.0009) -[2023-10-17 01:30:19,442][62408] Updated weights for policy 1, policy_version 30770 (0.0007) -[2023-10-17 01:30:19,724][62373] Updated weights for policy 0, policy_version 30990 (0.0007) -[2023-10-17 01:30:19,821][62408] Updated weights for policy 1, policy_version 30780 (0.0007) -[2023-10-17 01:30:20,082][62373] Updated weights for policy 0, policy_version 31000 (0.0007) -[2023-10-17 01:30:22,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 63275008. Throughput: 0: 1780.7, 1: 1768.2. Samples: 15822474. Policy #0 lag: (min: 31.0, avg: 31.4, max: 44.0) -[2023-10-17 01:30:22,214][61453] Avg episode reward: [(0, '7.970'), (1, '7.770')] -[2023-10-17 01:30:23,642][62408] Updated weights for policy 1, policy_version 30790 (0.0008) -[2023-10-17 01:30:23,814][62373] Updated weights for policy 0, policy_version 31010 (0.0007) -[2023-10-17 01:30:24,012][62408] Updated weights for policy 1, policy_version 30800 (0.0007) -[2023-10-17 01:30:24,184][62373] Updated weights for policy 0, policy_version 31020 (0.0008) -[2023-10-17 01:30:24,381][62408] Updated weights for policy 1, policy_version 30810 (0.0007) -[2023-10-17 01:30:24,562][62373] Updated weights for policy 0, policy_version 31030 (0.0007) -[2023-10-17 01:30:24,939][62373] Updated weights for policy 0, policy_version 31040 (0.0009) -[2023-10-17 01:30:27,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 63340544. Throughput: 0: 1763.2, 1: 1765.3. Samples: 15843634. Policy #0 lag: (min: 31.0, avg: 31.4, max: 44.0) -[2023-10-17 01:30:27,215][61453] Avg episode reward: [(0, '8.200'), (1, '7.930')] -[2023-10-17 01:30:28,331][62408] Updated weights for policy 1, policy_version 30820 (0.0007) -[2023-10-17 01:30:28,688][62408] Updated weights for policy 1, policy_version 30830 (0.0007) -[2023-10-17 01:30:28,762][62373] Updated weights for policy 0, policy_version 31050 (0.0008) -[2023-10-17 01:30:29,063][62408] Updated weights for policy 1, policy_version 30840 (0.0008) -[2023-10-17 01:30:29,136][62373] Updated weights for policy 0, policy_version 31060 (0.0010) -[2023-10-17 01:30:29,507][62373] Updated weights for policy 0, policy_version 31070 (0.0008) -[2023-10-17 01:30:32,214][61453] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 63406080. Throughput: 0: 1764.8, 1: 1775.9. Samples: 15865734. Policy #0 lag: (min: 31.0, avg: 31.4, max: 44.0) -[2023-10-17 01:30:32,215][61453] Avg episode reward: [(0, '8.350'), (1, '8.590')] -[2023-10-17 01:30:32,949][62408] Updated weights for policy 1, policy_version 30850 (0.0008) -[2023-10-17 01:30:33,288][62373] Updated weights for policy 0, policy_version 31080 (0.0008) -[2023-10-17 01:30:33,318][62408] Updated weights for policy 1, policy_version 30860 (0.0008) -[2023-10-17 01:30:33,657][62373] Updated weights for policy 0, policy_version 31090 (0.0007) -[2023-10-17 01:30:33,687][62408] Updated weights for policy 1, policy_version 30870 (0.0008) -[2023-10-17 01:30:34,037][62373] Updated weights for policy 0, policy_version 31100 (0.0008) -[2023-10-17 01:30:34,049][62408] Updated weights for policy 1, policy_version 30880 (0.0009) -[2023-10-17 01:30:37,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 63471616. Throughput: 0: 1768.8, 1: 1760.1. Samples: 15875356. Policy #0 lag: (min: 31.0, avg: 31.4, max: 44.0) -[2023-10-17 01:30:37,215][61453] Avg episode reward: [(0, '8.160'), (1, '8.320')] -[2023-10-17 01:30:37,905][62373] Updated weights for policy 0, policy_version 31110 (0.0009) -[2023-10-17 01:30:37,983][62408] Updated weights for policy 1, policy_version 30890 (0.0007) -[2023-10-17 01:30:38,280][62373] Updated weights for policy 0, policy_version 31120 (0.0009) -[2023-10-17 01:30:38,357][62408] Updated weights for policy 1, policy_version 30900 (0.0007) -[2023-10-17 01:30:38,658][62373] Updated weights for policy 0, policy_version 31130 (0.0009) -[2023-10-17 01:30:38,719][62408] Updated weights for policy 1, policy_version 30910 (0.0008) -[2023-10-17 01:30:42,214][61453] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 63537152. Throughput: 0: 1766.2, 1: 1756.1. Samples: 15896888. Policy #0 lag: (min: 31.0, avg: 31.4, max: 44.0) -[2023-10-17 01:30:42,215][61453] Avg episode reward: [(0, '8.450'), (1, '8.310')] -[2023-10-17 01:30:42,582][62373] Updated weights for policy 0, policy_version 31140 (0.0008) -[2023-10-17 01:30:42,619][62408] Updated weights for policy 1, policy_version 30920 (0.0008) -[2023-10-17 01:30:42,945][62373] Updated weights for policy 0, policy_version 31150 (0.0007) -[2023-10-17 01:30:42,996][62408] Updated weights for policy 1, policy_version 30930 (0.0009) -[2023-10-17 01:30:43,318][62373] Updated weights for policy 0, policy_version 31160 (0.0008) -[2023-10-17 01:30:43,365][62408] Updated weights for policy 1, policy_version 30940 (0.0007) -[2023-10-17 01:30:47,094][62373] Updated weights for policy 0, policy_version 31170 (0.0010) -[2023-10-17 01:30:47,175][62408] Updated weights for policy 1, policy_version 30950 (0.0007) -[2023-10-17 01:30:47,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 63602688. Throughput: 0: 1799.8, 1: 1778.4. Samples: 15919252. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-17 01:30:47,214][61453] Avg episode reward: [(0, '8.590'), (1, '7.770')] -[2023-10-17 01:30:47,457][62373] Updated weights for policy 0, policy_version 31180 (0.0008) -[2023-10-17 01:30:47,540][62408] Updated weights for policy 1, policy_version 30960 (0.0007) -[2023-10-17 01:30:47,825][62373] Updated weights for policy 0, policy_version 31190 (0.0007) -[2023-10-17 01:30:47,908][62408] Updated weights for policy 1, policy_version 30970 (0.0008) -[2023-10-17 01:30:48,198][62373] Updated weights for policy 0, policy_version 31200 (0.0008) -[2023-10-17 01:30:51,658][62408] Updated weights for policy 1, policy_version 30980 (0.0008) -[2023-10-17 01:30:52,027][62408] Updated weights for policy 1, policy_version 30990 (0.0009) -[2023-10-17 01:30:52,044][62373] Updated weights for policy 0, policy_version 31210 (0.0009) -[2023-10-17 01:30:52,214][61453] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13995.8). Total num frames: 63668224. Throughput: 0: 1761.6, 1: 1740.7. Samples: 15928672. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-17 01:30:52,215][61453] Avg episode reward: [(0, '8.830'), (1, '8.180')] -[2023-10-17 01:30:52,401][62408] Updated weights for policy 1, policy_version 31000 (0.0008) -[2023-10-17 01:30:52,411][62373] Updated weights for policy 0, policy_version 31220 (0.0009) -[2023-10-17 01:30:52,781][62373] Updated weights for policy 0, policy_version 31230 (0.0008) -[2023-10-17 01:30:56,253][62408] Updated weights for policy 1, policy_version 31010 (0.0009) -[2023-10-17 01:30:56,620][62373] Updated weights for policy 0, policy_version 31240 (0.0009) -[2023-10-17 01:30:56,655][62408] Updated weights for policy 1, policy_version 31020 (0.0008) -[2023-10-17 01:30:56,995][62373] Updated weights for policy 0, policy_version 31250 (0.0008) -[2023-10-17 01:30:57,026][62408] Updated weights for policy 1, policy_version 31030 (0.0008) -[2023-10-17 01:30:57,214][61453] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13995.8). Total num frames: 63733760. Throughput: 0: 1791.3, 1: 1770.4. Samples: 15950592. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-17 01:30:57,214][61453] Avg episode reward: [(0, '8.820'), (1, '8.080')] -[2023-10-17 01:30:57,354][62373] Updated weights for policy 0, policy_version 31260 (0.0008) -[2023-10-17 01:30:57,386][62408] Updated weights for policy 1, policy_version 31040 (0.0009) -[2023-10-17 01:31:01,239][62373] Updated weights for policy 0, policy_version 31270 (0.0008) -[2023-10-17 01:31:01,341][62408] Updated weights for policy 1, policy_version 31050 (0.0007) -[2023-10-17 01:31:01,609][62373] Updated weights for policy 0, policy_version 31280 (0.0007) -[2023-10-17 01:31:01,714][62408] Updated weights for policy 1, policy_version 31060 (0.0008) -[2023-10-17 01:31:01,978][62373] Updated weights for policy 0, policy_version 31290 (0.0007) -[2023-10-17 01:31:02,085][62408] Updated weights for policy 1, policy_version 31070 (0.0007) -[2023-10-17 01:31:02,214][61453] Fps is (10 sec: 19661.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 63864832. Throughput: 0: 1769.8, 1: 1742.1. Samples: 15970282. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-10-17 01:31:02,215][61453] Avg episode reward: [(0, '8.250'), (1, '7.560')] -[2023-10-17 01:31:05,883][62408] Updated weights for policy 1, policy_version 31080 (0.0009) -[2023-10-17 01:31:05,930][62373] Updated weights for policy 0, policy_version 31300 (0.0007) -[2023-10-17 01:31:06,241][62408] Updated weights for policy 1, policy_version 31090 (0.0008) -[2023-10-17 01:31:06,302][62373] Updated weights for policy 0, policy_version 31310 (0.0011) -[2023-10-17 01:31:06,605][62408] Updated weights for policy 1, policy_version 31100 (0.0008) -[2023-10-17 01:31:06,668][62373] Updated weights for policy 0, policy_version 31320 (0.0007) -[2023-10-17 01:31:07,214][61453] Fps is (10 sec: 19660.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 63930368. Throughput: 0: 1783.4, 1: 1759.7. Samples: 15981912. Policy #0 lag: (min: 0.0, avg: 28.2, max: 32.0) -[2023-10-17 01:31:07,215][61453] Avg episode reward: [(0, '8.360'), (1, '7.820')] -[2023-10-17 01:31:10,391][62373] Updated weights for policy 0, policy_version 31330 (0.0008) -[2023-10-17 01:31:10,565][62408] Updated weights for policy 1, policy_version 31110 (0.0010) -[2023-10-17 01:31:10,755][62373] Updated weights for policy 0, policy_version 31340 (0.0008) -[2023-10-17 01:31:10,920][62408] Updated weights for policy 1, policy_version 31120 (0.0008) -[2023-10-17 01:31:11,129][62373] Updated weights for policy 0, policy_version 31350 (0.0008) -[2023-10-17 01:31:11,282][62408] Updated weights for policy 1, policy_version 31130 (0.0007) -[2023-10-17 01:31:11,495][62373] Updated weights for policy 0, policy_version 31360 (0.0007) -[2023-10-17 01:31:12,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 63995904. Throughput: 0: 1780.7, 1: 1752.9. Samples: 16002648. Policy #0 lag: (min: 0.0, avg: 28.2, max: 32.0) -[2023-10-17 01:31:12,215][61453] Avg episode reward: [(0, '8.600'), (1, '7.700')] -[2023-10-17 01:31:15,007][62408] Updated weights for policy 1, policy_version 31140 (0.0008) -[2023-10-17 01:31:15,190][62373] Updated weights for policy 0, policy_version 31370 (0.0009) -[2023-10-17 01:31:15,381][62408] Updated weights for policy 1, policy_version 31150 (0.0009) -[2023-10-17 01:31:15,556][62373] Updated weights for policy 0, policy_version 31380 (0.0009) -[2023-10-17 01:31:15,744][62408] Updated weights for policy 1, policy_version 31160 (0.0008) -[2023-10-17 01:31:15,933][62373] Updated weights for policy 0, policy_version 31390 (0.0009) -[2023-10-17 01:31:17,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 64061440. Throughput: 0: 1763.6, 1: 1742.1. Samples: 16023490. Policy #0 lag: (min: 0.0, avg: 28.2, max: 32.0) -[2023-10-17 01:31:17,214][61453] Avg episode reward: [(0, '8.090'), (1, '7.180')] -[2023-10-17 01:31:19,432][62408] Updated weights for policy 1, policy_version 31170 (0.0009) -[2023-10-17 01:31:19,732][62373] Updated weights for policy 0, policy_version 31400 (0.0010) -[2023-10-17 01:31:19,811][62408] Updated weights for policy 1, policy_version 31180 (0.0008) -[2023-10-17 01:31:20,095][62373] Updated weights for policy 0, policy_version 31410 (0.0010) -[2023-10-17 01:31:20,174][62408] Updated weights for policy 1, policy_version 31190 (0.0009) -[2023-10-17 01:31:20,468][62373] Updated weights for policy 0, policy_version 31420 (0.0007) -[2023-10-17 01:31:20,541][62408] Updated weights for policy 1, policy_version 31200 (0.0009) -[2023-10-17 01:31:22,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 64126976. Throughput: 0: 1786.1, 1: 1766.8. Samples: 16035238. Policy #0 lag: (min: 0.0, avg: 28.2, max: 32.0) -[2023-10-17 01:31:22,215][61453] Avg episode reward: [(0, '8.330'), (1, '6.560')] -[2023-10-17 01:31:24,029][62373] Updated weights for policy 0, policy_version 31430 (0.0007) -[2023-10-17 01:31:24,393][62373] Updated weights for policy 0, policy_version 31440 (0.0007) -[2023-10-17 01:31:24,400][62408] Updated weights for policy 1, policy_version 31210 (0.0007) -[2023-10-17 01:31:24,764][62373] Updated weights for policy 0, policy_version 31450 (0.0009) -[2023-10-17 01:31:24,765][62408] Updated weights for policy 1, policy_version 31220 (0.0008) -[2023-10-17 01:31:25,137][62408] Updated weights for policy 1, policy_version 31230 (0.0007) -[2023-10-17 01:31:27,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 64192512. Throughput: 0: 1774.6, 1: 1753.4. Samples: 16055648. Policy #0 lag: (min: 0.0, avg: 28.2, max: 32.0) -[2023-10-17 01:31:27,215][61453] Avg episode reward: [(0, '8.680'), (1, '6.840')] -[2023-10-17 01:31:28,573][62373] Updated weights for policy 0, policy_version 31460 (0.0008) -[2023-10-17 01:31:28,940][62373] Updated weights for policy 0, policy_version 31470 (0.0008) -[2023-10-17 01:31:29,061][62408] Updated weights for policy 1, policy_version 31240 (0.0009) -[2023-10-17 01:31:29,309][62373] Updated weights for policy 0, policy_version 31480 (0.0009) -[2023-10-17 01:31:29,422][62408] Updated weights for policy 1, policy_version 31250 (0.0009) -[2023-10-17 01:31:29,788][62408] Updated weights for policy 1, policy_version 31260 (0.0008) -[2023-10-17 01:31:32,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.6, 300 sec: 14106.9). Total num frames: 64258048. Throughput: 0: 1765.6, 1: 1749.7. Samples: 16077442. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:31:32,214][61453] Avg episode reward: [(0, '8.810'), (1, '7.120')] -[2023-10-17 01:31:32,225][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000031488_32243712.pth... -[2023-10-17 01:31:32,225][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000031264_32014336.pth... -[2023-10-17 01:31:32,261][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000029632_30343168.pth -[2023-10-17 01:31:32,261][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000029824_30539776.pth -[2023-10-17 01:31:33,223][62373] Updated weights for policy 0, policy_version 31490 (0.0008) -[2023-10-17 01:31:33,540][62408] Updated weights for policy 1, policy_version 31270 (0.0009) -[2023-10-17 01:31:33,584][62373] Updated weights for policy 0, policy_version 31500 (0.0007) -[2023-10-17 01:31:33,900][62408] Updated weights for policy 1, policy_version 31280 (0.0007) -[2023-10-17 01:31:33,955][62373] Updated weights for policy 0, policy_version 31510 (0.0008) -[2023-10-17 01:31:34,262][62408] Updated weights for policy 1, policy_version 31290 (0.0008) -[2023-10-17 01:31:34,322][62373] Updated weights for policy 0, policy_version 31520 (0.0009) -[2023-10-17 01:31:37,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 64323584. Throughput: 0: 1768.0, 1: 1750.5. Samples: 16087006. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:31:37,214][61453] Avg episode reward: [(0, '8.420'), (1, '7.060')] -[2023-10-17 01:31:38,093][62373] Updated weights for policy 0, policy_version 31530 (0.0007) -[2023-10-17 01:31:38,225][62408] Updated weights for policy 1, policy_version 31300 (0.0009) -[2023-10-17 01:31:38,458][62373] Updated weights for policy 0, policy_version 31540 (0.0008) -[2023-10-17 01:31:38,595][62408] Updated weights for policy 1, policy_version 31310 (0.0007) -[2023-10-17 01:31:38,826][62373] Updated weights for policy 0, policy_version 31550 (0.0009) -[2023-10-17 01:31:38,964][62408] Updated weights for policy 1, policy_version 31320 (0.0007) -[2023-10-17 01:31:42,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 64389120. Throughput: 0: 1768.9, 1: 1744.8. Samples: 16108706. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:31:42,215][61453] Avg episode reward: [(0, '8.100'), (1, '7.570')] -[2023-10-17 01:31:42,638][62373] Updated weights for policy 0, policy_version 31560 (0.0009) -[2023-10-17 01:31:42,769][62408] Updated weights for policy 1, policy_version 31330 (0.0008) -[2023-10-17 01:31:43,006][62373] Updated weights for policy 0, policy_version 31570 (0.0008) -[2023-10-17 01:31:43,145][62408] Updated weights for policy 1, policy_version 31340 (0.0008) -[2023-10-17 01:31:43,375][62373] Updated weights for policy 0, policy_version 31580 (0.0009) -[2023-10-17 01:31:43,506][62408] Updated weights for policy 1, policy_version 31350 (0.0007) -[2023-10-17 01:31:43,876][62408] Updated weights for policy 1, policy_version 31360 (0.0008) -[2023-10-17 01:31:47,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 64454656. Throughput: 0: 1790.2, 1: 1770.9. Samples: 16130532. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:31:47,215][61453] Avg episode reward: [(0, '8.270'), (1, '8.040')] -[2023-10-17 01:31:47,326][62373] Updated weights for policy 0, policy_version 31590 (0.0008) -[2023-10-17 01:31:47,690][62373] Updated weights for policy 0, policy_version 31600 (0.0008) -[2023-10-17 01:31:47,806][62408] Updated weights for policy 1, policy_version 31370 (0.0007) -[2023-10-17 01:31:48,065][62373] Updated weights for policy 0, policy_version 31610 (0.0009) -[2023-10-17 01:31:48,171][62408] Updated weights for policy 1, policy_version 31380 (0.0007) -[2023-10-17 01:31:48,545][62408] Updated weights for policy 1, policy_version 31390 (0.0007) -[2023-10-17 01:31:51,952][62373] Updated weights for policy 0, policy_version 31620 (0.0008) -[2023-10-17 01:31:52,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 64520192. Throughput: 0: 1763.6, 1: 1744.7. Samples: 16139782. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:31:52,215][61453] Avg episode reward: [(0, '7.880'), (1, '7.490')] -[2023-10-17 01:31:52,342][62373] Updated weights for policy 0, policy_version 31630 (0.0008) -[2023-10-17 01:31:52,430][62408] Updated weights for policy 1, policy_version 31400 (0.0008) -[2023-10-17 01:31:52,715][62373] Updated weights for policy 0, policy_version 31640 (0.0008) -[2023-10-17 01:31:52,796][62408] Updated weights for policy 1, policy_version 31410 (0.0009) -[2023-10-17 01:31:53,171][62408] Updated weights for policy 1, policy_version 31420 (0.0008) -[2023-10-17 01:31:56,492][62373] Updated weights for policy 0, policy_version 31650 (0.0008) -[2023-10-17 01:31:56,868][62373] Updated weights for policy 0, policy_version 31660 (0.0009) -[2023-10-17 01:31:57,045][62408] Updated weights for policy 1, policy_version 31430 (0.0007) -[2023-10-17 01:31:57,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 64585728. Throughput: 0: 1783.6, 1: 1758.1. Samples: 16162024. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:31:57,215][61453] Avg episode reward: [(0, '8.120'), (1, '8.200')] -[2023-10-17 01:31:57,233][62373] Updated weights for policy 0, policy_version 31670 (0.0008) -[2023-10-17 01:31:57,414][62408] Updated weights for policy 1, policy_version 31440 (0.0009) -[2023-10-17 01:31:57,608][62373] Updated weights for policy 0, policy_version 31680 (0.0009) -[2023-10-17 01:31:57,793][62408] Updated weights for policy 1, policy_version 31450 (0.0008) -[2023-10-17 01:32:01,469][62373] Updated weights for policy 0, policy_version 31690 (0.0007) -[2023-10-17 01:32:01,571][62408] Updated weights for policy 1, policy_version 31460 (0.0009) -[2023-10-17 01:32:01,833][62373] Updated weights for policy 0, policy_version 31700 (0.0008) -[2023-10-17 01:32:01,936][62408] Updated weights for policy 1, policy_version 31470 (0.0008) -[2023-10-17 01:32:02,192][62373] Updated weights for policy 0, policy_version 31710 (0.0007) -[2023-10-17 01:32:02,214][61453] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13995.8). Total num frames: 64651264. Throughput: 0: 1773.7, 1: 1762.8. Samples: 16182634. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:32:02,215][61453] Avg episode reward: [(0, '8.330'), (1, '8.090')] -[2023-10-17 01:32:02,304][62408] Updated weights for policy 1, policy_version 31480 (0.0008) -[2023-10-17 01:32:05,878][62373] Updated weights for policy 0, policy_version 31720 (0.0007) -[2023-10-17 01:32:06,163][62408] Updated weights for policy 1, policy_version 31490 (0.0008) -[2023-10-17 01:32:06,247][62373] Updated weights for policy 0, policy_version 31730 (0.0007) -[2023-10-17 01:32:06,525][62408] Updated weights for policy 1, policy_version 31500 (0.0007) -[2023-10-17 01:32:06,608][62373] Updated weights for policy 0, policy_version 31740 (0.0007) -[2023-10-17 01:32:06,901][62408] Updated weights for policy 1, policy_version 31510 (0.0007) -[2023-10-17 01:32:07,214][61453] Fps is (10 sec: 16384.0, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 64749568. Throughput: 0: 1771.2, 1: 1746.6. Samples: 16193536. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:32:07,215][61453] Avg episode reward: [(0, '8.490'), (1, '8.020')] -[2023-10-17 01:32:07,266][62408] Updated weights for policy 1, policy_version 31520 (0.0009) -[2023-10-17 01:32:10,428][62373] Updated weights for policy 0, policy_version 31750 (0.0009) -[2023-10-17 01:32:10,800][62373] Updated weights for policy 0, policy_version 31760 (0.0010) -[2023-10-17 01:32:11,114][62408] Updated weights for policy 1, policy_version 31530 (0.0009) -[2023-10-17 01:32:11,159][62373] Updated weights for policy 0, policy_version 31770 (0.0009) -[2023-10-17 01:32:11,476][62408] Updated weights for policy 1, policy_version 31540 (0.0007) -[2023-10-17 01:32:11,847][62408] Updated weights for policy 1, policy_version 31550 (0.0008) -[2023-10-17 01:32:12,214][61453] Fps is (10 sec: 19661.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 64847872. Throughput: 0: 1766.6, 1: 1765.8. Samples: 16214604. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:32:12,214][61453] Avg episode reward: [(0, '8.680'), (1, '8.050')] -[2023-10-17 01:32:14,823][62373] Updated weights for policy 0, policy_version 31780 (0.0009) -[2023-10-17 01:32:15,191][62373] Updated weights for policy 0, policy_version 31790 (0.0009) -[2023-10-17 01:32:15,562][62373] Updated weights for policy 0, policy_version 31800 (0.0007) -[2023-10-17 01:32:15,663][62408] Updated weights for policy 1, policy_version 31560 (0.0007) -[2023-10-17 01:32:16,039][62408] Updated weights for policy 1, policy_version 31570 (0.0008) -[2023-10-17 01:32:16,405][62408] Updated weights for policy 1, policy_version 31580 (0.0007) -[2023-10-17 01:32:17,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 64913408. Throughput: 0: 1764.6, 1: 1735.4. Samples: 16234942. Policy #0 lag: (min: 31.0, avg: 31.5, max: 45.0) -[2023-10-17 01:32:17,215][61453] Avg episode reward: [(0, '8.740'), (1, '7.720')] -[2023-10-17 01:32:19,318][62373] Updated weights for policy 0, policy_version 31810 (0.0008) -[2023-10-17 01:32:19,686][62373] Updated weights for policy 0, policy_version 31820 (0.0007) -[2023-10-17 01:32:20,051][62373] Updated weights for policy 0, policy_version 31830 (0.0008) -[2023-10-17 01:32:20,160][62408] Updated weights for policy 1, policy_version 31590 (0.0008) -[2023-10-17 01:32:20,417][62373] Updated weights for policy 0, policy_version 31840 (0.0009) -[2023-10-17 01:32:20,528][62408] Updated weights for policy 1, policy_version 31600 (0.0008) -[2023-10-17 01:32:20,893][62408] Updated weights for policy 1, policy_version 31610 (0.0009) -[2023-10-17 01:32:22,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 64978944. Throughput: 0: 1779.5, 1: 1770.5. Samples: 16246754. Policy #0 lag: (min: 31.0, avg: 31.5, max: 45.0) -[2023-10-17 01:32:22,215][61453] Avg episode reward: [(0, '8.730'), (1, '8.490')] -[2023-10-17 01:32:24,301][62373] Updated weights for policy 0, policy_version 31850 (0.0008) -[2023-10-17 01:32:24,667][62373] Updated weights for policy 0, policy_version 31860 (0.0010) -[2023-10-17 01:32:24,886][62408] Updated weights for policy 1, policy_version 31620 (0.0010) -[2023-10-17 01:32:25,034][62373] Updated weights for policy 0, policy_version 31870 (0.0007) -[2023-10-17 01:32:25,263][62408] Updated weights for policy 1, policy_version 31630 (0.0010) -[2023-10-17 01:32:25,634][62408] Updated weights for policy 1, policy_version 31640 (0.0011) -[2023-10-17 01:32:27,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 65044480. Throughput: 0: 1765.1, 1: 1748.7. Samples: 16266828. Policy #0 lag: (min: 31.0, avg: 31.5, max: 45.0) -[2023-10-17 01:32:27,215][61453] Avg episode reward: [(0, '8.310'), (1, '8.490')] -[2023-10-17 01:32:28,714][62373] Updated weights for policy 0, policy_version 31880 (0.0008) -[2023-10-17 01:32:29,080][62373] Updated weights for policy 0, policy_version 31890 (0.0008) -[2023-10-17 01:32:29,444][62373] Updated weights for policy 0, policy_version 31900 (0.0007) -[2023-10-17 01:32:29,615][62408] Updated weights for policy 1, policy_version 31650 (0.0008) -[2023-10-17 01:32:30,026][62408] Updated weights for policy 1, policy_version 31660 (0.0008) -[2023-10-17 01:32:30,390][62408] Updated weights for policy 1, policy_version 31670 (0.0009) -[2023-10-17 01:32:30,757][62408] Updated weights for policy 1, policy_version 31680 (0.0010) -[2023-10-17 01:32:32,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 65110016. Throughput: 0: 1773.4, 1: 1739.7. Samples: 16288622. Policy #0 lag: (min: 31.0, avg: 31.5, max: 45.0) -[2023-10-17 01:32:32,215][61453] Avg episode reward: [(0, '7.890'), (1, '8.090')] -[2023-10-17 01:32:33,303][62373] Updated weights for policy 0, policy_version 31910 (0.0007) -[2023-10-17 01:32:33,679][62373] Updated weights for policy 0, policy_version 31920 (0.0007) -[2023-10-17 01:32:34,046][62373] Updated weights for policy 0, policy_version 31930 (0.0009) -[2023-10-17 01:32:34,533][62408] Updated weights for policy 1, policy_version 31690 (0.0009) -[2023-10-17 01:32:34,903][62408] Updated weights for policy 1, policy_version 31700 (0.0007) -[2023-10-17 01:32:35,265][62408] Updated weights for policy 1, policy_version 31710 (0.0008) -[2023-10-17 01:32:37,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 65175552. Throughput: 0: 1779.0, 1: 1757.9. Samples: 16298940. Policy #0 lag: (min: 31.0, avg: 31.5, max: 45.0) -[2023-10-17 01:32:37,214][61453] Avg episode reward: [(0, '8.030'), (1, '8.040')] -[2023-10-17 01:32:37,827][62373] Updated weights for policy 0, policy_version 31940 (0.0010) -[2023-10-17 01:32:38,186][62373] Updated weights for policy 0, policy_version 31950 (0.0007) -[2023-10-17 01:32:38,554][62373] Updated weights for policy 0, policy_version 31960 (0.0010) -[2023-10-17 01:32:39,141][62408] Updated weights for policy 1, policy_version 31720 (0.0007) -[2023-10-17 01:32:39,513][62408] Updated weights for policy 1, policy_version 31730 (0.0007) -[2023-10-17 01:32:39,885][62408] Updated weights for policy 1, policy_version 31740 (0.0007) -[2023-10-17 01:32:42,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 65241088. Throughput: 0: 1773.8, 1: 1746.3. Samples: 16320426. Policy #0 lag: (min: 6.0, avg: 9.6, max: 38.0) -[2023-10-17 01:32:42,215][61453] Avg episode reward: [(0, '7.790'), (1, '7.820')] -[2023-10-17 01:32:42,427][62373] Updated weights for policy 0, policy_version 31970 (0.0008) -[2023-10-17 01:32:42,834][62373] Updated weights for policy 0, policy_version 31980 (0.0009) -[2023-10-17 01:32:43,213][62373] Updated weights for policy 0, policy_version 31990 (0.0011) -[2023-10-17 01:32:43,571][62408] Updated weights for policy 1, policy_version 31750 (0.0007) -[2023-10-17 01:32:43,576][62373] Updated weights for policy 0, policy_version 32000 (0.0009) -[2023-10-17 01:32:43,935][62408] Updated weights for policy 1, policy_version 31760 (0.0010) -[2023-10-17 01:32:44,300][62408] Updated weights for policy 1, policy_version 31770 (0.0008) -[2023-10-17 01:32:47,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 65306624. Throughput: 0: 1793.1, 1: 1757.0. Samples: 16342388. Policy #0 lag: (min: 6.0, avg: 9.6, max: 38.0) -[2023-10-17 01:32:47,215][61453] Avg episode reward: [(0, '8.100'), (1, '7.370')] -[2023-10-17 01:32:47,308][62373] Updated weights for policy 0, policy_version 32010 (0.0008) -[2023-10-17 01:32:47,671][62373] Updated weights for policy 0, policy_version 32020 (0.0009) -[2023-10-17 01:32:48,043][62373] Updated weights for policy 0, policy_version 32030 (0.0009) -[2023-10-17 01:32:48,230][62408] Updated weights for policy 1, policy_version 31780 (0.0008) -[2023-10-17 01:32:48,603][62408] Updated weights for policy 1, policy_version 31790 (0.0008) -[2023-10-17 01:32:48,963][62408] Updated weights for policy 1, policy_version 31800 (0.0010) -[2023-10-17 01:32:52,013][62373] Updated weights for policy 0, policy_version 32040 (0.0008) -[2023-10-17 01:32:52,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 65372160. Throughput: 0: 1772.5, 1: 1751.7. Samples: 16352128. Policy #0 lag: (min: 6.0, avg: 9.6, max: 38.0) -[2023-10-17 01:32:52,214][61453] Avg episode reward: [(0, '8.940'), (1, '7.510')] -[2023-10-17 01:32:52,383][62373] Updated weights for policy 0, policy_version 32050 (0.0007) -[2023-10-17 01:32:52,689][62408] Updated weights for policy 1, policy_version 31810 (0.0007) -[2023-10-17 01:32:52,751][62373] Updated weights for policy 0, policy_version 32060 (0.0007) -[2023-10-17 01:32:53,061][62408] Updated weights for policy 1, policy_version 31820 (0.0008) -[2023-10-17 01:32:53,422][62408] Updated weights for policy 1, policy_version 31830 (0.0008) -[2023-10-17 01:32:53,784][62408] Updated weights for policy 1, policy_version 31840 (0.0010) -[2023-10-17 01:32:56,638][62373] Updated weights for policy 0, policy_version 32070 (0.0008) -[2023-10-17 01:32:57,017][62373] Updated weights for policy 0, policy_version 32080 (0.0008) -[2023-10-17 01:32:57,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 65437696. Throughput: 0: 1786.0, 1: 1758.8. Samples: 16374122. Policy #0 lag: (min: 6.0, avg: 9.6, max: 38.0) -[2023-10-17 01:32:57,215][61453] Avg episode reward: [(0, '8.230'), (1, '7.370')] -[2023-10-17 01:32:57,387][62373] Updated weights for policy 0, policy_version 32090 (0.0007) -[2023-10-17 01:32:57,618][62408] Updated weights for policy 1, policy_version 31850 (0.0010) -[2023-10-17 01:32:57,985][62408] Updated weights for policy 1, policy_version 31860 (0.0007) -[2023-10-17 01:32:58,366][62408] Updated weights for policy 1, policy_version 31870 (0.0009) -[2023-10-17 01:33:01,094][62373] Updated weights for policy 0, policy_version 32100 (0.0008) -[2023-10-17 01:33:01,466][62373] Updated weights for policy 0, policy_version 32110 (0.0010) -[2023-10-17 01:33:01,843][62373] Updated weights for policy 0, policy_version 32120 (0.0009) -[2023-10-17 01:33:02,191][62408] Updated weights for policy 1, policy_version 31880 (0.0008) -[2023-10-17 01:33:02,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14106.9). Total num frames: 65536000. Throughput: 0: 1766.1, 1: 1789.7. Samples: 16394948. Policy #0 lag: (min: 14.0, avg: 18.4, max: 46.0) -[2023-10-17 01:33:02,214][61453] Avg episode reward: [(0, '7.700'), (1, '7.920')] -[2023-10-17 01:33:02,561][62408] Updated weights for policy 1, policy_version 31890 (0.0010) -[2023-10-17 01:33:02,932][62408] Updated weights for policy 1, policy_version 31900 (0.0009) -[2023-10-17 01:33:05,580][62373] Updated weights for policy 0, policy_version 32130 (0.0008) -[2023-10-17 01:33:05,946][62373] Updated weights for policy 0, policy_version 32140 (0.0009) -[2023-10-17 01:33:06,315][62373] Updated weights for policy 0, policy_version 32150 (0.0010) -[2023-10-17 01:33:06,680][62373] Updated weights for policy 0, policy_version 32160 (0.0009) -[2023-10-17 01:33:06,767][62408] Updated weights for policy 1, policy_version 31910 (0.0009) -[2023-10-17 01:33:07,141][62408] Updated weights for policy 1, policy_version 31920 (0.0011) -[2023-10-17 01:33:07,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 65601536. Throughput: 0: 1781.5, 1: 1754.2. Samples: 16405858. Policy #0 lag: (min: 14.0, avg: 18.4, max: 46.0) -[2023-10-17 01:33:07,215][61453] Avg episode reward: [(0, '7.790'), (1, '7.950')] -[2023-10-17 01:33:07,509][62408] Updated weights for policy 1, policy_version 31930 (0.0009) -[2023-10-17 01:33:10,452][62373] Updated weights for policy 0, policy_version 32170 (0.0010) -[2023-10-17 01:33:10,832][62373] Updated weights for policy 0, policy_version 32180 (0.0009) -[2023-10-17 01:33:11,195][62373] Updated weights for policy 0, policy_version 32190 (0.0008) -[2023-10-17 01:33:11,310][62408] Updated weights for policy 1, policy_version 31940 (0.0007) -[2023-10-17 01:33:11,678][62408] Updated weights for policy 1, policy_version 31950 (0.0008) -[2023-10-17 01:33:12,048][62408] Updated weights for policy 1, policy_version 31960 (0.0009) -[2023-10-17 01:33:12,214][61453] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 65667072. Throughput: 0: 1770.6, 1: 1786.9. Samples: 16426916. Policy #0 lag: (min: 14.0, avg: 18.4, max: 46.0) -[2023-10-17 01:33:12,214][61453] Avg episode reward: [(0, '8.030'), (1, '7.980')] -[2023-10-17 01:33:14,966][62373] Updated weights for policy 0, policy_version 32200 (0.0008) -[2023-10-17 01:33:15,329][62373] Updated weights for policy 0, policy_version 32210 (0.0007) -[2023-10-17 01:33:15,702][62373] Updated weights for policy 0, policy_version 32220 (0.0011) -[2023-10-17 01:33:15,956][62408] Updated weights for policy 1, policy_version 31970 (0.0012) -[2023-10-17 01:33:16,382][62408] Updated weights for policy 1, policy_version 31980 (0.0007) -[2023-10-17 01:33:16,746][62408] Updated weights for policy 1, policy_version 31990 (0.0008) -[2023-10-17 01:33:17,115][62408] Updated weights for policy 1, policy_version 32000 (0.0008) -[2023-10-17 01:33:17,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 65765376. Throughput: 0: 1762.2, 1: 1768.1. Samples: 16447488. Policy #0 lag: (min: 14.0, avg: 18.4, max: 46.0) -[2023-10-17 01:33:17,215][61453] Avg episode reward: [(0, '7.650'), (1, '8.260')] -[2023-10-17 01:33:19,503][62373] Updated weights for policy 0, policy_version 32230 (0.0008) -[2023-10-17 01:33:19,866][62373] Updated weights for policy 0, policy_version 32240 (0.0008) -[2023-10-17 01:33:20,241][62373] Updated weights for policy 0, policy_version 32250 (0.0009) -[2023-10-17 01:33:20,915][62408] Updated weights for policy 1, policy_version 32010 (0.0008) -[2023-10-17 01:33:21,278][62408] Updated weights for policy 1, policy_version 32020 (0.0008) -[2023-10-17 01:33:21,657][62408] Updated weights for policy 1, policy_version 32030 (0.0008) -[2023-10-17 01:33:22,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 65830912. Throughput: 0: 1774.8, 1: 1776.5. Samples: 16458748. Policy #0 lag: (min: 14.0, avg: 18.4, max: 46.0) -[2023-10-17 01:33:22,215][61453] Avg episode reward: [(0, '7.610'), (1, '8.480')] -[2023-10-17 01:33:24,029][62373] Updated weights for policy 0, policy_version 32260 (0.0007) -[2023-10-17 01:33:24,400][62373] Updated weights for policy 0, policy_version 32270 (0.0009) -[2023-10-17 01:33:24,775][62373] Updated weights for policy 0, policy_version 32280 (0.0008) -[2023-10-17 01:33:25,450][62408] Updated weights for policy 1, policy_version 32040 (0.0010) -[2023-10-17 01:33:25,827][62408] Updated weights for policy 1, policy_version 32050 (0.0011) -[2023-10-17 01:33:26,199][62408] Updated weights for policy 1, policy_version 32060 (0.0010) -[2023-10-17 01:33:27,214][61453] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 65896448. Throughput: 0: 1761.2, 1: 1773.6. Samples: 16479492. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-17 01:33:27,214][61453] Avg episode reward: [(0, '8.340'), (1, '8.400')] -[2023-10-17 01:33:28,637][62373] Updated weights for policy 0, policy_version 32290 (0.0011) -[2023-10-17 01:33:29,030][62373] Updated weights for policy 0, policy_version 32300 (0.0009) -[2023-10-17 01:33:29,398][62373] Updated weights for policy 0, policy_version 32310 (0.0007) -[2023-10-17 01:33:29,772][62373] Updated weights for policy 0, policy_version 32320 (0.0008) -[2023-10-17 01:33:30,060][62408] Updated weights for policy 1, policy_version 32070 (0.0009) -[2023-10-17 01:33:30,425][62408] Updated weights for policy 1, policy_version 32080 (0.0009) -[2023-10-17 01:33:30,797][62408] Updated weights for policy 1, policy_version 32090 (0.0008) -[2023-10-17 01:33:32,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 65961984. Throughput: 0: 1765.8, 1: 1756.8. Samples: 16500904. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-17 01:33:32,215][61453] Avg episode reward: [(0, '8.290'), (1, '8.720')] -[2023-10-17 01:33:32,227][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000032320_33095680.pth... -[2023-10-17 01:33:32,227][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000032096_32866304.pth... -[2023-10-17 01:33:32,256][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000030656_31391744.pth -[2023-10-17 01:33:32,262][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000030432_31162368.pth -[2023-10-17 01:33:32,266][62252] Saving new best policy, reward=8.720! -[2023-10-17 01:33:33,490][62373] Updated weights for policy 0, policy_version 32330 (0.0009) -[2023-10-17 01:33:33,870][62373] Updated weights for policy 0, policy_version 32340 (0.0007) -[2023-10-17 01:33:34,239][62373] Updated weights for policy 0, policy_version 32350 (0.0009) -[2023-10-17 01:33:34,491][62408] Updated weights for policy 1, policy_version 32100 (0.0008) -[2023-10-17 01:33:34,864][62408] Updated weights for policy 1, policy_version 32110 (0.0009) -[2023-10-17 01:33:35,239][62408] Updated weights for policy 1, policy_version 32120 (0.0011) -[2023-10-17 01:33:37,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 66027520. Throughput: 0: 1766.4, 1: 1777.9. Samples: 16511622. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-17 01:33:37,214][61453] Avg episode reward: [(0, '8.420'), (1, '8.640')] -[2023-10-17 01:33:38,027][62373] Updated weights for policy 0, policy_version 32360 (0.0009) -[2023-10-17 01:33:38,405][62373] Updated weights for policy 0, policy_version 32370 (0.0010) -[2023-10-17 01:33:38,781][62373] Updated weights for policy 0, policy_version 32380 (0.0009) -[2023-10-17 01:33:38,985][62408] Updated weights for policy 1, policy_version 32130 (0.0010) -[2023-10-17 01:33:39,366][62408] Updated weights for policy 1, policy_version 32140 (0.0007) -[2023-10-17 01:33:39,735][62408] Updated weights for policy 1, policy_version 32150 (0.0007) -[2023-10-17 01:33:40,105][62408] Updated weights for policy 1, policy_version 32160 (0.0008) -[2023-10-17 01:33:42,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 66093056. Throughput: 0: 1768.4, 1: 1757.4. Samples: 16532784. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-17 01:33:42,215][61453] Avg episode reward: [(0, '7.900'), (1, '8.250')] -[2023-10-17 01:33:42,626][62373] Updated weights for policy 0, policy_version 32390 (0.0008) -[2023-10-17 01:33:43,005][62373] Updated weights for policy 0, policy_version 32400 (0.0009) -[2023-10-17 01:33:43,375][62373] Updated weights for policy 0, policy_version 32410 (0.0008) -[2023-10-17 01:33:43,941][62408] Updated weights for policy 1, policy_version 32170 (0.0007) -[2023-10-17 01:33:44,305][62408] Updated weights for policy 1, policy_version 32180 (0.0008) -[2023-10-17 01:33:44,681][62408] Updated weights for policy 1, policy_version 32190 (0.0010) -[2023-10-17 01:33:47,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 66158592. Throughput: 0: 1795.9, 1: 1764.2. Samples: 16555156. Policy #0 lag: (min: 29.0, avg: 29.0, max: 29.0) -[2023-10-17 01:33:47,215][61453] Avg episode reward: [(0, '7.820'), (1, '8.200')] -[2023-10-17 01:33:47,220][62373] Updated weights for policy 0, policy_version 32420 (0.0008) -[2023-10-17 01:33:47,593][62373] Updated weights for policy 0, policy_version 32430 (0.0009) -[2023-10-17 01:33:47,962][62373] Updated weights for policy 0, policy_version 32440 (0.0010) -[2023-10-17 01:33:48,371][62408] Updated weights for policy 1, policy_version 32200 (0.0010) -[2023-10-17 01:33:48,744][62408] Updated weights for policy 1, policy_version 32210 (0.0010) -[2023-10-17 01:33:49,120][62408] Updated weights for policy 1, policy_version 32220 (0.0009) -[2023-10-17 01:33:51,747][62373] Updated weights for policy 0, policy_version 32450 (0.0010) -[2023-10-17 01:33:52,121][62373] Updated weights for policy 0, policy_version 32460 (0.0010) -[2023-10-17 01:33:52,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 66224128. Throughput: 0: 1764.4, 1: 1766.6. Samples: 16564754. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-17 01:33:52,215][61453] Avg episode reward: [(0, '8.020'), (1, '8.010')] -[2023-10-17 01:33:52,503][62373] Updated weights for policy 0, policy_version 32470 (0.0009) -[2023-10-17 01:33:52,877][62373] Updated weights for policy 0, policy_version 32480 (0.0009) -[2023-10-17 01:33:52,917][62408] Updated weights for policy 1, policy_version 32230 (0.0009) -[2023-10-17 01:33:53,292][62408] Updated weights for policy 1, policy_version 32240 (0.0008) -[2023-10-17 01:33:53,652][62408] Updated weights for policy 1, policy_version 32250 (0.0009) -[2023-10-17 01:33:56,641][62373] Updated weights for policy 0, policy_version 32490 (0.0008) -[2023-10-17 01:33:57,013][62373] Updated weights for policy 0, policy_version 32500 (0.0007) -[2023-10-17 01:33:57,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 66289664. Throughput: 0: 1792.1, 1: 1762.4. Samples: 16586872. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-17 01:33:57,215][61453] Avg episode reward: [(0, '7.800'), (1, '8.250')] -[2023-10-17 01:33:57,375][62373] Updated weights for policy 0, policy_version 32510 (0.0007) -[2023-10-17 01:33:57,737][62408] Updated weights for policy 1, policy_version 32260 (0.0007) -[2023-10-17 01:33:58,101][62408] Updated weights for policy 1, policy_version 32270 (0.0007) -[2023-10-17 01:33:58,470][62408] Updated weights for policy 1, policy_version 32280 (0.0007) -[2023-10-17 01:34:01,233][62373] Updated weights for policy 0, policy_version 32520 (0.0007) -[2023-10-17 01:34:01,609][62373] Updated weights for policy 0, policy_version 32530 (0.0010) -[2023-10-17 01:34:01,980][62373] Updated weights for policy 0, policy_version 32540 (0.0008) -[2023-10-17 01:34:02,214][61453] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 66387968. Throughput: 0: 1769.0, 1: 1792.1. Samples: 16607738. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-17 01:34:02,214][61453] Avg episode reward: [(0, '7.910'), (1, '7.180')] -[2023-10-17 01:34:02,297][62408] Updated weights for policy 1, policy_version 32290 (0.0009) -[2023-10-17 01:34:02,704][62408] Updated weights for policy 1, policy_version 32300 (0.0009) -[2023-10-17 01:34:03,063][62408] Updated weights for policy 1, policy_version 32310 (0.0009) -[2023-10-17 01:34:03,432][62408] Updated weights for policy 1, policy_version 32320 (0.0007) -[2023-10-17 01:34:05,817][62373] Updated weights for policy 0, policy_version 32550 (0.0009) -[2023-10-17 01:34:06,191][62373] Updated weights for policy 0, policy_version 32560 (0.0008) -[2023-10-17 01:34:06,569][62373] Updated weights for policy 0, policy_version 32570 (0.0008) -[2023-10-17 01:34:07,124][62408] Updated weights for policy 1, policy_version 32330 (0.0008) -[2023-10-17 01:34:07,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 66453504. Throughput: 0: 1783.0, 1: 1767.4. Samples: 16618516. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-17 01:34:07,215][61453] Avg episode reward: [(0, '8.080'), (1, '7.070')] -[2023-10-17 01:34:07,487][62408] Updated weights for policy 1, policy_version 32340 (0.0007) -[2023-10-17 01:34:07,857][62408] Updated weights for policy 1, policy_version 32350 (0.0009) -[2023-10-17 01:34:10,416][62373] Updated weights for policy 0, policy_version 32580 (0.0008) -[2023-10-17 01:34:10,786][62373] Updated weights for policy 0, policy_version 32590 (0.0008) -[2023-10-17 01:34:11,151][62373] Updated weights for policy 0, policy_version 32600 (0.0008) -[2023-10-17 01:34:11,626][62408] Updated weights for policy 1, policy_version 32360 (0.0008) -[2023-10-17 01:34:11,995][62408] Updated weights for policy 1, policy_version 32370 (0.0010) -[2023-10-17 01:34:12,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 66519040. Throughput: 0: 1779.7, 1: 1785.4. Samples: 16639920. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-17 01:34:12,215][61453] Avg episode reward: [(0, '8.080'), (1, '7.370')] -[2023-10-17 01:34:12,360][62408] Updated weights for policy 1, policy_version 32380 (0.0010) -[2023-10-17 01:34:14,959][62373] Updated weights for policy 0, policy_version 32610 (0.0008) -[2023-10-17 01:34:15,366][62373] Updated weights for policy 0, policy_version 32620 (0.0007) -[2023-10-17 01:34:15,737][62373] Updated weights for policy 0, policy_version 32630 (0.0008) -[2023-10-17 01:34:16,002][62408] Updated weights for policy 1, policy_version 32390 (0.0007) -[2023-10-17 01:34:16,099][62373] Updated weights for policy 0, policy_version 32640 (0.0009) -[2023-10-17 01:34:16,383][62408] Updated weights for policy 1, policy_version 32400 (0.0011) -[2023-10-17 01:34:16,756][62408] Updated weights for policy 1, policy_version 32410 (0.0007) -[2023-10-17 01:34:17,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 66617344. Throughput: 0: 1769.3, 1: 1774.5. Samples: 16660378. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-17 01:34:17,214][61453] Avg episode reward: [(0, '7.920'), (1, '7.570')] -[2023-10-17 01:34:19,823][62373] Updated weights for policy 0, policy_version 32650 (0.0008) -[2023-10-17 01:34:20,196][62373] Updated weights for policy 0, policy_version 32660 (0.0011) -[2023-10-17 01:34:20,565][62373] Updated weights for policy 0, policy_version 32670 (0.0007) -[2023-10-17 01:34:20,599][62408] Updated weights for policy 1, policy_version 32420 (0.0008) -[2023-10-17 01:34:20,962][62408] Updated weights for policy 1, policy_version 32430 (0.0008) -[2023-10-17 01:34:21,327][62408] Updated weights for policy 1, policy_version 32440 (0.0008) -[2023-10-17 01:34:22,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 66682880. Throughput: 0: 1789.3, 1: 1779.8. Samples: 16672234. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-17 01:34:22,215][61453] Avg episode reward: [(0, '8.260'), (1, '7.350')] -[2023-10-17 01:34:24,298][62373] Updated weights for policy 0, policy_version 32680 (0.0008) -[2023-10-17 01:34:24,672][62373] Updated weights for policy 0, policy_version 32690 (0.0009) -[2023-10-17 01:34:25,044][62373] Updated weights for policy 0, policy_version 32700 (0.0008) -[2023-10-17 01:34:25,326][62408] Updated weights for policy 1, policy_version 32450 (0.0009) -[2023-10-17 01:34:25,708][62408] Updated weights for policy 1, policy_version 32460 (0.0010) -[2023-10-17 01:34:26,069][62408] Updated weights for policy 1, policy_version 32470 (0.0010) -[2023-10-17 01:34:26,423][62408] Updated weights for policy 1, policy_version 32480 (0.0007) -[2023-10-17 01:34:27,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 66748416. Throughput: 0: 1773.6, 1: 1782.1. Samples: 16692788. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-17 01:34:27,214][61453] Avg episode reward: [(0, '8.200'), (1, '7.280')] -[2023-10-17 01:34:28,827][62373] Updated weights for policy 0, policy_version 32710 (0.0010) -[2023-10-17 01:34:29,190][62373] Updated weights for policy 0, policy_version 32720 (0.0008) -[2023-10-17 01:34:29,563][62373] Updated weights for policy 0, policy_version 32730 (0.0007) -[2023-10-17 01:34:30,113][62408] Updated weights for policy 1, policy_version 32490 (0.0010) -[2023-10-17 01:34:30,478][62408] Updated weights for policy 1, policy_version 32500 (0.0008) -[2023-10-17 01:34:30,834][62408] Updated weights for policy 1, policy_version 32510 (0.0009) -[2023-10-17 01:34:32,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 66813952. Throughput: 0: 1779.1, 1: 1760.8. Samples: 16714452. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-17 01:34:32,215][61453] Avg episode reward: [(0, '7.740'), (1, '7.940')] -[2023-10-17 01:34:33,219][62373] Updated weights for policy 0, policy_version 32740 (0.0007) -[2023-10-17 01:34:33,586][62373] Updated weights for policy 0, policy_version 32750 (0.0007) -[2023-10-17 01:34:33,961][62373] Updated weights for policy 0, policy_version 32760 (0.0009) -[2023-10-17 01:34:34,635][62408] Updated weights for policy 1, policy_version 32520 (0.0008) -[2023-10-17 01:34:34,998][62408] Updated weights for policy 1, policy_version 32530 (0.0007) -[2023-10-17 01:34:35,360][62408] Updated weights for policy 1, policy_version 32540 (0.0007) -[2023-10-17 01:34:37,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 66879488. Throughput: 0: 1782.6, 1: 1775.1. Samples: 16724852. Policy #0 lag: (min: 12.0, avg: 13.0, max: 33.0) -[2023-10-17 01:34:37,215][61453] Avg episode reward: [(0, '7.680'), (1, '7.970')] -[2023-10-17 01:34:37,869][62373] Updated weights for policy 0, policy_version 32770 (0.0008) -[2023-10-17 01:34:38,240][62373] Updated weights for policy 0, policy_version 32780 (0.0010) -[2023-10-17 01:34:38,607][62373] Updated weights for policy 0, policy_version 32790 (0.0008) -[2023-10-17 01:34:38,984][62373] Updated weights for policy 0, policy_version 32800 (0.0008) -[2023-10-17 01:34:39,146][62408] Updated weights for policy 1, policy_version 32550 (0.0008) -[2023-10-17 01:34:39,519][62408] Updated weights for policy 1, policy_version 32560 (0.0008) -[2023-10-17 01:34:39,895][62408] Updated weights for policy 1, policy_version 32570 (0.0008) -[2023-10-17 01:34:42,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 66945024. Throughput: 0: 1779.9, 1: 1757.7. Samples: 16746062. Policy #0 lag: (min: 12.0, avg: 13.0, max: 33.0) -[2023-10-17 01:34:42,214][61453] Avg episode reward: [(0, '8.260'), (1, '8.270')] -[2023-10-17 01:34:42,596][62373] Updated weights for policy 0, policy_version 32810 (0.0008) -[2023-10-17 01:34:42,961][62373] Updated weights for policy 0, policy_version 32820 (0.0009) -[2023-10-17 01:34:43,333][62373] Updated weights for policy 0, policy_version 32830 (0.0008) -[2023-10-17 01:34:43,762][62408] Updated weights for policy 1, policy_version 32580 (0.0009) -[2023-10-17 01:34:44,130][62408] Updated weights for policy 1, policy_version 32590 (0.0009) -[2023-10-17 01:34:44,491][62408] Updated weights for policy 1, policy_version 32600 (0.0008) -[2023-10-17 01:34:47,177][62373] Updated weights for policy 0, policy_version 32840 (0.0009) -[2023-10-17 01:34:47,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 67010560. Throughput: 0: 1806.0, 1: 1759.1. Samples: 16768164. Policy #0 lag: (min: 12.0, avg: 13.0, max: 33.0) -[2023-10-17 01:34:47,214][61453] Avg episode reward: [(0, '8.240'), (1, '8.420')] -[2023-10-17 01:34:47,547][62373] Updated weights for policy 0, policy_version 32850 (0.0009) -[2023-10-17 01:34:47,918][62373] Updated weights for policy 0, policy_version 32860 (0.0008) -[2023-10-17 01:34:48,431][62408] Updated weights for policy 1, policy_version 32610 (0.0010) -[2023-10-17 01:34:48,833][62408] Updated weights for policy 1, policy_version 32620 (0.0010) -[2023-10-17 01:34:49,196][62408] Updated weights for policy 1, policy_version 32630 (0.0010) -[2023-10-17 01:34:49,563][62408] Updated weights for policy 1, policy_version 32640 (0.0007) -[2023-10-17 01:34:51,739][62373] Updated weights for policy 0, policy_version 32870 (0.0008) -[2023-10-17 01:34:52,105][62373] Updated weights for policy 0, policy_version 32880 (0.0007) -[2023-10-17 01:34:52,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 67076096. Throughput: 0: 1780.0, 1: 1757.9. Samples: 16777718. Policy #0 lag: (min: 12.0, avg: 13.0, max: 33.0) -[2023-10-17 01:34:52,214][61453] Avg episode reward: [(0, '8.130'), (1, '7.540')] -[2023-10-17 01:34:52,473][62373] Updated weights for policy 0, policy_version 32890 (0.0009) -[2023-10-17 01:34:53,361][62408] Updated weights for policy 1, policy_version 32650 (0.0007) -[2023-10-17 01:34:53,719][62408] Updated weights for policy 1, policy_version 32660 (0.0007) -[2023-10-17 01:34:54,088][62408] Updated weights for policy 1, policy_version 32670 (0.0008) -[2023-10-17 01:34:56,233][62373] Updated weights for policy 0, policy_version 32900 (0.0007) -[2023-10-17 01:34:56,598][62373] Updated weights for policy 0, policy_version 32910 (0.0008) -[2023-10-17 01:34:56,967][62373] Updated weights for policy 0, policy_version 32920 (0.0007) -[2023-10-17 01:34:57,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 67141632. Throughput: 0: 1795.6, 1: 1760.4. Samples: 16799938. Policy #0 lag: (min: 12.0, avg: 13.0, max: 33.0) -[2023-10-17 01:34:57,214][61453] Avg episode reward: [(0, '8.150'), (1, '7.360')] -[2023-10-17 01:34:57,816][62408] Updated weights for policy 1, policy_version 32680 (0.0008) -[2023-10-17 01:34:58,183][62408] Updated weights for policy 1, policy_version 32690 (0.0009) -[2023-10-17 01:34:58,564][62408] Updated weights for policy 1, policy_version 32700 (0.0009) -[2023-10-17 01:35:00,883][62373] Updated weights for policy 0, policy_version 32930 (0.0009) -[2023-10-17 01:35:01,295][62373] Updated weights for policy 0, policy_version 32940 (0.0008) -[2023-10-17 01:35:01,657][62373] Updated weights for policy 0, policy_version 32950 (0.0008) -[2023-10-17 01:35:02,029][62373] Updated weights for policy 0, policy_version 32960 (0.0009) -[2023-10-17 01:35:02,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 67239936. Throughput: 0: 1774.2, 1: 1786.5. Samples: 16820612. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:35:02,214][61453] Avg episode reward: [(0, '8.120'), (1, '7.920')] -[2023-10-17 01:35:02,309][62408] Updated weights for policy 1, policy_version 32710 (0.0008) -[2023-10-17 01:35:02,673][62408] Updated weights for policy 1, policy_version 32720 (0.0008) -[2023-10-17 01:35:03,048][62408] Updated weights for policy 1, policy_version 32730 (0.0009) -[2023-10-17 01:35:05,872][62373] Updated weights for policy 0, policy_version 32970 (0.0009) -[2023-10-17 01:35:06,242][62373] Updated weights for policy 0, policy_version 32980 (0.0008) -[2023-10-17 01:35:06,615][62373] Updated weights for policy 0, policy_version 32990 (0.0008) -[2023-10-17 01:35:06,812][62408] Updated weights for policy 1, policy_version 32740 (0.0008) -[2023-10-17 01:35:07,183][62408] Updated weights for policy 1, policy_version 32750 (0.0009) -[2023-10-17 01:35:07,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 67305472. Throughput: 0: 1779.9, 1: 1757.0. Samples: 16831394. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:35:07,214][61453] Avg episode reward: [(0, '8.860'), (1, '7.370')] -[2023-10-17 01:35:07,557][62408] Updated weights for policy 1, policy_version 32760 (0.0008) -[2023-10-17 01:35:10,499][62373] Updated weights for policy 0, policy_version 33000 (0.0009) -[2023-10-17 01:35:10,872][62373] Updated weights for policy 0, policy_version 33010 (0.0008) -[2023-10-17 01:35:11,247][62373] Updated weights for policy 0, policy_version 33020 (0.0009) -[2023-10-17 01:35:11,537][62408] Updated weights for policy 1, policy_version 32770 (0.0007) -[2023-10-17 01:35:11,916][62408] Updated weights for policy 1, policy_version 32780 (0.0010) -[2023-10-17 01:35:12,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 67371008. Throughput: 0: 1773.8, 1: 1771.4. Samples: 16852322. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:35:12,215][61453] Avg episode reward: [(0, '8.090'), (1, '7.290')] -[2023-10-17 01:35:12,284][62408] Updated weights for policy 1, policy_version 32790 (0.0009) -[2023-10-17 01:35:12,656][62408] Updated weights for policy 1, policy_version 32800 (0.0008) -[2023-10-17 01:35:14,935][62373] Updated weights for policy 0, policy_version 33030 (0.0009) -[2023-10-17 01:35:15,304][62373] Updated weights for policy 0, policy_version 33040 (0.0010) -[2023-10-17 01:35:15,681][62373] Updated weights for policy 0, policy_version 33050 (0.0007) -[2023-10-17 01:35:16,507][62408] Updated weights for policy 1, policy_version 32810 (0.0010) -[2023-10-17 01:35:16,879][62408] Updated weights for policy 1, policy_version 32820 (0.0008) -[2023-10-17 01:35:17,214][61453] Fps is (10 sec: 13106.7, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 67436544. Throughput: 0: 1756.7, 1: 1767.9. Samples: 16873062. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:35:17,215][61453] Avg episode reward: [(0, '8.030'), (1, '7.780')] -[2023-10-17 01:35:17,248][62408] Updated weights for policy 1, policy_version 32830 (0.0008) -[2023-10-17 01:35:19,481][62373] Updated weights for policy 0, policy_version 33060 (0.0008) -[2023-10-17 01:35:19,849][62373] Updated weights for policy 0, policy_version 33070 (0.0007) -[2023-10-17 01:35:20,230][62373] Updated weights for policy 0, policy_version 33080 (0.0008) -[2023-10-17 01:35:21,134][62408] Updated weights for policy 1, policy_version 32840 (0.0007) -[2023-10-17 01:35:21,499][62408] Updated weights for policy 1, policy_version 32850 (0.0007) -[2023-10-17 01:35:21,880][62408] Updated weights for policy 1, policy_version 32860 (0.0009) -[2023-10-17 01:35:22,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 67534848. Throughput: 0: 1770.8, 1: 1771.4. Samples: 16884248. Policy #0 lag: (min: 16.0, avg: 44.8, max: 48.0) -[2023-10-17 01:35:22,215][61453] Avg episode reward: [(0, '8.080'), (1, '7.470')] -[2023-10-17 01:35:23,885][62373] Updated weights for policy 0, policy_version 33090 (0.0009) -[2023-10-17 01:35:24,259][62373] Updated weights for policy 0, policy_version 33100 (0.0007) -[2023-10-17 01:35:24,624][62373] Updated weights for policy 0, policy_version 33110 (0.0007) -[2023-10-17 01:35:24,988][62373] Updated weights for policy 0, policy_version 33120 (0.0008) -[2023-10-17 01:35:25,747][62408] Updated weights for policy 1, policy_version 32870 (0.0010) -[2023-10-17 01:35:26,114][62408] Updated weights for policy 1, policy_version 32880 (0.0010) -[2023-10-17 01:35:26,478][62408] Updated weights for policy 1, policy_version 32890 (0.0009) -[2023-10-17 01:35:27,214][61453] Fps is (10 sec: 16384.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 67600384. Throughput: 0: 1758.7, 1: 1786.2. Samples: 16905582. Policy #0 lag: (min: 16.0, avg: 44.8, max: 48.0) -[2023-10-17 01:35:27,215][61453] Avg episode reward: [(0, '8.100'), (1, '7.340')] -[2023-10-17 01:35:28,737][62373] Updated weights for policy 0, policy_version 33130 (0.0008) -[2023-10-17 01:35:29,103][62373] Updated weights for policy 0, policy_version 33140 (0.0007) -[2023-10-17 01:35:29,462][62373] Updated weights for policy 0, policy_version 33150 (0.0008) -[2023-10-17 01:35:30,280][62408] Updated weights for policy 1, policy_version 32900 (0.0010) -[2023-10-17 01:35:30,645][62408] Updated weights for policy 1, policy_version 32910 (0.0009) -[2023-10-17 01:35:31,008][62408] Updated weights for policy 1, policy_version 32920 (0.0009) -[2023-10-17 01:35:32,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 67665920. Throughput: 0: 1761.0, 1: 1762.2. Samples: 16926708. Policy #0 lag: (min: 16.0, avg: 44.8, max: 48.0) -[2023-10-17 01:35:32,215][61453] Avg episode reward: [(0, '8.020'), (1, '7.840')] -[2023-10-17 01:35:32,230][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000033152_33947648.pth... -[2023-10-17 01:35:32,230][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000032928_33718272.pth... -[2023-10-17 01:35:32,266][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000031488_32243712.pth -[2023-10-17 01:35:32,266][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000031264_32014336.pth -[2023-10-17 01:35:32,270][62094] Saving a milestone ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/milestones/checkpoint_000033152_33947648.pth -[2023-10-17 01:35:32,271][62252] Saving a milestone ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/milestones/checkpoint_000032928_33718272.pth -[2023-10-17 01:35:33,287][62373] Updated weights for policy 0, policy_version 33160 (0.0009) -[2023-10-17 01:35:33,662][62373] Updated weights for policy 0, policy_version 33170 (0.0009) -[2023-10-17 01:35:34,026][62373] Updated weights for policy 0, policy_version 33180 (0.0010) -[2023-10-17 01:35:34,943][62408] Updated weights for policy 1, policy_version 32930 (0.0010) -[2023-10-17 01:35:35,368][62408] Updated weights for policy 1, policy_version 32940 (0.0008) -[2023-10-17 01:35:35,726][62408] Updated weights for policy 1, policy_version 32950 (0.0011) -[2023-10-17 01:35:36,093][62408] Updated weights for policy 1, policy_version 32960 (0.0008) -[2023-10-17 01:35:37,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 67731456. Throughput: 0: 1759.5, 1: 1796.3. Samples: 16937730. Policy #0 lag: (min: 16.0, avg: 44.8, max: 48.0) -[2023-10-17 01:35:37,215][61453] Avg episode reward: [(0, '7.840'), (1, '7.750')] -[2023-10-17 01:35:37,870][62373] Updated weights for policy 0, policy_version 33190 (0.0009) -[2023-10-17 01:35:38,252][62373] Updated weights for policy 0, policy_version 33200 (0.0009) -[2023-10-17 01:35:38,631][62373] Updated weights for policy 0, policy_version 33210 (0.0008) -[2023-10-17 01:35:40,013][62408] Updated weights for policy 1, policy_version 32970 (0.0010) -[2023-10-17 01:35:40,380][62408] Updated weights for policy 1, policy_version 32980 (0.0008) -[2023-10-17 01:35:40,745][62408] Updated weights for policy 1, policy_version 32990 (0.0008) -[2023-10-17 01:35:42,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 67796992. Throughput: 0: 1762.5, 1: 1754.6. Samples: 16958210. Policy #0 lag: (min: 16.0, avg: 44.8, max: 48.0) -[2023-10-17 01:35:42,215][61453] Avg episode reward: [(0, '7.900'), (1, '7.580')] -[2023-10-17 01:35:42,378][62373] Updated weights for policy 0, policy_version 33220 (0.0007) -[2023-10-17 01:35:42,755][62373] Updated weights for policy 0, policy_version 33230 (0.0008) -[2023-10-17 01:35:43,131][62373] Updated weights for policy 0, policy_version 33240 (0.0009) -[2023-10-17 01:35:44,641][62408] Updated weights for policy 1, policy_version 33000 (0.0007) -[2023-10-17 01:35:45,008][62408] Updated weights for policy 1, policy_version 33010 (0.0009) -[2023-10-17 01:35:45,375][62408] Updated weights for policy 1, policy_version 33020 (0.0007) -[2023-10-17 01:35:46,966][62373] Updated weights for policy 0, policy_version 33250 (0.0007) -[2023-10-17 01:35:47,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 67862528. Throughput: 0: 1789.4, 1: 1751.5. Samples: 16979954. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-17 01:35:47,215][61453] Avg episode reward: [(0, '8.000'), (1, '7.750')] -[2023-10-17 01:35:47,362][62373] Updated weights for policy 0, policy_version 33260 (0.0007) -[2023-10-17 01:35:47,735][62373] Updated weights for policy 0, policy_version 33270 (0.0007) -[2023-10-17 01:35:48,104][62373] Updated weights for policy 0, policy_version 33280 (0.0007) -[2023-10-17 01:35:49,233][62408] Updated weights for policy 1, policy_version 33030 (0.0011) -[2023-10-17 01:35:49,605][62408] Updated weights for policy 1, policy_version 33040 (0.0010) -[2023-10-17 01:35:49,976][62408] Updated weights for policy 1, policy_version 33050 (0.0009) -[2023-10-17 01:35:51,778][62373] Updated weights for policy 0, policy_version 33290 (0.0008) -[2023-10-17 01:35:52,154][62373] Updated weights for policy 0, policy_version 33300 (0.0007) -[2023-10-17 01:35:52,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 67928064. Throughput: 0: 1768.0, 1: 1763.9. Samples: 16990334. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-17 01:35:52,215][61453] Avg episode reward: [(0, '8.090'), (1, '7.940')] -[2023-10-17 01:35:52,528][62373] Updated weights for policy 0, policy_version 33310 (0.0008) -[2023-10-17 01:35:53,672][62408] Updated weights for policy 1, policy_version 33060 (0.0007) -[2023-10-17 01:35:54,047][62408] Updated weights for policy 1, policy_version 33070 (0.0007) -[2023-10-17 01:35:54,418][62408] Updated weights for policy 1, policy_version 33080 (0.0009) -[2023-10-17 01:35:56,339][62373] Updated weights for policy 0, policy_version 33320 (0.0008) -[2023-10-17 01:35:56,717][62373] Updated weights for policy 0, policy_version 33330 (0.0009) -[2023-10-17 01:35:57,086][62373] Updated weights for policy 0, policy_version 33340 (0.0009) -[2023-10-17 01:35:57,214][61453] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 67993600. Throughput: 0: 1796.5, 1: 1751.2. Samples: 17011966. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-17 01:35:57,215][61453] Avg episode reward: [(0, '8.410'), (1, '8.710')] -[2023-10-17 01:35:58,534][62408] Updated weights for policy 1, policy_version 33090 (0.0010) -[2023-10-17 01:35:58,908][62408] Updated weights for policy 1, policy_version 33100 (0.0007) -[2023-10-17 01:35:59,271][62408] Updated weights for policy 1, policy_version 33110 (0.0007) -[2023-10-17 01:35:59,641][62408] Updated weights for policy 1, policy_version 33120 (0.0008) -[2023-10-17 01:36:00,879][62373] Updated weights for policy 0, policy_version 33350 (0.0009) -[2023-10-17 01:36:01,255][62373] Updated weights for policy 0, policy_version 33360 (0.0009) -[2023-10-17 01:36:01,635][62373] Updated weights for policy 0, policy_version 33370 (0.0009) -[2023-10-17 01:36:02,214][61453] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 68091904. Throughput: 0: 1772.9, 1: 1763.4. Samples: 17032198. Policy #0 lag: (min: 20.0, avg: 20.0, max: 20.0) -[2023-10-17 01:36:02,215][61453] Avg episode reward: [(0, '8.450'), (1, '8.600')] -[2023-10-17 01:36:03,426][62408] Updated weights for policy 1, policy_version 33130 (0.0011) -[2023-10-17 01:36:03,797][62408] Updated weights for policy 1, policy_version 33140 (0.0010) -[2023-10-17 01:36:04,158][62408] Updated weights for policy 1, policy_version 33150 (0.0007) -[2023-10-17 01:36:05,367][62373] Updated weights for policy 0, policy_version 33380 (0.0009) -[2023-10-17 01:36:05,732][62373] Updated weights for policy 0, policy_version 33390 (0.0010) -[2023-10-17 01:36:06,099][62373] Updated weights for policy 0, policy_version 33400 (0.0010) -[2023-10-17 01:36:07,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 68157440. Throughput: 0: 1790.7, 1: 1742.2. Samples: 17043230. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:36:07,215][61453] Avg episode reward: [(0, '8.050'), (1, '8.170')] -[2023-10-17 01:36:08,011][62408] Updated weights for policy 1, policy_version 33160 (0.0007) -[2023-10-17 01:36:08,385][62408] Updated weights for policy 1, policy_version 33170 (0.0008) -[2023-10-17 01:36:08,749][62408] Updated weights for policy 1, policy_version 33180 (0.0009) -[2023-10-17 01:36:09,987][62373] Updated weights for policy 0, policy_version 33410 (0.0009) -[2023-10-17 01:36:10,360][62373] Updated weights for policy 0, policy_version 33420 (0.0008) -[2023-10-17 01:36:10,725][62373] Updated weights for policy 0, policy_version 33430 (0.0008) -[2023-10-17 01:36:11,094][62373] Updated weights for policy 0, policy_version 33440 (0.0007) -[2023-10-17 01:36:12,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 68222976. Throughput: 0: 1778.2, 1: 1745.3. Samples: 17064140. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:36:12,215][61453] Avg episode reward: [(0, '8.230'), (1, '8.470')] -[2023-10-17 01:36:12,763][62408] Updated weights for policy 1, policy_version 33190 (0.0008) -[2023-10-17 01:36:13,130][62408] Updated weights for policy 1, policy_version 33200 (0.0007) -[2023-10-17 01:36:13,498][62408] Updated weights for policy 1, policy_version 33210 (0.0009) -[2023-10-17 01:36:14,727][62373] Updated weights for policy 0, policy_version 33450 (0.0007) -[2023-10-17 01:36:15,103][62373] Updated weights for policy 0, policy_version 33460 (0.0009) -[2023-10-17 01:36:15,465][62373] Updated weights for policy 0, policy_version 33470 (0.0010) -[2023-10-17 01:36:17,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 68288512. Throughput: 0: 1779.0, 1: 1765.6. Samples: 17086214. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:36:17,215][62408] Updated weights for policy 1, policy_version 33220 (0.0009) -[2023-10-17 01:36:17,215][61453] Avg episode reward: [(0, '7.890'), (1, '8.660')] -[2023-10-17 01:36:17,586][62408] Updated weights for policy 1, policy_version 33230 (0.0010) -[2023-10-17 01:36:17,954][62408] Updated weights for policy 1, policy_version 33240 (0.0008) -[2023-10-17 01:36:19,265][62373] Updated weights for policy 0, policy_version 33480 (0.0009) -[2023-10-17 01:36:19,647][62373] Updated weights for policy 0, policy_version 33490 (0.0009) -[2023-10-17 01:36:20,021][62373] Updated weights for policy 0, policy_version 33500 (0.0009) -[2023-10-17 01:36:21,856][62408] Updated weights for policy 1, policy_version 33250 (0.0008) -[2023-10-17 01:36:22,214][61453] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 68354048. Throughput: 0: 1784.4, 1: 1736.4. Samples: 17096166. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:36:22,215][61453] Avg episode reward: [(0, '7.390'), (1, '8.520')] -[2023-10-17 01:36:22,265][62408] Updated weights for policy 1, policy_version 33260 (0.0007) -[2023-10-17 01:36:22,640][62408] Updated weights for policy 1, policy_version 33270 (0.0007) -[2023-10-17 01:36:23,010][62408] Updated weights for policy 1, policy_version 33280 (0.0010) -[2023-10-17 01:36:23,785][62373] Updated weights for policy 0, policy_version 33510 (0.0007) -[2023-10-17 01:36:24,151][62373] Updated weights for policy 0, policy_version 33520 (0.0007) -[2023-10-17 01:36:24,528][62373] Updated weights for policy 0, policy_version 33530 (0.0007) -[2023-10-17 01:36:26,801][62408] Updated weights for policy 1, policy_version 33290 (0.0008) -[2023-10-17 01:36:27,166][62408] Updated weights for policy 1, policy_version 33300 (0.0010) -[2023-10-17 01:36:27,214][61453] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 68419584. Throughput: 0: 1776.7, 1: 1767.9. Samples: 17117714. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:36:27,215][61453] Avg episode reward: [(0, '6.990'), (1, '8.120')] -[2023-10-17 01:36:27,545][62408] Updated weights for policy 1, policy_version 33310 (0.0007) -[2023-10-17 01:36:28,243][62373] Updated weights for policy 0, policy_version 33540 (0.0008) -[2023-10-17 01:36:28,616][62373] Updated weights for policy 0, policy_version 33550 (0.0008) -[2023-10-17 01:36:28,995][62373] Updated weights for policy 0, policy_version 33560 (0.0009) -[2023-10-17 01:36:31,346][62408] Updated weights for policy 1, policy_version 33320 (0.0007) -[2023-10-17 01:36:31,711][62408] Updated weights for policy 1, policy_version 33330 (0.0010) -[2023-10-17 01:36:32,081][62408] Updated weights for policy 1, policy_version 33340 (0.0010) -[2023-10-17 01:36:32,214][61453] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 68485120. Throughput: 0: 1787.9, 1: 1748.7. Samples: 17139102. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:36:32,215][61453] Avg episode reward: [(0, '7.680'), (1, '8.460')] -[2023-10-17 01:36:32,811][62373] Updated weights for policy 0, policy_version 33570 (0.0008) -[2023-10-17 01:36:33,218][62373] Updated weights for policy 0, policy_version 33580 (0.0007) -[2023-10-17 01:36:33,587][62373] Updated weights for policy 0, policy_version 33590 (0.0008) -[2023-10-17 01:36:33,956][62373] Updated weights for policy 0, policy_version 33600 (0.0009) -[2023-10-17 01:36:35,744][62408] Updated weights for policy 1, policy_version 33350 (0.0012) -[2023-10-17 01:36:36,103][62408] Updated weights for policy 1, policy_version 33360 (0.0009) -[2023-10-17 01:36:36,474][62408] Updated weights for policy 1, policy_version 33370 (0.0010) -[2023-10-17 01:36:37,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 68583424. Throughput: 0: 1776.6, 1: 1760.8. Samples: 17149514. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:36:37,215][61453] Avg episode reward: [(0, '7.630'), (1, '8.600')] -[2023-10-17 01:36:37,707][62373] Updated weights for policy 0, policy_version 33610 (0.0009) -[2023-10-17 01:36:38,087][62373] Updated weights for policy 0, policy_version 33620 (0.0009) -[2023-10-17 01:36:38,457][62373] Updated weights for policy 0, policy_version 33630 (0.0009) -[2023-10-17 01:36:40,230][62408] Updated weights for policy 1, policy_version 33380 (0.0007) -[2023-10-17 01:36:40,604][62408] Updated weights for policy 1, policy_version 33390 (0.0007) -[2023-10-17 01:36:40,977][62408] Updated weights for policy 1, policy_version 33400 (0.0009) -[2023-10-17 01:36:42,142][62373] Updated weights for policy 0, policy_version 33640 (0.0011) -[2023-10-17 01:36:42,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 68648960. Throughput: 0: 1776.1, 1: 1755.9. Samples: 17170906. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:36:42,215][61453] Avg episode reward: [(0, '7.820'), (1, '8.240')] -[2023-10-17 01:36:42,514][62373] Updated weights for policy 0, policy_version 33650 (0.0008) -[2023-10-17 01:36:42,886][62373] Updated weights for policy 0, policy_version 33660 (0.0008) -[2023-10-17 01:36:44,763][62408] Updated weights for policy 1, policy_version 33410 (0.0008) -[2023-10-17 01:36:45,135][62408] Updated weights for policy 1, policy_version 33420 (0.0009) -[2023-10-17 01:36:45,497][62408] Updated weights for policy 1, policy_version 33430 (0.0009) -[2023-10-17 01:36:45,865][62408] Updated weights for policy 1, policy_version 33440 (0.0008) -[2023-10-17 01:36:46,559][62373] Updated weights for policy 0, policy_version 33670 (0.0008) -[2023-10-17 01:36:46,930][62373] Updated weights for policy 0, policy_version 33680 (0.0008) -[2023-10-17 01:36:47,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 68714496. Throughput: 0: 1798.8, 1: 1755.6. Samples: 17192144. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:36:47,214][61453] Avg episode reward: [(0, '7.710'), (1, '8.450')] -[2023-10-17 01:36:47,298][62373] Updated weights for policy 0, policy_version 33690 (0.0007) -[2023-10-17 01:36:49,744][62408] Updated weights for policy 1, policy_version 33450 (0.0010) -[2023-10-17 01:36:50,119][62408] Updated weights for policy 1, policy_version 33460 (0.0008) -[2023-10-17 01:36:50,486][62408] Updated weights for policy 1, policy_version 33470 (0.0008) -[2023-10-17 01:36:51,007][62373] Updated weights for policy 0, policy_version 33700 (0.0008) -[2023-10-17 01:36:51,383][62373] Updated weights for policy 0, policy_version 33710 (0.0009) -[2023-10-17 01:36:51,754][62373] Updated weights for policy 0, policy_version 33720 (0.0007) -[2023-10-17 01:36:52,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 68812800. Throughput: 0: 1779.5, 1: 1772.8. Samples: 17203080. Policy #0 lag: (min: 5.0, avg: 5.2, max: 14.0) -[2023-10-17 01:36:52,215][61453] Avg episode reward: [(0, '7.940'), (1, '8.400')] -[2023-10-17 01:36:54,382][62408] Updated weights for policy 1, policy_version 33480 (0.0010) -[2023-10-17 01:36:54,754][62408] Updated weights for policy 1, policy_version 33490 (0.0008) -[2023-10-17 01:36:55,112][62408] Updated weights for policy 1, policy_version 33500 (0.0008) -[2023-10-17 01:36:55,526][62373] Updated weights for policy 0, policy_version 33730 (0.0008) -[2023-10-17 01:36:55,890][62373] Updated weights for policy 0, policy_version 33740 (0.0007) -[2023-10-17 01:36:56,256][62373] Updated weights for policy 0, policy_version 33750 (0.0010) -[2023-10-17 01:36:56,635][62373] Updated weights for policy 0, policy_version 33760 (0.0008) -[2023-10-17 01:36:57,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 68878336. Throughput: 0: 1798.3, 1: 1750.9. Samples: 17223854. Policy #0 lag: (min: 5.0, avg: 5.2, max: 14.0) -[2023-10-17 01:36:57,215][61453] Avg episode reward: [(0, '8.820'), (1, '8.450')] -[2023-10-17 01:36:59,226][62408] Updated weights for policy 1, policy_version 33510 (0.0008) -[2023-10-17 01:36:59,598][62408] Updated weights for policy 1, policy_version 33520 (0.0007) -[2023-10-17 01:36:59,961][62408] Updated weights for policy 1, policy_version 33530 (0.0007) -[2023-10-17 01:37:00,475][62373] Updated weights for policy 0, policy_version 33770 (0.0008) -[2023-10-17 01:37:00,852][62373] Updated weights for policy 0, policy_version 33780 (0.0008) -[2023-10-17 01:37:01,221][62373] Updated weights for policy 0, policy_version 33790 (0.0007) -[2023-10-17 01:37:02,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 68943872. Throughput: 0: 1777.2, 1: 1746.4. Samples: 17244774. Policy #0 lag: (min: 5.0, avg: 5.2, max: 14.0) -[2023-10-17 01:37:02,215][61453] Avg episode reward: [(0, '8.020'), (1, '8.090')] -[2023-10-17 01:37:03,910][62408] Updated weights for policy 1, policy_version 33540 (0.0008) -[2023-10-17 01:37:04,279][62408] Updated weights for policy 1, policy_version 33550 (0.0011) -[2023-10-17 01:37:04,653][62408] Updated weights for policy 1, policy_version 33560 (0.0008) -[2023-10-17 01:37:05,139][62373] Updated weights for policy 0, policy_version 33800 (0.0009) -[2023-10-17 01:37:05,507][62373] Updated weights for policy 0, policy_version 33810 (0.0008) -[2023-10-17 01:37:05,877][62373] Updated weights for policy 0, policy_version 33820 (0.0008) -[2023-10-17 01:37:07,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 69009408. Throughput: 0: 1796.3, 1: 1744.6. Samples: 17255504. Policy #0 lag: (min: 5.0, avg: 5.2, max: 14.0) -[2023-10-17 01:37:07,215][61453] Avg episode reward: [(0, '8.560'), (1, '7.760')] -[2023-10-17 01:37:08,559][62408] Updated weights for policy 1, policy_version 33570 (0.0008) -[2023-10-17 01:37:08,921][62408] Updated weights for policy 1, policy_version 33580 (0.0009) -[2023-10-17 01:37:09,285][62408] Updated weights for policy 1, policy_version 33590 (0.0007) -[2023-10-17 01:37:09,648][62408] Updated weights for policy 1, policy_version 33600 (0.0009) -[2023-10-17 01:37:09,662][62373] Updated weights for policy 0, policy_version 33830 (0.0007) -[2023-10-17 01:37:10,027][62373] Updated weights for policy 0, policy_version 33840 (0.0007) -[2023-10-17 01:37:10,408][62373] Updated weights for policy 0, policy_version 33850 (0.0007) -[2023-10-17 01:37:12,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 69074944. Throughput: 0: 1779.2, 1: 1745.9. Samples: 17276344. Policy #0 lag: (min: 5.0, avg: 5.2, max: 14.0) -[2023-10-17 01:37:12,215][61453] Avg episode reward: [(0, '9.060'), (1, '8.030')] -[2023-10-17 01:37:13,506][62408] Updated weights for policy 1, policy_version 33610 (0.0008) -[2023-10-17 01:37:13,892][62408] Updated weights for policy 1, policy_version 33620 (0.0007) -[2023-10-17 01:37:14,111][62373] Updated weights for policy 0, policy_version 33860 (0.0009) -[2023-10-17 01:37:14,255][62408] Updated weights for policy 1, policy_version 33630 (0.0008) -[2023-10-17 01:37:14,489][62373] Updated weights for policy 0, policy_version 33870 (0.0010) -[2023-10-17 01:37:14,856][62373] Updated weights for policy 0, policy_version 33880 (0.0010) -[2023-10-17 01:37:17,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 69140480. Throughput: 0: 1771.7, 1: 1768.0. Samples: 17298390. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-17 01:37:17,214][61453] Avg episode reward: [(0, '8.810'), (1, '8.190')] -[2023-10-17 01:37:17,982][62408] Updated weights for policy 1, policy_version 33640 (0.0008) -[2023-10-17 01:37:18,343][62408] Updated weights for policy 1, policy_version 33650 (0.0010) -[2023-10-17 01:37:18,692][62373] Updated weights for policy 0, policy_version 33890 (0.0010) -[2023-10-17 01:37:18,721][62408] Updated weights for policy 1, policy_version 33660 (0.0008) -[2023-10-17 01:37:19,092][62373] Updated weights for policy 0, policy_version 33900 (0.0009) -[2023-10-17 01:37:19,466][62373] Updated weights for policy 0, policy_version 33910 (0.0012) -[2023-10-17 01:37:19,835][62373] Updated weights for policy 0, policy_version 33920 (0.0011) -[2023-10-17 01:37:22,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 69206016. Throughput: 0: 1773.8, 1: 1741.8. Samples: 17307716. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-17 01:37:22,214][61453] Avg episode reward: [(0, '9.090'), (1, '8.050')] -[2023-10-17 01:37:22,514][62408] Updated weights for policy 1, policy_version 33670 (0.0007) -[2023-10-17 01:37:22,880][62408] Updated weights for policy 1, policy_version 33680 (0.0008) -[2023-10-17 01:37:23,241][62408] Updated weights for policy 1, policy_version 33690 (0.0009) -[2023-10-17 01:37:23,840][62373] Updated weights for policy 0, policy_version 33930 (0.0007) -[2023-10-17 01:37:24,211][62373] Updated weights for policy 0, policy_version 33940 (0.0008) -[2023-10-17 01:37:24,591][62373] Updated weights for policy 0, policy_version 33950 (0.0009) -[2023-10-17 01:37:27,051][62408] Updated weights for policy 1, policy_version 33700 (0.0011) -[2023-10-17 01:37:27,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 69271552. Throughput: 0: 1762.7, 1: 1760.0. Samples: 17329428. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-17 01:37:27,215][61453] Avg episode reward: [(0, '8.510'), (1, '7.940')] -[2023-10-17 01:37:27,429][62408] Updated weights for policy 1, policy_version 33710 (0.0007) -[2023-10-17 01:37:27,801][62408] Updated weights for policy 1, policy_version 33720 (0.0008) -[2023-10-17 01:37:28,346][62373] Updated weights for policy 0, policy_version 33960 (0.0008) -[2023-10-17 01:37:28,718][62373] Updated weights for policy 0, policy_version 33970 (0.0008) -[2023-10-17 01:37:29,090][62373] Updated weights for policy 0, policy_version 33980 (0.0007) -[2023-10-17 01:37:31,587][62408] Updated weights for policy 1, policy_version 33730 (0.0007) -[2023-10-17 01:37:31,955][62408] Updated weights for policy 1, policy_version 33740 (0.0010) -[2023-10-17 01:37:32,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 69337088. Throughput: 0: 1773.4, 1: 1759.8. Samples: 17351140. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-17 01:37:32,215][61453] Avg episode reward: [(0, '7.790'), (1, '8.070')] -[2023-10-17 01:37:32,225][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000033984_34799616.pth... -[2023-10-17 01:37:32,260][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000032320_33095680.pth -[2023-10-17 01:37:32,330][62408] Updated weights for policy 1, policy_version 33750 (0.0011) -[2023-10-17 01:37:32,694][62408] Updated weights for policy 1, policy_version 33760 (0.0011) -[2023-10-17 01:37:32,694][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000033760_34570240.pth... -[2023-10-17 01:37:32,728][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000032096_32866304.pth -[2023-10-17 01:37:33,015][62373] Updated weights for policy 0, policy_version 33990 (0.0008) -[2023-10-17 01:37:33,383][62373] Updated weights for policy 0, policy_version 34000 (0.0007) -[2023-10-17 01:37:33,752][62373] Updated weights for policy 0, policy_version 34010 (0.0007) -[2023-10-17 01:37:36,374][62408] Updated weights for policy 1, policy_version 33770 (0.0010) -[2023-10-17 01:37:36,746][62408] Updated weights for policy 1, policy_version 33780 (0.0009) -[2023-10-17 01:37:37,104][62408] Updated weights for policy 1, policy_version 33790 (0.0009) -[2023-10-17 01:37:37,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 69435392. Throughput: 0: 1761.1, 1: 1759.1. Samples: 17361488. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-17 01:37:37,214][61453] Avg episode reward: [(0, '8.260'), (1, '7.810')] -[2023-10-17 01:37:37,616][62373] Updated weights for policy 0, policy_version 34020 (0.0009) -[2023-10-17 01:37:37,980][62373] Updated weights for policy 0, policy_version 34030 (0.0008) -[2023-10-17 01:37:38,351][62373] Updated weights for policy 0, policy_version 34040 (0.0007) -[2023-10-17 01:37:40,971][62408] Updated weights for policy 1, policy_version 33800 (0.0010) -[2023-10-17 01:37:41,338][62408] Updated weights for policy 1, policy_version 33810 (0.0007) -[2023-10-17 01:37:41,701][62408] Updated weights for policy 1, policy_version 33820 (0.0008) -[2023-10-17 01:37:42,084][62373] Updated weights for policy 0, policy_version 34050 (0.0010) -[2023-10-17 01:37:42,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 69500928. Throughput: 0: 1760.8, 1: 1778.4. Samples: 17383116. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-17 01:37:42,214][61453] Avg episode reward: [(0, '8.150'), (1, '8.340')] -[2023-10-17 01:37:42,448][62373] Updated weights for policy 0, policy_version 34060 (0.0010) -[2023-10-17 01:37:42,818][62373] Updated weights for policy 0, policy_version 34070 (0.0008) -[2023-10-17 01:37:43,188][62373] Updated weights for policy 0, policy_version 34080 (0.0008) -[2023-10-17 01:37:45,618][62408] Updated weights for policy 1, policy_version 33830 (0.0009) -[2023-10-17 01:37:45,984][62408] Updated weights for policy 1, policy_version 33840 (0.0008) -[2023-10-17 01:37:46,362][62408] Updated weights for policy 1, policy_version 33850 (0.0010) -[2023-10-17 01:37:46,912][62373] Updated weights for policy 0, policy_version 34090 (0.0009) -[2023-10-17 01:37:47,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 69566464. Throughput: 0: 1776.8, 1: 1755.5. Samples: 17403730. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-17 01:37:47,215][61453] Avg episode reward: [(0, '8.570'), (1, '8.030')] -[2023-10-17 01:37:47,287][62373] Updated weights for policy 0, policy_version 34100 (0.0007) -[2023-10-17 01:37:47,659][62373] Updated weights for policy 0, policy_version 34110 (0.0008) -[2023-10-17 01:37:50,088][62408] Updated weights for policy 1, policy_version 33860 (0.0009) -[2023-10-17 01:37:50,463][62408] Updated weights for policy 1, policy_version 33870 (0.0007) -[2023-10-17 01:37:50,827][62408] Updated weights for policy 1, policy_version 33880 (0.0009) -[2023-10-17 01:37:51,534][62373] Updated weights for policy 0, policy_version 34120 (0.0010) -[2023-10-17 01:37:51,901][62373] Updated weights for policy 0, policy_version 34130 (0.0010) -[2023-10-17 01:37:52,214][61453] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 14218.0). Total num frames: 69632000. Throughput: 0: 1759.0, 1: 1790.8. Samples: 17415246. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-17 01:37:52,215][61453] Avg episode reward: [(0, '7.870'), (1, '8.050')] -[2023-10-17 01:37:52,272][62373] Updated weights for policy 0, policy_version 34140 (0.0009) -[2023-10-17 01:37:54,619][62408] Updated weights for policy 1, policy_version 33890 (0.0008) -[2023-10-17 01:37:54,991][62408] Updated weights for policy 1, policy_version 33900 (0.0009) -[2023-10-17 01:37:55,360][62408] Updated weights for policy 1, policy_version 33910 (0.0009) -[2023-10-17 01:37:55,724][62408] Updated weights for policy 1, policy_version 33920 (0.0009) -[2023-10-17 01:37:56,125][62373] Updated weights for policy 0, policy_version 34150 (0.0008) -[2023-10-17 01:37:56,494][62373] Updated weights for policy 0, policy_version 34160 (0.0008) -[2023-10-17 01:37:56,863][62373] Updated weights for policy 0, policy_version 34170 (0.0009) -[2023-10-17 01:37:57,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 69730304. Throughput: 0: 1785.6, 1: 1763.8. Samples: 17436066. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-17 01:37:57,215][61453] Avg episode reward: [(0, '8.540'), (1, '8.250')] -[2023-10-17 01:37:59,612][62408] Updated weights for policy 1, policy_version 33930 (0.0008) -[2023-10-17 01:37:59,989][62408] Updated weights for policy 1, policy_version 33940 (0.0007) -[2023-10-17 01:38:00,361][62408] Updated weights for policy 1, policy_version 33950 (0.0007) -[2023-10-17 01:38:00,644][62373] Updated weights for policy 0, policy_version 34180 (0.0010) -[2023-10-17 01:38:01,011][62373] Updated weights for policy 0, policy_version 34190 (0.0009) -[2023-10-17 01:38:01,384][62373] Updated weights for policy 0, policy_version 34200 (0.0009) -[2023-10-17 01:38:02,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 69795840. Throughput: 0: 1760.7, 1: 1767.3. Samples: 17457150. Policy #0 lag: (min: 14.0, avg: 21.7, max: 46.0) -[2023-10-17 01:38:02,214][61453] Avg episode reward: [(0, '8.980'), (1, '7.750')] -[2023-10-17 01:38:04,002][62408] Updated weights for policy 1, policy_version 33960 (0.0007) -[2023-10-17 01:38:04,372][62408] Updated weights for policy 1, policy_version 33970 (0.0009) -[2023-10-17 01:38:04,738][62408] Updated weights for policy 1, policy_version 33980 (0.0008) -[2023-10-17 01:38:05,233][62373] Updated weights for policy 0, policy_version 34210 (0.0008) -[2023-10-17 01:38:05,636][62373] Updated weights for policy 0, policy_version 34220 (0.0008) -[2023-10-17 01:38:06,001][62373] Updated weights for policy 0, policy_version 34230 (0.0008) -[2023-10-17 01:38:06,370][62373] Updated weights for policy 0, policy_version 34240 (0.0008) -[2023-10-17 01:38:07,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 69861376. Throughput: 0: 1801.5, 1: 1774.2. Samples: 17468620. Policy #0 lag: (min: 14.0, avg: 21.7, max: 46.0) -[2023-10-17 01:38:07,215][61453] Avg episode reward: [(0, '8.180'), (1, '8.240')] -[2023-10-17 01:38:08,410][62408] Updated weights for policy 1, policy_version 33990 (0.0008) -[2023-10-17 01:38:08,777][62408] Updated weights for policy 1, policy_version 34000 (0.0007) -[2023-10-17 01:38:09,144][62408] Updated weights for policy 1, policy_version 34010 (0.0007) -[2023-10-17 01:38:10,113][62373] Updated weights for policy 0, policy_version 34250 (0.0008) -[2023-10-17 01:38:10,487][62373] Updated weights for policy 0, policy_version 34260 (0.0008) -[2023-10-17 01:38:10,860][62373] Updated weights for policy 0, policy_version 34270 (0.0011) -[2023-10-17 01:38:12,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 69926912. Throughput: 0: 1775.6, 1: 1770.3. Samples: 17488990. Policy #0 lag: (min: 14.0, avg: 21.7, max: 46.0) -[2023-10-17 01:38:12,215][61453] Avg episode reward: [(0, '8.080'), (1, '7.930')] -[2023-10-17 01:38:12,911][62408] Updated weights for policy 1, policy_version 34020 (0.0007) -[2023-10-17 01:38:13,281][62408] Updated weights for policy 1, policy_version 34030 (0.0008) -[2023-10-17 01:38:13,650][62408] Updated weights for policy 1, policy_version 34040 (0.0008) -[2023-10-17 01:38:14,574][62373] Updated weights for policy 0, policy_version 34280 (0.0010) -[2023-10-17 01:38:14,951][62373] Updated weights for policy 0, policy_version 34290 (0.0010) -[2023-10-17 01:38:15,325][62373] Updated weights for policy 0, policy_version 34300 (0.0008) -[2023-10-17 01:38:17,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 69992448. Throughput: 0: 1774.4, 1: 1775.6. Samples: 17510888. Policy #0 lag: (min: 14.0, avg: 21.7, max: 46.0) -[2023-10-17 01:38:17,215][61453] Avg episode reward: [(0, '8.140'), (1, '8.020')] -[2023-10-17 01:38:17,640][62408] Updated weights for policy 1, policy_version 34050 (0.0010) -[2023-10-17 01:38:18,003][62408] Updated weights for policy 1, policy_version 34060 (0.0008) -[2023-10-17 01:38:18,376][62408] Updated weights for policy 1, policy_version 34070 (0.0008) -[2023-10-17 01:38:18,745][62408] Updated weights for policy 1, policy_version 34080 (0.0008) -[2023-10-17 01:38:19,163][62373] Updated weights for policy 0, policy_version 34310 (0.0009) -[2023-10-17 01:38:19,528][62373] Updated weights for policy 0, policy_version 34320 (0.0008) -[2023-10-17 01:38:19,904][62373] Updated weights for policy 0, policy_version 34330 (0.0007) -[2023-10-17 01:38:22,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 70057984. Throughput: 0: 1779.5, 1: 1758.4. Samples: 17520694. Policy #0 lag: (min: 14.0, avg: 21.7, max: 46.0) -[2023-10-17 01:38:22,215][61453] Avg episode reward: [(0, '8.270'), (1, '7.540')] -[2023-10-17 01:38:22,750][62408] Updated weights for policy 1, policy_version 34090 (0.0007) -[2023-10-17 01:38:23,115][62408] Updated weights for policy 1, policy_version 34100 (0.0007) -[2023-10-17 01:38:23,494][62408] Updated weights for policy 1, policy_version 34110 (0.0008) -[2023-10-17 01:38:23,706][62373] Updated weights for policy 0, policy_version 34340 (0.0008) -[2023-10-17 01:38:24,088][62373] Updated weights for policy 0, policy_version 34350 (0.0008) -[2023-10-17 01:38:24,462][62373] Updated weights for policy 0, policy_version 34360 (0.0009) -[2023-10-17 01:38:27,110][62408] Updated weights for policy 1, policy_version 34120 (0.0008) -[2023-10-17 01:38:27,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 70123520. Throughput: 0: 1777.2, 1: 1766.9. Samples: 17542600. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:38:27,214][61453] Avg episode reward: [(0, '8.540'), (1, '7.760')] -[2023-10-17 01:38:27,480][62408] Updated weights for policy 1, policy_version 34130 (0.0007) -[2023-10-17 01:38:27,854][62408] Updated weights for policy 1, policy_version 34140 (0.0008) -[2023-10-17 01:38:28,211][62373] Updated weights for policy 0, policy_version 34370 (0.0010) -[2023-10-17 01:38:28,577][62373] Updated weights for policy 0, policy_version 34380 (0.0010) -[2023-10-17 01:38:28,956][62373] Updated weights for policy 0, policy_version 34390 (0.0010) -[2023-10-17 01:38:29,325][62373] Updated weights for policy 0, policy_version 34400 (0.0007) -[2023-10-17 01:38:31,744][62408] Updated weights for policy 1, policy_version 34150 (0.0007) -[2023-10-17 01:38:32,106][62408] Updated weights for policy 1, policy_version 34160 (0.0008) -[2023-10-17 01:38:32,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 70189056. Throughput: 0: 1786.9, 1: 1789.7. Samples: 17564676. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:38:32,215][61453] Avg episode reward: [(0, '8.260'), (1, '7.800')] -[2023-10-17 01:38:32,478][62408] Updated weights for policy 1, policy_version 34170 (0.0007) -[2023-10-17 01:38:33,168][62373] Updated weights for policy 0, policy_version 34410 (0.0007) -[2023-10-17 01:38:33,534][62373] Updated weights for policy 0, policy_version 34420 (0.0011) -[2023-10-17 01:38:33,911][62373] Updated weights for policy 0, policy_version 34430 (0.0011) -[2023-10-17 01:38:36,174][62408] Updated weights for policy 1, policy_version 34180 (0.0007) -[2023-10-17 01:38:36,540][62408] Updated weights for policy 1, policy_version 34190 (0.0009) -[2023-10-17 01:38:36,912][62408] Updated weights for policy 1, policy_version 34200 (0.0008) -[2023-10-17 01:38:37,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 70287360. Throughput: 0: 1783.1, 1: 1764.4. Samples: 17574884. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:38:37,214][61453] Avg episode reward: [(0, '8.710'), (1, '7.690')] -[2023-10-17 01:38:37,571][62373] Updated weights for policy 0, policy_version 34440 (0.0007) -[2023-10-17 01:38:37,945][62373] Updated weights for policy 0, policy_version 34450 (0.0010) -[2023-10-17 01:38:38,312][62373] Updated weights for policy 0, policy_version 34460 (0.0009) -[2023-10-17 01:38:40,718][62408] Updated weights for policy 1, policy_version 34210 (0.0007) -[2023-10-17 01:38:41,091][62408] Updated weights for policy 1, policy_version 34220 (0.0011) -[2023-10-17 01:38:41,444][62408] Updated weights for policy 1, policy_version 34230 (0.0008) -[2023-10-17 01:38:41,818][62408] Updated weights for policy 1, policy_version 34240 (0.0008) -[2023-10-17 01:38:42,104][62373] Updated weights for policy 0, policy_version 34470 (0.0008) -[2023-10-17 01:38:42,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 70352896. Throughput: 0: 1782.0, 1: 1791.2. Samples: 17596858. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:38:42,215][61453] Avg episode reward: [(0, '8.580'), (1, '7.950')] -[2023-10-17 01:38:42,471][62373] Updated weights for policy 0, policy_version 34480 (0.0009) -[2023-10-17 01:38:42,844][62373] Updated weights for policy 0, policy_version 34490 (0.0008) -[2023-10-17 01:38:45,740][62408] Updated weights for policy 1, policy_version 34250 (0.0010) -[2023-10-17 01:38:46,114][62408] Updated weights for policy 1, policy_version 34260 (0.0009) -[2023-10-17 01:38:46,485][62408] Updated weights for policy 1, policy_version 34270 (0.0009) -[2023-10-17 01:38:46,587][62373] Updated weights for policy 0, policy_version 34500 (0.0009) -[2023-10-17 01:38:46,958][62373] Updated weights for policy 0, policy_version 34510 (0.0010) -[2023-10-17 01:38:47,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 70418432. Throughput: 0: 1796.4, 1: 1757.5. Samples: 17617072. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:38:47,214][61453] Avg episode reward: [(0, '9.620'), (1, '8.280')] -[2023-10-17 01:38:47,334][62373] Updated weights for policy 0, policy_version 34520 (0.0011) -[2023-10-17 01:38:47,629][62094] Saving new best policy, reward=9.620! -[2023-10-17 01:38:50,332][62408] Updated weights for policy 1, policy_version 34280 (0.0009) -[2023-10-17 01:38:50,700][62408] Updated weights for policy 1, policy_version 34290 (0.0007) -[2023-10-17 01:38:51,073][62408] Updated weights for policy 1, policy_version 34300 (0.0007) -[2023-10-17 01:38:51,085][62373] Updated weights for policy 0, policy_version 34530 (0.0010) -[2023-10-17 01:38:51,493][62373] Updated weights for policy 0, policy_version 34540 (0.0007) -[2023-10-17 01:38:51,857][62373] Updated weights for policy 0, policy_version 34550 (0.0008) -[2023-10-17 01:38:52,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 70483968. Throughput: 0: 1772.1, 1: 1786.2. Samples: 17628746. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:38:52,214][61453] Avg episode reward: [(0, '9.450'), (1, '8.750')] -[2023-10-17 01:38:52,215][62252] Saving new best policy, reward=8.750! -[2023-10-17 01:38:52,226][62373] Updated weights for policy 0, policy_version 34560 (0.0010) -[2023-10-17 01:38:54,926][62408] Updated weights for policy 1, policy_version 34310 (0.0009) -[2023-10-17 01:38:55,289][62408] Updated weights for policy 1, policy_version 34320 (0.0008) -[2023-10-17 01:38:55,658][62408] Updated weights for policy 1, policy_version 34330 (0.0007) -[2023-10-17 01:38:56,034][62373] Updated weights for policy 0, policy_version 34570 (0.0009) -[2023-10-17 01:38:56,400][62373] Updated weights for policy 0, policy_version 34580 (0.0009) -[2023-10-17 01:38:56,780][62373] Updated weights for policy 0, policy_version 34590 (0.0009) -[2023-10-17 01:38:57,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 70582272. Throughput: 0: 1796.3, 1: 1760.6. Samples: 17649052. Policy #0 lag: (min: 17.0, avg: 27.6, max: 49.0) -[2023-10-17 01:38:57,214][61453] Avg episode reward: [(0, '9.460'), (1, '9.370')] -[2023-10-17 01:38:57,215][62252] Saving new best policy, reward=9.370! -[2023-10-17 01:38:59,548][62408] Updated weights for policy 1, policy_version 34340 (0.0008) -[2023-10-17 01:38:59,925][62408] Updated weights for policy 1, policy_version 34350 (0.0009) -[2023-10-17 01:39:00,296][62408] Updated weights for policy 1, policy_version 34360 (0.0008) -[2023-10-17 01:39:00,504][62373] Updated weights for policy 0, policy_version 34600 (0.0008) -[2023-10-17 01:39:00,865][62373] Updated weights for policy 0, policy_version 34610 (0.0010) -[2023-10-17 01:39:01,248][62373] Updated weights for policy 0, policy_version 34620 (0.0011) -[2023-10-17 01:39:02,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 70647808. Throughput: 0: 1777.8, 1: 1762.4. Samples: 17670196. Policy #0 lag: (min: 17.0, avg: 27.6, max: 49.0) -[2023-10-17 01:39:02,214][61453] Avg episode reward: [(0, '9.230'), (1, '9.190')] -[2023-10-17 01:39:03,990][62408] Updated weights for policy 1, policy_version 34370 (0.0010) -[2023-10-17 01:39:04,359][62408] Updated weights for policy 1, policy_version 34380 (0.0008) -[2023-10-17 01:39:04,737][62408] Updated weights for policy 1, policy_version 34390 (0.0009) -[2023-10-17 01:39:05,100][62408] Updated weights for policy 1, policy_version 34400 (0.0009) -[2023-10-17 01:39:05,147][62373] Updated weights for policy 0, policy_version 34630 (0.0009) -[2023-10-17 01:39:05,519][62373] Updated weights for policy 0, policy_version 34640 (0.0008) -[2023-10-17 01:39:05,880][62373] Updated weights for policy 0, policy_version 34650 (0.0008) -[2023-10-17 01:39:07,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 70713344. Throughput: 0: 1800.9, 1: 1773.1. Samples: 17681526. Policy #0 lag: (min: 17.0, avg: 27.6, max: 49.0) -[2023-10-17 01:39:07,215][61453] Avg episode reward: [(0, '9.490'), (1, '8.780')] -[2023-10-17 01:39:08,865][62408] Updated weights for policy 1, policy_version 34410 (0.0008) -[2023-10-17 01:39:09,229][62408] Updated weights for policy 1, policy_version 34420 (0.0011) -[2023-10-17 01:39:09,590][62408] Updated weights for policy 1, policy_version 34430 (0.0008) -[2023-10-17 01:39:09,623][62373] Updated weights for policy 0, policy_version 34660 (0.0008) -[2023-10-17 01:39:09,993][62373] Updated weights for policy 0, policy_version 34670 (0.0008) -[2023-10-17 01:39:10,369][62373] Updated weights for policy 0, policy_version 34680 (0.0009) -[2023-10-17 01:39:12,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 70778880. Throughput: 0: 1781.8, 1: 1760.7. Samples: 17702016. Policy #0 lag: (min: 17.0, avg: 27.6, max: 49.0) -[2023-10-17 01:39:12,215][61453] Avg episode reward: [(0, '9.420'), (1, '8.870')] -[2023-10-17 01:39:13,363][62408] Updated weights for policy 1, policy_version 34440 (0.0009) -[2023-10-17 01:39:13,728][62408] Updated weights for policy 1, policy_version 34450 (0.0008) -[2023-10-17 01:39:14,094][62408] Updated weights for policy 1, policy_version 34460 (0.0008) -[2023-10-17 01:39:14,209][62373] Updated weights for policy 0, policy_version 34690 (0.0009) -[2023-10-17 01:39:14,567][62373] Updated weights for policy 0, policy_version 34700 (0.0008) -[2023-10-17 01:39:14,941][62373] Updated weights for policy 0, policy_version 34710 (0.0007) -[2023-10-17 01:39:15,309][62373] Updated weights for policy 0, policy_version 34720 (0.0008) -[2023-10-17 01:39:17,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 70844416. Throughput: 0: 1775.7, 1: 1773.9. Samples: 17724408. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:39:17,214][61453] Avg episode reward: [(0, '9.310'), (1, '8.690')] -[2023-10-17 01:39:17,766][62408] Updated weights for policy 1, policy_version 34470 (0.0008) -[2023-10-17 01:39:18,140][62408] Updated weights for policy 1, policy_version 34480 (0.0009) -[2023-10-17 01:39:18,509][62408] Updated weights for policy 1, policy_version 34490 (0.0010) -[2023-10-17 01:39:19,043][62373] Updated weights for policy 0, policy_version 34730 (0.0007) -[2023-10-17 01:39:19,414][62373] Updated weights for policy 0, policy_version 34740 (0.0008) -[2023-10-17 01:39:19,785][62373] Updated weights for policy 0, policy_version 34750 (0.0007) -[2023-10-17 01:39:22,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 70909952. Throughput: 0: 1774.4, 1: 1767.4. Samples: 17734268. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:39:22,215][61453] Avg episode reward: [(0, '9.290'), (1, '8.340')] -[2023-10-17 01:39:22,336][62408] Updated weights for policy 1, policy_version 34500 (0.0008) -[2023-10-17 01:39:22,717][62408] Updated weights for policy 1, policy_version 34510 (0.0009) -[2023-10-17 01:39:23,083][62408] Updated weights for policy 1, policy_version 34520 (0.0008) -[2023-10-17 01:39:23,599][62373] Updated weights for policy 0, policy_version 34760 (0.0009) -[2023-10-17 01:39:23,977][62373] Updated weights for policy 0, policy_version 34770 (0.0009) -[2023-10-17 01:39:24,344][62373] Updated weights for policy 0, policy_version 34780 (0.0010) -[2023-10-17 01:39:26,935][62408] Updated weights for policy 1, policy_version 34530 (0.0009) -[2023-10-17 01:39:27,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 70975488. Throughput: 0: 1766.5, 1: 1769.2. Samples: 17755964. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:39:27,215][61453] Avg episode reward: [(0, '9.540'), (1, '7.500')] -[2023-10-17 01:39:27,304][62408] Updated weights for policy 1, policy_version 34540 (0.0010) -[2023-10-17 01:39:27,672][62408] Updated weights for policy 1, policy_version 34550 (0.0009) -[2023-10-17 01:39:28,036][62408] Updated weights for policy 1, policy_version 34560 (0.0007) -[2023-10-17 01:39:28,156][62373] Updated weights for policy 0, policy_version 34790 (0.0008) -[2023-10-17 01:39:28,538][62373] Updated weights for policy 0, policy_version 34800 (0.0008) -[2023-10-17 01:39:28,910][62373] Updated weights for policy 0, policy_version 34810 (0.0009) -[2023-10-17 01:39:31,952][62408] Updated weights for policy 1, policy_version 34570 (0.0007) -[2023-10-17 01:39:32,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 71041024. Throughput: 0: 1778.3, 1: 1786.9. Samples: 17777504. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:39:32,215][61453] Avg episode reward: [(0, '9.620'), (1, '7.960')] -[2023-10-17 01:39:32,226][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000034816_35651584.pth... -[2023-10-17 01:39:32,260][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000033152_33947648.pth -[2023-10-17 01:39:32,323][62408] Updated weights for policy 1, policy_version 34580 (0.0009) -[2023-10-17 01:39:32,705][62408] Updated weights for policy 1, policy_version 34590 (0.0007) -[2023-10-17 01:39:32,754][62373] Updated weights for policy 0, policy_version 34820 (0.0008) -[2023-10-17 01:39:32,769][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000034592_35422208.pth... -[2023-10-17 01:39:32,797][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000032928_33718272.pth -[2023-10-17 01:39:33,119][62373] Updated weights for policy 0, policy_version 34830 (0.0008) -[2023-10-17 01:39:33,492][62373] Updated weights for policy 0, policy_version 34840 (0.0008) -[2023-10-17 01:39:36,618][62408] Updated weights for policy 1, policy_version 34600 (0.0010) -[2023-10-17 01:39:36,984][62408] Updated weights for policy 1, policy_version 34610 (0.0010) -[2023-10-17 01:39:37,147][62373] Updated weights for policy 0, policy_version 34850 (0.0010) -[2023-10-17 01:39:37,214][61453] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 71106560. Throughput: 0: 1765.1, 1: 1760.7. Samples: 17787406. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:39:37,215][61453] Avg episode reward: [(0, '10.030'), (1, '8.080')] -[2023-10-17 01:39:37,348][62408] Updated weights for policy 1, policy_version 34620 (0.0007) -[2023-10-17 01:39:37,540][62373] Updated weights for policy 0, policy_version 34860 (0.0007) -[2023-10-17 01:39:37,910][62373] Updated weights for policy 0, policy_version 34870 (0.0007) -[2023-10-17 01:39:38,275][62094] Saving new best policy, reward=10.030! -[2023-10-17 01:39:38,279][62373] Updated weights for policy 0, policy_version 34880 (0.0008) -[2023-10-17 01:39:41,161][62408] Updated weights for policy 1, policy_version 34630 (0.0007) -[2023-10-17 01:39:41,526][62408] Updated weights for policy 1, policy_version 34640 (0.0009) -[2023-10-17 01:39:41,898][62408] Updated weights for policy 1, policy_version 34650 (0.0007) -[2023-10-17 01:39:42,124][62373] Updated weights for policy 0, policy_version 34890 (0.0007) -[2023-10-17 01:39:42,214][61453] Fps is (10 sec: 16384.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 71204864. Throughput: 0: 1777.0, 1: 1787.4. Samples: 17809448. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:39:42,215][61453] Avg episode reward: [(0, '9.640'), (1, '8.320')] -[2023-10-17 01:39:42,491][62373] Updated weights for policy 0, policy_version 34900 (0.0009) -[2023-10-17 01:39:42,861][62373] Updated weights for policy 0, policy_version 34910 (0.0007) -[2023-10-17 01:39:45,780][62408] Updated weights for policy 1, policy_version 34660 (0.0008) -[2023-10-17 01:39:46,145][62408] Updated weights for policy 1, policy_version 34670 (0.0008) -[2023-10-17 01:39:46,448][62373] Updated weights for policy 0, policy_version 34920 (0.0008) -[2023-10-17 01:39:46,513][62408] Updated weights for policy 1, policy_version 34680 (0.0009) -[2023-10-17 01:39:46,816][62373] Updated weights for policy 0, policy_version 34930 (0.0009) -[2023-10-17 01:39:47,180][62373] Updated weights for policy 0, policy_version 34940 (0.0008) -[2023-10-17 01:39:47,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 71270400. Throughput: 0: 1783.0, 1: 1753.1. Samples: 17829320. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) -[2023-10-17 01:39:47,214][61453] Avg episode reward: [(0, '9.220'), (1, '8.010')] -[2023-10-17 01:39:50,495][62408] Updated weights for policy 1, policy_version 34690 (0.0008) -[2023-10-17 01:39:50,862][62408] Updated weights for policy 1, policy_version 34700 (0.0010) -[2023-10-17 01:39:51,002][62373] Updated weights for policy 0, policy_version 34950 (0.0007) -[2023-10-17 01:39:51,234][62408] Updated weights for policy 1, policy_version 34710 (0.0009) -[2023-10-17 01:39:51,368][62373] Updated weights for policy 0, policy_version 34960 (0.0010) -[2023-10-17 01:39:51,601][62408] Updated weights for policy 1, policy_version 34720 (0.0008) -[2023-10-17 01:39:51,742][62373] Updated weights for policy 0, policy_version 34970 (0.0009) -[2023-10-17 01:39:52,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14745.5, 300 sec: 14329.0). Total num frames: 71368704. Throughput: 0: 1771.8, 1: 1777.5. Samples: 17841242. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) -[2023-10-17 01:39:52,215][61453] Avg episode reward: [(0, '9.380'), (1, '7.670')] -[2023-10-17 01:39:55,371][62408] Updated weights for policy 1, policy_version 34730 (0.0009) -[2023-10-17 01:39:55,513][62373] Updated weights for policy 0, policy_version 34980 (0.0010) -[2023-10-17 01:39:55,728][62408] Updated weights for policy 1, policy_version 34740 (0.0009) -[2023-10-17 01:39:55,886][62373] Updated weights for policy 0, policy_version 34990 (0.0009) -[2023-10-17 01:39:56,093][62408] Updated weights for policy 1, policy_version 34750 (0.0007) -[2023-10-17 01:39:56,256][62373] Updated weights for policy 0, policy_version 35000 (0.0009) -[2023-10-17 01:39:57,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 71434240. Throughput: 0: 1788.3, 1: 1764.6. Samples: 17861896. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) -[2023-10-17 01:39:57,215][61453] Avg episode reward: [(0, '8.520'), (1, '7.720')] -[2023-10-17 01:39:59,817][62408] Updated weights for policy 1, policy_version 34760 (0.0010) -[2023-10-17 01:40:00,062][62373] Updated weights for policy 0, policy_version 35010 (0.0007) -[2023-10-17 01:40:00,184][62408] Updated weights for policy 1, policy_version 34770 (0.0009) -[2023-10-17 01:40:00,440][62373] Updated weights for policy 0, policy_version 35020 (0.0008) -[2023-10-17 01:40:00,549][62408] Updated weights for policy 1, policy_version 34780 (0.0008) -[2023-10-17 01:40:00,801][62373] Updated weights for policy 0, policy_version 35030 (0.0008) -[2023-10-17 01:40:01,171][62373] Updated weights for policy 0, policy_version 35040 (0.0007) -[2023-10-17 01:40:02,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 71499776. Throughput: 0: 1772.8, 1: 1751.2. Samples: 17882990. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) -[2023-10-17 01:40:02,215][61453] Avg episode reward: [(0, '8.690'), (1, '7.600')] -[2023-10-17 01:40:04,419][62408] Updated weights for policy 1, policy_version 34790 (0.0008) -[2023-10-17 01:40:04,787][62408] Updated weights for policy 1, policy_version 34800 (0.0007) -[2023-10-17 01:40:04,906][62373] Updated weights for policy 0, policy_version 35050 (0.0007) -[2023-10-17 01:40:05,155][62408] Updated weights for policy 1, policy_version 34810 (0.0007) -[2023-10-17 01:40:05,275][62373] Updated weights for policy 0, policy_version 35060 (0.0007) -[2023-10-17 01:40:05,645][62373] Updated weights for policy 0, policy_version 35070 (0.0008) -[2023-10-17 01:40:07,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 71565312. Throughput: 0: 1795.5, 1: 1761.9. Samples: 17894348. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) -[2023-10-17 01:40:07,214][61453] Avg episode reward: [(0, '8.770'), (1, '7.250')] -[2023-10-17 01:40:09,026][62408] Updated weights for policy 1, policy_version 34820 (0.0009) -[2023-10-17 01:40:09,396][62373] Updated weights for policy 0, policy_version 35080 (0.0009) -[2023-10-17 01:40:09,401][62408] Updated weights for policy 1, policy_version 34830 (0.0009) -[2023-10-17 01:40:09,762][62373] Updated weights for policy 0, policy_version 35090 (0.0008) -[2023-10-17 01:40:09,772][62408] Updated weights for policy 1, policy_version 34840 (0.0008) -[2023-10-17 01:40:10,136][62373] Updated weights for policy 0, policy_version 35100 (0.0008) -[2023-10-17 01:40:12,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 71630848. Throughput: 0: 1777.4, 1: 1745.6. Samples: 17914500. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-17 01:40:12,215][61453] Avg episode reward: [(0, '8.560'), (1, '7.470')] -[2023-10-17 01:40:13,646][62408] Updated weights for policy 1, policy_version 34850 (0.0009) -[2023-10-17 01:40:13,942][62373] Updated weights for policy 0, policy_version 35110 (0.0008) -[2023-10-17 01:40:14,016][62408] Updated weights for policy 1, policy_version 34860 (0.0009) -[2023-10-17 01:40:14,314][62373] Updated weights for policy 0, policy_version 35120 (0.0008) -[2023-10-17 01:40:14,385][62408] Updated weights for policy 1, policy_version 34870 (0.0007) -[2023-10-17 01:40:14,691][62373] Updated weights for policy 0, policy_version 35130 (0.0008) -[2023-10-17 01:40:14,744][62408] Updated weights for policy 1, policy_version 34880 (0.0008) -[2023-10-17 01:40:17,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 71696384. Throughput: 0: 1780.0, 1: 1753.7. Samples: 17936524. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-17 01:40:17,215][61453] Avg episode reward: [(0, '8.510'), (1, '8.160')] -[2023-10-17 01:40:18,350][62373] Updated weights for policy 0, policy_version 35140 (0.0008) -[2023-10-17 01:40:18,718][62373] Updated weights for policy 0, policy_version 35150 (0.0007) -[2023-10-17 01:40:18,763][62408] Updated weights for policy 1, policy_version 34890 (0.0007) -[2023-10-17 01:40:19,083][62373] Updated weights for policy 0, policy_version 35160 (0.0007) -[2023-10-17 01:40:19,140][62408] Updated weights for policy 1, policy_version 34900 (0.0008) -[2023-10-17 01:40:19,506][62408] Updated weights for policy 1, policy_version 34910 (0.0008) -[2023-10-17 01:40:22,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 71761920. Throughput: 0: 1787.5, 1: 1742.2. Samples: 17946242. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-17 01:40:22,215][61453] Avg episode reward: [(0, '8.310'), (1, '7.940')] -[2023-10-17 01:40:23,053][62373] Updated weights for policy 0, policy_version 35170 (0.0008) -[2023-10-17 01:40:23,375][62408] Updated weights for policy 1, policy_version 34920 (0.0008) -[2023-10-17 01:40:23,447][62373] Updated weights for policy 0, policy_version 35180 (0.0007) -[2023-10-17 01:40:23,744][62408] Updated weights for policy 1, policy_version 34930 (0.0007) -[2023-10-17 01:40:23,824][62373] Updated weights for policy 0, policy_version 35190 (0.0009) -[2023-10-17 01:40:24,110][62408] Updated weights for policy 1, policy_version 34940 (0.0007) -[2023-10-17 01:40:24,194][62373] Updated weights for policy 0, policy_version 35200 (0.0008) -[2023-10-17 01:40:27,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 71827456. Throughput: 0: 1775.5, 1: 1749.5. Samples: 17968072. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-17 01:40:27,215][61453] Avg episode reward: [(0, '9.400'), (1, '7.490')] -[2023-10-17 01:40:27,978][62408] Updated weights for policy 1, policy_version 34950 (0.0008) -[2023-10-17 01:40:28,087][62373] Updated weights for policy 0, policy_version 35210 (0.0007) -[2023-10-17 01:40:28,339][62408] Updated weights for policy 1, policy_version 34960 (0.0007) -[2023-10-17 01:40:28,456][62373] Updated weights for policy 0, policy_version 35220 (0.0008) -[2023-10-17 01:40:28,708][62408] Updated weights for policy 1, policy_version 34970 (0.0009) -[2023-10-17 01:40:28,830][62373] Updated weights for policy 0, policy_version 35230 (0.0008) -[2023-10-17 01:40:32,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 71892992. Throughput: 0: 1787.6, 1: 1782.7. Samples: 17989984. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-17 01:40:32,215][61453] Avg episode reward: [(0, '8.690'), (1, '8.010')] -[2023-10-17 01:40:32,421][62408] Updated weights for policy 1, policy_version 34980 (0.0008) -[2023-10-17 01:40:32,645][62373] Updated weights for policy 0, policy_version 35240 (0.0009) -[2023-10-17 01:40:32,782][62408] Updated weights for policy 1, policy_version 34990 (0.0010) -[2023-10-17 01:40:33,018][62373] Updated weights for policy 0, policy_version 35250 (0.0008) -[2023-10-17 01:40:33,159][62408] Updated weights for policy 1, policy_version 35000 (0.0009) -[2023-10-17 01:40:33,381][62373] Updated weights for policy 0, policy_version 35260 (0.0008) -[2023-10-17 01:40:37,069][62408] Updated weights for policy 1, policy_version 35010 (0.0010) -[2023-10-17 01:40:37,182][62373] Updated weights for policy 0, policy_version 35270 (0.0007) -[2023-10-17 01:40:37,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 71958528. Throughput: 0: 1767.7, 1: 1750.0. Samples: 17999536. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-17 01:40:37,214][61453] Avg episode reward: [(0, '8.680'), (1, '8.380')] -[2023-10-17 01:40:37,426][62408] Updated weights for policy 1, policy_version 35020 (0.0009) -[2023-10-17 01:40:37,551][62373] Updated weights for policy 0, policy_version 35280 (0.0007) -[2023-10-17 01:40:37,790][62408] Updated weights for policy 1, policy_version 35030 (0.0007) -[2023-10-17 01:40:37,915][62373] Updated weights for policy 0, policy_version 35290 (0.0008) -[2023-10-17 01:40:38,159][62408] Updated weights for policy 1, policy_version 35040 (0.0008) -[2023-10-17 01:40:41,654][62373] Updated weights for policy 0, policy_version 35300 (0.0008) -[2023-10-17 01:40:42,017][62373] Updated weights for policy 0, policy_version 35310 (0.0007) -[2023-10-17 01:40:42,174][62408] Updated weights for policy 1, policy_version 35050 (0.0008) -[2023-10-17 01:40:42,214][61453] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 72024064. Throughput: 0: 1781.2, 1: 1759.3. Samples: 18021218. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-17 01:40:42,215][61453] Avg episode reward: [(0, '8.980'), (1, '8.560')] -[2023-10-17 01:40:42,393][62373] Updated weights for policy 0, policy_version 35320 (0.0008) -[2023-10-17 01:40:42,527][62408] Updated weights for policy 1, policy_version 35060 (0.0008) -[2023-10-17 01:40:42,900][62408] Updated weights for policy 1, policy_version 35070 (0.0008) -[2023-10-17 01:40:46,343][62373] Updated weights for policy 0, policy_version 35330 (0.0007) -[2023-10-17 01:40:46,718][62373] Updated weights for policy 0, policy_version 35340 (0.0009) -[2023-10-17 01:40:46,787][62408] Updated weights for policy 1, policy_version 35080 (0.0008) -[2023-10-17 01:40:47,087][62373] Updated weights for policy 0, policy_version 35350 (0.0008) -[2023-10-17 01:40:47,154][62408] Updated weights for policy 1, policy_version 35090 (0.0008) -[2023-10-17 01:40:47,214][61453] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 72089600. Throughput: 0: 1775.6, 1: 1753.1. Samples: 18041784. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-17 01:40:47,215][61453] Avg episode reward: [(0, '8.830'), (1, '8.060')] -[2023-10-17 01:40:47,453][62373] Updated weights for policy 0, policy_version 35360 (0.0007) -[2023-10-17 01:40:47,523][62408] Updated weights for policy 1, policy_version 35100 (0.0008) -[2023-10-17 01:40:51,246][62373] Updated weights for policy 0, policy_version 35370 (0.0007) -[2023-10-17 01:40:51,355][62408] Updated weights for policy 1, policy_version 35110 (0.0007) -[2023-10-17 01:40:51,609][62373] Updated weights for policy 0, policy_version 35380 (0.0007) -[2023-10-17 01:40:51,729][62408] Updated weights for policy 1, policy_version 35120 (0.0007) -[2023-10-17 01:40:51,983][62373] Updated weights for policy 0, policy_version 35390 (0.0007) -[2023-10-17 01:40:52,101][62408] Updated weights for policy 1, policy_version 35130 (0.0010) -[2023-10-17 01:40:52,214][61453] Fps is (10 sec: 16384.2, 60 sec: 13653.4, 300 sec: 14218.0). Total num frames: 72187904. Throughput: 0: 1768.9, 1: 1747.1. Samples: 18052568. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-17 01:40:52,214][61453] Avg episode reward: [(0, '9.160'), (1, '8.580')] -[2023-10-17 01:40:55,762][62373] Updated weights for policy 0, policy_version 35400 (0.0007) -[2023-10-17 01:40:55,905][62408] Updated weights for policy 1, policy_version 35140 (0.0011) -[2023-10-17 01:40:56,131][62373] Updated weights for policy 0, policy_version 35410 (0.0009) -[2023-10-17 01:40:56,277][62408] Updated weights for policy 1, policy_version 35150 (0.0009) -[2023-10-17 01:40:56,498][62373] Updated weights for policy 0, policy_version 35420 (0.0009) -[2023-10-17 01:40:56,647][62408] Updated weights for policy 1, policy_version 35160 (0.0008) -[2023-10-17 01:40:57,214][61453] Fps is (10 sec: 19660.4, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 72286208. Throughput: 0: 1782.8, 1: 1762.0. Samples: 18074014. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-17 01:40:57,215][61453] Avg episode reward: [(0, '9.410'), (1, '9.190')] -[2023-10-17 01:41:00,206][62373] Updated weights for policy 0, policy_version 35430 (0.0009) -[2023-10-17 01:41:00,557][62408] Updated weights for policy 1, policy_version 35170 (0.0010) -[2023-10-17 01:41:00,583][62373] Updated weights for policy 0, policy_version 35440 (0.0008) -[2023-10-17 01:41:00,922][62408] Updated weights for policy 1, policy_version 35180 (0.0008) -[2023-10-17 01:41:00,946][62373] Updated weights for policy 0, policy_version 35450 (0.0007) -[2023-10-17 01:41:01,292][62408] Updated weights for policy 1, policy_version 35190 (0.0008) -[2023-10-17 01:41:01,655][62408] Updated weights for policy 1, policy_version 35200 (0.0008) -[2023-10-17 01:41:02,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 72351744. Throughput: 0: 1762.8, 1: 1734.4. Samples: 18093898. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-17 01:41:02,215][61453] Avg episode reward: [(0, '9.600'), (1, '9.510')] -[2023-10-17 01:41:02,226][62252] Saving new best policy, reward=9.510! -[2023-10-17 01:41:04,915][62373] Updated weights for policy 0, policy_version 35460 (0.0008) -[2023-10-17 01:41:05,284][62373] Updated weights for policy 0, policy_version 35470 (0.0008) -[2023-10-17 01:41:05,417][62408] Updated weights for policy 1, policy_version 35210 (0.0009) -[2023-10-17 01:41:05,648][62373] Updated weights for policy 0, policy_version 35480 (0.0009) -[2023-10-17 01:41:05,794][62408] Updated weights for policy 1, policy_version 35220 (0.0007) -[2023-10-17 01:41:06,157][62408] Updated weights for policy 1, policy_version 35230 (0.0010) -[2023-10-17 01:41:07,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 72417280. Throughput: 0: 1783.5, 1: 1777.7. Samples: 18106498. Policy #0 lag: (min: 13.0, avg: 21.0, max: 45.0) -[2023-10-17 01:41:07,215][61453] Avg episode reward: [(0, '9.530'), (1, '9.400')] -[2023-10-17 01:41:09,420][62373] Updated weights for policy 0, policy_version 35490 (0.0008) -[2023-10-17 01:41:09,789][62373] Updated weights for policy 0, policy_version 35500 (0.0007) -[2023-10-17 01:41:10,047][62408] Updated weights for policy 1, policy_version 35240 (0.0008) -[2023-10-17 01:41:10,161][62373] Updated weights for policy 0, policy_version 35510 (0.0007) -[2023-10-17 01:41:10,414][62408] Updated weights for policy 1, policy_version 35250 (0.0009) -[2023-10-17 01:41:10,535][62373] Updated weights for policy 0, policy_version 35520 (0.0008) -[2023-10-17 01:41:10,776][62408] Updated weights for policy 1, policy_version 35260 (0.0010) -[2023-10-17 01:41:12,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 72482816. Throughput: 0: 1764.9, 1: 1737.2. Samples: 18125666. Policy #0 lag: (min: 13.0, avg: 21.0, max: 45.0) -[2023-10-17 01:41:12,214][61453] Avg episode reward: [(0, '10.370'), (1, '8.930')] -[2023-10-17 01:41:12,215][62094] Saving new best policy, reward=10.370! -[2023-10-17 01:41:14,277][62373] Updated weights for policy 0, policy_version 35530 (0.0009) -[2023-10-17 01:41:14,647][62373] Updated weights for policy 0, policy_version 35540 (0.0007) -[2023-10-17 01:41:14,778][62408] Updated weights for policy 1, policy_version 35270 (0.0008) -[2023-10-17 01:41:15,026][62373] Updated weights for policy 0, policy_version 35550 (0.0007) -[2023-10-17 01:41:15,148][62408] Updated weights for policy 1, policy_version 35280 (0.0007) -[2023-10-17 01:41:15,513][62408] Updated weights for policy 1, policy_version 35290 (0.0008) -[2023-10-17 01:41:17,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 72548352. Throughput: 0: 1765.4, 1: 1727.2. Samples: 18147152. Policy #0 lag: (min: 13.0, avg: 21.0, max: 45.0) -[2023-10-17 01:41:17,215][61453] Avg episode reward: [(0, '9.280'), (1, '9.450')] -[2023-10-17 01:41:18,835][62373] Updated weights for policy 0, policy_version 35560 (0.0010) -[2023-10-17 01:41:19,213][62373] Updated weights for policy 0, policy_version 35570 (0.0008) -[2023-10-17 01:41:19,433][62408] Updated weights for policy 1, policy_version 35300 (0.0008) -[2023-10-17 01:41:19,580][62373] Updated weights for policy 0, policy_version 35580 (0.0007) -[2023-10-17 01:41:19,791][62408] Updated weights for policy 1, policy_version 35310 (0.0007) -[2023-10-17 01:41:20,151][62408] Updated weights for policy 1, policy_version 35320 (0.0007) -[2023-10-17 01:41:22,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 72613888. Throughput: 0: 1767.9, 1: 1744.2. Samples: 18157578. Policy #0 lag: (min: 13.0, avg: 21.0, max: 45.0) -[2023-10-17 01:41:22,215][61453] Avg episode reward: [(0, '9.590'), (1, '8.690')] -[2023-10-17 01:41:23,242][62373] Updated weights for policy 0, policy_version 35590 (0.0008) -[2023-10-17 01:41:23,600][62373] Updated weights for policy 0, policy_version 35600 (0.0007) -[2023-10-17 01:41:23,941][62408] Updated weights for policy 1, policy_version 35330 (0.0009) -[2023-10-17 01:41:23,973][62373] Updated weights for policy 0, policy_version 35610 (0.0007) -[2023-10-17 01:41:24,315][62408] Updated weights for policy 1, policy_version 35340 (0.0010) -[2023-10-17 01:41:24,685][62408] Updated weights for policy 1, policy_version 35350 (0.0008) -[2023-10-17 01:41:25,060][62408] Updated weights for policy 1, policy_version 35360 (0.0010) -[2023-10-17 01:41:27,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 72679424. Throughput: 0: 1773.6, 1: 1738.4. Samples: 18179254. Policy #0 lag: (min: 13.0, avg: 21.0, max: 45.0) -[2023-10-17 01:41:27,215][61453] Avg episode reward: [(0, '9.760'), (1, '8.030')] -[2023-10-17 01:41:27,717][62373] Updated weights for policy 0, policy_version 35620 (0.0008) -[2023-10-17 01:41:28,082][62373] Updated weights for policy 0, policy_version 35630 (0.0007) -[2023-10-17 01:41:28,450][62373] Updated weights for policy 0, policy_version 35640 (0.0008) -[2023-10-17 01:41:28,928][62408] Updated weights for policy 1, policy_version 35370 (0.0007) -[2023-10-17 01:41:29,299][62408] Updated weights for policy 1, policy_version 35380 (0.0008) -[2023-10-17 01:41:29,675][62408] Updated weights for policy 1, policy_version 35390 (0.0008) -[2023-10-17 01:41:32,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 72744960. Throughput: 0: 1790.8, 1: 1750.9. Samples: 18201162. Policy #0 lag: (min: 13.0, avg: 21.0, max: 45.0) -[2023-10-17 01:41:32,215][61453] Avg episode reward: [(0, '9.320'), (1, '8.160')] -[2023-10-17 01:41:32,225][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000035648_36503552.pth... -[2023-10-17 01:41:32,225][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000035392_36241408.pth... -[2023-10-17 01:41:32,275][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000033760_34570240.pth -[2023-10-17 01:41:32,277][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000033984_34799616.pth -[2023-10-17 01:41:32,491][62373] Updated weights for policy 0, policy_version 35650 (0.0009) -[2023-10-17 01:41:32,861][62373] Updated weights for policy 0, policy_version 35660 (0.0008) -[2023-10-17 01:41:33,239][62373] Updated weights for policy 0, policy_version 35670 (0.0009) -[2023-10-17 01:41:33,361][62408] Updated weights for policy 1, policy_version 35400 (0.0008) -[2023-10-17 01:41:33,611][62373] Updated weights for policy 0, policy_version 35680 (0.0008) -[2023-10-17 01:41:33,723][62408] Updated weights for policy 1, policy_version 35410 (0.0007) -[2023-10-17 01:41:34,096][62408] Updated weights for policy 1, policy_version 35420 (0.0008) -[2023-10-17 01:41:37,183][62373] Updated weights for policy 0, policy_version 35690 (0.0007) -[2023-10-17 01:41:37,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 72810496. Throughput: 0: 1773.2, 1: 1741.9. Samples: 18210750. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-17 01:41:37,215][61453] Avg episode reward: [(0, '9.160'), (1, '7.890')] -[2023-10-17 01:41:37,546][62373] Updated weights for policy 0, policy_version 35700 (0.0009) -[2023-10-17 01:41:37,916][62373] Updated weights for policy 0, policy_version 35710 (0.0007) -[2023-10-17 01:41:37,958][62408] Updated weights for policy 1, policy_version 35430 (0.0007) -[2023-10-17 01:41:38,323][62408] Updated weights for policy 1, policy_version 35440 (0.0007) -[2023-10-17 01:41:38,678][62408] Updated weights for policy 1, policy_version 35450 (0.0007) -[2023-10-17 01:41:41,781][62373] Updated weights for policy 0, policy_version 35720 (0.0007) -[2023-10-17 01:41:42,145][62373] Updated weights for policy 0, policy_version 35730 (0.0009) -[2023-10-17 01:41:42,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 72876032. Throughput: 0: 1783.9, 1: 1743.6. Samples: 18232750. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-17 01:41:42,215][61453] Avg episode reward: [(0, '9.360'), (1, '7.660')] -[2023-10-17 01:41:42,491][62408] Updated weights for policy 1, policy_version 35460 (0.0007) -[2023-10-17 01:41:42,518][62373] Updated weights for policy 0, policy_version 35740 (0.0009) -[2023-10-17 01:41:42,857][62408] Updated weights for policy 1, policy_version 35470 (0.0008) -[2023-10-17 01:41:43,223][62408] Updated weights for policy 1, policy_version 35480 (0.0010) -[2023-10-17 01:41:46,347][62373] Updated weights for policy 0, policy_version 35750 (0.0008) -[2023-10-17 01:41:46,720][62373] Updated weights for policy 0, policy_version 35760 (0.0008) -[2023-10-17 01:41:47,061][62408] Updated weights for policy 1, policy_version 35490 (0.0008) -[2023-10-17 01:41:47,083][62373] Updated weights for policy 0, policy_version 35770 (0.0008) -[2023-10-17 01:41:47,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 72941568. Throughput: 0: 1780.2, 1: 1780.1. Samples: 18254110. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-17 01:41:47,215][61453] Avg episode reward: [(0, '9.070'), (1, '7.490')] -[2023-10-17 01:41:47,420][62408] Updated weights for policy 1, policy_version 35500 (0.0007) -[2023-10-17 01:41:47,792][62408] Updated weights for policy 1, policy_version 35510 (0.0007) -[2023-10-17 01:41:48,159][62408] Updated weights for policy 1, policy_version 35520 (0.0007) -[2023-10-17 01:41:50,750][62373] Updated weights for policy 0, policy_version 35780 (0.0009) -[2023-10-17 01:41:51,119][62373] Updated weights for policy 0, policy_version 35790 (0.0008) -[2023-10-17 01:41:51,486][62373] Updated weights for policy 0, policy_version 35800 (0.0007) -[2023-10-17 01:41:52,034][62408] Updated weights for policy 1, policy_version 35530 (0.0009) -[2023-10-17 01:41:52,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 73039872. Throughput: 0: 1775.3, 1: 1738.4. Samples: 18264610. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-17 01:41:52,214][61453] Avg episode reward: [(0, '9.560'), (1, '7.980')] -[2023-10-17 01:41:52,405][62408] Updated weights for policy 1, policy_version 35540 (0.0011) -[2023-10-17 01:41:52,779][62408] Updated weights for policy 1, policy_version 35550 (0.0008) -[2023-10-17 01:41:55,180][62373] Updated weights for policy 0, policy_version 35810 (0.0008) -[2023-10-17 01:41:55,575][62373] Updated weights for policy 0, policy_version 35820 (0.0010) -[2023-10-17 01:41:55,943][62373] Updated weights for policy 0, policy_version 35830 (0.0009) -[2023-10-17 01:41:56,305][62373] Updated weights for policy 0, policy_version 35840 (0.0009) -[2023-10-17 01:41:56,680][62408] Updated weights for policy 1, policy_version 35560 (0.0009) -[2023-10-17 01:41:57,046][62408] Updated weights for policy 1, policy_version 35570 (0.0008) -[2023-10-17 01:41:57,214][61453] Fps is (10 sec: 16384.1, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 73105408. Throughput: 0: 1787.0, 1: 1775.1. Samples: 18285958. Policy #0 lag: (min: 19.0, avg: 19.0, max: 19.0) -[2023-10-17 01:41:57,214][61453] Avg episode reward: [(0, '8.850'), (1, '7.980')] -[2023-10-17 01:41:57,417][62408] Updated weights for policy 1, policy_version 35580 (0.0008) -[2023-10-17 01:41:59,868][62373] Updated weights for policy 0, policy_version 35850 (0.0010) -[2023-10-17 01:42:00,231][62373] Updated weights for policy 0, policy_version 35860 (0.0008) -[2023-10-17 01:42:00,607][62373] Updated weights for policy 0, policy_version 35870 (0.0008) -[2023-10-17 01:42:01,361][62408] Updated weights for policy 1, policy_version 35590 (0.0008) -[2023-10-17 01:42:01,728][62408] Updated weights for policy 1, policy_version 35600 (0.0009) -[2023-10-17 01:42:02,091][62408] Updated weights for policy 1, policy_version 35610 (0.0007) -[2023-10-17 01:42:02,214][61453] Fps is (10 sec: 13107.0, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 73170944. Throughput: 0: 1787.4, 1: 1762.4. Samples: 18306892. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:42:02,215][61453] Avg episode reward: [(0, '8.800'), (1, '8.350')] -[2023-10-17 01:42:04,435][62373] Updated weights for policy 0, policy_version 35880 (0.0008) -[2023-10-17 01:42:04,813][62373] Updated weights for policy 0, policy_version 35890 (0.0008) -[2023-10-17 01:42:05,182][62373] Updated weights for policy 0, policy_version 35900 (0.0010) -[2023-10-17 01:42:05,882][62408] Updated weights for policy 1, policy_version 35620 (0.0008) -[2023-10-17 01:42:06,242][62408] Updated weights for policy 1, policy_version 35630 (0.0009) -[2023-10-17 01:42:06,611][62408] Updated weights for policy 1, policy_version 35640 (0.0008) -[2023-10-17 01:42:07,214][61453] Fps is (10 sec: 16383.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 73269248. Throughput: 0: 1798.2, 1: 1762.7. Samples: 18317818. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:42:07,215][61453] Avg episode reward: [(0, '9.530'), (1, '8.120')] -[2023-10-17 01:42:09,079][62373] Updated weights for policy 0, policy_version 35910 (0.0009) -[2023-10-17 01:42:09,446][62373] Updated weights for policy 0, policy_version 35920 (0.0009) -[2023-10-17 01:42:09,823][62373] Updated weights for policy 0, policy_version 35930 (0.0007) -[2023-10-17 01:42:10,439][62408] Updated weights for policy 1, policy_version 35650 (0.0008) -[2023-10-17 01:42:10,809][62408] Updated weights for policy 1, policy_version 35660 (0.0010) -[2023-10-17 01:42:11,172][62408] Updated weights for policy 1, policy_version 35670 (0.0008) -[2023-10-17 01:42:11,539][62408] Updated weights for policy 1, policy_version 35680 (0.0007) -[2023-10-17 01:42:12,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 73334784. Throughput: 0: 1780.0, 1: 1764.1. Samples: 18338736. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:42:12,214][61453] Avg episode reward: [(0, '9.480'), (1, '8.380')] -[2023-10-17 01:42:13,614][62373] Updated weights for policy 0, policy_version 35940 (0.0008) -[2023-10-17 01:42:13,979][62373] Updated weights for policy 0, policy_version 35950 (0.0009) -[2023-10-17 01:42:14,350][62373] Updated weights for policy 0, policy_version 35960 (0.0007) -[2023-10-17 01:42:15,328][62408] Updated weights for policy 1, policy_version 35690 (0.0007) -[2023-10-17 01:42:15,694][62408] Updated weights for policy 1, policy_version 35700 (0.0007) -[2023-10-17 01:42:16,063][62408] Updated weights for policy 1, policy_version 35710 (0.0007) -[2023-10-17 01:42:17,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 73400320. Throughput: 0: 1788.8, 1: 1749.0. Samples: 18360362. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:42:17,215][61453] Avg episode reward: [(0, '9.010'), (1, '8.280')] -[2023-10-17 01:42:18,214][62373] Updated weights for policy 0, policy_version 35970 (0.0007) -[2023-10-17 01:42:18,582][62373] Updated weights for policy 0, policy_version 35980 (0.0007) -[2023-10-17 01:42:18,957][62373] Updated weights for policy 0, policy_version 35990 (0.0009) -[2023-10-17 01:42:19,326][62373] Updated weights for policy 0, policy_version 36000 (0.0007) -[2023-10-17 01:42:19,952][62408] Updated weights for policy 1, policy_version 35720 (0.0007) -[2023-10-17 01:42:20,327][62408] Updated weights for policy 1, policy_version 35730 (0.0008) -[2023-10-17 01:42:20,693][62408] Updated weights for policy 1, policy_version 35740 (0.0010) -[2023-10-17 01:42:22,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 73465856. Throughput: 0: 1785.8, 1: 1773.2. Samples: 18370904. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:42:22,214][61453] Avg episode reward: [(0, '9.340'), (1, '8.370')] -[2023-10-17 01:42:23,147][62373] Updated weights for policy 0, policy_version 36010 (0.0007) -[2023-10-17 01:42:23,519][62373] Updated weights for policy 0, policy_version 36020 (0.0010) -[2023-10-17 01:42:23,886][62373] Updated weights for policy 0, policy_version 36030 (0.0008) -[2023-10-17 01:42:24,469][62408] Updated weights for policy 1, policy_version 35750 (0.0008) -[2023-10-17 01:42:24,840][62408] Updated weights for policy 1, policy_version 35760 (0.0008) -[2023-10-17 01:42:25,209][62408] Updated weights for policy 1, policy_version 35770 (0.0008) -[2023-10-17 01:42:27,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 73531392. Throughput: 0: 1786.1, 1: 1749.5. Samples: 18391852. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:42:27,215][61453] Avg episode reward: [(0, '9.870'), (1, '8.530')] -[2023-10-17 01:42:27,626][62373] Updated weights for policy 0, policy_version 36040 (0.0008) -[2023-10-17 01:42:27,992][62373] Updated weights for policy 0, policy_version 36050 (0.0007) -[2023-10-17 01:42:28,374][62373] Updated weights for policy 0, policy_version 36060 (0.0007) -[2023-10-17 01:42:29,076][62408] Updated weights for policy 1, policy_version 35780 (0.0007) -[2023-10-17 01:42:29,441][62408] Updated weights for policy 1, policy_version 35790 (0.0007) -[2023-10-17 01:42:29,810][62408] Updated weights for policy 1, policy_version 35800 (0.0007) -[2023-10-17 01:42:32,096][62373] Updated weights for policy 0, policy_version 36070 (0.0008) -[2023-10-17 01:42:32,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 73596928. Throughput: 0: 1806.6, 1: 1747.9. Samples: 18414062. Policy #0 lag: (min: 23.0, avg: 23.3, max: 34.0) -[2023-10-17 01:42:32,214][61453] Avg episode reward: [(0, '9.640'), (1, '8.140')] -[2023-10-17 01:42:32,471][62373] Updated weights for policy 0, policy_version 36080 (0.0009) -[2023-10-17 01:42:32,842][62373] Updated weights for policy 0, policy_version 36090 (0.0008) -[2023-10-17 01:42:33,560][62408] Updated weights for policy 1, policy_version 35810 (0.0011) -[2023-10-17 01:42:33,925][62408] Updated weights for policy 1, policy_version 35820 (0.0009) -[2023-10-17 01:42:34,290][62408] Updated weights for policy 1, policy_version 35830 (0.0009) -[2023-10-17 01:42:34,658][62408] Updated weights for policy 1, policy_version 35840 (0.0010) -[2023-10-17 01:42:36,658][62373] Updated weights for policy 0, policy_version 36100 (0.0007) -[2023-10-17 01:42:37,038][62373] Updated weights for policy 0, policy_version 36110 (0.0008) -[2023-10-17 01:42:37,214][61453] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 73662464. Throughput: 0: 1789.0, 1: 1752.9. Samples: 18423994. Policy #0 lag: (min: 23.0, avg: 23.3, max: 34.0) -[2023-10-17 01:42:37,214][61453] Avg episode reward: [(0, '9.510'), (1, '8.510')] -[2023-10-17 01:42:37,408][62373] Updated weights for policy 0, policy_version 36120 (0.0009) -[2023-10-17 01:42:38,596][62408] Updated weights for policy 1, policy_version 35850 (0.0011) -[2023-10-17 01:42:38,957][62408] Updated weights for policy 1, policy_version 35860 (0.0009) -[2023-10-17 01:42:39,337][62408] Updated weights for policy 1, policy_version 35870 (0.0010) -[2023-10-17 01:42:41,225][62373] Updated weights for policy 0, policy_version 36130 (0.0007) -[2023-10-17 01:42:41,623][62373] Updated weights for policy 0, policy_version 36140 (0.0009) -[2023-10-17 01:42:42,001][62373] Updated weights for policy 0, policy_version 36150 (0.0009) -[2023-10-17 01:42:42,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 73728000. Throughput: 0: 1808.8, 1: 1753.3. Samples: 18446254. Policy #0 lag: (min: 23.0, avg: 23.3, max: 34.0) -[2023-10-17 01:42:42,215][61453] Avg episode reward: [(0, '9.510'), (1, '8.820')] -[2023-10-17 01:42:42,364][62373] Updated weights for policy 0, policy_version 36160 (0.0009) -[2023-10-17 01:42:43,162][62408] Updated weights for policy 1, policy_version 35880 (0.0008) -[2023-10-17 01:42:43,544][62408] Updated weights for policy 1, policy_version 35890 (0.0010) -[2023-10-17 01:42:43,910][62408] Updated weights for policy 1, policy_version 35900 (0.0008) -[2023-10-17 01:42:45,967][62373] Updated weights for policy 0, policy_version 36170 (0.0007) -[2023-10-17 01:42:46,334][62373] Updated weights for policy 0, policy_version 36180 (0.0008) -[2023-10-17 01:42:46,716][62373] Updated weights for policy 0, policy_version 36190 (0.0008) -[2023-10-17 01:42:47,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14218.0). Total num frames: 73826304. Throughput: 0: 1778.0, 1: 1774.6. Samples: 18466760. Policy #0 lag: (min: 23.0, avg: 23.3, max: 34.0) -[2023-10-17 01:42:47,214][61453] Avg episode reward: [(0, '9.770'), (1, '8.750')] -[2023-10-17 01:42:47,707][62408] Updated weights for policy 1, policy_version 35910 (0.0007) -[2023-10-17 01:42:48,080][62408] Updated weights for policy 1, policy_version 35920 (0.0009) -[2023-10-17 01:42:48,451][62408] Updated weights for policy 1, policy_version 35930 (0.0008) -[2023-10-17 01:42:50,508][62373] Updated weights for policy 0, policy_version 36200 (0.0008) -[2023-10-17 01:42:50,881][62373] Updated weights for policy 0, policy_version 36210 (0.0007) -[2023-10-17 01:42:51,253][62373] Updated weights for policy 0, policy_version 36220 (0.0008) -[2023-10-17 01:42:52,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 73891840. Throughput: 0: 1795.3, 1: 1758.8. Samples: 18477748. Policy #0 lag: (min: 23.0, avg: 23.3, max: 34.0) -[2023-10-17 01:42:52,214][61453] Avg episode reward: [(0, '9.960'), (1, '8.880')] -[2023-10-17 01:42:52,286][62408] Updated weights for policy 1, policy_version 35940 (0.0008) -[2023-10-17 01:42:52,658][62408] Updated weights for policy 1, policy_version 35950 (0.0007) -[2023-10-17 01:42:53,021][62408] Updated weights for policy 1, policy_version 35960 (0.0008) -[2023-10-17 01:42:55,069][62373] Updated weights for policy 0, policy_version 36230 (0.0009) -[2023-10-17 01:42:55,449][62373] Updated weights for policy 0, policy_version 36240 (0.0007) -[2023-10-17 01:42:55,809][62373] Updated weights for policy 0, policy_version 36250 (0.0009) -[2023-10-17 01:42:56,863][62408] Updated weights for policy 1, policy_version 35970 (0.0008) -[2023-10-17 01:42:57,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 73957376. Throughput: 0: 1779.6, 1: 1777.7. Samples: 18498818. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:42:57,215][61453] Avg episode reward: [(0, '9.700'), (1, '8.400')] -[2023-10-17 01:42:57,231][62408] Updated weights for policy 1, policy_version 35980 (0.0007) -[2023-10-17 01:42:57,591][62408] Updated weights for policy 1, policy_version 35990 (0.0007) -[2023-10-17 01:42:57,954][62408] Updated weights for policy 1, policy_version 36000 (0.0008) -[2023-10-17 01:42:59,710][62373] Updated weights for policy 0, policy_version 36260 (0.0008) -[2023-10-17 01:43:00,075][62373] Updated weights for policy 0, policy_version 36270 (0.0009) -[2023-10-17 01:43:00,445][62373] Updated weights for policy 0, policy_version 36280 (0.0007) -[2023-10-17 01:43:01,816][62408] Updated weights for policy 1, policy_version 36010 (0.0007) -[2023-10-17 01:43:02,179][62408] Updated weights for policy 1, policy_version 36020 (0.0008) -[2023-10-17 01:43:02,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 74022912. Throughput: 0: 1772.0, 1: 1782.7. Samples: 18520320. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:43:02,214][61453] Avg episode reward: [(0, '9.630'), (1, '8.780')] -[2023-10-17 01:43:02,544][62408] Updated weights for policy 1, policy_version 36030 (0.0007) -[2023-10-17 01:43:04,308][62373] Updated weights for policy 0, policy_version 36290 (0.0008) -[2023-10-17 01:43:04,691][62373] Updated weights for policy 0, policy_version 36300 (0.0010) -[2023-10-17 01:43:05,053][62373] Updated weights for policy 0, policy_version 36310 (0.0010) -[2023-10-17 01:43:05,424][62373] Updated weights for policy 0, policy_version 36320 (0.0011) -[2023-10-17 01:43:06,340][62408] Updated weights for policy 1, policy_version 36040 (0.0009) -[2023-10-17 01:43:06,700][62408] Updated weights for policy 1, policy_version 36050 (0.0009) -[2023-10-17 01:43:07,065][62408] Updated weights for policy 1, policy_version 36060 (0.0011) -[2023-10-17 01:43:07,214][61453] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 74121216. Throughput: 0: 1783.4, 1: 1773.7. Samples: 18530976. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:43:07,214][61453] Avg episode reward: [(0, '9.490'), (1, '8.010')] -[2023-10-17 01:43:09,160][62373] Updated weights for policy 0, policy_version 36330 (0.0011) -[2023-10-17 01:43:09,531][62373] Updated weights for policy 0, policy_version 36340 (0.0007) -[2023-10-17 01:43:09,903][62373] Updated weights for policy 0, policy_version 36350 (0.0009) -[2023-10-17 01:43:10,735][62408] Updated weights for policy 1, policy_version 36070 (0.0009) -[2023-10-17 01:43:11,098][62408] Updated weights for policy 1, policy_version 36080 (0.0008) -[2023-10-17 01:43:11,467][62408] Updated weights for policy 1, policy_version 36090 (0.0009) -[2023-10-17 01:43:12,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 74186752. Throughput: 0: 1772.0, 1: 1792.3. Samples: 18552242. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:43:12,215][61453] Avg episode reward: [(0, '9.720'), (1, '7.370')] -[2023-10-17 01:43:13,566][62373] Updated weights for policy 0, policy_version 36360 (0.0010) -[2023-10-17 01:43:13,954][62373] Updated weights for policy 0, policy_version 36370 (0.0009) -[2023-10-17 01:43:14,311][62373] Updated weights for policy 0, policy_version 36380 (0.0007) -[2023-10-17 01:43:15,242][62408] Updated weights for policy 1, policy_version 36100 (0.0010) -[2023-10-17 01:43:15,599][62408] Updated weights for policy 1, policy_version 36110 (0.0010) -[2023-10-17 01:43:15,978][62408] Updated weights for policy 1, policy_version 36120 (0.0010) -[2023-10-17 01:43:17,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 74252288. Throughput: 0: 1776.0, 1: 1768.7. Samples: 18573574. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:43:17,215][61453] Avg episode reward: [(0, '9.780'), (1, '7.820')] -[2023-10-17 01:43:18,169][62373] Updated weights for policy 0, policy_version 36390 (0.0008) -[2023-10-17 01:43:18,535][62373] Updated weights for policy 0, policy_version 36400 (0.0008) -[2023-10-17 01:43:18,911][62373] Updated weights for policy 0, policy_version 36410 (0.0010) -[2023-10-17 01:43:19,716][62408] Updated weights for policy 1, policy_version 36130 (0.0009) -[2023-10-17 01:43:20,097][62408] Updated weights for policy 1, policy_version 36140 (0.0009) -[2023-10-17 01:43:20,462][62408] Updated weights for policy 1, policy_version 36150 (0.0010) -[2023-10-17 01:43:20,828][62408] Updated weights for policy 1, policy_version 36160 (0.0010) -[2023-10-17 01:43:22,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 74317824. Throughput: 0: 1768.8, 1: 1793.0. Samples: 18584272. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:43:22,215][61453] Avg episode reward: [(0, '9.090'), (1, '7.680')] -[2023-10-17 01:43:22,710][62373] Updated weights for policy 0, policy_version 36420 (0.0008) -[2023-10-17 01:43:23,081][62373] Updated weights for policy 0, policy_version 36430 (0.0008) -[2023-10-17 01:43:23,450][62373] Updated weights for policy 0, policy_version 36440 (0.0010) -[2023-10-17 01:43:24,673][62408] Updated weights for policy 1, policy_version 36170 (0.0009) -[2023-10-17 01:43:25,041][62408] Updated weights for policy 1, policy_version 36180 (0.0008) -[2023-10-17 01:43:25,410][62408] Updated weights for policy 1, policy_version 36190 (0.0011) -[2023-10-17 01:43:27,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 74383360. Throughput: 0: 1770.1, 1: 1767.0. Samples: 18605422. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-17 01:43:27,214][61453] Avg episode reward: [(0, '9.160'), (1, '8.270')] -[2023-10-17 01:43:27,224][62373] Updated weights for policy 0, policy_version 36450 (0.0008) -[2023-10-17 01:43:27,634][62373] Updated weights for policy 0, policy_version 36460 (0.0008) -[2023-10-17 01:43:28,009][62373] Updated weights for policy 0, policy_version 36470 (0.0008) -[2023-10-17 01:43:28,369][62373] Updated weights for policy 0, policy_version 36480 (0.0007) -[2023-10-17 01:43:29,365][62408] Updated weights for policy 1, policy_version 36200 (0.0008) -[2023-10-17 01:43:29,741][62408] Updated weights for policy 1, policy_version 36210 (0.0007) -[2023-10-17 01:43:30,109][62408] Updated weights for policy 1, policy_version 36220 (0.0007) -[2023-10-17 01:43:32,100][62373] Updated weights for policy 0, policy_version 36490 (0.0010) -[2023-10-17 01:43:32,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 74448896. Throughput: 0: 1797.1, 1: 1757.0. Samples: 18626696. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-17 01:43:32,215][61453] Avg episode reward: [(0, '9.440'), (1, '7.650')] -[2023-10-17 01:43:32,226][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000036224_37093376.pth... -[2023-10-17 01:43:32,258][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000034592_35422208.pth -[2023-10-17 01:43:32,467][62373] Updated weights for policy 0, policy_version 36500 (0.0009) -[2023-10-17 01:43:32,830][62373] Updated weights for policy 0, policy_version 36510 (0.0007) -[2023-10-17 01:43:32,902][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000036512_37388288.pth... -[2023-10-17 01:43:32,937][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000034816_35651584.pth -[2023-10-17 01:43:34,038][62408] Updated weights for policy 1, policy_version 36230 (0.0008) -[2023-10-17 01:43:34,403][62408] Updated weights for policy 1, policy_version 36240 (0.0011) -[2023-10-17 01:43:34,779][62408] Updated weights for policy 1, policy_version 36250 (0.0010) -[2023-10-17 01:43:36,607][62373] Updated weights for policy 0, policy_version 36520 (0.0007) -[2023-10-17 01:43:36,986][62373] Updated weights for policy 0, policy_version 36530 (0.0009) -[2023-10-17 01:43:37,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 74514432. Throughput: 0: 1774.0, 1: 1761.4. Samples: 18636842. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-17 01:43:37,214][61453] Avg episode reward: [(0, '9.690'), (1, '7.990')] -[2023-10-17 01:43:37,356][62373] Updated weights for policy 0, policy_version 36540 (0.0009) -[2023-10-17 01:43:38,702][62408] Updated weights for policy 1, policy_version 36260 (0.0008) -[2023-10-17 01:43:39,069][62408] Updated weights for policy 1, policy_version 36270 (0.0008) -[2023-10-17 01:43:39,430][62408] Updated weights for policy 1, policy_version 36280 (0.0009) -[2023-10-17 01:43:41,131][62373] Updated weights for policy 0, policy_version 36550 (0.0008) -[2023-10-17 01:43:41,504][62373] Updated weights for policy 0, policy_version 36560 (0.0007) -[2023-10-17 01:43:41,873][62373] Updated weights for policy 0, policy_version 36570 (0.0008) -[2023-10-17 01:43:42,214][61453] Fps is (10 sec: 16384.4, 60 sec: 14745.6, 300 sec: 14218.0). Total num frames: 74612736. Throughput: 0: 1794.8, 1: 1745.4. Samples: 18658124. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-17 01:43:42,215][61453] Avg episode reward: [(0, '9.780'), (1, '8.860')] -[2023-10-17 01:43:43,309][62408] Updated weights for policy 1, policy_version 36290 (0.0009) -[2023-10-17 01:43:43,681][62408] Updated weights for policy 1, policy_version 36300 (0.0009) -[2023-10-17 01:43:44,052][62408] Updated weights for policy 1, policy_version 36310 (0.0009) -[2023-10-17 01:43:44,420][62408] Updated weights for policy 1, policy_version 36320 (0.0008) -[2023-10-17 01:43:45,704][62373] Updated weights for policy 0, policy_version 36580 (0.0009) -[2023-10-17 01:43:46,076][62373] Updated weights for policy 0, policy_version 36590 (0.0010) -[2023-10-17 01:43:46,446][62373] Updated weights for policy 0, policy_version 36600 (0.0009) -[2023-10-17 01:43:47,214][61453] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 74678272. Throughput: 0: 1766.1, 1: 1756.2. Samples: 18678824. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-17 01:43:47,215][61453] Avg episode reward: [(0, '10.320'), (1, '8.250')] -[2023-10-17 01:43:48,468][62408] Updated weights for policy 1, policy_version 36330 (0.0008) -[2023-10-17 01:43:48,832][62408] Updated weights for policy 1, policy_version 36340 (0.0009) -[2023-10-17 01:43:49,195][62408] Updated weights for policy 1, policy_version 36350 (0.0008) -[2023-10-17 01:43:50,121][62373] Updated weights for policy 0, policy_version 36610 (0.0008) -[2023-10-17 01:43:50,489][62373] Updated weights for policy 0, policy_version 36620 (0.0008) -[2023-10-17 01:43:50,861][62373] Updated weights for policy 0, policy_version 36630 (0.0009) -[2023-10-17 01:43:51,231][62373] Updated weights for policy 0, policy_version 36640 (0.0009) -[2023-10-17 01:43:52,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 74743808. Throughput: 0: 1793.3, 1: 1736.4. Samples: 18689814. Policy #0 lag: (min: 2.0, avg: 2.0, max: 5.0) -[2023-10-17 01:43:52,215][61453] Avg episode reward: [(0, '10.420'), (1, '8.320')] -[2023-10-17 01:43:52,215][62094] Saving new best policy, reward=10.420! -[2023-10-17 01:43:52,924][62408] Updated weights for policy 1, policy_version 36360 (0.0008) -[2023-10-17 01:43:53,280][62408] Updated weights for policy 1, policy_version 36370 (0.0008) -[2023-10-17 01:43:53,656][62408] Updated weights for policy 1, policy_version 36380 (0.0008) -[2023-10-17 01:43:55,035][62373] Updated weights for policy 0, policy_version 36650 (0.0007) -[2023-10-17 01:43:55,402][62373] Updated weights for policy 0, policy_version 36660 (0.0008) -[2023-10-17 01:43:55,767][62373] Updated weights for policy 0, policy_version 36670 (0.0007) -[2023-10-17 01:43:57,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 74809344. Throughput: 0: 1772.9, 1: 1747.7. Samples: 18710672. Policy #0 lag: (min: 2.0, avg: 2.0, max: 5.0) -[2023-10-17 01:43:57,214][61453] Avg episode reward: [(0, '10.560'), (1, '7.820')] -[2023-10-17 01:43:57,215][62094] Saving new best policy, reward=10.560! -[2023-10-17 01:43:57,504][62408] Updated weights for policy 1, policy_version 36390 (0.0009) -[2023-10-17 01:43:57,877][62408] Updated weights for policy 1, policy_version 36400 (0.0007) -[2023-10-17 01:43:58,242][62408] Updated weights for policy 1, policy_version 36410 (0.0007) -[2023-10-17 01:43:59,675][62373] Updated weights for policy 0, policy_version 36680 (0.0010) -[2023-10-17 01:44:00,051][62373] Updated weights for policy 0, policy_version 36690 (0.0010) -[2023-10-17 01:44:00,423][62373] Updated weights for policy 0, policy_version 36700 (0.0010) -[2023-10-17 01:44:02,112][62408] Updated weights for policy 1, policy_version 36420 (0.0008) -[2023-10-17 01:44:02,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 74874880. Throughput: 0: 1767.7, 1: 1763.4. Samples: 18732476. Policy #0 lag: (min: 2.0, avg: 2.0, max: 5.0) -[2023-10-17 01:44:02,215][61453] Avg episode reward: [(0, '10.460'), (1, '8.280')] -[2023-10-17 01:44:02,490][62408] Updated weights for policy 1, policy_version 36430 (0.0007) -[2023-10-17 01:44:02,861][62408] Updated weights for policy 1, policy_version 36440 (0.0008) -[2023-10-17 01:44:04,113][62373] Updated weights for policy 0, policy_version 36710 (0.0009) -[2023-10-17 01:44:04,484][62373] Updated weights for policy 0, policy_version 36720 (0.0007) -[2023-10-17 01:44:04,861][62373] Updated weights for policy 0, policy_version 36730 (0.0007) -[2023-10-17 01:44:06,839][62408] Updated weights for policy 1, policy_version 36450 (0.0009) -[2023-10-17 01:44:07,203][62408] Updated weights for policy 1, policy_version 36460 (0.0007) -[2023-10-17 01:44:07,214][61453] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 74940416. Throughput: 0: 1778.3, 1: 1735.3. Samples: 18742386. Policy #0 lag: (min: 2.0, avg: 2.0, max: 5.0) -[2023-10-17 01:44:07,215][61453] Avg episode reward: [(0, '10.250'), (1, '8.080')] -[2023-10-17 01:44:07,569][62408] Updated weights for policy 1, policy_version 36470 (0.0007) -[2023-10-17 01:44:07,937][62408] Updated weights for policy 1, policy_version 36480 (0.0009) -[2023-10-17 01:44:08,754][62373] Updated weights for policy 0, policy_version 36740 (0.0010) -[2023-10-17 01:44:09,129][62373] Updated weights for policy 0, policy_version 36750 (0.0008) -[2023-10-17 01:44:09,503][62373] Updated weights for policy 0, policy_version 36760 (0.0009) -[2023-10-17 01:44:11,763][62408] Updated weights for policy 1, policy_version 36490 (0.0008) -[2023-10-17 01:44:12,130][62408] Updated weights for policy 1, policy_version 36500 (0.0008) -[2023-10-17 01:44:12,214][61453] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 75005952. Throughput: 0: 1762.2, 1: 1757.3. Samples: 18763798. Policy #0 lag: (min: 2.0, avg: 2.0, max: 5.0) -[2023-10-17 01:44:12,215][61453] Avg episode reward: [(0, '9.560'), (1, '7.350')] -[2023-10-17 01:44:12,506][62408] Updated weights for policy 1, policy_version 36510 (0.0008) -[2023-10-17 01:44:13,346][62373] Updated weights for policy 0, policy_version 36770 (0.0008) -[2023-10-17 01:44:13,734][62373] Updated weights for policy 0, policy_version 36780 (0.0008) -[2023-10-17 01:44:14,101][62373] Updated weights for policy 0, policy_version 36790 (0.0007) -[2023-10-17 01:44:14,472][62373] Updated weights for policy 0, policy_version 36800 (0.0008) -[2023-10-17 01:44:16,254][62408] Updated weights for policy 1, policy_version 36520 (0.0010) -[2023-10-17 01:44:16,635][62408] Updated weights for policy 1, policy_version 36530 (0.0010) -[2023-10-17 01:44:17,008][62408] Updated weights for policy 1, policy_version 36540 (0.0011) -[2023-10-17 01:44:17,214][61453] Fps is (10 sec: 16383.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 75104256. Throughput: 0: 1766.8, 1: 1744.6. Samples: 18784708. Policy #0 lag: (min: 2.0, avg: 2.0, max: 5.0) -[2023-10-17 01:44:17,215][61453] Avg episode reward: [(0, '9.760'), (1, '7.590')] -[2023-10-17 01:44:18,311][62373] Updated weights for policy 0, policy_version 36810 (0.0008) -[2023-10-17 01:44:18,685][62373] Updated weights for policy 0, policy_version 36820 (0.0008) -[2023-10-17 01:44:19,052][62373] Updated weights for policy 0, policy_version 36830 (0.0009) -[2023-10-17 01:44:20,812][62408] Updated weights for policy 1, policy_version 36550 (0.0010) -[2023-10-17 01:44:21,179][62408] Updated weights for policy 1, policy_version 36560 (0.0008) -[2023-10-17 01:44:21,536][62408] Updated weights for policy 1, policy_version 36570 (0.0010) -[2023-10-17 01:44:22,214][61453] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 75169792. Throughput: 0: 1758.0, 1: 1764.1. Samples: 18795336. Policy #0 lag: (min: 31.0, avg: 31.2, max: 41.0) -[2023-10-17 01:44:22,214][61453] Avg episode reward: [(0, '9.610'), (1, '8.130')] -[2023-10-17 01:44:22,835][62373] Updated weights for policy 0, policy_version 36840 (0.0007) -[2023-10-17 01:44:23,210][62373] Updated weights for policy 0, policy_version 36850 (0.0008) -[2023-10-17 01:44:23,583][62373] Updated weights for policy 0, policy_version 36860 (0.0009) -[2023-10-17 01:44:25,310][62408] Updated weights for policy 1, policy_version 36580 (0.0009) -[2023-10-17 01:44:25,675][62408] Updated weights for policy 1, policy_version 36590 (0.0008) -[2023-10-17 01:44:26,035][62408] Updated weights for policy 1, policy_version 36600 (0.0010) -[2023-10-17 01:44:27,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 75235328. Throughput: 0: 1762.8, 1: 1762.3. Samples: 18816750. Policy #0 lag: (min: 31.0, avg: 31.2, max: 41.0) -[2023-10-17 01:44:27,215][61453] Avg episode reward: [(0, '9.680'), (1, '8.340')] -[2023-10-17 01:44:27,501][62373] Updated weights for policy 0, policy_version 36870 (0.0008) -[2023-10-17 01:44:27,876][62373] Updated weights for policy 0, policy_version 36880 (0.0010) -[2023-10-17 01:44:28,248][62373] Updated weights for policy 0, policy_version 36890 (0.0010) -[2023-10-17 01:44:29,970][62408] Updated weights for policy 1, policy_version 36610 (0.0009) -[2023-10-17 01:44:30,332][62408] Updated weights for policy 1, policy_version 36620 (0.0008) -[2023-10-17 01:44:30,696][62408] Updated weights for policy 1, policy_version 36630 (0.0009) -[2023-10-17 01:44:31,071][62408] Updated weights for policy 1, policy_version 36640 (0.0010) -[2023-10-17 01:44:31,888][62373] Updated weights for policy 0, policy_version 36900 (0.0010) -[2023-10-17 01:44:32,214][61453] Fps is (10 sec: 13106.6, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 75300864. Throughput: 0: 1791.7, 1: 1742.6. Samples: 18837868. Policy #0 lag: (min: 31.0, avg: 31.2, max: 41.0) -[2023-10-17 01:44:32,215][61453] Avg episode reward: [(0, '9.300'), (1, '7.950')] -[2023-10-17 01:44:32,256][62373] Updated weights for policy 0, policy_version 36910 (0.0008) -[2023-10-17 01:44:32,625][62373] Updated weights for policy 0, policy_version 36920 (0.0010) -[2023-10-17 01:44:34,964][62408] Updated weights for policy 1, policy_version 36650 (0.0008) -[2023-10-17 01:44:35,338][62408] Updated weights for policy 1, policy_version 36660 (0.0007) -[2023-10-17 01:44:35,704][62408] Updated weights for policy 1, policy_version 36670 (0.0009) -[2023-10-17 01:44:36,479][62373] Updated weights for policy 0, policy_version 36930 (0.0009) -[2023-10-17 01:44:36,852][62373] Updated weights for policy 0, policy_version 36940 (0.0010) -[2023-10-17 01:44:37,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 75366400. Throughput: 0: 1760.6, 1: 1773.7. Samples: 18848858. Policy #0 lag: (min: 31.0, avg: 31.2, max: 41.0) -[2023-10-17 01:44:37,214][61453] Avg episode reward: [(0, '9.130'), (1, '8.470')] -[2023-10-17 01:44:37,224][62373] Updated weights for policy 0, policy_version 36950 (0.0007) -[2023-10-17 01:44:37,594][62373] Updated weights for policy 0, policy_version 36960 (0.0007) -[2023-10-17 01:44:39,705][62408] Updated weights for policy 1, policy_version 36680 (0.0007) -[2023-10-17 01:44:40,074][62408] Updated weights for policy 1, policy_version 36690 (0.0010) -[2023-10-17 01:44:40,444][62408] Updated weights for policy 1, policy_version 36700 (0.0010) -[2023-10-17 01:44:41,335][62373] Updated weights for policy 0, policy_version 36970 (0.0009) -[2023-10-17 01:44:41,702][62373] Updated weights for policy 0, policy_version 36980 (0.0009) -[2023-10-17 01:44:42,065][62373] Updated weights for policy 0, policy_version 36990 (0.0008) -[2023-10-17 01:44:42,214][61453] Fps is (10 sec: 16384.5, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 75464704. Throughput: 0: 1796.0, 1: 1742.9. Samples: 18869924. Policy #0 lag: (min: 31.0, avg: 31.2, max: 41.0) -[2023-10-17 01:44:42,215][61453] Avg episode reward: [(0, '9.420'), (1, '8.750')] -[2023-10-17 01:44:44,180][62408] Updated weights for policy 1, policy_version 36710 (0.0008) -[2023-10-17 01:44:44,539][62408] Updated weights for policy 1, policy_version 36720 (0.0007) -[2023-10-17 01:44:44,905][62408] Updated weights for policy 1, policy_version 36730 (0.0008) -[2023-10-17 01:44:45,931][62373] Updated weights for policy 0, policy_version 37000 (0.0008) -[2023-10-17 01:44:46,300][62373] Updated weights for policy 0, policy_version 37010 (0.0008) -[2023-10-17 01:44:46,668][62373] Updated weights for policy 0, policy_version 37020 (0.0009) -[2023-10-17 01:44:47,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 75530240. Throughput: 0: 1762.2, 1: 1753.6. Samples: 18890688. Policy #0 lag: (min: 2.0, avg: 10.0, max: 34.0) -[2023-10-17 01:44:47,215][61453] Avg episode reward: [(0, '9.260'), (1, '8.100')] -[2023-10-17 01:44:48,723][62408] Updated weights for policy 1, policy_version 36740 (0.0010) -[2023-10-17 01:44:49,090][62408] Updated weights for policy 1, policy_version 36750 (0.0010) -[2023-10-17 01:44:49,457][62408] Updated weights for policy 1, policy_version 36760 (0.0009) -[2023-10-17 01:44:50,602][62373] Updated weights for policy 0, policy_version 37030 (0.0009) -[2023-10-17 01:44:50,984][62373] Updated weights for policy 0, policy_version 37040 (0.0009) -[2023-10-17 01:44:51,350][62373] Updated weights for policy 0, policy_version 37050 (0.0009) -[2023-10-17 01:44:52,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 75595776. Throughput: 0: 1783.3, 1: 1754.8. Samples: 18901604. Policy #0 lag: (min: 2.0, avg: 10.0, max: 34.0) -[2023-10-17 01:44:52,214][61453] Avg episode reward: [(0, '9.140'), (1, '7.930')] -[2023-10-17 01:44:53,395][62408] Updated weights for policy 1, policy_version 36770 (0.0009) -[2023-10-17 01:44:53,761][62408] Updated weights for policy 1, policy_version 36780 (0.0007) -[2023-10-17 01:44:54,124][62408] Updated weights for policy 1, policy_version 36790 (0.0007) -[2023-10-17 01:44:54,495][62408] Updated weights for policy 1, policy_version 36800 (0.0009) -[2023-10-17 01:44:55,070][62373] Updated weights for policy 0, policy_version 37060 (0.0008) -[2023-10-17 01:44:55,438][62373] Updated weights for policy 0, policy_version 37070 (0.0007) -[2023-10-17 01:44:55,815][62373] Updated weights for policy 0, policy_version 37080 (0.0007) -[2023-10-17 01:44:57,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 75661312. Throughput: 0: 1772.1, 1: 1758.8. Samples: 18922684. Policy #0 lag: (min: 2.0, avg: 10.0, max: 34.0) -[2023-10-17 01:44:57,214][61453] Avg episode reward: [(0, '8.330'), (1, '8.210')] -[2023-10-17 01:44:58,385][62408] Updated weights for policy 1, policy_version 36810 (0.0009) -[2023-10-17 01:44:58,754][62408] Updated weights for policy 1, policy_version 36820 (0.0007) -[2023-10-17 01:44:59,111][62408] Updated weights for policy 1, policy_version 36830 (0.0009) -[2023-10-17 01:44:59,505][62373] Updated weights for policy 0, policy_version 37090 (0.0009) -[2023-10-17 01:44:59,913][62373] Updated weights for policy 0, policy_version 37100 (0.0010) -[2023-10-17 01:45:00,286][62373] Updated weights for policy 0, policy_version 37110 (0.0008) -[2023-10-17 01:45:00,660][62373] Updated weights for policy 0, policy_version 37120 (0.0008) -[2023-10-17 01:45:02,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 75726848. Throughput: 0: 1765.7, 1: 1783.3. Samples: 18944414. Policy #0 lag: (min: 2.0, avg: 10.0, max: 34.0) -[2023-10-17 01:45:02,215][61453] Avg episode reward: [(0, '9.390'), (1, '8.500')] -[2023-10-17 01:45:02,901][62408] Updated weights for policy 1, policy_version 36840 (0.0009) -[2023-10-17 01:45:03,279][62408] Updated weights for policy 1, policy_version 36850 (0.0008) -[2023-10-17 01:45:03,651][62408] Updated weights for policy 1, policy_version 36860 (0.0011) -[2023-10-17 01:45:04,398][62373] Updated weights for policy 0, policy_version 37130 (0.0011) -[2023-10-17 01:45:04,764][62373] Updated weights for policy 0, policy_version 37140 (0.0011) -[2023-10-17 01:45:05,138][62373] Updated weights for policy 0, policy_version 37150 (0.0011) -[2023-10-17 01:45:07,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 75792384. Throughput: 0: 1777.7, 1: 1759.0. Samples: 18954490. Policy #0 lag: (min: 2.0, avg: 10.0, max: 34.0) -[2023-10-17 01:45:07,215][61453] Avg episode reward: [(0, '9.250'), (1, '8.660')] -[2023-10-17 01:45:07,448][62408] Updated weights for policy 1, policy_version 36870 (0.0011) -[2023-10-17 01:45:07,821][62408] Updated weights for policy 1, policy_version 36880 (0.0010) -[2023-10-17 01:45:08,198][62408] Updated weights for policy 1, policy_version 36890 (0.0008) -[2023-10-17 01:45:08,950][62373] Updated weights for policy 0, policy_version 37160 (0.0010) -[2023-10-17 01:45:09,336][62373] Updated weights for policy 0, policy_version 37170 (0.0010) -[2023-10-17 01:45:09,699][62373] Updated weights for policy 0, policy_version 37180 (0.0008) -[2023-10-17 01:45:11,821][62408] Updated weights for policy 1, policy_version 36900 (0.0008) -[2023-10-17 01:45:12,190][62408] Updated weights for policy 1, policy_version 36910 (0.0010) -[2023-10-17 01:45:12,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 75857920. Throughput: 0: 1772.7, 1: 1770.4. Samples: 18976188. Policy #0 lag: (min: 2.0, avg: 10.0, max: 34.0) -[2023-10-17 01:45:12,215][61453] Avg episode reward: [(0, '9.580'), (1, '8.250')] -[2023-10-17 01:45:12,565][62408] Updated weights for policy 1, policy_version 36920 (0.0010) -[2023-10-17 01:45:13,369][62373] Updated weights for policy 0, policy_version 37190 (0.0007) -[2023-10-17 01:45:13,741][62373] Updated weights for policy 0, policy_version 37200 (0.0007) -[2023-10-17 01:45:14,109][62373] Updated weights for policy 0, policy_version 37210 (0.0009) -[2023-10-17 01:45:16,344][62408] Updated weights for policy 1, policy_version 36930 (0.0009) -[2023-10-17 01:45:16,717][62408] Updated weights for policy 1, policy_version 36940 (0.0008) -[2023-10-17 01:45:17,077][62408] Updated weights for policy 1, policy_version 36950 (0.0008) -[2023-10-17 01:45:17,214][61453] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 75923456. Throughput: 0: 1783.5, 1: 1774.8. Samples: 18997992. Policy #0 lag: (min: 20.0, avg: 20.1, max: 28.0) -[2023-10-17 01:45:17,215][61453] Avg episode reward: [(0, '9.660'), (1, '8.670')] -[2023-10-17 01:45:17,449][62408] Updated weights for policy 1, policy_version 36960 (0.0009) -[2023-10-17 01:45:17,736][62373] Updated weights for policy 0, policy_version 37220 (0.0009) -[2023-10-17 01:45:18,105][62373] Updated weights for policy 0, policy_version 37230 (0.0008) -[2023-10-17 01:45:18,475][62373] Updated weights for policy 0, policy_version 37240 (0.0008) -[2023-10-17 01:45:21,288][62408] Updated weights for policy 1, policy_version 36970 (0.0011) -[2023-10-17 01:45:21,648][62408] Updated weights for policy 1, policy_version 36980 (0.0011) -[2023-10-17 01:45:22,017][62408] Updated weights for policy 1, policy_version 36990 (0.0010) -[2023-10-17 01:45:22,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 76021760. Throughput: 0: 1775.9, 1: 1768.0. Samples: 19008330. Policy #0 lag: (min: 20.0, avg: 20.1, max: 28.0) -[2023-10-17 01:45:22,214][61453] Avg episode reward: [(0, '10.070'), (1, '9.120')] -[2023-10-17 01:45:22,457][62373] Updated weights for policy 0, policy_version 37250 (0.0009) -[2023-10-17 01:45:22,824][62373] Updated weights for policy 0, policy_version 37260 (0.0010) -[2023-10-17 01:45:23,192][62373] Updated weights for policy 0, policy_version 37270 (0.0010) -[2023-10-17 01:45:23,561][62373] Updated weights for policy 0, policy_version 37280 (0.0011) -[2023-10-17 01:45:25,992][62408] Updated weights for policy 1, policy_version 37000 (0.0010) -[2023-10-17 01:45:26,374][62408] Updated weights for policy 1, policy_version 37010 (0.0011) -[2023-10-17 01:45:26,744][62408] Updated weights for policy 1, policy_version 37020 (0.0009) -[2023-10-17 01:45:27,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 76087296. Throughput: 0: 1768.4, 1: 1785.6. Samples: 19029854. Policy #0 lag: (min: 20.0, avg: 20.1, max: 28.0) -[2023-10-17 01:45:27,215][61453] Avg episode reward: [(0, '9.660'), (1, '8.900')] -[2023-10-17 01:45:27,445][62373] Updated weights for policy 0, policy_version 37290 (0.0007) -[2023-10-17 01:45:27,816][62373] Updated weights for policy 0, policy_version 37300 (0.0010) -[2023-10-17 01:45:28,181][62373] Updated weights for policy 0, policy_version 37310 (0.0008) -[2023-10-17 01:45:30,486][62408] Updated weights for policy 1, policy_version 37030 (0.0010) -[2023-10-17 01:45:30,849][62408] Updated weights for policy 1, policy_version 37040 (0.0008) -[2023-10-17 01:45:31,211][62408] Updated weights for policy 1, policy_version 37050 (0.0007) -[2023-10-17 01:45:32,025][62373] Updated weights for policy 0, policy_version 37320 (0.0009) -[2023-10-17 01:45:32,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 76152832. Throughput: 0: 1793.1, 1: 1757.0. Samples: 19050442. Policy #0 lag: (min: 20.0, avg: 20.1, max: 28.0) -[2023-10-17 01:45:32,215][61453] Avg episode reward: [(0, '9.780'), (1, '8.190')] -[2023-10-17 01:45:32,223][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000037056_37945344.pth... -[2023-10-17 01:45:32,263][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000035392_36241408.pth -[2023-10-17 01:45:32,403][62373] Updated weights for policy 0, policy_version 37330 (0.0007) -[2023-10-17 01:45:32,782][62373] Updated weights for policy 0, policy_version 37340 (0.0008) -[2023-10-17 01:45:32,925][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000037344_38240256.pth... -[2023-10-17 01:45:32,954][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000035648_36503552.pth -[2023-10-17 01:45:35,137][62408] Updated weights for policy 1, policy_version 37060 (0.0007) -[2023-10-17 01:45:35,493][62408] Updated weights for policy 1, policy_version 37070 (0.0008) -[2023-10-17 01:45:35,864][62408] Updated weights for policy 1, policy_version 37080 (0.0008) -[2023-10-17 01:45:36,522][62373] Updated weights for policy 0, policy_version 37350 (0.0008) -[2023-10-17 01:45:36,904][62373] Updated weights for policy 0, policy_version 37360 (0.0009) -[2023-10-17 01:45:37,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 76218368. Throughput: 0: 1770.2, 1: 1786.0. Samples: 19061634. Policy #0 lag: (min: 20.0, avg: 20.1, max: 28.0) -[2023-10-17 01:45:37,215][61453] Avg episode reward: [(0, '9.810'), (1, '8.450')] -[2023-10-17 01:45:37,271][62373] Updated weights for policy 0, policy_version 37370 (0.0010) -[2023-10-17 01:45:39,618][62408] Updated weights for policy 1, policy_version 37090 (0.0008) -[2023-10-17 01:45:39,992][62408] Updated weights for policy 1, policy_version 37100 (0.0009) -[2023-10-17 01:45:40,355][62408] Updated weights for policy 1, policy_version 37110 (0.0007) -[2023-10-17 01:45:40,716][62408] Updated weights for policy 1, policy_version 37120 (0.0010) -[2023-10-17 01:45:41,096][62373] Updated weights for policy 0, policy_version 37380 (0.0009) -[2023-10-17 01:45:41,466][62373] Updated weights for policy 0, policy_version 37390 (0.0008) -[2023-10-17 01:45:41,830][62373] Updated weights for policy 0, policy_version 37400 (0.0009) -[2023-10-17 01:45:42,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 76316672. Throughput: 0: 1792.9, 1: 1752.3. Samples: 19082216. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-17 01:45:42,215][61453] Avg episode reward: [(0, '9.530'), (1, '8.250')] -[2023-10-17 01:45:44,522][62408] Updated weights for policy 1, policy_version 37130 (0.0007) -[2023-10-17 01:45:44,891][62408] Updated weights for policy 1, policy_version 37140 (0.0008) -[2023-10-17 01:45:45,259][62408] Updated weights for policy 1, policy_version 37150 (0.0007) -[2023-10-17 01:45:45,672][62373] Updated weights for policy 0, policy_version 37410 (0.0010) -[2023-10-17 01:45:46,081][62373] Updated weights for policy 0, policy_version 37420 (0.0009) -[2023-10-17 01:45:46,458][62373] Updated weights for policy 0, policy_version 37430 (0.0008) -[2023-10-17 01:45:46,827][62373] Updated weights for policy 0, policy_version 37440 (0.0009) -[2023-10-17 01:45:47,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 76382208. Throughput: 0: 1765.4, 1: 1756.3. Samples: 19102892. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-17 01:45:47,215][61453] Avg episode reward: [(0, '9.750'), (1, '8.150')] -[2023-10-17 01:45:49,302][62408] Updated weights for policy 1, policy_version 37160 (0.0008) -[2023-10-17 01:45:49,683][62408] Updated weights for policy 1, policy_version 37170 (0.0008) -[2023-10-17 01:45:50,053][62408] Updated weights for policy 1, policy_version 37180 (0.0008) -[2023-10-17 01:45:50,632][62373] Updated weights for policy 0, policy_version 37450 (0.0008) -[2023-10-17 01:45:51,009][62373] Updated weights for policy 0, policy_version 37460 (0.0009) -[2023-10-17 01:45:51,387][62373] Updated weights for policy 0, policy_version 37470 (0.0009) -[2023-10-17 01:45:52,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 76447744. Throughput: 0: 1786.3, 1: 1761.9. Samples: 19114156. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-17 01:45:52,214][61453] Avg episode reward: [(0, '9.480'), (1, '8.280')] -[2023-10-17 01:45:53,904][62408] Updated weights for policy 1, policy_version 37190 (0.0009) -[2023-10-17 01:45:54,271][62408] Updated weights for policy 1, policy_version 37200 (0.0008) -[2023-10-17 01:45:54,643][62408] Updated weights for policy 1, policy_version 37210 (0.0007) -[2023-10-17 01:45:55,245][62373] Updated weights for policy 0, policy_version 37480 (0.0009) -[2023-10-17 01:45:55,615][62373] Updated weights for policy 0, policy_version 37490 (0.0007) -[2023-10-17 01:45:55,987][62373] Updated weights for policy 0, policy_version 37500 (0.0007) -[2023-10-17 01:45:57,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 76513280. Throughput: 0: 1765.6, 1: 1750.2. Samples: 19134396. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-17 01:45:57,215][61453] Avg episode reward: [(0, '9.340'), (1, '8.970')] -[2023-10-17 01:45:58,578][62408] Updated weights for policy 1, policy_version 37220 (0.0008) -[2023-10-17 01:45:58,952][62408] Updated weights for policy 1, policy_version 37230 (0.0011) -[2023-10-17 01:45:59,314][62408] Updated weights for policy 1, policy_version 37240 (0.0010) -[2023-10-17 01:45:59,600][62373] Updated weights for policy 0, policy_version 37510 (0.0007) -[2023-10-17 01:45:59,965][62373] Updated weights for policy 0, policy_version 37520 (0.0010) -[2023-10-17 01:46:00,338][62373] Updated weights for policy 0, policy_version 37530 (0.0007) -[2023-10-17 01:46:02,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 76578816. Throughput: 0: 1758.3, 1: 1762.1. Samples: 19156408. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-17 01:46:02,215][61453] Avg episode reward: [(0, '9.470'), (1, '8.550')] -[2023-10-17 01:46:03,050][62408] Updated weights for policy 1, policy_version 37250 (0.0008) -[2023-10-17 01:46:03,419][62408] Updated weights for policy 1, policy_version 37260 (0.0007) -[2023-10-17 01:46:03,788][62408] Updated weights for policy 1, policy_version 37270 (0.0008) -[2023-10-17 01:46:04,029][62373] Updated weights for policy 0, policy_version 37540 (0.0007) -[2023-10-17 01:46:04,149][62408] Updated weights for policy 1, policy_version 37280 (0.0008) -[2023-10-17 01:46:04,398][62373] Updated weights for policy 0, policy_version 37550 (0.0009) -[2023-10-17 01:46:04,767][62373] Updated weights for policy 0, policy_version 37560 (0.0009) -[2023-10-17 01:46:07,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 76644352. Throughput: 0: 1767.0, 1: 1743.8. Samples: 19166314. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-17 01:46:07,215][61453] Avg episode reward: [(0, '9.460'), (1, '8.810')] -[2023-10-17 01:46:08,129][62408] Updated weights for policy 1, policy_version 37290 (0.0007) -[2023-10-17 01:46:08,497][62408] Updated weights for policy 1, policy_version 37300 (0.0009) -[2023-10-17 01:46:08,588][62373] Updated weights for policy 0, policy_version 37570 (0.0007) -[2023-10-17 01:46:08,859][62408] Updated weights for policy 1, policy_version 37310 (0.0007) -[2023-10-17 01:46:08,960][62373] Updated weights for policy 0, policy_version 37580 (0.0008) -[2023-10-17 01:46:09,342][62373] Updated weights for policy 0, policy_version 37590 (0.0009) -[2023-10-17 01:46:09,708][62373] Updated weights for policy 0, policy_version 37600 (0.0009) -[2023-10-17 01:46:12,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 76709888. Throughput: 0: 1764.5, 1: 1752.0. Samples: 19188098. Policy #0 lag: (min: 31.0, avg: 35.1, max: 63.0) -[2023-10-17 01:46:12,215][61453] Avg episode reward: [(0, '9.080'), (1, '8.710')] -[2023-10-17 01:46:12,653][62408] Updated weights for policy 1, policy_version 37320 (0.0008) -[2023-10-17 01:46:13,017][62408] Updated weights for policy 1, policy_version 37330 (0.0008) -[2023-10-17 01:46:13,385][62408] Updated weights for policy 1, policy_version 37340 (0.0008) -[2023-10-17 01:46:13,577][62373] Updated weights for policy 0, policy_version 37610 (0.0008) -[2023-10-17 01:46:13,936][62373] Updated weights for policy 0, policy_version 37620 (0.0007) -[2023-10-17 01:46:14,313][62373] Updated weights for policy 0, policy_version 37630 (0.0010) -[2023-10-17 01:46:17,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 76775424. Throughput: 0: 1779.1, 1: 1773.7. Samples: 19210316. Policy #0 lag: (min: 31.0, avg: 35.1, max: 63.0) -[2023-10-17 01:46:17,214][61453] Avg episode reward: [(0, '8.110'), (1, '8.810')] -[2023-10-17 01:46:17,237][62408] Updated weights for policy 1, policy_version 37350 (0.0008) -[2023-10-17 01:46:17,596][62408] Updated weights for policy 1, policy_version 37360 (0.0009) -[2023-10-17 01:46:17,972][62408] Updated weights for policy 1, policy_version 37370 (0.0008) -[2023-10-17 01:46:18,143][62373] Updated weights for policy 0, policy_version 37640 (0.0009) -[2023-10-17 01:46:18,513][62373] Updated weights for policy 0, policy_version 37650 (0.0008) -[2023-10-17 01:46:18,886][62373] Updated weights for policy 0, policy_version 37660 (0.0009) -[2023-10-17 01:46:21,816][62408] Updated weights for policy 1, policy_version 37380 (0.0008) -[2023-10-17 01:46:22,190][62408] Updated weights for policy 1, policy_version 37390 (0.0007) -[2023-10-17 01:46:22,214][61453] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 76840960. Throughput: 0: 1773.3, 1: 1745.1. Samples: 19219960. Policy #0 lag: (min: 31.0, avg: 35.1, max: 63.0) -[2023-10-17 01:46:22,215][61453] Avg episode reward: [(0, '8.090'), (1, '8.310')] -[2023-10-17 01:46:22,553][62408] Updated weights for policy 1, policy_version 37400 (0.0007) -[2023-10-17 01:46:22,601][62373] Updated weights for policy 0, policy_version 37670 (0.0008) -[2023-10-17 01:46:22,962][62373] Updated weights for policy 0, policy_version 37680 (0.0007) -[2023-10-17 01:46:23,326][62373] Updated weights for policy 0, policy_version 37690 (0.0009) -[2023-10-17 01:46:26,332][62408] Updated weights for policy 1, policy_version 37410 (0.0007) -[2023-10-17 01:46:26,700][62408] Updated weights for policy 1, policy_version 37420 (0.0007) -[2023-10-17 01:46:27,067][62408] Updated weights for policy 1, policy_version 37430 (0.0009) -[2023-10-17 01:46:27,089][62373] Updated weights for policy 0, policy_version 37700 (0.0008) -[2023-10-17 01:46:27,214][61453] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 76906496. Throughput: 0: 1773.5, 1: 1779.4. Samples: 19242096. Policy #0 lag: (min: 31.0, avg: 35.1, max: 63.0) -[2023-10-17 01:46:27,214][61453] Avg episode reward: [(0, '7.610'), (1, '7.990')] -[2023-10-17 01:46:27,430][62408] Updated weights for policy 1, policy_version 37440 (0.0008) -[2023-10-17 01:46:27,455][62373] Updated weights for policy 0, policy_version 37710 (0.0007) -[2023-10-17 01:46:27,836][62373] Updated weights for policy 0, policy_version 37720 (0.0009) -[2023-10-17 01:46:31,212][62408] Updated weights for policy 1, policy_version 37450 (0.0007) -[2023-10-17 01:46:31,578][62408] Updated weights for policy 1, policy_version 37460 (0.0009) -[2023-10-17 01:46:31,612][62373] Updated weights for policy 0, policy_version 37730 (0.0008) -[2023-10-17 01:46:31,943][62408] Updated weights for policy 1, policy_version 37470 (0.0008) -[2023-10-17 01:46:32,022][62373] Updated weights for policy 0, policy_version 37740 (0.0007) -[2023-10-17 01:46:32,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 77004800. Throughput: 0: 1799.6, 1: 1748.7. Samples: 19262564. Policy #0 lag: (min: 31.0, avg: 35.1, max: 63.0) -[2023-10-17 01:46:32,215][61453] Avg episode reward: [(0, '8.370'), (1, '8.510')] -[2023-10-17 01:46:32,381][62373] Updated weights for policy 0, policy_version 37750 (0.0008) -[2023-10-17 01:46:32,753][62373] Updated weights for policy 0, policy_version 37760 (0.0009) -[2023-10-17 01:46:35,857][62408] Updated weights for policy 1, policy_version 37480 (0.0011) -[2023-10-17 01:46:36,232][62408] Updated weights for policy 1, policy_version 37490 (0.0008) -[2023-10-17 01:46:36,552][62373] Updated weights for policy 0, policy_version 37770 (0.0009) -[2023-10-17 01:46:36,595][62408] Updated weights for policy 1, policy_version 37500 (0.0007) -[2023-10-17 01:46:36,916][62373] Updated weights for policy 0, policy_version 37780 (0.0007) -[2023-10-17 01:46:37,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 77070336. Throughput: 0: 1778.3, 1: 1770.9. Samples: 19273872. Policy #0 lag: (min: 31.0, avg: 35.1, max: 63.0) -[2023-10-17 01:46:37,215][61453] Avg episode reward: [(0, '8.230'), (1, '8.510')] -[2023-10-17 01:46:37,287][62373] Updated weights for policy 0, policy_version 37790 (0.0009) -[2023-10-17 01:46:40,467][62408] Updated weights for policy 1, policy_version 37510 (0.0008) -[2023-10-17 01:46:40,840][62408] Updated weights for policy 1, policy_version 37520 (0.0009) -[2023-10-17 01:46:41,137][62373] Updated weights for policy 0, policy_version 37800 (0.0009) -[2023-10-17 01:46:41,208][62408] Updated weights for policy 1, policy_version 37530 (0.0009) -[2023-10-17 01:46:41,515][62373] Updated weights for policy 0, policy_version 37810 (0.0009) -[2023-10-17 01:46:41,886][62373] Updated weights for policy 0, policy_version 37820 (0.0008) -[2023-10-17 01:46:42,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 77168640. Throughput: 0: 1800.3, 1: 1764.0. Samples: 19294792. Policy #0 lag: (min: 26.0, avg: 34.0, max: 58.0) -[2023-10-17 01:46:42,215][61453] Avg episode reward: [(0, '8.110'), (1, '8.610')] -[2023-10-17 01:46:45,014][62408] Updated weights for policy 1, policy_version 37540 (0.0007) -[2023-10-17 01:46:45,391][62408] Updated weights for policy 1, policy_version 37550 (0.0008) -[2023-10-17 01:46:45,632][62373] Updated weights for policy 0, policy_version 37830 (0.0007) -[2023-10-17 01:46:45,757][62408] Updated weights for policy 1, policy_version 37560 (0.0007) -[2023-10-17 01:46:46,007][62373] Updated weights for policy 0, policy_version 37840 (0.0008) -[2023-10-17 01:46:46,382][62373] Updated weights for policy 0, policy_version 37850 (0.0009) -[2023-10-17 01:46:47,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 77234176. Throughput: 0: 1771.4, 1: 1753.6. Samples: 19315032. Policy #0 lag: (min: 26.0, avg: 34.0, max: 58.0) -[2023-10-17 01:46:47,215][61453] Avg episode reward: [(0, '8.450'), (1, '8.500')] -[2023-10-17 01:46:49,619][62408] Updated weights for policy 1, policy_version 37570 (0.0007) -[2023-10-17 01:46:49,989][62408] Updated weights for policy 1, policy_version 37580 (0.0007) -[2023-10-17 01:46:50,149][62373] Updated weights for policy 0, policy_version 37860 (0.0010) -[2023-10-17 01:46:50,350][62408] Updated weights for policy 1, policy_version 37590 (0.0008) -[2023-10-17 01:46:50,521][62373] Updated weights for policy 0, policy_version 37870 (0.0009) -[2023-10-17 01:46:50,716][62408] Updated weights for policy 1, policy_version 37600 (0.0008) -[2023-10-17 01:46:50,889][62373] Updated weights for policy 0, policy_version 37880 (0.0007) -[2023-10-17 01:46:52,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 77299712. Throughput: 0: 1795.5, 1: 1773.9. Samples: 19326934. Policy #0 lag: (min: 26.0, avg: 34.0, max: 58.0) -[2023-10-17 01:46:52,215][61453] Avg episode reward: [(0, '8.560'), (1, '8.680')] -[2023-10-17 01:46:54,460][62408] Updated weights for policy 1, policy_version 37610 (0.0011) -[2023-10-17 01:46:54,749][62373] Updated weights for policy 0, policy_version 37890 (0.0009) -[2023-10-17 01:46:54,833][62408] Updated weights for policy 1, policy_version 37620 (0.0007) -[2023-10-17 01:46:55,126][62373] Updated weights for policy 0, policy_version 37900 (0.0007) -[2023-10-17 01:46:55,200][62408] Updated weights for policy 1, policy_version 37630 (0.0007) -[2023-10-17 01:46:55,489][62373] Updated weights for policy 0, policy_version 37910 (0.0008) -[2023-10-17 01:46:55,860][62373] Updated weights for policy 0, policy_version 37920 (0.0008) -[2023-10-17 01:46:57,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 77365248. Throughput: 0: 1770.1, 1: 1756.2. Samples: 19346782. Policy #0 lag: (min: 26.0, avg: 34.0, max: 58.0) -[2023-10-17 01:46:57,215][61453] Avg episode reward: [(0, '8.770'), (1, '8.850')] -[2023-10-17 01:46:58,918][62408] Updated weights for policy 1, policy_version 37640 (0.0010) -[2023-10-17 01:46:59,292][62408] Updated weights for policy 1, policy_version 37650 (0.0008) -[2023-10-17 01:46:59,655][62373] Updated weights for policy 0, policy_version 37930 (0.0010) -[2023-10-17 01:46:59,660][62408] Updated weights for policy 1, policy_version 37660 (0.0009) -[2023-10-17 01:47:00,024][62373] Updated weights for policy 0, policy_version 37940 (0.0011) -[2023-10-17 01:47:00,388][62373] Updated weights for policy 0, policy_version 37950 (0.0009) -[2023-10-17 01:47:02,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 77430784. Throughput: 0: 1766.9, 1: 1757.3. Samples: 19368904. Policy #0 lag: (min: 26.0, avg: 34.0, max: 58.0) -[2023-10-17 01:47:02,214][61453] Avg episode reward: [(0, '8.150'), (1, '9.520')] -[2023-10-17 01:47:02,224][62252] Saving new best policy, reward=9.520! -[2023-10-17 01:47:03,524][62408] Updated weights for policy 1, policy_version 37670 (0.0009) -[2023-10-17 01:47:03,891][62408] Updated weights for policy 1, policy_version 37680 (0.0010) -[2023-10-17 01:47:04,163][62373] Updated weights for policy 0, policy_version 37960 (0.0009) -[2023-10-17 01:47:04,264][62408] Updated weights for policy 1, policy_version 37690 (0.0007) -[2023-10-17 01:47:04,538][62373] Updated weights for policy 0, policy_version 37970 (0.0009) -[2023-10-17 01:47:04,914][62373] Updated weights for policy 0, policy_version 37980 (0.0009) -[2023-10-17 01:47:07,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 77496320. Throughput: 0: 1769.8, 1: 1755.2. Samples: 19378588. Policy #0 lag: (min: 18.0, avg: 25.0, max: 50.0) -[2023-10-17 01:47:07,214][61453] Avg episode reward: [(0, '8.400'), (1, '8.880')] -[2023-10-17 01:47:08,050][62408] Updated weights for policy 1, policy_version 37700 (0.0008) -[2023-10-17 01:47:08,416][62408] Updated weights for policy 1, policy_version 37710 (0.0007) -[2023-10-17 01:47:08,784][62408] Updated weights for policy 1, policy_version 37720 (0.0008) -[2023-10-17 01:47:08,888][62373] Updated weights for policy 0, policy_version 37990 (0.0009) -[2023-10-17 01:47:09,254][62373] Updated weights for policy 0, policy_version 38000 (0.0010) -[2023-10-17 01:47:09,627][62373] Updated weights for policy 0, policy_version 38010 (0.0008) -[2023-10-17 01:47:12,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 77561856. Throughput: 0: 1762.9, 1: 1755.0. Samples: 19400400. Policy #0 lag: (min: 18.0, avg: 25.0, max: 50.0) -[2023-10-17 01:47:12,215][61453] Avg episode reward: [(0, '8.110'), (1, '8.780')] -[2023-10-17 01:47:12,743][62408] Updated weights for policy 1, policy_version 37730 (0.0008) -[2023-10-17 01:47:13,115][62408] Updated weights for policy 1, policy_version 37740 (0.0008) -[2023-10-17 01:47:13,341][62373] Updated weights for policy 0, policy_version 38020 (0.0008) -[2023-10-17 01:47:13,493][62408] Updated weights for policy 1, policy_version 37750 (0.0007) -[2023-10-17 01:47:13,706][62373] Updated weights for policy 0, policy_version 38030 (0.0008) -[2023-10-17 01:47:13,863][62408] Updated weights for policy 1, policy_version 37760 (0.0008) -[2023-10-17 01:47:14,080][62373] Updated weights for policy 0, policy_version 38040 (0.0010) -[2023-10-17 01:47:17,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 77627392. Throughput: 0: 1772.1, 1: 1776.2. Samples: 19422240. Policy #0 lag: (min: 18.0, avg: 25.0, max: 50.0) -[2023-10-17 01:47:17,215][61453] Avg episode reward: [(0, '8.900'), (1, '9.290')] -[2023-10-17 01:47:17,740][62408] Updated weights for policy 1, policy_version 37770 (0.0010) -[2023-10-17 01:47:18,020][62373] Updated weights for policy 0, policy_version 38050 (0.0010) -[2023-10-17 01:47:18,106][62408] Updated weights for policy 1, policy_version 37780 (0.0008) -[2023-10-17 01:47:18,413][62373] Updated weights for policy 0, policy_version 38060 (0.0008) -[2023-10-17 01:47:18,472][62408] Updated weights for policy 1, policy_version 37790 (0.0008) -[2023-10-17 01:47:18,779][62373] Updated weights for policy 0, policy_version 38070 (0.0008) -[2023-10-17 01:47:19,142][62373] Updated weights for policy 0, policy_version 38080 (0.0009) -[2023-10-17 01:47:22,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 77692928. Throughput: 0: 1762.3, 1: 1746.8. Samples: 19431782. Policy #0 lag: (min: 18.0, avg: 25.0, max: 50.0) -[2023-10-17 01:47:22,215][61453] Avg episode reward: [(0, '9.630'), (1, '8.880')] -[2023-10-17 01:47:22,464][62408] Updated weights for policy 1, policy_version 37800 (0.0008) -[2023-10-17 01:47:22,786][62373] Updated weights for policy 0, policy_version 38090 (0.0007) -[2023-10-17 01:47:22,837][62408] Updated weights for policy 1, policy_version 37810 (0.0007) -[2023-10-17 01:47:23,153][62373] Updated weights for policy 0, policy_version 38100 (0.0007) -[2023-10-17 01:47:23,196][62408] Updated weights for policy 1, policy_version 37820 (0.0007) -[2023-10-17 01:47:23,523][62373] Updated weights for policy 0, policy_version 38110 (0.0010) -[2023-10-17 01:47:27,002][62408] Updated weights for policy 1, policy_version 37830 (0.0010) -[2023-10-17 01:47:27,214][61453] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 77758464. Throughput: 0: 1764.7, 1: 1763.8. Samples: 19453576. Policy #0 lag: (min: 18.0, avg: 25.0, max: 50.0) -[2023-10-17 01:47:27,214][61453] Avg episode reward: [(0, '9.500'), (1, '8.490')] -[2023-10-17 01:47:27,372][62408] Updated weights for policy 1, policy_version 37840 (0.0009) -[2023-10-17 01:47:27,498][62373] Updated weights for policy 0, policy_version 38120 (0.0008) -[2023-10-17 01:47:27,732][62408] Updated weights for policy 1, policy_version 37850 (0.0008) -[2023-10-17 01:47:27,871][62373] Updated weights for policy 0, policy_version 38130 (0.0008) -[2023-10-17 01:47:28,248][62373] Updated weights for policy 0, policy_version 38140 (0.0010) -[2023-10-17 01:47:31,573][62408] Updated weights for policy 1, policy_version 37860 (0.0009) -[2023-10-17 01:47:31,932][62408] Updated weights for policy 1, policy_version 37870 (0.0008) -[2023-10-17 01:47:32,074][62373] Updated weights for policy 0, policy_version 38150 (0.0008) -[2023-10-17 01:47:32,214][61453] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 77824000. Throughput: 0: 1787.2, 1: 1763.6. Samples: 19474816. Policy #0 lag: (min: 18.0, avg: 25.0, max: 50.0) -[2023-10-17 01:47:32,214][61453] Avg episode reward: [(0, '9.270'), (1, '8.150')] -[2023-10-17 01:47:32,296][62408] Updated weights for policy 1, policy_version 37880 (0.0009) -[2023-10-17 01:47:32,448][62373] Updated weights for policy 0, policy_version 38160 (0.0009) -[2023-10-17 01:47:32,590][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000037888_38797312.pth... -[2023-10-17 01:47:32,623][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000036224_37093376.pth -[2023-10-17 01:47:32,825][62373] Updated weights for policy 0, policy_version 38170 (0.0008) -[2023-10-17 01:47:33,047][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000038176_39092224.pth... -[2023-10-17 01:47:33,076][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000036512_37388288.pth -[2023-10-17 01:47:36,207][62408] Updated weights for policy 1, policy_version 37890 (0.0009) -[2023-10-17 01:47:36,437][62373] Updated weights for policy 0, policy_version 38180 (0.0007) -[2023-10-17 01:47:36,572][62408] Updated weights for policy 1, policy_version 37900 (0.0007) -[2023-10-17 01:47:36,805][62373] Updated weights for policy 0, policy_version 38190 (0.0008) -[2023-10-17 01:47:36,941][62408] Updated weights for policy 1, policy_version 37910 (0.0007) -[2023-10-17 01:47:37,175][62373] Updated weights for policy 0, policy_version 38200 (0.0008) -[2023-10-17 01:47:37,214][61453] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 77889536. Throughput: 0: 1761.2, 1: 1752.2. Samples: 19485036. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-17 01:47:37,214][61453] Avg episode reward: [(0, '9.560'), (1, '8.700')] -[2023-10-17 01:47:37,303][62408] Updated weights for policy 1, policy_version 37920 (0.0007) -[2023-10-17 01:47:41,103][62373] Updated weights for policy 0, policy_version 38210 (0.0009) -[2023-10-17 01:47:41,203][62408] Updated weights for policy 1, policy_version 37930 (0.0008) -[2023-10-17 01:47:41,471][62373] Updated weights for policy 0, policy_version 38220 (0.0008) -[2023-10-17 01:47:41,576][62408] Updated weights for policy 1, policy_version 37940 (0.0010) -[2023-10-17 01:47:41,850][62373] Updated weights for policy 0, policy_version 38230 (0.0010) -[2023-10-17 01:47:41,942][62408] Updated weights for policy 1, policy_version 37950 (0.0008) -[2023-10-17 01:47:42,210][62373] Updated weights for policy 0, policy_version 38240 (0.0009) -[2023-10-17 01:47:42,214][61453] Fps is (10 sec: 19661.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 78020608. Throughput: 0: 1787.1, 1: 1765.8. Samples: 19506660. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-17 01:47:42,214][61453] Avg episode reward: [(0, '9.550'), (1, '8.640')] -[2023-10-17 01:47:45,813][62408] Updated weights for policy 1, policy_version 37960 (0.0010) -[2023-10-17 01:47:46,107][62373] Updated weights for policy 0, policy_version 38250 (0.0008) -[2023-10-17 01:47:46,181][62408] Updated weights for policy 1, policy_version 37970 (0.0008) -[2023-10-17 01:47:46,474][62373] Updated weights for policy 0, policy_version 38260 (0.0008) -[2023-10-17 01:47:46,551][62408] Updated weights for policy 1, policy_version 37980 (0.0008) -[2023-10-17 01:47:46,851][62373] Updated weights for policy 0, policy_version 38270 (0.0009) -[2023-10-17 01:47:47,214][61453] Fps is (10 sec: 19660.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 78086144. Throughput: 0: 1753.5, 1: 1734.3. Samples: 19525856. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-17 01:47:47,215][61453] Avg episode reward: [(0, '10.100'), (1, '8.650')] -[2023-10-17 01:47:50,387][62408] Updated weights for policy 1, policy_version 37990 (0.0008) -[2023-10-17 01:47:50,666][62373] Updated weights for policy 0, policy_version 38280 (0.0008) -[2023-10-17 01:47:50,747][62408] Updated weights for policy 1, policy_version 38000 (0.0008) -[2023-10-17 01:47:51,036][62373] Updated weights for policy 0, policy_version 38290 (0.0007) -[2023-10-17 01:47:51,114][62408] Updated weights for policy 1, policy_version 38010 (0.0008) -[2023-10-17 01:47:51,401][62373] Updated weights for policy 0, policy_version 38300 (0.0007) -[2023-10-17 01:47:52,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 78151680. Throughput: 0: 1778.9, 1: 1770.0. Samples: 19538290. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-17 01:47:52,215][61453] Avg episode reward: [(0, '9.890'), (1, '8.790')] -[2023-10-17 01:47:54,934][62408] Updated weights for policy 1, policy_version 38020 (0.0007) -[2023-10-17 01:47:55,125][62373] Updated weights for policy 0, policy_version 38310 (0.0009) -[2023-10-17 01:47:55,300][62408] Updated weights for policy 1, policy_version 38030 (0.0009) -[2023-10-17 01:47:55,492][62373] Updated weights for policy 0, policy_version 38320 (0.0007) -[2023-10-17 01:47:55,663][62408] Updated weights for policy 1, policy_version 38040 (0.0009) -[2023-10-17 01:47:55,851][62373] Updated weights for policy 0, policy_version 38330 (0.0007) -[2023-10-17 01:47:57,214][61453] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 78217216. Throughput: 0: 1762.6, 1: 1737.4. Samples: 19557900. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-17 01:47:57,214][61453] Avg episode reward: [(0, '9.400'), (1, '8.940')] -[2023-10-17 01:47:59,605][62408] Updated weights for policy 1, policy_version 38050 (0.0007) -[2023-10-17 01:47:59,642][62373] Updated weights for policy 0, policy_version 38340 (0.0008) -[2023-10-17 01:47:59,975][62408] Updated weights for policy 1, policy_version 38060 (0.0009) -[2023-10-17 01:48:00,003][62373] Updated weights for policy 0, policy_version 38350 (0.0008) -[2023-10-17 01:48:00,342][62408] Updated weights for policy 1, policy_version 38070 (0.0007) -[2023-10-17 01:48:00,373][62373] Updated weights for policy 0, policy_version 38360 (0.0008) -[2023-10-17 01:48:00,713][62408] Updated weights for policy 1, policy_version 38080 (0.0009) -[2023-10-17 01:48:02,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 78282752. Throughput: 0: 1763.5, 1: 1737.5. Samples: 19579784. Policy #0 lag: (min: 16.0, avg: 42.3, max: 48.0) -[2023-10-17 01:48:02,215][61453] Avg episode reward: [(0, '9.420'), (1, '8.890')] -[2023-10-17 01:48:04,330][62373] Updated weights for policy 0, policy_version 38370 (0.0007) -[2023-10-17 01:48:04,448][62408] Updated weights for policy 1, policy_version 38090 (0.0009) -[2023-10-17 01:48:04,739][62373] Updated weights for policy 0, policy_version 38380 (0.0007) -[2023-10-17 01:48:04,812][62408] Updated weights for policy 1, policy_version 38100 (0.0007) -[2023-10-17 01:48:05,105][62373] Updated weights for policy 0, policy_version 38390 (0.0007) -[2023-10-17 01:48:05,178][62408] Updated weights for policy 1, policy_version 38110 (0.0007) -[2023-10-17 01:48:05,469][62373] Updated weights for policy 0, policy_version 38400 (0.0008) -[2023-10-17 01:48:07,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 78348288. Throughput: 0: 1773.4, 1: 1752.8. Samples: 19590460. Policy #0 lag: (min: 16.0, avg: 42.3, max: 48.0) -[2023-10-17 01:48:07,214][61453] Avg episode reward: [(0, '9.600'), (1, '8.250')] -[2023-10-17 01:48:09,049][62408] Updated weights for policy 1, policy_version 38120 (0.0008) -[2023-10-17 01:48:09,147][62373] Updated weights for policy 0, policy_version 38410 (0.0008) -[2023-10-17 01:48:09,425][62408] Updated weights for policy 1, policy_version 38130 (0.0009) -[2023-10-17 01:48:09,516][62373] Updated weights for policy 0, policy_version 38420 (0.0007) -[2023-10-17 01:48:09,786][62408] Updated weights for policy 1, policy_version 38140 (0.0009) -[2023-10-17 01:48:09,882][62373] Updated weights for policy 0, policy_version 38430 (0.0008) -[2023-10-17 01:48:12,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 78413824. Throughput: 0: 1763.7, 1: 1742.2. Samples: 19611344. Policy #0 lag: (min: 16.0, avg: 42.3, max: 48.0) -[2023-10-17 01:48:12,214][61453] Avg episode reward: [(0, '9.740'), (1, '8.810')] -[2023-10-17 01:48:13,754][62373] Updated weights for policy 0, policy_version 38440 (0.0010) -[2023-10-17 01:48:13,770][62408] Updated weights for policy 1, policy_version 38150 (0.0009) -[2023-10-17 01:48:14,127][62373] Updated weights for policy 0, policy_version 38450 (0.0008) -[2023-10-17 01:48:14,152][62408] Updated weights for policy 1, policy_version 38160 (0.0009) -[2023-10-17 01:48:14,493][62373] Updated weights for policy 0, policy_version 38460 (0.0010) -[2023-10-17 01:48:14,519][62408] Updated weights for policy 1, policy_version 38170 (0.0007) -[2023-10-17 01:48:17,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 78479360. Throughput: 0: 1764.3, 1: 1754.2. Samples: 19633150. Policy #0 lag: (min: 16.0, avg: 42.3, max: 48.0) -[2023-10-17 01:48:17,215][61453] Avg episode reward: [(0, '9.150'), (1, '9.010')] -[2023-10-17 01:48:18,338][62373] Updated weights for policy 0, policy_version 38470 (0.0008) -[2023-10-17 01:48:18,380][62408] Updated weights for policy 1, policy_version 38180 (0.0008) -[2023-10-17 01:48:18,709][62373] Updated weights for policy 0, policy_version 38480 (0.0007) -[2023-10-17 01:48:18,741][62408] Updated weights for policy 1, policy_version 38190 (0.0007) -[2023-10-17 01:48:19,079][62373] Updated weights for policy 0, policy_version 38490 (0.0010) -[2023-10-17 01:48:19,118][62408] Updated weights for policy 1, policy_version 38200 (0.0008) -[2023-10-17 01:48:22,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 78544896. Throughput: 0: 1760.3, 1: 1745.1. Samples: 19642780. Policy #0 lag: (min: 16.0, avg: 42.3, max: 48.0) -[2023-10-17 01:48:22,215][61453] Avg episode reward: [(0, '9.150'), (1, '8.870')] -[2023-10-17 01:48:22,827][62408] Updated weights for policy 1, policy_version 38210 (0.0008) -[2023-10-17 01:48:23,041][62373] Updated weights for policy 0, policy_version 38500 (0.0009) -[2023-10-17 01:48:23,200][62408] Updated weights for policy 1, policy_version 38220 (0.0007) -[2023-10-17 01:48:23,409][62373] Updated weights for policy 0, policy_version 38510 (0.0008) -[2023-10-17 01:48:23,568][62408] Updated weights for policy 1, policy_version 38230 (0.0007) -[2023-10-17 01:48:23,777][62373] Updated weights for policy 0, policy_version 38520 (0.0007) -[2023-10-17 01:48:23,931][62408] Updated weights for policy 1, policy_version 38240 (0.0007) -[2023-10-17 01:48:27,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 78610432. Throughput: 0: 1766.9, 1: 1748.6. Samples: 19664860. Policy #0 lag: (min: 16.0, avg: 42.3, max: 48.0) -[2023-10-17 01:48:27,215][61453] Avg episode reward: [(0, '9.340'), (1, '8.540')] -[2023-10-17 01:48:27,479][62373] Updated weights for policy 0, policy_version 38530 (0.0008) -[2023-10-17 01:48:27,858][62373] Updated weights for policy 0, policy_version 38540 (0.0008) -[2023-10-17 01:48:27,930][62408] Updated weights for policy 1, policy_version 38250 (0.0009) -[2023-10-17 01:48:28,221][62373] Updated weights for policy 0, policy_version 38550 (0.0008) -[2023-10-17 01:48:28,299][62408] Updated weights for policy 1, policy_version 38260 (0.0008) -[2023-10-17 01:48:28,590][62373] Updated weights for policy 0, policy_version 38560 (0.0008) -[2023-10-17 01:48:28,673][62408] Updated weights for policy 1, policy_version 38270 (0.0007) -[2023-10-17 01:48:32,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 78675968. Throughput: 0: 1797.6, 1: 1778.6. Samples: 19686786. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-17 01:48:32,215][61453] Avg episode reward: [(0, '9.000'), (1, '8.730')] -[2023-10-17 01:48:32,441][62373] Updated weights for policy 0, policy_version 38570 (0.0007) -[2023-10-17 01:48:32,511][62408] Updated weights for policy 1, policy_version 38280 (0.0007) -[2023-10-17 01:48:32,809][62373] Updated weights for policy 0, policy_version 38580 (0.0007) -[2023-10-17 01:48:32,875][62408] Updated weights for policy 1, policy_version 38290 (0.0008) -[2023-10-17 01:48:33,173][62373] Updated weights for policy 0, policy_version 38590 (0.0007) -[2023-10-17 01:48:33,240][62408] Updated weights for policy 1, policy_version 38300 (0.0009) -[2023-10-17 01:48:36,980][62373] Updated weights for policy 0, policy_version 38600 (0.0008) -[2023-10-17 01:48:37,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 78741504. Throughput: 0: 1770.7, 1: 1745.2. Samples: 19696506. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-17 01:48:37,215][61453] Avg episode reward: [(0, '8.770'), (1, '8.990')] -[2023-10-17 01:48:37,219][62408] Updated weights for policy 1, policy_version 38310 (0.0009) -[2023-10-17 01:48:37,347][62373] Updated weights for policy 0, policy_version 38610 (0.0009) -[2023-10-17 01:48:37,579][62408] Updated weights for policy 1, policy_version 38320 (0.0009) -[2023-10-17 01:48:37,709][62373] Updated weights for policy 0, policy_version 38620 (0.0008) -[2023-10-17 01:48:37,952][62408] Updated weights for policy 1, policy_version 38330 (0.0009) -[2023-10-17 01:48:41,526][62373] Updated weights for policy 0, policy_version 38630 (0.0010) -[2023-10-17 01:48:41,813][62408] Updated weights for policy 1, policy_version 38340 (0.0010) -[2023-10-17 01:48:41,880][62373] Updated weights for policy 0, policy_version 38640 (0.0009) -[2023-10-17 01:48:42,179][62408] Updated weights for policy 1, policy_version 38350 (0.0008) -[2023-10-17 01:48:42,214][61453] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 13995.8). Total num frames: 78807040. Throughput: 0: 1791.1, 1: 1769.0. Samples: 19718106. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-17 01:48:42,215][61453] Avg episode reward: [(0, '8.770'), (1, '8.740')] -[2023-10-17 01:48:42,244][62373] Updated weights for policy 0, policy_version 38650 (0.0009) -[2023-10-17 01:48:42,543][62408] Updated weights for policy 1, policy_version 38360 (0.0008) -[2023-10-17 01:48:46,134][62373] Updated weights for policy 0, policy_version 38660 (0.0009) -[2023-10-17 01:48:46,471][62408] Updated weights for policy 1, policy_version 38370 (0.0009) -[2023-10-17 01:48:46,501][62373] Updated weights for policy 0, policy_version 38670 (0.0007) -[2023-10-17 01:48:46,831][62408] Updated weights for policy 1, policy_version 38380 (0.0010) -[2023-10-17 01:48:46,872][62373] Updated weights for policy 0, policy_version 38680 (0.0008) -[2023-10-17 01:48:47,198][62408] Updated weights for policy 1, policy_version 38390 (0.0008) -[2023-10-17 01:48:47,214][61453] Fps is (10 sec: 16384.2, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 78905344. Throughput: 0: 1763.4, 1: 1762.4. Samples: 19738444. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-17 01:48:47,215][61453] Avg episode reward: [(0, '8.750'), (1, '8.590')] -[2023-10-17 01:48:47,575][62408] Updated weights for policy 1, policy_version 38400 (0.0010) -[2023-10-17 01:48:50,830][62373] Updated weights for policy 0, policy_version 38690 (0.0008) -[2023-10-17 01:48:51,200][62373] Updated weights for policy 0, policy_version 38700 (0.0008) -[2023-10-17 01:48:51,478][62408] Updated weights for policy 1, policy_version 38410 (0.0008) -[2023-10-17 01:48:51,575][62373] Updated weights for policy 0, policy_version 38710 (0.0008) -[2023-10-17 01:48:51,839][62408] Updated weights for policy 1, policy_version 38420 (0.0007) -[2023-10-17 01:48:51,941][62373] Updated weights for policy 0, policy_version 38720 (0.0008) -[2023-10-17 01:48:52,207][62408] Updated weights for policy 1, policy_version 38430 (0.0007) -[2023-10-17 01:48:52,214][61453] Fps is (10 sec: 16384.0, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 78970880. Throughput: 0: 1777.7, 1: 1758.8. Samples: 19749604. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-17 01:48:52,215][61453] Avg episode reward: [(0, '9.360'), (1, '8.510')] -[2023-10-17 01:48:55,666][62373] Updated weights for policy 0, policy_version 38730 (0.0009) -[2023-10-17 01:48:55,976][62408] Updated weights for policy 1, policy_version 38440 (0.0007) -[2023-10-17 01:48:56,022][62373] Updated weights for policy 0, policy_version 38740 (0.0009) -[2023-10-17 01:48:56,353][62408] Updated weights for policy 1, policy_version 38450 (0.0009) -[2023-10-17 01:48:56,391][62373] Updated weights for policy 0, policy_version 38750 (0.0008) -[2023-10-17 01:48:56,725][62408] Updated weights for policy 1, policy_version 38460 (0.0008) -[2023-10-17 01:48:57,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 79069184. Throughput: 0: 1773.0, 1: 1770.4. Samples: 19770800. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:48:57,215][61453] Avg episode reward: [(0, '9.310'), (1, '8.670')] -[2023-10-17 01:49:00,211][62373] Updated weights for policy 0, policy_version 38760 (0.0008) -[2023-10-17 01:49:00,579][62373] Updated weights for policy 0, policy_version 38770 (0.0007) -[2023-10-17 01:49:00,583][62408] Updated weights for policy 1, policy_version 38470 (0.0009) -[2023-10-17 01:49:00,937][62373] Updated weights for policy 0, policy_version 38780 (0.0007) -[2023-10-17 01:49:00,952][62408] Updated weights for policy 1, policy_version 38480 (0.0008) -[2023-10-17 01:49:01,317][62408] Updated weights for policy 1, policy_version 38490 (0.0007) -[2023-10-17 01:49:02,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 79134720. Throughput: 0: 1764.5, 1: 1745.5. Samples: 19791100. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:49:02,215][61453] Avg episode reward: [(0, '9.260'), (1, '8.510')] -[2023-10-17 01:49:04,750][62373] Updated weights for policy 0, policy_version 38790 (0.0009) -[2023-10-17 01:49:04,896][62408] Updated weights for policy 1, policy_version 38500 (0.0007) -[2023-10-17 01:49:05,118][62373] Updated weights for policy 0, policy_version 38800 (0.0007) -[2023-10-17 01:49:05,277][62408] Updated weights for policy 1, policy_version 38510 (0.0007) -[2023-10-17 01:49:05,495][62373] Updated weights for policy 0, policy_version 38810 (0.0009) -[2023-10-17 01:49:05,639][62408] Updated weights for policy 1, policy_version 38520 (0.0008) -[2023-10-17 01:49:07,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 79200256. Throughput: 0: 1783.0, 1: 1777.3. Samples: 19802994. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:49:07,215][61453] Avg episode reward: [(0, '9.080'), (1, '8.590')] -[2023-10-17 01:49:09,092][62373] Updated weights for policy 0, policy_version 38820 (0.0007) -[2023-10-17 01:49:09,461][62373] Updated weights for policy 0, policy_version 38830 (0.0008) -[2023-10-17 01:49:09,531][62408] Updated weights for policy 1, policy_version 38530 (0.0008) -[2023-10-17 01:49:09,845][62373] Updated weights for policy 0, policy_version 38840 (0.0008) -[2023-10-17 01:49:09,916][62408] Updated weights for policy 1, policy_version 38540 (0.0010) -[2023-10-17 01:49:10,271][62408] Updated weights for policy 1, policy_version 38550 (0.0010) -[2023-10-17 01:49:10,635][62408] Updated weights for policy 1, policy_version 38560 (0.0008) -[2023-10-17 01:49:12,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 79265792. Throughput: 0: 1762.9, 1: 1748.8. Samples: 19822888. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:49:12,215][61453] Avg episode reward: [(0, '8.610'), (1, '7.680')] -[2023-10-17 01:49:13,606][62373] Updated weights for policy 0, policy_version 38850 (0.0008) -[2023-10-17 01:49:13,972][62373] Updated weights for policy 0, policy_version 38860 (0.0009) -[2023-10-17 01:49:14,335][62373] Updated weights for policy 0, policy_version 38870 (0.0009) -[2023-10-17 01:49:14,532][62408] Updated weights for policy 1, policy_version 38570 (0.0008) -[2023-10-17 01:49:14,700][62373] Updated weights for policy 0, policy_version 38880 (0.0007) -[2023-10-17 01:49:14,895][62408] Updated weights for policy 1, policy_version 38580 (0.0007) -[2023-10-17 01:49:15,273][62408] Updated weights for policy 1, policy_version 38590 (0.0007) -[2023-10-17 01:49:17,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 79331328. Throughput: 0: 1766.2, 1: 1747.0. Samples: 19844878. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:49:17,215][61453] Avg episode reward: [(0, '9.160'), (1, '8.390')] -[2023-10-17 01:49:18,625][62373] Updated weights for policy 0, policy_version 38890 (0.0007) -[2023-10-17 01:49:19,005][62373] Updated weights for policy 0, policy_version 38900 (0.0007) -[2023-10-17 01:49:19,266][62408] Updated weights for policy 1, policy_version 38600 (0.0008) -[2023-10-17 01:49:19,376][62373] Updated weights for policy 0, policy_version 38910 (0.0008) -[2023-10-17 01:49:19,634][62408] Updated weights for policy 1, policy_version 38610 (0.0007) -[2023-10-17 01:49:19,996][62408] Updated weights for policy 1, policy_version 38620 (0.0008) -[2023-10-17 01:49:22,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 79396864. Throughput: 0: 1763.0, 1: 1751.9. Samples: 19854678. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:49:22,215][61453] Avg episode reward: [(0, '9.110'), (1, '7.780')] -[2023-10-17 01:49:23,160][62373] Updated weights for policy 0, policy_version 38920 (0.0010) -[2023-10-17 01:49:23,522][62373] Updated weights for policy 0, policy_version 38930 (0.0009) -[2023-10-17 01:49:23,827][62408] Updated weights for policy 1, policy_version 38630 (0.0007) -[2023-10-17 01:49:23,893][62373] Updated weights for policy 0, policy_version 38940 (0.0008) -[2023-10-17 01:49:24,193][62408] Updated weights for policy 1, policy_version 38640 (0.0007) -[2023-10-17 01:49:24,562][62408] Updated weights for policy 1, policy_version 38650 (0.0007) -[2023-10-17 01:49:27,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 79462400. Throughput: 0: 1763.3, 1: 1746.6. Samples: 19876050. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-17 01:49:27,215][61453] Avg episode reward: [(0, '8.000'), (1, '7.440')] -[2023-10-17 01:49:27,729][62373] Updated weights for policy 0, policy_version 38950 (0.0007) -[2023-10-17 01:49:28,093][62373] Updated weights for policy 0, policy_version 38960 (0.0009) -[2023-10-17 01:49:28,354][62408] Updated weights for policy 1, policy_version 38660 (0.0007) -[2023-10-17 01:49:28,464][62373] Updated weights for policy 0, policy_version 38970 (0.0008) -[2023-10-17 01:49:28,718][62408] Updated weights for policy 1, policy_version 38670 (0.0007) -[2023-10-17 01:49:29,090][62408] Updated weights for policy 1, policy_version 38680 (0.0009) -[2023-10-17 01:49:32,208][62373] Updated weights for policy 0, policy_version 38980 (0.0008) -[2023-10-17 01:49:32,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 79527936. Throughput: 0: 1792.1, 1: 1760.0. Samples: 19898290. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-17 01:49:32,215][61453] Avg episode reward: [(0, '8.170'), (1, '7.300')] -[2023-10-17 01:49:32,225][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000038688_39616512.pth... -[2023-10-17 01:49:32,263][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000037056_37945344.pth -[2023-10-17 01:49:32,569][62373] Updated weights for policy 0, policy_version 38990 (0.0007) -[2023-10-17 01:49:32,920][62408] Updated weights for policy 1, policy_version 38690 (0.0007) -[2023-10-17 01:49:32,946][62373] Updated weights for policy 0, policy_version 39000 (0.0008) -[2023-10-17 01:49:33,228][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000039008_39944192.pth... -[2023-10-17 01:49:33,256][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000037344_38240256.pth -[2023-10-17 01:49:33,298][62408] Updated weights for policy 1, policy_version 38700 (0.0009) -[2023-10-17 01:49:33,653][62408] Updated weights for policy 1, policy_version 38710 (0.0010) -[2023-10-17 01:49:34,017][62408] Updated weights for policy 1, policy_version 38720 (0.0009) -[2023-10-17 01:49:36,731][62373] Updated weights for policy 0, policy_version 39010 (0.0008) -[2023-10-17 01:49:37,142][62373] Updated weights for policy 0, policy_version 39020 (0.0009) -[2023-10-17 01:49:37,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 79593472. Throughput: 0: 1769.6, 1: 1749.9. Samples: 19907978. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-17 01:49:37,214][61453] Avg episode reward: [(0, '8.390'), (1, '7.380')] -[2023-10-17 01:49:37,509][62373] Updated weights for policy 0, policy_version 39030 (0.0009) -[2023-10-17 01:49:37,876][62373] Updated weights for policy 0, policy_version 39040 (0.0008) -[2023-10-17 01:49:37,882][62408] Updated weights for policy 1, policy_version 38730 (0.0009) -[2023-10-17 01:49:38,243][62408] Updated weights for policy 1, policy_version 38740 (0.0009) -[2023-10-17 01:49:38,619][62408] Updated weights for policy 1, policy_version 38750 (0.0010) -[2023-10-17 01:49:41,708][62373] Updated weights for policy 0, policy_version 39050 (0.0009) -[2023-10-17 01:49:42,079][62373] Updated weights for policy 0, policy_version 39060 (0.0010) -[2023-10-17 01:49:42,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 79659008. Throughput: 0: 1782.3, 1: 1751.1. Samples: 19929802. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-17 01:49:42,215][61453] Avg episode reward: [(0, '8.410'), (1, '8.120')] -[2023-10-17 01:49:42,454][62373] Updated weights for policy 0, policy_version 39070 (0.0008) -[2023-10-17 01:49:42,461][62408] Updated weights for policy 1, policy_version 38760 (0.0008) -[2023-10-17 01:49:42,827][62408] Updated weights for policy 1, policy_version 38770 (0.0008) -[2023-10-17 01:49:43,196][62408] Updated weights for policy 1, policy_version 38780 (0.0007) -[2023-10-17 01:49:46,242][62373] Updated weights for policy 0, policy_version 39080 (0.0010) -[2023-10-17 01:49:46,609][62373] Updated weights for policy 0, policy_version 39090 (0.0009) -[2023-10-17 01:49:46,976][62373] Updated weights for policy 0, policy_version 39100 (0.0011) -[2023-10-17 01:49:47,197][62408] Updated weights for policy 1, policy_version 38790 (0.0008) -[2023-10-17 01:49:47,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 79757312. Throughput: 0: 1770.6, 1: 1777.2. Samples: 19950750. Policy #0 lag: (min: 31.0, avg: 33.7, max: 63.0) -[2023-10-17 01:49:47,215][61453] Avg episode reward: [(0, '8.050'), (1, '7.370')] -[2023-10-17 01:49:47,580][62408] Updated weights for policy 1, policy_version 38800 (0.0010) -[2023-10-17 01:49:47,938][62408] Updated weights for policy 1, policy_version 38810 (0.0011) -[2023-10-17 01:49:50,675][62373] Updated weights for policy 0, policy_version 39110 (0.0009) -[2023-10-17 01:49:51,036][62373] Updated weights for policy 0, policy_version 39120 (0.0010) -[2023-10-17 01:49:51,410][62373] Updated weights for policy 0, policy_version 39130 (0.0010) -[2023-10-17 01:49:51,661][62408] Updated weights for policy 1, policy_version 38820 (0.0009) -[2023-10-17 01:49:52,035][62408] Updated weights for policy 1, policy_version 38830 (0.0008) -[2023-10-17 01:49:52,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 79822848. Throughput: 0: 1778.4, 1: 1739.3. Samples: 19961292. Policy #0 lag: (min: 20.0, avg: 21.4, max: 46.0) -[2023-10-17 01:49:52,215][61453] Avg episode reward: [(0, '8.290'), (1, '8.340')] -[2023-10-17 01:49:52,411][62408] Updated weights for policy 1, policy_version 38840 (0.0008) -[2023-10-17 01:49:55,237][62373] Updated weights for policy 0, policy_version 39140 (0.0009) -[2023-10-17 01:49:55,612][62373] Updated weights for policy 0, policy_version 39150 (0.0011) -[2023-10-17 01:49:55,974][62373] Updated weights for policy 0, policy_version 39160 (0.0010) -[2023-10-17 01:49:56,306][62408] Updated weights for policy 1, policy_version 38850 (0.0007) -[2023-10-17 01:49:56,674][62408] Updated weights for policy 1, policy_version 38860 (0.0007) -[2023-10-17 01:49:57,040][62408] Updated weights for policy 1, policy_version 38870 (0.0010) -[2023-10-17 01:49:57,214][61453] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 79888384. Throughput: 0: 1776.1, 1: 1766.7. Samples: 19982314. Policy #0 lag: (min: 20.0, avg: 21.4, max: 46.0) -[2023-10-17 01:49:57,215][61453] Avg episode reward: [(0, '8.290'), (1, '8.300')] -[2023-10-17 01:49:57,414][62408] Updated weights for policy 1, policy_version 38880 (0.0009) -[2023-10-17 01:49:59,969][62373] Updated weights for policy 0, policy_version 39170 (0.0008) -[2023-10-17 01:50:00,341][62373] Updated weights for policy 0, policy_version 39180 (0.0009) -[2023-10-17 01:50:00,710][62373] Updated weights for policy 0, policy_version 39190 (0.0011) -[2023-10-17 01:50:01,081][62373] Updated weights for policy 0, policy_version 39200 (0.0009) -[2023-10-17 01:50:01,290][62408] Updated weights for policy 1, policy_version 38890 (0.0009) -[2023-10-17 01:50:01,657][62408] Updated weights for policy 1, policy_version 38900 (0.0009) -[2023-10-17 01:50:02,025][62408] Updated weights for policy 1, policy_version 38910 (0.0010) -[2023-10-17 01:50:02,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 79986688. Throughput: 0: 1764.8, 1: 1742.6. Samples: 20002710. Policy #0 lag: (min: 20.0, avg: 21.4, max: 46.0) -[2023-10-17 01:50:02,215][61453] Avg episode reward: [(0, '8.500'), (1, '8.330')] -[2023-10-17 01:50:04,768][62373] Updated weights for policy 0, policy_version 39210 (0.0007) -[2023-10-17 01:50:05,145][62373] Updated weights for policy 0, policy_version 39220 (0.0007) -[2023-10-17 01:50:05,512][62373] Updated weights for policy 0, policy_version 39230 (0.0009) -[2023-10-17 01:50:05,710][62408] Updated weights for policy 1, policy_version 38920 (0.0008) -[2023-10-17 01:50:06,085][62408] Updated weights for policy 1, policy_version 38930 (0.0008) -[2023-10-17 01:50:06,454][62408] Updated weights for policy 1, policy_version 38940 (0.0009) -[2023-10-17 01:50:07,214][61453] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 80052224. Throughput: 0: 1781.0, 1: 1768.7. Samples: 20014416. Policy #0 lag: (min: 20.0, avg: 21.4, max: 46.0) -[2023-10-17 01:50:07,214][61453] Avg episode reward: [(0, '8.790'), (1, '8.340')] -[2023-10-17 01:50:09,236][62373] Updated weights for policy 0, policy_version 39240 (0.0007) -[2023-10-17 01:50:09,613][62373] Updated weights for policy 0, policy_version 39250 (0.0008) -[2023-10-17 01:50:09,987][62373] Updated weights for policy 0, policy_version 39260 (0.0009) -[2023-10-17 01:50:10,184][62408] Updated weights for policy 1, policy_version 38950 (0.0009) -[2023-10-17 01:50:10,554][62408] Updated weights for policy 1, policy_version 38960 (0.0011) -[2023-10-17 01:50:10,914][62408] Updated weights for policy 1, policy_version 38970 (0.0009) -[2023-10-17 01:50:12,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 80117760. Throughput: 0: 1769.7, 1: 1761.7. Samples: 20034964. Policy #0 lag: (min: 20.0, avg: 21.4, max: 46.0) -[2023-10-17 01:50:12,215][61453] Avg episode reward: [(0, '8.570'), (1, '7.860')] -[2023-10-17 01:50:13,821][62373] Updated weights for policy 0, policy_version 39270 (0.0007) -[2023-10-17 01:50:14,196][62373] Updated weights for policy 0, policy_version 39280 (0.0008) -[2023-10-17 01:50:14,570][62373] Updated weights for policy 0, policy_version 39290 (0.0007) -[2023-10-17 01:50:14,718][62408] Updated weights for policy 1, policy_version 38980 (0.0009) -[2023-10-17 01:50:15,095][62408] Updated weights for policy 1, policy_version 38990 (0.0009) -[2023-10-17 01:50:15,460][62408] Updated weights for policy 1, policy_version 39000 (0.0009) -[2023-10-17 01:50:17,214][61453] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 80183296. Throughput: 0: 1768.5, 1: 1752.2. Samples: 20056722. Policy #0 lag: (min: 20.0, avg: 21.4, max: 46.0) -[2023-10-17 01:50:17,215][61453] Avg episode reward: [(0, '9.060'), (1, '8.490')] -[2023-10-17 01:50:18,303][62373] Updated weights for policy 0, policy_version 39300 (0.0009) -[2023-10-17 01:50:18,679][62373] Updated weights for policy 0, policy_version 39310 (0.0008) -[2023-10-17 01:50:19,052][62373] Updated weights for policy 0, policy_version 39320 (0.0008) -[2023-10-17 01:50:19,288][62408] Updated weights for policy 1, policy_version 39010 (0.0009) -[2023-10-17 01:50:19,658][62408] Updated weights for policy 1, policy_version 39020 (0.0009) -[2023-10-17 01:50:20,022][62408] Updated weights for policy 1, policy_version 39030 (0.0007) -[2023-10-17 01:50:20,387][62408] Updated weights for policy 1, policy_version 39040 (0.0007) -[2023-10-17 01:50:22,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 80248832. Throughput: 0: 1767.2, 1: 1770.6. Samples: 20067178. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:50:22,214][61453] Avg episode reward: [(0, '9.120'), (1, '8.340')] -[2023-10-17 01:50:22,834][62373] Updated weights for policy 0, policy_version 39330 (0.0008) -[2023-10-17 01:50:23,232][62373] Updated weights for policy 0, policy_version 39340 (0.0009) -[2023-10-17 01:50:23,598][62373] Updated weights for policy 0, policy_version 39350 (0.0009) -[2023-10-17 01:50:23,963][62373] Updated weights for policy 0, policy_version 39360 (0.0008) -[2023-10-17 01:50:24,234][62408] Updated weights for policy 1, policy_version 39050 (0.0008) -[2023-10-17 01:50:24,604][62408] Updated weights for policy 1, policy_version 39060 (0.0008) -[2023-10-17 01:50:24,964][62408] Updated weights for policy 1, policy_version 39070 (0.0009) -[2023-10-17 01:50:27,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 80314368. Throughput: 0: 1771.2, 1: 1757.2. Samples: 20088578. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:50:27,215][61453] Avg episode reward: [(0, '9.480'), (1, '8.830')] -[2023-10-17 01:50:27,693][62373] Updated weights for policy 0, policy_version 39370 (0.0008) -[2023-10-17 01:50:28,056][62373] Updated weights for policy 0, policy_version 39380 (0.0009) -[2023-10-17 01:50:28,423][62373] Updated weights for policy 0, policy_version 39390 (0.0008) -[2023-10-17 01:50:28,921][62408] Updated weights for policy 1, policy_version 39080 (0.0009) -[2023-10-17 01:50:29,296][62408] Updated weights for policy 1, policy_version 39090 (0.0007) -[2023-10-17 01:50:29,662][62408] Updated weights for policy 1, policy_version 39100 (0.0007) -[2023-10-17 01:50:32,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 80379904. Throughput: 0: 1797.5, 1: 1754.4. Samples: 20110586. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:50:32,215][61453] Avg episode reward: [(0, '9.430'), (1, '9.080')] -[2023-10-17 01:50:32,276][62373] Updated weights for policy 0, policy_version 39400 (0.0009) -[2023-10-17 01:50:32,645][62373] Updated weights for policy 0, policy_version 39410 (0.0009) -[2023-10-17 01:50:33,021][62373] Updated weights for policy 0, policy_version 39420 (0.0007) -[2023-10-17 01:50:33,419][62408] Updated weights for policy 1, policy_version 39110 (0.0008) -[2023-10-17 01:50:33,800][62408] Updated weights for policy 1, policy_version 39120 (0.0011) -[2023-10-17 01:50:34,168][62408] Updated weights for policy 1, policy_version 39130 (0.0011) -[2023-10-17 01:50:36,706][62373] Updated weights for policy 0, policy_version 39430 (0.0008) -[2023-10-17 01:50:37,067][62373] Updated weights for policy 0, policy_version 39440 (0.0009) -[2023-10-17 01:50:37,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 80445440. Throughput: 0: 1771.4, 1: 1756.6. Samples: 20120054. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:50:37,214][61453] Avg episode reward: [(0, '9.380'), (1, '8.570')] -[2023-10-17 01:50:37,443][62373] Updated weights for policy 0, policy_version 39450 (0.0010) -[2023-10-17 01:50:37,994][62408] Updated weights for policy 1, policy_version 39140 (0.0008) -[2023-10-17 01:50:38,364][62408] Updated weights for policy 1, policy_version 39150 (0.0008) -[2023-10-17 01:50:38,735][62408] Updated weights for policy 1, policy_version 39160 (0.0008) -[2023-10-17 01:50:41,313][62373] Updated weights for policy 0, policy_version 39460 (0.0010) -[2023-10-17 01:50:41,684][62373] Updated weights for policy 0, policy_version 39470 (0.0008) -[2023-10-17 01:50:42,047][62373] Updated weights for policy 0, policy_version 39480 (0.0007) -[2023-10-17 01:50:42,214][61453] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 80510976. Throughput: 0: 1790.7, 1: 1757.2. Samples: 20141970. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:50:42,214][61453] Avg episode reward: [(0, '9.390'), (1, '9.140')] -[2023-10-17 01:50:42,426][62408] Updated weights for policy 1, policy_version 39170 (0.0007) -[2023-10-17 01:50:42,801][62408] Updated weights for policy 1, policy_version 39180 (0.0007) -[2023-10-17 01:50:43,165][62408] Updated weights for policy 1, policy_version 39190 (0.0007) -[2023-10-17 01:50:43,536][62408] Updated weights for policy 1, policy_version 39200 (0.0011) -[2023-10-17 01:50:45,839][62373] Updated weights for policy 0, policy_version 39490 (0.0008) -[2023-10-17 01:50:46,213][62373] Updated weights for policy 0, policy_version 39500 (0.0009) -[2023-10-17 01:50:46,578][62373] Updated weights for policy 0, policy_version 39510 (0.0009) -[2023-10-17 01:50:46,941][62373] Updated weights for policy 0, policy_version 39520 (0.0010) -[2023-10-17 01:50:47,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 80609280. Throughput: 0: 1769.1, 1: 1787.4. Samples: 20162750. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-17 01:50:47,215][61453] Avg episode reward: [(0, '9.150'), (1, '9.260')] -[2023-10-17 01:50:47,494][62408] Updated weights for policy 1, policy_version 39210 (0.0011) -[2023-10-17 01:50:47,868][62408] Updated weights for policy 1, policy_version 39220 (0.0009) -[2023-10-17 01:50:48,237][62408] Updated weights for policy 1, policy_version 39230 (0.0007) -[2023-10-17 01:50:50,658][62373] Updated weights for policy 0, policy_version 39530 (0.0009) -[2023-10-17 01:50:51,034][62373] Updated weights for policy 0, policy_version 39540 (0.0008) -[2023-10-17 01:50:51,410][62373] Updated weights for policy 0, policy_version 39550 (0.0007) -[2023-10-17 01:50:52,015][62408] Updated weights for policy 1, policy_version 39240 (0.0007) -[2023-10-17 01:50:52,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 80674816. Throughput: 0: 1783.7, 1: 1754.5. Samples: 20173638. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-17 01:50:52,215][61453] Avg episode reward: [(0, '9.070'), (1, '9.370')] -[2023-10-17 01:50:52,379][62408] Updated weights for policy 1, policy_version 39250 (0.0010) -[2023-10-17 01:50:52,753][62408] Updated weights for policy 1, policy_version 39260 (0.0008) -[2023-10-17 01:50:55,179][62373] Updated weights for policy 0, policy_version 39560 (0.0007) -[2023-10-17 01:50:55,544][62373] Updated weights for policy 0, policy_version 39570 (0.0008) -[2023-10-17 01:50:55,913][62373] Updated weights for policy 0, policy_version 39580 (0.0010) -[2023-10-17 01:50:56,578][62408] Updated weights for policy 1, policy_version 39270 (0.0008) -[2023-10-17 01:50:56,948][62408] Updated weights for policy 1, policy_version 39280 (0.0007) -[2023-10-17 01:50:57,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 80740352. Throughput: 0: 1774.8, 1: 1778.0. Samples: 20194844. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-17 01:50:57,215][61453] Avg episode reward: [(0, '9.250'), (1, '9.380')] -[2023-10-17 01:50:57,313][62408] Updated weights for policy 1, policy_version 39290 (0.0008) -[2023-10-17 01:50:59,785][62373] Updated weights for policy 0, policy_version 39590 (0.0009) -[2023-10-17 01:51:00,156][62373] Updated weights for policy 0, policy_version 39600 (0.0009) -[2023-10-17 01:51:00,531][62373] Updated weights for policy 0, policy_version 39610 (0.0009) -[2023-10-17 01:51:01,062][62408] Updated weights for policy 1, policy_version 39300 (0.0008) -[2023-10-17 01:51:01,439][62408] Updated weights for policy 1, policy_version 39310 (0.0008) -[2023-10-17 01:51:01,805][62408] Updated weights for policy 1, policy_version 39320 (0.0008) -[2023-10-17 01:51:02,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 80838656. Throughput: 0: 1771.4, 1: 1761.8. Samples: 20215718. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-17 01:51:02,215][61453] Avg episode reward: [(0, '9.250'), (1, '9.180')] -[2023-10-17 01:51:04,125][62373] Updated weights for policy 0, policy_version 39620 (0.0010) -[2023-10-17 01:51:04,501][62373] Updated weights for policy 0, policy_version 39630 (0.0010) -[2023-10-17 01:51:04,869][62373] Updated weights for policy 0, policy_version 39640 (0.0010) -[2023-10-17 01:51:05,714][62408] Updated weights for policy 1, policy_version 39330 (0.0007) -[2023-10-17 01:51:06,080][62408] Updated weights for policy 1, policy_version 39340 (0.0008) -[2023-10-17 01:51:06,443][62408] Updated weights for policy 1, policy_version 39350 (0.0007) -[2023-10-17 01:51:06,809][62408] Updated weights for policy 1, policy_version 39360 (0.0007) -[2023-10-17 01:51:07,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 80904192. Throughput: 0: 1784.7, 1: 1768.4. Samples: 20227068. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-17 01:51:07,215][61453] Avg episode reward: [(0, '9.290'), (1, '8.910')] -[2023-10-17 01:51:08,605][62373] Updated weights for policy 0, policy_version 39650 (0.0009) -[2023-10-17 01:51:08,968][62373] Updated weights for policy 0, policy_version 39660 (0.0007) -[2023-10-17 01:51:09,344][62373] Updated weights for policy 0, policy_version 39670 (0.0009) -[2023-10-17 01:51:09,711][62373] Updated weights for policy 0, policy_version 39680 (0.0008) -[2023-10-17 01:51:10,753][62408] Updated weights for policy 1, policy_version 39370 (0.0008) -[2023-10-17 01:51:11,121][62408] Updated weights for policy 1, policy_version 39380 (0.0009) -[2023-10-17 01:51:11,487][62408] Updated weights for policy 1, policy_version 39390 (0.0010) -[2023-10-17 01:51:12,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 80969728. Throughput: 0: 1781.1, 1: 1771.2. Samples: 20248430. Policy #0 lag: (min: 28.0, avg: 28.0, max: 28.0) -[2023-10-17 01:51:12,215][61453] Avg episode reward: [(0, '9.010'), (1, '9.430')] -[2023-10-17 01:51:13,520][62373] Updated weights for policy 0, policy_version 39690 (0.0007) -[2023-10-17 01:51:13,892][62373] Updated weights for policy 0, policy_version 39700 (0.0007) -[2023-10-17 01:51:14,266][62373] Updated weights for policy 0, policy_version 39710 (0.0009) -[2023-10-17 01:51:15,273][62408] Updated weights for policy 1, policy_version 39400 (0.0008) -[2023-10-17 01:51:15,643][62408] Updated weights for policy 1, policy_version 39410 (0.0008) -[2023-10-17 01:51:16,011][62408] Updated weights for policy 1, policy_version 39420 (0.0010) -[2023-10-17 01:51:17,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 81035264. Throughput: 0: 1784.0, 1: 1757.0. Samples: 20269934. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-17 01:51:17,215][61453] Avg episode reward: [(0, '8.660'), (1, '9.720')] -[2023-10-17 01:51:17,227][62252] Saving new best policy, reward=9.720! -[2023-10-17 01:51:18,107][62373] Updated weights for policy 0, policy_version 39720 (0.0009) -[2023-10-17 01:51:18,471][62373] Updated weights for policy 0, policy_version 39730 (0.0007) -[2023-10-17 01:51:18,846][62373] Updated weights for policy 0, policy_version 39740 (0.0011) -[2023-10-17 01:51:19,749][62408] Updated weights for policy 1, policy_version 39430 (0.0007) -[2023-10-17 01:51:20,141][62408] Updated weights for policy 1, policy_version 39440 (0.0008) -[2023-10-17 01:51:20,517][62408] Updated weights for policy 1, policy_version 39450 (0.0008) -[2023-10-17 01:51:22,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 81100800. Throughput: 0: 1783.5, 1: 1784.7. Samples: 20280620. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-17 01:51:22,215][61453] Avg episode reward: [(0, '8.140'), (1, '9.440')] -[2023-10-17 01:51:22,707][62373] Updated weights for policy 0, policy_version 39750 (0.0008) -[2023-10-17 01:51:23,069][62373] Updated weights for policy 0, policy_version 39760 (0.0009) -[2023-10-17 01:51:23,435][62373] Updated weights for policy 0, policy_version 39770 (0.0010) -[2023-10-17 01:51:24,403][62408] Updated weights for policy 1, policy_version 39460 (0.0010) -[2023-10-17 01:51:24,774][62408] Updated weights for policy 1, policy_version 39470 (0.0009) -[2023-10-17 01:51:25,139][62408] Updated weights for policy 1, policy_version 39480 (0.0008) -[2023-10-17 01:51:27,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 81166336. Throughput: 0: 1784.2, 1: 1760.0. Samples: 20301460. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-17 01:51:27,215][61453] Avg episode reward: [(0, '8.570'), (1, '9.360')] -[2023-10-17 01:51:27,369][62373] Updated weights for policy 0, policy_version 39780 (0.0009) -[2023-10-17 01:51:27,746][62373] Updated weights for policy 0, policy_version 39790 (0.0008) -[2023-10-17 01:51:28,113][62373] Updated weights for policy 0, policy_version 39800 (0.0008) -[2023-10-17 01:51:28,910][62408] Updated weights for policy 1, policy_version 39490 (0.0009) -[2023-10-17 01:51:29,268][62408] Updated weights for policy 1, policy_version 39500 (0.0009) -[2023-10-17 01:51:29,637][62408] Updated weights for policy 1, policy_version 39510 (0.0010) -[2023-10-17 01:51:30,005][62408] Updated weights for policy 1, policy_version 39520 (0.0010) -[2023-10-17 01:51:32,012][62373] Updated weights for policy 0, policy_version 39810 (0.0009) -[2023-10-17 01:51:32,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 81231872. Throughput: 0: 1814.2, 1: 1756.0. Samples: 20323410. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-17 01:51:32,215][61453] Avg episode reward: [(0, '8.440'), (1, '9.660')] -[2023-10-17 01:51:32,225][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000039520_40468480.pth... -[2023-10-17 01:51:32,260][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000037888_38797312.pth -[2023-10-17 01:51:32,387][62373] Updated weights for policy 0, policy_version 39820 (0.0011) -[2023-10-17 01:51:32,750][62373] Updated weights for policy 0, policy_version 39830 (0.0010) -[2023-10-17 01:51:33,118][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000039840_40796160.pth... -[2023-10-17 01:51:33,120][62373] Updated weights for policy 0, policy_version 39840 (0.0008) -[2023-10-17 01:51:33,150][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000038176_39092224.pth -[2023-10-17 01:51:33,808][62408] Updated weights for policy 1, policy_version 39530 (0.0008) -[2023-10-17 01:51:34,169][62408] Updated weights for policy 1, policy_version 39540 (0.0008) -[2023-10-17 01:51:34,542][62408] Updated weights for policy 1, policy_version 39550 (0.0011) -[2023-10-17 01:51:36,923][62373] Updated weights for policy 0, policy_version 39850 (0.0008) -[2023-10-17 01:51:37,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 81297408. Throughput: 0: 1782.7, 1: 1759.0. Samples: 20333016. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-17 01:51:37,214][61453] Avg episode reward: [(0, '8.350'), (1, '10.250')] -[2023-10-17 01:51:37,215][62252] Saving new best policy, reward=10.250! -[2023-10-17 01:51:37,296][62373] Updated weights for policy 0, policy_version 39860 (0.0008) -[2023-10-17 01:51:37,670][62373] Updated weights for policy 0, policy_version 39870 (0.0008) -[2023-10-17 01:51:38,534][62408] Updated weights for policy 1, policy_version 39560 (0.0008) -[2023-10-17 01:51:38,902][62408] Updated weights for policy 1, policy_version 39570 (0.0010) -[2023-10-17 01:51:39,271][62408] Updated weights for policy 1, policy_version 39580 (0.0010) -[2023-10-17 01:51:41,447][62373] Updated weights for policy 0, policy_version 39880 (0.0009) -[2023-10-17 01:51:41,823][62373] Updated weights for policy 0, policy_version 39890 (0.0009) -[2023-10-17 01:51:42,180][62373] Updated weights for policy 0, policy_version 39900 (0.0009) -[2023-10-17 01:51:42,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 81362944. Throughput: 0: 1805.1, 1: 1755.2. Samples: 20355058. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-17 01:51:42,215][61453] Avg episode reward: [(0, '8.460'), (1, '9.430')] -[2023-10-17 01:51:43,086][62408] Updated weights for policy 1, policy_version 39590 (0.0009) -[2023-10-17 01:51:43,454][62408] Updated weights for policy 1, policy_version 39600 (0.0010) -[2023-10-17 01:51:43,830][62408] Updated weights for policy 1, policy_version 39610 (0.0010) -[2023-10-17 01:51:45,908][62373] Updated weights for policy 0, policy_version 39910 (0.0008) -[2023-10-17 01:51:46,283][62373] Updated weights for policy 0, policy_version 39920 (0.0009) -[2023-10-17 01:51:46,649][62373] Updated weights for policy 0, policy_version 39930 (0.0009) -[2023-10-17 01:51:47,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 81461248. Throughput: 0: 1775.2, 1: 1781.2. Samples: 20375754. Policy #0 lag: (min: 3.0, avg: 4.5, max: 30.0) -[2023-10-17 01:51:47,214][61453] Avg episode reward: [(0, '8.540'), (1, '9.270')] -[2023-10-17 01:51:47,735][62408] Updated weights for policy 1, policy_version 39620 (0.0008) -[2023-10-17 01:51:48,110][62408] Updated weights for policy 1, policy_version 39630 (0.0009) -[2023-10-17 01:51:48,488][62408] Updated weights for policy 1, policy_version 39640 (0.0008) -[2023-10-17 01:51:50,310][62373] Updated weights for policy 0, policy_version 39940 (0.0007) -[2023-10-17 01:51:50,681][62373] Updated weights for policy 0, policy_version 39950 (0.0010) -[2023-10-17 01:51:51,043][62373] Updated weights for policy 0, policy_version 39960 (0.0010) -[2023-10-17 01:51:52,067][62408] Updated weights for policy 1, policy_version 39650 (0.0011) -[2023-10-17 01:51:52,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 81526784. Throughput: 0: 1797.2, 1: 1754.5. Samples: 20386896. Policy #0 lag: (min: 3.0, avg: 4.5, max: 30.0) -[2023-10-17 01:51:52,215][61453] Avg episode reward: [(0, '8.360'), (1, '9.200')] -[2023-10-17 01:51:52,437][62408] Updated weights for policy 1, policy_version 39660 (0.0007) -[2023-10-17 01:51:52,802][62408] Updated weights for policy 1, policy_version 39670 (0.0007) -[2023-10-17 01:51:53,170][62408] Updated weights for policy 1, policy_version 39680 (0.0008) -[2023-10-17 01:51:54,788][62373] Updated weights for policy 0, policy_version 39970 (0.0007) -[2023-10-17 01:51:55,162][62373] Updated weights for policy 0, policy_version 39980 (0.0010) -[2023-10-17 01:51:55,516][62373] Updated weights for policy 0, policy_version 39990 (0.0010) -[2023-10-17 01:51:55,881][62373] Updated weights for policy 0, policy_version 40000 (0.0011) -[2023-10-17 01:51:56,804][62408] Updated weights for policy 1, policy_version 39690 (0.0008) -[2023-10-17 01:51:57,175][62408] Updated weights for policy 1, policy_version 39700 (0.0008) -[2023-10-17 01:51:57,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 81592320. Throughput: 0: 1769.4, 1: 1775.0. Samples: 20407928. Policy #0 lag: (min: 3.0, avg: 4.5, max: 30.0) -[2023-10-17 01:51:57,215][61453] Avg episode reward: [(0, '8.020'), (1, '9.080')] -[2023-10-17 01:51:57,536][62408] Updated weights for policy 1, policy_version 39710 (0.0008) -[2023-10-17 01:51:59,899][62373] Updated weights for policy 0, policy_version 40010 (0.0008) -[2023-10-17 01:52:00,278][62373] Updated weights for policy 0, policy_version 40020 (0.0008) -[2023-10-17 01:52:00,651][62373] Updated weights for policy 0, policy_version 40030 (0.0008) -[2023-10-17 01:52:01,405][62408] Updated weights for policy 1, policy_version 39720 (0.0008) -[2023-10-17 01:52:01,776][62408] Updated weights for policy 1, policy_version 39730 (0.0009) -[2023-10-17 01:52:02,153][62408] Updated weights for policy 1, policy_version 39740 (0.0008) -[2023-10-17 01:52:02,214][61453] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 81657856. Throughput: 0: 1761.6, 1: 1774.6. Samples: 20429062. Policy #0 lag: (min: 3.0, avg: 4.5, max: 30.0) -[2023-10-17 01:52:02,214][61453] Avg episode reward: [(0, '8.490'), (1, '9.360')] -[2023-10-17 01:52:04,418][62373] Updated weights for policy 0, policy_version 40040 (0.0008) -[2023-10-17 01:52:04,793][62373] Updated weights for policy 0, policy_version 40050 (0.0007) -[2023-10-17 01:52:05,174][62373] Updated weights for policy 0, policy_version 40060 (0.0007) -[2023-10-17 01:52:05,839][62408] Updated weights for policy 1, policy_version 39750 (0.0010) -[2023-10-17 01:52:06,224][62408] Updated weights for policy 1, policy_version 39760 (0.0008) -[2023-10-17 01:52:06,597][62408] Updated weights for policy 1, policy_version 39770 (0.0008) -[2023-10-17 01:52:07,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 81756160. Throughput: 0: 1770.7, 1: 1772.0. Samples: 20440042. Policy #0 lag: (min: 3.0, avg: 4.5, max: 30.0) -[2023-10-17 01:52:07,215][61453] Avg episode reward: [(0, '8.000'), (1, '8.790')] -[2023-10-17 01:52:09,128][62373] Updated weights for policy 0, policy_version 40070 (0.0009) -[2023-10-17 01:52:09,504][62373] Updated weights for policy 0, policy_version 40080 (0.0009) -[2023-10-17 01:52:09,879][62373] Updated weights for policy 0, policy_version 40090 (0.0007) -[2023-10-17 01:52:10,407][62408] Updated weights for policy 1, policy_version 39780 (0.0010) -[2023-10-17 01:52:10,775][62408] Updated weights for policy 1, policy_version 39790 (0.0010) -[2023-10-17 01:52:11,150][62408] Updated weights for policy 1, policy_version 39800 (0.0011) -[2023-10-17 01:52:12,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 81821696. Throughput: 0: 1753.2, 1: 1783.1. Samples: 20460594. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:52:12,215][61453] Avg episode reward: [(0, '8.250'), (1, '8.410')] -[2023-10-17 01:52:13,737][62373] Updated weights for policy 0, policy_version 40100 (0.0008) -[2023-10-17 01:52:14,110][62373] Updated weights for policy 0, policy_version 40110 (0.0007) -[2023-10-17 01:52:14,481][62373] Updated weights for policy 0, policy_version 40120 (0.0007) -[2023-10-17 01:52:15,064][62408] Updated weights for policy 1, policy_version 39810 (0.0010) -[2023-10-17 01:52:15,429][62408] Updated weights for policy 1, policy_version 39820 (0.0010) -[2023-10-17 01:52:15,800][62408] Updated weights for policy 1, policy_version 39830 (0.0011) -[2023-10-17 01:52:16,168][62408] Updated weights for policy 1, policy_version 39840 (0.0009) -[2023-10-17 01:52:17,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 81887232. Throughput: 0: 1760.3, 1: 1767.1. Samples: 20482144. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:52:17,214][61453] Avg episode reward: [(0, '8.470'), (1, '8.480')] -[2023-10-17 01:52:18,105][62373] Updated weights for policy 0, policy_version 40130 (0.0008) -[2023-10-17 01:52:18,470][62373] Updated weights for policy 0, policy_version 40140 (0.0010) -[2023-10-17 01:52:18,842][62373] Updated weights for policy 0, policy_version 40150 (0.0008) -[2023-10-17 01:52:19,213][62373] Updated weights for policy 0, policy_version 40160 (0.0008) -[2023-10-17 01:52:20,082][62408] Updated weights for policy 1, policy_version 39850 (0.0009) -[2023-10-17 01:52:20,455][62408] Updated weights for policy 1, policy_version 39860 (0.0009) -[2023-10-17 01:52:20,823][62408] Updated weights for policy 1, policy_version 39870 (0.0010) -[2023-10-17 01:52:22,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 81952768. Throughput: 0: 1760.5, 1: 1792.2. Samples: 20492888. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:52:22,214][61453] Avg episode reward: [(0, '8.460'), (1, '9.200')] -[2023-10-17 01:52:22,945][62373] Updated weights for policy 0, policy_version 40170 (0.0008) -[2023-10-17 01:52:23,320][62373] Updated weights for policy 0, policy_version 40180 (0.0008) -[2023-10-17 01:52:23,694][62373] Updated weights for policy 0, policy_version 40190 (0.0008) -[2023-10-17 01:52:24,730][62408] Updated weights for policy 1, policy_version 39880 (0.0010) -[2023-10-17 01:52:25,102][62408] Updated weights for policy 1, policy_version 39890 (0.0008) -[2023-10-17 01:52:25,465][62408] Updated weights for policy 1, policy_version 39900 (0.0010) -[2023-10-17 01:52:27,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 82018304. Throughput: 0: 1764.6, 1: 1767.7. Samples: 20514008. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:52:27,214][61453] Avg episode reward: [(0, '8.990'), (1, '9.450')] -[2023-10-17 01:52:27,350][62373] Updated weights for policy 0, policy_version 40200 (0.0008) -[2023-10-17 01:52:27,727][62373] Updated weights for policy 0, policy_version 40210 (0.0009) -[2023-10-17 01:52:28,099][62373] Updated weights for policy 0, policy_version 40220 (0.0007) -[2023-10-17 01:52:29,282][62408] Updated weights for policy 1, policy_version 39910 (0.0009) -[2023-10-17 01:52:29,650][62408] Updated weights for policy 1, policy_version 39920 (0.0007) -[2023-10-17 01:52:30,024][62408] Updated weights for policy 1, policy_version 39930 (0.0008) -[2023-10-17 01:52:32,025][62373] Updated weights for policy 0, policy_version 40230 (0.0009) -[2023-10-17 01:52:32,214][61453] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 82083840. Throughput: 0: 1793.1, 1: 1769.2. Samples: 20536060. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:52:32,215][61453] Avg episode reward: [(0, '8.590'), (1, '8.320')] -[2023-10-17 01:52:32,392][62373] Updated weights for policy 0, policy_version 40240 (0.0011) -[2023-10-17 01:52:32,759][62373] Updated weights for policy 0, policy_version 40250 (0.0009) -[2023-10-17 01:52:33,832][62408] Updated weights for policy 1, policy_version 39940 (0.0007) -[2023-10-17 01:52:34,191][62408] Updated weights for policy 1, policy_version 39950 (0.0009) -[2023-10-17 01:52:34,557][62408] Updated weights for policy 1, policy_version 39960 (0.0008) -[2023-10-17 01:52:36,394][62373] Updated weights for policy 0, policy_version 40260 (0.0009) -[2023-10-17 01:52:36,768][62373] Updated weights for policy 0, policy_version 40270 (0.0010) -[2023-10-17 01:52:37,141][62373] Updated weights for policy 0, policy_version 40280 (0.0008) -[2023-10-17 01:52:37,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 82149376. Throughput: 0: 1761.0, 1: 1775.3. Samples: 20546030. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:52:37,215][61453] Avg episode reward: [(0, '8.860'), (1, '9.190')] -[2023-10-17 01:52:38,559][62408] Updated weights for policy 1, policy_version 39970 (0.0008) -[2023-10-17 01:52:38,934][62408] Updated weights for policy 1, policy_version 39980 (0.0009) -[2023-10-17 01:52:39,300][62408] Updated weights for policy 1, policy_version 39990 (0.0010) -[2023-10-17 01:52:39,666][62408] Updated weights for policy 1, policy_version 40000 (0.0007) -[2023-10-17 01:52:40,883][62373] Updated weights for policy 0, policy_version 40290 (0.0009) -[2023-10-17 01:52:41,260][62373] Updated weights for policy 0, policy_version 40300 (0.0009) -[2023-10-17 01:52:41,626][62373] Updated weights for policy 0, policy_version 40310 (0.0007) -[2023-10-17 01:52:41,996][62373] Updated weights for policy 0, policy_version 40320 (0.0007) -[2023-10-17 01:52:42,214][61453] Fps is (10 sec: 16384.8, 60 sec: 14745.7, 300 sec: 14106.9). Total num frames: 82247680. Throughput: 0: 1790.8, 1: 1761.8. Samples: 20567792. Policy #0 lag: (min: 2.0, avg: 8.7, max: 34.0) -[2023-10-17 01:52:42,214][61453] Avg episode reward: [(0, '9.490'), (1, '8.880')] -[2023-10-17 01:52:43,456][62408] Updated weights for policy 1, policy_version 40010 (0.0008) -[2023-10-17 01:52:43,833][62408] Updated weights for policy 1, policy_version 40020 (0.0007) -[2023-10-17 01:52:44,199][62408] Updated weights for policy 1, policy_version 40030 (0.0009) -[2023-10-17 01:52:45,835][62373] Updated weights for policy 0, policy_version 40330 (0.0009) -[2023-10-17 01:52:46,208][62373] Updated weights for policy 0, policy_version 40340 (0.0008) -[2023-10-17 01:52:46,582][62373] Updated weights for policy 0, policy_version 40350 (0.0007) -[2023-10-17 01:52:47,214][61453] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 82313216. Throughput: 0: 1766.6, 1: 1782.8. Samples: 20588782. Policy #0 lag: (min: 2.0, avg: 8.7, max: 34.0) -[2023-10-17 01:52:47,214][61453] Avg episode reward: [(0, '10.450'), (1, '8.770')] -[2023-10-17 01:52:47,935][62408] Updated weights for policy 1, policy_version 40040 (0.0008) -[2023-10-17 01:52:48,311][62408] Updated weights for policy 1, policy_version 40050 (0.0011) -[2023-10-17 01:52:48,682][62408] Updated weights for policy 1, policy_version 40060 (0.0009) -[2023-10-17 01:52:50,420][62373] Updated weights for policy 0, policy_version 40360 (0.0010) -[2023-10-17 01:52:50,790][62373] Updated weights for policy 0, policy_version 40370 (0.0010) -[2023-10-17 01:52:51,156][62373] Updated weights for policy 0, policy_version 40380 (0.0010) -[2023-10-17 01:52:52,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 82378752. Throughput: 0: 1790.6, 1: 1760.5. Samples: 20599840. Policy #0 lag: (min: 2.0, avg: 8.7, max: 34.0) -[2023-10-17 01:52:52,215][61453] Avg episode reward: [(0, '10.410'), (1, '8.340')] -[2023-10-17 01:52:52,536][62408] Updated weights for policy 1, policy_version 40070 (0.0008) -[2023-10-17 01:52:52,913][62408] Updated weights for policy 1, policy_version 40080 (0.0008) -[2023-10-17 01:52:53,285][62408] Updated weights for policy 1, policy_version 40090 (0.0008) -[2023-10-17 01:52:55,008][62373] Updated weights for policy 0, policy_version 40390 (0.0009) -[2023-10-17 01:52:55,381][62373] Updated weights for policy 0, policy_version 40400 (0.0007) -[2023-10-17 01:52:55,748][62373] Updated weights for policy 0, policy_version 40410 (0.0008) -[2023-10-17 01:52:57,065][62408] Updated weights for policy 1, policy_version 40100 (0.0007) -[2023-10-17 01:52:57,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 82444288. Throughput: 0: 1780.9, 1: 1771.5. Samples: 20620450. Policy #0 lag: (min: 2.0, avg: 8.7, max: 34.0) -[2023-10-17 01:52:57,214][61453] Avg episode reward: [(0, '10.110'), (1, '8.350')] -[2023-10-17 01:52:57,437][62408] Updated weights for policy 1, policy_version 40110 (0.0007) -[2023-10-17 01:52:57,804][62408] Updated weights for policy 1, policy_version 40120 (0.0007) -[2023-10-17 01:52:59,397][62373] Updated weights for policy 0, policy_version 40420 (0.0009) -[2023-10-17 01:52:59,776][62373] Updated weights for policy 0, policy_version 40430 (0.0010) -[2023-10-17 01:53:00,137][62373] Updated weights for policy 0, policy_version 40440 (0.0008) -[2023-10-17 01:53:01,740][62408] Updated weights for policy 1, policy_version 40130 (0.0008) -[2023-10-17 01:53:02,112][62408] Updated weights for policy 1, policy_version 40140 (0.0008) -[2023-10-17 01:53:02,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 82509824. Throughput: 0: 1779.9, 1: 1778.3. Samples: 20642264. Policy #0 lag: (min: 2.0, avg: 8.7, max: 34.0) -[2023-10-17 01:53:02,215][61453] Avg episode reward: [(0, '9.750'), (1, '8.720')] -[2023-10-17 01:53:02,476][62408] Updated weights for policy 1, policy_version 40150 (0.0008) -[2023-10-17 01:53:02,845][62408] Updated weights for policy 1, policy_version 40160 (0.0009) -[2023-10-17 01:53:03,903][62373] Updated weights for policy 0, policy_version 40450 (0.0008) -[2023-10-17 01:53:04,280][62373] Updated weights for policy 0, policy_version 40460 (0.0010) -[2023-10-17 01:53:04,656][62373] Updated weights for policy 0, policy_version 40470 (0.0008) -[2023-10-17 01:53:05,022][62373] Updated weights for policy 0, policy_version 40480 (0.0007) -[2023-10-17 01:53:06,734][62408] Updated weights for policy 1, policy_version 40170 (0.0008) -[2023-10-17 01:53:07,106][62408] Updated weights for policy 1, policy_version 40180 (0.0008) -[2023-10-17 01:53:07,214][61453] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 82575360. Throughput: 0: 1785.6, 1: 1759.5. Samples: 20652420. Policy #0 lag: (min: 17.0, avg: 28.1, max: 49.0) -[2023-10-17 01:53:07,214][61453] Avg episode reward: [(0, '10.120'), (1, '8.620')] -[2023-10-17 01:53:07,467][62408] Updated weights for policy 1, policy_version 40190 (0.0007) -[2023-10-17 01:53:08,745][62373] Updated weights for policy 0, policy_version 40490 (0.0008) -[2023-10-17 01:53:09,109][62373] Updated weights for policy 0, policy_version 40500 (0.0009) -[2023-10-17 01:53:09,477][62373] Updated weights for policy 0, policy_version 40510 (0.0008) -[2023-10-17 01:53:11,296][62408] Updated weights for policy 1, policy_version 40200 (0.0011) -[2023-10-17 01:53:11,677][62408] Updated weights for policy 1, policy_version 40210 (0.0010) -[2023-10-17 01:53:12,048][62408] Updated weights for policy 1, policy_version 40220 (0.0008) -[2023-10-17 01:53:12,214][61453] Fps is (10 sec: 16384.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 82673664. Throughput: 0: 1782.1, 1: 1785.6. Samples: 20674552. Policy #0 lag: (min: 17.0, avg: 28.1, max: 49.0) -[2023-10-17 01:53:12,214][61453] Avg episode reward: [(0, '10.510'), (1, '8.280')] -[2023-10-17 01:53:13,221][62373] Updated weights for policy 0, policy_version 40520 (0.0010) -[2023-10-17 01:53:13,592][62373] Updated weights for policy 0, policy_version 40530 (0.0011) -[2023-10-17 01:53:13,971][62373] Updated weights for policy 0, policy_version 40540 (0.0009) -[2023-10-17 01:53:15,911][62408] Updated weights for policy 1, policy_version 40230 (0.0007) -[2023-10-17 01:53:16,279][62408] Updated weights for policy 1, policy_version 40240 (0.0007) -[2023-10-17 01:53:16,643][62408] Updated weights for policy 1, policy_version 40250 (0.0009) -[2023-10-17 01:53:17,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 82739200. Throughput: 0: 1786.8, 1: 1751.3. Samples: 20695274. Policy #0 lag: (min: 17.0, avg: 28.1, max: 49.0) -[2023-10-17 01:53:17,214][61453] Avg episode reward: [(0, '9.800'), (1, '8.970')] -[2023-10-17 01:53:17,826][62373] Updated weights for policy 0, policy_version 40550 (0.0009) -[2023-10-17 01:53:18,202][62373] Updated weights for policy 0, policy_version 40560 (0.0009) -[2023-10-17 01:53:18,582][62373] Updated weights for policy 0, policy_version 40570 (0.0008) -[2023-10-17 01:53:20,273][62408] Updated weights for policy 1, policy_version 40260 (0.0011) -[2023-10-17 01:53:20,632][62408] Updated weights for policy 1, policy_version 40270 (0.0010) -[2023-10-17 01:53:20,992][62408] Updated weights for policy 1, policy_version 40280 (0.0008) -[2023-10-17 01:53:22,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 82804736. Throughput: 0: 1783.3, 1: 1778.6. Samples: 20706314. Policy #0 lag: (min: 17.0, avg: 28.1, max: 49.0) -[2023-10-17 01:53:22,214][61453] Avg episode reward: [(0, '9.410'), (1, '8.960')] -[2023-10-17 01:53:22,241][62373] Updated weights for policy 0, policy_version 40580 (0.0011) -[2023-10-17 01:53:22,618][62373] Updated weights for policy 0, policy_version 40590 (0.0008) -[2023-10-17 01:53:22,989][62373] Updated weights for policy 0, policy_version 40600 (0.0009) -[2023-10-17 01:53:24,673][62408] Updated weights for policy 1, policy_version 40290 (0.0007) -[2023-10-17 01:53:25,039][62408] Updated weights for policy 1, policy_version 40300 (0.0008) -[2023-10-17 01:53:25,401][62408] Updated weights for policy 1, policy_version 40310 (0.0008) -[2023-10-17 01:53:25,774][62408] Updated weights for policy 1, policy_version 40320 (0.0009) -[2023-10-17 01:53:26,680][62373] Updated weights for policy 0, policy_version 40610 (0.0009) -[2023-10-17 01:53:27,052][62373] Updated weights for policy 0, policy_version 40620 (0.0008) -[2023-10-17 01:53:27,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 82870272. Throughput: 0: 1790.9, 1: 1758.0. Samples: 20727494. Policy #0 lag: (min: 17.0, avg: 28.1, max: 49.0) -[2023-10-17 01:53:27,214][61453] Avg episode reward: [(0, '9.350'), (1, '9.340')] -[2023-10-17 01:53:27,421][62373] Updated weights for policy 0, policy_version 40630 (0.0007) -[2023-10-17 01:53:27,793][62373] Updated weights for policy 0, policy_version 40640 (0.0007) -[2023-10-17 01:53:29,504][62408] Updated weights for policy 1, policy_version 40330 (0.0010) -[2023-10-17 01:53:29,878][62408] Updated weights for policy 1, policy_version 40340 (0.0011) -[2023-10-17 01:53:30,249][62408] Updated weights for policy 1, policy_version 40350 (0.0011) -[2023-10-17 01:53:31,649][62373] Updated weights for policy 0, policy_version 40650 (0.0008) -[2023-10-17 01:53:32,011][62373] Updated weights for policy 0, policy_version 40660 (0.0008) -[2023-10-17 01:53:32,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.6, 300 sec: 14218.0). Total num frames: 82935808. Throughput: 0: 1798.6, 1: 1753.2. Samples: 20748616. Policy #0 lag: (min: 17.0, avg: 28.1, max: 49.0) -[2023-10-17 01:53:32,214][61453] Avg episode reward: [(0, '9.300'), (1, '8.850')] -[2023-10-17 01:53:32,225][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000040352_41320448.pth... -[2023-10-17 01:53:32,256][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000038688_39616512.pth -[2023-10-17 01:53:32,387][62373] Updated weights for policy 0, policy_version 40670 (0.0008) -[2023-10-17 01:53:32,457][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000040672_41648128.pth... -[2023-10-17 01:53:32,496][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000039008_39944192.pth -[2023-10-17 01:53:34,078][62408] Updated weights for policy 1, policy_version 40360 (0.0010) -[2023-10-17 01:53:34,439][62408] Updated weights for policy 1, policy_version 40370 (0.0010) -[2023-10-17 01:53:34,812][62408] Updated weights for policy 1, policy_version 40380 (0.0010) -[2023-10-17 01:53:36,014][62373] Updated weights for policy 0, policy_version 40680 (0.0010) -[2023-10-17 01:53:36,382][62373] Updated weights for policy 0, policy_version 40690 (0.0010) -[2023-10-17 01:53:36,756][62373] Updated weights for policy 0, policy_version 40700 (0.0011) -[2023-10-17 01:53:37,214][61453] Fps is (10 sec: 16383.5, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 83034112. Throughput: 0: 1785.9, 1: 1756.5. Samples: 20759248. Policy #0 lag: (min: 18.0, avg: 24.6, max: 50.0) -[2023-10-17 01:53:37,215][61453] Avg episode reward: [(0, '9.940'), (1, '8.750')] -[2023-10-17 01:53:38,782][62408] Updated weights for policy 1, policy_version 40390 (0.0011) -[2023-10-17 01:53:39,144][62408] Updated weights for policy 1, policy_version 40400 (0.0009) -[2023-10-17 01:53:39,509][62408] Updated weights for policy 1, policy_version 40410 (0.0007) -[2023-10-17 01:53:40,661][62373] Updated weights for policy 0, policy_version 40710 (0.0008) -[2023-10-17 01:53:41,036][62373] Updated weights for policy 0, policy_version 40720 (0.0008) -[2023-10-17 01:53:41,407][62373] Updated weights for policy 0, policy_version 40730 (0.0008) -[2023-10-17 01:53:42,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 83099648. Throughput: 0: 1797.9, 1: 1755.1. Samples: 20780336. Policy #0 lag: (min: 18.0, avg: 24.6, max: 50.0) -[2023-10-17 01:53:42,215][61453] Avg episode reward: [(0, '9.420'), (1, '9.120')] -[2023-10-17 01:53:43,367][62408] Updated weights for policy 1, policy_version 40420 (0.0008) -[2023-10-17 01:53:43,760][62408] Updated weights for policy 1, policy_version 40430 (0.0007) -[2023-10-17 01:53:44,131][62408] Updated weights for policy 1, policy_version 40440 (0.0008) -[2023-10-17 01:53:45,183][62373] Updated weights for policy 0, policy_version 40740 (0.0009) -[2023-10-17 01:53:45,553][62373] Updated weights for policy 0, policy_version 40750 (0.0008) -[2023-10-17 01:53:45,922][62373] Updated weights for policy 0, policy_version 40760 (0.0007) -[2023-10-17 01:53:47,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 83165184. Throughput: 0: 1782.0, 1: 1762.2. Samples: 20801754. Policy #0 lag: (min: 18.0, avg: 24.6, max: 50.0) -[2023-10-17 01:53:47,215][61453] Avg episode reward: [(0, '9.090'), (1, '9.030')] -[2023-10-17 01:53:48,067][62408] Updated weights for policy 1, policy_version 40450 (0.0008) -[2023-10-17 01:53:48,430][62408] Updated weights for policy 1, policy_version 40460 (0.0007) -[2023-10-17 01:53:48,806][62408] Updated weights for policy 1, policy_version 40470 (0.0009) -[2023-10-17 01:53:49,173][62408] Updated weights for policy 1, policy_version 40480 (0.0009) -[2023-10-17 01:53:49,690][62373] Updated weights for policy 0, policy_version 40770 (0.0007) -[2023-10-17 01:53:50,065][62373] Updated weights for policy 0, policy_version 40780 (0.0008) -[2023-10-17 01:53:50,427][62373] Updated weights for policy 0, policy_version 40790 (0.0007) -[2023-10-17 01:53:50,800][62373] Updated weights for policy 0, policy_version 40800 (0.0009) -[2023-10-17 01:53:52,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 83230720. Throughput: 0: 1800.3, 1: 1753.9. Samples: 20812358. Policy #0 lag: (min: 18.0, avg: 24.6, max: 50.0) -[2023-10-17 01:53:52,215][61453] Avg episode reward: [(0, '9.470'), (1, '9.190')] -[2023-10-17 01:53:52,858][62408] Updated weights for policy 1, policy_version 40490 (0.0007) -[2023-10-17 01:53:53,226][62408] Updated weights for policy 1, policy_version 40500 (0.0008) -[2023-10-17 01:53:53,598][62408] Updated weights for policy 1, policy_version 40510 (0.0008) -[2023-10-17 01:53:54,698][62373] Updated weights for policy 0, policy_version 40810 (0.0007) -[2023-10-17 01:53:55,068][62373] Updated weights for policy 0, policy_version 40820 (0.0007) -[2023-10-17 01:53:55,441][62373] Updated weights for policy 0, policy_version 40830 (0.0009) -[2023-10-17 01:53:57,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 83296256. Throughput: 0: 1772.5, 1: 1757.1. Samples: 20833386. Policy #0 lag: (min: 18.0, avg: 24.6, max: 50.0) -[2023-10-17 01:53:57,214][61453] Avg episode reward: [(0, '10.260'), (1, '8.740')] -[2023-10-17 01:53:57,474][62408] Updated weights for policy 1, policy_version 40520 (0.0009) -[2023-10-17 01:53:57,836][62408] Updated weights for policy 1, policy_version 40530 (0.0007) -[2023-10-17 01:53:58,204][62408] Updated weights for policy 1, policy_version 40540 (0.0010) -[2023-10-17 01:53:59,185][62373] Updated weights for policy 0, policy_version 40840 (0.0011) -[2023-10-17 01:53:59,554][62373] Updated weights for policy 0, policy_version 40850 (0.0007) -[2023-10-17 01:53:59,919][62373] Updated weights for policy 0, policy_version 40860 (0.0007) -[2023-10-17 01:54:02,043][62408] Updated weights for policy 1, policy_version 40550 (0.0007) -[2023-10-17 01:54:02,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 83361792. Throughput: 0: 1772.0, 1: 1788.0. Samples: 20855472. Policy #0 lag: (min: 0.0, avg: 21.5, max: 32.0) -[2023-10-17 01:54:02,215][61453] Avg episode reward: [(0, '9.950'), (1, '9.080')] -[2023-10-17 01:54:02,415][62408] Updated weights for policy 1, policy_version 40560 (0.0008) -[2023-10-17 01:54:02,784][62408] Updated weights for policy 1, policy_version 40570 (0.0008) -[2023-10-17 01:54:03,846][62373] Updated weights for policy 0, policy_version 40870 (0.0008) -[2023-10-17 01:54:04,208][62373] Updated weights for policy 0, policy_version 40880 (0.0008) -[2023-10-17 01:54:04,589][62373] Updated weights for policy 0, policy_version 40890 (0.0009) -[2023-10-17 01:54:06,474][62408] Updated weights for policy 1, policy_version 40580 (0.0008) -[2023-10-17 01:54:06,845][62408] Updated weights for policy 1, policy_version 40590 (0.0008) -[2023-10-17 01:54:07,210][62408] Updated weights for policy 1, policy_version 40600 (0.0008) -[2023-10-17 01:54:07,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 83427328. Throughput: 0: 1771.4, 1: 1759.5. Samples: 20865204. Policy #0 lag: (min: 0.0, avg: 21.5, max: 32.0) -[2023-10-17 01:54:07,215][61453] Avg episode reward: [(0, '9.450'), (1, '9.390')] -[2023-10-17 01:54:08,417][62373] Updated weights for policy 0, policy_version 40900 (0.0007) -[2023-10-17 01:54:08,790][62373] Updated weights for policy 0, policy_version 40910 (0.0008) -[2023-10-17 01:54:09,153][62373] Updated weights for policy 0, policy_version 40920 (0.0008) -[2023-10-17 01:54:11,107][62408] Updated weights for policy 1, policy_version 40610 (0.0009) -[2023-10-17 01:54:11,482][62408] Updated weights for policy 1, policy_version 40620 (0.0007) -[2023-10-17 01:54:11,847][62408] Updated weights for policy 1, policy_version 40630 (0.0008) -[2023-10-17 01:54:12,214][61453] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 83492864. Throughput: 0: 1761.0, 1: 1786.3. Samples: 20887120. Policy #0 lag: (min: 0.0, avg: 21.5, max: 32.0) -[2023-10-17 01:54:12,214][61453] Avg episode reward: [(0, '9.000'), (1, '9.000')] -[2023-10-17 01:54:12,224][62408] Updated weights for policy 1, policy_version 40640 (0.0007) -[2023-10-17 01:54:13,021][62373] Updated weights for policy 0, policy_version 40930 (0.0009) -[2023-10-17 01:54:13,394][62373] Updated weights for policy 0, policy_version 40940 (0.0009) -[2023-10-17 01:54:13,764][62373] Updated weights for policy 0, policy_version 40950 (0.0007) -[2023-10-17 01:54:14,130][62373] Updated weights for policy 0, policy_version 40960 (0.0010) -[2023-10-17 01:54:15,899][62408] Updated weights for policy 1, policy_version 40650 (0.0007) -[2023-10-17 01:54:16,265][62408] Updated weights for policy 1, policy_version 40660 (0.0010) -[2023-10-17 01:54:16,627][62408] Updated weights for policy 1, policy_version 40670 (0.0008) -[2023-10-17 01:54:17,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 83591168. Throughput: 0: 1778.4, 1: 1761.8. Samples: 20907926. Policy #0 lag: (min: 0.0, avg: 21.5, max: 32.0) -[2023-10-17 01:54:17,215][61453] Avg episode reward: [(0, '9.290'), (1, '9.070')] -[2023-10-17 01:54:18,048][62373] Updated weights for policy 0, policy_version 40970 (0.0007) -[2023-10-17 01:54:18,416][62373] Updated weights for policy 0, policy_version 40980 (0.0007) -[2023-10-17 01:54:18,781][62373] Updated weights for policy 0, policy_version 40990 (0.0008) -[2023-10-17 01:54:20,390][62408] Updated weights for policy 1, policy_version 40680 (0.0010) -[2023-10-17 01:54:20,758][62408] Updated weights for policy 1, policy_version 40690 (0.0009) -[2023-10-17 01:54:21,123][62408] Updated weights for policy 1, policy_version 40700 (0.0009) -[2023-10-17 01:54:22,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 83656704. Throughput: 0: 1756.1, 1: 1794.2. Samples: 20919012. Policy #0 lag: (min: 0.0, avg: 21.5, max: 32.0) -[2023-10-17 01:54:22,215][61453] Avg episode reward: [(0, '9.120'), (1, '9.120')] -[2023-10-17 01:54:22,575][62373] Updated weights for policy 0, policy_version 41000 (0.0009) -[2023-10-17 01:54:22,950][62373] Updated weights for policy 0, policy_version 41010 (0.0009) -[2023-10-17 01:54:23,328][62373] Updated weights for policy 0, policy_version 41020 (0.0009) -[2023-10-17 01:54:24,983][62408] Updated weights for policy 1, policy_version 40710 (0.0008) -[2023-10-17 01:54:25,356][62408] Updated weights for policy 1, policy_version 40720 (0.0007) -[2023-10-17 01:54:25,722][62408] Updated weights for policy 1, policy_version 40730 (0.0007) -[2023-10-17 01:54:27,212][62373] Updated weights for policy 0, policy_version 41030 (0.0009) -[2023-10-17 01:54:27,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 83722240. Throughput: 0: 1772.5, 1: 1774.8. Samples: 20939962. Policy #0 lag: (min: 0.0, avg: 21.5, max: 32.0) -[2023-10-17 01:54:27,214][61453] Avg episode reward: [(0, '8.340'), (1, '9.050')] -[2023-10-17 01:54:27,594][62373] Updated weights for policy 0, policy_version 41040 (0.0009) -[2023-10-17 01:54:27,963][62373] Updated weights for policy 0, policy_version 41050 (0.0009) -[2023-10-17 01:54:29,413][62408] Updated weights for policy 1, policy_version 40740 (0.0008) -[2023-10-17 01:54:29,805][62408] Updated weights for policy 1, policy_version 40750 (0.0008) -[2023-10-17 01:54:30,173][62408] Updated weights for policy 1, policy_version 40760 (0.0008) -[2023-10-17 01:54:31,791][62373] Updated weights for policy 0, policy_version 41060 (0.0009) -[2023-10-17 01:54:32,165][62373] Updated weights for policy 0, policy_version 41070 (0.0009) -[2023-10-17 01:54:32,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 83787776. Throughput: 0: 1775.6, 1: 1772.5. Samples: 20961418. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) -[2023-10-17 01:54:32,215][61453] Avg episode reward: [(0, '8.260'), (1, '9.530')] -[2023-10-17 01:54:32,527][62373] Updated weights for policy 0, policy_version 41080 (0.0007) -[2023-10-17 01:54:34,164][62408] Updated weights for policy 1, policy_version 40770 (0.0010) -[2023-10-17 01:54:34,532][62408] Updated weights for policy 1, policy_version 40780 (0.0009) -[2023-10-17 01:54:34,902][62408] Updated weights for policy 1, policy_version 40790 (0.0007) -[2023-10-17 01:54:35,269][62408] Updated weights for policy 1, policy_version 40800 (0.0007) -[2023-10-17 01:54:36,351][62373] Updated weights for policy 0, policy_version 41090 (0.0008) -[2023-10-17 01:54:36,724][62373] Updated weights for policy 0, policy_version 41100 (0.0008) -[2023-10-17 01:54:37,091][62373] Updated weights for policy 0, policy_version 41110 (0.0007) -[2023-10-17 01:54:37,214][61453] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 14218.0). Total num frames: 83853312. Throughput: 0: 1760.5, 1: 1784.7. Samples: 20971892. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) -[2023-10-17 01:54:37,214][61453] Avg episode reward: [(0, '8.170'), (1, '9.370')] -[2023-10-17 01:54:37,456][62373] Updated weights for policy 0, policy_version 41120 (0.0007) -[2023-10-17 01:54:39,129][62408] Updated weights for policy 1, policy_version 40810 (0.0007) -[2023-10-17 01:54:39,497][62408] Updated weights for policy 1, policy_version 40820 (0.0007) -[2023-10-17 01:54:39,863][62408] Updated weights for policy 1, policy_version 40830 (0.0008) -[2023-10-17 01:54:41,250][62373] Updated weights for policy 0, policy_version 41130 (0.0007) -[2023-10-17 01:54:41,606][62373] Updated weights for policy 0, policy_version 41140 (0.0008) -[2023-10-17 01:54:41,979][62373] Updated weights for policy 0, policy_version 41150 (0.0008) -[2023-10-17 01:54:42,214][61453] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 83951616. Throughput: 0: 1785.8, 1: 1767.2. Samples: 20993272. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) -[2023-10-17 01:54:42,215][61453] Avg episode reward: [(0, '8.520'), (1, '8.840')] -[2023-10-17 01:54:43,601][62408] Updated weights for policy 1, policy_version 40840 (0.0009) -[2023-10-17 01:54:43,969][62408] Updated weights for policy 1, policy_version 40850 (0.0009) -[2023-10-17 01:54:44,330][62408] Updated weights for policy 1, policy_version 40860 (0.0010) -[2023-10-17 01:54:45,743][62373] Updated weights for policy 0, policy_version 41160 (0.0009) -[2023-10-17 01:54:46,114][62373] Updated weights for policy 0, policy_version 41170 (0.0009) -[2023-10-17 01:54:46,498][62373] Updated weights for policy 0, policy_version 41180 (0.0008) -[2023-10-17 01:54:47,214][61453] Fps is (10 sec: 16383.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 84017152. Throughput: 0: 1756.5, 1: 1770.2. Samples: 21014172. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) -[2023-10-17 01:54:47,215][61453] Avg episode reward: [(0, '8.460'), (1, '9.520')] -[2023-10-17 01:54:48,078][62408] Updated weights for policy 1, policy_version 40870 (0.0010) -[2023-10-17 01:54:48,450][62408] Updated weights for policy 1, policy_version 40880 (0.0010) -[2023-10-17 01:54:48,815][62408] Updated weights for policy 1, policy_version 40890 (0.0010) -[2023-10-17 01:54:50,260][62373] Updated weights for policy 0, policy_version 41190 (0.0008) -[2023-10-17 01:54:50,629][62373] Updated weights for policy 0, policy_version 41200 (0.0009) -[2023-10-17 01:54:50,996][62373] Updated weights for policy 0, policy_version 41210 (0.0008) -[2023-10-17 01:54:52,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 84082688. Throughput: 0: 1792.1, 1: 1770.2. Samples: 21025506. Policy #0 lag: (min: 31.0, avg: 36.1, max: 63.0) -[2023-10-17 01:54:52,215][61453] Avg episode reward: [(0, '8.300'), (1, '9.430')] -[2023-10-17 01:54:52,512][62408] Updated weights for policy 1, policy_version 40900 (0.0009) -[2023-10-17 01:54:52,882][62408] Updated weights for policy 1, policy_version 40910 (0.0008) -[2023-10-17 01:54:53,247][62408] Updated weights for policy 1, policy_version 40920 (0.0010) -[2023-10-17 01:54:54,760][62373] Updated weights for policy 0, policy_version 41220 (0.0007) -[2023-10-17 01:54:55,132][62373] Updated weights for policy 0, policy_version 41230 (0.0007) -[2023-10-17 01:54:55,504][62373] Updated weights for policy 0, policy_version 41240 (0.0008) -[2023-10-17 01:54:57,084][62408] Updated weights for policy 1, policy_version 40930 (0.0009) -[2023-10-17 01:54:57,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 84148224. Throughput: 0: 1767.9, 1: 1773.4. Samples: 21046478. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-10-17 01:54:57,215][61453] Avg episode reward: [(0, '8.330'), (1, '9.500')] -[2023-10-17 01:54:57,456][62408] Updated weights for policy 1, policy_version 40940 (0.0009) -[2023-10-17 01:54:57,834][62408] Updated weights for policy 1, policy_version 40950 (0.0008) -[2023-10-17 01:54:58,209][62408] Updated weights for policy 1, policy_version 40960 (0.0009) -[2023-10-17 01:54:59,224][62373] Updated weights for policy 0, policy_version 41250 (0.0007) -[2023-10-17 01:54:59,587][62373] Updated weights for policy 0, policy_version 41260 (0.0008) -[2023-10-17 01:54:59,959][62373] Updated weights for policy 0, policy_version 41270 (0.0009) -[2023-10-17 01:55:00,332][62373] Updated weights for policy 0, policy_version 41280 (0.0009) -[2023-10-17 01:55:02,022][62408] Updated weights for policy 1, policy_version 40970 (0.0009) -[2023-10-17 01:55:02,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 84213760. Throughput: 0: 1773.6, 1: 1788.8. Samples: 21068236. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-10-17 01:55:02,214][61453] Avg episode reward: [(0, '8.260'), (1, '9.070')] -[2023-10-17 01:55:02,381][62408] Updated weights for policy 1, policy_version 40980 (0.0010) -[2023-10-17 01:55:02,755][62408] Updated weights for policy 1, policy_version 40990 (0.0007) -[2023-10-17 01:55:04,231][62373] Updated weights for policy 0, policy_version 41290 (0.0010) -[2023-10-17 01:55:04,605][62373] Updated weights for policy 0, policy_version 41300 (0.0008) -[2023-10-17 01:55:04,981][62373] Updated weights for policy 0, policy_version 41310 (0.0008) -[2023-10-17 01:55:06,572][62408] Updated weights for policy 1, policy_version 41000 (0.0008) -[2023-10-17 01:55:06,942][62408] Updated weights for policy 1, policy_version 41010 (0.0008) -[2023-10-17 01:55:07,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 84279296. Throughput: 0: 1776.6, 1: 1760.7. Samples: 21078190. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-10-17 01:55:07,215][61453] Avg episode reward: [(0, '8.920'), (1, '9.830')] -[2023-10-17 01:55:07,308][62408] Updated weights for policy 1, policy_version 41020 (0.0008) -[2023-10-17 01:55:08,686][62373] Updated weights for policy 0, policy_version 41320 (0.0008) -[2023-10-17 01:55:09,056][62373] Updated weights for policy 0, policy_version 41330 (0.0007) -[2023-10-17 01:55:09,423][62373] Updated weights for policy 0, policy_version 41340 (0.0008) -[2023-10-17 01:55:11,176][62408] Updated weights for policy 1, policy_version 41030 (0.0009) -[2023-10-17 01:55:11,533][62408] Updated weights for policy 1, policy_version 41040 (0.0010) -[2023-10-17 01:55:11,898][62408] Updated weights for policy 1, policy_version 41050 (0.0010) -[2023-10-17 01:55:12,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14218.0). Total num frames: 84377600. Throughput: 0: 1774.7, 1: 1782.4. Samples: 21100030. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-10-17 01:55:12,215][61453] Avg episode reward: [(0, '8.460'), (1, '9.480')] -[2023-10-17 01:55:13,167][62373] Updated weights for policy 0, policy_version 41350 (0.0008) -[2023-10-17 01:55:13,538][62373] Updated weights for policy 0, policy_version 41360 (0.0010) -[2023-10-17 01:55:13,915][62373] Updated weights for policy 0, policy_version 41370 (0.0009) -[2023-10-17 01:55:15,770][62408] Updated weights for policy 1, policy_version 41060 (0.0008) -[2023-10-17 01:55:16,148][62408] Updated weights for policy 1, policy_version 41070 (0.0010) -[2023-10-17 01:55:16,515][62408] Updated weights for policy 1, policy_version 41080 (0.0008) -[2023-10-17 01:55:17,214][61453] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 84443136. Throughput: 0: 1785.4, 1: 1755.3. Samples: 21120748. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-10-17 01:55:17,214][61453] Avg episode reward: [(0, '9.180'), (1, '9.290')] -[2023-10-17 01:55:17,796][62373] Updated weights for policy 0, policy_version 41380 (0.0008) -[2023-10-17 01:55:18,171][62373] Updated weights for policy 0, policy_version 41390 (0.0008) -[2023-10-17 01:55:18,529][62373] Updated weights for policy 0, policy_version 41400 (0.0008) -[2023-10-17 01:55:20,453][62408] Updated weights for policy 1, policy_version 41090 (0.0008) -[2023-10-17 01:55:20,811][62408] Updated weights for policy 1, policy_version 41100 (0.0008) -[2023-10-17 01:55:21,188][62408] Updated weights for policy 1, policy_version 41110 (0.0008) -[2023-10-17 01:55:21,549][62408] Updated weights for policy 1, policy_version 41120 (0.0008) -[2023-10-17 01:55:22,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 84508672. Throughput: 0: 1776.0, 1: 1774.5. Samples: 21131668. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-10-17 01:55:22,214][61453] Avg episode reward: [(0, '9.130'), (1, '8.650')] -[2023-10-17 01:55:22,267][62373] Updated weights for policy 0, policy_version 41410 (0.0008) -[2023-10-17 01:55:22,644][62373] Updated weights for policy 0, policy_version 41420 (0.0009) -[2023-10-17 01:55:23,005][62373] Updated weights for policy 0, policy_version 41430 (0.0008) -[2023-10-17 01:55:23,371][62373] Updated weights for policy 0, policy_version 41440 (0.0007) -[2023-10-17 01:55:25,449][62408] Updated weights for policy 1, policy_version 41130 (0.0007) -[2023-10-17 01:55:25,818][62408] Updated weights for policy 1, policy_version 41140 (0.0008) -[2023-10-17 01:55:26,187][62408] Updated weights for policy 1, policy_version 41150 (0.0008) -[2023-10-17 01:55:27,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 84574208. Throughput: 0: 1780.1, 1: 1766.3. Samples: 21152862. Policy #0 lag: (min: 17.0, avg: 28.2, max: 49.0) -[2023-10-17 01:55:27,215][61453] Avg episode reward: [(0, '9.020'), (1, '8.850')] -[2023-10-17 01:55:27,231][62373] Updated weights for policy 0, policy_version 41450 (0.0007) -[2023-10-17 01:55:27,596][62373] Updated weights for policy 0, policy_version 41460 (0.0008) -[2023-10-17 01:55:27,971][62373] Updated weights for policy 0, policy_version 41470 (0.0007) -[2023-10-17 01:55:30,143][62408] Updated weights for policy 1, policy_version 41160 (0.0008) -[2023-10-17 01:55:30,519][62408] Updated weights for policy 1, policy_version 41170 (0.0009) -[2023-10-17 01:55:30,884][62408] Updated weights for policy 1, policy_version 41180 (0.0009) -[2023-10-17 01:55:31,606][62373] Updated weights for policy 0, policy_version 41480 (0.0007) -[2023-10-17 01:55:31,976][62373] Updated weights for policy 0, policy_version 41490 (0.0010) -[2023-10-17 01:55:32,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 84639744. Throughput: 0: 1796.1, 1: 1752.4. Samples: 21173854. Policy #0 lag: (min: 17.0, avg: 28.2, max: 49.0) -[2023-10-17 01:55:32,215][61453] Avg episode reward: [(0, '9.490'), (1, '8.760')] -[2023-10-17 01:55:32,223][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000041184_42172416.pth... -[2023-10-17 01:55:32,257][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000039520_40468480.pth -[2023-10-17 01:55:32,262][62252] Saving a milestone ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/milestones/checkpoint_000041184_42172416.pth -[2023-10-17 01:55:32,341][62373] Updated weights for policy 0, policy_version 41500 (0.0010) -[2023-10-17 01:55:32,487][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000041504_42500096.pth... -[2023-10-17 01:55:32,527][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000039840_40796160.pth -[2023-10-17 01:55:32,532][62094] Saving a milestone ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/milestones/checkpoint_000041504_42500096.pth -[2023-10-17 01:55:34,880][62408] Updated weights for policy 1, policy_version 41190 (0.0010) -[2023-10-17 01:55:35,236][62408] Updated weights for policy 1, policy_version 41200 (0.0007) -[2023-10-17 01:55:35,607][62408] Updated weights for policy 1, policy_version 41210 (0.0009) -[2023-10-17 01:55:36,105][62373] Updated weights for policy 0, policy_version 41510 (0.0010) -[2023-10-17 01:55:36,473][62373] Updated weights for policy 0, policy_version 41520 (0.0008) -[2023-10-17 01:55:36,838][62373] Updated weights for policy 0, policy_version 41530 (0.0008) -[2023-10-17 01:55:37,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 84738048. Throughput: 0: 1777.3, 1: 1771.3. Samples: 21185192. Policy #0 lag: (min: 17.0, avg: 28.2, max: 49.0) -[2023-10-17 01:55:37,215][61453] Avg episode reward: [(0, '9.950'), (1, '8.750')] -[2023-10-17 01:55:39,498][62408] Updated weights for policy 1, policy_version 41220 (0.0009) -[2023-10-17 01:55:39,871][62408] Updated weights for policy 1, policy_version 41230 (0.0007) -[2023-10-17 01:55:40,242][62408] Updated weights for policy 1, policy_version 41240 (0.0008) -[2023-10-17 01:55:40,647][62373] Updated weights for policy 0, policy_version 41540 (0.0010) -[2023-10-17 01:55:41,024][62373] Updated weights for policy 0, policy_version 41550 (0.0011) -[2023-10-17 01:55:41,391][62373] Updated weights for policy 0, policy_version 41560 (0.0009) -[2023-10-17 01:55:42,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 84803584. Throughput: 0: 1795.6, 1: 1738.1. Samples: 21205492. Policy #0 lag: (min: 17.0, avg: 28.2, max: 49.0) -[2023-10-17 01:55:42,215][61453] Avg episode reward: [(0, '9.760'), (1, '9.000')] -[2023-10-17 01:55:43,919][62408] Updated weights for policy 1, policy_version 41250 (0.0009) -[2023-10-17 01:55:44,282][62408] Updated weights for policy 1, policy_version 41260 (0.0011) -[2023-10-17 01:55:44,656][62408] Updated weights for policy 1, policy_version 41270 (0.0010) -[2023-10-17 01:55:45,024][62408] Updated weights for policy 1, policy_version 41280 (0.0010) -[2023-10-17 01:55:45,150][62373] Updated weights for policy 0, policy_version 41570 (0.0008) -[2023-10-17 01:55:45,515][62373] Updated weights for policy 0, policy_version 41580 (0.0008) -[2023-10-17 01:55:45,885][62373] Updated weights for policy 0, policy_version 41590 (0.0008) -[2023-10-17 01:55:46,245][62373] Updated weights for policy 0, policy_version 41600 (0.0008) -[2023-10-17 01:55:47,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 84869120. Throughput: 0: 1772.5, 1: 1750.8. Samples: 21226786. Policy #0 lag: (min: 17.0, avg: 28.2, max: 49.0) -[2023-10-17 01:55:47,215][61453] Avg episode reward: [(0, '10.660'), (1, '8.960')] -[2023-10-17 01:55:47,228][62094] Saving new best policy, reward=10.660! -[2023-10-17 01:55:48,730][62408] Updated weights for policy 1, policy_version 41290 (0.0010) -[2023-10-17 01:55:49,093][62408] Updated weights for policy 1, policy_version 41300 (0.0011) -[2023-10-17 01:55:49,463][62408] Updated weights for policy 1, policy_version 41310 (0.0010) -[2023-10-17 01:55:50,032][62373] Updated weights for policy 0, policy_version 41610 (0.0008) -[2023-10-17 01:55:50,410][62373] Updated weights for policy 0, policy_version 41620 (0.0009) -[2023-10-17 01:55:50,773][62373] Updated weights for policy 0, policy_version 41630 (0.0007) -[2023-10-17 01:55:52,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 84934656. Throughput: 0: 1795.5, 1: 1742.8. Samples: 21237412. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:55:52,215][61453] Avg episode reward: [(0, '10.600'), (1, '9.120')] -[2023-10-17 01:55:53,283][62408] Updated weights for policy 1, policy_version 41320 (0.0009) -[2023-10-17 01:55:53,653][62408] Updated weights for policy 1, policy_version 41330 (0.0008) -[2023-10-17 01:55:54,016][62408] Updated weights for policy 1, policy_version 41340 (0.0007) -[2023-10-17 01:55:54,388][62373] Updated weights for policy 0, policy_version 41640 (0.0008) -[2023-10-17 01:55:54,758][62373] Updated weights for policy 0, policy_version 41650 (0.0008) -[2023-10-17 01:55:55,128][62373] Updated weights for policy 0, policy_version 41660 (0.0009) -[2023-10-17 01:55:57,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 85000192. Throughput: 0: 1776.2, 1: 1753.3. Samples: 21258858. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:55:57,214][61453] Avg episode reward: [(0, '10.580'), (1, '10.150')] -[2023-10-17 01:55:57,745][62408] Updated weights for policy 1, policy_version 41350 (0.0009) -[2023-10-17 01:55:58,111][62408] Updated weights for policy 1, policy_version 41360 (0.0009) -[2023-10-17 01:55:58,473][62408] Updated weights for policy 1, policy_version 41370 (0.0008) -[2023-10-17 01:55:59,018][62373] Updated weights for policy 0, policy_version 41670 (0.0009) -[2023-10-17 01:55:59,386][62373] Updated weights for policy 0, policy_version 41680 (0.0011) -[2023-10-17 01:55:59,762][62373] Updated weights for policy 0, policy_version 41690 (0.0010) -[2023-10-17 01:56:02,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 85065728. Throughput: 0: 1767.9, 1: 1790.2. Samples: 21280866. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:56:02,215][61453] Avg episode reward: [(0, '10.580'), (1, '9.630')] -[2023-10-17 01:56:02,336][62408] Updated weights for policy 1, policy_version 41380 (0.0008) -[2023-10-17 01:56:02,738][62408] Updated weights for policy 1, policy_version 41390 (0.0008) -[2023-10-17 01:56:03,102][62408] Updated weights for policy 1, policy_version 41400 (0.0008) -[2023-10-17 01:56:03,725][62373] Updated weights for policy 0, policy_version 41700 (0.0009) -[2023-10-17 01:56:04,095][62373] Updated weights for policy 0, policy_version 41710 (0.0009) -[2023-10-17 01:56:04,470][62373] Updated weights for policy 0, policy_version 41720 (0.0009) -[2023-10-17 01:56:06,956][62408] Updated weights for policy 1, policy_version 41410 (0.0008) -[2023-10-17 01:56:07,214][61453] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 85131264. Throughput: 0: 1769.8, 1: 1758.5. Samples: 21290440. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:56:07,216][61453] Avg episode reward: [(0, '10.040'), (1, '9.130')] -[2023-10-17 01:56:07,325][62408] Updated weights for policy 1, policy_version 41420 (0.0008) -[2023-10-17 01:56:07,693][62408] Updated weights for policy 1, policy_version 41430 (0.0008) -[2023-10-17 01:56:08,061][62408] Updated weights for policy 1, policy_version 41440 (0.0009) -[2023-10-17 01:56:08,230][62373] Updated weights for policy 0, policy_version 41730 (0.0008) -[2023-10-17 01:56:08,601][62373] Updated weights for policy 0, policy_version 41740 (0.0011) -[2023-10-17 01:56:08,975][62373] Updated weights for policy 0, policy_version 41750 (0.0010) -[2023-10-17 01:56:09,339][62373] Updated weights for policy 0, policy_version 41760 (0.0011) -[2023-10-17 01:56:11,802][62408] Updated weights for policy 1, policy_version 41450 (0.0007) -[2023-10-17 01:56:12,167][62408] Updated weights for policy 1, policy_version 41460 (0.0008) -[2023-10-17 01:56:12,214][61453] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 85196800. Throughput: 0: 1767.4, 1: 1778.2. Samples: 21312414. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:56:12,214][61453] Avg episode reward: [(0, '10.200'), (1, '8.720')] -[2023-10-17 01:56:12,541][62408] Updated weights for policy 1, policy_version 41470 (0.0011) -[2023-10-17 01:56:13,267][62373] Updated weights for policy 0, policy_version 41770 (0.0007) -[2023-10-17 01:56:13,636][62373] Updated weights for policy 0, policy_version 41780 (0.0007) -[2023-10-17 01:56:14,006][62373] Updated weights for policy 0, policy_version 41790 (0.0007) -[2023-10-17 01:56:16,485][62408] Updated weights for policy 1, policy_version 41480 (0.0010) -[2023-10-17 01:56:16,847][62408] Updated weights for policy 1, policy_version 41490 (0.0009) -[2023-10-17 01:56:17,214][61453] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 85262336. Throughput: 0: 1783.6, 1: 1770.3. Samples: 21333782. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:56:17,215][62408] Updated weights for policy 1, policy_version 41500 (0.0008) -[2023-10-17 01:56:17,215][61453] Avg episode reward: [(0, '9.930'), (1, '8.830')] -[2023-10-17 01:56:17,740][62373] Updated weights for policy 0, policy_version 41800 (0.0008) -[2023-10-17 01:56:18,115][62373] Updated weights for policy 0, policy_version 41810 (0.0008) -[2023-10-17 01:56:18,486][62373] Updated weights for policy 0, policy_version 41820 (0.0009) -[2023-10-17 01:56:20,997][62408] Updated weights for policy 1, policy_version 41510 (0.0010) -[2023-10-17 01:56:21,364][62408] Updated weights for policy 1, policy_version 41520 (0.0009) -[2023-10-17 01:56:21,735][62408] Updated weights for policy 1, policy_version 41530 (0.0007) -[2023-10-17 01:56:22,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 85360640. Throughput: 0: 1765.8, 1: 1764.3. Samples: 21344048. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-17 01:56:22,214][61453] Avg episode reward: [(0, '9.900'), (1, '8.880')] -[2023-10-17 01:56:22,282][62373] Updated weights for policy 0, policy_version 41830 (0.0007) -[2023-10-17 01:56:22,655][62373] Updated weights for policy 0, policy_version 41840 (0.0009) -[2023-10-17 01:56:23,031][62373] Updated weights for policy 0, policy_version 41850 (0.0008) -[2023-10-17 01:56:25,510][62408] Updated weights for policy 1, policy_version 41540 (0.0009) -[2023-10-17 01:56:25,884][62408] Updated weights for policy 1, policy_version 41550 (0.0010) -[2023-10-17 01:56:26,249][62408] Updated weights for policy 1, policy_version 41560 (0.0009) -[2023-10-17 01:56:26,819][62373] Updated weights for policy 0, policy_version 41860 (0.0009) -[2023-10-17 01:56:27,193][62373] Updated weights for policy 0, policy_version 41870 (0.0009) -[2023-10-17 01:56:27,214][61453] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 85426176. Throughput: 0: 1777.2, 1: 1781.3. Samples: 21365620. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-17 01:56:27,214][61453] Avg episode reward: [(0, '10.160'), (1, '8.120')] -[2023-10-17 01:56:27,562][62373] Updated weights for policy 0, policy_version 41880 (0.0008) -[2023-10-17 01:56:30,086][62408] Updated weights for policy 1, policy_version 41570 (0.0009) -[2023-10-17 01:56:30,459][62408] Updated weights for policy 1, policy_version 41580 (0.0008) -[2023-10-17 01:56:30,839][62408] Updated weights for policy 1, policy_version 41590 (0.0008) -[2023-10-17 01:56:31,204][62408] Updated weights for policy 1, policy_version 41600 (0.0008) -[2023-10-17 01:56:31,343][62373] Updated weights for policy 0, policy_version 41890 (0.0008) -[2023-10-17 01:56:31,713][62373] Updated weights for policy 0, policy_version 41900 (0.0008) -[2023-10-17 01:56:32,097][62373] Updated weights for policy 0, policy_version 41910 (0.0008) -[2023-10-17 01:56:32,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 85491712. Throughput: 0: 1779.7, 1: 1767.0. Samples: 21386388. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-17 01:56:32,214][61453] Avg episode reward: [(0, '9.600'), (1, '8.420')] -[2023-10-17 01:56:32,463][62373] Updated weights for policy 0, policy_version 41920 (0.0007) -[2023-10-17 01:56:35,112][62408] Updated weights for policy 1, policy_version 41610 (0.0008) -[2023-10-17 01:56:35,473][62408] Updated weights for policy 1, policy_version 41620 (0.0007) -[2023-10-17 01:56:35,843][62408] Updated weights for policy 1, policy_version 41630 (0.0009) -[2023-10-17 01:56:36,314][62373] Updated weights for policy 0, policy_version 41930 (0.0010) -[2023-10-17 01:56:36,681][62373] Updated weights for policy 0, policy_version 41940 (0.0011) -[2023-10-17 01:56:37,047][62373] Updated weights for policy 0, policy_version 41950 (0.0010) -[2023-10-17 01:56:37,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 85590016. Throughput: 0: 1773.2, 1: 1794.7. Samples: 21397966. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-17 01:56:37,215][61453] Avg episode reward: [(0, '9.300'), (1, '8.570')] -[2023-10-17 01:56:39,616][62408] Updated weights for policy 1, policy_version 41640 (0.0011) -[2023-10-17 01:56:39,988][62408] Updated weights for policy 1, policy_version 41650 (0.0008) -[2023-10-17 01:56:40,346][62408] Updated weights for policy 1, policy_version 41660 (0.0007) -[2023-10-17 01:56:40,826][62373] Updated weights for policy 0, policy_version 41960 (0.0010) -[2023-10-17 01:56:41,199][62373] Updated weights for policy 0, policy_version 41970 (0.0011) -[2023-10-17 01:56:41,575][62373] Updated weights for policy 0, policy_version 41980 (0.0008) -[2023-10-17 01:56:42,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 85655552. Throughput: 0: 1783.5, 1: 1760.4. Samples: 21418334. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-17 01:56:42,214][61453] Avg episode reward: [(0, '9.380'), (1, '8.920')] -[2023-10-17 01:56:44,281][62408] Updated weights for policy 1, policy_version 41670 (0.0008) -[2023-10-17 01:56:44,652][62408] Updated weights for policy 1, policy_version 41680 (0.0008) -[2023-10-17 01:56:45,015][62408] Updated weights for policy 1, policy_version 41690 (0.0008) -[2023-10-17 01:56:45,371][62373] Updated weights for policy 0, policy_version 41990 (0.0008) -[2023-10-17 01:56:45,748][62373] Updated weights for policy 0, policy_version 42000 (0.0009) -[2023-10-17 01:56:46,117][62373] Updated weights for policy 0, policy_version 42010 (0.0009) -[2023-10-17 01:56:47,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 85721088. Throughput: 0: 1771.7, 1: 1754.1. Samples: 21439528. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-17 01:56:47,215][61453] Avg episode reward: [(0, '9.470'), (1, '8.700')] -[2023-10-17 01:56:48,827][62408] Updated weights for policy 1, policy_version 41700 (0.0008) -[2023-10-17 01:56:49,228][62408] Updated weights for policy 1, policy_version 41710 (0.0009) -[2023-10-17 01:56:49,589][62408] Updated weights for policy 1, policy_version 41720 (0.0007) -[2023-10-17 01:56:50,018][62373] Updated weights for policy 0, policy_version 42020 (0.0007) -[2023-10-17 01:56:50,396][62373] Updated weights for policy 0, policy_version 42030 (0.0009) -[2023-10-17 01:56:50,760][62373] Updated weights for policy 0, policy_version 42040 (0.0008) -[2023-10-17 01:56:52,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 85786624. Throughput: 0: 1796.1, 1: 1753.9. Samples: 21450192. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-17 01:56:52,215][61453] Avg episode reward: [(0, '9.110'), (1, '8.520')] -[2023-10-17 01:56:53,340][62408] Updated weights for policy 1, policy_version 41730 (0.0008) -[2023-10-17 01:56:53,712][62408] Updated weights for policy 1, policy_version 41740 (0.0009) -[2023-10-17 01:56:54,074][62408] Updated weights for policy 1, policy_version 41750 (0.0008) -[2023-10-17 01:56:54,444][62408] Updated weights for policy 1, policy_version 41760 (0.0009) -[2023-10-17 01:56:54,554][62373] Updated weights for policy 0, policy_version 42050 (0.0007) -[2023-10-17 01:56:54,920][62373] Updated weights for policy 0, policy_version 42060 (0.0008) -[2023-10-17 01:56:55,292][62373] Updated weights for policy 0, policy_version 42070 (0.0009) -[2023-10-17 01:56:55,664][62373] Updated weights for policy 0, policy_version 42080 (0.0009) -[2023-10-17 01:56:57,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 85852160. Throughput: 0: 1767.1, 1: 1761.7. Samples: 21471208. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-17 01:56:57,215][61453] Avg episode reward: [(0, '9.650'), (1, '8.890')] -[2023-10-17 01:56:58,114][62408] Updated weights for policy 1, policy_version 41770 (0.0009) -[2023-10-17 01:56:58,487][62408] Updated weights for policy 1, policy_version 41780 (0.0008) -[2023-10-17 01:56:58,859][62408] Updated weights for policy 1, policy_version 41790 (0.0007) -[2023-10-17 01:56:59,500][62373] Updated weights for policy 0, policy_version 42090 (0.0007) -[2023-10-17 01:56:59,866][62373] Updated weights for policy 0, policy_version 42100 (0.0007) -[2023-10-17 01:57:00,246][62373] Updated weights for policy 0, policy_version 42110 (0.0007) -[2023-10-17 01:57:02,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 85917696. Throughput: 0: 1759.6, 1: 1783.4. Samples: 21493216. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-17 01:57:02,215][61453] Avg episode reward: [(0, '9.430'), (1, '8.550')] -[2023-10-17 01:57:02,736][62408] Updated weights for policy 1, policy_version 41800 (0.0008) -[2023-10-17 01:57:03,094][62408] Updated weights for policy 1, policy_version 41810 (0.0008) -[2023-10-17 01:57:03,463][62408] Updated weights for policy 1, policy_version 41820 (0.0009) -[2023-10-17 01:57:03,863][62373] Updated weights for policy 0, policy_version 42120 (0.0009) -[2023-10-17 01:57:04,227][62373] Updated weights for policy 0, policy_version 42130 (0.0009) -[2023-10-17 01:57:04,595][62373] Updated weights for policy 0, policy_version 42140 (0.0008) -[2023-10-17 01:57:07,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 85983232. Throughput: 0: 1764.9, 1: 1766.0. Samples: 21502936. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-17 01:57:07,215][61453] Avg episode reward: [(0, '9.020'), (1, '8.530')] -[2023-10-17 01:57:07,334][62408] Updated weights for policy 1, policy_version 41830 (0.0010) -[2023-10-17 01:57:07,704][62408] Updated weights for policy 1, policy_version 41840 (0.0007) -[2023-10-17 01:57:08,079][62408] Updated weights for policy 1, policy_version 41850 (0.0007) -[2023-10-17 01:57:08,487][62373] Updated weights for policy 0, policy_version 42150 (0.0009) -[2023-10-17 01:57:08,854][62373] Updated weights for policy 0, policy_version 42160 (0.0007) -[2023-10-17 01:57:09,224][62373] Updated weights for policy 0, policy_version 42170 (0.0008) -[2023-10-17 01:57:11,918][62408] Updated weights for policy 1, policy_version 41860 (0.0007) -[2023-10-17 01:57:12,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 86048768. Throughput: 0: 1762.3, 1: 1772.5. Samples: 21524688. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-17 01:57:12,215][61453] Avg episode reward: [(0, '9.570'), (1, '8.090')] -[2023-10-17 01:57:12,282][62408] Updated weights for policy 1, policy_version 41870 (0.0008) -[2023-10-17 01:57:12,654][62408] Updated weights for policy 1, policy_version 41880 (0.0009) -[2023-10-17 01:57:12,988][62373] Updated weights for policy 0, policy_version 42180 (0.0008) -[2023-10-17 01:57:13,362][62373] Updated weights for policy 0, policy_version 42190 (0.0008) -[2023-10-17 01:57:13,732][62373] Updated weights for policy 0, policy_version 42200 (0.0007) -[2023-10-17 01:57:16,505][62408] Updated weights for policy 1, policy_version 41890 (0.0007) -[2023-10-17 01:57:16,869][62408] Updated weights for policy 1, policy_version 41900 (0.0010) -[2023-10-17 01:57:17,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 86114304. Throughput: 0: 1778.3, 1: 1775.0. Samples: 21546286. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:57:17,215][61453] Avg episode reward: [(0, '9.610'), (1, '8.370')] -[2023-10-17 01:57:17,237][62408] Updated weights for policy 1, policy_version 41910 (0.0008) -[2023-10-17 01:57:17,606][62408] Updated weights for policy 1, policy_version 41920 (0.0009) -[2023-10-17 01:57:17,619][62373] Updated weights for policy 0, policy_version 42210 (0.0008) -[2023-10-17 01:57:17,976][62373] Updated weights for policy 0, policy_version 42220 (0.0010) -[2023-10-17 01:57:18,342][62373] Updated weights for policy 0, policy_version 42230 (0.0009) -[2023-10-17 01:57:18,717][62373] Updated weights for policy 0, policy_version 42240 (0.0010) -[2023-10-17 01:57:21,525][62408] Updated weights for policy 1, policy_version 41930 (0.0008) -[2023-10-17 01:57:21,895][62408] Updated weights for policy 1, policy_version 41940 (0.0008) -[2023-10-17 01:57:22,214][61453] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 86179840. Throughput: 0: 1761.5, 1: 1758.4. Samples: 21556360. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:57:22,215][61453] Avg episode reward: [(0, '9.310'), (1, '8.840')] -[2023-10-17 01:57:22,271][62408] Updated weights for policy 1, policy_version 41950 (0.0008) -[2023-10-17 01:57:22,448][62373] Updated weights for policy 0, policy_version 42250 (0.0008) -[2023-10-17 01:57:22,810][62373] Updated weights for policy 0, policy_version 42260 (0.0008) -[2023-10-17 01:57:23,182][62373] Updated weights for policy 0, policy_version 42270 (0.0008) -[2023-10-17 01:57:26,086][62408] Updated weights for policy 1, policy_version 41960 (0.0010) -[2023-10-17 01:57:26,454][62408] Updated weights for policy 1, policy_version 41970 (0.0008) -[2023-10-17 01:57:26,831][62408] Updated weights for policy 1, policy_version 41980 (0.0008) -[2023-10-17 01:57:27,076][62373] Updated weights for policy 0, policy_version 42280 (0.0007) -[2023-10-17 01:57:27,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 86278144. Throughput: 0: 1767.4, 1: 1779.1. Samples: 21577928. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:57:27,215][61453] Avg episode reward: [(0, '9.220'), (1, '9.290')] -[2023-10-17 01:57:27,443][62373] Updated weights for policy 0, policy_version 42290 (0.0009) -[2023-10-17 01:57:27,814][62373] Updated weights for policy 0, policy_version 42300 (0.0008) -[2023-10-17 01:57:30,698][62408] Updated weights for policy 1, policy_version 41990 (0.0009) -[2023-10-17 01:57:31,078][62408] Updated weights for policy 1, policy_version 42000 (0.0010) -[2023-10-17 01:57:31,446][62408] Updated weights for policy 1, policy_version 42010 (0.0010) -[2023-10-17 01:57:31,559][62373] Updated weights for policy 0, policy_version 42310 (0.0007) -[2023-10-17 01:57:31,918][62373] Updated weights for policy 0, policy_version 42320 (0.0007) -[2023-10-17 01:57:32,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 86343680. Throughput: 0: 1773.2, 1: 1745.7. Samples: 21597878. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:57:32,215][61453] Avg episode reward: [(0, '9.060'), (1, '9.010')] -[2023-10-17 01:57:32,226][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000042016_43024384.pth... -[2023-10-17 01:57:32,265][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000040352_41320448.pth -[2023-10-17 01:57:32,292][62373] Updated weights for policy 0, policy_version 42330 (0.0010) -[2023-10-17 01:57:32,515][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000042336_43352064.pth... -[2023-10-17 01:57:32,544][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000040672_41648128.pth -[2023-10-17 01:57:35,489][62408] Updated weights for policy 1, policy_version 42020 (0.0009) -[2023-10-17 01:57:35,899][62408] Updated weights for policy 1, policy_version 42030 (0.0009) -[2023-10-17 01:57:36,096][62373] Updated weights for policy 0, policy_version 42340 (0.0008) -[2023-10-17 01:57:36,271][62408] Updated weights for policy 1, policy_version 42040 (0.0008) -[2023-10-17 01:57:36,461][62373] Updated weights for policy 0, policy_version 42350 (0.0008) -[2023-10-17 01:57:36,839][62373] Updated weights for policy 0, policy_version 42360 (0.0008) -[2023-10-17 01:57:37,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 86441984. Throughput: 0: 1764.8, 1: 1780.8. Samples: 21609746. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:57:37,215][61453] Avg episode reward: [(0, '9.480'), (1, '9.110')] -[2023-10-17 01:57:40,074][62408] Updated weights for policy 1, policy_version 42050 (0.0007) -[2023-10-17 01:57:40,438][62408] Updated weights for policy 1, policy_version 42060 (0.0007) -[2023-10-17 01:57:40,706][62373] Updated weights for policy 0, policy_version 42370 (0.0008) -[2023-10-17 01:57:40,806][62408] Updated weights for policy 1, policy_version 42070 (0.0008) -[2023-10-17 01:57:41,071][62373] Updated weights for policy 0, policy_version 42380 (0.0007) -[2023-10-17 01:57:41,179][62408] Updated weights for policy 1, policy_version 42080 (0.0008) -[2023-10-17 01:57:41,435][62373] Updated weights for policy 0, policy_version 42390 (0.0009) -[2023-10-17 01:57:41,814][62373] Updated weights for policy 0, policy_version 42400 (0.0010) -[2023-10-17 01:57:42,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 86507520. Throughput: 0: 1784.5, 1: 1747.7. Samples: 21630160. Policy #0 lag: (min: 2.0, avg: 3.3, max: 27.0) -[2023-10-17 01:57:42,215][61453] Avg episode reward: [(0, '9.770'), (1, '9.540')] -[2023-10-17 01:57:44,914][62408] Updated weights for policy 1, policy_version 42090 (0.0008) -[2023-10-17 01:57:45,281][62408] Updated weights for policy 1, policy_version 42100 (0.0008) -[2023-10-17 01:57:45,527][62373] Updated weights for policy 0, policy_version 42410 (0.0008) -[2023-10-17 01:57:45,649][62408] Updated weights for policy 1, policy_version 42110 (0.0010) -[2023-10-17 01:57:45,897][62373] Updated weights for policy 0, policy_version 42420 (0.0008) -[2023-10-17 01:57:46,271][62373] Updated weights for policy 0, policy_version 42430 (0.0010) -[2023-10-17 01:57:47,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 86573056. Throughput: 0: 1766.0, 1: 1737.0. Samples: 21650850. Policy #0 lag: (min: 2.0, avg: 3.3, max: 27.0) -[2023-10-17 01:57:47,214][61453] Avg episode reward: [(0, '10.340'), (1, '9.610')] -[2023-10-17 01:57:49,523][62408] Updated weights for policy 1, policy_version 42120 (0.0007) -[2023-10-17 01:57:49,892][62408] Updated weights for policy 1, policy_version 42130 (0.0007) -[2023-10-17 01:57:50,176][62373] Updated weights for policy 0, policy_version 42440 (0.0009) -[2023-10-17 01:57:50,252][62408] Updated weights for policy 1, policy_version 42140 (0.0007) -[2023-10-17 01:57:50,541][62373] Updated weights for policy 0, policy_version 42450 (0.0009) -[2023-10-17 01:57:50,914][62373] Updated weights for policy 0, policy_version 42460 (0.0010) -[2023-10-17 01:57:52,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 86638592. Throughput: 0: 1789.5, 1: 1748.4. Samples: 21662138. Policy #0 lag: (min: 2.0, avg: 3.3, max: 27.0) -[2023-10-17 01:57:52,214][61453] Avg episode reward: [(0, '10.040'), (1, '9.100')] -[2023-10-17 01:57:53,978][62408] Updated weights for policy 1, policy_version 42150 (0.0009) -[2023-10-17 01:57:54,347][62408] Updated weights for policy 1, policy_version 42160 (0.0010) -[2023-10-17 01:57:54,652][62373] Updated weights for policy 0, policy_version 42470 (0.0010) -[2023-10-17 01:57:54,714][62408] Updated weights for policy 1, policy_version 42170 (0.0008) -[2023-10-17 01:57:55,015][62373] Updated weights for policy 0, policy_version 42480 (0.0007) -[2023-10-17 01:57:55,390][62373] Updated weights for policy 0, policy_version 42490 (0.0008) -[2023-10-17 01:57:57,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 86704128. Throughput: 0: 1762.1, 1: 1740.0. Samples: 21682284. Policy #0 lag: (min: 2.0, avg: 3.3, max: 27.0) -[2023-10-17 01:57:57,215][61453] Avg episode reward: [(0, '10.070'), (1, '9.260')] -[2023-10-17 01:57:58,507][62408] Updated weights for policy 1, policy_version 42180 (0.0010) -[2023-10-17 01:57:58,877][62408] Updated weights for policy 1, policy_version 42190 (0.0010) -[2023-10-17 01:57:59,239][62408] Updated weights for policy 1, policy_version 42200 (0.0008) -[2023-10-17 01:57:59,252][62373] Updated weights for policy 0, policy_version 42500 (0.0009) -[2023-10-17 01:57:59,629][62373] Updated weights for policy 0, policy_version 42510 (0.0007) -[2023-10-17 01:58:00,005][62373] Updated weights for policy 0, policy_version 42520 (0.0008) -[2023-10-17 01:58:02,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 86769664. Throughput: 0: 1762.7, 1: 1751.7. Samples: 21704434. Policy #0 lag: (min: 2.0, avg: 3.3, max: 27.0) -[2023-10-17 01:58:02,215][61453] Avg episode reward: [(0, '9.950'), (1, '8.930')] -[2023-10-17 01:58:02,943][62408] Updated weights for policy 1, policy_version 42210 (0.0008) -[2023-10-17 01:58:03,312][62408] Updated weights for policy 1, policy_version 42220 (0.0007) -[2023-10-17 01:58:03,681][62408] Updated weights for policy 1, policy_version 42230 (0.0008) -[2023-10-17 01:58:03,805][62373] Updated weights for policy 0, policy_version 42530 (0.0008) -[2023-10-17 01:58:04,047][62408] Updated weights for policy 1, policy_version 42240 (0.0007) -[2023-10-17 01:58:04,170][62373] Updated weights for policy 0, policy_version 42540 (0.0007) -[2023-10-17 01:58:04,547][62373] Updated weights for policy 0, policy_version 42550 (0.0008) -[2023-10-17 01:58:04,916][62373] Updated weights for policy 0, policy_version 42560 (0.0009) -[2023-10-17 01:58:07,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 86835200. Throughput: 0: 1764.0, 1: 1741.4. Samples: 21714104. Policy #0 lag: (min: 2.0, avg: 3.3, max: 27.0) -[2023-10-17 01:58:07,215][61453] Avg episode reward: [(0, '9.530'), (1, '9.220')] -[2023-10-17 01:58:07,896][62408] Updated weights for policy 1, policy_version 42250 (0.0007) -[2023-10-17 01:58:08,264][62408] Updated weights for policy 1, policy_version 42260 (0.0008) -[2023-10-17 01:58:08,635][62408] Updated weights for policy 1, policy_version 42270 (0.0008) -[2023-10-17 01:58:08,642][62373] Updated weights for policy 0, policy_version 42570 (0.0008) -[2023-10-17 01:58:09,011][62373] Updated weights for policy 0, policy_version 42580 (0.0010) -[2023-10-17 01:58:09,390][62373] Updated weights for policy 0, policy_version 42590 (0.0011) -[2023-10-17 01:58:12,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 86900736. Throughput: 0: 1768.9, 1: 1745.5. Samples: 21736078. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-17 01:58:12,215][61453] Avg episode reward: [(0, '9.690'), (1, '8.840')] -[2023-10-17 01:58:12,548][62408] Updated weights for policy 1, policy_version 42280 (0.0007) -[2023-10-17 01:58:12,919][62408] Updated weights for policy 1, policy_version 42290 (0.0009) -[2023-10-17 01:58:13,233][62373] Updated weights for policy 0, policy_version 42600 (0.0008) -[2023-10-17 01:58:13,276][62408] Updated weights for policy 1, policy_version 42300 (0.0008) -[2023-10-17 01:58:13,604][62373] Updated weights for policy 0, policy_version 42610 (0.0008) -[2023-10-17 01:58:13,979][62373] Updated weights for policy 0, policy_version 42620 (0.0009) -[2023-10-17 01:58:17,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 86966272. Throughput: 0: 1778.4, 1: 1780.2. Samples: 21758014. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-17 01:58:17,215][61453] Avg episode reward: [(0, '9.840'), (1, '9.090')] -[2023-10-17 01:58:17,376][62408] Updated weights for policy 1, policy_version 42310 (0.0008) -[2023-10-17 01:58:17,744][62408] Updated weights for policy 1, policy_version 42320 (0.0009) -[2023-10-17 01:58:17,853][62373] Updated weights for policy 0, policy_version 42630 (0.0008) -[2023-10-17 01:58:18,120][62408] Updated weights for policy 1, policy_version 42330 (0.0008) -[2023-10-17 01:58:18,224][62373] Updated weights for policy 0, policy_version 42640 (0.0009) -[2023-10-17 01:58:18,600][62373] Updated weights for policy 0, policy_version 42650 (0.0009) -[2023-10-17 01:58:22,089][62408] Updated weights for policy 1, policy_version 42340 (0.0008) -[2023-10-17 01:58:22,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 87031808. Throughput: 0: 1760.2, 1: 1746.7. Samples: 21767556. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-17 01:58:22,215][61453] Avg episode reward: [(0, '8.830'), (1, '8.880')] -[2023-10-17 01:58:22,461][62373] Updated weights for policy 0, policy_version 42660 (0.0008) -[2023-10-17 01:58:22,474][62408] Updated weights for policy 1, policy_version 42350 (0.0007) -[2023-10-17 01:58:22,832][62373] Updated weights for policy 0, policy_version 42670 (0.0008) -[2023-10-17 01:58:22,849][62408] Updated weights for policy 1, policy_version 42360 (0.0007) -[2023-10-17 01:58:23,199][62373] Updated weights for policy 0, policy_version 42680 (0.0007) -[2023-10-17 01:58:26,836][62373] Updated weights for policy 0, policy_version 42690 (0.0008) -[2023-10-17 01:58:26,887][62408] Updated weights for policy 1, policy_version 42370 (0.0007) -[2023-10-17 01:58:27,212][62373] Updated weights for policy 0, policy_version 42700 (0.0009) -[2023-10-17 01:58:27,214][61453] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 87097344. Throughput: 0: 1774.5, 1: 1764.1. Samples: 21789394. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-17 01:58:27,215][61453] Avg episode reward: [(0, '9.390'), (1, '8.890')] -[2023-10-17 01:58:27,256][62408] Updated weights for policy 1, policy_version 42380 (0.0007) -[2023-10-17 01:58:27,575][62373] Updated weights for policy 0, policy_version 42710 (0.0009) -[2023-10-17 01:58:27,620][62408] Updated weights for policy 1, policy_version 42390 (0.0009) -[2023-10-17 01:58:27,950][62373] Updated weights for policy 0, policy_version 42720 (0.0008) -[2023-10-17 01:58:27,988][62408] Updated weights for policy 1, policy_version 42400 (0.0008) -[2023-10-17 01:58:31,727][62373] Updated weights for policy 0, policy_version 42730 (0.0008) -[2023-10-17 01:58:31,836][62408] Updated weights for policy 1, policy_version 42410 (0.0007) -[2023-10-17 01:58:32,098][62373] Updated weights for policy 0, policy_version 42740 (0.0008) -[2023-10-17 01:58:32,200][62408] Updated weights for policy 1, policy_version 42420 (0.0007) -[2023-10-17 01:58:32,214][61453] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 13995.8). Total num frames: 87162880. Throughput: 0: 1783.3, 1: 1757.9. Samples: 21810202. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-17 01:58:32,215][61453] Avg episode reward: [(0, '10.210'), (1, '8.800')] -[2023-10-17 01:58:32,470][62373] Updated weights for policy 0, policy_version 42750 (0.0008) -[2023-10-17 01:58:32,572][62408] Updated weights for policy 1, policy_version 42430 (0.0008) -[2023-10-17 01:58:36,253][62373] Updated weights for policy 0, policy_version 42760 (0.0008) -[2023-10-17 01:58:36,319][62408] Updated weights for policy 1, policy_version 42440 (0.0008) -[2023-10-17 01:58:36,631][62373] Updated weights for policy 0, policy_version 42770 (0.0008) -[2023-10-17 01:58:36,677][62408] Updated weights for policy 1, policy_version 42450 (0.0008) -[2023-10-17 01:58:36,999][62373] Updated weights for policy 0, policy_version 42780 (0.0007) -[2023-10-17 01:58:37,050][62408] Updated weights for policy 1, policy_version 42460 (0.0010) -[2023-10-17 01:58:37,214][61453] Fps is (10 sec: 19660.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 87293952. Throughput: 0: 1771.1, 1: 1756.0. Samples: 21820858. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:58:37,215][61453] Avg episode reward: [(0, '9.640'), (1, '9.340')] -[2023-10-17 01:58:40,843][62408] Updated weights for policy 1, policy_version 42470 (0.0008) -[2023-10-17 01:58:40,945][62373] Updated weights for policy 0, policy_version 42790 (0.0008) -[2023-10-17 01:58:41,210][62408] Updated weights for policy 1, policy_version 42480 (0.0008) -[2023-10-17 01:58:41,318][62373] Updated weights for policy 0, policy_version 42800 (0.0007) -[2023-10-17 01:58:41,579][62408] Updated weights for policy 1, policy_version 42490 (0.0008) -[2023-10-17 01:58:41,690][62373] Updated weights for policy 0, policy_version 42810 (0.0007) -[2023-10-17 01:58:42,214][61453] Fps is (10 sec: 19660.8, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 87359488. Throughput: 0: 1789.5, 1: 1766.5. Samples: 21842304. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:58:42,215][61453] Avg episode reward: [(0, '9.640'), (1, '8.820')] -[2023-10-17 01:58:45,356][62408] Updated weights for policy 1, policy_version 42500 (0.0010) -[2023-10-17 01:58:45,676][62373] Updated weights for policy 0, policy_version 42820 (0.0008) -[2023-10-17 01:58:45,719][62408] Updated weights for policy 1, policy_version 42510 (0.0008) -[2023-10-17 01:58:46,043][62373] Updated weights for policy 0, policy_version 42830 (0.0009) -[2023-10-17 01:58:46,081][62408] Updated weights for policy 1, policy_version 42520 (0.0008) -[2023-10-17 01:58:46,412][62373] Updated weights for policy 0, policy_version 42840 (0.0009) -[2023-10-17 01:58:47,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 87425024. Throughput: 0: 1761.2, 1: 1742.8. Samples: 21862112. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:58:47,215][61453] Avg episode reward: [(0, '9.100'), (1, '9.310')] -[2023-10-17 01:58:49,808][62408] Updated weights for policy 1, policy_version 42530 (0.0007) -[2023-10-17 01:58:50,115][62373] Updated weights for policy 0, policy_version 42850 (0.0009) -[2023-10-17 01:58:50,175][62408] Updated weights for policy 1, policy_version 42540 (0.0007) -[2023-10-17 01:58:50,478][62373] Updated weights for policy 0, policy_version 42860 (0.0008) -[2023-10-17 01:58:50,544][62408] Updated weights for policy 1, policy_version 42550 (0.0008) -[2023-10-17 01:58:50,847][62373] Updated weights for policy 0, policy_version 42870 (0.0008) -[2023-10-17 01:58:50,905][62408] Updated weights for policy 1, policy_version 42560 (0.0008) -[2023-10-17 01:58:51,218][62373] Updated weights for policy 0, policy_version 42880 (0.0007) -[2023-10-17 01:58:52,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 87490560. Throughput: 0: 1796.7, 1: 1768.9. Samples: 21874556. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:58:52,215][61453] Avg episode reward: [(0, '9.640'), (1, '9.020')] -[2023-10-17 01:58:54,659][62408] Updated weights for policy 1, policy_version 42570 (0.0008) -[2023-10-17 01:58:54,982][62373] Updated weights for policy 0, policy_version 42890 (0.0008) -[2023-10-17 01:58:55,027][62408] Updated weights for policy 1, policy_version 42580 (0.0007) -[2023-10-17 01:58:55,356][62373] Updated weights for policy 0, policy_version 42900 (0.0007) -[2023-10-17 01:58:55,404][62408] Updated weights for policy 1, policy_version 42590 (0.0007) -[2023-10-17 01:58:55,721][62373] Updated weights for policy 0, policy_version 42910 (0.0010) -[2023-10-17 01:58:57,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 87556096. Throughput: 0: 1763.4, 1: 1748.2. Samples: 21894102. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:58:57,215][61453] Avg episode reward: [(0, '9.850'), (1, '9.240')] -[2023-10-17 01:58:59,396][62408] Updated weights for policy 1, policy_version 42600 (0.0008) -[2023-10-17 01:58:59,605][62373] Updated weights for policy 0, policy_version 42920 (0.0008) -[2023-10-17 01:58:59,773][62408] Updated weights for policy 1, policy_version 42610 (0.0008) -[2023-10-17 01:58:59,980][62373] Updated weights for policy 0, policy_version 42930 (0.0008) -[2023-10-17 01:59:00,139][62408] Updated weights for policy 1, policy_version 42620 (0.0008) -[2023-10-17 01:59:00,338][62373] Updated weights for policy 0, policy_version 42940 (0.0008) -[2023-10-17 01:59:02,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 87621632. Throughput: 0: 1758.3, 1: 1746.7. Samples: 21915738. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:59:02,215][61453] Avg episode reward: [(0, '10.390'), (1, '9.100')] -[2023-10-17 01:59:03,968][62408] Updated weights for policy 1, policy_version 42630 (0.0007) -[2023-10-17 01:59:04,149][62373] Updated weights for policy 0, policy_version 42950 (0.0010) -[2023-10-17 01:59:04,337][62408] Updated weights for policy 1, policy_version 42640 (0.0007) -[2023-10-17 01:59:04,515][62373] Updated weights for policy 0, policy_version 42960 (0.0009) -[2023-10-17 01:59:04,708][62408] Updated weights for policy 1, policy_version 42650 (0.0009) -[2023-10-17 01:59:04,884][62373] Updated weights for policy 0, policy_version 42970 (0.0008) -[2023-10-17 01:59:07,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 87687168. Throughput: 0: 1767.6, 1: 1749.7. Samples: 21925836. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:59:07,215][61453] Avg episode reward: [(0, '9.230'), (1, '8.530')] -[2023-10-17 01:59:08,659][62408] Updated weights for policy 1, policy_version 42660 (0.0007) -[2023-10-17 01:59:08,768][62373] Updated weights for policy 0, policy_version 42980 (0.0008) -[2023-10-17 01:59:09,023][62408] Updated weights for policy 1, policy_version 42670 (0.0007) -[2023-10-17 01:59:09,128][62373] Updated weights for policy 0, policy_version 42990 (0.0009) -[2023-10-17 01:59:09,391][62408] Updated weights for policy 1, policy_version 42680 (0.0009) -[2023-10-17 01:59:09,497][62373] Updated weights for policy 0, policy_version 43000 (0.0009) -[2023-10-17 01:59:12,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 87752704. Throughput: 0: 1763.5, 1: 1749.0. Samples: 21947454. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:59:12,215][61453] Avg episode reward: [(0, '10.110'), (1, '9.020')] -[2023-10-17 01:59:13,212][62373] Updated weights for policy 0, policy_version 43010 (0.0010) -[2023-10-17 01:59:13,364][62408] Updated weights for policy 1, policy_version 42690 (0.0008) -[2023-10-17 01:59:13,575][62373] Updated weights for policy 0, policy_version 43020 (0.0009) -[2023-10-17 01:59:13,782][62408] Updated weights for policy 1, policy_version 42700 (0.0008) -[2023-10-17 01:59:13,949][62373] Updated weights for policy 0, policy_version 43030 (0.0008) -[2023-10-17 01:59:14,142][62408] Updated weights for policy 1, policy_version 42710 (0.0007) -[2023-10-17 01:59:14,308][62373] Updated weights for policy 0, policy_version 43040 (0.0008) -[2023-10-17 01:59:14,511][62408] Updated weights for policy 1, policy_version 42720 (0.0011) -[2023-10-17 01:59:17,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 87818240. Throughput: 0: 1780.9, 1: 1755.6. Samples: 21969348. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:59:17,215][61453] Avg episode reward: [(0, '10.040'), (1, '9.050')] -[2023-10-17 01:59:18,066][62373] Updated weights for policy 0, policy_version 43050 (0.0009) -[2023-10-17 01:59:18,218][62408] Updated weights for policy 1, policy_version 42730 (0.0008) -[2023-10-17 01:59:18,432][62373] Updated weights for policy 0, policy_version 43060 (0.0008) -[2023-10-17 01:59:18,582][62408] Updated weights for policy 1, policy_version 42740 (0.0008) -[2023-10-17 01:59:18,797][62373] Updated weights for policy 0, policy_version 43070 (0.0007) -[2023-10-17 01:59:18,954][62408] Updated weights for policy 1, policy_version 42750 (0.0008) -[2023-10-17 01:59:22,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 87883776. Throughput: 0: 1764.8, 1: 1747.8. Samples: 21978924. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:59:22,215][61453] Avg episode reward: [(0, '10.570'), (1, '9.200')] -[2023-10-17 01:59:22,641][62373] Updated weights for policy 0, policy_version 43080 (0.0008) -[2023-10-17 01:59:22,828][62408] Updated weights for policy 1, policy_version 42760 (0.0008) -[2023-10-17 01:59:23,008][62373] Updated weights for policy 0, policy_version 43090 (0.0007) -[2023-10-17 01:59:23,192][62408] Updated weights for policy 1, policy_version 42770 (0.0008) -[2023-10-17 01:59:23,372][62373] Updated weights for policy 0, policy_version 43100 (0.0009) -[2023-10-17 01:59:23,564][62408] Updated weights for policy 1, policy_version 42780 (0.0008) -[2023-10-17 01:59:27,179][62373] Updated weights for policy 0, policy_version 43110 (0.0008) -[2023-10-17 01:59:27,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 87949312. Throughput: 0: 1774.0, 1: 1745.6. Samples: 22000684. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:59:27,215][61453] Avg episode reward: [(0, '9.750'), (1, '9.040')] -[2023-10-17 01:59:27,504][62408] Updated weights for policy 1, policy_version 42790 (0.0007) -[2023-10-17 01:59:27,552][62373] Updated weights for policy 0, policy_version 43120 (0.0007) -[2023-10-17 01:59:27,870][62408] Updated weights for policy 1, policy_version 42800 (0.0007) -[2023-10-17 01:59:27,925][62373] Updated weights for policy 0, policy_version 43130 (0.0007) -[2023-10-17 01:59:28,242][62408] Updated weights for policy 1, policy_version 42810 (0.0008) -[2023-10-17 01:59:31,805][62373] Updated weights for policy 0, policy_version 43140 (0.0008) -[2023-10-17 01:59:32,122][62408] Updated weights for policy 1, policy_version 42820 (0.0010) -[2023-10-17 01:59:32,192][62373] Updated weights for policy 0, policy_version 43150 (0.0009) -[2023-10-17 01:59:32,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 88014848. Throughput: 0: 1788.0, 1: 1768.3. Samples: 22022146. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:59:32,215][61453] Avg episode reward: [(0, '10.290'), (1, '9.180')] -[2023-10-17 01:59:32,479][62408] Updated weights for policy 1, policy_version 42830 (0.0007) -[2023-10-17 01:59:32,566][62373] Updated weights for policy 0, policy_version 43160 (0.0008) -[2023-10-17 01:59:32,851][62408] Updated weights for policy 1, policy_version 42840 (0.0009) -[2023-10-17 01:59:32,854][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000043168_44204032.pth... -[2023-10-17 01:59:32,883][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000041504_42500096.pth -[2023-10-17 01:59:33,146][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000042848_43876352.pth... -[2023-10-17 01:59:33,185][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000041184_42172416.pth -[2023-10-17 01:59:36,353][62373] Updated weights for policy 0, policy_version 43170 (0.0009) -[2023-10-17 01:59:36,686][62408] Updated weights for policy 1, policy_version 42850 (0.0008) -[2023-10-17 01:59:36,710][62373] Updated weights for policy 0, policy_version 43180 (0.0007) -[2023-10-17 01:59:37,043][62408] Updated weights for policy 1, policy_version 42860 (0.0009) -[2023-10-17 01:59:37,076][62373] Updated weights for policy 0, policy_version 43190 (0.0007) -[2023-10-17 01:59:37,214][61453] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 13995.8). Total num frames: 88080384. Throughput: 0: 1756.7, 1: 1741.7. Samples: 22031984. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 01:59:37,215][61453] Avg episode reward: [(0, '9.720'), (1, '9.350')] -[2023-10-17 01:59:37,420][62408] Updated weights for policy 1, policy_version 42870 (0.0008) -[2023-10-17 01:59:37,455][62373] Updated weights for policy 0, policy_version 43200 (0.0007) -[2023-10-17 01:59:37,782][62408] Updated weights for policy 1, policy_version 42880 (0.0008) -[2023-10-17 01:59:41,328][62373] Updated weights for policy 0, policy_version 43210 (0.0009) -[2023-10-17 01:59:41,691][62373] Updated weights for policy 0, policy_version 43220 (0.0008) -[2023-10-17 01:59:41,719][62408] Updated weights for policy 1, policy_version 42890 (0.0007) -[2023-10-17 01:59:42,061][62373] Updated weights for policy 0, policy_version 43230 (0.0007) -[2023-10-17 01:59:42,087][62408] Updated weights for policy 1, policy_version 42900 (0.0007) -[2023-10-17 01:59:42,214][61453] Fps is (10 sec: 16384.7, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 88178688. Throughput: 0: 1787.0, 1: 1761.8. Samples: 22053798. Policy #0 lag: (min: 28.0, avg: 38.7, max: 60.0) -[2023-10-17 01:59:42,214][61453] Avg episode reward: [(0, '10.110'), (1, '9.210')] -[2023-10-17 01:59:42,463][62408] Updated weights for policy 1, policy_version 42910 (0.0009) -[2023-10-17 01:59:46,013][62373] Updated weights for policy 0, policy_version 43240 (0.0007) -[2023-10-17 01:59:46,199][62408] Updated weights for policy 1, policy_version 42920 (0.0008) -[2023-10-17 01:59:46,390][62373] Updated weights for policy 0, policy_version 43250 (0.0008) -[2023-10-17 01:59:46,568][62408] Updated weights for policy 1, policy_version 42930 (0.0009) -[2023-10-17 01:59:46,754][62373] Updated weights for policy 0, policy_version 43260 (0.0008) -[2023-10-17 01:59:46,936][62408] Updated weights for policy 1, policy_version 42940 (0.0008) -[2023-10-17 01:59:47,214][61453] Fps is (10 sec: 19660.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 88276992. Throughput: 0: 1759.5, 1: 1743.6. Samples: 22073380. Policy #0 lag: (min: 28.0, avg: 38.7, max: 60.0) -[2023-10-17 01:59:47,215][61453] Avg episode reward: [(0, '9.870'), (1, '9.290')] -[2023-10-17 01:59:50,702][62373] Updated weights for policy 0, policy_version 43270 (0.0010) -[2023-10-17 01:59:50,862][62408] Updated weights for policy 1, policy_version 42950 (0.0009) -[2023-10-17 01:59:51,061][62373] Updated weights for policy 0, policy_version 43280 (0.0009) -[2023-10-17 01:59:51,226][62408] Updated weights for policy 1, policy_version 42960 (0.0007) -[2023-10-17 01:59:51,434][62373] Updated weights for policy 0, policy_version 43290 (0.0008) -[2023-10-17 01:59:51,600][62408] Updated weights for policy 1, policy_version 42970 (0.0007) -[2023-10-17 01:59:52,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 88342528. Throughput: 0: 1779.4, 1: 1766.7. Samples: 22085408. Policy #0 lag: (min: 28.0, avg: 38.7, max: 60.0) -[2023-10-17 01:59:52,215][61453] Avg episode reward: [(0, '9.540'), (1, '9.330')] -[2023-10-17 01:59:55,198][62373] Updated weights for policy 0, policy_version 43300 (0.0008) -[2023-10-17 01:59:55,442][62408] Updated weights for policy 1, policy_version 42980 (0.0008) -[2023-10-17 01:59:55,574][62373] Updated weights for policy 0, policy_version 43310 (0.0008) -[2023-10-17 01:59:55,815][62408] Updated weights for policy 1, policy_version 42990 (0.0008) -[2023-10-17 01:59:55,936][62373] Updated weights for policy 0, policy_version 43320 (0.0007) -[2023-10-17 01:59:56,172][62408] Updated weights for policy 1, policy_version 43000 (0.0009) -[2023-10-17 01:59:57,214][61453] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 88408064. Throughput: 0: 1757.6, 1: 1761.5. Samples: 22105812. Policy #0 lag: (min: 28.0, avg: 38.7, max: 60.0) -[2023-10-17 01:59:57,214][61453] Avg episode reward: [(0, '9.540'), (1, '8.920')] -[2023-10-17 01:59:59,658][62373] Updated weights for policy 0, policy_version 43330 (0.0009) -[2023-10-17 02:00:00,030][62373] Updated weights for policy 0, policy_version 43340 (0.0009) -[2023-10-17 02:00:00,053][62408] Updated weights for policy 1, policy_version 43010 (0.0008) -[2023-10-17 02:00:00,391][62373] Updated weights for policy 0, policy_version 43350 (0.0008) -[2023-10-17 02:00:00,472][62408] Updated weights for policy 1, policy_version 43020 (0.0008) -[2023-10-17 02:00:00,754][62373] Updated weights for policy 0, policy_version 43360 (0.0008) -[2023-10-17 02:00:00,842][62408] Updated weights for policy 1, policy_version 43030 (0.0007) -[2023-10-17 02:00:01,206][62408] Updated weights for policy 1, policy_version 43040 (0.0007) -[2023-10-17 02:00:02,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 88473600. Throughput: 0: 1749.5, 1: 1741.9. Samples: 22126460. Policy #0 lag: (min: 28.0, avg: 38.7, max: 60.0) -[2023-10-17 02:00:02,215][61453] Avg episode reward: [(0, '9.420'), (1, '8.780')] -[2023-10-17 02:00:04,492][62373] Updated weights for policy 0, policy_version 43370 (0.0010) -[2023-10-17 02:00:04,865][62373] Updated weights for policy 0, policy_version 43380 (0.0008) -[2023-10-17 02:00:05,193][62408] Updated weights for policy 1, policy_version 43050 (0.0007) -[2023-10-17 02:00:05,239][62373] Updated weights for policy 0, policy_version 43390 (0.0010) -[2023-10-17 02:00:05,553][62408] Updated weights for policy 1, policy_version 43060 (0.0008) -[2023-10-17 02:00:05,912][62408] Updated weights for policy 1, policy_version 43070 (0.0009) -[2023-10-17 02:00:07,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 88539136. Throughput: 0: 1762.7, 1: 1767.4. Samples: 22137778. Policy #0 lag: (min: 28.0, avg: 38.7, max: 60.0) -[2023-10-17 02:00:07,214][61453] Avg episode reward: [(0, '9.560'), (1, '9.010')] -[2023-10-17 02:00:08,999][62373] Updated weights for policy 0, policy_version 43400 (0.0009) -[2023-10-17 02:00:09,364][62373] Updated weights for policy 0, policy_version 43410 (0.0011) -[2023-10-17 02:00:09,734][62373] Updated weights for policy 0, policy_version 43420 (0.0009) -[2023-10-17 02:00:09,817][62408] Updated weights for policy 1, policy_version 43080 (0.0008) -[2023-10-17 02:00:10,187][62408] Updated weights for policy 1, policy_version 43090 (0.0009) -[2023-10-17 02:00:10,552][62408] Updated weights for policy 1, policy_version 43100 (0.0010) -[2023-10-17 02:00:12,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 88604672. Throughput: 0: 1755.7, 1: 1738.9. Samples: 22157942. Policy #0 lag: (min: 28.0, avg: 38.7, max: 60.0) -[2023-10-17 02:00:12,215][61453] Avg episode reward: [(0, '9.490'), (1, '8.850')] -[2023-10-17 02:00:13,694][62373] Updated weights for policy 0, policy_version 43430 (0.0011) -[2023-10-17 02:00:14,065][62373] Updated weights for policy 0, policy_version 43440 (0.0010) -[2023-10-17 02:00:14,285][62408] Updated weights for policy 1, policy_version 43110 (0.0008) -[2023-10-17 02:00:14,439][62373] Updated weights for policy 0, policy_version 43450 (0.0008) -[2023-10-17 02:00:14,646][62408] Updated weights for policy 1, policy_version 43120 (0.0009) -[2023-10-17 02:00:15,017][62408] Updated weights for policy 1, policy_version 43130 (0.0010) -[2023-10-17 02:00:17,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 88670208. Throughput: 0: 1766.3, 1: 1736.8. Samples: 22179782. Policy #0 lag: (min: 26.0, avg: 26.0, max: 26.0) -[2023-10-17 02:00:17,214][61453] Avg episode reward: [(0, '10.510'), (1, '9.270')] -[2023-10-17 02:00:18,235][62373] Updated weights for policy 0, policy_version 43460 (0.0008) -[2023-10-17 02:00:18,608][62373] Updated weights for policy 0, policy_version 43470 (0.0007) -[2023-10-17 02:00:18,974][62373] Updated weights for policy 0, policy_version 43480 (0.0008) -[2023-10-17 02:00:18,986][62408] Updated weights for policy 1, policy_version 43140 (0.0008) -[2023-10-17 02:00:19,351][62408] Updated weights for policy 1, policy_version 43150 (0.0007) -[2023-10-17 02:00:19,719][62408] Updated weights for policy 1, policy_version 43160 (0.0007) -[2023-10-17 02:00:22,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 88735744. Throughput: 0: 1762.5, 1: 1741.0. Samples: 22189642. Policy #0 lag: (min: 26.0, avg: 26.0, max: 26.0) -[2023-10-17 02:00:22,214][61453] Avg episode reward: [(0, '10.170'), (1, '8.780')] -[2023-10-17 02:00:22,669][62373] Updated weights for policy 0, policy_version 43490 (0.0008) -[2023-10-17 02:00:23,034][62373] Updated weights for policy 0, policy_version 43500 (0.0008) -[2023-10-17 02:00:23,409][62373] Updated weights for policy 0, policy_version 43510 (0.0009) -[2023-10-17 02:00:23,598][62408] Updated weights for policy 1, policy_version 43170 (0.0008) -[2023-10-17 02:00:23,785][62373] Updated weights for policy 0, policy_version 43520 (0.0007) -[2023-10-17 02:00:23,973][62408] Updated weights for policy 1, policy_version 43180 (0.0009) -[2023-10-17 02:00:24,331][62408] Updated weights for policy 1, policy_version 43190 (0.0010) -[2023-10-17 02:00:24,697][62408] Updated weights for policy 1, policy_version 43200 (0.0008) -[2023-10-17 02:00:27,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 88801280. Throughput: 0: 1764.0, 1: 1738.2. Samples: 22211394. Policy #0 lag: (min: 26.0, avg: 26.0, max: 26.0) -[2023-10-17 02:00:27,215][61453] Avg episode reward: [(0, '10.050'), (1, '8.810')] -[2023-10-17 02:00:27,613][62373] Updated weights for policy 0, policy_version 43530 (0.0008) -[2023-10-17 02:00:27,987][62373] Updated weights for policy 0, policy_version 43540 (0.0008) -[2023-10-17 02:00:28,347][62408] Updated weights for policy 1, policy_version 43210 (0.0007) -[2023-10-17 02:00:28,353][62373] Updated weights for policy 0, policy_version 43550 (0.0007) -[2023-10-17 02:00:28,714][62408] Updated weights for policy 1, policy_version 43220 (0.0008) -[2023-10-17 02:00:29,087][62408] Updated weights for policy 1, policy_version 43230 (0.0009) -[2023-10-17 02:00:32,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.6, 300 sec: 13995.8). Total num frames: 88866816. Throughput: 0: 1797.6, 1: 1761.5. Samples: 22233538. Policy #0 lag: (min: 26.0, avg: 26.0, max: 26.0) -[2023-10-17 02:00:32,214][61453] Avg episode reward: [(0, '10.800'), (1, '9.000')] -[2023-10-17 02:00:32,327][62373] Updated weights for policy 0, policy_version 43560 (0.0008) -[2023-10-17 02:00:32,701][62373] Updated weights for policy 0, policy_version 43570 (0.0009) -[2023-10-17 02:00:32,879][62408] Updated weights for policy 1, policy_version 43240 (0.0007) -[2023-10-17 02:00:33,070][62373] Updated weights for policy 0, policy_version 43580 (0.0008) -[2023-10-17 02:00:33,215][62094] Saving new best policy, reward=10.800! -[2023-10-17 02:00:33,250][62408] Updated weights for policy 1, policy_version 43250 (0.0008) -[2023-10-17 02:00:33,614][62408] Updated weights for policy 1, policy_version 43260 (0.0011) -[2023-10-17 02:00:36,748][62373] Updated weights for policy 0, policy_version 43590 (0.0008) -[2023-10-17 02:00:37,114][62373] Updated weights for policy 0, policy_version 43600 (0.0010) -[2023-10-17 02:00:37,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 88932352. Throughput: 0: 1766.4, 1: 1731.6. Samples: 22242820. Policy #0 lag: (min: 26.0, avg: 26.0, max: 26.0) -[2023-10-17 02:00:37,214][61453] Avg episode reward: [(0, '10.670'), (1, '9.120')] -[2023-10-17 02:00:37,482][62373] Updated weights for policy 0, policy_version 43610 (0.0010) -[2023-10-17 02:00:37,583][62408] Updated weights for policy 1, policy_version 43270 (0.0008) -[2023-10-17 02:00:37,951][62408] Updated weights for policy 1, policy_version 43280 (0.0007) -[2023-10-17 02:00:38,321][62408] Updated weights for policy 1, policy_version 43290 (0.0007) -[2023-10-17 02:00:41,309][62373] Updated weights for policy 0, policy_version 43620 (0.0009) -[2023-10-17 02:00:41,676][62373] Updated weights for policy 0, policy_version 43630 (0.0008) -[2023-10-17 02:00:42,047][62373] Updated weights for policy 0, policy_version 43640 (0.0007) -[2023-10-17 02:00:42,203][62408] Updated weights for policy 1, policy_version 43300 (0.0009) -[2023-10-17 02:00:42,214][61453] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 13995.8). Total num frames: 88997888. Throughput: 0: 1791.9, 1: 1742.7. Samples: 22264868. Policy #0 lag: (min: 26.0, avg: 26.0, max: 26.0) -[2023-10-17 02:00:42,214][61453] Avg episode reward: [(0, '10.860'), (1, '9.220')] -[2023-10-17 02:00:42,337][62094] Saving new best policy, reward=10.860! -[2023-10-17 02:00:42,562][62408] Updated weights for policy 1, policy_version 43310 (0.0009) -[2023-10-17 02:00:42,930][62408] Updated weights for policy 1, policy_version 43320 (0.0007) -[2023-10-17 02:00:45,812][62373] Updated weights for policy 0, policy_version 43650 (0.0008) -[2023-10-17 02:00:46,187][62373] Updated weights for policy 0, policy_version 43660 (0.0008) -[2023-10-17 02:00:46,558][62373] Updated weights for policy 0, policy_version 43670 (0.0009) -[2023-10-17 02:00:46,740][62408] Updated weights for policy 1, policy_version 43330 (0.0008) -[2023-10-17 02:00:46,924][62373] Updated weights for policy 0, policy_version 43680 (0.0008) -[2023-10-17 02:00:47,142][62408] Updated weights for policy 1, policy_version 43340 (0.0008) -[2023-10-17 02:00:47,214][61453] Fps is (10 sec: 16383.9, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 89096192. Throughput: 0: 1762.8, 1: 1769.1. Samples: 22285396. Policy #0 lag: (min: 25.0, avg: 28.3, max: 55.0) -[2023-10-17 02:00:47,214][61453] Avg episode reward: [(0, '10.730'), (1, '9.610')] -[2023-10-17 02:00:47,502][62408] Updated weights for policy 1, policy_version 43350 (0.0008) -[2023-10-17 02:00:47,876][62408] Updated weights for policy 1, policy_version 43360 (0.0012) -[2023-10-17 02:00:50,702][62373] Updated weights for policy 0, policy_version 43690 (0.0010) -[2023-10-17 02:00:51,074][62373] Updated weights for policy 0, policy_version 43700 (0.0009) -[2023-10-17 02:00:51,439][62373] Updated weights for policy 0, policy_version 43710 (0.0008) -[2023-10-17 02:00:51,675][62408] Updated weights for policy 1, policy_version 43370 (0.0007) -[2023-10-17 02:00:52,045][62408] Updated weights for policy 1, policy_version 43380 (0.0008) -[2023-10-17 02:00:52,214][61453] Fps is (10 sec: 16383.8, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 89161728. Throughput: 0: 1782.0, 1: 1744.8. Samples: 22296482. Policy #0 lag: (min: 25.0, avg: 28.3, max: 55.0) -[2023-10-17 02:00:52,215][61453] Avg episode reward: [(0, '9.890'), (1, '9.260')] -[2023-10-17 02:00:52,413][62408] Updated weights for policy 1, policy_version 43390 (0.0008) -[2023-10-17 02:00:55,190][62373] Updated weights for policy 0, policy_version 43720 (0.0007) -[2023-10-17 02:00:55,569][62373] Updated weights for policy 0, policy_version 43730 (0.0008) -[2023-10-17 02:00:55,941][62373] Updated weights for policy 0, policy_version 43740 (0.0010) -[2023-10-17 02:00:56,282][62408] Updated weights for policy 1, policy_version 43400 (0.0007) -[2023-10-17 02:00:56,651][62408] Updated weights for policy 1, policy_version 43410 (0.0007) -[2023-10-17 02:00:57,010][62408] Updated weights for policy 1, policy_version 43420 (0.0009) -[2023-10-17 02:00:57,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 89260032. Throughput: 0: 1765.0, 1: 1779.3. Samples: 22317436. Policy #0 lag: (min: 25.0, avg: 28.3, max: 55.0) -[2023-10-17 02:00:57,215][61453] Avg episode reward: [(0, '9.930'), (1, '9.420')] -[2023-10-17 02:00:59,720][62373] Updated weights for policy 0, policy_version 43750 (0.0010) -[2023-10-17 02:01:00,089][62373] Updated weights for policy 0, policy_version 43760 (0.0007) -[2023-10-17 02:01:00,460][62373] Updated weights for policy 0, policy_version 43770 (0.0009) -[2023-10-17 02:01:01,082][62408] Updated weights for policy 1, policy_version 43430 (0.0009) -[2023-10-17 02:01:01,458][62408] Updated weights for policy 1, policy_version 43440 (0.0011) -[2023-10-17 02:01:01,823][62408] Updated weights for policy 1, policy_version 43450 (0.0009) -[2023-10-17 02:01:02,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 89325568. Throughput: 0: 1766.8, 1: 1748.0. Samples: 22337944. Policy #0 lag: (min: 25.0, avg: 28.3, max: 55.0) -[2023-10-17 02:01:02,215][61453] Avg episode reward: [(0, '9.960'), (1, '8.750')] -[2023-10-17 02:01:04,316][62373] Updated weights for policy 0, policy_version 43780 (0.0010) -[2023-10-17 02:01:04,699][62373] Updated weights for policy 0, policy_version 43790 (0.0009) -[2023-10-17 02:01:05,063][62373] Updated weights for policy 0, policy_version 43800 (0.0011) -[2023-10-17 02:01:05,594][62408] Updated weights for policy 1, policy_version 43460 (0.0009) -[2023-10-17 02:01:05,957][62408] Updated weights for policy 1, policy_version 43470 (0.0009) -[2023-10-17 02:01:06,331][62408] Updated weights for policy 1, policy_version 43480 (0.0008) -[2023-10-17 02:01:07,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 89391104. Throughput: 0: 1774.8, 1: 1770.8. Samples: 22349194. Policy #0 lag: (min: 25.0, avg: 28.3, max: 55.0) -[2023-10-17 02:01:07,215][61453] Avg episode reward: [(0, '9.360'), (1, '8.310')] -[2023-10-17 02:01:08,900][62373] Updated weights for policy 0, policy_version 43810 (0.0010) -[2023-10-17 02:01:09,260][62373] Updated weights for policy 0, policy_version 43820 (0.0009) -[2023-10-17 02:01:09,634][62373] Updated weights for policy 0, policy_version 43830 (0.0008) -[2023-10-17 02:01:10,011][62373] Updated weights for policy 0, policy_version 43840 (0.0009) -[2023-10-17 02:01:10,270][62408] Updated weights for policy 1, policy_version 43490 (0.0009) -[2023-10-17 02:01:10,634][62408] Updated weights for policy 1, policy_version 43500 (0.0009) -[2023-10-17 02:01:11,001][62408] Updated weights for policy 1, policy_version 43510 (0.0008) -[2023-10-17 02:01:11,378][62408] Updated weights for policy 1, policy_version 43520 (0.0010) -[2023-10-17 02:01:12,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 89456640. Throughput: 0: 1762.9, 1: 1759.1. Samples: 22369882. Policy #0 lag: (min: 25.0, avg: 28.3, max: 55.0) -[2023-10-17 02:01:12,215][61453] Avg episode reward: [(0, '9.350'), (1, '9.080')] -[2023-10-17 02:01:13,946][62373] Updated weights for policy 0, policy_version 43850 (0.0009) -[2023-10-17 02:01:14,315][62373] Updated weights for policy 0, policy_version 43860 (0.0009) -[2023-10-17 02:01:14,682][62373] Updated weights for policy 0, policy_version 43870 (0.0009) -[2023-10-17 02:01:15,098][62408] Updated weights for policy 1, policy_version 43530 (0.0009) -[2023-10-17 02:01:15,467][62408] Updated weights for policy 1, policy_version 43540 (0.0008) -[2023-10-17 02:01:15,830][62408] Updated weights for policy 1, policy_version 43550 (0.0010) -[2023-10-17 02:01:17,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 89522176. Throughput: 0: 1761.5, 1: 1740.3. Samples: 22391122. Policy #0 lag: (min: 25.0, avg: 28.3, max: 55.0) -[2023-10-17 02:01:17,215][61453] Avg episode reward: [(0, '9.730'), (1, '9.060')] -[2023-10-17 02:01:18,540][62373] Updated weights for policy 0, policy_version 43880 (0.0008) -[2023-10-17 02:01:18,915][62373] Updated weights for policy 0, policy_version 43890 (0.0007) -[2023-10-17 02:01:19,293][62373] Updated weights for policy 0, policy_version 43900 (0.0009) -[2023-10-17 02:01:19,757][62408] Updated weights for policy 1, policy_version 43560 (0.0009) -[2023-10-17 02:01:20,123][62408] Updated weights for policy 1, policy_version 43570 (0.0007) -[2023-10-17 02:01:20,487][62408] Updated weights for policy 1, policy_version 43580 (0.0010) -[2023-10-17 02:01:22,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 89587712. Throughput: 0: 1763.0, 1: 1762.1. Samples: 22401452. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-17 02:01:22,215][61453] Avg episode reward: [(0, '9.100'), (1, '8.450')] -[2023-10-17 02:01:23,081][62373] Updated weights for policy 0, policy_version 43910 (0.0009) -[2023-10-17 02:01:23,443][62373] Updated weights for policy 0, policy_version 43920 (0.0011) -[2023-10-17 02:01:23,814][62373] Updated weights for policy 0, policy_version 43930 (0.0010) -[2023-10-17 02:01:24,262][62408] Updated weights for policy 1, policy_version 43590 (0.0008) -[2023-10-17 02:01:24,635][62408] Updated weights for policy 1, policy_version 43600 (0.0009) -[2023-10-17 02:01:25,000][62408] Updated weights for policy 1, policy_version 43610 (0.0007) -[2023-10-17 02:01:27,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 89653248. Throughput: 0: 1757.6, 1: 1749.9. Samples: 22422706. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-17 02:01:27,214][61453] Avg episode reward: [(0, '9.030'), (1, '8.490')] -[2023-10-17 02:01:27,377][62373] Updated weights for policy 0, policy_version 43940 (0.0007) -[2023-10-17 02:01:27,741][62373] Updated weights for policy 0, policy_version 43950 (0.0008) -[2023-10-17 02:01:28,109][62373] Updated weights for policy 0, policy_version 43960 (0.0009) -[2023-10-17 02:01:28,740][62408] Updated weights for policy 1, policy_version 43620 (0.0008) -[2023-10-17 02:01:29,119][62408] Updated weights for policy 1, policy_version 43630 (0.0009) -[2023-10-17 02:01:29,487][62408] Updated weights for policy 1, policy_version 43640 (0.0008) -[2023-10-17 02:01:31,886][62373] Updated weights for policy 0, policy_version 43970 (0.0010) -[2023-10-17 02:01:32,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 89718784. Throughput: 0: 1793.0, 1: 1750.0. Samples: 22444832. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-17 02:01:32,215][61453] Avg episode reward: [(0, '9.640'), (1, '9.090')] -[2023-10-17 02:01:32,227][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000043648_44695552.pth... -[2023-10-17 02:01:32,253][62373] Updated weights for policy 0, policy_version 43980 (0.0008) -[2023-10-17 02:01:32,260][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000042016_43024384.pth -[2023-10-17 02:01:32,618][62373] Updated weights for policy 0, policy_version 43990 (0.0009) -[2023-10-17 02:01:32,983][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000044000_45056000.pth... -[2023-10-17 02:01:32,984][62373] Updated weights for policy 0, policy_version 44000 (0.0007) -[2023-10-17 02:01:33,014][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000042336_43352064.pth -[2023-10-17 02:01:33,220][62408] Updated weights for policy 1, policy_version 43650 (0.0008) -[2023-10-17 02:01:33,589][62408] Updated weights for policy 1, policy_version 43660 (0.0008) -[2023-10-17 02:01:33,962][62408] Updated weights for policy 1, policy_version 43670 (0.0010) -[2023-10-17 02:01:34,329][62408] Updated weights for policy 1, policy_version 43680 (0.0011) -[2023-10-17 02:01:36,798][62373] Updated weights for policy 0, policy_version 44010 (0.0009) -[2023-10-17 02:01:37,163][62373] Updated weights for policy 0, policy_version 44020 (0.0008) -[2023-10-17 02:01:37,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 89784320. Throughput: 0: 1770.0, 1: 1748.4. Samples: 22454814. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-17 02:01:37,215][61453] Avg episode reward: [(0, '9.730'), (1, '9.150')] -[2023-10-17 02:01:37,532][62373] Updated weights for policy 0, policy_version 44030 (0.0007) -[2023-10-17 02:01:38,252][62408] Updated weights for policy 1, policy_version 43690 (0.0009) -[2023-10-17 02:01:38,629][62408] Updated weights for policy 1, policy_version 43700 (0.0008) -[2023-10-17 02:01:39,000][62408] Updated weights for policy 1, policy_version 43710 (0.0009) -[2023-10-17 02:01:41,329][62373] Updated weights for policy 0, policy_version 44040 (0.0008) -[2023-10-17 02:01:41,697][62373] Updated weights for policy 0, policy_version 44050 (0.0008) -[2023-10-17 02:01:42,074][62373] Updated weights for policy 0, policy_version 44060 (0.0008) -[2023-10-17 02:01:42,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 89849856. Throughput: 0: 1792.4, 1: 1740.7. Samples: 22476426. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-17 02:01:42,215][61453] Avg episode reward: [(0, '10.160'), (1, '9.380')] -[2023-10-17 02:01:43,041][62408] Updated weights for policy 1, policy_version 43720 (0.0008) -[2023-10-17 02:01:43,404][62408] Updated weights for policy 1, policy_version 43730 (0.0008) -[2023-10-17 02:01:43,774][62408] Updated weights for policy 1, policy_version 43740 (0.0009) -[2023-10-17 02:01:45,936][62373] Updated weights for policy 0, policy_version 44070 (0.0008) -[2023-10-17 02:01:46,305][62373] Updated weights for policy 0, policy_version 44080 (0.0008) -[2023-10-17 02:01:46,674][62373] Updated weights for policy 0, policy_version 44090 (0.0008) -[2023-10-17 02:01:47,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 89948160. Throughput: 0: 1761.9, 1: 1771.4. Samples: 22496940. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-17 02:01:47,215][61453] Avg episode reward: [(0, '9.920'), (1, '9.560')] -[2023-10-17 02:01:47,760][62408] Updated weights for policy 1, policy_version 43750 (0.0008) -[2023-10-17 02:01:48,131][62408] Updated weights for policy 1, policy_version 43760 (0.0007) -[2023-10-17 02:01:48,502][62408] Updated weights for policy 1, policy_version 43770 (0.0009) -[2023-10-17 02:01:50,549][62373] Updated weights for policy 0, policy_version 44100 (0.0011) -[2023-10-17 02:01:50,917][62373] Updated weights for policy 0, policy_version 44110 (0.0010) -[2023-10-17 02:01:51,288][62373] Updated weights for policy 0, policy_version 44120 (0.0010) -[2023-10-17 02:01:52,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 90013696. Throughput: 0: 1782.5, 1: 1741.7. Samples: 22507784. Policy #0 lag: (min: 31.0, avg: 31.2, max: 41.0) -[2023-10-17 02:01:52,215][61453] Avg episode reward: [(0, '9.460'), (1, '9.100')] -[2023-10-17 02:01:52,248][62408] Updated weights for policy 1, policy_version 43780 (0.0008) -[2023-10-17 02:01:52,620][62408] Updated weights for policy 1, policy_version 43790 (0.0009) -[2023-10-17 02:01:52,981][62408] Updated weights for policy 1, policy_version 43800 (0.0007) -[2023-10-17 02:01:54,998][62373] Updated weights for policy 0, policy_version 44130 (0.0010) -[2023-10-17 02:01:55,368][62373] Updated weights for policy 0, policy_version 44140 (0.0008) -[2023-10-17 02:01:55,748][62373] Updated weights for policy 0, policy_version 44150 (0.0010) -[2023-10-17 02:01:56,107][62373] Updated weights for policy 0, policy_version 44160 (0.0009) -[2023-10-17 02:01:56,711][62408] Updated weights for policy 1, policy_version 43810 (0.0009) -[2023-10-17 02:01:57,075][62408] Updated weights for policy 1, policy_version 43820 (0.0011) -[2023-10-17 02:01:57,214][61453] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 90079232. Throughput: 0: 1769.8, 1: 1763.6. Samples: 22528888. Policy #0 lag: (min: 31.0, avg: 31.2, max: 41.0) -[2023-10-17 02:01:57,215][61453] Avg episode reward: [(0, '9.870'), (1, '8.960')] -[2023-10-17 02:01:57,442][62408] Updated weights for policy 1, policy_version 43830 (0.0008) -[2023-10-17 02:01:57,817][62408] Updated weights for policy 1, policy_version 43840 (0.0010) -[2023-10-17 02:01:59,866][62373] Updated weights for policy 0, policy_version 44170 (0.0007) -[2023-10-17 02:02:00,232][62373] Updated weights for policy 0, policy_version 44180 (0.0009) -[2023-10-17 02:02:00,596][62373] Updated weights for policy 0, policy_version 44190 (0.0010) -[2023-10-17 02:02:01,592][62408] Updated weights for policy 1, policy_version 43850 (0.0009) -[2023-10-17 02:02:01,960][62408] Updated weights for policy 1, policy_version 43860 (0.0009) -[2023-10-17 02:02:02,214][61453] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 90144768. Throughput: 0: 1767.3, 1: 1764.2. Samples: 22550040. Policy #0 lag: (min: 31.0, avg: 31.2, max: 41.0) -[2023-10-17 02:02:02,214][61453] Avg episode reward: [(0, '9.950'), (1, '9.610')] -[2023-10-17 02:02:02,330][62408] Updated weights for policy 1, policy_version 43870 (0.0011) -[2023-10-17 02:02:04,488][62373] Updated weights for policy 0, policy_version 44200 (0.0009) -[2023-10-17 02:02:04,864][62373] Updated weights for policy 0, policy_version 44210 (0.0008) -[2023-10-17 02:02:05,231][62373] Updated weights for policy 0, policy_version 44220 (0.0007) -[2023-10-17 02:02:06,243][62408] Updated weights for policy 1, policy_version 43880 (0.0008) -[2023-10-17 02:02:06,609][62408] Updated weights for policy 1, policy_version 43890 (0.0008) -[2023-10-17 02:02:06,982][62408] Updated weights for policy 1, policy_version 43900 (0.0009) -[2023-10-17 02:02:07,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 90243072. Throughput: 0: 1781.5, 1: 1760.1. Samples: 22560824. Policy #0 lag: (min: 31.0, avg: 31.2, max: 41.0) -[2023-10-17 02:02:07,214][61453] Avg episode reward: [(0, '9.820'), (1, '9.990')] -[2023-10-17 02:02:08,944][62373] Updated weights for policy 0, policy_version 44230 (0.0010) -[2023-10-17 02:02:09,307][62373] Updated weights for policy 0, policy_version 44240 (0.0011) -[2023-10-17 02:02:09,678][62373] Updated weights for policy 0, policy_version 44250 (0.0011) -[2023-10-17 02:02:10,759][62408] Updated weights for policy 1, policy_version 43910 (0.0008) -[2023-10-17 02:02:11,134][62408] Updated weights for policy 1, policy_version 43920 (0.0009) -[2023-10-17 02:02:11,499][62408] Updated weights for policy 1, policy_version 43930 (0.0009) -[2023-10-17 02:02:12,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 90308608. Throughput: 0: 1773.4, 1: 1773.4. Samples: 22582314. Policy #0 lag: (min: 31.0, avg: 31.2, max: 41.0) -[2023-10-17 02:02:12,214][61453] Avg episode reward: [(0, '10.160'), (1, '9.420')] -[2023-10-17 02:02:13,480][62373] Updated weights for policy 0, policy_version 44260 (0.0009) -[2023-10-17 02:02:13,842][62373] Updated weights for policy 0, policy_version 44270 (0.0010) -[2023-10-17 02:02:14,208][62373] Updated weights for policy 0, policy_version 44280 (0.0009) -[2023-10-17 02:02:15,370][62408] Updated weights for policy 1, policy_version 43940 (0.0008) -[2023-10-17 02:02:15,735][62408] Updated weights for policy 1, policy_version 43950 (0.0008) -[2023-10-17 02:02:16,102][62408] Updated weights for policy 1, policy_version 43960 (0.0007) -[2023-10-17 02:02:17,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 90374144. Throughput: 0: 1769.7, 1: 1748.4. Samples: 22603148. Policy #0 lag: (min: 31.0, avg: 31.2, max: 41.0) -[2023-10-17 02:02:17,215][61453] Avg episode reward: [(0, '10.270'), (1, '9.290')] -[2023-10-17 02:02:18,086][62373] Updated weights for policy 0, policy_version 44290 (0.0009) -[2023-10-17 02:02:18,458][62373] Updated weights for policy 0, policy_version 44300 (0.0008) -[2023-10-17 02:02:18,817][62373] Updated weights for policy 0, policy_version 44310 (0.0008) -[2023-10-17 02:02:19,184][62373] Updated weights for policy 0, policy_version 44320 (0.0010) -[2023-10-17 02:02:19,960][62408] Updated weights for policy 1, policy_version 43970 (0.0009) -[2023-10-17 02:02:20,372][62408] Updated weights for policy 1, policy_version 43980 (0.0010) -[2023-10-17 02:02:20,731][62408] Updated weights for policy 1, policy_version 43990 (0.0008) -[2023-10-17 02:02:21,105][62408] Updated weights for policy 1, policy_version 44000 (0.0007) -[2023-10-17 02:02:22,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 90439680. Throughput: 0: 1763.7, 1: 1781.1. Samples: 22614330. Policy #0 lag: (min: 31.0, avg: 31.2, max: 41.0) -[2023-10-17 02:02:22,214][61453] Avg episode reward: [(0, '9.980'), (1, '8.950')] -[2023-10-17 02:02:23,008][62373] Updated weights for policy 0, policy_version 44330 (0.0009) -[2023-10-17 02:02:23,376][62373] Updated weights for policy 0, policy_version 44340 (0.0008) -[2023-10-17 02:02:23,749][62373] Updated weights for policy 0, policy_version 44350 (0.0010) -[2023-10-17 02:02:24,895][62408] Updated weights for policy 1, policy_version 44010 (0.0007) -[2023-10-17 02:02:25,257][62408] Updated weights for policy 1, policy_version 44020 (0.0009) -[2023-10-17 02:02:25,631][62408] Updated weights for policy 1, policy_version 44030 (0.0011) -[2023-10-17 02:02:27,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 90505216. Throughput: 0: 1767.7, 1: 1754.5. Samples: 22634924. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-17 02:02:27,214][61453] Avg episode reward: [(0, '10.410'), (1, '8.760')] -[2023-10-17 02:02:27,570][62373] Updated weights for policy 0, policy_version 44360 (0.0009) -[2023-10-17 02:02:27,950][62373] Updated weights for policy 0, policy_version 44370 (0.0010) -[2023-10-17 02:02:28,322][62373] Updated weights for policy 0, policy_version 44380 (0.0008) -[2023-10-17 02:02:29,525][62408] Updated weights for policy 1, policy_version 44040 (0.0007) -[2023-10-17 02:02:29,897][62408] Updated weights for policy 1, policy_version 44050 (0.0009) -[2023-10-17 02:02:30,254][62408] Updated weights for policy 1, policy_version 44060 (0.0010) -[2023-10-17 02:02:32,156][62373] Updated weights for policy 0, policy_version 44390 (0.0008) -[2023-10-17 02:02:32,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 90570752. Throughput: 0: 1803.5, 1: 1750.7. Samples: 22656876. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-17 02:02:32,215][61453] Avg episode reward: [(0, '10.320'), (1, '8.250')] -[2023-10-17 02:02:32,532][62373] Updated weights for policy 0, policy_version 44400 (0.0009) -[2023-10-17 02:02:32,898][62373] Updated weights for policy 0, policy_version 44410 (0.0009) -[2023-10-17 02:02:34,100][62408] Updated weights for policy 1, policy_version 44070 (0.0010) -[2023-10-17 02:02:34,471][62408] Updated weights for policy 1, policy_version 44080 (0.0010) -[2023-10-17 02:02:34,847][62408] Updated weights for policy 1, policy_version 44090 (0.0009) -[2023-10-17 02:02:36,557][62373] Updated weights for policy 0, policy_version 44420 (0.0009) -[2023-10-17 02:02:36,918][62373] Updated weights for policy 0, policy_version 44430 (0.0009) -[2023-10-17 02:02:37,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 90636288. Throughput: 0: 1775.1, 1: 1761.1. Samples: 22666910. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-17 02:02:37,214][61453] Avg episode reward: [(0, '9.800'), (1, '8.080')] -[2023-10-17 02:02:37,284][62373] Updated weights for policy 0, policy_version 44440 (0.0008) -[2023-10-17 02:02:38,658][62408] Updated weights for policy 1, policy_version 44100 (0.0009) -[2023-10-17 02:02:39,025][62408] Updated weights for policy 1, policy_version 44110 (0.0009) -[2023-10-17 02:02:39,399][62408] Updated weights for policy 1, policy_version 44120 (0.0008) -[2023-10-17 02:02:41,008][62373] Updated weights for policy 0, policy_version 44450 (0.0008) -[2023-10-17 02:02:41,386][62373] Updated weights for policy 0, policy_version 44460 (0.0011) -[2023-10-17 02:02:41,750][62373] Updated weights for policy 0, policy_version 44470 (0.0009) -[2023-10-17 02:02:42,117][62373] Updated weights for policy 0, policy_version 44480 (0.0008) -[2023-10-17 02:02:42,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14745.7, 300 sec: 14106.9). Total num frames: 90734592. Throughput: 0: 1802.5, 1: 1748.9. Samples: 22688702. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-17 02:02:42,214][61453] Avg episode reward: [(0, '9.520'), (1, '8.520')] -[2023-10-17 02:02:43,173][62408] Updated weights for policy 1, policy_version 44130 (0.0008) -[2023-10-17 02:02:43,554][62408] Updated weights for policy 1, policy_version 44140 (0.0009) -[2023-10-17 02:02:43,923][62408] Updated weights for policy 1, policy_version 44150 (0.0009) -[2023-10-17 02:02:44,288][62408] Updated weights for policy 1, policy_version 44160 (0.0011) -[2023-10-17 02:02:46,016][62373] Updated weights for policy 0, policy_version 44490 (0.0009) -[2023-10-17 02:02:46,378][62373] Updated weights for policy 0, policy_version 44500 (0.0009) -[2023-10-17 02:02:46,753][62373] Updated weights for policy 0, policy_version 44510 (0.0007) -[2023-10-17 02:02:47,214][61453] Fps is (10 sec: 16383.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 90800128. Throughput: 0: 1772.2, 1: 1771.6. Samples: 22709512. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-17 02:02:47,215][61453] Avg episode reward: [(0, '9.580'), (1, '8.560')] -[2023-10-17 02:02:48,129][62408] Updated weights for policy 1, policy_version 44170 (0.0009) -[2023-10-17 02:02:48,500][62408] Updated weights for policy 1, policy_version 44180 (0.0007) -[2023-10-17 02:02:48,866][62408] Updated weights for policy 1, policy_version 44190 (0.0008) -[2023-10-17 02:02:50,584][62373] Updated weights for policy 0, policy_version 44520 (0.0009) -[2023-10-17 02:02:50,965][62373] Updated weights for policy 0, policy_version 44530 (0.0011) -[2023-10-17 02:02:51,330][62373] Updated weights for policy 0, policy_version 44540 (0.0008) -[2023-10-17 02:02:52,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 90865664. Throughput: 0: 1793.3, 1: 1753.4. Samples: 22720426. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-10-17 02:02:52,214][61453] Avg episode reward: [(0, '9.510'), (1, '8.470')] -[2023-10-17 02:02:52,813][62408] Updated weights for policy 1, policy_version 44200 (0.0008) -[2023-10-17 02:02:53,177][62408] Updated weights for policy 1, policy_version 44210 (0.0009) -[2023-10-17 02:02:53,545][62408] Updated weights for policy 1, policy_version 44220 (0.0007) -[2023-10-17 02:02:55,031][62373] Updated weights for policy 0, policy_version 44550 (0.0009) -[2023-10-17 02:02:55,407][62373] Updated weights for policy 0, policy_version 44560 (0.0009) -[2023-10-17 02:02:55,775][62373] Updated weights for policy 0, policy_version 44570 (0.0007) -[2023-10-17 02:02:57,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 90931200. Throughput: 0: 1775.1, 1: 1762.3. Samples: 22741496. Policy #0 lag: (min: 16.0, avg: 42.5, max: 48.0) -[2023-10-17 02:02:57,214][61453] Avg episode reward: [(0, '9.620'), (1, '8.140')] -[2023-10-17 02:02:57,357][62408] Updated weights for policy 1, policy_version 44230 (0.0008) -[2023-10-17 02:02:57,722][62408] Updated weights for policy 1, policy_version 44240 (0.0007) -[2023-10-17 02:02:58,091][62408] Updated weights for policy 1, policy_version 44250 (0.0008) -[2023-10-17 02:02:59,436][62373] Updated weights for policy 0, policy_version 44580 (0.0007) -[2023-10-17 02:02:59,811][62373] Updated weights for policy 0, policy_version 44590 (0.0008) -[2023-10-17 02:03:00,179][62373] Updated weights for policy 0, policy_version 44600 (0.0007) -[2023-10-17 02:03:01,912][62408] Updated weights for policy 1, policy_version 44260 (0.0008) -[2023-10-17 02:03:02,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 90996736. Throughput: 0: 1777.9, 1: 1795.0. Samples: 22763930. Policy #0 lag: (min: 16.0, avg: 42.5, max: 48.0) -[2023-10-17 02:03:02,215][61453] Avg episode reward: [(0, '9.550'), (1, '8.950')] -[2023-10-17 02:03:02,288][62408] Updated weights for policy 1, policy_version 44270 (0.0009) -[2023-10-17 02:03:02,641][62408] Updated weights for policy 1, policy_version 44280 (0.0010) -[2023-10-17 02:03:03,861][62373] Updated weights for policy 0, policy_version 44610 (0.0009) -[2023-10-17 02:03:04,224][62373] Updated weights for policy 0, policy_version 44620 (0.0009) -[2023-10-17 02:03:04,594][62373] Updated weights for policy 0, policy_version 44630 (0.0010) -[2023-10-17 02:03:04,965][62373] Updated weights for policy 0, policy_version 44640 (0.0010) -[2023-10-17 02:03:06,618][62408] Updated weights for policy 1, policy_version 44290 (0.0010) -[2023-10-17 02:03:07,038][62408] Updated weights for policy 1, policy_version 44300 (0.0007) -[2023-10-17 02:03:07,214][61453] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 91062272. Throughput: 0: 1781.9, 1: 1762.7. Samples: 22773834. Policy #0 lag: (min: 16.0, avg: 42.5, max: 48.0) -[2023-10-17 02:03:07,214][61453] Avg episode reward: [(0, '9.470'), (1, '8.230')] -[2023-10-17 02:03:07,403][62408] Updated weights for policy 1, policy_version 44310 (0.0008) -[2023-10-17 02:03:07,776][62408] Updated weights for policy 1, policy_version 44320 (0.0009) -[2023-10-17 02:03:08,762][62373] Updated weights for policy 0, policy_version 44650 (0.0007) -[2023-10-17 02:03:09,133][62373] Updated weights for policy 0, policy_version 44660 (0.0008) -[2023-10-17 02:03:09,504][62373] Updated weights for policy 0, policy_version 44670 (0.0007) -[2023-10-17 02:03:11,466][62408] Updated weights for policy 1, policy_version 44330 (0.0007) -[2023-10-17 02:03:11,839][62408] Updated weights for policy 1, policy_version 44340 (0.0009) -[2023-10-17 02:03:12,202][62408] Updated weights for policy 1, policy_version 44350 (0.0010) -[2023-10-17 02:03:12,214][61453] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 91127808. Throughput: 0: 1782.3, 1: 1794.6. Samples: 22795882. Policy #0 lag: (min: 16.0, avg: 42.5, max: 48.0) -[2023-10-17 02:03:12,215][61453] Avg episode reward: [(0, '9.410'), (1, '8.400')] -[2023-10-17 02:03:13,317][62373] Updated weights for policy 0, policy_version 44680 (0.0008) -[2023-10-17 02:03:13,696][62373] Updated weights for policy 0, policy_version 44690 (0.0009) -[2023-10-17 02:03:14,071][62373] Updated weights for policy 0, policy_version 44700 (0.0011) -[2023-10-17 02:03:15,981][62408] Updated weights for policy 1, policy_version 44360 (0.0011) -[2023-10-17 02:03:16,341][62408] Updated weights for policy 1, policy_version 44370 (0.0011) -[2023-10-17 02:03:16,702][62408] Updated weights for policy 1, policy_version 44380 (0.0010) -[2023-10-17 02:03:17,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 91226112. Throughput: 0: 1778.9, 1: 1765.8. Samples: 22816388. Policy #0 lag: (min: 16.0, avg: 42.5, max: 48.0) -[2023-10-17 02:03:17,214][61453] Avg episode reward: [(0, '9.930'), (1, '8.610')] -[2023-10-17 02:03:17,959][62373] Updated weights for policy 0, policy_version 44710 (0.0009) -[2023-10-17 02:03:18,329][62373] Updated weights for policy 0, policy_version 44720 (0.0010) -[2023-10-17 02:03:18,701][62373] Updated weights for policy 0, policy_version 44730 (0.0007) -[2023-10-17 02:03:20,452][62408] Updated weights for policy 1, policy_version 44390 (0.0009) -[2023-10-17 02:03:20,817][62408] Updated weights for policy 1, policy_version 44400 (0.0008) -[2023-10-17 02:03:21,193][62408] Updated weights for policy 1, policy_version 44410 (0.0008) -[2023-10-17 02:03:22,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 91291648. Throughput: 0: 1777.0, 1: 1790.0. Samples: 22827426. Policy #0 lag: (min: 16.0, avg: 42.5, max: 48.0) -[2023-10-17 02:03:22,215][61453] Avg episode reward: [(0, '10.290'), (1, '9.070')] -[2023-10-17 02:03:22,581][62373] Updated weights for policy 0, policy_version 44740 (0.0009) -[2023-10-17 02:03:22,949][62373] Updated weights for policy 0, policy_version 44750 (0.0009) -[2023-10-17 02:03:23,316][62373] Updated weights for policy 0, policy_version 44760 (0.0010) -[2023-10-17 02:03:25,052][62408] Updated weights for policy 1, policy_version 44420 (0.0009) -[2023-10-17 02:03:25,422][62408] Updated weights for policy 1, policy_version 44430 (0.0010) -[2023-10-17 02:03:25,781][62408] Updated weights for policy 1, policy_version 44440 (0.0008) -[2023-10-17 02:03:27,019][62373] Updated weights for policy 0, policy_version 44770 (0.0010) -[2023-10-17 02:03:27,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 91357184. Throughput: 0: 1780.7, 1: 1772.9. Samples: 22848612. Policy #0 lag: (min: 16.0, avg: 42.5, max: 48.0) -[2023-10-17 02:03:27,215][61453] Avg episode reward: [(0, '10.100'), (1, '8.850')] -[2023-10-17 02:03:27,398][62373] Updated weights for policy 0, policy_version 44780 (0.0007) -[2023-10-17 02:03:27,776][62373] Updated weights for policy 0, policy_version 44790 (0.0007) -[2023-10-17 02:03:28,144][62373] Updated weights for policy 0, policy_version 44800 (0.0009) -[2023-10-17 02:03:29,661][62408] Updated weights for policy 1, policy_version 44450 (0.0008) -[2023-10-17 02:03:30,035][62408] Updated weights for policy 1, policy_version 44460 (0.0009) -[2023-10-17 02:03:30,404][62408] Updated weights for policy 1, policy_version 44470 (0.0007) -[2023-10-17 02:03:30,771][62408] Updated weights for policy 1, policy_version 44480 (0.0010) -[2023-10-17 02:03:32,066][62373] Updated weights for policy 0, policy_version 44810 (0.0009) -[2023-10-17 02:03:32,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 91422720. Throughput: 0: 1807.2, 1: 1759.6. Samples: 22870016. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-10-17 02:03:32,215][61453] Avg episode reward: [(0, '10.170'), (1, '9.110')] -[2023-10-17 02:03:32,226][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000044480_45547520.pth... -[2023-10-17 02:03:32,258][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000042848_43876352.pth -[2023-10-17 02:03:32,440][62373] Updated weights for policy 0, policy_version 44820 (0.0008) -[2023-10-17 02:03:32,812][62373] Updated weights for policy 0, policy_version 44830 (0.0007) -[2023-10-17 02:03:32,880][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000044832_45907968.pth... -[2023-10-17 02:03:32,909][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000043168_44204032.pth -[2023-10-17 02:03:34,567][62408] Updated weights for policy 1, policy_version 44490 (0.0010) -[2023-10-17 02:03:34,925][62408] Updated weights for policy 1, policy_version 44500 (0.0009) -[2023-10-17 02:03:35,289][62408] Updated weights for policy 1, policy_version 44510 (0.0010) -[2023-10-17 02:03:36,567][62373] Updated weights for policy 0, policy_version 44840 (0.0008) -[2023-10-17 02:03:36,944][62373] Updated weights for policy 0, policy_version 44850 (0.0010) -[2023-10-17 02:03:37,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 91488256. Throughput: 0: 1783.5, 1: 1780.6. Samples: 22880810. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-10-17 02:03:37,214][61453] Avg episode reward: [(0, '10.360'), (1, '8.640')] -[2023-10-17 02:03:37,317][62373] Updated weights for policy 0, policy_version 44860 (0.0007) -[2023-10-17 02:03:39,042][62408] Updated weights for policy 1, policy_version 44520 (0.0010) -[2023-10-17 02:03:39,410][62408] Updated weights for policy 1, policy_version 44530 (0.0011) -[2023-10-17 02:03:39,783][62408] Updated weights for policy 1, policy_version 44540 (0.0007) -[2023-10-17 02:03:41,130][62373] Updated weights for policy 0, policy_version 44870 (0.0007) -[2023-10-17 02:03:41,497][62373] Updated weights for policy 0, policy_version 44880 (0.0008) -[2023-10-17 02:03:41,873][62373] Updated weights for policy 0, policy_version 44890 (0.0007) -[2023-10-17 02:03:42,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 91586560. Throughput: 0: 1806.8, 1: 1762.4. Samples: 22902108. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-10-17 02:03:42,215][61453] Avg episode reward: [(0, '9.750'), (1, '9.060')] -[2023-10-17 02:03:43,653][62408] Updated weights for policy 1, policy_version 44550 (0.0009) -[2023-10-17 02:03:44,015][62408] Updated weights for policy 1, policy_version 44560 (0.0009) -[2023-10-17 02:03:44,388][62408] Updated weights for policy 1, policy_version 44570 (0.0010) -[2023-10-17 02:03:45,508][62373] Updated weights for policy 0, policy_version 44900 (0.0008) -[2023-10-17 02:03:45,878][62373] Updated weights for policy 0, policy_version 44910 (0.0012) -[2023-10-17 02:03:46,244][62373] Updated weights for policy 0, policy_version 44920 (0.0008) -[2023-10-17 02:03:47,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 91652096. Throughput: 0: 1776.7, 1: 1754.4. Samples: 22922830. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-10-17 02:03:47,215][61453] Avg episode reward: [(0, '10.290'), (1, '8.490')] -[2023-10-17 02:03:48,041][62408] Updated weights for policy 1, policy_version 44580 (0.0008) -[2023-10-17 02:03:48,405][62408] Updated weights for policy 1, policy_version 44590 (0.0010) -[2023-10-17 02:03:48,773][62408] Updated weights for policy 1, policy_version 44600 (0.0010) -[2023-10-17 02:03:50,181][62373] Updated weights for policy 0, policy_version 44930 (0.0008) -[2023-10-17 02:03:50,560][62373] Updated weights for policy 0, policy_version 44940 (0.0009) -[2023-10-17 02:03:50,933][62373] Updated weights for policy 0, policy_version 44950 (0.0010) -[2023-10-17 02:03:51,299][62373] Updated weights for policy 0, policy_version 44960 (0.0009) -[2023-10-17 02:03:52,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 91717632. Throughput: 0: 1799.6, 1: 1755.0. Samples: 22933792. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-10-17 02:03:52,214][61453] Avg episode reward: [(0, '9.890'), (1, '7.810')] -[2023-10-17 02:03:52,409][62408] Updated weights for policy 1, policy_version 44610 (0.0009) -[2023-10-17 02:03:52,816][62408] Updated weights for policy 1, policy_version 44620 (0.0008) -[2023-10-17 02:03:53,189][62408] Updated weights for policy 1, policy_version 44630 (0.0008) -[2023-10-17 02:03:53,556][62408] Updated weights for policy 1, policy_version 44640 (0.0010) -[2023-10-17 02:03:55,198][62373] Updated weights for policy 0, policy_version 44970 (0.0011) -[2023-10-17 02:03:55,564][62373] Updated weights for policy 0, policy_version 44980 (0.0011) -[2023-10-17 02:03:55,939][62373] Updated weights for policy 0, policy_version 44990 (0.0009) -[2023-10-17 02:03:57,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 91783168. Throughput: 0: 1763.9, 1: 1767.6. Samples: 22954798. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-10-17 02:03:57,214][61453] Avg episode reward: [(0, '9.990'), (1, '7.870')] -[2023-10-17 02:03:57,250][62408] Updated weights for policy 1, policy_version 44650 (0.0007) -[2023-10-17 02:03:57,618][62408] Updated weights for policy 1, policy_version 44660 (0.0009) -[2023-10-17 02:03:57,987][62408] Updated weights for policy 1, policy_version 44670 (0.0007) -[2023-10-17 02:03:59,580][62373] Updated weights for policy 0, policy_version 45000 (0.0010) -[2023-10-17 02:03:59,951][62373] Updated weights for policy 0, policy_version 45010 (0.0008) -[2023-10-17 02:04:00,329][62373] Updated weights for policy 0, policy_version 45020 (0.0008) -[2023-10-17 02:04:01,813][62408] Updated weights for policy 1, policy_version 44680 (0.0008) -[2023-10-17 02:04:02,186][62408] Updated weights for policy 1, policy_version 44690 (0.0009) -[2023-10-17 02:04:02,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 91848704. Throughput: 0: 1761.4, 1: 1794.7. Samples: 22976410. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-17 02:04:02,215][61453] Avg episode reward: [(0, '9.870'), (1, '8.470')] -[2023-10-17 02:04:02,555][62408] Updated weights for policy 1, policy_version 44700 (0.0009) -[2023-10-17 02:04:04,133][62373] Updated weights for policy 0, policy_version 45030 (0.0010) -[2023-10-17 02:04:04,498][62373] Updated weights for policy 0, policy_version 45040 (0.0007) -[2023-10-17 02:04:04,877][62373] Updated weights for policy 0, policy_version 45050 (0.0008) -[2023-10-17 02:04:06,337][62408] Updated weights for policy 1, policy_version 44710 (0.0010) -[2023-10-17 02:04:06,701][62408] Updated weights for policy 1, policy_version 44720 (0.0007) -[2023-10-17 02:04:07,073][62408] Updated weights for policy 1, policy_version 44730 (0.0008) -[2023-10-17 02:04:07,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 91914240. Throughput: 0: 1767.6, 1: 1773.9. Samples: 22986792. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-17 02:04:07,215][61453] Avg episode reward: [(0, '9.650'), (1, '8.670')] -[2023-10-17 02:04:08,635][62373] Updated weights for policy 0, policy_version 45060 (0.0007) -[2023-10-17 02:04:09,011][62373] Updated weights for policy 0, policy_version 45070 (0.0009) -[2023-10-17 02:04:09,369][62373] Updated weights for policy 0, policy_version 45080 (0.0007) -[2023-10-17 02:04:11,041][62408] Updated weights for policy 1, policy_version 44740 (0.0008) -[2023-10-17 02:04:11,415][62408] Updated weights for policy 1, policy_version 44750 (0.0008) -[2023-10-17 02:04:11,787][62408] Updated weights for policy 1, policy_version 44760 (0.0007) -[2023-10-17 02:04:12,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14218.0). Total num frames: 92012544. Throughput: 0: 1756.5, 1: 1797.7. Samples: 23008552. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-17 02:04:12,215][61453] Avg episode reward: [(0, '9.880'), (1, '8.860')] -[2023-10-17 02:04:13,155][62373] Updated weights for policy 0, policy_version 45090 (0.0008) -[2023-10-17 02:04:13,523][62373] Updated weights for policy 0, policy_version 45100 (0.0010) -[2023-10-17 02:04:13,891][62373] Updated weights for policy 0, policy_version 45110 (0.0007) -[2023-10-17 02:04:14,260][62373] Updated weights for policy 0, policy_version 45120 (0.0008) -[2023-10-17 02:04:15,578][62408] Updated weights for policy 1, policy_version 44770 (0.0008) -[2023-10-17 02:04:15,940][62408] Updated weights for policy 1, policy_version 44780 (0.0007) -[2023-10-17 02:04:16,303][62408] Updated weights for policy 1, policy_version 44790 (0.0008) -[2023-10-17 02:04:16,667][62408] Updated weights for policy 1, policy_version 44800 (0.0008) -[2023-10-17 02:04:17,214][61453] Fps is (10 sec: 16384.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 92078080. Throughput: 0: 1767.0, 1: 1772.7. Samples: 23029302. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-17 02:04:17,215][61453] Avg episode reward: [(0, '10.400'), (1, '8.390')] -[2023-10-17 02:04:18,222][62373] Updated weights for policy 0, policy_version 45130 (0.0008) -[2023-10-17 02:04:18,605][62373] Updated weights for policy 0, policy_version 45140 (0.0007) -[2023-10-17 02:04:18,976][62373] Updated weights for policy 0, policy_version 45150 (0.0008) -[2023-10-17 02:04:20,532][62408] Updated weights for policy 1, policy_version 44810 (0.0008) -[2023-10-17 02:04:20,900][62408] Updated weights for policy 1, policy_version 44820 (0.0010) -[2023-10-17 02:04:21,275][62408] Updated weights for policy 1, policy_version 44830 (0.0009) -[2023-10-17 02:04:22,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 92143616. Throughput: 0: 1755.9, 1: 1784.4. Samples: 23040122. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-17 02:04:22,215][61453] Avg episode reward: [(0, '10.350'), (1, '9.120')] -[2023-10-17 02:04:22,724][62373] Updated weights for policy 0, policy_version 45160 (0.0009) -[2023-10-17 02:04:23,097][62373] Updated weights for policy 0, policy_version 45170 (0.0011) -[2023-10-17 02:04:23,469][62373] Updated weights for policy 0, policy_version 45180 (0.0010) -[2023-10-17 02:04:25,156][62408] Updated weights for policy 1, policy_version 44840 (0.0009) -[2023-10-17 02:04:25,513][62408] Updated weights for policy 1, policy_version 44850 (0.0009) -[2023-10-17 02:04:25,880][62408] Updated weights for policy 1, policy_version 44860 (0.0009) -[2023-10-17 02:04:27,144][62373] Updated weights for policy 0, policy_version 45190 (0.0009) -[2023-10-17 02:04:27,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 92209152. Throughput: 0: 1761.5, 1: 1773.2. Samples: 23061170. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-17 02:04:27,214][61453] Avg episode reward: [(0, '10.300'), (1, '9.830')] -[2023-10-17 02:04:27,518][62373] Updated weights for policy 0, policy_version 45200 (0.0009) -[2023-10-17 02:04:27,879][62373] Updated weights for policy 0, policy_version 45210 (0.0007) -[2023-10-17 02:04:29,629][62408] Updated weights for policy 1, policy_version 44870 (0.0008) -[2023-10-17 02:04:29,988][62408] Updated weights for policy 1, policy_version 44880 (0.0008) -[2023-10-17 02:04:30,367][62408] Updated weights for policy 1, policy_version 44890 (0.0009) -[2023-10-17 02:04:31,575][62373] Updated weights for policy 0, policy_version 45220 (0.0007) -[2023-10-17 02:04:31,947][62373] Updated weights for policy 0, policy_version 45230 (0.0007) -[2023-10-17 02:04:32,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 92274688. Throughput: 0: 1784.9, 1: 1765.8. Samples: 23082612. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-17 02:04:32,215][61453] Avg episode reward: [(0, '10.030'), (1, '9.390')] -[2023-10-17 02:04:32,312][62373] Updated weights for policy 0, policy_version 45240 (0.0009) -[2023-10-17 02:04:34,040][62408] Updated weights for policy 1, policy_version 44900 (0.0008) -[2023-10-17 02:04:34,419][62408] Updated weights for policy 1, policy_version 44910 (0.0010) -[2023-10-17 02:04:34,783][62408] Updated weights for policy 1, policy_version 44920 (0.0007) -[2023-10-17 02:04:36,258][62373] Updated weights for policy 0, policy_version 45250 (0.0011) -[2023-10-17 02:04:36,622][62373] Updated weights for policy 0, policy_version 45260 (0.0009) -[2023-10-17 02:04:36,985][62373] Updated weights for policy 0, policy_version 45270 (0.0009) -[2023-10-17 02:04:37,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 92340224. Throughput: 0: 1771.9, 1: 1776.4. Samples: 23093462. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:04:37,215][61453] Avg episode reward: [(0, '9.760'), (1, '8.360')] -[2023-10-17 02:04:37,350][62373] Updated weights for policy 0, policy_version 45280 (0.0011) -[2023-10-17 02:04:38,652][62408] Updated weights for policy 1, policy_version 44930 (0.0007) -[2023-10-17 02:04:39,020][62408] Updated weights for policy 1, policy_version 44940 (0.0011) -[2023-10-17 02:04:39,389][62408] Updated weights for policy 1, policy_version 44950 (0.0010) -[2023-10-17 02:04:39,764][62408] Updated weights for policy 1, policy_version 44960 (0.0007) -[2023-10-17 02:04:41,049][62373] Updated weights for policy 0, policy_version 45290 (0.0008) -[2023-10-17 02:04:41,423][62373] Updated weights for policy 0, policy_version 45300 (0.0008) -[2023-10-17 02:04:41,796][62373] Updated weights for policy 0, policy_version 45310 (0.0007) -[2023-10-17 02:04:42,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 92438528. Throughput: 0: 1802.1, 1: 1756.6. Samples: 23114940. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:04:42,215][61453] Avg episode reward: [(0, '10.400'), (1, '8.480')] -[2023-10-17 02:04:43,637][62408] Updated weights for policy 1, policy_version 44970 (0.0008) -[2023-10-17 02:04:43,998][62408] Updated weights for policy 1, policy_version 44980 (0.0007) -[2023-10-17 02:04:44,362][62408] Updated weights for policy 1, policy_version 44990 (0.0007) -[2023-10-17 02:04:45,491][62373] Updated weights for policy 0, policy_version 45320 (0.0009) -[2023-10-17 02:04:45,860][62373] Updated weights for policy 0, policy_version 45330 (0.0009) -[2023-10-17 02:04:46,226][62373] Updated weights for policy 0, policy_version 45340 (0.0010) -[2023-10-17 02:04:47,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 92504064. Throughput: 0: 1778.0, 1: 1762.4. Samples: 23135728. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:04:47,214][61453] Avg episode reward: [(0, '9.810'), (1, '9.040')] -[2023-10-17 02:04:48,332][62408] Updated weights for policy 1, policy_version 45000 (0.0009) -[2023-10-17 02:04:48,698][62408] Updated weights for policy 1, policy_version 45010 (0.0009) -[2023-10-17 02:04:49,076][62408] Updated weights for policy 1, policy_version 45020 (0.0009) -[2023-10-17 02:04:50,111][62373] Updated weights for policy 0, policy_version 45350 (0.0009) -[2023-10-17 02:04:50,491][62373] Updated weights for policy 0, policy_version 45360 (0.0009) -[2023-10-17 02:04:50,861][62373] Updated weights for policy 0, policy_version 45370 (0.0007) -[2023-10-17 02:04:52,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 92569600. Throughput: 0: 1802.1, 1: 1746.0. Samples: 23146458. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:04:52,215][61453] Avg episode reward: [(0, '8.760'), (1, '8.890')] -[2023-10-17 02:04:52,854][62408] Updated weights for policy 1, policy_version 45030 (0.0008) -[2023-10-17 02:04:53,227][62408] Updated weights for policy 1, policy_version 45040 (0.0010) -[2023-10-17 02:04:53,601][62408] Updated weights for policy 1, policy_version 45050 (0.0010) -[2023-10-17 02:04:54,560][62373] Updated weights for policy 0, policy_version 45380 (0.0007) -[2023-10-17 02:04:54,939][62373] Updated weights for policy 0, policy_version 45390 (0.0008) -[2023-10-17 02:04:55,308][62373] Updated weights for policy 0, policy_version 45400 (0.0007) -[2023-10-17 02:04:57,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 92635136. Throughput: 0: 1780.5, 1: 1748.2. Samples: 23167346. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:04:57,215][61453] Avg episode reward: [(0, '8.880'), (1, '8.580')] -[2023-10-17 02:04:57,371][62408] Updated weights for policy 1, policy_version 45060 (0.0007) -[2023-10-17 02:04:57,732][62408] Updated weights for policy 1, policy_version 45070 (0.0008) -[2023-10-17 02:04:58,104][62408] Updated weights for policy 1, policy_version 45080 (0.0007) -[2023-10-17 02:04:59,221][62373] Updated weights for policy 0, policy_version 45410 (0.0009) -[2023-10-17 02:04:59,592][62373] Updated weights for policy 0, policy_version 45420 (0.0011) -[2023-10-17 02:04:59,960][62373] Updated weights for policy 0, policy_version 45430 (0.0009) -[2023-10-17 02:05:00,323][62373] Updated weights for policy 0, policy_version 45440 (0.0009) -[2023-10-17 02:05:01,973][62408] Updated weights for policy 1, policy_version 45090 (0.0009) -[2023-10-17 02:05:02,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 92700672. Throughput: 0: 1780.4, 1: 1782.3. Samples: 23189622. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:05:02,215][61453] Avg episode reward: [(0, '9.210'), (1, '8.520')] -[2023-10-17 02:05:02,329][62408] Updated weights for policy 1, policy_version 45100 (0.0009) -[2023-10-17 02:05:02,696][62408] Updated weights for policy 1, policy_version 45110 (0.0007) -[2023-10-17 02:05:03,071][62408] Updated weights for policy 1, policy_version 45120 (0.0009) -[2023-10-17 02:05:04,187][62373] Updated weights for policy 0, policy_version 45450 (0.0007) -[2023-10-17 02:05:04,556][62373] Updated weights for policy 0, policy_version 45460 (0.0009) -[2023-10-17 02:05:04,922][62373] Updated weights for policy 0, policy_version 45470 (0.0007) -[2023-10-17 02:05:06,837][62408] Updated weights for policy 1, policy_version 45130 (0.0007) -[2023-10-17 02:05:07,205][62408] Updated weights for policy 1, policy_version 45140 (0.0007) -[2023-10-17 02:05:07,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 92766208. Throughput: 0: 1785.8, 1: 1756.0. Samples: 23199506. Policy #0 lag: (min: 8.0, avg: 30.3, max: 40.0) -[2023-10-17 02:05:07,215][61453] Avg episode reward: [(0, '9.280'), (1, '9.230')] -[2023-10-17 02:05:07,572][62408] Updated weights for policy 1, policy_version 45150 (0.0008) -[2023-10-17 02:05:08,787][62373] Updated weights for policy 0, policy_version 45480 (0.0007) -[2023-10-17 02:05:09,149][62373] Updated weights for policy 0, policy_version 45490 (0.0008) -[2023-10-17 02:05:09,517][62373] Updated weights for policy 0, policy_version 45500 (0.0008) -[2023-10-17 02:05:11,416][62408] Updated weights for policy 1, policy_version 45160 (0.0008) -[2023-10-17 02:05:11,783][62408] Updated weights for policy 1, policy_version 45170 (0.0008) -[2023-10-17 02:05:12,149][62408] Updated weights for policy 1, policy_version 45180 (0.0008) -[2023-10-17 02:05:12,214][61453] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 92831744. Throughput: 0: 1779.4, 1: 1780.3. Samples: 23221358. Policy #0 lag: (min: 8.0, avg: 30.3, max: 40.0) -[2023-10-17 02:05:12,215][61453] Avg episode reward: [(0, '9.120'), (1, '8.730')] -[2023-10-17 02:05:13,393][62373] Updated weights for policy 0, policy_version 45510 (0.0010) -[2023-10-17 02:05:13,769][62373] Updated weights for policy 0, policy_version 45520 (0.0008) -[2023-10-17 02:05:14,133][62373] Updated weights for policy 0, policy_version 45530 (0.0008) -[2023-10-17 02:05:15,900][62408] Updated weights for policy 1, policy_version 45190 (0.0008) -[2023-10-17 02:05:16,261][62408] Updated weights for policy 1, policy_version 45200 (0.0009) -[2023-10-17 02:05:16,626][62408] Updated weights for policy 1, policy_version 45210 (0.0009) -[2023-10-17 02:05:17,214][61453] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 92930048. Throughput: 0: 1781.9, 1: 1761.6. Samples: 23242072. Policy #0 lag: (min: 8.0, avg: 30.3, max: 40.0) -[2023-10-17 02:05:17,214][61453] Avg episode reward: [(0, '8.960'), (1, '8.210')] -[2023-10-17 02:05:17,847][62373] Updated weights for policy 0, policy_version 45540 (0.0008) -[2023-10-17 02:05:18,224][62373] Updated weights for policy 0, policy_version 45550 (0.0007) -[2023-10-17 02:05:18,585][62373] Updated weights for policy 0, policy_version 45560 (0.0008) -[2023-10-17 02:05:20,488][62408] Updated weights for policy 1, policy_version 45220 (0.0009) -[2023-10-17 02:05:20,860][62408] Updated weights for policy 1, policy_version 45230 (0.0008) -[2023-10-17 02:05:21,229][62408] Updated weights for policy 1, policy_version 45240 (0.0008) -[2023-10-17 02:05:22,214][61453] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 92995584. Throughput: 0: 1767.2, 1: 1778.8. Samples: 23253034. Policy #0 lag: (min: 8.0, avg: 30.3, max: 40.0) -[2023-10-17 02:05:22,214][61453] Avg episode reward: [(0, '8.840'), (1, '8.220')] -[2023-10-17 02:05:22,279][62373] Updated weights for policy 0, policy_version 45570 (0.0010) -[2023-10-17 02:05:22,652][62373] Updated weights for policy 0, policy_version 45580 (0.0010) -[2023-10-17 02:05:23,018][62373] Updated weights for policy 0, policy_version 45590 (0.0009) -[2023-10-17 02:05:23,390][62373] Updated weights for policy 0, policy_version 45600 (0.0010) -[2023-10-17 02:05:25,090][62408] Updated weights for policy 1, policy_version 45250 (0.0007) -[2023-10-17 02:05:25,452][62408] Updated weights for policy 1, policy_version 45260 (0.0010) -[2023-10-17 02:05:25,827][62408] Updated weights for policy 1, policy_version 45270 (0.0009) -[2023-10-17 02:05:26,189][62408] Updated weights for policy 1, policy_version 45280 (0.0008) -[2023-10-17 02:05:27,209][62373] Updated weights for policy 0, policy_version 45610 (0.0011) -[2023-10-17 02:05:27,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 93061120. Throughput: 0: 1774.4, 1: 1764.2. Samples: 23274176. Policy #0 lag: (min: 8.0, avg: 30.3, max: 40.0) -[2023-10-17 02:05:27,214][61453] Avg episode reward: [(0, '10.030'), (1, '8.540')] -[2023-10-17 02:05:27,574][62373] Updated weights for policy 0, policy_version 45620 (0.0008) -[2023-10-17 02:05:27,954][62373] Updated weights for policy 0, policy_version 45630 (0.0009) -[2023-10-17 02:05:30,228][62408] Updated weights for policy 1, policy_version 45290 (0.0009) -[2023-10-17 02:05:30,607][62408] Updated weights for policy 1, policy_version 45300 (0.0010) -[2023-10-17 02:05:30,971][62408] Updated weights for policy 1, policy_version 45310 (0.0008) -[2023-10-17 02:05:31,795][62373] Updated weights for policy 0, policy_version 45640 (0.0008) -[2023-10-17 02:05:32,169][62373] Updated weights for policy 0, policy_version 45650 (0.0010) -[2023-10-17 02:05:32,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 93126656. Throughput: 0: 1791.5, 1: 1754.0. Samples: 23295276. Policy #0 lag: (min: 8.0, avg: 30.3, max: 40.0) -[2023-10-17 02:05:32,215][61453] Avg episode reward: [(0, '9.530'), (1, '8.260')] -[2023-10-17 02:05:32,225][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000045312_46399488.pth... -[2023-10-17 02:05:32,266][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000043648_44695552.pth -[2023-10-17 02:05:32,539][62373] Updated weights for policy 0, policy_version 45660 (0.0008) -[2023-10-17 02:05:32,678][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000045664_46759936.pth... -[2023-10-17 02:05:32,707][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000044000_45056000.pth -[2023-10-17 02:05:34,691][62408] Updated weights for policy 1, policy_version 45320 (0.0008) -[2023-10-17 02:05:35,062][62408] Updated weights for policy 1, policy_version 45330 (0.0009) -[2023-10-17 02:05:35,438][62408] Updated weights for policy 1, policy_version 45340 (0.0010) -[2023-10-17 02:05:36,252][62373] Updated weights for policy 0, policy_version 45670 (0.0008) -[2023-10-17 02:05:36,625][62373] Updated weights for policy 0, policy_version 45680 (0.0009) -[2023-10-17 02:05:37,003][62373] Updated weights for policy 0, policy_version 45690 (0.0009) -[2023-10-17 02:05:37,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 93192192. Throughput: 0: 1772.1, 1: 1779.4. Samples: 23306276. Policy #0 lag: (min: 8.0, avg: 30.3, max: 40.0) -[2023-10-17 02:05:37,215][61453] Avg episode reward: [(0, '9.270'), (1, '8.210')] -[2023-10-17 02:05:39,356][62408] Updated weights for policy 1, policy_version 45350 (0.0008) -[2023-10-17 02:05:39,716][62408] Updated weights for policy 1, policy_version 45360 (0.0007) -[2023-10-17 02:05:40,090][62408] Updated weights for policy 1, policy_version 45370 (0.0009) -[2023-10-17 02:05:40,775][62373] Updated weights for policy 0, policy_version 45700 (0.0008) -[2023-10-17 02:05:41,142][62373] Updated weights for policy 0, policy_version 45710 (0.0007) -[2023-10-17 02:05:41,508][62373] Updated weights for policy 0, policy_version 45720 (0.0009) -[2023-10-17 02:05:42,214][61453] Fps is (10 sec: 16384.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 93290496. Throughput: 0: 1791.2, 1: 1759.2. Samples: 23327114. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:05:42,214][61453] Avg episode reward: [(0, '9.420'), (1, '8.120')] -[2023-10-17 02:05:43,731][62408] Updated weights for policy 1, policy_version 45380 (0.0010) -[2023-10-17 02:05:44,093][62408] Updated weights for policy 1, policy_version 45390 (0.0009) -[2023-10-17 02:05:44,462][62408] Updated weights for policy 1, policy_version 45400 (0.0008) -[2023-10-17 02:05:45,319][62373] Updated weights for policy 0, policy_version 45730 (0.0007) -[2023-10-17 02:05:45,686][62373] Updated weights for policy 0, policy_version 45740 (0.0008) -[2023-10-17 02:05:46,059][62373] Updated weights for policy 0, policy_version 45750 (0.0008) -[2023-10-17 02:05:46,418][62373] Updated weights for policy 0, policy_version 45760 (0.0007) -[2023-10-17 02:05:47,214][61453] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 93356032. Throughput: 0: 1772.0, 1: 1758.0. Samples: 23348472. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:05:47,215][61453] Avg episode reward: [(0, '9.150'), (1, '8.210')] -[2023-10-17 02:05:48,427][62408] Updated weights for policy 1, policy_version 45410 (0.0007) -[2023-10-17 02:05:48,792][62408] Updated weights for policy 1, policy_version 45420 (0.0009) -[2023-10-17 02:05:49,157][62408] Updated weights for policy 1, policy_version 45430 (0.0009) -[2023-10-17 02:05:49,519][62408] Updated weights for policy 1, policy_version 45440 (0.0009) -[2023-10-17 02:05:50,124][62373] Updated weights for policy 0, policy_version 45770 (0.0009) -[2023-10-17 02:05:50,496][62373] Updated weights for policy 0, policy_version 45780 (0.0009) -[2023-10-17 02:05:50,856][62373] Updated weights for policy 0, policy_version 45790 (0.0009) -[2023-10-17 02:05:52,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 93421568. Throughput: 0: 1797.9, 1: 1752.9. Samples: 23359294. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:05:52,215][61453] Avg episode reward: [(0, '9.250'), (1, '8.060')] -[2023-10-17 02:05:53,196][62408] Updated weights for policy 1, policy_version 45450 (0.0011) -[2023-10-17 02:05:53,575][62408] Updated weights for policy 1, policy_version 45460 (0.0010) -[2023-10-17 02:05:53,949][62408] Updated weights for policy 1, policy_version 45470 (0.0008) -[2023-10-17 02:05:54,598][62373] Updated weights for policy 0, policy_version 45800 (0.0008) -[2023-10-17 02:05:54,969][62373] Updated weights for policy 0, policy_version 45810 (0.0010) -[2023-10-17 02:05:55,338][62373] Updated weights for policy 0, policy_version 45820 (0.0007) -[2023-10-17 02:05:57,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 93487104. Throughput: 0: 1778.5, 1: 1757.2. Samples: 23380462. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:05:57,215][61453] Avg episode reward: [(0, '8.670'), (1, '8.250')] -[2023-10-17 02:05:57,867][62408] Updated weights for policy 1, policy_version 45480 (0.0008) -[2023-10-17 02:05:58,236][62408] Updated weights for policy 1, policy_version 45490 (0.0008) -[2023-10-17 02:05:58,601][62408] Updated weights for policy 1, policy_version 45500 (0.0007) -[2023-10-17 02:05:59,090][62373] Updated weights for policy 0, policy_version 45830 (0.0009) -[2023-10-17 02:05:59,483][62373] Updated weights for policy 0, policy_version 45840 (0.0008) -[2023-10-17 02:05:59,849][62373] Updated weights for policy 0, policy_version 45850 (0.0008) -[2023-10-17 02:06:02,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 93552640. Throughput: 0: 1782.9, 1: 1778.3. Samples: 23402326. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:06:02,215][61453] Avg episode reward: [(0, '8.810'), (1, '8.560')] -[2023-10-17 02:06:02,502][62408] Updated weights for policy 1, policy_version 45510 (0.0008) -[2023-10-17 02:06:02,871][62408] Updated weights for policy 1, policy_version 45520 (0.0007) -[2023-10-17 02:06:03,238][62408] Updated weights for policy 1, policy_version 45530 (0.0011) -[2023-10-17 02:06:03,471][62373] Updated weights for policy 0, policy_version 45860 (0.0007) -[2023-10-17 02:06:03,836][62373] Updated weights for policy 0, policy_version 45870 (0.0008) -[2023-10-17 02:06:04,219][62373] Updated weights for policy 0, policy_version 45880 (0.0009) -[2023-10-17 02:06:07,134][62408] Updated weights for policy 1, policy_version 45540 (0.0010) -[2023-10-17 02:06:07,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 93618176. Throughput: 0: 1784.8, 1: 1749.0. Samples: 23412056. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:06:07,214][61453] Avg episode reward: [(0, '8.280'), (1, '8.720')] -[2023-10-17 02:06:07,501][62408] Updated weights for policy 1, policy_version 45550 (0.0007) -[2023-10-17 02:06:07,869][62408] Updated weights for policy 1, policy_version 45560 (0.0009) -[2023-10-17 02:06:07,962][62373] Updated weights for policy 0, policy_version 45890 (0.0008) -[2023-10-17 02:06:08,322][62373] Updated weights for policy 0, policy_version 45900 (0.0009) -[2023-10-17 02:06:08,689][62373] Updated weights for policy 0, policy_version 45910 (0.0008) -[2023-10-17 02:06:09,066][62373] Updated weights for policy 0, policy_version 45920 (0.0008) -[2023-10-17 02:06:11,699][62408] Updated weights for policy 1, policy_version 45570 (0.0007) -[2023-10-17 02:06:12,072][62408] Updated weights for policy 1, policy_version 45580 (0.0009) -[2023-10-17 02:06:12,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 93683712. Throughput: 0: 1790.6, 1: 1772.6. Samples: 23434522. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:06:12,215][61453] Avg episode reward: [(0, '8.120'), (1, '8.870')] -[2023-10-17 02:06:12,424][62408] Updated weights for policy 1, policy_version 45590 (0.0007) -[2023-10-17 02:06:12,686][62373] Updated weights for policy 0, policy_version 45930 (0.0007) -[2023-10-17 02:06:12,790][62408] Updated weights for policy 1, policy_version 45600 (0.0007) -[2023-10-17 02:06:13,062][62373] Updated weights for policy 0, policy_version 45940 (0.0007) -[2023-10-17 02:06:13,422][62373] Updated weights for policy 0, policy_version 45950 (0.0010) -[2023-10-17 02:06:16,683][62408] Updated weights for policy 1, policy_version 45610 (0.0007) -[2023-10-17 02:06:17,048][62408] Updated weights for policy 1, policy_version 45620 (0.0008) -[2023-10-17 02:06:17,214][61453] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 93749248. Throughput: 0: 1805.0, 1: 1768.4. Samples: 23456076. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:06:17,214][61453] Avg episode reward: [(0, '8.290'), (1, '9.580')] -[2023-10-17 02:06:17,245][62373] Updated weights for policy 0, policy_version 45960 (0.0009) -[2023-10-17 02:06:17,413][62408] Updated weights for policy 1, policy_version 45630 (0.0008) -[2023-10-17 02:06:17,630][62373] Updated weights for policy 0, policy_version 45970 (0.0007) -[2023-10-17 02:06:18,002][62373] Updated weights for policy 0, policy_version 45980 (0.0009) -[2023-10-17 02:06:21,243][62408] Updated weights for policy 1, policy_version 45640 (0.0008) -[2023-10-17 02:06:21,614][62408] Updated weights for policy 1, policy_version 45650 (0.0010) -[2023-10-17 02:06:21,830][62373] Updated weights for policy 0, policy_version 45990 (0.0009) -[2023-10-17 02:06:21,976][62408] Updated weights for policy 1, policy_version 45660 (0.0008) -[2023-10-17 02:06:22,203][62373] Updated weights for policy 0, policy_version 46000 (0.0009) -[2023-10-17 02:06:22,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 93847552. Throughput: 0: 1793.6, 1: 1761.9. Samples: 23466272. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:06:22,215][61453] Avg episode reward: [(0, '7.830'), (1, '9.530')] -[2023-10-17 02:06:22,576][62373] Updated weights for policy 0, policy_version 46010 (0.0007) -[2023-10-17 02:06:25,708][62408] Updated weights for policy 1, policy_version 45670 (0.0010) -[2023-10-17 02:06:26,087][62408] Updated weights for policy 1, policy_version 45680 (0.0009) -[2023-10-17 02:06:26,410][62373] Updated weights for policy 0, policy_version 46020 (0.0007) -[2023-10-17 02:06:26,448][62408] Updated weights for policy 1, policy_version 45690 (0.0008) -[2023-10-17 02:06:26,786][62373] Updated weights for policy 0, policy_version 46030 (0.0008) -[2023-10-17 02:06:27,159][62373] Updated weights for policy 0, policy_version 46040 (0.0008) -[2023-10-17 02:06:27,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 93913088. Throughput: 0: 1798.0, 1: 1775.6. Samples: 23487930. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:06:27,215][61453] Avg episode reward: [(0, '8.460'), (1, '9.380')] -[2023-10-17 02:06:30,442][62408] Updated weights for policy 1, policy_version 45700 (0.0010) -[2023-10-17 02:06:30,801][62408] Updated weights for policy 1, policy_version 45710 (0.0009) -[2023-10-17 02:06:30,863][62373] Updated weights for policy 0, policy_version 46050 (0.0008) -[2023-10-17 02:06:31,172][62408] Updated weights for policy 1, policy_version 45720 (0.0008) -[2023-10-17 02:06:31,239][62373] Updated weights for policy 0, policy_version 46060 (0.0009) -[2023-10-17 02:06:31,612][62373] Updated weights for policy 0, policy_version 46070 (0.0008) -[2023-10-17 02:06:31,986][62373] Updated weights for policy 0, policy_version 46080 (0.0008) -[2023-10-17 02:06:32,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 94011392. Throughput: 0: 1787.1, 1: 1747.9. Samples: 23507546. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:06:32,215][61453] Avg episode reward: [(0, '8.440'), (1, '9.310')] -[2023-10-17 02:06:35,170][62408] Updated weights for policy 1, policy_version 45730 (0.0007) -[2023-10-17 02:06:35,530][62408] Updated weights for policy 1, policy_version 45740 (0.0009) -[2023-10-17 02:06:35,841][62373] Updated weights for policy 0, policy_version 46090 (0.0008) -[2023-10-17 02:06:35,902][62408] Updated weights for policy 1, policy_version 45750 (0.0007) -[2023-10-17 02:06:36,209][62373] Updated weights for policy 0, policy_version 46100 (0.0009) -[2023-10-17 02:06:36,267][62408] Updated weights for policy 1, policy_version 45760 (0.0007) -[2023-10-17 02:06:36,567][62373] Updated weights for policy 0, policy_version 46110 (0.0010) -[2023-10-17 02:06:37,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 94076928. Throughput: 0: 1785.2, 1: 1777.7. Samples: 23519624. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:06:37,214][61453] Avg episode reward: [(0, '8.560'), (1, '9.330')] -[2023-10-17 02:06:40,014][62408] Updated weights for policy 1, policy_version 45770 (0.0007) -[2023-10-17 02:06:40,391][62408] Updated weights for policy 1, policy_version 45780 (0.0007) -[2023-10-17 02:06:40,447][62373] Updated weights for policy 0, policy_version 46120 (0.0009) -[2023-10-17 02:06:40,750][62408] Updated weights for policy 1, policy_version 45790 (0.0008) -[2023-10-17 02:06:40,814][62373] Updated weights for policy 0, policy_version 46130 (0.0008) -[2023-10-17 02:06:41,179][62373] Updated weights for policy 0, policy_version 46140 (0.0009) -[2023-10-17 02:06:42,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 94142464. Throughput: 0: 1790.9, 1: 1745.3. Samples: 23539590. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-10-17 02:06:42,215][61453] Avg episode reward: [(0, '9.010'), (1, '8.990')] -[2023-10-17 02:06:44,524][62408] Updated weights for policy 1, policy_version 45800 (0.0007) -[2023-10-17 02:06:44,894][62408] Updated weights for policy 1, policy_version 45810 (0.0010) -[2023-10-17 02:06:44,941][62373] Updated weights for policy 0, policy_version 46150 (0.0008) -[2023-10-17 02:06:45,258][62408] Updated weights for policy 1, policy_version 45820 (0.0009) -[2023-10-17 02:06:45,339][62373] Updated weights for policy 0, policy_version 46160 (0.0008) -[2023-10-17 02:06:45,707][62373] Updated weights for policy 0, policy_version 46170 (0.0009) -[2023-10-17 02:06:47,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 94208000. Throughput: 0: 1780.8, 1: 1756.7. Samples: 23561510. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-10-17 02:06:47,214][61453] Avg episode reward: [(0, '9.170'), (1, '8.680')] -[2023-10-17 02:06:48,948][62408] Updated weights for policy 1, policy_version 45830 (0.0008) -[2023-10-17 02:06:49,312][62408] Updated weights for policy 1, policy_version 45840 (0.0010) -[2023-10-17 02:06:49,526][62373] Updated weights for policy 0, policy_version 46180 (0.0009) -[2023-10-17 02:06:49,680][62408] Updated weights for policy 1, policy_version 45850 (0.0008) -[2023-10-17 02:06:49,897][62373] Updated weights for policy 0, policy_version 46190 (0.0007) -[2023-10-17 02:06:50,266][62373] Updated weights for policy 0, policy_version 46200 (0.0007) -[2023-10-17 02:06:52,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 94273536. Throughput: 0: 1791.1, 1: 1762.0. Samples: 23571948. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-10-17 02:06:52,215][61453] Avg episode reward: [(0, '9.440'), (1, '8.250')] -[2023-10-17 02:06:53,385][62408] Updated weights for policy 1, policy_version 45860 (0.0008) -[2023-10-17 02:06:53,756][62408] Updated weights for policy 1, policy_version 45870 (0.0009) -[2023-10-17 02:06:53,888][62373] Updated weights for policy 0, policy_version 46210 (0.0008) -[2023-10-17 02:06:54,120][62408] Updated weights for policy 1, policy_version 45880 (0.0007) -[2023-10-17 02:06:54,267][62373] Updated weights for policy 0, policy_version 46220 (0.0008) -[2023-10-17 02:06:54,631][62373] Updated weights for policy 0, policy_version 46230 (0.0007) -[2023-10-17 02:06:55,001][62373] Updated weights for policy 0, policy_version 46240 (0.0008) -[2023-10-17 02:06:57,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 94339072. Throughput: 0: 1770.6, 1: 1762.2. Samples: 23593498. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-10-17 02:06:57,215][61453] Avg episode reward: [(0, '9.720'), (1, '8.480')] -[2023-10-17 02:06:58,008][62408] Updated weights for policy 1, policy_version 45890 (0.0008) -[2023-10-17 02:06:58,369][62408] Updated weights for policy 1, policy_version 45900 (0.0007) -[2023-10-17 02:06:58,733][62408] Updated weights for policy 1, policy_version 45910 (0.0007) -[2023-10-17 02:06:58,942][62373] Updated weights for policy 0, policy_version 46250 (0.0007) -[2023-10-17 02:06:59,101][62408] Updated weights for policy 1, policy_version 45920 (0.0008) -[2023-10-17 02:06:59,306][62373] Updated weights for policy 0, policy_version 46260 (0.0010) -[2023-10-17 02:06:59,672][62373] Updated weights for policy 0, policy_version 46270 (0.0010) -[2023-10-17 02:07:02,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 94404608. Throughput: 0: 1764.7, 1: 1782.6. Samples: 23615702. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-10-17 02:07:02,215][61453] Avg episode reward: [(0, '9.210'), (1, '8.430')] -[2023-10-17 02:07:02,992][62408] Updated weights for policy 1, policy_version 45930 (0.0007) -[2023-10-17 02:07:03,359][62408] Updated weights for policy 1, policy_version 45940 (0.0009) -[2023-10-17 02:07:03,479][62373] Updated weights for policy 0, policy_version 46280 (0.0009) -[2023-10-17 02:07:03,736][62408] Updated weights for policy 1, policy_version 45950 (0.0010) -[2023-10-17 02:07:03,842][62373] Updated weights for policy 0, policy_version 46290 (0.0009) -[2023-10-17 02:07:04,218][62373] Updated weights for policy 0, policy_version 46300 (0.0009) -[2023-10-17 02:07:07,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 94470144. Throughput: 0: 1765.6, 1: 1767.7. Samples: 23625272. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-10-17 02:07:07,215][61453] Avg episode reward: [(0, '9.070'), (1, '8.170')] -[2023-10-17 02:07:07,621][62408] Updated weights for policy 1, policy_version 45960 (0.0009) -[2023-10-17 02:07:07,991][62373] Updated weights for policy 0, policy_version 46310 (0.0009) -[2023-10-17 02:07:08,002][62408] Updated weights for policy 1, policy_version 45970 (0.0007) -[2023-10-17 02:07:08,361][62373] Updated weights for policy 0, policy_version 46320 (0.0008) -[2023-10-17 02:07:08,372][62408] Updated weights for policy 1, policy_version 45980 (0.0008) -[2023-10-17 02:07:08,727][62373] Updated weights for policy 0, policy_version 46330 (0.0007) -[2023-10-17 02:07:12,205][62408] Updated weights for policy 1, policy_version 45990 (0.0008) -[2023-10-17 02:07:12,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 94535680. Throughput: 0: 1772.0, 1: 1773.3. Samples: 23647468. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-10-17 02:07:12,214][61453] Avg episode reward: [(0, '9.100'), (1, '8.120')] -[2023-10-17 02:07:12,531][62373] Updated weights for policy 0, policy_version 46340 (0.0008) -[2023-10-17 02:07:12,561][62408] Updated weights for policy 1, policy_version 46000 (0.0007) -[2023-10-17 02:07:12,897][62373] Updated weights for policy 0, policy_version 46350 (0.0007) -[2023-10-17 02:07:12,926][62408] Updated weights for policy 1, policy_version 46010 (0.0008) -[2023-10-17 02:07:13,263][62373] Updated weights for policy 0, policy_version 46360 (0.0008) -[2023-10-17 02:07:16,687][62408] Updated weights for policy 1, policy_version 46020 (0.0009) -[2023-10-17 02:07:16,947][62373] Updated weights for policy 0, policy_version 46370 (0.0009) -[2023-10-17 02:07:17,050][62408] Updated weights for policy 1, policy_version 46030 (0.0009) -[2023-10-17 02:07:17,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 94601216. Throughput: 0: 1803.6, 1: 1790.0. Samples: 23669258. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:07:17,214][61453] Avg episode reward: [(0, '8.600'), (1, '7.890')] -[2023-10-17 02:07:17,324][62373] Updated weights for policy 0, policy_version 46380 (0.0008) -[2023-10-17 02:07:17,420][62408] Updated weights for policy 1, policy_version 46040 (0.0008) -[2023-10-17 02:07:17,681][62373] Updated weights for policy 0, policy_version 46390 (0.0009) -[2023-10-17 02:07:18,048][62373] Updated weights for policy 0, policy_version 46400 (0.0009) -[2023-10-17 02:07:21,251][62408] Updated weights for policy 1, policy_version 46050 (0.0008) -[2023-10-17 02:07:21,617][62408] Updated weights for policy 1, policy_version 46060 (0.0008) -[2023-10-17 02:07:21,888][62373] Updated weights for policy 0, policy_version 46410 (0.0007) -[2023-10-17 02:07:21,974][62408] Updated weights for policy 1, policy_version 46070 (0.0009) -[2023-10-17 02:07:22,214][61453] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 94666752. Throughput: 0: 1779.7, 1: 1770.6. Samples: 23679388. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:07:22,215][61453] Avg episode reward: [(0, '9.190'), (1, '8.360')] -[2023-10-17 02:07:22,268][62373] Updated weights for policy 0, policy_version 46420 (0.0008) -[2023-10-17 02:07:22,346][62408] Updated weights for policy 1, policy_version 46080 (0.0008) -[2023-10-17 02:07:22,636][62373] Updated weights for policy 0, policy_version 46430 (0.0008) -[2023-10-17 02:07:26,272][62408] Updated weights for policy 1, policy_version 46090 (0.0008) -[2023-10-17 02:07:26,511][62373] Updated weights for policy 0, policy_version 46440 (0.0008) -[2023-10-17 02:07:26,638][62408] Updated weights for policy 1, policy_version 46100 (0.0009) -[2023-10-17 02:07:26,894][62373] Updated weights for policy 0, policy_version 46450 (0.0009) -[2023-10-17 02:07:27,012][62408] Updated weights for policy 1, policy_version 46110 (0.0009) -[2023-10-17 02:07:27,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 94765056. Throughput: 0: 1794.8, 1: 1796.8. Samples: 23701214. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:07:27,215][61453] Avg episode reward: [(0, '9.030'), (1, '8.890')] -[2023-10-17 02:07:27,258][62373] Updated weights for policy 0, policy_version 46460 (0.0007) -[2023-10-17 02:07:30,810][62408] Updated weights for policy 1, policy_version 46120 (0.0008) -[2023-10-17 02:07:31,082][62373] Updated weights for policy 0, policy_version 46470 (0.0009) -[2023-10-17 02:07:31,182][62408] Updated weights for policy 1, policy_version 46130 (0.0009) -[2023-10-17 02:07:31,464][62373] Updated weights for policy 0, policy_version 46480 (0.0008) -[2023-10-17 02:07:31,548][62408] Updated weights for policy 1, policy_version 46140 (0.0008) -[2023-10-17 02:07:31,841][62373] Updated weights for policy 0, policy_version 46490 (0.0009) -[2023-10-17 02:07:32,214][61453] Fps is (10 sec: 19660.2, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 94863360. Throughput: 0: 1776.7, 1: 1758.1. Samples: 23720576. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:07:32,215][61453] Avg episode reward: [(0, '8.330'), (1, '8.990')] -[2023-10-17 02:07:32,226][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000046496_47611904.pth... -[2023-10-17 02:07:32,226][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000046144_47251456.pth... -[2023-10-17 02:07:32,266][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000044480_45547520.pth -[2023-10-17 02:07:32,267][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000044832_45907968.pth -[2023-10-17 02:07:35,387][62408] Updated weights for policy 1, policy_version 46150 (0.0009) -[2023-10-17 02:07:35,629][62373] Updated weights for policy 0, policy_version 46500 (0.0007) -[2023-10-17 02:07:35,751][62408] Updated weights for policy 1, policy_version 46160 (0.0009) -[2023-10-17 02:07:36,002][62373] Updated weights for policy 0, policy_version 46510 (0.0008) -[2023-10-17 02:07:36,125][62408] Updated weights for policy 1, policy_version 46170 (0.0010) -[2023-10-17 02:07:36,364][62373] Updated weights for policy 0, policy_version 46520 (0.0008) -[2023-10-17 02:07:37,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 94928896. Throughput: 0: 1786.2, 1: 1786.3. Samples: 23732710. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:07:37,215][61453] Avg episode reward: [(0, '8.350'), (1, '9.450')] -[2023-10-17 02:07:39,909][62408] Updated weights for policy 1, policy_version 46180 (0.0008) -[2023-10-17 02:07:40,159][62373] Updated weights for policy 0, policy_version 46530 (0.0009) -[2023-10-17 02:07:40,283][62408] Updated weights for policy 1, policy_version 46190 (0.0008) -[2023-10-17 02:07:40,527][62373] Updated weights for policy 0, policy_version 46540 (0.0009) -[2023-10-17 02:07:40,657][62408] Updated weights for policy 1, policy_version 46200 (0.0008) -[2023-10-17 02:07:40,900][62373] Updated weights for policy 0, policy_version 46550 (0.0009) -[2023-10-17 02:07:41,282][62373] Updated weights for policy 0, policy_version 46560 (0.0008) -[2023-10-17 02:07:42,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 94994432. Throughput: 0: 1777.4, 1: 1761.5. Samples: 23752748. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:07:42,215][61453] Avg episode reward: [(0, '8.420'), (1, '9.750')] -[2023-10-17 02:07:44,524][62408] Updated weights for policy 1, policy_version 46210 (0.0008) -[2023-10-17 02:07:44,891][62408] Updated weights for policy 1, policy_version 46220 (0.0010) -[2023-10-17 02:07:45,172][62373] Updated weights for policy 0, policy_version 46570 (0.0008) -[2023-10-17 02:07:45,257][62408] Updated weights for policy 1, policy_version 46230 (0.0007) -[2023-10-17 02:07:45,537][62373] Updated weights for policy 0, policy_version 46580 (0.0008) -[2023-10-17 02:07:45,627][62408] Updated weights for policy 1, policy_version 46240 (0.0007) -[2023-10-17 02:07:45,908][62373] Updated weights for policy 0, policy_version 46590 (0.0008) -[2023-10-17 02:07:47,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 95059968. Throughput: 0: 1767.1, 1: 1750.1. Samples: 23773976. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:07:47,214][61453] Avg episode reward: [(0, '8.670'), (1, '9.670')] -[2023-10-17 02:07:49,590][62408] Updated weights for policy 1, policy_version 46250 (0.0008) -[2023-10-17 02:07:49,659][62373] Updated weights for policy 0, policy_version 46600 (0.0008) -[2023-10-17 02:07:49,960][62408] Updated weights for policy 1, policy_version 46260 (0.0008) -[2023-10-17 02:07:50,037][62373] Updated weights for policy 0, policy_version 46610 (0.0009) -[2023-10-17 02:07:50,326][62408] Updated weights for policy 1, policy_version 46270 (0.0008) -[2023-10-17 02:07:50,399][62373] Updated weights for policy 0, policy_version 46620 (0.0008) -[2023-10-17 02:07:52,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 95125504. Throughput: 0: 1782.5, 1: 1763.2. Samples: 23784830. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:07:52,214][61453] Avg episode reward: [(0, '8.550'), (1, '9.390')] -[2023-10-17 02:07:54,001][62408] Updated weights for policy 1, policy_version 46280 (0.0008) -[2023-10-17 02:07:54,359][62373] Updated weights for policy 0, policy_version 46630 (0.0009) -[2023-10-17 02:07:54,367][62408] Updated weights for policy 1, policy_version 46290 (0.0007) -[2023-10-17 02:07:54,737][62373] Updated weights for policy 0, policy_version 46640 (0.0009) -[2023-10-17 02:07:54,739][62408] Updated weights for policy 1, policy_version 46300 (0.0007) -[2023-10-17 02:07:55,097][62373] Updated weights for policy 0, policy_version 46650 (0.0009) -[2023-10-17 02:07:57,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 95191040. Throughput: 0: 1755.1, 1: 1749.0. Samples: 23805152. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:07:57,215][61453] Avg episode reward: [(0, '9.100'), (1, '10.000')] -[2023-10-17 02:07:58,610][62408] Updated weights for policy 1, policy_version 46310 (0.0009) -[2023-10-17 02:07:58,985][62408] Updated weights for policy 1, policy_version 46320 (0.0008) -[2023-10-17 02:07:59,012][62373] Updated weights for policy 0, policy_version 46660 (0.0008) -[2023-10-17 02:07:59,343][62408] Updated weights for policy 1, policy_version 46330 (0.0008) -[2023-10-17 02:07:59,375][62373] Updated weights for policy 0, policy_version 46670 (0.0009) -[2023-10-17 02:07:59,744][62373] Updated weights for policy 0, policy_version 46680 (0.0009) -[2023-10-17 02:08:02,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 95256576. Throughput: 0: 1755.7, 1: 1759.2. Samples: 23827430. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:08:02,214][61453] Avg episode reward: [(0, '8.850'), (1, '9.760')] -[2023-10-17 02:08:03,206][62408] Updated weights for policy 1, policy_version 46340 (0.0010) -[2023-10-17 02:08:03,375][62373] Updated weights for policy 0, policy_version 46690 (0.0010) -[2023-10-17 02:08:03,576][62408] Updated weights for policy 1, policy_version 46350 (0.0008) -[2023-10-17 02:08:03,753][62373] Updated weights for policy 0, policy_version 46700 (0.0008) -[2023-10-17 02:08:03,946][62408] Updated weights for policy 1, policy_version 46360 (0.0007) -[2023-10-17 02:08:04,127][62373] Updated weights for policy 0, policy_version 46710 (0.0009) -[2023-10-17 02:08:04,498][62373] Updated weights for policy 0, policy_version 46720 (0.0009) -[2023-10-17 02:08:07,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 95322112. Throughput: 0: 1750.5, 1: 1752.5. Samples: 23837026. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:08:07,214][61453] Avg episode reward: [(0, '8.590'), (1, '9.360')] -[2023-10-17 02:08:07,857][62408] Updated weights for policy 1, policy_version 46370 (0.0007) -[2023-10-17 02:08:08,224][62408] Updated weights for policy 1, policy_version 46380 (0.0008) -[2023-10-17 02:08:08,400][62373] Updated weights for policy 0, policy_version 46730 (0.0008) -[2023-10-17 02:08:08,598][62408] Updated weights for policy 1, policy_version 46390 (0.0008) -[2023-10-17 02:08:08,765][62373] Updated weights for policy 0, policy_version 46740 (0.0008) -[2023-10-17 02:08:08,959][62408] Updated weights for policy 1, policy_version 46400 (0.0008) -[2023-10-17 02:08:09,134][62373] Updated weights for policy 0, policy_version 46750 (0.0008) -[2023-10-17 02:08:12,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 95387648. Throughput: 0: 1756.1, 1: 1745.8. Samples: 23858800. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:08:12,215][61453] Avg episode reward: [(0, '9.010'), (1, '9.900')] -[2023-10-17 02:08:12,747][62373] Updated weights for policy 0, policy_version 46760 (0.0010) -[2023-10-17 02:08:12,850][62408] Updated weights for policy 1, policy_version 46410 (0.0009) -[2023-10-17 02:08:13,111][62373] Updated weights for policy 0, policy_version 46770 (0.0009) -[2023-10-17 02:08:13,224][62408] Updated weights for policy 1, policy_version 46420 (0.0008) -[2023-10-17 02:08:13,474][62373] Updated weights for policy 0, policy_version 46780 (0.0010) -[2023-10-17 02:08:13,585][62408] Updated weights for policy 1, policy_version 46430 (0.0009) -[2023-10-17 02:08:17,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 95453184. Throughput: 0: 1784.7, 1: 1777.6. Samples: 23880876. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:08:17,215][61453] Avg episode reward: [(0, '9.480'), (1, '9.530')] -[2023-10-17 02:08:17,291][62408] Updated weights for policy 1, policy_version 46440 (0.0009) -[2023-10-17 02:08:17,437][62373] Updated weights for policy 0, policy_version 46790 (0.0008) -[2023-10-17 02:08:17,657][62408] Updated weights for policy 1, policy_version 46450 (0.0008) -[2023-10-17 02:08:17,810][62373] Updated weights for policy 0, policy_version 46800 (0.0008) -[2023-10-17 02:08:18,027][62408] Updated weights for policy 1, policy_version 46460 (0.0009) -[2023-10-17 02:08:18,176][62373] Updated weights for policy 0, policy_version 46810 (0.0007) -[2023-10-17 02:08:21,905][62373] Updated weights for policy 0, policy_version 46820 (0.0010) -[2023-10-17 02:08:21,980][62408] Updated weights for policy 1, policy_version 46470 (0.0008) -[2023-10-17 02:08:22,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 95518720. Throughput: 0: 1760.8, 1: 1742.6. Samples: 23890362. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:08:22,215][61453] Avg episode reward: [(0, '9.300'), (1, '9.740')] -[2023-10-17 02:08:22,275][62373] Updated weights for policy 0, policy_version 46830 (0.0008) -[2023-10-17 02:08:22,346][62408] Updated weights for policy 1, policy_version 46480 (0.0007) -[2023-10-17 02:08:22,645][62373] Updated weights for policy 0, policy_version 46840 (0.0007) -[2023-10-17 02:08:22,713][62408] Updated weights for policy 1, policy_version 46490 (0.0007) -[2023-10-17 02:08:26,449][62408] Updated weights for policy 1, policy_version 46500 (0.0007) -[2023-10-17 02:08:26,590][62373] Updated weights for policy 0, policy_version 46850 (0.0009) -[2023-10-17 02:08:26,819][62408] Updated weights for policy 1, policy_version 46510 (0.0007) -[2023-10-17 02:08:26,960][62373] Updated weights for policy 0, policy_version 46860 (0.0007) -[2023-10-17 02:08:27,191][62408] Updated weights for policy 1, policy_version 46520 (0.0007) -[2023-10-17 02:08:27,214][61453] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 95584256. Throughput: 0: 1770.7, 1: 1769.0. Samples: 23912036. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:08:27,215][61453] Avg episode reward: [(0, '8.900'), (1, '9.290')] -[2023-10-17 02:08:27,328][62373] Updated weights for policy 0, policy_version 46870 (0.0007) -[2023-10-17 02:08:27,694][62373] Updated weights for policy 0, policy_version 46880 (0.0008) -[2023-10-17 02:08:30,993][62408] Updated weights for policy 1, policy_version 46530 (0.0007) -[2023-10-17 02:08:31,360][62408] Updated weights for policy 1, policy_version 46540 (0.0007) -[2023-10-17 02:08:31,553][62373] Updated weights for policy 0, policy_version 46890 (0.0007) -[2023-10-17 02:08:31,738][62408] Updated weights for policy 1, policy_version 46550 (0.0007) -[2023-10-17 02:08:31,921][62373] Updated weights for policy 0, policy_version 46900 (0.0007) -[2023-10-17 02:08:32,107][62408] Updated weights for policy 1, policy_version 46560 (0.0008) -[2023-10-17 02:08:32,214][61453] Fps is (10 sec: 16384.0, 60 sec: 13653.4, 300 sec: 14218.0). Total num frames: 95682560. Throughput: 0: 1764.1, 1: 1750.8. Samples: 23932146. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:08:32,215][61453] Avg episode reward: [(0, '9.100'), (1, '9.150')] -[2023-10-17 02:08:32,294][62373] Updated weights for policy 0, policy_version 46910 (0.0008) -[2023-10-17 02:08:36,026][62373] Updated weights for policy 0, policy_version 46920 (0.0007) -[2023-10-17 02:08:36,225][62408] Updated weights for policy 1, policy_version 46570 (0.0007) -[2023-10-17 02:08:36,406][62373] Updated weights for policy 0, policy_version 46930 (0.0007) -[2023-10-17 02:08:36,601][62408] Updated weights for policy 1, policy_version 46580 (0.0008) -[2023-10-17 02:08:36,771][62373] Updated weights for policy 0, policy_version 46940 (0.0008) -[2023-10-17 02:08:36,965][62408] Updated weights for policy 1, policy_version 46590 (0.0008) -[2023-10-17 02:08:37,214][61453] Fps is (10 sec: 19660.8, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 95780864. Throughput: 0: 1765.1, 1: 1761.7. Samples: 23943536. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:08:37,214][61453] Avg episode reward: [(0, '9.510'), (1, '9.180')] -[2023-10-17 02:08:40,650][62373] Updated weights for policy 0, policy_version 46950 (0.0008) -[2023-10-17 02:08:40,792][62408] Updated weights for policy 1, policy_version 46600 (0.0008) -[2023-10-17 02:08:41,019][62373] Updated weights for policy 0, policy_version 46960 (0.0008) -[2023-10-17 02:08:41,160][62408] Updated weights for policy 1, policy_version 46610 (0.0007) -[2023-10-17 02:08:41,399][62373] Updated weights for policy 0, policy_version 46970 (0.0008) -[2023-10-17 02:08:41,528][62408] Updated weights for policy 1, policy_version 46620 (0.0007) -[2023-10-17 02:08:42,214][61453] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 95846400. Throughput: 0: 1775.4, 1: 1758.1. Samples: 23964162. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:08:42,215][61453] Avg episode reward: [(0, '9.340'), (1, '8.390')] -[2023-10-17 02:08:45,253][62373] Updated weights for policy 0, policy_version 46980 (0.0008) -[2023-10-17 02:08:45,482][62408] Updated weights for policy 1, policy_version 46630 (0.0008) -[2023-10-17 02:08:45,620][62373] Updated weights for policy 0, policy_version 46990 (0.0008) -[2023-10-17 02:08:45,851][62408] Updated weights for policy 1, policy_version 46640 (0.0009) -[2023-10-17 02:08:45,992][62373] Updated weights for policy 0, policy_version 47000 (0.0009) -[2023-10-17 02:08:46,229][62408] Updated weights for policy 1, policy_version 46650 (0.0008) -[2023-10-17 02:08:47,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 95911936. Throughput: 0: 1754.7, 1: 1730.9. Samples: 23984284. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:08:47,215][61453] Avg episode reward: [(0, '9.090'), (1, '9.010')] -[2023-10-17 02:08:49,917][62373] Updated weights for policy 0, policy_version 47010 (0.0009) -[2023-10-17 02:08:50,090][62408] Updated weights for policy 1, policy_version 46660 (0.0011) -[2023-10-17 02:08:50,281][62373] Updated weights for policy 0, policy_version 47020 (0.0009) -[2023-10-17 02:08:50,448][62408] Updated weights for policy 1, policy_version 46670 (0.0008) -[2023-10-17 02:08:50,649][62373] Updated weights for policy 0, policy_version 47030 (0.0008) -[2023-10-17 02:08:50,821][62408] Updated weights for policy 1, policy_version 46680 (0.0008) -[2023-10-17 02:08:51,012][62373] Updated weights for policy 0, policy_version 47040 (0.0007) -[2023-10-17 02:08:52,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 95977472. Throughput: 0: 1781.9, 1: 1758.8. Samples: 23996354. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:08:52,215][61453] Avg episode reward: [(0, '8.460'), (1, '9.210')] -[2023-10-17 02:08:54,626][62373] Updated weights for policy 0, policy_version 47050 (0.0007) -[2023-10-17 02:08:54,832][62408] Updated weights for policy 1, policy_version 46690 (0.0007) -[2023-10-17 02:08:54,993][62373] Updated weights for policy 0, policy_version 47060 (0.0008) -[2023-10-17 02:08:55,208][62408] Updated weights for policy 1, policy_version 46700 (0.0009) -[2023-10-17 02:08:55,359][62373] Updated weights for policy 0, policy_version 47070 (0.0009) -[2023-10-17 02:08:55,570][62408] Updated weights for policy 1, policy_version 46710 (0.0009) -[2023-10-17 02:08:55,941][62408] Updated weights for policy 1, policy_version 46720 (0.0008) -[2023-10-17 02:08:57,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 96043008. Throughput: 0: 1757.5, 1: 1736.2. Samples: 24016014. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:08:57,214][61453] Avg episode reward: [(0, '8.580'), (1, '8.960')] -[2023-10-17 02:08:59,049][62373] Updated weights for policy 0, policy_version 47080 (0.0008) -[2023-10-17 02:08:59,407][62373] Updated weights for policy 0, policy_version 47090 (0.0008) -[2023-10-17 02:08:59,772][62373] Updated weights for policy 0, policy_version 47100 (0.0010) -[2023-10-17 02:08:59,774][62408] Updated weights for policy 1, policy_version 46730 (0.0009) -[2023-10-17 02:09:00,141][62408] Updated weights for policy 1, policy_version 46740 (0.0009) -[2023-10-17 02:09:00,513][62408] Updated weights for policy 1, policy_version 46750 (0.0009) -[2023-10-17 02:09:02,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 96108544. Throughput: 0: 1761.4, 1: 1730.0. Samples: 24037992. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:09:02,215][61453] Avg episode reward: [(0, '8.210'), (1, '9.250')] -[2023-10-17 02:09:03,632][62373] Updated weights for policy 0, policy_version 47110 (0.0009) -[2023-10-17 02:09:04,018][62373] Updated weights for policy 0, policy_version 47120 (0.0008) -[2023-10-17 02:09:04,377][62373] Updated weights for policy 0, policy_version 47130 (0.0009) -[2023-10-17 02:09:04,418][62408] Updated weights for policy 1, policy_version 46760 (0.0008) -[2023-10-17 02:09:04,785][62408] Updated weights for policy 1, policy_version 46770 (0.0007) -[2023-10-17 02:09:05,159][62408] Updated weights for policy 1, policy_version 46780 (0.0008) -[2023-10-17 02:09:07,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 96174080. Throughput: 0: 1760.0, 1: 1743.0. Samples: 24047996. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:09:07,215][61453] Avg episode reward: [(0, '8.280'), (1, '8.810')] -[2023-10-17 02:09:08,153][62373] Updated weights for policy 0, policy_version 47140 (0.0007) -[2023-10-17 02:09:08,524][62373] Updated weights for policy 0, policy_version 47150 (0.0009) -[2023-10-17 02:09:08,894][62373] Updated weights for policy 0, policy_version 47160 (0.0009) -[2023-10-17 02:09:08,945][62408] Updated weights for policy 1, policy_version 46790 (0.0007) -[2023-10-17 02:09:09,326][62408] Updated weights for policy 1, policy_version 46800 (0.0008) -[2023-10-17 02:09:09,699][62408] Updated weights for policy 1, policy_version 46810 (0.0008) -[2023-10-17 02:09:12,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 96239616. Throughput: 0: 1769.5, 1: 1725.7. Samples: 24069320. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:09:12,214][61453] Avg episode reward: [(0, '9.150'), (1, '8.920')] -[2023-10-17 02:09:12,748][62373] Updated weights for policy 0, policy_version 47170 (0.0009) -[2023-10-17 02:09:13,119][62373] Updated weights for policy 0, policy_version 47180 (0.0011) -[2023-10-17 02:09:13,487][62373] Updated weights for policy 0, policy_version 47190 (0.0008) -[2023-10-17 02:09:13,540][62408] Updated weights for policy 1, policy_version 46820 (0.0008) -[2023-10-17 02:09:13,859][62373] Updated weights for policy 0, policy_version 47200 (0.0007) -[2023-10-17 02:09:13,902][62408] Updated weights for policy 1, policy_version 46830 (0.0008) -[2023-10-17 02:09:14,261][62408] Updated weights for policy 1, policy_version 46840 (0.0009) -[2023-10-17 02:09:17,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 96305152. Throughput: 0: 1788.6, 1: 1750.3. Samples: 24091398. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:09:17,215][61453] Avg episode reward: [(0, '8.930'), (1, '8.210')] -[2023-10-17 02:09:17,672][62373] Updated weights for policy 0, policy_version 47210 (0.0008) -[2023-10-17 02:09:18,044][62373] Updated weights for policy 0, policy_version 47220 (0.0011) -[2023-10-17 02:09:18,157][62408] Updated weights for policy 1, policy_version 46850 (0.0008) -[2023-10-17 02:09:18,430][62373] Updated weights for policy 0, policy_version 47230 (0.0007) -[2023-10-17 02:09:18,537][62408] Updated weights for policy 1, policy_version 46860 (0.0008) -[2023-10-17 02:09:18,899][62408] Updated weights for policy 1, policy_version 46870 (0.0009) -[2023-10-17 02:09:19,263][62408] Updated weights for policy 1, policy_version 46880 (0.0011) -[2023-10-17 02:09:22,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 96370688. Throughput: 0: 1772.8, 1: 1725.5. Samples: 24100958. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:09:22,215][61453] Avg episode reward: [(0, '9.190'), (1, '7.970')] -[2023-10-17 02:09:22,230][62373] Updated weights for policy 0, policy_version 47240 (0.0008) -[2023-10-17 02:09:22,598][62373] Updated weights for policy 0, policy_version 47250 (0.0010) -[2023-10-17 02:09:22,976][62373] Updated weights for policy 0, policy_version 47260 (0.0008) -[2023-10-17 02:09:23,207][62408] Updated weights for policy 1, policy_version 46890 (0.0008) -[2023-10-17 02:09:23,586][62408] Updated weights for policy 1, policy_version 46900 (0.0009) -[2023-10-17 02:09:23,954][62408] Updated weights for policy 1, policy_version 46910 (0.0007) -[2023-10-17 02:09:26,790][62373] Updated weights for policy 0, policy_version 47270 (0.0009) -[2023-10-17 02:09:27,170][62373] Updated weights for policy 0, policy_version 47280 (0.0010) -[2023-10-17 02:09:27,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 96436224. Throughput: 0: 1787.9, 1: 1742.3. Samples: 24123018. Policy #0 lag: (min: 31.0, avg: 31.0, max: 36.0) -[2023-10-17 02:09:27,215][61453] Avg episode reward: [(0, '8.950'), (1, '8.660')] -[2023-10-17 02:09:27,532][62373] Updated weights for policy 0, policy_version 47290 (0.0010) -[2023-10-17 02:09:27,680][62408] Updated weights for policy 1, policy_version 46920 (0.0008) -[2023-10-17 02:09:28,055][62408] Updated weights for policy 1, policy_version 46930 (0.0008) -[2023-10-17 02:09:28,414][62408] Updated weights for policy 1, policy_version 46940 (0.0009) -[2023-10-17 02:09:31,249][62373] Updated weights for policy 0, policy_version 47300 (0.0010) -[2023-10-17 02:09:31,614][62373] Updated weights for policy 0, policy_version 47310 (0.0008) -[2023-10-17 02:09:31,979][62373] Updated weights for policy 0, policy_version 47320 (0.0007) -[2023-10-17 02:09:32,195][62408] Updated weights for policy 1, policy_version 46950 (0.0007) -[2023-10-17 02:09:32,214][61453] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 96501760. Throughput: 0: 1789.8, 1: 1775.5. Samples: 24144724. Policy #0 lag: (min: 31.0, avg: 31.0, max: 36.0) -[2023-10-17 02:09:32,215][61453] Avg episode reward: [(0, '9.210'), (1, '8.170')] -[2023-10-17 02:09:32,268][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000047328_48463872.pth... -[2023-10-17 02:09:32,304][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000045664_46759936.pth -[2023-10-17 02:09:32,568][62408] Updated weights for policy 1, policy_version 46960 (0.0007) -[2023-10-17 02:09:32,938][62408] Updated weights for policy 1, policy_version 46970 (0.0009) -[2023-10-17 02:09:33,158][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000046976_48103424.pth... -[2023-10-17 02:09:33,200][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000045312_46399488.pth -[2023-10-17 02:09:35,591][62373] Updated weights for policy 0, policy_version 47330 (0.0007) -[2023-10-17 02:09:35,961][62373] Updated weights for policy 0, policy_version 47340 (0.0008) -[2023-10-17 02:09:36,346][62373] Updated weights for policy 0, policy_version 47350 (0.0008) -[2023-10-17 02:09:36,712][62373] Updated weights for policy 0, policy_version 47360 (0.0009) -[2023-10-17 02:09:36,768][62408] Updated weights for policy 1, policy_version 46980 (0.0009) -[2023-10-17 02:09:37,136][62408] Updated weights for policy 1, policy_version 46990 (0.0009) -[2023-10-17 02:09:37,214][61453] Fps is (10 sec: 16384.3, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 96600064. Throughput: 0: 1793.0, 1: 1745.3. Samples: 24155580. Policy #0 lag: (min: 31.0, avg: 31.0, max: 36.0) -[2023-10-17 02:09:37,215][61453] Avg episode reward: [(0, '9.330'), (1, '8.620')] -[2023-10-17 02:09:37,513][62408] Updated weights for policy 1, policy_version 47000 (0.0009) -[2023-10-17 02:09:40,462][62373] Updated weights for policy 0, policy_version 47370 (0.0010) -[2023-10-17 02:09:40,831][62373] Updated weights for policy 0, policy_version 47380 (0.0008) -[2023-10-17 02:09:41,210][62373] Updated weights for policy 0, policy_version 47390 (0.0010) -[2023-10-17 02:09:41,292][62408] Updated weights for policy 1, policy_version 47010 (0.0009) -[2023-10-17 02:09:41,650][62408] Updated weights for policy 1, policy_version 47020 (0.0007) -[2023-10-17 02:09:42,018][62408] Updated weights for policy 1, policy_version 47030 (0.0007) -[2023-10-17 02:09:42,214][61453] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 96665600. Throughput: 0: 1792.7, 1: 1775.0. Samples: 24176562. Policy #0 lag: (min: 31.0, avg: 31.0, max: 36.0) -[2023-10-17 02:09:42,215][61453] Avg episode reward: [(0, '8.870'), (1, '8.870')] -[2023-10-17 02:09:42,382][62408] Updated weights for policy 1, policy_version 47040 (0.0008) -[2023-10-17 02:09:45,094][62373] Updated weights for policy 0, policy_version 47400 (0.0008) -[2023-10-17 02:09:45,460][62373] Updated weights for policy 0, policy_version 47410 (0.0008) -[2023-10-17 02:09:45,837][62373] Updated weights for policy 0, policy_version 47420 (0.0009) -[2023-10-17 02:09:46,159][62408] Updated weights for policy 1, policy_version 47050 (0.0010) -[2023-10-17 02:09:46,538][62408] Updated weights for policy 1, policy_version 47060 (0.0009) -[2023-10-17 02:09:46,899][62408] Updated weights for policy 1, policy_version 47070 (0.0009) -[2023-10-17 02:09:47,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 96763904. Throughput: 0: 1775.0, 1: 1757.9. Samples: 24196972. Policy #0 lag: (min: 31.0, avg: 31.0, max: 36.0) -[2023-10-17 02:09:47,215][61453] Avg episode reward: [(0, '8.780'), (1, '9.210')] -[2023-10-17 02:09:49,740][62373] Updated weights for policy 0, policy_version 47430 (0.0009) -[2023-10-17 02:09:50,117][62373] Updated weights for policy 0, policy_version 47440 (0.0010) -[2023-10-17 02:09:50,485][62373] Updated weights for policy 0, policy_version 47450 (0.0010) -[2023-10-17 02:09:50,804][62408] Updated weights for policy 1, policy_version 47080 (0.0010) -[2023-10-17 02:09:51,172][62408] Updated weights for policy 1, policy_version 47090 (0.0010) -[2023-10-17 02:09:51,542][62408] Updated weights for policy 1, policy_version 47100 (0.0011) -[2023-10-17 02:09:52,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 96829440. Throughput: 0: 1795.0, 1: 1772.0. Samples: 24208514. Policy #0 lag: (min: 31.0, avg: 31.0, max: 36.0) -[2023-10-17 02:09:52,215][61453] Avg episode reward: [(0, '8.720'), (1, '9.240')] -[2023-10-17 02:09:54,199][62373] Updated weights for policy 0, policy_version 47460 (0.0007) -[2023-10-17 02:09:54,566][62373] Updated weights for policy 0, policy_version 47470 (0.0008) -[2023-10-17 02:09:54,946][62373] Updated weights for policy 0, policy_version 47480 (0.0009) -[2023-10-17 02:09:55,345][62408] Updated weights for policy 1, policy_version 47110 (0.0009) -[2023-10-17 02:09:55,719][62408] Updated weights for policy 1, policy_version 47120 (0.0008) -[2023-10-17 02:09:56,086][62408] Updated weights for policy 1, policy_version 47130 (0.0008) -[2023-10-17 02:09:57,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 96894976. Throughput: 0: 1778.4, 1: 1769.2. Samples: 24228962. Policy #0 lag: (min: 27.0, avg: 28.8, max: 57.0) -[2023-10-17 02:09:57,214][61453] Avg episode reward: [(0, '9.210'), (1, '8.610')] -[2023-10-17 02:09:58,779][62373] Updated weights for policy 0, policy_version 47490 (0.0010) -[2023-10-17 02:09:59,154][62373] Updated weights for policy 0, policy_version 47500 (0.0008) -[2023-10-17 02:09:59,531][62373] Updated weights for policy 0, policy_version 47510 (0.0008) -[2023-10-17 02:09:59,899][62373] Updated weights for policy 0, policy_version 47520 (0.0009) -[2023-10-17 02:09:59,905][62408] Updated weights for policy 1, policy_version 47140 (0.0008) -[2023-10-17 02:10:00,273][62408] Updated weights for policy 1, policy_version 47150 (0.0007) -[2023-10-17 02:10:00,647][62408] Updated weights for policy 1, policy_version 47160 (0.0010) -[2023-10-17 02:10:02,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 96960512. Throughput: 0: 1781.7, 1: 1756.5. Samples: 24250616. Policy #0 lag: (min: 27.0, avg: 28.8, max: 57.0) -[2023-10-17 02:10:02,215][61453] Avg episode reward: [(0, '9.240'), (1, '8.700')] -[2023-10-17 02:10:03,667][62373] Updated weights for policy 0, policy_version 47530 (0.0011) -[2023-10-17 02:10:04,050][62373] Updated weights for policy 0, policy_version 47540 (0.0009) -[2023-10-17 02:10:04,376][62408] Updated weights for policy 1, policy_version 47170 (0.0008) -[2023-10-17 02:10:04,415][62373] Updated weights for policy 0, policy_version 47550 (0.0008) -[2023-10-17 02:10:04,736][62408] Updated weights for policy 1, policy_version 47180 (0.0007) -[2023-10-17 02:10:05,108][62408] Updated weights for policy 1, policy_version 47190 (0.0008) -[2023-10-17 02:10:05,474][62408] Updated weights for policy 1, policy_version 47200 (0.0009) -[2023-10-17 02:10:07,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 97026048. Throughput: 0: 1775.7, 1: 1780.4. Samples: 24260984. Policy #0 lag: (min: 27.0, avg: 28.8, max: 57.0) -[2023-10-17 02:10:07,215][61453] Avg episode reward: [(0, '9.610'), (1, '9.420')] -[2023-10-17 02:10:08,160][62373] Updated weights for policy 0, policy_version 47560 (0.0007) -[2023-10-17 02:10:08,535][62373] Updated weights for policy 0, policy_version 47570 (0.0010) -[2023-10-17 02:10:08,903][62373] Updated weights for policy 0, policy_version 47580 (0.0008) -[2023-10-17 02:10:09,436][62408] Updated weights for policy 1, policy_version 47210 (0.0007) -[2023-10-17 02:10:09,813][62408] Updated weights for policy 1, policy_version 47220 (0.0008) -[2023-10-17 02:10:10,183][62408] Updated weights for policy 1, policy_version 47230 (0.0009) -[2023-10-17 02:10:12,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 97091584. Throughput: 0: 1778.1, 1: 1760.8. Samples: 24282266. Policy #0 lag: (min: 27.0, avg: 28.8, max: 57.0) -[2023-10-17 02:10:12,215][61453] Avg episode reward: [(0, '9.020'), (1, '9.340')] -[2023-10-17 02:10:12,712][62373] Updated weights for policy 0, policy_version 47590 (0.0008) -[2023-10-17 02:10:13,090][62373] Updated weights for policy 0, policy_version 47600 (0.0010) -[2023-10-17 02:10:13,461][62373] Updated weights for policy 0, policy_version 47610 (0.0009) -[2023-10-17 02:10:14,129][62408] Updated weights for policy 1, policy_version 47240 (0.0009) -[2023-10-17 02:10:14,504][62408] Updated weights for policy 1, policy_version 47250 (0.0010) -[2023-10-17 02:10:14,872][62408] Updated weights for policy 1, policy_version 47260 (0.0010) -[2023-10-17 02:10:17,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 97157120. Throughput: 0: 1789.8, 1: 1749.4. Samples: 24303988. Policy #0 lag: (min: 27.0, avg: 28.8, max: 57.0) -[2023-10-17 02:10:17,215][61453] Avg episode reward: [(0, '8.990'), (1, '8.980')] -[2023-10-17 02:10:17,334][62373] Updated weights for policy 0, policy_version 47620 (0.0009) -[2023-10-17 02:10:17,706][62373] Updated weights for policy 0, policy_version 47630 (0.0008) -[2023-10-17 02:10:18,076][62373] Updated weights for policy 0, policy_version 47640 (0.0007) -[2023-10-17 02:10:18,558][62408] Updated weights for policy 1, policy_version 47270 (0.0010) -[2023-10-17 02:10:18,926][62408] Updated weights for policy 1, policy_version 47280 (0.0009) -[2023-10-17 02:10:19,304][62408] Updated weights for policy 1, policy_version 47290 (0.0010) -[2023-10-17 02:10:21,990][62373] Updated weights for policy 0, policy_version 47650 (0.0008) -[2023-10-17 02:10:22,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 97222656. Throughput: 0: 1760.6, 1: 1754.4. Samples: 24313754. Policy #0 lag: (min: 27.0, avg: 28.8, max: 57.0) -[2023-10-17 02:10:22,214][61453] Avg episode reward: [(0, '8.910'), (1, '9.350')] -[2023-10-17 02:10:22,360][62373] Updated weights for policy 0, policy_version 47660 (0.0009) -[2023-10-17 02:10:22,728][62373] Updated weights for policy 0, policy_version 47670 (0.0007) -[2023-10-17 02:10:23,043][62408] Updated weights for policy 1, policy_version 47300 (0.0009) -[2023-10-17 02:10:23,091][62373] Updated weights for policy 0, policy_version 47680 (0.0007) -[2023-10-17 02:10:23,406][62408] Updated weights for policy 1, policy_version 47310 (0.0009) -[2023-10-17 02:10:23,773][62408] Updated weights for policy 1, policy_version 47320 (0.0008) -[2023-10-17 02:10:26,852][62373] Updated weights for policy 0, policy_version 47690 (0.0009) -[2023-10-17 02:10:27,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 97288192. Throughput: 0: 1781.4, 1: 1755.5. Samples: 24335722. Policy #0 lag: (min: 27.0, avg: 28.8, max: 57.0) -[2023-10-17 02:10:27,214][61453] Avg episode reward: [(0, '8.960'), (1, '9.780')] -[2023-10-17 02:10:27,233][62373] Updated weights for policy 0, policy_version 47700 (0.0011) -[2023-10-17 02:10:27,598][62373] Updated weights for policy 0, policy_version 47710 (0.0009) -[2023-10-17 02:10:27,688][62408] Updated weights for policy 1, policy_version 47330 (0.0010) -[2023-10-17 02:10:28,055][62408] Updated weights for policy 1, policy_version 47340 (0.0010) -[2023-10-17 02:10:28,433][62408] Updated weights for policy 1, policy_version 47350 (0.0009) -[2023-10-17 02:10:28,808][62408] Updated weights for policy 1, policy_version 47360 (0.0008) -[2023-10-17 02:10:31,490][62373] Updated weights for policy 0, policy_version 47720 (0.0008) -[2023-10-17 02:10:31,863][62373] Updated weights for policy 0, policy_version 47730 (0.0009) -[2023-10-17 02:10:32,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 97353728. Throughput: 0: 1773.0, 1: 1780.1. Samples: 24356860. Policy #0 lag: (min: 9.0, avg: 24.1, max: 41.0) -[2023-10-17 02:10:32,214][61453] Avg episode reward: [(0, '8.490'), (1, '9.030')] -[2023-10-17 02:10:32,227][62373] Updated weights for policy 0, policy_version 47740 (0.0007) -[2023-10-17 02:10:32,585][62408] Updated weights for policy 1, policy_version 47370 (0.0009) -[2023-10-17 02:10:32,962][62408] Updated weights for policy 1, policy_version 47380 (0.0009) -[2023-10-17 02:10:33,323][62408] Updated weights for policy 1, policy_version 47390 (0.0009) -[2023-10-17 02:10:35,942][62373] Updated weights for policy 0, policy_version 47750 (0.0009) -[2023-10-17 02:10:36,322][62373] Updated weights for policy 0, policy_version 47760 (0.0009) -[2023-10-17 02:10:36,684][62373] Updated weights for policy 0, policy_version 47770 (0.0009) -[2023-10-17 02:10:37,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 97452032. Throughput: 0: 1779.0, 1: 1751.2. Samples: 24367374. Policy #0 lag: (min: 9.0, avg: 24.1, max: 41.0) -[2023-10-17 02:10:37,215][61453] Avg episode reward: [(0, '8.470'), (1, '9.050')] -[2023-10-17 02:10:37,257][62408] Updated weights for policy 1, policy_version 47400 (0.0008) -[2023-10-17 02:10:37,627][62408] Updated weights for policy 1, policy_version 47410 (0.0007) -[2023-10-17 02:10:37,990][62408] Updated weights for policy 1, policy_version 47420 (0.0007) -[2023-10-17 02:10:40,487][62373] Updated weights for policy 0, policy_version 47780 (0.0009) -[2023-10-17 02:10:40,857][62373] Updated weights for policy 0, policy_version 47790 (0.0010) -[2023-10-17 02:10:41,235][62373] Updated weights for policy 0, policy_version 47800 (0.0009) -[2023-10-17 02:10:41,792][62408] Updated weights for policy 1, policy_version 47430 (0.0007) -[2023-10-17 02:10:42,159][62408] Updated weights for policy 1, policy_version 47440 (0.0008) -[2023-10-17 02:10:42,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 97517568. Throughput: 0: 1779.0, 1: 1769.6. Samples: 24388652. Policy #0 lag: (min: 9.0, avg: 24.1, max: 41.0) -[2023-10-17 02:10:42,214][61453] Avg episode reward: [(0, '8.640'), (1, '9.380')] -[2023-10-17 02:10:42,526][62408] Updated weights for policy 1, policy_version 47450 (0.0009) -[2023-10-17 02:10:44,904][62373] Updated weights for policy 0, policy_version 47810 (0.0008) -[2023-10-17 02:10:45,266][62373] Updated weights for policy 0, policy_version 47820 (0.0008) -[2023-10-17 02:10:45,640][62373] Updated weights for policy 0, policy_version 47830 (0.0010) -[2023-10-17 02:10:46,007][62373] Updated weights for policy 0, policy_version 47840 (0.0008) -[2023-10-17 02:10:46,326][62408] Updated weights for policy 1, policy_version 47460 (0.0008) -[2023-10-17 02:10:46,685][62408] Updated weights for policy 1, policy_version 47470 (0.0007) -[2023-10-17 02:10:47,060][62408] Updated weights for policy 1, policy_version 47480 (0.0007) -[2023-10-17 02:10:47,214][61453] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 97583104. Throughput: 0: 1761.1, 1: 1769.0. Samples: 24409468. Policy #0 lag: (min: 9.0, avg: 24.1, max: 41.0) -[2023-10-17 02:10:47,215][61453] Avg episode reward: [(0, '8.380'), (1, '8.680')] -[2023-10-17 02:10:49,824][62373] Updated weights for policy 0, policy_version 47850 (0.0009) -[2023-10-17 02:10:50,193][62373] Updated weights for policy 0, policy_version 47860 (0.0008) -[2023-10-17 02:10:50,560][62373] Updated weights for policy 0, policy_version 47870 (0.0009) -[2023-10-17 02:10:51,000][62408] Updated weights for policy 1, policy_version 47490 (0.0010) -[2023-10-17 02:10:51,360][62408] Updated weights for policy 1, policy_version 47500 (0.0008) -[2023-10-17 02:10:51,735][62408] Updated weights for policy 1, policy_version 47510 (0.0008) -[2023-10-17 02:10:52,104][62408] Updated weights for policy 1, policy_version 47520 (0.0008) -[2023-10-17 02:10:52,214][61453] Fps is (10 sec: 16383.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 97681408. Throughput: 0: 1785.8, 1: 1765.7. Samples: 24420802. Policy #0 lag: (min: 9.0, avg: 24.1, max: 41.0) -[2023-10-17 02:10:52,215][61453] Avg episode reward: [(0, '8.860'), (1, '8.910')] -[2023-10-17 02:10:54,292][62373] Updated weights for policy 0, policy_version 47880 (0.0007) -[2023-10-17 02:10:54,662][62373] Updated weights for policy 0, policy_version 47890 (0.0007) -[2023-10-17 02:10:55,040][62373] Updated weights for policy 0, policy_version 47900 (0.0008) -[2023-10-17 02:10:56,001][62408] Updated weights for policy 1, policy_version 47530 (0.0009) -[2023-10-17 02:10:56,377][62408] Updated weights for policy 1, policy_version 47540 (0.0008) -[2023-10-17 02:10:56,736][62408] Updated weights for policy 1, policy_version 47550 (0.0008) -[2023-10-17 02:10:57,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 97746944. Throughput: 0: 1763.8, 1: 1776.7. Samples: 24441588. Policy #0 lag: (min: 9.0, avg: 24.1, max: 41.0) -[2023-10-17 02:10:57,215][61453] Avg episode reward: [(0, '8.400'), (1, '8.750')] -[2023-10-17 02:10:58,927][62373] Updated weights for policy 0, policy_version 47910 (0.0007) -[2023-10-17 02:10:59,303][62373] Updated weights for policy 0, policy_version 47920 (0.0008) -[2023-10-17 02:10:59,662][62373] Updated weights for policy 0, policy_version 47930 (0.0010) -[2023-10-17 02:11:00,759][62408] Updated weights for policy 1, policy_version 47560 (0.0008) -[2023-10-17 02:11:01,141][62408] Updated weights for policy 1, policy_version 47570 (0.0008) -[2023-10-17 02:11:01,519][62408] Updated weights for policy 1, policy_version 47580 (0.0008) -[2023-10-17 02:11:02,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 97812480. Throughput: 0: 1767.7, 1: 1748.7. Samples: 24462226. Policy #0 lag: (min: 31.0, avg: 34.6, max: 63.0) -[2023-10-17 02:11:02,215][61453] Avg episode reward: [(0, '8.940'), (1, '9.190')] -[2023-10-17 02:11:03,379][62373] Updated weights for policy 0, policy_version 47940 (0.0009) -[2023-10-17 02:11:03,748][62373] Updated weights for policy 0, policy_version 47950 (0.0009) -[2023-10-17 02:11:04,114][62373] Updated weights for policy 0, policy_version 47960 (0.0008) -[2023-10-17 02:11:05,089][62408] Updated weights for policy 1, policy_version 47590 (0.0008) -[2023-10-17 02:11:05,454][62408] Updated weights for policy 1, policy_version 47600 (0.0010) -[2023-10-17 02:11:05,825][62408] Updated weights for policy 1, policy_version 47610 (0.0010) -[2023-10-17 02:11:07,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 97878016. Throughput: 0: 1768.0, 1: 1780.2. Samples: 24473424. Policy #0 lag: (min: 31.0, avg: 34.6, max: 63.0) -[2023-10-17 02:11:07,215][61453] Avg episode reward: [(0, '9.060'), (1, '8.900')] -[2023-10-17 02:11:07,950][62373] Updated weights for policy 0, policy_version 47970 (0.0008) -[2023-10-17 02:11:08,321][62373] Updated weights for policy 0, policy_version 47980 (0.0010) -[2023-10-17 02:11:08,680][62373] Updated weights for policy 0, policy_version 47990 (0.0009) -[2023-10-17 02:11:09,046][62373] Updated weights for policy 0, policy_version 48000 (0.0010) -[2023-10-17 02:11:09,659][62408] Updated weights for policy 1, policy_version 47620 (0.0010) -[2023-10-17 02:11:10,028][62408] Updated weights for policy 1, policy_version 47630 (0.0012) -[2023-10-17 02:11:10,396][62408] Updated weights for policy 1, policy_version 47640 (0.0009) -[2023-10-17 02:11:12,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 97943552. Throughput: 0: 1772.1, 1: 1747.1. Samples: 24494086. Policy #0 lag: (min: 31.0, avg: 34.6, max: 63.0) -[2023-10-17 02:11:12,215][61453] Avg episode reward: [(0, '9.490'), (1, '7.770')] -[2023-10-17 02:11:12,954][62373] Updated weights for policy 0, policy_version 48010 (0.0010) -[2023-10-17 02:11:13,312][62373] Updated weights for policy 0, policy_version 48020 (0.0008) -[2023-10-17 02:11:13,684][62373] Updated weights for policy 0, policy_version 48030 (0.0009) -[2023-10-17 02:11:14,093][62408] Updated weights for policy 1, policy_version 47650 (0.0009) -[2023-10-17 02:11:14,472][62408] Updated weights for policy 1, policy_version 47660 (0.0009) -[2023-10-17 02:11:14,831][62408] Updated weights for policy 1, policy_version 47670 (0.0010) -[2023-10-17 02:11:15,197][62408] Updated weights for policy 1, policy_version 47680 (0.0010) -[2023-10-17 02:11:17,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 98009088. Throughput: 0: 1793.0, 1: 1747.7. Samples: 24516194. Policy #0 lag: (min: 31.0, avg: 34.6, max: 63.0) -[2023-10-17 02:11:17,215][61453] Avg episode reward: [(0, '9.020'), (1, '8.700')] -[2023-10-17 02:11:17,389][62373] Updated weights for policy 0, policy_version 48040 (0.0008) -[2023-10-17 02:11:17,762][62373] Updated weights for policy 0, policy_version 48050 (0.0007) -[2023-10-17 02:11:18,129][62373] Updated weights for policy 0, policy_version 48060 (0.0010) -[2023-10-17 02:11:19,199][62408] Updated weights for policy 1, policy_version 47690 (0.0007) -[2023-10-17 02:11:19,576][62408] Updated weights for policy 1, policy_version 47700 (0.0009) -[2023-10-17 02:11:19,950][62408] Updated weights for policy 1, policy_version 47710 (0.0007) -[2023-10-17 02:11:22,138][62373] Updated weights for policy 0, policy_version 48070 (0.0009) -[2023-10-17 02:11:22,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 98074624. Throughput: 0: 1770.2, 1: 1755.3. Samples: 24526022. Policy #0 lag: (min: 31.0, avg: 34.6, max: 63.0) -[2023-10-17 02:11:22,215][61453] Avg episode reward: [(0, '8.670'), (1, '8.550')] -[2023-10-17 02:11:22,494][62373] Updated weights for policy 0, policy_version 48080 (0.0007) -[2023-10-17 02:11:22,853][62373] Updated weights for policy 0, policy_version 48090 (0.0008) -[2023-10-17 02:11:23,740][62408] Updated weights for policy 1, policy_version 47720 (0.0008) -[2023-10-17 02:11:24,098][62408] Updated weights for policy 1, policy_version 47730 (0.0008) -[2023-10-17 02:11:24,443][62408] Updated weights for policy 1, policy_version 47740 (0.0008) -[2023-10-17 02:11:26,374][62373] Updated weights for policy 0, policy_version 48100 (0.0007) -[2023-10-17 02:11:26,736][62373] Updated weights for policy 0, policy_version 48110 (0.0009) -[2023-10-17 02:11:27,089][62373] Updated weights for policy 0, policy_version 48120 (0.0007) -[2023-10-17 02:11:27,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 98140160. Throughput: 0: 1798.4, 1: 1756.7. Samples: 24548632. Policy #0 lag: (min: 31.0, avg: 34.6, max: 63.0) -[2023-10-17 02:11:27,215][61453] Avg episode reward: [(0, '8.640'), (1, '8.400')] -[2023-10-17 02:11:28,227][62408] Updated weights for policy 1, policy_version 47750 (0.0010) -[2023-10-17 02:11:28,580][62408] Updated weights for policy 1, policy_version 47760 (0.0007) -[2023-10-17 02:11:28,941][62408] Updated weights for policy 1, policy_version 47770 (0.0007) -[2023-10-17 02:11:30,762][62373] Updated weights for policy 0, policy_version 48130 (0.0007) -[2023-10-17 02:11:31,132][62373] Updated weights for policy 0, policy_version 48140 (0.0008) -[2023-10-17 02:11:31,485][62373] Updated weights for policy 0, policy_version 48150 (0.0008) -[2023-10-17 02:11:31,844][62373] Updated weights for policy 0, policy_version 48160 (0.0008) -[2023-10-17 02:11:32,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14106.9). Total num frames: 98238464. Throughput: 0: 1789.4, 1: 1785.0. Samples: 24570316. Policy #0 lag: (min: 10.0, avg: 12.0, max: 37.0) -[2023-10-17 02:11:32,215][61453] Avg episode reward: [(0, '8.170'), (1, '8.720')] -[2023-10-17 02:11:32,223][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000048160_49315840.pth... -[2023-10-17 02:11:32,223][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000047776_48922624.pth... -[2023-10-17 02:11:32,261][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000046496_47611904.pth -[2023-10-17 02:11:32,262][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000046144_47251456.pth -[2023-10-17 02:11:32,645][62408] Updated weights for policy 1, policy_version 47780 (0.0007) -[2023-10-17 02:11:33,018][62408] Updated weights for policy 1, policy_version 47790 (0.0008) -[2023-10-17 02:11:33,374][62408] Updated weights for policy 1, policy_version 47800 (0.0008) -[2023-10-17 02:11:35,393][62373] Updated weights for policy 0, policy_version 48170 (0.0008) -[2023-10-17 02:11:35,761][62373] Updated weights for policy 0, policy_version 48180 (0.0009) -[2023-10-17 02:11:36,121][62373] Updated weights for policy 0, policy_version 48190 (0.0008) -[2023-10-17 02:11:37,207][62408] Updated weights for policy 1, policy_version 47810 (0.0008) -[2023-10-17 02:11:37,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 98304000. Throughput: 0: 1809.3, 1: 1767.1. Samples: 24581740. Policy #0 lag: (min: 10.0, avg: 12.0, max: 37.0) -[2023-10-17 02:11:37,214][61453] Avg episode reward: [(0, '8.110'), (1, '8.880')] -[2023-10-17 02:11:37,571][62408] Updated weights for policy 1, policy_version 47820 (0.0009) -[2023-10-17 02:11:37,944][62408] Updated weights for policy 1, policy_version 47830 (0.0007) -[2023-10-17 02:11:38,310][62408] Updated weights for policy 1, policy_version 47840 (0.0007) -[2023-10-17 02:11:39,933][62373] Updated weights for policy 0, policy_version 48200 (0.0008) -[2023-10-17 02:11:40,297][62373] Updated weights for policy 0, policy_version 48210 (0.0007) -[2023-10-17 02:11:40,670][62373] Updated weights for policy 0, policy_version 48220 (0.0008) -[2023-10-17 02:11:42,032][62408] Updated weights for policy 1, policy_version 47850 (0.0007) -[2023-10-17 02:11:42,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 98369536. Throughput: 0: 1797.8, 1: 1787.6. Samples: 24602930. Policy #0 lag: (min: 10.0, avg: 12.0, max: 37.0) -[2023-10-17 02:11:42,215][61453] Avg episode reward: [(0, '8.160'), (1, '9.730')] -[2023-10-17 02:11:42,407][62408] Updated weights for policy 1, policy_version 47860 (0.0011) -[2023-10-17 02:11:42,778][62408] Updated weights for policy 1, policy_version 47870 (0.0011) -[2023-10-17 02:11:44,323][62373] Updated weights for policy 0, policy_version 48230 (0.0008) -[2023-10-17 02:11:44,694][62373] Updated weights for policy 0, policy_version 48240 (0.0007) -[2023-10-17 02:11:45,063][62373] Updated weights for policy 0, policy_version 48250 (0.0008) -[2023-10-17 02:11:46,818][62408] Updated weights for policy 1, policy_version 47880 (0.0008) -[2023-10-17 02:11:47,204][62408] Updated weights for policy 1, policy_version 47890 (0.0007) -[2023-10-17 02:11:47,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 98435072. Throughput: 0: 1803.8, 1: 1807.5. Samples: 24624736. Policy #0 lag: (min: 10.0, avg: 12.0, max: 37.0) -[2023-10-17 02:11:47,214][61453] Avg episode reward: [(0, '8.390'), (1, '9.110')] -[2023-10-17 02:11:47,574][62408] Updated weights for policy 1, policy_version 47900 (0.0009) -[2023-10-17 02:11:48,745][62373] Updated weights for policy 0, policy_version 48260 (0.0009) -[2023-10-17 02:11:49,121][62373] Updated weights for policy 0, policy_version 48270 (0.0008) -[2023-10-17 02:11:49,494][62373] Updated weights for policy 0, policy_version 48280 (0.0009) -[2023-10-17 02:11:51,303][62408] Updated weights for policy 1, policy_version 47910 (0.0009) -[2023-10-17 02:11:51,674][62408] Updated weights for policy 1, policy_version 47920 (0.0008) -[2023-10-17 02:11:52,033][62408] Updated weights for policy 1, policy_version 47930 (0.0007) -[2023-10-17 02:11:52,214][61453] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 98500608. Throughput: 0: 1808.1, 1: 1780.9. Samples: 24634930. Policy #0 lag: (min: 10.0, avg: 12.0, max: 37.0) -[2023-10-17 02:11:52,215][61453] Avg episode reward: [(0, '8.770'), (1, '9.300')] -[2023-10-17 02:11:53,321][62373] Updated weights for policy 0, policy_version 48290 (0.0009) -[2023-10-17 02:11:53,689][62373] Updated weights for policy 0, policy_version 48300 (0.0007) -[2023-10-17 02:11:54,065][62373] Updated weights for policy 0, policy_version 48310 (0.0009) -[2023-10-17 02:11:54,430][62373] Updated weights for policy 0, policy_version 48320 (0.0008) -[2023-10-17 02:11:55,613][62408] Updated weights for policy 1, policy_version 47940 (0.0008) -[2023-10-17 02:11:55,981][62408] Updated weights for policy 1, policy_version 47950 (0.0008) -[2023-10-17 02:11:56,344][62408] Updated weights for policy 1, policy_version 47960 (0.0008) -[2023-10-17 02:11:57,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 98598912. Throughput: 0: 1804.0, 1: 1809.2. Samples: 24656682. Policy #0 lag: (min: 10.0, avg: 12.0, max: 37.0) -[2023-10-17 02:11:57,215][61453] Avg episode reward: [(0, '9.370'), (1, '9.110')] -[2023-10-17 02:11:58,237][62373] Updated weights for policy 0, policy_version 48330 (0.0009) -[2023-10-17 02:11:58,602][62373] Updated weights for policy 0, policy_version 48340 (0.0007) -[2023-10-17 02:11:58,973][62373] Updated weights for policy 0, policy_version 48350 (0.0008) -[2023-10-17 02:12:00,189][62408] Updated weights for policy 1, policy_version 47970 (0.0010) -[2023-10-17 02:12:00,562][62408] Updated weights for policy 1, policy_version 47980 (0.0008) -[2023-10-17 02:12:00,926][62408] Updated weights for policy 1, policy_version 47990 (0.0007) -[2023-10-17 02:12:01,287][62408] Updated weights for policy 1, policy_version 48000 (0.0007) -[2023-10-17 02:12:02,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 98664448. Throughput: 0: 1803.5, 1: 1787.8. Samples: 24677800. Policy #0 lag: (min: 10.0, avg: 12.0, max: 37.0) -[2023-10-17 02:12:02,214][61453] Avg episode reward: [(0, '9.410'), (1, '9.080')] -[2023-10-17 02:12:02,782][62373] Updated weights for policy 0, policy_version 48360 (0.0009) -[2023-10-17 02:12:03,154][62373] Updated weights for policy 0, policy_version 48370 (0.0009) -[2023-10-17 02:12:03,528][62373] Updated weights for policy 0, policy_version 48380 (0.0009) -[2023-10-17 02:12:05,112][62408] Updated weights for policy 1, policy_version 48010 (0.0009) -[2023-10-17 02:12:05,487][62408] Updated weights for policy 1, policy_version 48020 (0.0008) -[2023-10-17 02:12:05,850][62408] Updated weights for policy 1, policy_version 48030 (0.0007) -[2023-10-17 02:12:07,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 98729984. Throughput: 0: 1803.0, 1: 1811.3. Samples: 24688666. Policy #0 lag: (min: 31.0, avg: 48.8, max: 63.0) -[2023-10-17 02:12:07,215][61453] Avg episode reward: [(0, '9.160'), (1, '8.260')] -[2023-10-17 02:12:07,298][62373] Updated weights for policy 0, policy_version 48390 (0.0010) -[2023-10-17 02:12:07,683][62373] Updated weights for policy 0, policy_version 48400 (0.0010) -[2023-10-17 02:12:08,050][62373] Updated weights for policy 0, policy_version 48410 (0.0010) -[2023-10-17 02:12:09,507][62408] Updated weights for policy 1, policy_version 48040 (0.0009) -[2023-10-17 02:12:09,876][62408] Updated weights for policy 1, policy_version 48050 (0.0008) -[2023-10-17 02:12:10,232][62408] Updated weights for policy 1, policy_version 48060 (0.0007) -[2023-10-17 02:12:11,880][62373] Updated weights for policy 0, policy_version 48420 (0.0007) -[2023-10-17 02:12:12,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 98795520. Throughput: 0: 1788.4, 1: 1784.0. Samples: 24709392. Policy #0 lag: (min: 31.0, avg: 48.8, max: 63.0) -[2023-10-17 02:12:12,215][61453] Avg episode reward: [(0, '8.940'), (1, '9.090')] -[2023-10-17 02:12:12,236][62373] Updated weights for policy 0, policy_version 48430 (0.0009) -[2023-10-17 02:12:12,604][62373] Updated weights for policy 0, policy_version 48440 (0.0009) -[2023-10-17 02:12:14,034][62408] Updated weights for policy 1, policy_version 48070 (0.0008) -[2023-10-17 02:12:14,397][62408] Updated weights for policy 1, policy_version 48080 (0.0009) -[2023-10-17 02:12:14,769][62408] Updated weights for policy 1, policy_version 48090 (0.0010) -[2023-10-17 02:12:16,319][62373] Updated weights for policy 0, policy_version 48450 (0.0008) -[2023-10-17 02:12:16,679][62373] Updated weights for policy 0, policy_version 48460 (0.0007) -[2023-10-17 02:12:17,057][62373] Updated weights for policy 0, policy_version 48470 (0.0007) -[2023-10-17 02:12:17,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 98861056. Throughput: 0: 1799.5, 1: 1770.4. Samples: 24730962. Policy #0 lag: (min: 31.0, avg: 48.8, max: 63.0) -[2023-10-17 02:12:17,216][61453] Avg episode reward: [(0, '8.510'), (1, '8.720')] -[2023-10-17 02:12:17,423][62373] Updated weights for policy 0, policy_version 48480 (0.0009) -[2023-10-17 02:12:18,677][62408] Updated weights for policy 1, policy_version 48100 (0.0009) -[2023-10-17 02:12:19,058][62408] Updated weights for policy 1, policy_version 48110 (0.0009) -[2023-10-17 02:12:19,422][62408] Updated weights for policy 1, policy_version 48120 (0.0010) -[2023-10-17 02:12:21,237][62373] Updated weights for policy 0, policy_version 48490 (0.0010) -[2023-10-17 02:12:21,609][62373] Updated weights for policy 0, policy_version 48500 (0.0010) -[2023-10-17 02:12:21,976][62373] Updated weights for policy 0, policy_version 48510 (0.0010) -[2023-10-17 02:12:22,214][61453] Fps is (10 sec: 16384.3, 60 sec: 14745.7, 300 sec: 14218.0). Total num frames: 98959360. Throughput: 0: 1776.0, 1: 1771.1. Samples: 24741360. Policy #0 lag: (min: 31.0, avg: 48.8, max: 63.0) -[2023-10-17 02:12:22,214][61453] Avg episode reward: [(0, '8.220'), (1, '8.670')] -[2023-10-17 02:12:23,171][62408] Updated weights for policy 1, policy_version 48130 (0.0008) -[2023-10-17 02:12:23,537][62408] Updated weights for policy 1, policy_version 48140 (0.0008) -[2023-10-17 02:12:23,914][62408] Updated weights for policy 1, policy_version 48150 (0.0008) -[2023-10-17 02:12:24,277][62408] Updated weights for policy 1, policy_version 48160 (0.0008) -[2023-10-17 02:12:25,856][62373] Updated weights for policy 0, policy_version 48520 (0.0008) -[2023-10-17 02:12:26,227][62373] Updated weights for policy 0, policy_version 48530 (0.0008) -[2023-10-17 02:12:26,597][62373] Updated weights for policy 0, policy_version 48540 (0.0009) -[2023-10-17 02:12:27,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14745.5, 300 sec: 14106.9). Total num frames: 99024896. Throughput: 0: 1796.9, 1: 1764.3. Samples: 24763184. Policy #0 lag: (min: 31.0, avg: 48.8, max: 63.0) -[2023-10-17 02:12:27,215][61453] Avg episode reward: [(0, '8.190'), (1, '8.530')] -[2023-10-17 02:12:28,051][62408] Updated weights for policy 1, policy_version 48170 (0.0008) -[2023-10-17 02:12:28,424][62408] Updated weights for policy 1, policy_version 48180 (0.0007) -[2023-10-17 02:12:28,793][62408] Updated weights for policy 1, policy_version 48190 (0.0007) -[2023-10-17 02:12:30,485][62373] Updated weights for policy 0, policy_version 48550 (0.0009) -[2023-10-17 02:12:30,858][62373] Updated weights for policy 0, policy_version 48560 (0.0010) -[2023-10-17 02:12:31,237][62373] Updated weights for policy 0, policy_version 48570 (0.0010) -[2023-10-17 02:12:32,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 99090432. Throughput: 0: 1764.1, 1: 1778.6. Samples: 24784156. Policy #0 lag: (min: 31.0, avg: 48.8, max: 63.0) -[2023-10-17 02:12:32,215][61453] Avg episode reward: [(0, '8.370'), (1, '8.640')] -[2023-10-17 02:12:32,708][62408] Updated weights for policy 1, policy_version 48200 (0.0007) -[2023-10-17 02:12:33,084][62408] Updated weights for policy 1, policy_version 48210 (0.0009) -[2023-10-17 02:12:33,447][62408] Updated weights for policy 1, policy_version 48220 (0.0011) -[2023-10-17 02:12:34,897][62373] Updated weights for policy 0, policy_version 48580 (0.0008) -[2023-10-17 02:12:35,265][62373] Updated weights for policy 0, policy_version 48590 (0.0008) -[2023-10-17 02:12:35,630][62373] Updated weights for policy 0, policy_version 48600 (0.0008) -[2023-10-17 02:12:37,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 99155968. Throughput: 0: 1789.3, 1: 1763.6. Samples: 24794812. Policy #0 lag: (min: 26.0, avg: 34.3, max: 58.0) -[2023-10-17 02:12:37,215][61453] Avg episode reward: [(0, '8.430'), (1, '8.540')] -[2023-10-17 02:12:37,358][62408] Updated weights for policy 1, policy_version 48230 (0.0010) -[2023-10-17 02:12:37,726][62408] Updated weights for policy 1, policy_version 48240 (0.0009) -[2023-10-17 02:12:38,092][62408] Updated weights for policy 1, policy_version 48250 (0.0010) -[2023-10-17 02:12:39,465][62373] Updated weights for policy 0, policy_version 48610 (0.0007) -[2023-10-17 02:12:39,833][62373] Updated weights for policy 0, policy_version 48620 (0.0007) -[2023-10-17 02:12:40,197][62373] Updated weights for policy 0, policy_version 48630 (0.0009) -[2023-10-17 02:12:40,561][62373] Updated weights for policy 0, policy_version 48640 (0.0010) -[2023-10-17 02:12:41,890][62408] Updated weights for policy 1, policy_version 48260 (0.0010) -[2023-10-17 02:12:42,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 99221504. Throughput: 0: 1765.4, 1: 1770.1. Samples: 24815780. Policy #0 lag: (min: 26.0, avg: 34.3, max: 58.0) -[2023-10-17 02:12:42,215][61453] Avg episode reward: [(0, '8.460'), (1, '8.440')] -[2023-10-17 02:12:42,256][62408] Updated weights for policy 1, policy_version 48270 (0.0008) -[2023-10-17 02:12:42,625][62408] Updated weights for policy 1, policy_version 48280 (0.0008) -[2023-10-17 02:12:44,240][62373] Updated weights for policy 0, policy_version 48650 (0.0008) -[2023-10-17 02:12:44,617][62373] Updated weights for policy 0, policy_version 48660 (0.0009) -[2023-10-17 02:12:44,988][62373] Updated weights for policy 0, policy_version 48670 (0.0010) -[2023-10-17 02:12:46,353][62408] Updated weights for policy 1, policy_version 48290 (0.0008) -[2023-10-17 02:12:46,727][62408] Updated weights for policy 1, policy_version 48300 (0.0008) -[2023-10-17 02:12:47,105][62408] Updated weights for policy 1, policy_version 48310 (0.0011) -[2023-10-17 02:12:47,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 99287040. Throughput: 0: 1769.6, 1: 1778.5. Samples: 24837462. Policy #0 lag: (min: 26.0, avg: 34.3, max: 58.0) -[2023-10-17 02:12:47,215][61453] Avg episode reward: [(0, '8.610'), (1, '8.270')] -[2023-10-17 02:12:47,472][62408] Updated weights for policy 1, policy_version 48320 (0.0007) -[2023-10-17 02:12:48,821][62373] Updated weights for policy 0, policy_version 48680 (0.0010) -[2023-10-17 02:12:49,199][62373] Updated weights for policy 0, policy_version 48690 (0.0007) -[2023-10-17 02:12:49,574][62373] Updated weights for policy 0, policy_version 48700 (0.0008) -[2023-10-17 02:12:51,245][62408] Updated weights for policy 1, policy_version 48330 (0.0007) -[2023-10-17 02:12:51,605][62408] Updated weights for policy 1, policy_version 48340 (0.0008) -[2023-10-17 02:12:51,966][62408] Updated weights for policy 1, policy_version 48350 (0.0010) -[2023-10-17 02:12:52,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14218.0). Total num frames: 99385344. Throughput: 0: 1766.8, 1: 1766.4. Samples: 24847656. Policy #0 lag: (min: 26.0, avg: 34.3, max: 58.0) -[2023-10-17 02:12:52,214][61453] Avg episode reward: [(0, '9.600'), (1, '8.360')] -[2023-10-17 02:12:53,465][62373] Updated weights for policy 0, policy_version 48710 (0.0010) -[2023-10-17 02:12:53,855][62373] Updated weights for policy 0, policy_version 48720 (0.0009) -[2023-10-17 02:12:54,226][62373] Updated weights for policy 0, policy_version 48730 (0.0009) -[2023-10-17 02:12:55,884][62408] Updated weights for policy 1, policy_version 48360 (0.0009) -[2023-10-17 02:12:56,245][62408] Updated weights for policy 1, policy_version 48370 (0.0008) -[2023-10-17 02:12:56,615][62408] Updated weights for policy 1, policy_version 48380 (0.0007) -[2023-10-17 02:12:57,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 99450880. Throughput: 0: 1771.6, 1: 1785.5. Samples: 24869460. Policy #0 lag: (min: 26.0, avg: 34.3, max: 58.0) -[2023-10-17 02:12:57,215][61453] Avg episode reward: [(0, '9.410'), (1, '8.690')] -[2023-10-17 02:12:58,037][62373] Updated weights for policy 0, policy_version 48740 (0.0008) -[2023-10-17 02:12:58,409][62373] Updated weights for policy 0, policy_version 48750 (0.0008) -[2023-10-17 02:12:58,780][62373] Updated weights for policy 0, policy_version 48760 (0.0008) -[2023-10-17 02:13:00,352][62408] Updated weights for policy 1, policy_version 48390 (0.0009) -[2023-10-17 02:13:00,728][62408] Updated weights for policy 1, policy_version 48400 (0.0010) -[2023-10-17 02:13:01,096][62408] Updated weights for policy 1, policy_version 48410 (0.0009) -[2023-10-17 02:13:02,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 99516416. Throughput: 0: 1784.5, 1: 1762.0. Samples: 24890554. Policy #0 lag: (min: 26.0, avg: 34.3, max: 58.0) -[2023-10-17 02:13:02,214][61453] Avg episode reward: [(0, '9.140'), (1, '8.700')] -[2023-10-17 02:13:02,680][62373] Updated weights for policy 0, policy_version 48770 (0.0007) -[2023-10-17 02:13:03,055][62373] Updated weights for policy 0, policy_version 48780 (0.0008) -[2023-10-17 02:13:03,425][62373] Updated weights for policy 0, policy_version 48790 (0.0008) -[2023-10-17 02:13:03,798][62373] Updated weights for policy 0, policy_version 48800 (0.0007) -[2023-10-17 02:13:04,810][62408] Updated weights for policy 1, policy_version 48420 (0.0011) -[2023-10-17 02:13:05,181][62408] Updated weights for policy 1, policy_version 48430 (0.0010) -[2023-10-17 02:13:05,543][62408] Updated weights for policy 1, policy_version 48440 (0.0011) -[2023-10-17 02:13:07,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 99581952. Throughput: 0: 1769.2, 1: 1790.7. Samples: 24901558. Policy #0 lag: (min: 26.0, avg: 34.3, max: 58.0) -[2023-10-17 02:13:07,215][61453] Avg episode reward: [(0, '8.430'), (1, '8.990')] -[2023-10-17 02:13:07,531][62373] Updated weights for policy 0, policy_version 48810 (0.0008) -[2023-10-17 02:13:07,901][62373] Updated weights for policy 0, policy_version 48820 (0.0007) -[2023-10-17 02:13:08,279][62373] Updated weights for policy 0, policy_version 48830 (0.0007) -[2023-10-17 02:13:09,349][62408] Updated weights for policy 1, policy_version 48450 (0.0010) -[2023-10-17 02:13:09,717][62408] Updated weights for policy 1, policy_version 48460 (0.0008) -[2023-10-17 02:13:10,087][62408] Updated weights for policy 1, policy_version 48470 (0.0008) -[2023-10-17 02:13:10,463][62408] Updated weights for policy 1, policy_version 48480 (0.0008) -[2023-10-17 02:13:11,940][62373] Updated weights for policy 0, policy_version 48840 (0.0008) -[2023-10-17 02:13:12,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 99647488. Throughput: 0: 1784.5, 1: 1760.0. Samples: 24922688. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:13:12,215][61453] Avg episode reward: [(0, '8.950'), (1, '8.640')] -[2023-10-17 02:13:12,316][62373] Updated weights for policy 0, policy_version 48850 (0.0007) -[2023-10-17 02:13:12,695][62373] Updated weights for policy 0, policy_version 48860 (0.0008) -[2023-10-17 02:13:14,429][62408] Updated weights for policy 1, policy_version 48490 (0.0007) -[2023-10-17 02:13:14,806][62408] Updated weights for policy 1, policy_version 48500 (0.0008) -[2023-10-17 02:13:15,175][62408] Updated weights for policy 1, policy_version 48510 (0.0007) -[2023-10-17 02:13:16,584][62373] Updated weights for policy 0, policy_version 48870 (0.0007) -[2023-10-17 02:13:16,954][62373] Updated weights for policy 0, policy_version 48880 (0.0008) -[2023-10-17 02:13:17,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 99713024. Throughput: 0: 1794.5, 1: 1756.9. Samples: 24943968. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:13:17,215][61453] Avg episode reward: [(0, '8.770'), (1, '9.040')] -[2023-10-17 02:13:17,314][62373] Updated weights for policy 0, policy_version 48890 (0.0008) -[2023-10-17 02:13:18,968][62408] Updated weights for policy 1, policy_version 48520 (0.0007) -[2023-10-17 02:13:19,345][62408] Updated weights for policy 1, policy_version 48530 (0.0008) -[2023-10-17 02:13:19,712][62408] Updated weights for policy 1, policy_version 48540 (0.0009) -[2023-10-17 02:13:21,155][62373] Updated weights for policy 0, policy_version 48900 (0.0007) -[2023-10-17 02:13:21,531][62373] Updated weights for policy 0, policy_version 48910 (0.0009) -[2023-10-17 02:13:21,905][62373] Updated weights for policy 0, policy_version 48920 (0.0007) -[2023-10-17 02:13:22,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 99811328. Throughput: 0: 1780.6, 1: 1766.7. Samples: 24954440. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:13:22,215][61453] Avg episode reward: [(0, '8.850'), (1, '9.280')] -[2023-10-17 02:13:23,443][62408] Updated weights for policy 1, policy_version 48550 (0.0008) -[2023-10-17 02:13:23,804][62408] Updated weights for policy 1, policy_version 48560 (0.0009) -[2023-10-17 02:13:24,173][62408] Updated weights for policy 1, policy_version 48570 (0.0009) -[2023-10-17 02:13:25,691][62373] Updated weights for policy 0, policy_version 48930 (0.0009) -[2023-10-17 02:13:26,065][62373] Updated weights for policy 0, policy_version 48940 (0.0010) -[2023-10-17 02:13:26,441][62373] Updated weights for policy 0, policy_version 48950 (0.0011) -[2023-10-17 02:13:26,799][62373] Updated weights for policy 0, policy_version 48960 (0.0010) -[2023-10-17 02:13:27,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 99876864. Throughput: 0: 1795.6, 1: 1769.1. Samples: 24976188. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:13:27,215][61453] Avg episode reward: [(0, '8.500'), (1, '9.790')] -[2023-10-17 02:13:27,846][62408] Updated weights for policy 1, policy_version 48580 (0.0008) -[2023-10-17 02:13:28,229][62408] Updated weights for policy 1, policy_version 48590 (0.0007) -[2023-10-17 02:13:28,590][62408] Updated weights for policy 1, policy_version 48600 (0.0010) -[2023-10-17 02:13:30,630][62373] Updated weights for policy 0, policy_version 48970 (0.0008) -[2023-10-17 02:13:30,995][62373] Updated weights for policy 0, policy_version 48980 (0.0008) -[2023-10-17 02:13:31,368][62373] Updated weights for policy 0, policy_version 48990 (0.0009) -[2023-10-17 02:13:32,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 99942400. Throughput: 0: 1769.2, 1: 1775.9. Samples: 24996990. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:13:32,214][61453] Avg episode reward: [(0, '8.670'), (1, '9.430')] -[2023-10-17 02:13:32,223][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000048992_50167808.pth... -[2023-10-17 02:13:32,224][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000048608_49774592.pth... -[2023-10-17 02:13:32,254][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000047328_48463872.pth -[2023-10-17 02:13:32,262][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000046976_48103424.pth -[2023-10-17 02:13:32,506][62408] Updated weights for policy 1, policy_version 48610 (0.0010) -[2023-10-17 02:13:32,873][62408] Updated weights for policy 1, policy_version 48620 (0.0010) -[2023-10-17 02:13:33,237][62408] Updated weights for policy 1, policy_version 48630 (0.0009) -[2023-10-17 02:13:33,607][62408] Updated weights for policy 1, policy_version 48640 (0.0008) -[2023-10-17 02:13:35,046][62373] Updated weights for policy 0, policy_version 49000 (0.0009) -[2023-10-17 02:13:35,415][62373] Updated weights for policy 0, policy_version 49010 (0.0010) -[2023-10-17 02:13:35,789][62373] Updated weights for policy 0, policy_version 49020 (0.0010) -[2023-10-17 02:13:37,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 100007936. Throughput: 0: 1801.3, 1: 1761.3. Samples: 25007972. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:13:37,215][61453] Avg episode reward: [(0, '9.300'), (1, '9.330')] -[2023-10-17 02:13:37,387][62408] Updated weights for policy 1, policy_version 48650 (0.0008) -[2023-10-17 02:13:37,758][62408] Updated weights for policy 1, policy_version 48660 (0.0007) -[2023-10-17 02:13:38,121][62408] Updated weights for policy 1, policy_version 48670 (0.0008) -[2023-10-17 02:13:39,636][62373] Updated weights for policy 0, policy_version 49030 (0.0009) -[2023-10-17 02:13:40,008][62373] Updated weights for policy 0, policy_version 49040 (0.0008) -[2023-10-17 02:13:40,366][62373] Updated weights for policy 0, policy_version 49050 (0.0007) -[2023-10-17 02:13:41,982][62408] Updated weights for policy 1, policy_version 48680 (0.0009) -[2023-10-17 02:13:42,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 100073472. Throughput: 0: 1774.1, 1: 1769.5. Samples: 25028920. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-17 02:13:42,215][61453] Avg episode reward: [(0, '9.600'), (1, '9.180')] -[2023-10-17 02:13:42,353][62408] Updated weights for policy 1, policy_version 48690 (0.0009) -[2023-10-17 02:13:42,718][62408] Updated weights for policy 1, policy_version 48700 (0.0007) -[2023-10-17 02:13:44,017][62373] Updated weights for policy 0, policy_version 49060 (0.0011) -[2023-10-17 02:13:44,400][62373] Updated weights for policy 0, policy_version 49070 (0.0009) -[2023-10-17 02:13:44,778][62373] Updated weights for policy 0, policy_version 49080 (0.0007) -[2023-10-17 02:13:46,543][62408] Updated weights for policy 1, policy_version 48710 (0.0007) -[2023-10-17 02:13:46,903][62408] Updated weights for policy 1, policy_version 48720 (0.0009) -[2023-10-17 02:13:47,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 100139008. Throughput: 0: 1778.1, 1: 1778.3. Samples: 25050592. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-17 02:13:47,215][61453] Avg episode reward: [(0, '9.670'), (1, '8.530')] -[2023-10-17 02:13:47,276][62408] Updated weights for policy 1, policy_version 48730 (0.0008) -[2023-10-17 02:13:48,422][62373] Updated weights for policy 0, policy_version 49090 (0.0008) -[2023-10-17 02:13:48,802][62373] Updated weights for policy 0, policy_version 49100 (0.0010) -[2023-10-17 02:13:49,161][62373] Updated weights for policy 0, policy_version 49110 (0.0008) -[2023-10-17 02:13:49,530][62373] Updated weights for policy 0, policy_version 49120 (0.0007) -[2023-10-17 02:13:51,026][62408] Updated weights for policy 1, policy_version 48740 (0.0009) -[2023-10-17 02:13:51,393][62408] Updated weights for policy 1, policy_version 48750 (0.0011) -[2023-10-17 02:13:51,762][62408] Updated weights for policy 1, policy_version 48760 (0.0010) -[2023-10-17 02:13:52,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 100237312. Throughput: 0: 1773.4, 1: 1765.1. Samples: 25060792. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-17 02:13:52,215][61453] Avg episode reward: [(0, '8.710'), (1, '9.260')] -[2023-10-17 02:13:53,281][62373] Updated weights for policy 0, policy_version 49130 (0.0008) -[2023-10-17 02:13:53,657][62373] Updated weights for policy 0, policy_version 49140 (0.0009) -[2023-10-17 02:13:54,030][62373] Updated weights for policy 0, policy_version 49150 (0.0008) -[2023-10-17 02:13:55,738][62408] Updated weights for policy 1, policy_version 48770 (0.0010) -[2023-10-17 02:13:56,114][62408] Updated weights for policy 1, policy_version 48780 (0.0010) -[2023-10-17 02:13:56,478][62408] Updated weights for policy 1, policy_version 48790 (0.0010) -[2023-10-17 02:13:56,845][62408] Updated weights for policy 1, policy_version 48800 (0.0009) -[2023-10-17 02:13:57,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 100302848. Throughput: 0: 1763.7, 1: 1785.6. Samples: 25082408. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-17 02:13:57,215][61453] Avg episode reward: [(0, '8.580'), (1, '9.090')] -[2023-10-17 02:13:57,941][62373] Updated weights for policy 0, policy_version 49160 (0.0010) -[2023-10-17 02:13:58,297][62373] Updated weights for policy 0, policy_version 49170 (0.0010) -[2023-10-17 02:13:58,665][62373] Updated weights for policy 0, policy_version 49180 (0.0009) -[2023-10-17 02:14:00,576][62408] Updated weights for policy 1, policy_version 48810 (0.0009) -[2023-10-17 02:14:00,957][62408] Updated weights for policy 1, policy_version 48820 (0.0008) -[2023-10-17 02:14:01,326][62408] Updated weights for policy 1, policy_version 48830 (0.0010) -[2023-10-17 02:14:02,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 100368384. Throughput: 0: 1776.2, 1: 1765.1. Samples: 25103328. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-17 02:14:02,214][61453] Avg episode reward: [(0, '8.990'), (1, '9.190')] -[2023-10-17 02:14:02,574][62373] Updated weights for policy 0, policy_version 49190 (0.0008) -[2023-10-17 02:14:02,947][62373] Updated weights for policy 0, policy_version 49200 (0.0010) -[2023-10-17 02:14:03,319][62373] Updated weights for policy 0, policy_version 49210 (0.0009) -[2023-10-17 02:14:05,176][62408] Updated weights for policy 1, policy_version 48840 (0.0011) -[2023-10-17 02:14:05,551][62408] Updated weights for policy 1, policy_version 48850 (0.0010) -[2023-10-17 02:14:05,914][62408] Updated weights for policy 1, policy_version 48860 (0.0008) -[2023-10-17 02:14:07,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 100433920. Throughput: 0: 1762.1, 1: 1791.7. Samples: 25114356. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-17 02:14:07,215][61453] Avg episode reward: [(0, '8.360'), (1, '9.380')] -[2023-10-17 02:14:07,245][62373] Updated weights for policy 0, policy_version 49220 (0.0007) -[2023-10-17 02:14:07,618][62373] Updated weights for policy 0, policy_version 49230 (0.0007) -[2023-10-17 02:14:07,982][62373] Updated weights for policy 0, policy_version 49240 (0.0007) -[2023-10-17 02:14:09,909][62408] Updated weights for policy 1, policy_version 48870 (0.0008) -[2023-10-17 02:14:10,274][62408] Updated weights for policy 1, policy_version 48880 (0.0007) -[2023-10-17 02:14:10,639][62408] Updated weights for policy 1, policy_version 48890 (0.0008) -[2023-10-17 02:14:11,681][62373] Updated weights for policy 0, policy_version 49250 (0.0010) -[2023-10-17 02:14:12,048][62373] Updated weights for policy 0, policy_version 49260 (0.0010) -[2023-10-17 02:14:12,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 100499456. Throughput: 0: 1769.7, 1: 1755.4. Samples: 25134814. Policy #0 lag: (min: 27.0, avg: 27.0, max: 27.0) -[2023-10-17 02:14:12,215][61453] Avg episode reward: [(0, '8.650'), (1, '9.090')] -[2023-10-17 02:14:12,418][62373] Updated weights for policy 0, policy_version 49270 (0.0009) -[2023-10-17 02:14:12,790][62373] Updated weights for policy 0, policy_version 49280 (0.0008) -[2023-10-17 02:14:14,392][62408] Updated weights for policy 1, policy_version 48900 (0.0009) -[2023-10-17 02:14:14,771][62408] Updated weights for policy 1, policy_version 48910 (0.0007) -[2023-10-17 02:14:15,143][62408] Updated weights for policy 1, policy_version 48920 (0.0007) -[2023-10-17 02:14:16,490][62373] Updated weights for policy 0, policy_version 49290 (0.0008) -[2023-10-17 02:14:16,850][62373] Updated weights for policy 0, policy_version 49300 (0.0011) -[2023-10-17 02:14:17,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 100564992. Throughput: 0: 1776.7, 1: 1756.9. Samples: 25156006. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-17 02:14:17,215][61453] Avg episode reward: [(0, '8.270'), (1, '9.490')] -[2023-10-17 02:14:17,229][62373] Updated weights for policy 0, policy_version 49310 (0.0011) -[2023-10-17 02:14:18,994][62408] Updated weights for policy 1, policy_version 48930 (0.0008) -[2023-10-17 02:14:19,370][62408] Updated weights for policy 1, policy_version 48940 (0.0008) -[2023-10-17 02:14:19,742][62408] Updated weights for policy 1, policy_version 48950 (0.0009) -[2023-10-17 02:14:20,102][62408] Updated weights for policy 1, policy_version 48960 (0.0008) -[2023-10-17 02:14:21,093][62373] Updated weights for policy 0, policy_version 49320 (0.0010) -[2023-10-17 02:14:21,462][62373] Updated weights for policy 0, policy_version 49330 (0.0008) -[2023-10-17 02:14:21,842][62373] Updated weights for policy 0, policy_version 49340 (0.0009) -[2023-10-17 02:14:22,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 100663296. Throughput: 0: 1770.8, 1: 1767.5. Samples: 25167192. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-17 02:14:22,214][61453] Avg episode reward: [(0, '8.900'), (1, '10.540')] -[2023-10-17 02:14:22,215][62252] Saving new best policy, reward=10.540! -[2023-10-17 02:14:23,955][62408] Updated weights for policy 1, policy_version 48970 (0.0010) -[2023-10-17 02:14:24,326][62408] Updated weights for policy 1, policy_version 48980 (0.0010) -[2023-10-17 02:14:24,708][62408] Updated weights for policy 1, policy_version 48990 (0.0009) -[2023-10-17 02:14:25,610][62373] Updated weights for policy 0, policy_version 49350 (0.0007) -[2023-10-17 02:14:25,979][62373] Updated weights for policy 0, policy_version 49360 (0.0008) -[2023-10-17 02:14:26,352][62373] Updated weights for policy 0, policy_version 49370 (0.0007) -[2023-10-17 02:14:27,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 100728832. Throughput: 0: 1783.5, 1: 1757.8. Samples: 25188276. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-17 02:14:27,215][61453] Avg episode reward: [(0, '9.830'), (1, '9.520')] -[2023-10-17 02:14:28,405][62408] Updated weights for policy 1, policy_version 49000 (0.0009) -[2023-10-17 02:14:28,776][62408] Updated weights for policy 1, policy_version 49010 (0.0007) -[2023-10-17 02:14:29,142][62408] Updated weights for policy 1, policy_version 49020 (0.0008) -[2023-10-17 02:14:30,153][62373] Updated weights for policy 0, policy_version 49380 (0.0009) -[2023-10-17 02:14:30,538][62373] Updated weights for policy 0, policy_version 49390 (0.0008) -[2023-10-17 02:14:30,904][62373] Updated weights for policy 0, policy_version 49400 (0.0008) -[2023-10-17 02:14:32,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 100794368. Throughput: 0: 1759.2, 1: 1771.1. Samples: 25209454. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-17 02:14:32,215][61453] Avg episode reward: [(0, '9.640'), (1, '9.270')] -[2023-10-17 02:14:32,983][62408] Updated weights for policy 1, policy_version 49030 (0.0007) -[2023-10-17 02:14:33,340][62408] Updated weights for policy 1, policy_version 49040 (0.0007) -[2023-10-17 02:14:33,712][62408] Updated weights for policy 1, policy_version 49050 (0.0010) -[2023-10-17 02:14:34,581][62373] Updated weights for policy 0, policy_version 49410 (0.0007) -[2023-10-17 02:14:34,954][62373] Updated weights for policy 0, policy_version 49420 (0.0007) -[2023-10-17 02:14:35,324][62373] Updated weights for policy 0, policy_version 49430 (0.0007) -[2023-10-17 02:14:35,691][62373] Updated weights for policy 0, policy_version 49440 (0.0010) -[2023-10-17 02:14:37,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 100859904. Throughput: 0: 1784.4, 1: 1755.3. Samples: 25220078. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-17 02:14:37,215][61453] Avg episode reward: [(0, '9.960'), (1, '9.490')] -[2023-10-17 02:14:37,581][62408] Updated weights for policy 1, policy_version 49060 (0.0009) -[2023-10-17 02:14:37,953][62408] Updated weights for policy 1, policy_version 49070 (0.0008) -[2023-10-17 02:14:38,319][62408] Updated weights for policy 1, policy_version 49080 (0.0007) -[2023-10-17 02:14:39,613][62373] Updated weights for policy 0, policy_version 49450 (0.0007) -[2023-10-17 02:14:39,984][62373] Updated weights for policy 0, policy_version 49460 (0.0009) -[2023-10-17 02:14:40,353][62373] Updated weights for policy 0, policy_version 49470 (0.0010) -[2023-10-17 02:14:42,045][62408] Updated weights for policy 1, policy_version 49090 (0.0008) -[2023-10-17 02:14:42,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 100925440. Throughput: 0: 1763.4, 1: 1758.3. Samples: 25240884. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-17 02:14:42,214][61453] Avg episode reward: [(0, '9.770'), (1, '9.190')] -[2023-10-17 02:14:42,425][62408] Updated weights for policy 1, policy_version 49100 (0.0009) -[2023-10-17 02:14:42,788][62408] Updated weights for policy 1, policy_version 49110 (0.0008) -[2023-10-17 02:14:43,154][62408] Updated weights for policy 1, policy_version 49120 (0.0008) -[2023-10-17 02:14:44,056][62373] Updated weights for policy 0, policy_version 49480 (0.0008) -[2023-10-17 02:14:44,425][62373] Updated weights for policy 0, policy_version 49490 (0.0007) -[2023-10-17 02:14:44,802][62373] Updated weights for policy 0, policy_version 49500 (0.0007) -[2023-10-17 02:14:46,970][62408] Updated weights for policy 1, policy_version 49130 (0.0010) -[2023-10-17 02:14:47,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 100990976. Throughput: 0: 1768.4, 1: 1774.8. Samples: 25262768. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:14:47,214][61453] Avg episode reward: [(0, '9.800'), (1, '9.900')] -[2023-10-17 02:14:47,337][62408] Updated weights for policy 1, policy_version 49140 (0.0008) -[2023-10-17 02:14:47,701][62408] Updated weights for policy 1, policy_version 49150 (0.0007) -[2023-10-17 02:14:48,595][62373] Updated weights for policy 0, policy_version 49510 (0.0007) -[2023-10-17 02:14:48,957][62373] Updated weights for policy 0, policy_version 49520 (0.0009) -[2023-10-17 02:14:49,319][62373] Updated weights for policy 0, policy_version 49530 (0.0007) -[2023-10-17 02:14:51,683][62408] Updated weights for policy 1, policy_version 49160 (0.0008) -[2023-10-17 02:14:52,065][62408] Updated weights for policy 1, policy_version 49170 (0.0007) -[2023-10-17 02:14:52,214][61453] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 101056512. Throughput: 0: 1767.5, 1: 1748.3. Samples: 25272568. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:14:52,215][61453] Avg episode reward: [(0, '9.610'), (1, '9.490')] -[2023-10-17 02:14:52,425][62408] Updated weights for policy 1, policy_version 49180 (0.0007) -[2023-10-17 02:14:53,101][62373] Updated weights for policy 0, policy_version 49540 (0.0008) -[2023-10-17 02:14:53,460][62373] Updated weights for policy 0, policy_version 49550 (0.0011) -[2023-10-17 02:14:53,830][62373] Updated weights for policy 0, policy_version 49560 (0.0009) -[2023-10-17 02:14:56,222][62408] Updated weights for policy 1, policy_version 49190 (0.0009) -[2023-10-17 02:14:56,586][62408] Updated weights for policy 1, policy_version 49200 (0.0008) -[2023-10-17 02:14:56,948][62408] Updated weights for policy 1, policy_version 49210 (0.0007) -[2023-10-17 02:14:57,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 101154816. Throughput: 0: 1774.7, 1: 1779.8. Samples: 25294766. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:14:57,214][61453] Avg episode reward: [(0, '9.140'), (1, '9.640')] -[2023-10-17 02:14:57,667][62373] Updated weights for policy 0, policy_version 49570 (0.0009) -[2023-10-17 02:14:58,046][62373] Updated weights for policy 0, policy_version 49580 (0.0008) -[2023-10-17 02:14:58,414][62373] Updated weights for policy 0, policy_version 49590 (0.0007) -[2023-10-17 02:14:58,781][62373] Updated weights for policy 0, policy_version 49600 (0.0008) -[2023-10-17 02:15:00,465][62408] Updated weights for policy 1, policy_version 49220 (0.0007) -[2023-10-17 02:15:00,836][62408] Updated weights for policy 1, policy_version 49230 (0.0009) -[2023-10-17 02:15:01,197][62408] Updated weights for policy 1, policy_version 49240 (0.0008) -[2023-10-17 02:15:02,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 101220352. Throughput: 0: 1794.0, 1: 1763.2. Samples: 25316076. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:15:02,215][61453] Avg episode reward: [(0, '9.100'), (1, '10.020')] -[2023-10-17 02:15:02,653][62373] Updated weights for policy 0, policy_version 49610 (0.0008) -[2023-10-17 02:15:03,030][62373] Updated weights for policy 0, policy_version 49620 (0.0008) -[2023-10-17 02:15:03,399][62373] Updated weights for policy 0, policy_version 49630 (0.0010) -[2023-10-17 02:15:05,121][62408] Updated weights for policy 1, policy_version 49250 (0.0007) -[2023-10-17 02:15:05,483][62408] Updated weights for policy 1, policy_version 49260 (0.0009) -[2023-10-17 02:15:05,853][62408] Updated weights for policy 1, policy_version 49270 (0.0009) -[2023-10-17 02:15:06,219][62408] Updated weights for policy 1, policy_version 49280 (0.0009) -[2023-10-17 02:15:07,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 101285888. Throughput: 0: 1769.1, 1: 1783.6. Samples: 25327064. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:15:07,215][61453] Avg episode reward: [(0, '8.630'), (1, '9.730')] -[2023-10-17 02:15:07,281][62373] Updated weights for policy 0, policy_version 49640 (0.0008) -[2023-10-17 02:15:07,647][62373] Updated weights for policy 0, policy_version 49650 (0.0008) -[2023-10-17 02:15:08,031][62373] Updated weights for policy 0, policy_version 49660 (0.0009) -[2023-10-17 02:15:09,940][62408] Updated weights for policy 1, policy_version 49290 (0.0010) -[2023-10-17 02:15:10,305][62408] Updated weights for policy 1, policy_version 49300 (0.0009) -[2023-10-17 02:15:10,675][62408] Updated weights for policy 1, policy_version 49310 (0.0010) -[2023-10-17 02:15:11,862][62373] Updated weights for policy 0, policy_version 49670 (0.0008) -[2023-10-17 02:15:12,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 101351424. Throughput: 0: 1785.4, 1: 1763.9. Samples: 25347992. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:15:12,215][61453] Avg episode reward: [(0, '8.330'), (1, '10.010')] -[2023-10-17 02:15:12,233][62373] Updated weights for policy 0, policy_version 49680 (0.0010) -[2023-10-17 02:15:12,603][62373] Updated weights for policy 0, policy_version 49690 (0.0009) -[2023-10-17 02:15:14,561][62408] Updated weights for policy 1, policy_version 49320 (0.0009) -[2023-10-17 02:15:14,930][62408] Updated weights for policy 1, policy_version 49330 (0.0008) -[2023-10-17 02:15:15,296][62408] Updated weights for policy 1, policy_version 49340 (0.0007) -[2023-10-17 02:15:16,372][62373] Updated weights for policy 0, policy_version 49700 (0.0008) -[2023-10-17 02:15:16,760][62373] Updated weights for policy 0, policy_version 49710 (0.0008) -[2023-10-17 02:15:17,138][62373] Updated weights for policy 0, policy_version 49720 (0.0009) -[2023-10-17 02:15:17,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 101416960. Throughput: 0: 1785.9, 1: 1768.0. Samples: 25369380. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:15:17,215][61453] Avg episode reward: [(0, '8.870'), (1, '10.050')] -[2023-10-17 02:15:19,216][62408] Updated weights for policy 1, policy_version 49350 (0.0007) -[2023-10-17 02:15:19,589][62408] Updated weights for policy 1, policy_version 49360 (0.0007) -[2023-10-17 02:15:19,955][62408] Updated weights for policy 1, policy_version 49370 (0.0007) -[2023-10-17 02:15:20,862][62373] Updated weights for policy 0, policy_version 49730 (0.0008) -[2023-10-17 02:15:21,229][62373] Updated weights for policy 0, policy_version 49740 (0.0010) -[2023-10-17 02:15:21,606][62373] Updated weights for policy 0, policy_version 49750 (0.0011) -[2023-10-17 02:15:21,972][62373] Updated weights for policy 0, policy_version 49760 (0.0009) -[2023-10-17 02:15:22,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 101515264. Throughput: 0: 1785.2, 1: 1776.7. Samples: 25380362. Policy #0 lag: (min: 14.0, avg: 21.9, max: 46.0) -[2023-10-17 02:15:22,215][61453] Avg episode reward: [(0, '8.770'), (1, '9.500')] -[2023-10-17 02:15:23,861][62408] Updated weights for policy 1, policy_version 49380 (0.0008) -[2023-10-17 02:15:24,224][62408] Updated weights for policy 1, policy_version 49390 (0.0010) -[2023-10-17 02:15:24,600][62408] Updated weights for policy 1, policy_version 49400 (0.0008) -[2023-10-17 02:15:25,727][62373] Updated weights for policy 0, policy_version 49770 (0.0010) -[2023-10-17 02:15:26,103][62373] Updated weights for policy 0, policy_version 49780 (0.0010) -[2023-10-17 02:15:26,465][62373] Updated weights for policy 0, policy_version 49790 (0.0009) -[2023-10-17 02:15:27,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 101580800. Throughput: 0: 1795.1, 1: 1775.8. Samples: 25401576. Policy #0 lag: (min: 14.0, avg: 21.9, max: 46.0) -[2023-10-17 02:15:27,215][61453] Avg episode reward: [(0, '9.120'), (1, '9.640')] -[2023-10-17 02:15:28,440][62408] Updated weights for policy 1, policy_version 49410 (0.0010) -[2023-10-17 02:15:28,824][62408] Updated weights for policy 1, policy_version 49420 (0.0009) -[2023-10-17 02:15:29,190][62408] Updated weights for policy 1, policy_version 49430 (0.0009) -[2023-10-17 02:15:29,552][62408] Updated weights for policy 1, policy_version 49440 (0.0008) -[2023-10-17 02:15:30,254][62373] Updated weights for policy 0, policy_version 49800 (0.0008) -[2023-10-17 02:15:30,616][62373] Updated weights for policy 0, policy_version 49810 (0.0009) -[2023-10-17 02:15:30,990][62373] Updated weights for policy 0, policy_version 49820 (0.0009) -[2023-10-17 02:15:32,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 101646336. Throughput: 0: 1779.3, 1: 1781.7. Samples: 25423014. Policy #0 lag: (min: 14.0, avg: 21.9, max: 46.0) -[2023-10-17 02:15:32,214][61453] Avg episode reward: [(0, '9.240'), (1, '8.870')] -[2023-10-17 02:15:32,222][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000049824_51019776.pth... -[2023-10-17 02:15:32,222][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000049440_50626560.pth... -[2023-10-17 02:15:32,262][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000048160_49315840.pth -[2023-10-17 02:15:32,263][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000047776_48922624.pth -[2023-10-17 02:15:32,268][62094] Saving a milestone ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/milestones/checkpoint_000049824_51019776.pth -[2023-10-17 02:15:32,268][62252] Saving a milestone ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/milestones/checkpoint_000049440_50626560.pth -[2023-10-17 02:15:33,214][62408] Updated weights for policy 1, policy_version 49450 (0.0008) -[2023-10-17 02:15:33,581][62408] Updated weights for policy 1, policy_version 49460 (0.0008) -[2023-10-17 02:15:33,953][62408] Updated weights for policy 1, policy_version 49470 (0.0011) -[2023-10-17 02:15:34,587][62373] Updated weights for policy 0, policy_version 49830 (0.0010) -[2023-10-17 02:15:34,947][62373] Updated weights for policy 0, policy_version 49840 (0.0008) -[2023-10-17 02:15:35,305][62373] Updated weights for policy 0, policy_version 49850 (0.0009) -[2023-10-17 02:15:37,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 101711872. Throughput: 0: 1794.2, 1: 1781.1. Samples: 25433458. Policy #0 lag: (min: 14.0, avg: 21.9, max: 46.0) -[2023-10-17 02:15:37,214][61453] Avg episode reward: [(0, '9.090'), (1, '9.600')] -[2023-10-17 02:15:37,816][62408] Updated weights for policy 1, policy_version 49480 (0.0008) -[2023-10-17 02:15:38,186][62408] Updated weights for policy 1, policy_version 49490 (0.0007) -[2023-10-17 02:15:38,562][62408] Updated weights for policy 1, policy_version 49500 (0.0010) -[2023-10-17 02:15:39,106][62373] Updated weights for policy 0, policy_version 49860 (0.0008) -[2023-10-17 02:15:39,474][62373] Updated weights for policy 0, policy_version 49870 (0.0008) -[2023-10-17 02:15:39,844][62373] Updated weights for policy 0, policy_version 49880 (0.0010) -[2023-10-17 02:15:42,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 101777408. Throughput: 0: 1775.0, 1: 1776.3. Samples: 25454574. Policy #0 lag: (min: 14.0, avg: 21.9, max: 46.0) -[2023-10-17 02:15:42,215][61453] Avg episode reward: [(0, '9.130'), (1, '9.070')] -[2023-10-17 02:15:42,308][62408] Updated weights for policy 1, policy_version 49510 (0.0010) -[2023-10-17 02:15:42,673][62408] Updated weights for policy 1, policy_version 49520 (0.0009) -[2023-10-17 02:15:43,055][62408] Updated weights for policy 1, policy_version 49530 (0.0009) -[2023-10-17 02:15:43,529][62373] Updated weights for policy 0, policy_version 49890 (0.0010) -[2023-10-17 02:15:43,901][62373] Updated weights for policy 0, policy_version 49900 (0.0009) -[2023-10-17 02:15:44,279][62373] Updated weights for policy 0, policy_version 49910 (0.0008) -[2023-10-17 02:15:44,644][62373] Updated weights for policy 0, policy_version 49920 (0.0009) -[2023-10-17 02:15:46,865][62408] Updated weights for policy 1, policy_version 49540 (0.0008) -[2023-10-17 02:15:47,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 101842944. Throughput: 0: 1774.6, 1: 1797.0. Samples: 25476796. Policy #0 lag: (min: 14.0, avg: 21.9, max: 46.0) -[2023-10-17 02:15:47,215][61453] Avg episode reward: [(0, '9.760'), (1, '8.600')] -[2023-10-17 02:15:47,236][62408] Updated weights for policy 1, policy_version 49550 (0.0010) -[2023-10-17 02:15:47,593][62408] Updated weights for policy 1, policy_version 49560 (0.0010) -[2023-10-17 02:15:48,630][62373] Updated weights for policy 0, policy_version 49930 (0.0008) -[2023-10-17 02:15:49,007][62373] Updated weights for policy 0, policy_version 49940 (0.0008) -[2023-10-17 02:15:49,376][62373] Updated weights for policy 0, policy_version 49950 (0.0009) -[2023-10-17 02:15:51,421][62408] Updated weights for policy 1, policy_version 49570 (0.0010) -[2023-10-17 02:15:51,795][62408] Updated weights for policy 1, policy_version 49580 (0.0009) -[2023-10-17 02:15:52,162][62408] Updated weights for policy 1, policy_version 49590 (0.0010) -[2023-10-17 02:15:52,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 101908480. Throughput: 0: 1774.0, 1: 1768.3. Samples: 25486468. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:15:52,215][61453] Avg episode reward: [(0, '10.020'), (1, '9.910')] -[2023-10-17 02:15:52,519][62408] Updated weights for policy 1, policy_version 49600 (0.0010) -[2023-10-17 02:15:53,028][62373] Updated weights for policy 0, policy_version 49960 (0.0009) -[2023-10-17 02:15:53,402][62373] Updated weights for policy 0, policy_version 49970 (0.0010) -[2023-10-17 02:15:53,785][62373] Updated weights for policy 0, policy_version 49980 (0.0009) -[2023-10-17 02:15:56,342][62408] Updated weights for policy 1, policy_version 49610 (0.0010) -[2023-10-17 02:15:56,712][62408] Updated weights for policy 1, policy_version 49620 (0.0007) -[2023-10-17 02:15:57,089][62408] Updated weights for policy 1, policy_version 49630 (0.0010) -[2023-10-17 02:15:57,214][61453] Fps is (10 sec: 16384.4, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 102006784. Throughput: 0: 1776.0, 1: 1796.9. Samples: 25508774. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:15:57,215][61453] Avg episode reward: [(0, '9.640'), (1, '9.960')] -[2023-10-17 02:15:57,540][62373] Updated weights for policy 0, policy_version 49990 (0.0009) -[2023-10-17 02:15:57,913][62373] Updated weights for policy 0, policy_version 50000 (0.0008) -[2023-10-17 02:15:58,280][62373] Updated weights for policy 0, policy_version 50010 (0.0008) -[2023-10-17 02:16:00,874][62408] Updated weights for policy 1, policy_version 49640 (0.0010) -[2023-10-17 02:16:01,248][62408] Updated weights for policy 1, policy_version 49650 (0.0008) -[2023-10-17 02:16:01,610][62408] Updated weights for policy 1, policy_version 49660 (0.0008) -[2023-10-17 02:16:02,197][62373] Updated weights for policy 0, policy_version 50020 (0.0009) -[2023-10-17 02:16:02,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 102072320. Throughput: 0: 1793.7, 1: 1766.0. Samples: 25529564. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:16:02,214][61453] Avg episode reward: [(0, '9.540'), (1, '10.220')] -[2023-10-17 02:16:02,590][62373] Updated weights for policy 0, policy_version 50030 (0.0008) -[2023-10-17 02:16:02,963][62373] Updated weights for policy 0, policy_version 50040 (0.0011) -[2023-10-17 02:16:05,358][62408] Updated weights for policy 1, policy_version 49670 (0.0009) -[2023-10-17 02:16:05,726][62408] Updated weights for policy 1, policy_version 49680 (0.0007) -[2023-10-17 02:16:06,089][62408] Updated weights for policy 1, policy_version 49690 (0.0007) -[2023-10-17 02:16:06,701][62373] Updated weights for policy 0, policy_version 50050 (0.0008) -[2023-10-17 02:16:07,071][62373] Updated weights for policy 0, policy_version 50060 (0.0009) -[2023-10-17 02:16:07,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 102137856. Throughput: 0: 1767.7, 1: 1787.1. Samples: 25540328. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:16:07,215][61453] Avg episode reward: [(0, '9.260'), (1, '10.500')] -[2023-10-17 02:16:07,438][62373] Updated weights for policy 0, policy_version 50070 (0.0009) -[2023-10-17 02:16:07,816][62373] Updated weights for policy 0, policy_version 50080 (0.0012) -[2023-10-17 02:16:09,944][62408] Updated weights for policy 1, policy_version 49700 (0.0008) -[2023-10-17 02:16:10,310][62408] Updated weights for policy 1, policy_version 49710 (0.0007) -[2023-10-17 02:16:10,684][62408] Updated weights for policy 1, policy_version 49720 (0.0009) -[2023-10-17 02:16:11,765][62373] Updated weights for policy 0, policy_version 50090 (0.0011) -[2023-10-17 02:16:12,134][62373] Updated weights for policy 0, policy_version 50100 (0.0011) -[2023-10-17 02:16:12,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 102203392. Throughput: 0: 1779.9, 1: 1765.8. Samples: 25561134. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:16:12,215][61453] Avg episode reward: [(0, '9.520'), (1, '10.080')] -[2023-10-17 02:16:12,503][62373] Updated weights for policy 0, policy_version 50110 (0.0009) -[2023-10-17 02:16:14,568][62408] Updated weights for policy 1, policy_version 49730 (0.0010) -[2023-10-17 02:16:14,925][62408] Updated weights for policy 1, policy_version 49740 (0.0009) -[2023-10-17 02:16:15,292][62408] Updated weights for policy 1, policy_version 49750 (0.0010) -[2023-10-17 02:16:15,665][62408] Updated weights for policy 1, policy_version 49760 (0.0009) -[2023-10-17 02:16:16,227][62373] Updated weights for policy 0, policy_version 50120 (0.0009) -[2023-10-17 02:16:16,593][62373] Updated weights for policy 0, policy_version 50130 (0.0007) -[2023-10-17 02:16:16,958][62373] Updated weights for policy 0, policy_version 50140 (0.0009) -[2023-10-17 02:16:17,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 102301696. Throughput: 0: 1773.7, 1: 1758.2. Samples: 25581950. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:16:17,215][61453] Avg episode reward: [(0, '9.710'), (1, '10.160')] -[2023-10-17 02:16:19,425][62408] Updated weights for policy 1, policy_version 49770 (0.0011) -[2023-10-17 02:16:19,803][62408] Updated weights for policy 1, policy_version 49780 (0.0010) -[2023-10-17 02:16:20,181][62408] Updated weights for policy 1, policy_version 49790 (0.0008) -[2023-10-17 02:16:20,748][62373] Updated weights for policy 0, policy_version 50150 (0.0010) -[2023-10-17 02:16:21,125][62373] Updated weights for policy 0, policy_version 50160 (0.0010) -[2023-10-17 02:16:21,492][62373] Updated weights for policy 0, policy_version 50170 (0.0009) -[2023-10-17 02:16:22,214][61453] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 102367232. Throughput: 0: 1788.9, 1: 1766.5. Samples: 25593450. Policy #0 lag: (min: 26.0, avg: 30.8, max: 58.0) -[2023-10-17 02:16:22,215][61453] Avg episode reward: [(0, '9.310'), (1, '9.630')] -[2023-10-17 02:16:24,093][62408] Updated weights for policy 1, policy_version 49800 (0.0008) -[2023-10-17 02:16:24,473][62408] Updated weights for policy 1, policy_version 49810 (0.0009) -[2023-10-17 02:16:24,841][62408] Updated weights for policy 1, policy_version 49820 (0.0008) -[2023-10-17 02:16:25,188][62373] Updated weights for policy 0, policy_version 50180 (0.0010) -[2023-10-17 02:16:25,555][62373] Updated weights for policy 0, policy_version 50190 (0.0009) -[2023-10-17 02:16:25,925][62373] Updated weights for policy 0, policy_version 50200 (0.0009) -[2023-10-17 02:16:27,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 102432768. Throughput: 0: 1781.8, 1: 1756.2. Samples: 25613786. Policy #0 lag: (min: 26.0, avg: 30.8, max: 58.0) -[2023-10-17 02:16:27,215][61453] Avg episode reward: [(0, '8.700'), (1, '9.840')] -[2023-10-17 02:16:28,536][62408] Updated weights for policy 1, policy_version 49830 (0.0007) -[2023-10-17 02:16:28,899][62408] Updated weights for policy 1, policy_version 49840 (0.0008) -[2023-10-17 02:16:29,262][62408] Updated weights for policy 1, policy_version 49850 (0.0010) -[2023-10-17 02:16:29,734][62373] Updated weights for policy 0, policy_version 50210 (0.0009) -[2023-10-17 02:16:30,106][62373] Updated weights for policy 0, policy_version 50220 (0.0010) -[2023-10-17 02:16:30,478][62373] Updated weights for policy 0, policy_version 50230 (0.0011) -[2023-10-17 02:16:30,846][62373] Updated weights for policy 0, policy_version 50240 (0.0009) -[2023-10-17 02:16:32,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 102498304. Throughput: 0: 1771.8, 1: 1763.6. Samples: 25635888. Policy #0 lag: (min: 26.0, avg: 30.8, max: 58.0) -[2023-10-17 02:16:32,215][61453] Avg episode reward: [(0, '9.810'), (1, '9.810')] -[2023-10-17 02:16:33,167][62408] Updated weights for policy 1, policy_version 49860 (0.0008) -[2023-10-17 02:16:33,547][62408] Updated weights for policy 1, policy_version 49870 (0.0010) -[2023-10-17 02:16:33,910][62408] Updated weights for policy 1, policy_version 49880 (0.0008) -[2023-10-17 02:16:34,771][62373] Updated weights for policy 0, policy_version 50250 (0.0008) -[2023-10-17 02:16:35,150][62373] Updated weights for policy 0, policy_version 50260 (0.0008) -[2023-10-17 02:16:35,508][62373] Updated weights for policy 0, policy_version 50270 (0.0011) -[2023-10-17 02:16:37,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 102563840. Throughput: 0: 1790.5, 1: 1759.5. Samples: 25646218. Policy #0 lag: (min: 26.0, avg: 30.8, max: 58.0) -[2023-10-17 02:16:37,215][61453] Avg episode reward: [(0, '9.560'), (1, '9.630')] -[2023-10-17 02:16:37,743][62408] Updated weights for policy 1, policy_version 49890 (0.0008) -[2023-10-17 02:16:38,111][62408] Updated weights for policy 1, policy_version 49900 (0.0008) -[2023-10-17 02:16:38,478][62408] Updated weights for policy 1, policy_version 49910 (0.0010) -[2023-10-17 02:16:38,840][62408] Updated weights for policy 1, policy_version 49920 (0.0007) -[2023-10-17 02:16:39,349][62373] Updated weights for policy 0, policy_version 50280 (0.0008) -[2023-10-17 02:16:39,719][62373] Updated weights for policy 0, policy_version 50290 (0.0008) -[2023-10-17 02:16:40,088][62373] Updated weights for policy 0, policy_version 50300 (0.0007) -[2023-10-17 02:16:42,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 102629376. Throughput: 0: 1767.9, 1: 1762.0. Samples: 25667622. Policy #0 lag: (min: 26.0, avg: 30.8, max: 58.0) -[2023-10-17 02:16:42,215][61453] Avg episode reward: [(0, '9.540'), (1, '10.020')] -[2023-10-17 02:16:42,511][62408] Updated weights for policy 1, policy_version 49930 (0.0008) -[2023-10-17 02:16:42,880][62408] Updated weights for policy 1, policy_version 49940 (0.0008) -[2023-10-17 02:16:43,244][62408] Updated weights for policy 1, policy_version 49950 (0.0010) -[2023-10-17 02:16:43,809][62373] Updated weights for policy 0, policy_version 50310 (0.0007) -[2023-10-17 02:16:44,184][62373] Updated weights for policy 0, policy_version 50320 (0.0009) -[2023-10-17 02:16:44,555][62373] Updated weights for policy 0, policy_version 50330 (0.0009) -[2023-10-17 02:16:47,024][62408] Updated weights for policy 1, policy_version 49960 (0.0009) -[2023-10-17 02:16:47,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 102694912. Throughput: 0: 1773.6, 1: 1788.6. Samples: 25689862. Policy #0 lag: (min: 26.0, avg: 30.8, max: 58.0) -[2023-10-17 02:16:47,215][61453] Avg episode reward: [(0, '9.200'), (1, '9.650')] -[2023-10-17 02:16:47,388][62408] Updated weights for policy 1, policy_version 49970 (0.0010) -[2023-10-17 02:16:47,757][62408] Updated weights for policy 1, policy_version 49980 (0.0011) -[2023-10-17 02:16:48,382][62373] Updated weights for policy 0, policy_version 50340 (0.0009) -[2023-10-17 02:16:48,768][62373] Updated weights for policy 0, policy_version 50350 (0.0008) -[2023-10-17 02:16:49,134][62373] Updated weights for policy 0, policy_version 50360 (0.0009) -[2023-10-17 02:16:51,621][62408] Updated weights for policy 1, policy_version 49990 (0.0007) -[2023-10-17 02:16:51,986][62408] Updated weights for policy 1, policy_version 50000 (0.0009) -[2023-10-17 02:16:52,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 102760448. Throughput: 0: 1777.8, 1: 1760.2. Samples: 25699540. Policy #0 lag: (min: 26.0, avg: 30.8, max: 58.0) -[2023-10-17 02:16:52,214][61453] Avg episode reward: [(0, '9.210'), (1, '9.170')] -[2023-10-17 02:16:52,352][62408] Updated weights for policy 1, policy_version 50010 (0.0010) -[2023-10-17 02:16:52,740][62373] Updated weights for policy 0, policy_version 50370 (0.0007) -[2023-10-17 02:16:53,122][62373] Updated weights for policy 0, policy_version 50380 (0.0007) -[2023-10-17 02:16:53,486][62373] Updated weights for policy 0, policy_version 50390 (0.0010) -[2023-10-17 02:16:53,847][62373] Updated weights for policy 0, policy_version 50400 (0.0009) -[2023-10-17 02:16:56,339][62408] Updated weights for policy 1, policy_version 50020 (0.0008) -[2023-10-17 02:16:56,712][62408] Updated weights for policy 1, policy_version 50030 (0.0010) -[2023-10-17 02:16:57,074][62408] Updated weights for policy 1, policy_version 50040 (0.0010) -[2023-10-17 02:16:57,214][61453] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 102825984. Throughput: 0: 1780.0, 1: 1787.5. Samples: 25721672. Policy #0 lag: (min: 26.0, avg: 30.8, max: 58.0) -[2023-10-17 02:16:57,214][61453] Avg episode reward: [(0, '10.020'), (1, '9.520')] -[2023-10-17 02:16:57,596][62373] Updated weights for policy 0, policy_version 50410 (0.0007) -[2023-10-17 02:16:57,965][62373] Updated weights for policy 0, policy_version 50420 (0.0011) -[2023-10-17 02:16:58,328][62373] Updated weights for policy 0, policy_version 50430 (0.0008) -[2023-10-17 02:17:00,866][62408] Updated weights for policy 1, policy_version 50050 (0.0010) -[2023-10-17 02:17:01,244][62408] Updated weights for policy 1, policy_version 50060 (0.0008) -[2023-10-17 02:17:01,621][62408] Updated weights for policy 1, policy_version 50070 (0.0009) -[2023-10-17 02:17:01,976][62408] Updated weights for policy 1, policy_version 50080 (0.0007) -[2023-10-17 02:17:01,989][62373] Updated weights for policy 0, policy_version 50440 (0.0009) -[2023-10-17 02:17:02,214][61453] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 102924288. Throughput: 0: 1800.2, 1: 1767.2. Samples: 25742486. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-17 02:17:02,215][61453] Avg episode reward: [(0, '9.530'), (1, '9.050')] -[2023-10-17 02:17:02,360][62373] Updated weights for policy 0, policy_version 50450 (0.0009) -[2023-10-17 02:17:02,739][62373] Updated weights for policy 0, policy_version 50460 (0.0007) -[2023-10-17 02:17:05,804][62408] Updated weights for policy 1, policy_version 50090 (0.0009) -[2023-10-17 02:17:06,187][62408] Updated weights for policy 1, policy_version 50100 (0.0008) -[2023-10-17 02:17:06,487][62373] Updated weights for policy 0, policy_version 50470 (0.0009) -[2023-10-17 02:17:06,558][62408] Updated weights for policy 1, policy_version 50110 (0.0008) -[2023-10-17 02:17:06,860][62373] Updated weights for policy 0, policy_version 50480 (0.0007) -[2023-10-17 02:17:07,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 102989824. Throughput: 0: 1775.6, 1: 1783.3. Samples: 25753600. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-17 02:17:07,214][61453] Avg episode reward: [(0, '9.100'), (1, '9.420')] -[2023-10-17 02:17:07,227][62373] Updated weights for policy 0, policy_version 50490 (0.0008) -[2023-10-17 02:17:10,608][62408] Updated weights for policy 1, policy_version 50120 (0.0010) -[2023-10-17 02:17:10,983][62408] Updated weights for policy 1, policy_version 50130 (0.0010) -[2023-10-17 02:17:11,179][62373] Updated weights for policy 0, policy_version 50500 (0.0008) -[2023-10-17 02:17:11,349][62408] Updated weights for policy 1, policy_version 50140 (0.0007) -[2023-10-17 02:17:11,551][62373] Updated weights for policy 0, policy_version 50510 (0.0009) -[2023-10-17 02:17:11,916][62373] Updated weights for policy 0, policy_version 50520 (0.0007) -[2023-10-17 02:17:12,214][61453] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 103088128. Throughput: 0: 1794.0, 1: 1783.4. Samples: 25774768. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-17 02:17:12,215][61453] Avg episode reward: [(0, '9.450'), (1, '9.460')] -[2023-10-17 02:17:15,061][62408] Updated weights for policy 1, policy_version 50150 (0.0008) -[2023-10-17 02:17:15,437][62408] Updated weights for policy 1, policy_version 50160 (0.0008) -[2023-10-17 02:17:15,685][62373] Updated weights for policy 0, policy_version 50530 (0.0008) -[2023-10-17 02:17:15,804][62408] Updated weights for policy 1, policy_version 50170 (0.0009) -[2023-10-17 02:17:16,055][62373] Updated weights for policy 0, policy_version 50540 (0.0008) -[2023-10-17 02:17:16,425][62373] Updated weights for policy 0, policy_version 50550 (0.0010) -[2023-10-17 02:17:16,796][62373] Updated weights for policy 0, policy_version 50560 (0.0011) -[2023-10-17 02:17:17,214][61453] Fps is (10 sec: 16383.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 103153664. Throughput: 0: 1770.3, 1: 1760.5. Samples: 25794774. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-17 02:17:17,216][61453] Avg episode reward: [(0, '10.080'), (1, '10.160')] -[2023-10-17 02:17:19,537][62408] Updated weights for policy 1, policy_version 50180 (0.0008) -[2023-10-17 02:17:19,909][62408] Updated weights for policy 1, policy_version 50190 (0.0007) -[2023-10-17 02:17:20,276][62408] Updated weights for policy 1, policy_version 50200 (0.0007) -[2023-10-17 02:17:20,680][62373] Updated weights for policy 0, policy_version 50570 (0.0008) -[2023-10-17 02:17:21,043][62373] Updated weights for policy 0, policy_version 50580 (0.0011) -[2023-10-17 02:17:21,415][62373] Updated weights for policy 0, policy_version 50590 (0.0010) -[2023-10-17 02:17:22,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 103219200. Throughput: 0: 1783.7, 1: 1780.0. Samples: 25806584. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-17 02:17:22,214][61453] Avg episode reward: [(0, '10.020'), (1, '9.930')] -[2023-10-17 02:17:24,021][62408] Updated weights for policy 1, policy_version 50210 (0.0008) -[2023-10-17 02:17:24,401][62408] Updated weights for policy 1, policy_version 50220 (0.0011) -[2023-10-17 02:17:24,768][62408] Updated weights for policy 1, policy_version 50230 (0.0008) -[2023-10-17 02:17:25,137][62408] Updated weights for policy 1, policy_version 50240 (0.0007) -[2023-10-17 02:17:25,179][62373] Updated weights for policy 0, policy_version 50600 (0.0008) -[2023-10-17 02:17:25,540][62373] Updated weights for policy 0, policy_version 50610 (0.0010) -[2023-10-17 02:17:25,909][62373] Updated weights for policy 0, policy_version 50620 (0.0009) -[2023-10-17 02:17:27,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 103284736. Throughput: 0: 1776.5, 1: 1759.1. Samples: 25826724. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-17 02:17:27,215][61453] Avg episode reward: [(0, '9.930'), (1, '9.810')] -[2023-10-17 02:17:28,919][62408] Updated weights for policy 1, policy_version 50250 (0.0008) -[2023-10-17 02:17:29,284][62408] Updated weights for policy 1, policy_version 50260 (0.0007) -[2023-10-17 02:17:29,659][62408] Updated weights for policy 1, policy_version 50270 (0.0008) -[2023-10-17 02:17:29,726][62373] Updated weights for policy 0, policy_version 50630 (0.0008) -[2023-10-17 02:17:30,098][62373] Updated weights for policy 0, policy_version 50640 (0.0008) -[2023-10-17 02:17:30,470][62373] Updated weights for policy 0, policy_version 50650 (0.0008) -[2023-10-17 02:17:32,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 103350272. Throughput: 0: 1769.6, 1: 1762.1. Samples: 25848790. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-10-17 02:17:32,215][61453] Avg episode reward: [(0, '9.680'), (1, '9.960')] -[2023-10-17 02:17:32,227][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000050656_51871744.pth... -[2023-10-17 02:17:32,227][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000050272_51478528.pth... -[2023-10-17 02:17:32,260][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000048608_49774592.pth -[2023-10-17 02:17:32,267][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000048992_50167808.pth -[2023-10-17 02:17:33,326][62408] Updated weights for policy 1, policy_version 50280 (0.0009) -[2023-10-17 02:17:33,697][62408] Updated weights for policy 1, policy_version 50290 (0.0009) -[2023-10-17 02:17:34,069][62408] Updated weights for policy 1, policy_version 50300 (0.0010) -[2023-10-17 02:17:34,336][62373] Updated weights for policy 0, policy_version 50660 (0.0010) -[2023-10-17 02:17:34,713][62373] Updated weights for policy 0, policy_version 50670 (0.0010) -[2023-10-17 02:17:35,085][62373] Updated weights for policy 0, policy_version 50680 (0.0008) -[2023-10-17 02:17:37,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 103415808. Throughput: 0: 1778.4, 1: 1761.5. Samples: 25858834. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:17:37,215][61453] Avg episode reward: [(0, '9.770'), (1, '9.640')] -[2023-10-17 02:17:38,123][62408] Updated weights for policy 1, policy_version 50310 (0.0008) -[2023-10-17 02:17:38,486][62408] Updated weights for policy 1, policy_version 50320 (0.0007) -[2023-10-17 02:17:38,835][62373] Updated weights for policy 0, policy_version 50690 (0.0008) -[2023-10-17 02:17:38,847][62408] Updated weights for policy 1, policy_version 50330 (0.0008) -[2023-10-17 02:17:39,205][62373] Updated weights for policy 0, policy_version 50700 (0.0008) -[2023-10-17 02:17:39,576][62373] Updated weights for policy 0, policy_version 50710 (0.0008) -[2023-10-17 02:17:39,939][62373] Updated weights for policy 0, policy_version 50720 (0.0011) -[2023-10-17 02:17:42,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 103481344. Throughput: 0: 1763.7, 1: 1758.2. Samples: 25880158. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:17:42,214][61453] Avg episode reward: [(0, '9.270'), (1, '9.850')] -[2023-10-17 02:17:42,682][62408] Updated weights for policy 1, policy_version 50340 (0.0007) -[2023-10-17 02:17:43,060][62408] Updated weights for policy 1, policy_version 50350 (0.0008) -[2023-10-17 02:17:43,422][62408] Updated weights for policy 1, policy_version 50360 (0.0008) -[2023-10-17 02:17:43,658][62373] Updated weights for policy 0, policy_version 50730 (0.0008) -[2023-10-17 02:17:44,019][62373] Updated weights for policy 0, policy_version 50740 (0.0007) -[2023-10-17 02:17:44,386][62373] Updated weights for policy 0, policy_version 50750 (0.0008) -[2023-10-17 02:17:47,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 103546880. Throughput: 0: 1769.1, 1: 1784.5. Samples: 25902398. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:17:47,215][61453] Avg episode reward: [(0, '9.480'), (1, '9.560')] -[2023-10-17 02:17:47,247][62408] Updated weights for policy 1, policy_version 50370 (0.0008) -[2023-10-17 02:17:47,612][62408] Updated weights for policy 1, policy_version 50380 (0.0008) -[2023-10-17 02:17:47,986][62408] Updated weights for policy 1, policy_version 50390 (0.0008) -[2023-10-17 02:17:48,190][62373] Updated weights for policy 0, policy_version 50760 (0.0008) -[2023-10-17 02:17:48,346][62408] Updated weights for policy 1, policy_version 50400 (0.0008) -[2023-10-17 02:17:48,556][62373] Updated weights for policy 0, policy_version 50770 (0.0009) -[2023-10-17 02:17:48,922][62373] Updated weights for policy 0, policy_version 50780 (0.0010) -[2023-10-17 02:17:52,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 103612416. Throughput: 0: 1763.6, 1: 1756.1. Samples: 25911988. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:17:52,214][61453] Avg episode reward: [(0, '8.960'), (1, '8.900')] -[2023-10-17 02:17:52,233][62408] Updated weights for policy 1, policy_version 50410 (0.0008) -[2023-10-17 02:17:52,601][62408] Updated weights for policy 1, policy_version 50420 (0.0011) -[2023-10-17 02:17:52,851][62373] Updated weights for policy 0, policy_version 50790 (0.0008) -[2023-10-17 02:17:52,971][62408] Updated weights for policy 1, policy_version 50430 (0.0008) -[2023-10-17 02:17:53,214][62373] Updated weights for policy 0, policy_version 50800 (0.0008) -[2023-10-17 02:17:53,592][62373] Updated weights for policy 0, policy_version 50810 (0.0009) -[2023-10-17 02:17:56,856][62408] Updated weights for policy 1, policy_version 50440 (0.0008) -[2023-10-17 02:17:57,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 103677952. Throughput: 0: 1771.2, 1: 1776.3. Samples: 25934406. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:17:57,215][61453] Avg episode reward: [(0, '9.360'), (1, '8.670')] -[2023-10-17 02:17:57,219][62408] Updated weights for policy 1, policy_version 50450 (0.0009) -[2023-10-17 02:17:57,281][62373] Updated weights for policy 0, policy_version 50820 (0.0008) -[2023-10-17 02:17:57,587][62408] Updated weights for policy 1, policy_version 50460 (0.0007) -[2023-10-17 02:17:57,647][62373] Updated weights for policy 0, policy_version 50830 (0.0008) -[2023-10-17 02:17:58,025][62373] Updated weights for policy 0, policy_version 50840 (0.0009) -[2023-10-17 02:18:01,316][62408] Updated weights for policy 1, policy_version 50470 (0.0007) -[2023-10-17 02:18:01,682][62408] Updated weights for policy 1, policy_version 50480 (0.0008) -[2023-10-17 02:18:01,788][62373] Updated weights for policy 0, policy_version 50850 (0.0007) -[2023-10-17 02:18:02,042][62408] Updated weights for policy 1, policy_version 50490 (0.0008) -[2023-10-17 02:18:02,162][62373] Updated weights for policy 0, policy_version 50860 (0.0007) -[2023-10-17 02:18:02,214][61453] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 103743488. Throughput: 0: 1797.4, 1: 1770.1. Samples: 25955310. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:18:02,214][61453] Avg episode reward: [(0, '9.270'), (1, '8.310')] -[2023-10-17 02:18:02,531][62373] Updated weights for policy 0, policy_version 50870 (0.0008) -[2023-10-17 02:18:02,898][62373] Updated weights for policy 0, policy_version 50880 (0.0009) -[2023-10-17 02:18:05,855][62408] Updated weights for policy 1, policy_version 50500 (0.0010) -[2023-10-17 02:18:06,219][62408] Updated weights for policy 1, policy_version 50510 (0.0008) -[2023-10-17 02:18:06,583][62408] Updated weights for policy 1, policy_version 50520 (0.0010) -[2023-10-17 02:18:06,734][62373] Updated weights for policy 0, policy_version 50890 (0.0008) -[2023-10-17 02:18:07,112][62373] Updated weights for policy 0, policy_version 50900 (0.0009) -[2023-10-17 02:18:07,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 103841792. Throughput: 0: 1773.1, 1: 1773.0. Samples: 25966160. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:18:07,215][61453] Avg episode reward: [(0, '9.020'), (1, '8.450')] -[2023-10-17 02:18:07,475][62373] Updated weights for policy 0, policy_version 50910 (0.0011) -[2023-10-17 02:18:10,485][62408] Updated weights for policy 1, policy_version 50530 (0.0009) -[2023-10-17 02:18:10,846][62408] Updated weights for policy 1, policy_version 50540 (0.0009) -[2023-10-17 02:18:11,219][62408] Updated weights for policy 1, policy_version 50550 (0.0008) -[2023-10-17 02:18:11,271][62373] Updated weights for policy 0, policy_version 50920 (0.0007) -[2023-10-17 02:18:11,591][62408] Updated weights for policy 1, policy_version 50560 (0.0007) -[2023-10-17 02:18:11,640][62373] Updated weights for policy 0, policy_version 50930 (0.0007) -[2023-10-17 02:18:12,015][62373] Updated weights for policy 0, policy_version 50940 (0.0007) -[2023-10-17 02:18:12,214][61453] Fps is (10 sec: 19660.8, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 103940096. Throughput: 0: 1799.2, 1: 1779.5. Samples: 25987766. Policy #0 lag: (min: 3.0, avg: 9.3, max: 35.0) -[2023-10-17 02:18:12,214][61453] Avg episode reward: [(0, '9.550'), (1, '8.600')] -[2023-10-17 02:18:15,368][62408] Updated weights for policy 1, policy_version 50570 (0.0009) -[2023-10-17 02:18:15,732][62408] Updated weights for policy 1, policy_version 50580 (0.0009) -[2023-10-17 02:18:15,929][62373] Updated weights for policy 0, policy_version 50950 (0.0008) -[2023-10-17 02:18:16,106][62408] Updated weights for policy 1, policy_version 50590 (0.0007) -[2023-10-17 02:18:16,293][62373] Updated weights for policy 0, policy_version 50960 (0.0007) -[2023-10-17 02:18:16,664][62373] Updated weights for policy 0, policy_version 50970 (0.0008) -[2023-10-17 02:18:17,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 104005632. Throughput: 0: 1763.9, 1: 1762.5. Samples: 26007480. Policy #0 lag: (min: 3.0, avg: 9.3, max: 35.0) -[2023-10-17 02:18:17,215][61453] Avg episode reward: [(0, '9.300'), (1, '9.200')] -[2023-10-17 02:18:19,703][62408] Updated weights for policy 1, policy_version 50600 (0.0009) -[2023-10-17 02:18:20,071][62408] Updated weights for policy 1, policy_version 50610 (0.0009) -[2023-10-17 02:18:20,447][62408] Updated weights for policy 1, policy_version 50620 (0.0009) -[2023-10-17 02:18:20,549][62373] Updated weights for policy 0, policy_version 50980 (0.0009) -[2023-10-17 02:18:20,932][62373] Updated weights for policy 0, policy_version 50990 (0.0008) -[2023-10-17 02:18:21,306][62373] Updated weights for policy 0, policy_version 51000 (0.0008) -[2023-10-17 02:18:22,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 104071168. Throughput: 0: 1790.4, 1: 1782.5. Samples: 26019616. Policy #0 lag: (min: 3.0, avg: 9.3, max: 35.0) -[2023-10-17 02:18:22,215][61453] Avg episode reward: [(0, '9.350'), (1, '9.290')] -[2023-10-17 02:18:24,343][62408] Updated weights for policy 1, policy_version 50630 (0.0009) -[2023-10-17 02:18:24,714][62408] Updated weights for policy 1, policy_version 50640 (0.0008) -[2023-10-17 02:18:25,071][62408] Updated weights for policy 1, policy_version 50650 (0.0009) -[2023-10-17 02:18:25,089][62373] Updated weights for policy 0, policy_version 51010 (0.0008) -[2023-10-17 02:18:25,461][62373] Updated weights for policy 0, policy_version 51020 (0.0008) -[2023-10-17 02:18:25,833][62373] Updated weights for policy 0, policy_version 51030 (0.0007) -[2023-10-17 02:18:26,206][62373] Updated weights for policy 0, policy_version 51040 (0.0008) -[2023-10-17 02:18:27,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 104136704. Throughput: 0: 1779.4, 1: 1762.9. Samples: 26039562. Policy #0 lag: (min: 3.0, avg: 9.3, max: 35.0) -[2023-10-17 02:18:27,214][61453] Avg episode reward: [(0, '9.360'), (1, '9.410')] -[2023-10-17 02:18:28,916][62408] Updated weights for policy 1, policy_version 50660 (0.0009) -[2023-10-17 02:18:29,277][62408] Updated weights for policy 1, policy_version 50670 (0.0010) -[2023-10-17 02:18:29,637][62408] Updated weights for policy 1, policy_version 50680 (0.0007) -[2023-10-17 02:18:29,994][62373] Updated weights for policy 0, policy_version 51050 (0.0008) -[2023-10-17 02:18:30,360][62373] Updated weights for policy 0, policy_version 51060 (0.0009) -[2023-10-17 02:18:30,728][62373] Updated weights for policy 0, policy_version 51070 (0.0009) -[2023-10-17 02:18:32,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 104202240. Throughput: 0: 1768.0, 1: 1764.8. Samples: 26061374. Policy #0 lag: (min: 3.0, avg: 9.3, max: 35.0) -[2023-10-17 02:18:32,214][61453] Avg episode reward: [(0, '10.090'), (1, '9.980')] -[2023-10-17 02:18:33,440][62408] Updated weights for policy 1, policy_version 50690 (0.0007) -[2023-10-17 02:18:33,816][62408] Updated weights for policy 1, policy_version 50700 (0.0010) -[2023-10-17 02:18:34,177][62408] Updated weights for policy 1, policy_version 50710 (0.0008) -[2023-10-17 02:18:34,552][62408] Updated weights for policy 1, policy_version 50720 (0.0008) -[2023-10-17 02:18:34,600][62373] Updated weights for policy 0, policy_version 51080 (0.0008) -[2023-10-17 02:18:34,978][62373] Updated weights for policy 0, policy_version 51090 (0.0007) -[2023-10-17 02:18:35,348][62373] Updated weights for policy 0, policy_version 51100 (0.0008) -[2023-10-17 02:18:37,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 104267776. Throughput: 0: 1782.0, 1: 1764.7. Samples: 26071590. Policy #0 lag: (min: 3.0, avg: 9.3, max: 35.0) -[2023-10-17 02:18:37,215][61453] Avg episode reward: [(0, '10.460'), (1, '10.210')] -[2023-10-17 02:18:38,488][62408] Updated weights for policy 1, policy_version 50730 (0.0008) -[2023-10-17 02:18:38,847][62408] Updated weights for policy 1, policy_version 50740 (0.0009) -[2023-10-17 02:18:39,151][62373] Updated weights for policy 0, policy_version 51110 (0.0009) -[2023-10-17 02:18:39,217][62408] Updated weights for policy 1, policy_version 50750 (0.0007) -[2023-10-17 02:18:39,524][62373] Updated weights for policy 0, policy_version 51120 (0.0008) -[2023-10-17 02:18:39,899][62373] Updated weights for policy 0, policy_version 51130 (0.0008) -[2023-10-17 02:18:42,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 104333312. Throughput: 0: 1759.3, 1: 1758.6. Samples: 26092714. Policy #0 lag: (min: 3.0, avg: 9.3, max: 35.0) -[2023-10-17 02:18:42,215][61453] Avg episode reward: [(0, '10.240'), (1, '9.740')] -[2023-10-17 02:18:43,081][62408] Updated weights for policy 1, policy_version 50760 (0.0010) -[2023-10-17 02:18:43,461][62408] Updated weights for policy 1, policy_version 50770 (0.0010) -[2023-10-17 02:18:43,619][62373] Updated weights for policy 0, policy_version 51140 (0.0009) -[2023-10-17 02:18:43,824][62408] Updated weights for policy 1, policy_version 50780 (0.0007) -[2023-10-17 02:18:43,977][62373] Updated weights for policy 0, policy_version 51150 (0.0009) -[2023-10-17 02:18:44,351][62373] Updated weights for policy 0, policy_version 51160 (0.0008) -[2023-10-17 02:18:47,214][61453] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 104398848. Throughput: 0: 1765.1, 1: 1773.7. Samples: 26114558. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:18:47,214][61453] Avg episode reward: [(0, '10.070'), (1, '9.840')] -[2023-10-17 02:18:47,773][62408] Updated weights for policy 1, policy_version 50790 (0.0009) -[2023-10-17 02:18:47,965][62373] Updated weights for policy 0, policy_version 51170 (0.0009) -[2023-10-17 02:18:48,138][62408] Updated weights for policy 1, policy_version 50800 (0.0008) -[2023-10-17 02:18:48,331][62373] Updated weights for policy 0, policy_version 51180 (0.0009) -[2023-10-17 02:18:48,501][62408] Updated weights for policy 1, policy_version 50810 (0.0008) -[2023-10-17 02:18:48,701][62373] Updated weights for policy 0, policy_version 51190 (0.0009) -[2023-10-17 02:18:49,071][62373] Updated weights for policy 0, policy_version 51200 (0.0010) -[2023-10-17 02:18:52,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 104464384. Throughput: 0: 1761.7, 1: 1749.2. Samples: 26124150. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:18:52,215][61453] Avg episode reward: [(0, '10.750'), (1, '9.670')] -[2023-10-17 02:18:52,409][62408] Updated weights for policy 1, policy_version 50820 (0.0010) -[2023-10-17 02:18:52,777][62408] Updated weights for policy 1, policy_version 50830 (0.0007) -[2023-10-17 02:18:52,987][62373] Updated weights for policy 0, policy_version 51210 (0.0008) -[2023-10-17 02:18:53,142][62408] Updated weights for policy 1, policy_version 50840 (0.0007) -[2023-10-17 02:18:53,353][62373] Updated weights for policy 0, policy_version 51220 (0.0008) -[2023-10-17 02:18:53,726][62373] Updated weights for policy 0, policy_version 51230 (0.0009) -[2023-10-17 02:18:56,961][62408] Updated weights for policy 1, policy_version 50850 (0.0008) -[2023-10-17 02:18:57,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 104529920. Throughput: 0: 1759.8, 1: 1762.1. Samples: 26146252. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:18:57,215][61453] Avg episode reward: [(0, '10.460'), (1, '9.480')] -[2023-10-17 02:18:57,329][62408] Updated weights for policy 1, policy_version 50860 (0.0009) -[2023-10-17 02:18:57,595][62373] Updated weights for policy 0, policy_version 51240 (0.0008) -[2023-10-17 02:18:57,700][62408] Updated weights for policy 1, policy_version 50870 (0.0008) -[2023-10-17 02:18:57,968][62373] Updated weights for policy 0, policy_version 51250 (0.0009) -[2023-10-17 02:18:58,069][62408] Updated weights for policy 1, policy_version 50880 (0.0009) -[2023-10-17 02:18:58,337][62373] Updated weights for policy 0, policy_version 51260 (0.0011) -[2023-10-17 02:19:01,869][62408] Updated weights for policy 1, policy_version 50890 (0.0007) -[2023-10-17 02:19:02,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 104595456. Throughput: 0: 1798.0, 1: 1769.1. Samples: 26168000. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:19:02,215][61453] Avg episode reward: [(0, '10.390'), (1, '9.790')] -[2023-10-17 02:19:02,225][62373] Updated weights for policy 0, policy_version 51270 (0.0009) -[2023-10-17 02:19:02,239][62408] Updated weights for policy 1, policy_version 50900 (0.0008) -[2023-10-17 02:19:02,598][62373] Updated weights for policy 0, policy_version 51280 (0.0009) -[2023-10-17 02:19:02,610][62408] Updated weights for policy 1, policy_version 50910 (0.0009) -[2023-10-17 02:19:02,967][62373] Updated weights for policy 0, policy_version 51290 (0.0009) -[2023-10-17 02:19:06,336][62408] Updated weights for policy 1, policy_version 50920 (0.0008) -[2023-10-17 02:19:06,696][62408] Updated weights for policy 1, policy_version 50930 (0.0008) -[2023-10-17 02:19:06,697][62373] Updated weights for policy 0, policy_version 51300 (0.0008) -[2023-10-17 02:19:07,068][62408] Updated weights for policy 1, policy_version 50940 (0.0007) -[2023-10-17 02:19:07,086][62373] Updated weights for policy 0, policy_version 51310 (0.0007) -[2023-10-17 02:19:07,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 104693760. Throughput: 0: 1762.9, 1: 1759.9. Samples: 26178142. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:19:07,215][61453] Avg episode reward: [(0, '10.210'), (1, '9.940')] -[2023-10-17 02:19:07,456][62373] Updated weights for policy 0, policy_version 51320 (0.0007) -[2023-10-17 02:19:10,803][62408] Updated weights for policy 1, policy_version 50950 (0.0008) -[2023-10-17 02:19:11,167][62408] Updated weights for policy 1, policy_version 50960 (0.0008) -[2023-10-17 02:19:11,246][62373] Updated weights for policy 0, policy_version 51330 (0.0007) -[2023-10-17 02:19:11,530][62408] Updated weights for policy 1, policy_version 50970 (0.0008) -[2023-10-17 02:19:11,609][62373] Updated weights for policy 0, policy_version 51340 (0.0008) -[2023-10-17 02:19:11,981][62373] Updated weights for policy 0, policy_version 51350 (0.0009) -[2023-10-17 02:19:12,214][61453] Fps is (10 sec: 16384.4, 60 sec: 13653.3, 300 sec: 14218.0). Total num frames: 104759296. Throughput: 0: 1786.8, 1: 1783.8. Samples: 26200240. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:19:12,214][61453] Avg episode reward: [(0, '9.340'), (1, '9.610')] -[2023-10-17 02:19:12,352][62373] Updated weights for policy 0, policy_version 51360 (0.0007) -[2023-10-17 02:19:15,376][62408] Updated weights for policy 1, policy_version 50980 (0.0008) -[2023-10-17 02:19:15,742][62408] Updated weights for policy 1, policy_version 50990 (0.0010) -[2023-10-17 02:19:16,115][62408] Updated weights for policy 1, policy_version 51000 (0.0008) -[2023-10-17 02:19:16,142][62373] Updated weights for policy 0, policy_version 51370 (0.0007) -[2023-10-17 02:19:16,507][62373] Updated weights for policy 0, policy_version 51380 (0.0007) -[2023-10-17 02:19:16,879][62373] Updated weights for policy 0, policy_version 51390 (0.0008) -[2023-10-17 02:19:17,214][61453] Fps is (10 sec: 16383.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 104857600. Throughput: 0: 1767.6, 1: 1756.2. Samples: 26219946. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:19:17,216][61453] Avg episode reward: [(0, '9.160'), (1, '9.210')] -[2023-10-17 02:19:19,823][62408] Updated weights for policy 1, policy_version 51010 (0.0008) -[2023-10-17 02:19:20,181][62408] Updated weights for policy 1, policy_version 51020 (0.0009) -[2023-10-17 02:19:20,542][62408] Updated weights for policy 1, policy_version 51030 (0.0008) -[2023-10-17 02:19:20,594][62373] Updated weights for policy 0, policy_version 51400 (0.0009) -[2023-10-17 02:19:20,909][62408] Updated weights for policy 1, policy_version 51040 (0.0009) -[2023-10-17 02:19:20,960][62373] Updated weights for policy 0, policy_version 51410 (0.0007) -[2023-10-17 02:19:21,325][62373] Updated weights for policy 0, policy_version 51420 (0.0010) -[2023-10-17 02:19:22,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 104923136. Throughput: 0: 1789.0, 1: 1789.3. Samples: 26232612. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:19:22,215][61453] Avg episode reward: [(0, '9.440'), (1, '9.880')] -[2023-10-17 02:19:24,712][62408] Updated weights for policy 1, policy_version 51050 (0.0007) -[2023-10-17 02:19:25,077][62408] Updated weights for policy 1, policy_version 51060 (0.0009) -[2023-10-17 02:19:25,140][62373] Updated weights for policy 0, policy_version 51430 (0.0008) -[2023-10-17 02:19:25,446][62408] Updated weights for policy 1, policy_version 51070 (0.0007) -[2023-10-17 02:19:25,509][62373] Updated weights for policy 0, policy_version 51440 (0.0008) -[2023-10-17 02:19:25,868][62373] Updated weights for policy 0, policy_version 51450 (0.0010) -[2023-10-17 02:19:27,214][61453] Fps is (10 sec: 13107.6, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 104988672. Throughput: 0: 1780.5, 1: 1762.0. Samples: 26252130. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:19:27,215][61453] Avg episode reward: [(0, '8.890'), (1, '9.720')] -[2023-10-17 02:19:29,463][62408] Updated weights for policy 1, policy_version 51080 (0.0007) -[2023-10-17 02:19:29,688][62373] Updated weights for policy 0, policy_version 51460 (0.0010) -[2023-10-17 02:19:29,848][62408] Updated weights for policy 1, policy_version 51090 (0.0008) -[2023-10-17 02:19:30,054][62373] Updated weights for policy 0, policy_version 51470 (0.0007) -[2023-10-17 02:19:30,221][62408] Updated weights for policy 1, policy_version 51100 (0.0007) -[2023-10-17 02:19:30,417][62373] Updated weights for policy 0, policy_version 51480 (0.0009) -[2023-10-17 02:19:32,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 105054208. Throughput: 0: 1776.6, 1: 1763.8. Samples: 26273876. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:19:32,215][61453] Avg episode reward: [(0, '8.960'), (1, '9.820')] -[2023-10-17 02:19:32,226][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000051104_52330496.pth... -[2023-10-17 02:19:32,227][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000051488_52723712.pth... -[2023-10-17 02:19:32,256][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000049440_50626560.pth -[2023-10-17 02:19:32,263][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000049824_51019776.pth -[2023-10-17 02:19:33,920][62408] Updated weights for policy 1, policy_version 51110 (0.0009) -[2023-10-17 02:19:34,116][62373] Updated weights for policy 0, policy_version 51490 (0.0010) -[2023-10-17 02:19:34,286][62408] Updated weights for policy 1, policy_version 51120 (0.0008) -[2023-10-17 02:19:34,481][62373] Updated weights for policy 0, policy_version 51500 (0.0009) -[2023-10-17 02:19:34,657][62408] Updated weights for policy 1, policy_version 51130 (0.0007) -[2023-10-17 02:19:34,854][62373] Updated weights for policy 0, policy_version 51510 (0.0009) -[2023-10-17 02:19:35,218][62373] Updated weights for policy 0, policy_version 51520 (0.0008) -[2023-10-17 02:19:37,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 105119744. Throughput: 0: 1786.8, 1: 1768.3. Samples: 26284132. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:19:37,215][61453] Avg episode reward: [(0, '9.040'), (1, '9.480')] -[2023-10-17 02:19:38,528][62408] Updated weights for policy 1, policy_version 51140 (0.0008) -[2023-10-17 02:19:38,898][62408] Updated weights for policy 1, policy_version 51150 (0.0008) -[2023-10-17 02:19:39,021][62373] Updated weights for policy 0, policy_version 51530 (0.0007) -[2023-10-17 02:19:39,261][62408] Updated weights for policy 1, policy_version 51160 (0.0008) -[2023-10-17 02:19:39,395][62373] Updated weights for policy 0, policy_version 51540 (0.0007) -[2023-10-17 02:19:39,772][62373] Updated weights for policy 0, policy_version 51550 (0.0009) -[2023-10-17 02:19:42,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 105185280. Throughput: 0: 1777.3, 1: 1759.0. Samples: 26305386. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:19:42,215][61453] Avg episode reward: [(0, '9.430'), (1, '9.370')] -[2023-10-17 02:19:43,181][62408] Updated weights for policy 1, policy_version 51170 (0.0009) -[2023-10-17 02:19:43,556][62408] Updated weights for policy 1, policy_version 51180 (0.0009) -[2023-10-17 02:19:43,688][62373] Updated weights for policy 0, policy_version 51560 (0.0010) -[2023-10-17 02:19:43,919][62408] Updated weights for policy 1, policy_version 51190 (0.0008) -[2023-10-17 02:19:44,066][62373] Updated weights for policy 0, policy_version 51570 (0.0009) -[2023-10-17 02:19:44,287][62408] Updated weights for policy 1, policy_version 51200 (0.0007) -[2023-10-17 02:19:44,431][62373] Updated weights for policy 0, policy_version 51580 (0.0008) -[2023-10-17 02:19:47,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 105250816. Throughput: 0: 1775.7, 1: 1763.0. Samples: 26327240. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:19:47,215][61453] Avg episode reward: [(0, '9.020'), (1, '10.730')] -[2023-10-17 02:19:47,226][62252] Saving new best policy, reward=10.730! -[2023-10-17 02:19:48,130][62373] Updated weights for policy 0, policy_version 51590 (0.0007) -[2023-10-17 02:19:48,146][62408] Updated weights for policy 1, policy_version 51210 (0.0007) -[2023-10-17 02:19:48,501][62373] Updated weights for policy 0, policy_version 51600 (0.0009) -[2023-10-17 02:19:48,512][62408] Updated weights for policy 1, policy_version 51220 (0.0008) -[2023-10-17 02:19:48,867][62373] Updated weights for policy 0, policy_version 51610 (0.0008) -[2023-10-17 02:19:48,879][62408] Updated weights for policy 1, policy_version 51230 (0.0008) -[2023-10-17 02:19:52,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 105316352. Throughput: 0: 1774.9, 1: 1751.4. Samples: 26336826. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:19:52,214][61453] Avg episode reward: [(0, '9.520'), (1, '9.400')] -[2023-10-17 02:19:52,733][62408] Updated weights for policy 1, policy_version 51240 (0.0009) -[2023-10-17 02:19:52,792][62373] Updated weights for policy 0, policy_version 51620 (0.0009) -[2023-10-17 02:19:53,104][62408] Updated weights for policy 1, policy_version 51250 (0.0008) -[2023-10-17 02:19:53,172][62373] Updated weights for policy 0, policy_version 51630 (0.0007) -[2023-10-17 02:19:53,471][62408] Updated weights for policy 1, policy_version 51260 (0.0009) -[2023-10-17 02:19:53,545][62373] Updated weights for policy 0, policy_version 51640 (0.0008) -[2023-10-17 02:19:57,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 105381888. Throughput: 0: 1777.1, 1: 1747.8. Samples: 26358862. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:19:57,215][61453] Avg episode reward: [(0, '9.010'), (1, '9.840')] -[2023-10-17 02:19:57,302][62373] Updated weights for policy 0, policy_version 51650 (0.0008) -[2023-10-17 02:19:57,353][62408] Updated weights for policy 1, policy_version 51270 (0.0008) -[2023-10-17 02:19:57,676][62373] Updated weights for policy 0, policy_version 51660 (0.0008) -[2023-10-17 02:19:57,721][62408] Updated weights for policy 1, policy_version 51280 (0.0007) -[2023-10-17 02:19:58,056][62373] Updated weights for policy 0, policy_version 51670 (0.0008) -[2023-10-17 02:19:58,093][62408] Updated weights for policy 1, policy_version 51290 (0.0007) -[2023-10-17 02:19:58,426][62373] Updated weights for policy 0, policy_version 51680 (0.0009) -[2023-10-17 02:20:01,920][62408] Updated weights for policy 1, policy_version 51300 (0.0008) -[2023-10-17 02:20:02,058][62373] Updated weights for policy 0, policy_version 51690 (0.0008) -[2023-10-17 02:20:02,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 105447424. Throughput: 0: 1797.0, 1: 1768.6. Samples: 26380396. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:20:02,215][61453] Avg episode reward: [(0, '9.520'), (1, '9.320')] -[2023-10-17 02:20:02,283][62408] Updated weights for policy 1, policy_version 51310 (0.0008) -[2023-10-17 02:20:02,439][62373] Updated weights for policy 0, policy_version 51700 (0.0007) -[2023-10-17 02:20:02,649][62408] Updated weights for policy 1, policy_version 51320 (0.0007) -[2023-10-17 02:20:02,807][62373] Updated weights for policy 0, policy_version 51710 (0.0009) -[2023-10-17 02:20:06,497][62408] Updated weights for policy 1, policy_version 51330 (0.0007) -[2023-10-17 02:20:06,828][62373] Updated weights for policy 0, policy_version 51720 (0.0008) -[2023-10-17 02:20:06,866][62408] Updated weights for policy 1, policy_version 51340 (0.0008) -[2023-10-17 02:20:07,194][62373] Updated weights for policy 0, policy_version 51730 (0.0009) -[2023-10-17 02:20:07,214][61453] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 105512960. Throughput: 0: 1762.9, 1: 1734.8. Samples: 26390010. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:20:07,215][61453] Avg episode reward: [(0, '10.900'), (1, '9.880')] -[2023-10-17 02:20:07,233][62408] Updated weights for policy 1, policy_version 51350 (0.0008) -[2023-10-17 02:20:07,563][62373] Updated weights for policy 0, policy_version 51740 (0.0009) -[2023-10-17 02:20:07,591][62408] Updated weights for policy 1, policy_version 51360 (0.0009) -[2023-10-17 02:20:07,706][62094] Saving new best policy, reward=10.900! -[2023-10-17 02:20:11,429][62408] Updated weights for policy 1, policy_version 51370 (0.0011) -[2023-10-17 02:20:11,441][62373] Updated weights for policy 0, policy_version 51750 (0.0008) -[2023-10-17 02:20:11,794][62408] Updated weights for policy 1, policy_version 51380 (0.0010) -[2023-10-17 02:20:11,815][62373] Updated weights for policy 0, policy_version 51760 (0.0007) -[2023-10-17 02:20:12,153][62408] Updated weights for policy 1, policy_version 51390 (0.0008) -[2023-10-17 02:20:12,180][62373] Updated weights for policy 0, policy_version 51770 (0.0008) -[2023-10-17 02:20:12,214][61453] Fps is (10 sec: 13107.6, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 105578496. Throughput: 0: 1783.8, 1: 1767.3. Samples: 26411928. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:20:12,214][61453] Avg episode reward: [(0, '9.950'), (1, '10.100')] -[2023-10-17 02:20:15,885][62373] Updated weights for policy 0, policy_version 51780 (0.0007) -[2023-10-17 02:20:15,996][62408] Updated weights for policy 1, policy_version 51400 (0.0007) -[2023-10-17 02:20:16,258][62373] Updated weights for policy 0, policy_version 51790 (0.0008) -[2023-10-17 02:20:16,358][62408] Updated weights for policy 1, policy_version 51410 (0.0007) -[2023-10-17 02:20:16,630][62373] Updated weights for policy 0, policy_version 51800 (0.0009) -[2023-10-17 02:20:16,726][62408] Updated weights for policy 1, policy_version 51420 (0.0008) -[2023-10-17 02:20:17,214][61453] Fps is (10 sec: 19660.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 105709568. Throughput: 0: 1760.9, 1: 1741.5. Samples: 26431486. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:20:17,215][61453] Avg episode reward: [(0, '9.670'), (1, '9.300')] -[2023-10-17 02:20:20,263][62373] Updated weights for policy 0, policy_version 51810 (0.0009) -[2023-10-17 02:20:20,511][62408] Updated weights for policy 1, policy_version 51430 (0.0008) -[2023-10-17 02:20:20,628][62373] Updated weights for policy 0, policy_version 51820 (0.0007) -[2023-10-17 02:20:20,877][62408] Updated weights for policy 1, policy_version 51440 (0.0011) -[2023-10-17 02:20:20,990][62373] Updated weights for policy 0, policy_version 51830 (0.0008) -[2023-10-17 02:20:21,243][62408] Updated weights for policy 1, policy_version 51450 (0.0007) -[2023-10-17 02:20:21,362][62373] Updated weights for policy 0, policy_version 51840 (0.0007) -[2023-10-17 02:20:22,214][61453] Fps is (10 sec: 19660.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 105775104. Throughput: 0: 1784.8, 1: 1771.0. Samples: 26444142. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:20:22,215][61453] Avg episode reward: [(0, '9.930'), (1, '9.240')] -[2023-10-17 02:20:25,118][62408] Updated weights for policy 1, policy_version 51460 (0.0008) -[2023-10-17 02:20:25,185][62373] Updated weights for policy 0, policy_version 51850 (0.0007) -[2023-10-17 02:20:25,487][62408] Updated weights for policy 1, policy_version 51470 (0.0009) -[2023-10-17 02:20:25,561][62373] Updated weights for policy 0, policy_version 51860 (0.0009) -[2023-10-17 02:20:25,856][62408] Updated weights for policy 1, policy_version 51480 (0.0009) -[2023-10-17 02:20:25,922][62373] Updated weights for policy 0, policy_version 51870 (0.0008) -[2023-10-17 02:20:27,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 105840640. Throughput: 0: 1765.4, 1: 1753.1. Samples: 26463716. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:20:27,215][61453] Avg episode reward: [(0, '9.620'), (1, '9.230')] -[2023-10-17 02:20:29,503][62408] Updated weights for policy 1, policy_version 51490 (0.0008) -[2023-10-17 02:20:29,769][62373] Updated weights for policy 0, policy_version 51880 (0.0008) -[2023-10-17 02:20:29,879][62408] Updated weights for policy 1, policy_version 51500 (0.0008) -[2023-10-17 02:20:30,143][62373] Updated weights for policy 0, policy_version 51890 (0.0007) -[2023-10-17 02:20:30,252][62408] Updated weights for policy 1, policy_version 51510 (0.0009) -[2023-10-17 02:20:30,507][62373] Updated weights for policy 0, policy_version 51900 (0.0007) -[2023-10-17 02:20:30,612][62408] Updated weights for policy 1, policy_version 51520 (0.0007) -[2023-10-17 02:20:32,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 105906176. Throughput: 0: 1762.5, 1: 1752.8. Samples: 26485430. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:20:32,215][61453] Avg episode reward: [(0, '10.190'), (1, '9.280')] -[2023-10-17 02:20:34,325][62373] Updated weights for policy 0, policy_version 51910 (0.0009) -[2023-10-17 02:20:34,415][62408] Updated weights for policy 1, policy_version 51530 (0.0009) -[2023-10-17 02:20:34,702][62373] Updated weights for policy 0, policy_version 51920 (0.0007) -[2023-10-17 02:20:34,783][62408] Updated weights for policy 1, policy_version 51540 (0.0008) -[2023-10-17 02:20:35,076][62373] Updated weights for policy 0, policy_version 51930 (0.0007) -[2023-10-17 02:20:35,140][62408] Updated weights for policy 1, policy_version 51550 (0.0008) -[2023-10-17 02:20:37,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 105971712. Throughput: 0: 1772.4, 1: 1765.6. Samples: 26496034. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-17 02:20:37,215][61453] Avg episode reward: [(0, '9.890'), (1, '9.220')] -[2023-10-17 02:20:39,048][62408] Updated weights for policy 1, policy_version 51560 (0.0007) -[2023-10-17 02:20:39,106][62373] Updated weights for policy 0, policy_version 51940 (0.0009) -[2023-10-17 02:20:39,423][62408] Updated weights for policy 1, policy_version 51570 (0.0009) -[2023-10-17 02:20:39,469][62373] Updated weights for policy 0, policy_version 51950 (0.0009) -[2023-10-17 02:20:39,787][62408] Updated weights for policy 1, policy_version 51580 (0.0008) -[2023-10-17 02:20:39,849][62373] Updated weights for policy 0, policy_version 51960 (0.0009) -[2023-10-17 02:20:42,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 106037248. Throughput: 0: 1752.4, 1: 1752.8. Samples: 26516592. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-17 02:20:42,215][61453] Avg episode reward: [(0, '9.700'), (1, '8.780')] -[2023-10-17 02:20:43,557][62408] Updated weights for policy 1, policy_version 51590 (0.0009) -[2023-10-17 02:20:43,692][62373] Updated weights for policy 0, policy_version 51970 (0.0008) -[2023-10-17 02:20:43,922][62408] Updated weights for policy 1, policy_version 51600 (0.0008) -[2023-10-17 02:20:44,116][62373] Updated weights for policy 0, policy_version 51980 (0.0008) -[2023-10-17 02:20:44,290][62408] Updated weights for policy 1, policy_version 51610 (0.0009) -[2023-10-17 02:20:44,485][62373] Updated weights for policy 0, policy_version 51990 (0.0008) -[2023-10-17 02:20:44,847][62373] Updated weights for policy 0, policy_version 52000 (0.0008) -[2023-10-17 02:20:47,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 106102784. Throughput: 0: 1758.2, 1: 1759.5. Samples: 26538694. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-17 02:20:47,214][61453] Avg episode reward: [(0, '9.860'), (1, '8.800')] -[2023-10-17 02:20:48,248][62408] Updated weights for policy 1, policy_version 51620 (0.0008) -[2023-10-17 02:20:48,537][62373] Updated weights for policy 0, policy_version 52010 (0.0010) -[2023-10-17 02:20:48,607][62408] Updated weights for policy 1, policy_version 51630 (0.0007) -[2023-10-17 02:20:48,901][62373] Updated weights for policy 0, policy_version 52020 (0.0008) -[2023-10-17 02:20:48,972][62408] Updated weights for policy 1, policy_version 51640 (0.0009) -[2023-10-17 02:20:49,268][62373] Updated weights for policy 0, policy_version 52030 (0.0008) -[2023-10-17 02:20:52,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 106168320. Throughput: 0: 1755.6, 1: 1759.7. Samples: 26548198. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-17 02:20:52,215][61453] Avg episode reward: [(0, '10.020'), (1, '8.970')] -[2023-10-17 02:20:52,780][62408] Updated weights for policy 1, policy_version 51650 (0.0009) -[2023-10-17 02:20:53,144][62408] Updated weights for policy 1, policy_version 51660 (0.0008) -[2023-10-17 02:20:53,247][62373] Updated weights for policy 0, policy_version 52040 (0.0009) -[2023-10-17 02:20:53,519][62408] Updated weights for policy 1, policy_version 51670 (0.0007) -[2023-10-17 02:20:53,611][62373] Updated weights for policy 0, policy_version 52050 (0.0010) -[2023-10-17 02:20:53,886][62408] Updated weights for policy 1, policy_version 51680 (0.0007) -[2023-10-17 02:20:53,981][62373] Updated weights for policy 0, policy_version 52060 (0.0008) -[2023-10-17 02:20:57,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 106233856. Throughput: 0: 1760.4, 1: 1761.2. Samples: 26570400. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-17 02:20:57,214][61453] Avg episode reward: [(0, '10.610'), (1, '9.310')] -[2023-10-17 02:20:57,649][62373] Updated weights for policy 0, policy_version 52070 (0.0009) -[2023-10-17 02:20:57,811][62408] Updated weights for policy 1, policy_version 51690 (0.0008) -[2023-10-17 02:20:58,014][62373] Updated weights for policy 0, policy_version 52080 (0.0009) -[2023-10-17 02:20:58,169][62408] Updated weights for policy 1, policy_version 51700 (0.0008) -[2023-10-17 02:20:58,383][62373] Updated weights for policy 0, policy_version 52090 (0.0008) -[2023-10-17 02:20:58,541][62408] Updated weights for policy 1, policy_version 51710 (0.0009) -[2023-10-17 02:21:02,014][62373] Updated weights for policy 0, policy_version 52100 (0.0010) -[2023-10-17 02:21:02,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 106299392. Throughput: 0: 1788.2, 1: 1787.5. Samples: 26592390. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-17 02:21:02,215][61453] Avg episode reward: [(0, '10.290'), (1, '9.550')] -[2023-10-17 02:21:02,384][62373] Updated weights for policy 0, policy_version 52110 (0.0008) -[2023-10-17 02:21:02,579][62408] Updated weights for policy 1, policy_version 51720 (0.0008) -[2023-10-17 02:21:02,738][62373] Updated weights for policy 0, policy_version 52120 (0.0007) -[2023-10-17 02:21:02,943][62408] Updated weights for policy 1, policy_version 51730 (0.0008) -[2023-10-17 02:21:03,308][62408] Updated weights for policy 1, policy_version 51740 (0.0009) -[2023-10-17 02:21:06,645][62373] Updated weights for policy 0, policy_version 52130 (0.0008) -[2023-10-17 02:21:07,019][62373] Updated weights for policy 0, policy_version 52140 (0.0010) -[2023-10-17 02:21:07,168][62408] Updated weights for policy 1, policy_version 51750 (0.0009) -[2023-10-17 02:21:07,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 106364928. Throughput: 0: 1751.9, 1: 1755.0. Samples: 26601954. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-17 02:21:07,214][61453] Avg episode reward: [(0, '10.170'), (1, '9.750')] -[2023-10-17 02:21:07,384][62373] Updated weights for policy 0, policy_version 52150 (0.0008) -[2023-10-17 02:21:07,531][62408] Updated weights for policy 1, policy_version 51760 (0.0008) -[2023-10-17 02:21:07,758][62373] Updated weights for policy 0, policy_version 52160 (0.0007) -[2023-10-17 02:21:07,888][62408] Updated weights for policy 1, policy_version 51770 (0.0009) -[2023-10-17 02:21:11,653][62408] Updated weights for policy 1, policy_version 51780 (0.0007) -[2023-10-17 02:21:11,682][62373] Updated weights for policy 0, policy_version 52170 (0.0008) -[2023-10-17 02:21:12,019][62408] Updated weights for policy 1, policy_version 51790 (0.0009) -[2023-10-17 02:21:12,047][62373] Updated weights for policy 0, policy_version 52180 (0.0008) -[2023-10-17 02:21:12,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 106430464. Throughput: 0: 1774.4, 1: 1781.8. Samples: 26623746. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-17 02:21:12,214][61453] Avg episode reward: [(0, '9.910'), (1, '9.910')] -[2023-10-17 02:21:12,392][62408] Updated weights for policy 1, policy_version 51800 (0.0010) -[2023-10-17 02:21:12,423][62373] Updated weights for policy 0, policy_version 52190 (0.0011) -[2023-10-17 02:21:16,391][62373] Updated weights for policy 0, policy_version 52200 (0.0008) -[2023-10-17 02:21:16,415][62408] Updated weights for policy 1, policy_version 51810 (0.0010) -[2023-10-17 02:21:16,759][62373] Updated weights for policy 0, policy_version 52210 (0.0008) -[2023-10-17 02:21:16,776][62408] Updated weights for policy 1, policy_version 51820 (0.0008) -[2023-10-17 02:21:17,119][62373] Updated weights for policy 0, policy_version 52220 (0.0007) -[2023-10-17 02:21:17,146][62408] Updated weights for policy 1, policy_version 51830 (0.0010) -[2023-10-17 02:21:17,214][61453] Fps is (10 sec: 13107.2, 60 sec: 13107.3, 300 sec: 13995.8). Total num frames: 106496000. Throughput: 0: 1755.5, 1: 1765.8. Samples: 26643888. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:21:17,214][61453] Avg episode reward: [(0, '10.250'), (1, '10.490')] -[2023-10-17 02:21:17,510][62408] Updated weights for policy 1, policy_version 51840 (0.0008) -[2023-10-17 02:21:20,936][62373] Updated weights for policy 0, policy_version 52230 (0.0009) -[2023-10-17 02:21:21,274][62408] Updated weights for policy 1, policy_version 51850 (0.0008) -[2023-10-17 02:21:21,291][62373] Updated weights for policy 0, policy_version 52240 (0.0007) -[2023-10-17 02:21:21,637][62408] Updated weights for policy 1, policy_version 51860 (0.0007) -[2023-10-17 02:21:21,657][62373] Updated weights for policy 0, policy_version 52250 (0.0008) -[2023-10-17 02:21:22,008][62408] Updated weights for policy 1, policy_version 51870 (0.0007) -[2023-10-17 02:21:22,214][61453] Fps is (10 sec: 19660.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 106627072. Throughput: 0: 1773.3, 1: 1765.6. Samples: 26655286. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:21:22,215][61453] Avg episode reward: [(0, '10.410'), (1, '10.750')] -[2023-10-17 02:21:22,217][62252] Saving new best policy, reward=10.750! -[2023-10-17 02:21:25,545][62373] Updated weights for policy 0, policy_version 52260 (0.0007) -[2023-10-17 02:21:25,799][62408] Updated weights for policy 1, policy_version 51880 (0.0008) -[2023-10-17 02:21:25,912][62373] Updated weights for policy 0, policy_version 52270 (0.0008) -[2023-10-17 02:21:26,157][62408] Updated weights for policy 1, policy_version 51890 (0.0009) -[2023-10-17 02:21:26,274][62373] Updated weights for policy 0, policy_version 52280 (0.0007) -[2023-10-17 02:21:26,523][62408] Updated weights for policy 1, policy_version 51900 (0.0008) -[2023-10-17 02:21:27,214][61453] Fps is (10 sec: 19660.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 106692608. Throughput: 0: 1774.5, 1: 1768.1. Samples: 26676012. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:21:27,215][61453] Avg episode reward: [(0, '10.490'), (1, '10.700')] -[2023-10-17 02:21:30,131][62373] Updated weights for policy 0, policy_version 52290 (0.0009) -[2023-10-17 02:21:30,275][62408] Updated weights for policy 1, policy_version 51910 (0.0009) -[2023-10-17 02:21:30,536][62373] Updated weights for policy 0, policy_version 52300 (0.0008) -[2023-10-17 02:21:30,640][62408] Updated weights for policy 1, policy_version 51920 (0.0009) -[2023-10-17 02:21:30,902][62373] Updated weights for policy 0, policy_version 52310 (0.0009) -[2023-10-17 02:21:31,005][62408] Updated weights for policy 1, policy_version 51930 (0.0007) -[2023-10-17 02:21:31,265][62373] Updated weights for policy 0, policy_version 52320 (0.0009) -[2023-10-17 02:21:32,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 106758144. Throughput: 0: 1755.5, 1: 1751.5. Samples: 26696512. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:21:32,215][61453] Avg episode reward: [(0, '10.100'), (1, '11.380')] -[2023-10-17 02:21:32,228][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000051936_53182464.pth... -[2023-10-17 02:21:32,228][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000052320_53575680.pth... -[2023-10-17 02:21:32,267][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000050656_51871744.pth -[2023-10-17 02:21:32,269][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000050272_51478528.pth -[2023-10-17 02:21:32,273][62252] Saving new best policy, reward=11.380! -[2023-10-17 02:21:34,733][62408] Updated weights for policy 1, policy_version 51940 (0.0008) -[2023-10-17 02:21:34,948][62373] Updated weights for policy 0, policy_version 52330 (0.0007) -[2023-10-17 02:21:35,103][62408] Updated weights for policy 1, policy_version 51950 (0.0009) -[2023-10-17 02:21:35,321][62373] Updated weights for policy 0, policy_version 52340 (0.0008) -[2023-10-17 02:21:35,477][62408] Updated weights for policy 1, policy_version 51960 (0.0008) -[2023-10-17 02:21:35,687][62373] Updated weights for policy 0, policy_version 52350 (0.0009) -[2023-10-17 02:21:37,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 106823680. Throughput: 0: 1780.0, 1: 1775.2. Samples: 26708178. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:21:37,214][61453] Avg episode reward: [(0, '9.790'), (1, '10.380')] -[2023-10-17 02:21:39,441][62408] Updated weights for policy 1, policy_version 51970 (0.0007) -[2023-10-17 02:21:39,531][62373] Updated weights for policy 0, policy_version 52360 (0.0009) -[2023-10-17 02:21:39,810][62408] Updated weights for policy 1, policy_version 51980 (0.0007) -[2023-10-17 02:21:39,907][62373] Updated weights for policy 0, policy_version 52370 (0.0008) -[2023-10-17 02:21:40,180][62408] Updated weights for policy 1, policy_version 51990 (0.0008) -[2023-10-17 02:21:40,272][62373] Updated weights for policy 0, policy_version 52380 (0.0007) -[2023-10-17 02:21:40,549][62408] Updated weights for policy 1, policy_version 52000 (0.0008) -[2023-10-17 02:21:42,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 106889216. Throughput: 0: 1755.2, 1: 1742.7. Samples: 26727802. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:21:42,214][61453] Avg episode reward: [(0, '9.740'), (1, '10.370')] -[2023-10-17 02:21:44,074][62373] Updated weights for policy 0, policy_version 52390 (0.0009) -[2023-10-17 02:21:44,438][62373] Updated weights for policy 0, policy_version 52400 (0.0008) -[2023-10-17 02:21:44,504][62408] Updated weights for policy 1, policy_version 52010 (0.0009) -[2023-10-17 02:21:44,816][62373] Updated weights for policy 0, policy_version 52410 (0.0009) -[2023-10-17 02:21:44,879][62408] Updated weights for policy 1, policy_version 52020 (0.0009) -[2023-10-17 02:21:45,252][62408] Updated weights for policy 1, policy_version 52030 (0.0008) -[2023-10-17 02:21:47,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 106954752. Throughput: 0: 1755.8, 1: 1745.4. Samples: 26749944. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:21:47,215][61453] Avg episode reward: [(0, '9.540'), (1, '10.350')] -[2023-10-17 02:21:48,700][62373] Updated weights for policy 0, policy_version 52420 (0.0008) -[2023-10-17 02:21:49,059][62373] Updated weights for policy 0, policy_version 52430 (0.0009) -[2023-10-17 02:21:49,219][62408] Updated weights for policy 1, policy_version 52040 (0.0008) -[2023-10-17 02:21:49,427][62373] Updated weights for policy 0, policy_version 52440 (0.0007) -[2023-10-17 02:21:49,598][62408] Updated weights for policy 1, policy_version 52050 (0.0008) -[2023-10-17 02:21:49,967][62408] Updated weights for policy 1, policy_version 52060 (0.0008) -[2023-10-17 02:21:52,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 107020288. Throughput: 0: 1755.1, 1: 1748.4. Samples: 26759612. Policy #0 lag: (min: 29.0, avg: 52.6, max: 56.0) -[2023-10-17 02:21:52,214][61453] Avg episode reward: [(0, '9.370'), (1, '10.760')] -[2023-10-17 02:21:53,168][62373] Updated weights for policy 0, policy_version 52450 (0.0007) -[2023-10-17 02:21:53,536][62373] Updated weights for policy 0, policy_version 52460 (0.0009) -[2023-10-17 02:21:53,694][62408] Updated weights for policy 1, policy_version 52070 (0.0007) -[2023-10-17 02:21:53,907][62373] Updated weights for policy 0, policy_version 52470 (0.0007) -[2023-10-17 02:21:54,049][62408] Updated weights for policy 1, policy_version 52080 (0.0009) -[2023-10-17 02:21:54,280][62373] Updated weights for policy 0, policy_version 52480 (0.0009) -[2023-10-17 02:21:54,424][62408] Updated weights for policy 1, policy_version 52090 (0.0009) -[2023-10-17 02:21:57,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 107085824. Throughput: 0: 1762.9, 1: 1738.9. Samples: 26781330. Policy #0 lag: (min: 29.0, avg: 52.6, max: 56.0) -[2023-10-17 02:21:57,215][61453] Avg episode reward: [(0, '9.270'), (1, '10.770')] -[2023-10-17 02:21:58,062][62373] Updated weights for policy 0, policy_version 52490 (0.0007) -[2023-10-17 02:21:58,273][62408] Updated weights for policy 1, policy_version 52100 (0.0009) -[2023-10-17 02:21:58,424][62373] Updated weights for policy 0, policy_version 52500 (0.0008) -[2023-10-17 02:21:58,642][62408] Updated weights for policy 1, policy_version 52110 (0.0009) -[2023-10-17 02:21:58,783][62373] Updated weights for policy 0, policy_version 52510 (0.0008) -[2023-10-17 02:21:59,005][62408] Updated weights for policy 1, policy_version 52120 (0.0009) -[2023-10-17 02:22:02,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 107151360. Throughput: 0: 1788.0, 1: 1758.6. Samples: 26803486. Policy #0 lag: (min: 29.0, avg: 52.6, max: 56.0) -[2023-10-17 02:22:02,215][61453] Avg episode reward: [(0, '9.170'), (1, '9.600')] -[2023-10-17 02:22:02,636][62373] Updated weights for policy 0, policy_version 52520 (0.0009) -[2023-10-17 02:22:02,831][62408] Updated weights for policy 1, policy_version 52130 (0.0010) -[2023-10-17 02:22:03,002][62373] Updated weights for policy 0, policy_version 52530 (0.0007) -[2023-10-17 02:22:03,204][62408] Updated weights for policy 1, policy_version 52140 (0.0007) -[2023-10-17 02:22:03,372][62373] Updated weights for policy 0, policy_version 52540 (0.0007) -[2023-10-17 02:22:03,573][62408] Updated weights for policy 1, policy_version 52150 (0.0007) -[2023-10-17 02:22:03,937][62408] Updated weights for policy 1, policy_version 52160 (0.0007) -[2023-10-17 02:22:07,063][62373] Updated weights for policy 0, policy_version 52550 (0.0010) -[2023-10-17 02:22:07,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 107216896. Throughput: 0: 1761.8, 1: 1748.1. Samples: 26813234. Policy #0 lag: (min: 29.0, avg: 52.6, max: 56.0) -[2023-10-17 02:22:07,214][61453] Avg episode reward: [(0, '9.900'), (1, '9.840')] -[2023-10-17 02:22:07,438][62373] Updated weights for policy 0, policy_version 52560 (0.0008) -[2023-10-17 02:22:07,804][62373] Updated weights for policy 0, policy_version 52570 (0.0008) -[2023-10-17 02:22:07,930][62408] Updated weights for policy 1, policy_version 52170 (0.0009) -[2023-10-17 02:22:08,304][62408] Updated weights for policy 1, policy_version 52180 (0.0009) -[2023-10-17 02:22:08,674][62408] Updated weights for policy 1, policy_version 52190 (0.0010) -[2023-10-17 02:22:11,454][62373] Updated weights for policy 0, policy_version 52580 (0.0009) -[2023-10-17 02:22:11,831][62373] Updated weights for policy 0, policy_version 52590 (0.0009) -[2023-10-17 02:22:12,195][62373] Updated weights for policy 0, policy_version 52600 (0.0007) -[2023-10-17 02:22:12,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 107282432. Throughput: 0: 1787.2, 1: 1754.9. Samples: 26835408. Policy #0 lag: (min: 29.0, avg: 52.6, max: 56.0) -[2023-10-17 02:22:12,215][61453] Avg episode reward: [(0, '10.040'), (1, '10.250')] -[2023-10-17 02:22:12,480][62408] Updated weights for policy 1, policy_version 52200 (0.0008) -[2023-10-17 02:22:12,841][62408] Updated weights for policy 1, policy_version 52210 (0.0010) -[2023-10-17 02:22:13,215][62408] Updated weights for policy 1, policy_version 52220 (0.0008) -[2023-10-17 02:22:16,120][62373] Updated weights for policy 0, policy_version 52610 (0.0007) -[2023-10-17 02:22:16,533][62373] Updated weights for policy 0, policy_version 52620 (0.0008) -[2023-10-17 02:22:16,898][62373] Updated weights for policy 0, policy_version 52630 (0.0008) -[2023-10-17 02:22:17,143][62408] Updated weights for policy 1, policy_version 52230 (0.0008) -[2023-10-17 02:22:17,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 107347968. Throughput: 0: 1780.8, 1: 1767.3. Samples: 26856178. Policy #0 lag: (min: 29.0, avg: 52.6, max: 56.0) -[2023-10-17 02:22:17,215][61453] Avg episode reward: [(0, '10.150'), (1, '10.070')] -[2023-10-17 02:22:17,270][62373] Updated weights for policy 0, policy_version 52640 (0.0008) -[2023-10-17 02:22:17,519][62408] Updated weights for policy 1, policy_version 52240 (0.0009) -[2023-10-17 02:22:17,888][62408] Updated weights for policy 1, policy_version 52250 (0.0008) -[2023-10-17 02:22:20,979][62373] Updated weights for policy 0, policy_version 52650 (0.0008) -[2023-10-17 02:22:21,344][62373] Updated weights for policy 0, policy_version 52660 (0.0010) -[2023-10-17 02:22:21,621][62408] Updated weights for policy 1, policy_version 52260 (0.0009) -[2023-10-17 02:22:21,718][62373] Updated weights for policy 0, policy_version 52670 (0.0007) -[2023-10-17 02:22:22,002][62408] Updated weights for policy 1, policy_version 52270 (0.0008) -[2023-10-17 02:22:22,214][61453] Fps is (10 sec: 16384.3, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 107446272. Throughput: 0: 1781.8, 1: 1744.1. Samples: 26866844. Policy #0 lag: (min: 29.0, avg: 52.6, max: 56.0) -[2023-10-17 02:22:22,214][61453] Avg episode reward: [(0, '10.180'), (1, '9.880')] -[2023-10-17 02:22:22,358][62408] Updated weights for policy 1, policy_version 52280 (0.0007) -[2023-10-17 02:22:25,382][62373] Updated weights for policy 0, policy_version 52680 (0.0009) -[2023-10-17 02:22:25,748][62373] Updated weights for policy 0, policy_version 52690 (0.0009) -[2023-10-17 02:22:26,125][62373] Updated weights for policy 0, policy_version 52700 (0.0007) -[2023-10-17 02:22:26,236][62408] Updated weights for policy 1, policy_version 52290 (0.0010) -[2023-10-17 02:22:26,610][62408] Updated weights for policy 1, policy_version 52300 (0.0009) -[2023-10-17 02:22:26,979][62408] Updated weights for policy 1, policy_version 52310 (0.0008) -[2023-10-17 02:22:27,214][61453] Fps is (10 sec: 16384.1, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 107511808. Throughput: 0: 1792.1, 1: 1773.0. Samples: 26888234. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:22:27,215][61453] Avg episode reward: [(0, '9.990'), (1, '9.600')] -[2023-10-17 02:22:27,350][62408] Updated weights for policy 1, policy_version 52320 (0.0009) -[2023-10-17 02:22:29,910][62373] Updated weights for policy 0, policy_version 52710 (0.0007) -[2023-10-17 02:22:30,286][62373] Updated weights for policy 0, policy_version 52720 (0.0007) -[2023-10-17 02:22:30,661][62373] Updated weights for policy 0, policy_version 52730 (0.0008) -[2023-10-17 02:22:31,356][62408] Updated weights for policy 1, policy_version 52330 (0.0011) -[2023-10-17 02:22:31,715][62408] Updated weights for policy 1, policy_version 52340 (0.0010) -[2023-10-17 02:22:32,089][62408] Updated weights for policy 1, policy_version 52350 (0.0011) -[2023-10-17 02:22:32,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 107610112. Throughput: 0: 1784.9, 1: 1747.3. Samples: 26908892. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:22:32,214][61453] Avg episode reward: [(0, '9.900'), (1, '10.420')] -[2023-10-17 02:22:34,410][62373] Updated weights for policy 0, policy_version 52740 (0.0010) -[2023-10-17 02:22:34,788][62373] Updated weights for policy 0, policy_version 52750 (0.0010) -[2023-10-17 02:22:35,164][62373] Updated weights for policy 0, policy_version 52760 (0.0007) -[2023-10-17 02:22:36,074][62408] Updated weights for policy 1, policy_version 52360 (0.0009) -[2023-10-17 02:22:36,438][62408] Updated weights for policy 1, policy_version 52370 (0.0010) -[2023-10-17 02:22:36,810][62408] Updated weights for policy 1, policy_version 52380 (0.0011) -[2023-10-17 02:22:37,214][61453] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 107675648. Throughput: 0: 1800.0, 1: 1765.0. Samples: 26920040. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:22:37,214][61453] Avg episode reward: [(0, '10.120'), (1, '9.790')] -[2023-10-17 02:22:38,770][62373] Updated weights for policy 0, policy_version 52770 (0.0007) -[2023-10-17 02:22:39,145][62373] Updated weights for policy 0, policy_version 52780 (0.0008) -[2023-10-17 02:22:39,509][62373] Updated weights for policy 0, policy_version 52790 (0.0008) -[2023-10-17 02:22:39,878][62373] Updated weights for policy 0, policy_version 52800 (0.0008) -[2023-10-17 02:22:40,610][62408] Updated weights for policy 1, policy_version 52390 (0.0008) -[2023-10-17 02:22:40,979][62408] Updated weights for policy 1, policy_version 52400 (0.0008) -[2023-10-17 02:22:41,350][62408] Updated weights for policy 1, policy_version 52410 (0.0009) -[2023-10-17 02:22:42,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 107741184. Throughput: 0: 1791.0, 1: 1762.0. Samples: 26941218. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:22:42,215][61453] Avg episode reward: [(0, '10.070'), (1, '10.010')] -[2023-10-17 02:22:43,638][62373] Updated weights for policy 0, policy_version 52810 (0.0011) -[2023-10-17 02:22:44,011][62373] Updated weights for policy 0, policy_version 52820 (0.0009) -[2023-10-17 02:22:44,375][62373] Updated weights for policy 0, policy_version 52830 (0.0010) -[2023-10-17 02:22:44,936][62408] Updated weights for policy 1, policy_version 52420 (0.0008) -[2023-10-17 02:22:45,305][62408] Updated weights for policy 1, policy_version 52430 (0.0007) -[2023-10-17 02:22:45,669][62408] Updated weights for policy 1, policy_version 52440 (0.0007) -[2023-10-17 02:22:47,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 107806720. Throughput: 0: 1791.2, 1: 1750.1. Samples: 26962846. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:22:47,215][61453] Avg episode reward: [(0, '9.550'), (1, '9.280')] -[2023-10-17 02:22:48,260][62373] Updated weights for policy 0, policy_version 52840 (0.0007) -[2023-10-17 02:22:48,636][62373] Updated weights for policy 0, policy_version 52850 (0.0008) -[2023-10-17 02:22:49,003][62373] Updated weights for policy 0, policy_version 52860 (0.0010) -[2023-10-17 02:22:49,421][62408] Updated weights for policy 1, policy_version 52450 (0.0009) -[2023-10-17 02:22:49,797][62408] Updated weights for policy 1, policy_version 52460 (0.0008) -[2023-10-17 02:22:50,162][62408] Updated weights for policy 1, policy_version 52470 (0.0007) -[2023-10-17 02:22:50,532][62408] Updated weights for policy 1, policy_version 52480 (0.0007) -[2023-10-17 02:22:52,214][61453] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 107872256. Throughput: 0: 1791.6, 1: 1763.9. Samples: 26973232. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:22:52,214][61453] Avg episode reward: [(0, '9.400'), (1, '8.760')] -[2023-10-17 02:22:52,761][62373] Updated weights for policy 0, policy_version 52870 (0.0008) -[2023-10-17 02:22:53,136][62373] Updated weights for policy 0, policy_version 52880 (0.0009) -[2023-10-17 02:22:53,504][62373] Updated weights for policy 0, policy_version 52890 (0.0009) -[2023-10-17 02:22:54,292][62408] Updated weights for policy 1, policy_version 52490 (0.0007) -[2023-10-17 02:22:54,667][62408] Updated weights for policy 1, policy_version 52500 (0.0007) -[2023-10-17 02:22:55,039][62408] Updated weights for policy 1, policy_version 52510 (0.0007) -[2023-10-17 02:22:57,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 107937792. Throughput: 0: 1785.9, 1: 1751.6. Samples: 26994598. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:22:57,215][61453] Avg episode reward: [(0, '9.280'), (1, '8.650')] -[2023-10-17 02:22:57,375][62373] Updated weights for policy 0, policy_version 52900 (0.0009) -[2023-10-17 02:22:57,738][62373] Updated weights for policy 0, policy_version 52910 (0.0009) -[2023-10-17 02:22:58,117][62373] Updated weights for policy 0, policy_version 52920 (0.0008) -[2023-10-17 02:22:58,869][62408] Updated weights for policy 1, policy_version 52520 (0.0008) -[2023-10-17 02:22:59,233][62408] Updated weights for policy 1, policy_version 52530 (0.0007) -[2023-10-17 02:22:59,598][62408] Updated weights for policy 1, policy_version 52540 (0.0007) -[2023-10-17 02:23:02,007][62373] Updated weights for policy 0, policy_version 52930 (0.0010) -[2023-10-17 02:23:02,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 108003328. Throughput: 0: 1805.8, 1: 1758.3. Samples: 27016564. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:23:02,215][61453] Avg episode reward: [(0, '9.280'), (1, '8.110')] -[2023-10-17 02:23:02,399][62373] Updated weights for policy 0, policy_version 52940 (0.0009) -[2023-10-17 02:23:02,766][62373] Updated weights for policy 0, policy_version 52950 (0.0009) -[2023-10-17 02:23:03,150][62373] Updated weights for policy 0, policy_version 52960 (0.0009) -[2023-10-17 02:23:03,358][62408] Updated weights for policy 1, policy_version 52550 (0.0008) -[2023-10-17 02:23:03,713][62408] Updated weights for policy 1, policy_version 52560 (0.0009) -[2023-10-17 02:23:04,081][62408] Updated weights for policy 1, policy_version 52570 (0.0008) -[2023-10-17 02:23:06,842][62373] Updated weights for policy 0, policy_version 52970 (0.0008) -[2023-10-17 02:23:07,202][62373] Updated weights for policy 0, policy_version 52980 (0.0008) -[2023-10-17 02:23:07,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 108068864. Throughput: 0: 1784.7, 1: 1760.6. Samples: 27026382. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:23:07,215][61453] Avg episode reward: [(0, '9.230'), (1, '7.960')] -[2023-10-17 02:23:07,574][62373] Updated weights for policy 0, policy_version 52990 (0.0008) -[2023-10-17 02:23:07,983][62408] Updated weights for policy 1, policy_version 52580 (0.0009) -[2023-10-17 02:23:08,356][62408] Updated weights for policy 1, policy_version 52590 (0.0009) -[2023-10-17 02:23:08,737][62408] Updated weights for policy 1, policy_version 52600 (0.0010) -[2023-10-17 02:23:11,433][62373] Updated weights for policy 0, policy_version 53000 (0.0007) -[2023-10-17 02:23:11,802][62373] Updated weights for policy 0, policy_version 53010 (0.0007) -[2023-10-17 02:23:12,169][62373] Updated weights for policy 0, policy_version 53020 (0.0007) -[2023-10-17 02:23:12,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 108134400. Throughput: 0: 1801.1, 1: 1756.2. Samples: 27048312. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:23:12,214][61453] Avg episode reward: [(0, '9.160'), (1, '8.100')] -[2023-10-17 02:23:12,649][62408] Updated weights for policy 1, policy_version 52610 (0.0008) -[2023-10-17 02:23:13,021][62408] Updated weights for policy 1, policy_version 52620 (0.0009) -[2023-10-17 02:23:13,379][62408] Updated weights for policy 1, policy_version 52630 (0.0008) -[2023-10-17 02:23:13,745][62408] Updated weights for policy 1, policy_version 52640 (0.0011) -[2023-10-17 02:23:15,857][62373] Updated weights for policy 0, policy_version 53030 (0.0008) -[2023-10-17 02:23:16,222][62373] Updated weights for policy 0, policy_version 53040 (0.0009) -[2023-10-17 02:23:16,587][62373] Updated weights for policy 0, policy_version 53050 (0.0011) -[2023-10-17 02:23:17,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14106.9). Total num frames: 108232704. Throughput: 0: 1772.8, 1: 1783.3. Samples: 27068918. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:23:17,215][61453] Avg episode reward: [(0, '9.030'), (1, '8.410')] -[2023-10-17 02:23:17,491][62408] Updated weights for policy 1, policy_version 52650 (0.0007) -[2023-10-17 02:23:17,861][62408] Updated weights for policy 1, policy_version 52660 (0.0008) -[2023-10-17 02:23:18,239][62408] Updated weights for policy 1, policy_version 52670 (0.0009) -[2023-10-17 02:23:20,421][62373] Updated weights for policy 0, policy_version 53060 (0.0009) -[2023-10-17 02:23:20,781][62373] Updated weights for policy 0, policy_version 53070 (0.0009) -[2023-10-17 02:23:21,151][62373] Updated weights for policy 0, policy_version 53080 (0.0009) -[2023-10-17 02:23:22,117][62408] Updated weights for policy 1, policy_version 52680 (0.0009) -[2023-10-17 02:23:22,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 108298240. Throughput: 0: 1792.1, 1: 1764.3. Samples: 27080082. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:23:22,215][61453] Avg episode reward: [(0, '9.300'), (1, '8.200')] -[2023-10-17 02:23:22,497][62408] Updated weights for policy 1, policy_version 52690 (0.0010) -[2023-10-17 02:23:22,870][62408] Updated weights for policy 1, policy_version 52700 (0.0012) -[2023-10-17 02:23:25,013][62373] Updated weights for policy 0, policy_version 53090 (0.0009) -[2023-10-17 02:23:25,381][62373] Updated weights for policy 0, policy_version 53100 (0.0007) -[2023-10-17 02:23:25,747][62373] Updated weights for policy 0, policy_version 53110 (0.0010) -[2023-10-17 02:23:26,117][62373] Updated weights for policy 0, policy_version 53120 (0.0009) -[2023-10-17 02:23:26,643][62408] Updated weights for policy 1, policy_version 52710 (0.0009) -[2023-10-17 02:23:27,009][62408] Updated weights for policy 1, policy_version 52720 (0.0008) -[2023-10-17 02:23:27,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 108363776. Throughput: 0: 1775.9, 1: 1772.2. Samples: 27100882. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:23:27,214][61453] Avg episode reward: [(0, '9.750'), (1, '8.500')] -[2023-10-17 02:23:27,378][62408] Updated weights for policy 1, policy_version 52730 (0.0008) -[2023-10-17 02:23:29,648][62373] Updated weights for policy 0, policy_version 53130 (0.0008) -[2023-10-17 02:23:30,015][62373] Updated weights for policy 0, policy_version 53140 (0.0007) -[2023-10-17 02:23:30,385][62373] Updated weights for policy 0, policy_version 53150 (0.0007) -[2023-10-17 02:23:31,269][62408] Updated weights for policy 1, policy_version 52740 (0.0008) -[2023-10-17 02:23:31,638][62408] Updated weights for policy 1, policy_version 52750 (0.0009) -[2023-10-17 02:23:32,005][62408] Updated weights for policy 1, policy_version 52760 (0.0008) -[2023-10-17 02:23:32,214][61453] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 108429312. Throughput: 0: 1775.3, 1: 1770.6. Samples: 27122412. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:23:32,215][61453] Avg episode reward: [(0, '10.120'), (1, '8.720')] -[2023-10-17 02:23:32,222][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000053152_54427648.pth... -[2023-10-17 02:23:32,261][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000051488_52723712.pth -[2023-10-17 02:23:32,292][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000052768_54034432.pth... -[2023-10-17 02:23:32,330][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000051104_52330496.pth -[2023-10-17 02:23:33,980][62373] Updated weights for policy 0, policy_version 53160 (0.0007) -[2023-10-17 02:23:34,353][62373] Updated weights for policy 0, policy_version 53170 (0.0011) -[2023-10-17 02:23:34,709][62373] Updated weights for policy 0, policy_version 53180 (0.0011) -[2023-10-17 02:23:35,813][62408] Updated weights for policy 1, policy_version 52770 (0.0011) -[2023-10-17 02:23:36,174][62408] Updated weights for policy 1, policy_version 52780 (0.0008) -[2023-10-17 02:23:36,546][62408] Updated weights for policy 1, policy_version 52790 (0.0010) -[2023-10-17 02:23:36,915][62408] Updated weights for policy 1, policy_version 52800 (0.0010) -[2023-10-17 02:23:37,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 108527616. Throughput: 0: 1775.8, 1: 1776.5. Samples: 27133084. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:23:37,215][61453] Avg episode reward: [(0, '9.980'), (1, '9.650')] -[2023-10-17 02:23:38,551][62373] Updated weights for policy 0, policy_version 53190 (0.0008) -[2023-10-17 02:23:38,920][62373] Updated weights for policy 0, policy_version 53200 (0.0007) -[2023-10-17 02:23:39,288][62373] Updated weights for policy 0, policy_version 53210 (0.0008) -[2023-10-17 02:23:40,743][62408] Updated weights for policy 1, policy_version 52810 (0.0007) -[2023-10-17 02:23:41,120][62408] Updated weights for policy 1, policy_version 52820 (0.0009) -[2023-10-17 02:23:41,480][62408] Updated weights for policy 1, policy_version 52830 (0.0010) -[2023-10-17 02:23:42,214][61453] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 108593152. Throughput: 0: 1773.1, 1: 1783.1. Samples: 27154626. Policy #0 lag: (min: 31.0, avg: 31.6, max: 49.0) -[2023-10-17 02:23:42,214][61453] Avg episode reward: [(0, '10.780'), (1, '9.430')] -[2023-10-17 02:23:43,056][62373] Updated weights for policy 0, policy_version 53220 (0.0008) -[2023-10-17 02:23:43,428][62373] Updated weights for policy 0, policy_version 53230 (0.0007) -[2023-10-17 02:23:43,798][62373] Updated weights for policy 0, policy_version 53240 (0.0007) -[2023-10-17 02:23:45,237][62408] Updated weights for policy 1, policy_version 52840 (0.0008) -[2023-10-17 02:23:45,595][62408] Updated weights for policy 1, policy_version 52850 (0.0009) -[2023-10-17 02:23:45,970][62408] Updated weights for policy 1, policy_version 52860 (0.0009) -[2023-10-17 02:23:47,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 108658688. Throughput: 0: 1780.9, 1: 1761.0. Samples: 27175952. Policy #0 lag: (min: 31.0, avg: 31.6, max: 49.0) -[2023-10-17 02:23:47,215][61453] Avg episode reward: [(0, '10.850'), (1, '9.030')] -[2023-10-17 02:23:47,798][62373] Updated weights for policy 0, policy_version 53250 (0.0010) -[2023-10-17 02:23:48,203][62373] Updated weights for policy 0, policy_version 53260 (0.0008) -[2023-10-17 02:23:48,567][62373] Updated weights for policy 0, policy_version 53270 (0.0010) -[2023-10-17 02:23:48,932][62373] Updated weights for policy 0, policy_version 53280 (0.0009) -[2023-10-17 02:23:49,727][62408] Updated weights for policy 1, policy_version 52870 (0.0009) -[2023-10-17 02:23:50,095][62408] Updated weights for policy 1, policy_version 52880 (0.0008) -[2023-10-17 02:23:50,457][62408] Updated weights for policy 1, policy_version 52890 (0.0008) -[2023-10-17 02:23:52,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 108724224. Throughput: 0: 1772.4, 1: 1783.2. Samples: 27186384. Policy #0 lag: (min: 31.0, avg: 31.6, max: 49.0) -[2023-10-17 02:23:52,215][61453] Avg episode reward: [(0, '10.580'), (1, '8.680')] -[2023-10-17 02:23:52,660][62373] Updated weights for policy 0, policy_version 53290 (0.0007) -[2023-10-17 02:23:53,032][62373] Updated weights for policy 0, policy_version 53300 (0.0009) -[2023-10-17 02:23:53,402][62373] Updated weights for policy 0, policy_version 53310 (0.0010) -[2023-10-17 02:23:54,204][62408] Updated weights for policy 1, policy_version 52900 (0.0008) -[2023-10-17 02:23:54,566][62408] Updated weights for policy 1, policy_version 52910 (0.0009) -[2023-10-17 02:23:54,938][62408] Updated weights for policy 1, policy_version 52920 (0.0010) -[2023-10-17 02:23:57,194][62373] Updated weights for policy 0, policy_version 53320 (0.0010) -[2023-10-17 02:23:57,214][61453] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 108789760. Throughput: 0: 1775.7, 1: 1767.8. Samples: 27207770. Policy #0 lag: (min: 31.0, avg: 31.6, max: 49.0) -[2023-10-17 02:23:57,214][61453] Avg episode reward: [(0, '11.140'), (1, '9.190')] -[2023-10-17 02:23:57,570][62373] Updated weights for policy 0, policy_version 53330 (0.0008) -[2023-10-17 02:23:57,946][62373] Updated weights for policy 0, policy_version 53340 (0.0008) -[2023-10-17 02:23:58,087][62094] Saving new best policy, reward=11.140! -[2023-10-17 02:23:58,801][62408] Updated weights for policy 1, policy_version 52930 (0.0009) -[2023-10-17 02:23:59,166][62408] Updated weights for policy 1, policy_version 52940 (0.0007) -[2023-10-17 02:23:59,542][62408] Updated weights for policy 1, policy_version 52950 (0.0008) -[2023-10-17 02:23:59,903][62408] Updated weights for policy 1, policy_version 52960 (0.0007) -[2023-10-17 02:24:01,823][62373] Updated weights for policy 0, policy_version 53350 (0.0009) -[2023-10-17 02:24:02,185][62373] Updated weights for policy 0, policy_version 53360 (0.0009) -[2023-10-17 02:24:02,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 108855296. Throughput: 0: 1798.6, 1: 1774.5. Samples: 27229708. Policy #0 lag: (min: 31.0, avg: 31.6, max: 49.0) -[2023-10-17 02:24:02,214][61453] Avg episode reward: [(0, '10.850'), (1, '9.220')] -[2023-10-17 02:24:02,564][62373] Updated weights for policy 0, policy_version 53370 (0.0009) -[2023-10-17 02:24:03,516][62408] Updated weights for policy 1, policy_version 52970 (0.0010) -[2023-10-17 02:24:03,887][62408] Updated weights for policy 1, policy_version 52980 (0.0007) -[2023-10-17 02:24:04,258][62408] Updated weights for policy 1, policy_version 52990 (0.0007) -[2023-10-17 02:24:06,357][62373] Updated weights for policy 0, policy_version 53380 (0.0010) -[2023-10-17 02:24:06,734][62373] Updated weights for policy 0, policy_version 53390 (0.0009) -[2023-10-17 02:24:07,095][62373] Updated weights for policy 0, policy_version 53400 (0.0009) -[2023-10-17 02:24:07,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 108920832. Throughput: 0: 1773.9, 1: 1778.2. Samples: 27239928. Policy #0 lag: (min: 31.0, avg: 31.6, max: 49.0) -[2023-10-17 02:24:07,215][61453] Avg episode reward: [(0, '10.670'), (1, '8.620')] -[2023-10-17 02:24:08,078][62408] Updated weights for policy 1, policy_version 53000 (0.0007) -[2023-10-17 02:24:08,449][62408] Updated weights for policy 1, policy_version 53010 (0.0009) -[2023-10-17 02:24:08,818][62408] Updated weights for policy 1, policy_version 53020 (0.0008) -[2023-10-17 02:24:10,990][62373] Updated weights for policy 0, policy_version 53410 (0.0008) -[2023-10-17 02:24:11,362][62373] Updated weights for policy 0, policy_version 53420 (0.0008) -[2023-10-17 02:24:11,720][62373] Updated weights for policy 0, policy_version 53430 (0.0008) -[2023-10-17 02:24:12,087][62373] Updated weights for policy 0, policy_version 53440 (0.0009) -[2023-10-17 02:24:12,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14106.9). Total num frames: 109019136. Throughput: 0: 1791.4, 1: 1778.5. Samples: 27261530. Policy #0 lag: (min: 31.0, avg: 31.6, max: 49.0) -[2023-10-17 02:24:12,215][61453] Avg episode reward: [(0, '10.750'), (1, '8.430')] -[2023-10-17 02:24:12,695][62408] Updated weights for policy 1, policy_version 53030 (0.0009) -[2023-10-17 02:24:13,075][62408] Updated weights for policy 1, policy_version 53040 (0.0007) -[2023-10-17 02:24:13,446][62408] Updated weights for policy 1, policy_version 53050 (0.0008) -[2023-10-17 02:24:15,912][62373] Updated weights for policy 0, policy_version 53450 (0.0007) -[2023-10-17 02:24:16,291][62373] Updated weights for policy 0, policy_version 53460 (0.0008) -[2023-10-17 02:24:16,666][62373] Updated weights for policy 0, policy_version 53470 (0.0007) -[2023-10-17 02:24:17,214][61453] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 109084672. Throughput: 0: 1760.3, 1: 1788.4. Samples: 27282100. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:24:17,215][61453] Avg episode reward: [(0, '9.780'), (1, '8.990')] -[2023-10-17 02:24:17,335][62408] Updated weights for policy 1, policy_version 53060 (0.0007) -[2023-10-17 02:24:17,698][62408] Updated weights for policy 1, policy_version 53070 (0.0011) -[2023-10-17 02:24:18,067][62408] Updated weights for policy 1, policy_version 53080 (0.0009) -[2023-10-17 02:24:20,580][62373] Updated weights for policy 0, policy_version 53480 (0.0008) -[2023-10-17 02:24:20,960][62373] Updated weights for policy 0, policy_version 53490 (0.0007) -[2023-10-17 02:24:21,328][62373] Updated weights for policy 0, policy_version 53500 (0.0008) -[2023-10-17 02:24:21,844][62408] Updated weights for policy 1, policy_version 53090 (0.0010) -[2023-10-17 02:24:22,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 109150208. Throughput: 0: 1791.5, 1: 1765.2. Samples: 27293136. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:24:22,214][61453] Avg episode reward: [(0, '9.850'), (1, '8.700')] -[2023-10-17 02:24:22,215][62408] Updated weights for policy 1, policy_version 53100 (0.0010) -[2023-10-17 02:24:22,586][62408] Updated weights for policy 1, policy_version 53110 (0.0008) -[2023-10-17 02:24:22,948][62408] Updated weights for policy 1, policy_version 53120 (0.0009) -[2023-10-17 02:24:24,963][62373] Updated weights for policy 0, policy_version 53510 (0.0008) -[2023-10-17 02:24:25,338][62373] Updated weights for policy 0, policy_version 53520 (0.0010) -[2023-10-17 02:24:25,714][62373] Updated weights for policy 0, policy_version 53530 (0.0011) -[2023-10-17 02:24:26,931][62408] Updated weights for policy 1, policy_version 53130 (0.0009) -[2023-10-17 02:24:27,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 109215744. Throughput: 0: 1764.0, 1: 1774.8. Samples: 27313872. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:24:27,215][61453] Avg episode reward: [(0, '8.930'), (1, '8.750')] -[2023-10-17 02:24:27,308][62408] Updated weights for policy 1, policy_version 53140 (0.0010) -[2023-10-17 02:24:27,676][62408] Updated weights for policy 1, policy_version 53150 (0.0008) -[2023-10-17 02:24:29,657][62373] Updated weights for policy 0, policy_version 53540 (0.0009) -[2023-10-17 02:24:30,034][62373] Updated weights for policy 0, policy_version 53550 (0.0008) -[2023-10-17 02:24:30,403][62373] Updated weights for policy 0, policy_version 53560 (0.0009) -[2023-10-17 02:24:31,521][62408] Updated weights for policy 1, policy_version 53160 (0.0007) -[2023-10-17 02:24:31,888][62408] Updated weights for policy 1, policy_version 53170 (0.0008) -[2023-10-17 02:24:32,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 109281280. Throughput: 0: 1757.2, 1: 1777.2. Samples: 27334998. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:24:32,215][61453] Avg episode reward: [(0, '9.090'), (1, '7.870')] -[2023-10-17 02:24:32,261][62408] Updated weights for policy 1, policy_version 53180 (0.0007) -[2023-10-17 02:24:34,166][62373] Updated weights for policy 0, policy_version 53570 (0.0010) -[2023-10-17 02:24:34,568][62373] Updated weights for policy 0, policy_version 53580 (0.0010) -[2023-10-17 02:24:34,933][62373] Updated weights for policy 0, policy_version 53590 (0.0010) -[2023-10-17 02:24:35,296][62373] Updated weights for policy 0, policy_version 53600 (0.0010) -[2023-10-17 02:24:36,187][62408] Updated weights for policy 1, policy_version 53190 (0.0009) -[2023-10-17 02:24:36,552][62408] Updated weights for policy 1, policy_version 53200 (0.0009) -[2023-10-17 02:24:36,920][62408] Updated weights for policy 1, policy_version 53210 (0.0007) -[2023-10-17 02:24:37,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 109379584. Throughput: 0: 1770.1, 1: 1768.4. Samples: 27345614. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:24:37,214][61453] Avg episode reward: [(0, '9.730'), (1, '8.680')] -[2023-10-17 02:24:39,182][62373] Updated weights for policy 0, policy_version 53610 (0.0010) -[2023-10-17 02:24:39,557][62373] Updated weights for policy 0, policy_version 53620 (0.0009) -[2023-10-17 02:24:39,919][62373] Updated weights for policy 0, policy_version 53630 (0.0011) -[2023-10-17 02:24:40,700][62408] Updated weights for policy 1, policy_version 53220 (0.0009) -[2023-10-17 02:24:41,063][62408] Updated weights for policy 1, policy_version 53230 (0.0007) -[2023-10-17 02:24:41,435][62408] Updated weights for policy 1, policy_version 53240 (0.0008) -[2023-10-17 02:24:42,214][61453] Fps is (10 sec: 16384.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 109445120. Throughput: 0: 1754.0, 1: 1777.6. Samples: 27366696. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:24:42,214][61453] Avg episode reward: [(0, '9.520'), (1, '8.530')] -[2023-10-17 02:24:43,626][62373] Updated weights for policy 0, policy_version 53640 (0.0008) -[2023-10-17 02:24:44,003][62373] Updated weights for policy 0, policy_version 53650 (0.0007) -[2023-10-17 02:24:44,365][62373] Updated weights for policy 0, policy_version 53660 (0.0008) -[2023-10-17 02:24:45,228][62408] Updated weights for policy 1, policy_version 53250 (0.0010) -[2023-10-17 02:24:45,587][62408] Updated weights for policy 1, policy_version 53260 (0.0010) -[2023-10-17 02:24:45,955][62408] Updated weights for policy 1, policy_version 53270 (0.0011) -[2023-10-17 02:24:46,335][62408] Updated weights for policy 1, policy_version 53280 (0.0010) -[2023-10-17 02:24:47,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 109510656. Throughput: 0: 1766.9, 1: 1749.6. Samples: 27387952. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:24:47,214][61453] Avg episode reward: [(0, '8.910'), (1, '9.230')] -[2023-10-17 02:24:48,229][62373] Updated weights for policy 0, policy_version 53670 (0.0008) -[2023-10-17 02:24:48,598][62373] Updated weights for policy 0, policy_version 53680 (0.0009) -[2023-10-17 02:24:48,975][62373] Updated weights for policy 0, policy_version 53690 (0.0010) -[2023-10-17 02:24:50,216][62408] Updated weights for policy 1, policy_version 53290 (0.0007) -[2023-10-17 02:24:50,580][62408] Updated weights for policy 1, policy_version 53300 (0.0009) -[2023-10-17 02:24:50,948][62408] Updated weights for policy 1, policy_version 53310 (0.0008) -[2023-10-17 02:24:52,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 109576192. Throughput: 0: 1756.3, 1: 1776.3. Samples: 27398896. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:24:52,215][61453] Avg episode reward: [(0, '9.310'), (1, '9.130')] -[2023-10-17 02:24:52,780][62373] Updated weights for policy 0, policy_version 53700 (0.0010) -[2023-10-17 02:24:53,150][62373] Updated weights for policy 0, policy_version 53710 (0.0008) -[2023-10-17 02:24:53,524][62373] Updated weights for policy 0, policy_version 53720 (0.0009) -[2023-10-17 02:24:54,801][62408] Updated weights for policy 1, policy_version 53320 (0.0007) -[2023-10-17 02:24:55,166][62408] Updated weights for policy 1, policy_version 53330 (0.0009) -[2023-10-17 02:24:55,540][62408] Updated weights for policy 1, policy_version 53340 (0.0008) -[2023-10-17 02:24:57,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 109641728. Throughput: 0: 1761.2, 1: 1746.4. Samples: 27419374. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-17 02:24:57,215][61453] Avg episode reward: [(0, '10.440'), (1, '9.450')] -[2023-10-17 02:24:57,446][62373] Updated weights for policy 0, policy_version 53730 (0.0010) -[2023-10-17 02:24:57,808][62373] Updated weights for policy 0, policy_version 53740 (0.0008) -[2023-10-17 02:24:58,174][62373] Updated weights for policy 0, policy_version 53750 (0.0008) -[2023-10-17 02:24:58,542][62373] Updated weights for policy 0, policy_version 53760 (0.0008) -[2023-10-17 02:24:59,329][62408] Updated weights for policy 1, policy_version 53350 (0.0008) -[2023-10-17 02:24:59,699][62408] Updated weights for policy 1, policy_version 53360 (0.0007) -[2023-10-17 02:25:00,070][62408] Updated weights for policy 1, policy_version 53370 (0.0007) -[2023-10-17 02:25:02,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 109707264. Throughput: 0: 1789.9, 1: 1748.5. Samples: 27441328. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-17 02:25:02,215][61453] Avg episode reward: [(0, '10.380'), (1, '10.150')] -[2023-10-17 02:25:02,326][62373] Updated weights for policy 0, policy_version 53770 (0.0007) -[2023-10-17 02:25:02,693][62373] Updated weights for policy 0, policy_version 53780 (0.0007) -[2023-10-17 02:25:03,062][62373] Updated weights for policy 0, policy_version 53790 (0.0008) -[2023-10-17 02:25:03,948][62408] Updated weights for policy 1, policy_version 53380 (0.0009) -[2023-10-17 02:25:04,313][62408] Updated weights for policy 1, policy_version 53390 (0.0008) -[2023-10-17 02:25:04,680][62408] Updated weights for policy 1, policy_version 53400 (0.0008) -[2023-10-17 02:25:06,814][62373] Updated weights for policy 0, policy_version 53800 (0.0010) -[2023-10-17 02:25:07,170][62373] Updated weights for policy 0, policy_version 53810 (0.0010) -[2023-10-17 02:25:07,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 109772800. Throughput: 0: 1759.2, 1: 1755.8. Samples: 27451314. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-17 02:25:07,215][61453] Avg episode reward: [(0, '9.900'), (1, '10.080')] -[2023-10-17 02:25:07,538][62373] Updated weights for policy 0, policy_version 53820 (0.0010) -[2023-10-17 02:25:08,523][62408] Updated weights for policy 1, policy_version 53410 (0.0008) -[2023-10-17 02:25:08,888][62408] Updated weights for policy 1, policy_version 53420 (0.0009) -[2023-10-17 02:25:09,253][62408] Updated weights for policy 1, policy_version 53430 (0.0009) -[2023-10-17 02:25:09,615][62408] Updated weights for policy 1, policy_version 53440 (0.0008) -[2023-10-17 02:25:11,370][62373] Updated weights for policy 0, policy_version 53830 (0.0009) -[2023-10-17 02:25:11,742][62373] Updated weights for policy 0, policy_version 53840 (0.0007) -[2023-10-17 02:25:12,120][62373] Updated weights for policy 0, policy_version 53850 (0.0007) -[2023-10-17 02:25:12,214][61453] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13995.8). Total num frames: 109838336. Throughput: 0: 1793.4, 1: 1749.0. Samples: 27473280. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-17 02:25:12,215][61453] Avg episode reward: [(0, '8.900'), (1, '9.880')] -[2023-10-17 02:25:13,434][62408] Updated weights for policy 1, policy_version 53450 (0.0009) -[2023-10-17 02:25:13,811][62408] Updated weights for policy 1, policy_version 53460 (0.0009) -[2023-10-17 02:25:14,176][62408] Updated weights for policy 1, policy_version 53470 (0.0011) -[2023-10-17 02:25:15,856][62373] Updated weights for policy 0, policy_version 53860 (0.0010) -[2023-10-17 02:25:16,220][62373] Updated weights for policy 0, policy_version 53870 (0.0010) -[2023-10-17 02:25:16,590][62373] Updated weights for policy 0, policy_version 53880 (0.0010) -[2023-10-17 02:25:17,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 109936640. Throughput: 0: 1767.8, 1: 1766.2. Samples: 27494030. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-17 02:25:17,214][61453] Avg episode reward: [(0, '9.030'), (1, '10.030')] -[2023-10-17 02:25:18,024][62408] Updated weights for policy 1, policy_version 53480 (0.0009) -[2023-10-17 02:25:18,399][62408] Updated weights for policy 1, policy_version 53490 (0.0008) -[2023-10-17 02:25:18,758][62408] Updated weights for policy 1, policy_version 53500 (0.0008) -[2023-10-17 02:25:20,386][62373] Updated weights for policy 0, policy_version 53890 (0.0011) -[2023-10-17 02:25:20,776][62373] Updated weights for policy 0, policy_version 53900 (0.0008) -[2023-10-17 02:25:21,149][62373] Updated weights for policy 0, policy_version 53910 (0.0007) -[2023-10-17 02:25:21,513][62373] Updated weights for policy 0, policy_version 53920 (0.0008) -[2023-10-17 02:25:22,214][61453] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 110002176. Throughput: 0: 1793.6, 1: 1748.3. Samples: 27505000. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-17 02:25:22,214][61453] Avg episode reward: [(0, '9.140'), (1, '9.830')] -[2023-10-17 02:25:22,617][62408] Updated weights for policy 1, policy_version 53510 (0.0011) -[2023-10-17 02:25:22,986][62408] Updated weights for policy 1, policy_version 53520 (0.0008) -[2023-10-17 02:25:23,347][62408] Updated weights for policy 1, policy_version 53530 (0.0009) -[2023-10-17 02:25:25,343][62373] Updated weights for policy 0, policy_version 53930 (0.0010) -[2023-10-17 02:25:25,706][62373] Updated weights for policy 0, policy_version 53940 (0.0009) -[2023-10-17 02:25:26,075][62373] Updated weights for policy 0, policy_version 53950 (0.0008) -[2023-10-17 02:25:27,204][62408] Updated weights for policy 1, policy_version 53540 (0.0007) -[2023-10-17 02:25:27,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 110067712. Throughput: 0: 1777.4, 1: 1762.3. Samples: 27525980. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-17 02:25:27,215][61453] Avg episode reward: [(0, '8.310'), (1, '9.410')] -[2023-10-17 02:25:27,568][62408] Updated weights for policy 1, policy_version 53550 (0.0008) -[2023-10-17 02:25:27,938][62408] Updated weights for policy 1, policy_version 53560 (0.0008) -[2023-10-17 02:25:29,778][62373] Updated weights for policy 0, policy_version 53960 (0.0008) -[2023-10-17 02:25:30,147][62373] Updated weights for policy 0, policy_version 53970 (0.0010) -[2023-10-17 02:25:30,525][62373] Updated weights for policy 0, policy_version 53980 (0.0009) -[2023-10-17 02:25:31,734][62408] Updated weights for policy 1, policy_version 53570 (0.0008) -[2023-10-17 02:25:32,096][62408] Updated weights for policy 1, policy_version 53580 (0.0010) -[2023-10-17 02:25:32,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 110133248. Throughput: 0: 1767.5, 1: 1776.3. Samples: 27547422. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-17 02:25:32,214][61453] Avg episode reward: [(0, '8.450'), (1, '9.280')] -[2023-10-17 02:25:32,223][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000053984_55279616.pth... -[2023-10-17 02:25:32,257][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000052320_53575680.pth -[2023-10-17 02:25:32,461][62408] Updated weights for policy 1, policy_version 53590 (0.0008) -[2023-10-17 02:25:32,824][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000053600_54886400.pth... -[2023-10-17 02:25:32,825][62408] Updated weights for policy 1, policy_version 53600 (0.0009) -[2023-10-17 02:25:32,863][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000051936_53182464.pth -[2023-10-17 02:25:34,303][62373] Updated weights for policy 0, policy_version 53990 (0.0008) -[2023-10-17 02:25:34,669][62373] Updated weights for policy 0, policy_version 54000 (0.0007) -[2023-10-17 02:25:35,041][62373] Updated weights for policy 0, policy_version 54010 (0.0009) -[2023-10-17 02:25:36,670][62408] Updated weights for policy 1, policy_version 53610 (0.0007) -[2023-10-17 02:25:37,032][62408] Updated weights for policy 1, policy_version 53620 (0.0007) -[2023-10-17 02:25:37,214][61453] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 110198784. Throughput: 0: 1776.4, 1: 1749.4. Samples: 27557554. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-17 02:25:37,214][61453] Avg episode reward: [(0, '8.480'), (1, '9.350')] -[2023-10-17 02:25:37,401][62408] Updated weights for policy 1, policy_version 53630 (0.0007) -[2023-10-17 02:25:38,888][62373] Updated weights for policy 0, policy_version 54020 (0.0007) -[2023-10-17 02:25:39,256][62373] Updated weights for policy 0, policy_version 54030 (0.0009) -[2023-10-17 02:25:39,624][62373] Updated weights for policy 0, policy_version 54040 (0.0009) -[2023-10-17 02:25:41,190][62408] Updated weights for policy 1, policy_version 53640 (0.0008) -[2023-10-17 02:25:41,557][62408] Updated weights for policy 1, policy_version 53650 (0.0010) -[2023-10-17 02:25:41,929][62408] Updated weights for policy 1, policy_version 53660 (0.0008) -[2023-10-17 02:25:42,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 110297088. Throughput: 0: 1762.3, 1: 1784.4. Samples: 27578974. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-17 02:25:42,215][61453] Avg episode reward: [(0, '9.210'), (1, '9.020')] -[2023-10-17 02:25:43,446][62373] Updated weights for policy 0, policy_version 54050 (0.0011) -[2023-10-17 02:25:43,826][62373] Updated weights for policy 0, policy_version 54060 (0.0011) -[2023-10-17 02:25:44,187][62373] Updated weights for policy 0, policy_version 54070 (0.0008) -[2023-10-17 02:25:44,557][62373] Updated weights for policy 0, policy_version 54080 (0.0009) -[2023-10-17 02:25:45,802][62408] Updated weights for policy 1, policy_version 53670 (0.0009) -[2023-10-17 02:25:46,165][62408] Updated weights for policy 1, policy_version 53680 (0.0008) -[2023-10-17 02:25:46,536][62408] Updated weights for policy 1, policy_version 53690 (0.0009) -[2023-10-17 02:25:47,214][61453] Fps is (10 sec: 16383.5, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 110362624. Throughput: 0: 1772.4, 1: 1753.0. Samples: 27599974. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-17 02:25:47,215][61453] Avg episode reward: [(0, '9.020'), (1, '8.380')] -[2023-10-17 02:25:48,337][62373] Updated weights for policy 0, policy_version 54090 (0.0009) -[2023-10-17 02:25:48,712][62373] Updated weights for policy 0, policy_version 54100 (0.0008) -[2023-10-17 02:25:49,071][62373] Updated weights for policy 0, policy_version 54110 (0.0010) -[2023-10-17 02:25:50,443][62408] Updated weights for policy 1, policy_version 53700 (0.0009) -[2023-10-17 02:25:50,815][62408] Updated weights for policy 1, policy_version 53710 (0.0010) -[2023-10-17 02:25:51,186][62408] Updated weights for policy 1, policy_version 53720 (0.0010) -[2023-10-17 02:25:52,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 110428160. Throughput: 0: 1769.4, 1: 1779.5. Samples: 27611012. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-17 02:25:52,215][61453] Avg episode reward: [(0, '9.520'), (1, '9.190')] -[2023-10-17 02:25:52,739][62373] Updated weights for policy 0, policy_version 54120 (0.0008) -[2023-10-17 02:25:53,116][62373] Updated weights for policy 0, policy_version 54130 (0.0007) -[2023-10-17 02:25:53,485][62373] Updated weights for policy 0, policy_version 54140 (0.0008) -[2023-10-17 02:25:55,158][62408] Updated weights for policy 1, policy_version 53730 (0.0008) -[2023-10-17 02:25:55,527][62408] Updated weights for policy 1, policy_version 53740 (0.0007) -[2023-10-17 02:25:55,890][62408] Updated weights for policy 1, policy_version 53750 (0.0008) -[2023-10-17 02:25:56,253][62408] Updated weights for policy 1, policy_version 53760 (0.0009) -[2023-10-17 02:25:57,214][61453] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 110493696. Throughput: 0: 1766.5, 1: 1762.3. Samples: 27632072. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-17 02:25:57,214][61453] Avg episode reward: [(0, '9.680'), (1, '9.670')] -[2023-10-17 02:25:57,314][62373] Updated weights for policy 0, policy_version 54150 (0.0010) -[2023-10-17 02:25:57,685][62373] Updated weights for policy 0, policy_version 54160 (0.0010) -[2023-10-17 02:25:58,069][62373] Updated weights for policy 0, policy_version 54170 (0.0008) -[2023-10-17 02:26:00,103][62408] Updated weights for policy 1, policy_version 53770 (0.0010) -[2023-10-17 02:26:00,480][62408] Updated weights for policy 1, policy_version 53780 (0.0010) -[2023-10-17 02:26:00,849][62408] Updated weights for policy 1, policy_version 53790 (0.0010) -[2023-10-17 02:26:01,857][62373] Updated weights for policy 0, policy_version 54180 (0.0007) -[2023-10-17 02:26:02,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 110559232. Throughput: 0: 1793.3, 1: 1744.1. Samples: 27653214. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-17 02:26:02,215][61453] Avg episode reward: [(0, '9.890'), (1, '8.970')] -[2023-10-17 02:26:02,236][62373] Updated weights for policy 0, policy_version 54190 (0.0007) -[2023-10-17 02:26:02,609][62373] Updated weights for policy 0, policy_version 54200 (0.0007) -[2023-10-17 02:26:04,599][62408] Updated weights for policy 1, policy_version 53800 (0.0011) -[2023-10-17 02:26:04,972][62408] Updated weights for policy 1, policy_version 53810 (0.0009) -[2023-10-17 02:26:05,336][62408] Updated weights for policy 1, policy_version 53820 (0.0010) -[2023-10-17 02:26:06,385][62373] Updated weights for policy 0, policy_version 54210 (0.0009) -[2023-10-17 02:26:06,796][62373] Updated weights for policy 0, policy_version 54220 (0.0008) -[2023-10-17 02:26:07,165][62373] Updated weights for policy 0, policy_version 54230 (0.0010) -[2023-10-17 02:26:07,214][61453] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 110624768. Throughput: 0: 1768.7, 1: 1766.0. Samples: 27664066. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-17 02:26:07,215][61453] Avg episode reward: [(0, '10.120'), (1, '9.320')] -[2023-10-17 02:26:07,543][62373] Updated weights for policy 0, policy_version 54240 (0.0010) -[2023-10-17 02:26:09,255][62408] Updated weights for policy 1, policy_version 53830 (0.0011) -[2023-10-17 02:26:09,620][62408] Updated weights for policy 1, policy_version 53840 (0.0011) -[2023-10-17 02:26:09,989][62408] Updated weights for policy 1, policy_version 53850 (0.0008) -[2023-10-17 02:26:11,298][62373] Updated weights for policy 0, policy_version 54250 (0.0010) -[2023-10-17 02:26:11,673][62373] Updated weights for policy 0, policy_version 54260 (0.0007) -[2023-10-17 02:26:12,048][62373] Updated weights for policy 0, policy_version 54270 (0.0007) -[2023-10-17 02:26:12,214][61453] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 110723072. Throughput: 0: 1794.5, 1: 1741.7. Samples: 27685108. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:26:12,214][61453] Avg episode reward: [(0, '10.020'), (1, '9.120')] -[2023-10-17 02:26:13,792][62408] Updated weights for policy 1, policy_version 53860 (0.0010) -[2023-10-17 02:26:14,158][62408] Updated weights for policy 1, policy_version 53870 (0.0010) -[2023-10-17 02:26:14,538][62408] Updated weights for policy 1, policy_version 53880 (0.0008) -[2023-10-17 02:26:15,823][62373] Updated weights for policy 0, policy_version 54280 (0.0009) -[2023-10-17 02:26:16,187][62373] Updated weights for policy 0, policy_version 54290 (0.0009) -[2023-10-17 02:26:16,560][62373] Updated weights for policy 0, policy_version 54300 (0.0011) -[2023-10-17 02:26:17,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 110788608. Throughput: 0: 1772.7, 1: 1749.5. Samples: 27705920. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:26:17,215][61453] Avg episode reward: [(0, '10.120'), (1, '10.160')] -[2023-10-17 02:26:18,426][62408] Updated weights for policy 1, policy_version 53890 (0.0007) -[2023-10-17 02:26:18,795][62408] Updated weights for policy 1, policy_version 53900 (0.0007) -[2023-10-17 02:26:19,154][62408] Updated weights for policy 1, policy_version 53910 (0.0007) -[2023-10-17 02:26:19,520][62408] Updated weights for policy 1, policy_version 53920 (0.0007) -[2023-10-17 02:26:20,255][62373] Updated weights for policy 0, policy_version 54310 (0.0010) -[2023-10-17 02:26:20,624][62373] Updated weights for policy 0, policy_version 54320 (0.0008) -[2023-10-17 02:26:20,981][62373] Updated weights for policy 0, policy_version 54330 (0.0007) -[2023-10-17 02:26:22,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 110854144. Throughput: 0: 1798.0, 1: 1744.8. Samples: 27716980. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:26:22,215][61453] Avg episode reward: [(0, '10.320'), (1, '10.170')] -[2023-10-17 02:26:23,342][62408] Updated weights for policy 1, policy_version 53930 (0.0011) -[2023-10-17 02:26:23,712][62408] Updated weights for policy 1, policy_version 53940 (0.0008) -[2023-10-17 02:26:24,072][62408] Updated weights for policy 1, policy_version 53950 (0.0010) -[2023-10-17 02:26:24,777][62373] Updated weights for policy 0, policy_version 54340 (0.0009) -[2023-10-17 02:26:25,152][62373] Updated weights for policy 0, policy_version 54350 (0.0009) -[2023-10-17 02:26:25,533][62373] Updated weights for policy 0, policy_version 54360 (0.0008) -[2023-10-17 02:26:27,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 110919680. Throughput: 0: 1785.5, 1: 1744.7. Samples: 27737830. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:26:27,215][61453] Avg episode reward: [(0, '10.010'), (1, '9.450')] -[2023-10-17 02:26:28,010][62408] Updated weights for policy 1, policy_version 53960 (0.0009) -[2023-10-17 02:26:28,387][62408] Updated weights for policy 1, policy_version 53970 (0.0009) -[2023-10-17 02:26:28,764][62408] Updated weights for policy 1, policy_version 53980 (0.0009) -[2023-10-17 02:26:29,255][62373] Updated weights for policy 0, policy_version 54370 (0.0008) -[2023-10-17 02:26:29,620][62373] Updated weights for policy 0, policy_version 54380 (0.0009) -[2023-10-17 02:26:29,988][62373] Updated weights for policy 0, policy_version 54390 (0.0010) -[2023-10-17 02:26:30,357][62373] Updated weights for policy 0, policy_version 54400 (0.0007) -[2023-10-17 02:26:32,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 110985216. Throughput: 0: 1778.3, 1: 1775.7. Samples: 27759902. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:26:32,215][61453] Avg episode reward: [(0, '9.940'), (1, '9.600')] -[2023-10-17 02:26:32,736][62408] Updated weights for policy 1, policy_version 53990 (0.0008) -[2023-10-17 02:26:33,120][62408] Updated weights for policy 1, policy_version 54000 (0.0007) -[2023-10-17 02:26:33,495][62408] Updated weights for policy 1, policy_version 54010 (0.0009) -[2023-10-17 02:26:34,200][62373] Updated weights for policy 0, policy_version 54410 (0.0008) -[2023-10-17 02:26:34,567][62373] Updated weights for policy 0, policy_version 54420 (0.0007) -[2023-10-17 02:26:34,946][62373] Updated weights for policy 0, policy_version 54430 (0.0008) -[2023-10-17 02:26:37,185][62408] Updated weights for policy 1, policy_version 54020 (0.0007) -[2023-10-17 02:26:37,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 111050752. Throughput: 0: 1785.9, 1: 1738.1. Samples: 27769594. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:26:37,214][61453] Avg episode reward: [(0, '9.540'), (1, '10.150')] -[2023-10-17 02:26:37,560][62408] Updated weights for policy 1, policy_version 54030 (0.0008) -[2023-10-17 02:26:37,916][62408] Updated weights for policy 1, policy_version 54040 (0.0007) -[2023-10-17 02:26:38,754][62373] Updated weights for policy 0, policy_version 54440 (0.0007) -[2023-10-17 02:26:39,122][62373] Updated weights for policy 0, policy_version 54450 (0.0009) -[2023-10-17 02:26:39,503][62373] Updated weights for policy 0, policy_version 54460 (0.0008) -[2023-10-17 02:26:41,730][62408] Updated weights for policy 1, policy_version 54050 (0.0010) -[2023-10-17 02:26:42,102][62408] Updated weights for policy 1, policy_version 54060 (0.0007) -[2023-10-17 02:26:42,214][61453] Fps is (10 sec: 13107.7, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 111116288. Throughput: 0: 1778.9, 1: 1764.7. Samples: 27791534. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:26:42,214][61453] Avg episode reward: [(0, '10.250'), (1, '10.300')] -[2023-10-17 02:26:42,469][62408] Updated weights for policy 1, policy_version 54070 (0.0009) -[2023-10-17 02:26:42,834][62408] Updated weights for policy 1, policy_version 54080 (0.0010) -[2023-10-17 02:26:43,355][62373] Updated weights for policy 0, policy_version 54470 (0.0007) -[2023-10-17 02:26:43,733][62373] Updated weights for policy 0, policy_version 54480 (0.0008) -[2023-10-17 02:26:44,113][62373] Updated weights for policy 0, policy_version 54490 (0.0008) -[2023-10-17 02:26:46,824][62408] Updated weights for policy 1, policy_version 54090 (0.0009) -[2023-10-17 02:26:47,182][62408] Updated weights for policy 1, policy_version 54100 (0.0008) -[2023-10-17 02:26:47,214][61453] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 111181824. Throughput: 0: 1783.8, 1: 1763.9. Samples: 27812858. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-17 02:26:47,215][61453] Avg episode reward: [(0, '10.790'), (1, '9.910')] -[2023-10-17 02:26:47,544][62408] Updated weights for policy 1, policy_version 54110 (0.0010) -[2023-10-17 02:26:48,089][62373] Updated weights for policy 0, policy_version 54500 (0.0010) -[2023-10-17 02:26:48,467][62373] Updated weights for policy 0, policy_version 54510 (0.0009) -[2023-10-17 02:26:48,832][62373] Updated weights for policy 0, policy_version 54520 (0.0010) -[2023-10-17 02:26:51,345][62408] Updated weights for policy 1, policy_version 54120 (0.0009) -[2023-10-17 02:26:51,708][62408] Updated weights for policy 1, policy_version 54130 (0.0007) -[2023-10-17 02:26:52,083][62408] Updated weights for policy 1, policy_version 54140 (0.0008) -[2023-10-17 02:26:52,214][61453] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 111247360. Throughput: 0: 1774.9, 1: 1756.9. Samples: 27823000. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-17 02:26:52,214][61453] Avg episode reward: [(0, '10.440'), (1, '9.770')] -[2023-10-17 02:26:52,648][62373] Updated weights for policy 0, policy_version 54530 (0.0009) -[2023-10-17 02:26:53,044][62373] Updated weights for policy 0, policy_version 54540 (0.0010) -[2023-10-17 02:26:53,411][62373] Updated weights for policy 0, policy_version 54550 (0.0007) -[2023-10-17 02:26:53,782][62373] Updated weights for policy 0, policy_version 54560 (0.0007) -[2023-10-17 02:26:55,935][62408] Updated weights for policy 1, policy_version 54150 (0.0010) -[2023-10-17 02:26:56,293][62408] Updated weights for policy 1, policy_version 54160 (0.0010) -[2023-10-17 02:26:56,672][62408] Updated weights for policy 1, policy_version 54170 (0.0011) -[2023-10-17 02:26:57,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 111345664. Throughput: 0: 1771.2, 1: 1774.3. Samples: 27844658. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-17 02:26:57,215][61453] Avg episode reward: [(0, '10.280'), (1, '8.940')] -[2023-10-17 02:26:57,542][62373] Updated weights for policy 0, policy_version 54570 (0.0007) -[2023-10-17 02:26:57,902][62373] Updated weights for policy 0, policy_version 54580 (0.0007) -[2023-10-17 02:26:58,271][62373] Updated weights for policy 0, policy_version 54590 (0.0008) -[2023-10-17 02:27:00,587][62408] Updated weights for policy 1, policy_version 54180 (0.0009) -[2023-10-17 02:27:00,957][62408] Updated weights for policy 1, policy_version 54190 (0.0011) -[2023-10-17 02:27:01,321][62408] Updated weights for policy 1, policy_version 54200 (0.0010) -[2023-10-17 02:27:02,167][62373] Updated weights for policy 0, policy_version 54600 (0.0008) -[2023-10-17 02:27:02,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 111411200. Throughput: 0: 1797.2, 1: 1743.4. Samples: 27865246. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-17 02:27:02,215][61453] Avg episode reward: [(0, '10.330'), (1, '9.920')] -[2023-10-17 02:27:02,540][62373] Updated weights for policy 0, policy_version 54610 (0.0008) -[2023-10-17 02:27:02,921][62373] Updated weights for policy 0, policy_version 54620 (0.0008) -[2023-10-17 02:27:05,155][62408] Updated weights for policy 1, policy_version 54210 (0.0008) -[2023-10-17 02:27:05,513][62408] Updated weights for policy 1, policy_version 54220 (0.0009) -[2023-10-17 02:27:05,882][62408] Updated weights for policy 1, policy_version 54230 (0.0008) -[2023-10-17 02:27:06,248][62408] Updated weights for policy 1, policy_version 54240 (0.0008) -[2023-10-17 02:27:06,598][62373] Updated weights for policy 0, policy_version 54630 (0.0009) -[2023-10-17 02:27:06,967][62373] Updated weights for policy 0, policy_version 54640 (0.0008) -[2023-10-17 02:27:07,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 111476736. Throughput: 0: 1770.0, 1: 1776.7. Samples: 27876578. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-17 02:27:07,214][61453] Avg episode reward: [(0, '10.880'), (1, '9.630')] -[2023-10-17 02:27:07,327][62373] Updated weights for policy 0, policy_version 54650 (0.0008) -[2023-10-17 02:27:09,973][62408] Updated weights for policy 1, policy_version 54250 (0.0007) -[2023-10-17 02:27:10,341][62408] Updated weights for policy 1, policy_version 54260 (0.0008) -[2023-10-17 02:27:10,711][62408] Updated weights for policy 1, policy_version 54270 (0.0009) -[2023-10-17 02:27:11,182][62373] Updated weights for policy 0, policy_version 54660 (0.0008) -[2023-10-17 02:27:11,560][62373] Updated weights for policy 0, policy_version 54670 (0.0010) -[2023-10-17 02:27:11,925][62373] Updated weights for policy 0, policy_version 54680 (0.0009) -[2023-10-17 02:27:12,214][61453] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 111575040. Throughput: 0: 1798.1, 1: 1745.8. Samples: 27897304. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-17 02:27:12,214][61453] Avg episode reward: [(0, '10.670'), (1, '9.050')] -[2023-10-17 02:27:14,214][62408] Updated weights for policy 1, policy_version 54280 (0.0010) -[2023-10-17 02:27:14,585][62408] Updated weights for policy 1, policy_version 54290 (0.0010) -[2023-10-17 02:27:14,946][62408] Updated weights for policy 1, policy_version 54300 (0.0008) -[2023-10-17 02:27:15,765][62373] Updated weights for policy 0, policy_version 54690 (0.0009) -[2023-10-17 02:27:16,132][62373] Updated weights for policy 0, policy_version 54700 (0.0008) -[2023-10-17 02:27:16,506][62373] Updated weights for policy 0, policy_version 54710 (0.0008) -[2023-10-17 02:27:16,874][62373] Updated weights for policy 0, policy_version 54720 (0.0009) -[2023-10-17 02:27:17,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 111640576. Throughput: 0: 1762.5, 1: 1756.3. Samples: 27918246. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-17 02:27:17,215][61453] Avg episode reward: [(0, '11.090'), (1, '8.760')] -[2023-10-17 02:27:18,866][62408] Updated weights for policy 1, policy_version 54310 (0.0009) -[2023-10-17 02:27:19,254][62408] Updated weights for policy 1, policy_version 54320 (0.0007) -[2023-10-17 02:27:19,624][62408] Updated weights for policy 1, policy_version 54330 (0.0009) -[2023-10-17 02:27:20,661][62373] Updated weights for policy 0, policy_version 54730 (0.0012) -[2023-10-17 02:27:21,038][62373] Updated weights for policy 0, policy_version 54740 (0.0010) -[2023-10-17 02:27:21,404][62373] Updated weights for policy 0, policy_version 54750 (0.0009) -[2023-10-17 02:27:22,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 111706112. Throughput: 0: 1790.9, 1: 1761.9. Samples: 27929470. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-17 02:27:22,214][61453] Avg episode reward: [(0, '10.300'), (1, '8.850')] -[2023-10-17 02:27:23,586][62408] Updated weights for policy 1, policy_version 54340 (0.0008) -[2023-10-17 02:27:23,953][62408] Updated weights for policy 1, policy_version 54350 (0.0009) -[2023-10-17 02:27:24,318][62408] Updated weights for policy 1, policy_version 54360 (0.0008) -[2023-10-17 02:27:25,193][62373] Updated weights for policy 0, policy_version 54760 (0.0009) -[2023-10-17 02:27:25,569][62373] Updated weights for policy 0, policy_version 54770 (0.0009) -[2023-10-17 02:27:25,926][62373] Updated weights for policy 0, policy_version 54780 (0.0007) -[2023-10-17 02:27:27,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 111771648. Throughput: 0: 1766.5, 1: 1756.6. Samples: 27950074. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-17 02:27:27,215][61453] Avg episode reward: [(0, '10.330'), (1, '9.160')] -[2023-10-17 02:27:28,161][62408] Updated weights for policy 1, policy_version 54370 (0.0008) -[2023-10-17 02:27:28,529][62408] Updated weights for policy 1, policy_version 54380 (0.0010) -[2023-10-17 02:27:28,894][62408] Updated weights for policy 1, policy_version 54390 (0.0010) -[2023-10-17 02:27:29,260][62408] Updated weights for policy 1, policy_version 54400 (0.0011) -[2023-10-17 02:27:29,629][62373] Updated weights for policy 0, policy_version 54790 (0.0007) -[2023-10-17 02:27:30,006][62373] Updated weights for policy 0, policy_version 54800 (0.0007) -[2023-10-17 02:27:30,377][62373] Updated weights for policy 0, policy_version 54810 (0.0009) -[2023-10-17 02:27:32,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 111837184. Throughput: 0: 1764.9, 1: 1774.1. Samples: 27972116. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-17 02:27:32,215][61453] Avg episode reward: [(0, '9.970'), (1, '9.690')] -[2023-10-17 02:27:32,227][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000054816_56131584.pth... -[2023-10-17 02:27:32,228][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000054400_55705600.pth... -[2023-10-17 02:27:32,264][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000053152_54427648.pth -[2023-10-17 02:27:32,264][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000052768_54034432.pth -[2023-10-17 02:27:33,011][62408] Updated weights for policy 1, policy_version 54410 (0.0009) -[2023-10-17 02:27:33,384][62408] Updated weights for policy 1, policy_version 54420 (0.0010) -[2023-10-17 02:27:33,759][62408] Updated weights for policy 1, policy_version 54430 (0.0009) -[2023-10-17 02:27:34,216][62373] Updated weights for policy 0, policy_version 54820 (0.0009) -[2023-10-17 02:27:34,586][62373] Updated weights for policy 0, policy_version 54830 (0.0010) -[2023-10-17 02:27:34,948][62373] Updated weights for policy 0, policy_version 54840 (0.0008) -[2023-10-17 02:27:37,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 111902720. Throughput: 0: 1774.0, 1: 1760.7. Samples: 27982060. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-17 02:27:37,215][61453] Avg episode reward: [(0, '10.410'), (1, '9.540')] -[2023-10-17 02:27:37,613][62408] Updated weights for policy 1, policy_version 54440 (0.0008) -[2023-10-17 02:27:37,983][62408] Updated weights for policy 1, policy_version 54450 (0.0008) -[2023-10-17 02:27:38,336][62408] Updated weights for policy 1, policy_version 54460 (0.0008) -[2023-10-17 02:27:38,730][62373] Updated weights for policy 0, policy_version 54850 (0.0010) -[2023-10-17 02:27:39,106][62373] Updated weights for policy 0, policy_version 54860 (0.0011) -[2023-10-17 02:27:39,478][62373] Updated weights for policy 0, policy_version 54870 (0.0011) -[2023-10-17 02:27:39,845][62373] Updated weights for policy 0, policy_version 54880 (0.0007) -[2023-10-17 02:27:42,204][62408] Updated weights for policy 1, policy_version 54470 (0.0007) -[2023-10-17 02:27:42,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 111968256. Throughput: 0: 1773.2, 1: 1760.4. Samples: 28003672. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-17 02:27:42,214][61453] Avg episode reward: [(0, '10.060'), (1, '10.470')] -[2023-10-17 02:27:42,569][62408] Updated weights for policy 1, policy_version 54480 (0.0010) -[2023-10-17 02:27:42,941][62408] Updated weights for policy 1, policy_version 54490 (0.0010) -[2023-10-17 02:27:43,529][62373] Updated weights for policy 0, policy_version 54890 (0.0008) -[2023-10-17 02:27:43,900][62373] Updated weights for policy 0, policy_version 54900 (0.0011) -[2023-10-17 02:27:44,273][62373] Updated weights for policy 0, policy_version 54910 (0.0009) -[2023-10-17 02:27:46,749][62408] Updated weights for policy 1, policy_version 54500 (0.0008) -[2023-10-17 02:27:47,124][62408] Updated weights for policy 1, policy_version 54510 (0.0011) -[2023-10-17 02:27:47,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 112033792. Throughput: 0: 1778.7, 1: 1787.7. Samples: 28025736. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-17 02:27:47,215][61453] Avg episode reward: [(0, '9.480'), (1, '10.080')] -[2023-10-17 02:27:47,494][62408] Updated weights for policy 1, policy_version 54520 (0.0011) -[2023-10-17 02:27:48,047][62373] Updated weights for policy 0, policy_version 54920 (0.0008) -[2023-10-17 02:27:48,413][62373] Updated weights for policy 0, policy_version 54930 (0.0010) -[2023-10-17 02:27:48,778][62373] Updated weights for policy 0, policy_version 54940 (0.0008) -[2023-10-17 02:27:51,151][62408] Updated weights for policy 1, policy_version 54530 (0.0008) -[2023-10-17 02:27:51,516][62408] Updated weights for policy 1, policy_version 54540 (0.0010) -[2023-10-17 02:27:51,886][62408] Updated weights for policy 1, policy_version 54550 (0.0009) -[2023-10-17 02:27:52,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 112099328. Throughput: 0: 1774.0, 1: 1764.0. Samples: 28035790. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-17 02:27:52,215][61453] Avg episode reward: [(0, '10.010'), (1, '9.490')] -[2023-10-17 02:27:52,252][62408] Updated weights for policy 1, policy_version 54560 (0.0009) -[2023-10-17 02:27:52,459][62373] Updated weights for policy 0, policy_version 54950 (0.0007) -[2023-10-17 02:27:52,830][62373] Updated weights for policy 0, policy_version 54960 (0.0007) -[2023-10-17 02:27:53,191][62373] Updated weights for policy 0, policy_version 54970 (0.0007) -[2023-10-17 02:27:56,111][62408] Updated weights for policy 1, policy_version 54570 (0.0010) -[2023-10-17 02:27:56,479][62408] Updated weights for policy 1, policy_version 54580 (0.0007) -[2023-10-17 02:27:56,845][62408] Updated weights for policy 1, policy_version 54590 (0.0009) -[2023-10-17 02:27:56,983][62373] Updated weights for policy 0, policy_version 54980 (0.0009) -[2023-10-17 02:27:57,214][61453] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 112197632. Throughput: 0: 1777.7, 1: 1788.9. Samples: 28057800. Policy #0 lag: (min: 13.0, avg: 13.0, max: 13.0) -[2023-10-17 02:27:57,215][61453] Avg episode reward: [(0, '10.400'), (1, '9.500')] -[2023-10-17 02:27:57,346][62373] Updated weights for policy 0, policy_version 54990 (0.0010) -[2023-10-17 02:27:57,714][62373] Updated weights for policy 0, policy_version 55000 (0.0007) -[2023-10-17 02:28:00,670][62408] Updated weights for policy 1, policy_version 54600 (0.0008) -[2023-10-17 02:28:01,038][62408] Updated weights for policy 1, policy_version 54610 (0.0007) -[2023-10-17 02:28:01,404][62408] Updated weights for policy 1, policy_version 54620 (0.0009) -[2023-10-17 02:28:01,463][62373] Updated weights for policy 0, policy_version 55010 (0.0008) -[2023-10-17 02:28:01,840][62373] Updated weights for policy 0, policy_version 55020 (0.0007) -[2023-10-17 02:28:02,210][62373] Updated weights for policy 0, policy_version 55030 (0.0008) -[2023-10-17 02:28:02,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 112263168. Throughput: 0: 1800.6, 1: 1753.0. Samples: 28078158. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-17 02:28:02,214][61453] Avg episode reward: [(0, '10.650'), (1, '8.760')] -[2023-10-17 02:28:02,587][62373] Updated weights for policy 0, policy_version 55040 (0.0009) -[2023-10-17 02:28:05,284][62408] Updated weights for policy 1, policy_version 54630 (0.0008) -[2023-10-17 02:28:05,679][62408] Updated weights for policy 1, policy_version 54640 (0.0008) -[2023-10-17 02:28:06,038][62408] Updated weights for policy 1, policy_version 54650 (0.0011) -[2023-10-17 02:28:06,459][62373] Updated weights for policy 0, policy_version 55050 (0.0009) -[2023-10-17 02:28:06,825][62373] Updated weights for policy 0, policy_version 55060 (0.0009) -[2023-10-17 02:28:07,198][62373] Updated weights for policy 0, policy_version 55070 (0.0008) -[2023-10-17 02:28:07,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 112328704. Throughput: 0: 1775.3, 1: 1785.1. Samples: 28089688. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-17 02:28:07,215][61453] Avg episode reward: [(0, '10.780'), (1, '8.700')] -[2023-10-17 02:28:09,911][62408] Updated weights for policy 1, policy_version 54660 (0.0007) -[2023-10-17 02:28:10,275][62408] Updated weights for policy 1, policy_version 54670 (0.0008) -[2023-10-17 02:28:10,640][62408] Updated weights for policy 1, policy_version 54680 (0.0009) -[2023-10-17 02:28:11,050][62373] Updated weights for policy 0, policy_version 55080 (0.0009) -[2023-10-17 02:28:11,420][62373] Updated weights for policy 0, policy_version 55090 (0.0008) -[2023-10-17 02:28:11,804][62373] Updated weights for policy 0, policy_version 55100 (0.0008) -[2023-10-17 02:28:12,214][61453] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 112427008. Throughput: 0: 1799.4, 1: 1759.4. Samples: 28110220. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-17 02:28:12,215][61453] Avg episode reward: [(0, '10.010'), (1, '8.030')] -[2023-10-17 02:28:14,482][62408] Updated weights for policy 1, policy_version 54690 (0.0008) -[2023-10-17 02:28:14,850][62408] Updated weights for policy 1, policy_version 54700 (0.0008) -[2023-10-17 02:28:15,219][62408] Updated weights for policy 1, policy_version 54710 (0.0008) -[2023-10-17 02:28:15,470][62373] Updated weights for policy 0, policy_version 55110 (0.0008) -[2023-10-17 02:28:15,586][62408] Updated weights for policy 1, policy_version 54720 (0.0008) -[2023-10-17 02:28:15,836][62373] Updated weights for policy 0, policy_version 55120 (0.0008) -[2023-10-17 02:28:16,198][62373] Updated weights for policy 0, policy_version 55130 (0.0008) -[2023-10-17 02:28:17,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 112492544. Throughput: 0: 1777.5, 1: 1758.9. Samples: 28131254. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-17 02:28:17,215][61453] Avg episode reward: [(0, '10.070'), (1, '8.380')] -[2023-10-17 02:28:19,313][62408] Updated weights for policy 1, policy_version 54730 (0.0007) -[2023-10-17 02:28:19,681][62408] Updated weights for policy 1, policy_version 54740 (0.0007) -[2023-10-17 02:28:19,945][62373] Updated weights for policy 0, policy_version 55140 (0.0008) -[2023-10-17 02:28:20,055][62408] Updated weights for policy 1, policy_version 54750 (0.0007) -[2023-10-17 02:28:20,300][62373] Updated weights for policy 0, policy_version 55150 (0.0008) -[2023-10-17 02:28:20,673][62373] Updated weights for policy 0, policy_version 55160 (0.0011) -[2023-10-17 02:28:22,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 112558080. Throughput: 0: 1799.5, 1: 1769.3. Samples: 28142656. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-17 02:28:22,214][61453] Avg episode reward: [(0, '10.360'), (1, '8.830')] -[2023-10-17 02:28:23,709][62408] Updated weights for policy 1, policy_version 54760 (0.0008) -[2023-10-17 02:28:24,079][62408] Updated weights for policy 1, policy_version 54770 (0.0010) -[2023-10-17 02:28:24,440][62408] Updated weights for policy 1, policy_version 54780 (0.0008) -[2023-10-17 02:28:24,582][62373] Updated weights for policy 0, policy_version 55170 (0.0008) -[2023-10-17 02:28:24,951][62373] Updated weights for policy 0, policy_version 55180 (0.0008) -[2023-10-17 02:28:25,325][62373] Updated weights for policy 0, policy_version 55190 (0.0009) -[2023-10-17 02:28:25,700][62373] Updated weights for policy 0, policy_version 55200 (0.0009) -[2023-10-17 02:28:27,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 112623616. Throughput: 0: 1776.4, 1: 1767.1. Samples: 28163130. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-17 02:28:27,215][61453] Avg episode reward: [(0, '10.020'), (1, '9.110')] -[2023-10-17 02:28:28,315][62408] Updated weights for policy 1, policy_version 54790 (0.0009) -[2023-10-17 02:28:28,691][62408] Updated weights for policy 1, policy_version 54800 (0.0009) -[2023-10-17 02:28:29,062][62408] Updated weights for policy 1, policy_version 54810 (0.0008) -[2023-10-17 02:28:29,459][62373] Updated weights for policy 0, policy_version 55210 (0.0009) -[2023-10-17 02:28:29,825][62373] Updated weights for policy 0, policy_version 55220 (0.0010) -[2023-10-17 02:28:30,182][62373] Updated weights for policy 0, policy_version 55230 (0.0010) -[2023-10-17 02:28:32,214][61453] Fps is (10 sec: 13106.7, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 112689152. Throughput: 0: 1774.9, 1: 1770.0. Samples: 28185256. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-10-17 02:28:32,215][61453] Avg episode reward: [(0, '9.900'), (1, '9.480')] -[2023-10-17 02:28:32,968][62408] Updated weights for policy 1, policy_version 54820 (0.0008) -[2023-10-17 02:28:33,333][62408] Updated weights for policy 1, policy_version 54830 (0.0010) -[2023-10-17 02:28:33,703][62408] Updated weights for policy 1, policy_version 54840 (0.0008) -[2023-10-17 02:28:33,900][62373] Updated weights for policy 0, policy_version 55240 (0.0008) -[2023-10-17 02:28:34,265][62373] Updated weights for policy 0, policy_version 55250 (0.0008) -[2023-10-17 02:28:34,641][62373] Updated weights for policy 0, policy_version 55260 (0.0011) -[2023-10-17 02:28:37,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 112754688. Throughput: 0: 1776.4, 1: 1761.6. Samples: 28195000. Policy #0 lag: (min: 31.0, avg: 41.6, max: 63.0) -[2023-10-17 02:28:37,214][61453] Avg episode reward: [(0, '9.360'), (1, '10.310')] -[2023-10-17 02:28:37,583][62408] Updated weights for policy 1, policy_version 54850 (0.0009) -[2023-10-17 02:28:37,955][62408] Updated weights for policy 1, policy_version 54860 (0.0007) -[2023-10-17 02:28:38,316][62408] Updated weights for policy 1, policy_version 54870 (0.0007) -[2023-10-17 02:28:38,453][62373] Updated weights for policy 0, policy_version 55270 (0.0007) -[2023-10-17 02:28:38,684][62408] Updated weights for policy 1, policy_version 54880 (0.0007) -[2023-10-17 02:28:38,817][62373] Updated weights for policy 0, policy_version 55280 (0.0007) -[2023-10-17 02:28:39,196][62373] Updated weights for policy 0, policy_version 55290 (0.0010) -[2023-10-17 02:28:42,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 112820224. Throughput: 0: 1776.9, 1: 1762.5. Samples: 28217074. Policy #0 lag: (min: 31.0, avg: 41.6, max: 63.0) -[2023-10-17 02:28:42,215][61453] Avg episode reward: [(0, '10.320'), (1, '10.540')] -[2023-10-17 02:28:42,429][62408] Updated weights for policy 1, policy_version 54890 (0.0007) -[2023-10-17 02:28:42,803][62408] Updated weights for policy 1, policy_version 54900 (0.0007) -[2023-10-17 02:28:42,937][62373] Updated weights for policy 0, policy_version 55300 (0.0007) -[2023-10-17 02:28:43,167][62408] Updated weights for policy 1, policy_version 54910 (0.0009) -[2023-10-17 02:28:43,295][62373] Updated weights for policy 0, policy_version 55310 (0.0008) -[2023-10-17 02:28:43,679][62373] Updated weights for policy 0, policy_version 55320 (0.0010) -[2023-10-17 02:28:47,130][62408] Updated weights for policy 1, policy_version 54920 (0.0008) -[2023-10-17 02:28:47,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 112885760. Throughput: 0: 1790.4, 1: 1788.2. Samples: 28239194. Policy #0 lag: (min: 31.0, avg: 41.6, max: 63.0) -[2023-10-17 02:28:47,214][61453] Avg episode reward: [(0, '10.490'), (1, '10.130')] -[2023-10-17 02:28:47,441][62373] Updated weights for policy 0, policy_version 55330 (0.0008) -[2023-10-17 02:28:47,505][62408] Updated weights for policy 1, policy_version 54930 (0.0009) -[2023-10-17 02:28:47,815][62373] Updated weights for policy 0, policy_version 55340 (0.0008) -[2023-10-17 02:28:47,876][62408] Updated weights for policy 1, policy_version 54940 (0.0009) -[2023-10-17 02:28:48,185][62373] Updated weights for policy 0, policy_version 55350 (0.0008) -[2023-10-17 02:28:48,549][62373] Updated weights for policy 0, policy_version 55360 (0.0009) -[2023-10-17 02:28:51,711][62408] Updated weights for policy 1, policy_version 54950 (0.0008) -[2023-10-17 02:28:52,103][62408] Updated weights for policy 1, policy_version 54960 (0.0007) -[2023-10-17 02:28:52,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 112951296. Throughput: 0: 1776.5, 1: 1757.6. Samples: 28248726. Policy #0 lag: (min: 31.0, avg: 41.6, max: 63.0) -[2023-10-17 02:28:52,215][61453] Avg episode reward: [(0, '10.880'), (1, '10.100')] -[2023-10-17 02:28:52,391][62373] Updated weights for policy 0, policy_version 55370 (0.0008) -[2023-10-17 02:28:52,470][62408] Updated weights for policy 1, policy_version 54970 (0.0007) -[2023-10-17 02:28:52,756][62373] Updated weights for policy 0, policy_version 55380 (0.0011) -[2023-10-17 02:28:53,124][62373] Updated weights for policy 0, policy_version 55390 (0.0009) -[2023-10-17 02:28:56,362][62408] Updated weights for policy 1, policy_version 54980 (0.0007) -[2023-10-17 02:28:56,732][62408] Updated weights for policy 1, policy_version 54990 (0.0009) -[2023-10-17 02:28:56,965][62373] Updated weights for policy 0, policy_version 55400 (0.0009) -[2023-10-17 02:28:57,093][62408] Updated weights for policy 1, policy_version 55000 (0.0009) -[2023-10-17 02:28:57,214][61453] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 113016832. Throughput: 0: 1780.5, 1: 1784.1. Samples: 28270622. Policy #0 lag: (min: 31.0, avg: 41.6, max: 63.0) -[2023-10-17 02:28:57,214][61453] Avg episode reward: [(0, '10.630'), (1, '9.630')] -[2023-10-17 02:28:57,333][62373] Updated weights for policy 0, policy_version 55410 (0.0007) -[2023-10-17 02:28:57,706][62373] Updated weights for policy 0, policy_version 55420 (0.0007) -[2023-10-17 02:29:00,904][62408] Updated weights for policy 1, policy_version 55010 (0.0008) -[2023-10-17 02:29:01,265][62408] Updated weights for policy 1, policy_version 55020 (0.0007) -[2023-10-17 02:29:01,501][62373] Updated weights for policy 0, policy_version 55430 (0.0007) -[2023-10-17 02:29:01,629][62408] Updated weights for policy 1, policy_version 55030 (0.0007) -[2023-10-17 02:29:01,868][62373] Updated weights for policy 0, policy_version 55440 (0.0007) -[2023-10-17 02:29:01,992][62408] Updated weights for policy 1, policy_version 55040 (0.0007) -[2023-10-17 02:29:02,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 113115136. Throughput: 0: 1784.6, 1: 1758.2. Samples: 28290680. Policy #0 lag: (min: 31.0, avg: 41.6, max: 63.0) -[2023-10-17 02:29:02,214][61453] Avg episode reward: [(0, '10.920'), (1, '10.480')] -[2023-10-17 02:29:02,234][62373] Updated weights for policy 0, policy_version 55450 (0.0009) -[2023-10-17 02:29:05,786][62408] Updated weights for policy 1, policy_version 55050 (0.0008) -[2023-10-17 02:29:06,136][62373] Updated weights for policy 0, policy_version 55460 (0.0009) -[2023-10-17 02:29:06,154][62408] Updated weights for policy 1, policy_version 55060 (0.0008) -[2023-10-17 02:29:06,492][62373] Updated weights for policy 0, policy_version 55470 (0.0010) -[2023-10-17 02:29:06,516][62408] Updated weights for policy 1, policy_version 55070 (0.0009) -[2023-10-17 02:29:06,871][62373] Updated weights for policy 0, policy_version 55480 (0.0011) -[2023-10-17 02:29:07,214][61453] Fps is (10 sec: 19660.9, 60 sec: 14745.6, 300 sec: 14218.0). Total num frames: 113213440. Throughput: 0: 1769.2, 1: 1779.4. Samples: 28302340. Policy #0 lag: (min: 31.0, avg: 41.6, max: 63.0) -[2023-10-17 02:29:07,214][61453] Avg episode reward: [(0, '10.410'), (1, '10.060')] -[2023-10-17 02:29:10,314][62408] Updated weights for policy 1, policy_version 55080 (0.0010) -[2023-10-17 02:29:10,643][62373] Updated weights for policy 0, policy_version 55490 (0.0009) -[2023-10-17 02:29:10,682][62408] Updated weights for policy 1, policy_version 55090 (0.0009) -[2023-10-17 02:29:11,016][62373] Updated weights for policy 0, policy_version 55500 (0.0009) -[2023-10-17 02:29:11,040][62408] Updated weights for policy 1, policy_version 55100 (0.0008) -[2023-10-17 02:29:11,384][62373] Updated weights for policy 0, policy_version 55510 (0.0009) -[2023-10-17 02:29:11,758][62373] Updated weights for policy 0, policy_version 55520 (0.0008) -[2023-10-17 02:29:12,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 113278976. Throughput: 0: 1791.3, 1: 1760.4. Samples: 28322956. Policy #0 lag: (min: 23.0, avg: 23.0, max: 24.0) -[2023-10-17 02:29:12,214][61453] Avg episode reward: [(0, '10.060'), (1, '8.910')] -[2023-10-17 02:29:14,830][62408] Updated weights for policy 1, policy_version 55110 (0.0007) -[2023-10-17 02:29:15,198][62408] Updated weights for policy 1, policy_version 55120 (0.0008) -[2023-10-17 02:29:15,556][62408] Updated weights for policy 1, policy_version 55130 (0.0008) -[2023-10-17 02:29:15,606][62373] Updated weights for policy 0, policy_version 55530 (0.0008) -[2023-10-17 02:29:15,974][62373] Updated weights for policy 0, policy_version 55540 (0.0009) -[2023-10-17 02:29:16,346][62373] Updated weights for policy 0, policy_version 55550 (0.0008) -[2023-10-17 02:29:17,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 113344512. Throughput: 0: 1766.2, 1: 1754.7. Samples: 28343698. Policy #0 lag: (min: 23.0, avg: 23.0, max: 24.0) -[2023-10-17 02:29:17,214][61453] Avg episode reward: [(0, '10.150'), (1, '9.490')] -[2023-10-17 02:29:19,525][62408] Updated weights for policy 1, policy_version 55140 (0.0008) -[2023-10-17 02:29:19,903][62408] Updated weights for policy 1, policy_version 55150 (0.0007) -[2023-10-17 02:29:20,037][62373] Updated weights for policy 0, policy_version 55560 (0.0009) -[2023-10-17 02:29:20,279][62408] Updated weights for policy 1, policy_version 55160 (0.0008) -[2023-10-17 02:29:20,400][62373] Updated weights for policy 0, policy_version 55570 (0.0008) -[2023-10-17 02:29:20,770][62373] Updated weights for policy 0, policy_version 55580 (0.0008) -[2023-10-17 02:29:22,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 113410048. Throughput: 0: 1795.5, 1: 1771.8. Samples: 28355526. Policy #0 lag: (min: 23.0, avg: 23.0, max: 24.0) -[2023-10-17 02:29:22,215][61453] Avg episode reward: [(0, '9.900'), (1, '9.650')] -[2023-10-17 02:29:24,217][62408] Updated weights for policy 1, policy_version 55170 (0.0008) -[2023-10-17 02:29:24,575][62408] Updated weights for policy 1, policy_version 55180 (0.0009) -[2023-10-17 02:29:24,601][62373] Updated weights for policy 0, policy_version 55590 (0.0009) -[2023-10-17 02:29:24,946][62408] Updated weights for policy 1, policy_version 55190 (0.0008) -[2023-10-17 02:29:24,972][62373] Updated weights for policy 0, policy_version 55600 (0.0009) -[2023-10-17 02:29:25,309][62408] Updated weights for policy 1, policy_version 55200 (0.0008) -[2023-10-17 02:29:25,340][62373] Updated weights for policy 0, policy_version 55610 (0.0008) -[2023-10-17 02:29:27,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 113475584. Throughput: 0: 1766.0, 1: 1756.4. Samples: 28375580. Policy #0 lag: (min: 23.0, avg: 23.0, max: 24.0) -[2023-10-17 02:29:27,215][61453] Avg episode reward: [(0, '9.770'), (1, '10.020')] -[2023-10-17 02:29:28,987][62373] Updated weights for policy 0, policy_version 55620 (0.0008) -[2023-10-17 02:29:29,223][62408] Updated weights for policy 1, policy_version 55210 (0.0010) -[2023-10-17 02:29:29,357][62373] Updated weights for policy 0, policy_version 55630 (0.0009) -[2023-10-17 02:29:29,594][62408] Updated weights for policy 1, policy_version 55220 (0.0010) -[2023-10-17 02:29:29,731][62373] Updated weights for policy 0, policy_version 55640 (0.0008) -[2023-10-17 02:29:29,952][62408] Updated weights for policy 1, policy_version 55230 (0.0007) -[2023-10-17 02:29:32,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 113541120. Throughput: 0: 1768.1, 1: 1752.3. Samples: 28397614. Policy #0 lag: (min: 23.0, avg: 23.0, max: 24.0) -[2023-10-17 02:29:32,215][61453] Avg episode reward: [(0, '9.100'), (1, '10.090')] -[2023-10-17 02:29:32,225][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000055232_56557568.pth... -[2023-10-17 02:29:32,226][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000055648_56983552.pth... -[2023-10-17 02:29:32,255][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000053600_54886400.pth -[2023-10-17 02:29:32,263][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000053984_55279616.pth -[2023-10-17 02:29:33,570][62373] Updated weights for policy 0, policy_version 55650 (0.0009) -[2023-10-17 02:29:33,802][62408] Updated weights for policy 1, policy_version 55240 (0.0009) -[2023-10-17 02:29:33,937][62373] Updated weights for policy 0, policy_version 55660 (0.0008) -[2023-10-17 02:29:34,167][62408] Updated weights for policy 1, policy_version 55250 (0.0008) -[2023-10-17 02:29:34,310][62373] Updated weights for policy 0, policy_version 55670 (0.0010) -[2023-10-17 02:29:34,526][62408] Updated weights for policy 1, policy_version 55260 (0.0008) -[2023-10-17 02:29:34,680][62373] Updated weights for policy 0, policy_version 55680 (0.0008) -[2023-10-17 02:29:37,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 113606656. Throughput: 0: 1770.6, 1: 1750.1. Samples: 28407156. Policy #0 lag: (min: 23.0, avg: 23.0, max: 24.0) -[2023-10-17 02:29:37,215][61453] Avg episode reward: [(0, '9.370'), (1, '9.840')] -[2023-10-17 02:29:38,509][62373] Updated weights for policy 0, policy_version 55690 (0.0009) -[2023-10-17 02:29:38,533][62408] Updated weights for policy 1, policy_version 55270 (0.0007) -[2023-10-17 02:29:38,878][62373] Updated weights for policy 0, policy_version 55700 (0.0009) -[2023-10-17 02:29:38,916][62408] Updated weights for policy 1, policy_version 55280 (0.0008) -[2023-10-17 02:29:39,250][62373] Updated weights for policy 0, policy_version 55710 (0.0010) -[2023-10-17 02:29:39,280][62408] Updated weights for policy 1, policy_version 55290 (0.0008) -[2023-10-17 02:29:42,214][61453] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 113672192. Throughput: 0: 1769.5, 1: 1742.0. Samples: 28428638. Policy #0 lag: (min: 23.0, avg: 23.0, max: 24.0) -[2023-10-17 02:29:42,214][61453] Avg episode reward: [(0, '9.790'), (1, '10.300')] -[2023-10-17 02:29:42,916][62373] Updated weights for policy 0, policy_version 55720 (0.0011) -[2023-10-17 02:29:43,180][62408] Updated weights for policy 1, policy_version 55300 (0.0007) -[2023-10-17 02:29:43,291][62373] Updated weights for policy 0, policy_version 55730 (0.0008) -[2023-10-17 02:29:43,539][62408] Updated weights for policy 1, policy_version 55310 (0.0008) -[2023-10-17 02:29:43,663][62373] Updated weights for policy 0, policy_version 55740 (0.0009) -[2023-10-17 02:29:43,904][62408] Updated weights for policy 1, policy_version 55320 (0.0007) -[2023-10-17 02:29:47,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 113737728. Throughput: 0: 1787.4, 1: 1763.9. Samples: 28450492. Policy #0 lag: (min: 23.0, avg: 23.0, max: 24.0) -[2023-10-17 02:29:47,215][61453] Avg episode reward: [(0, '9.690'), (1, '10.120')] -[2023-10-17 02:29:47,685][62373] Updated weights for policy 0, policy_version 55750 (0.0009) -[2023-10-17 02:29:47,808][62408] Updated weights for policy 1, policy_version 55330 (0.0008) -[2023-10-17 02:29:48,052][62373] Updated weights for policy 0, policy_version 55760 (0.0008) -[2023-10-17 02:29:48,173][62408] Updated weights for policy 1, policy_version 55340 (0.0009) -[2023-10-17 02:29:48,415][62373] Updated weights for policy 0, policy_version 55770 (0.0007) -[2023-10-17 02:29:48,532][62408] Updated weights for policy 1, policy_version 55350 (0.0008) -[2023-10-17 02:29:48,901][62408] Updated weights for policy 1, policy_version 55360 (0.0010) -[2023-10-17 02:29:52,200][62373] Updated weights for policy 0, policy_version 55780 (0.0008) -[2023-10-17 02:29:52,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 113803264. Throughput: 0: 1773.1, 1: 1734.8. Samples: 28460194. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-17 02:29:52,214][61453] Avg episode reward: [(0, '9.660'), (1, '9.970')] -[2023-10-17 02:29:52,567][62408] Updated weights for policy 1, policy_version 55370 (0.0007) -[2023-10-17 02:29:52,568][62373] Updated weights for policy 0, policy_version 55790 (0.0008) -[2023-10-17 02:29:52,928][62373] Updated weights for policy 0, policy_version 55800 (0.0009) -[2023-10-17 02:29:52,933][62408] Updated weights for policy 1, policy_version 55380 (0.0008) -[2023-10-17 02:29:53,305][62408] Updated weights for policy 1, policy_version 55390 (0.0008) -[2023-10-17 02:29:56,794][62373] Updated weights for policy 0, policy_version 55810 (0.0009) -[2023-10-17 02:29:57,103][62408] Updated weights for policy 1, policy_version 55400 (0.0007) -[2023-10-17 02:29:57,163][62373] Updated weights for policy 0, policy_version 55820 (0.0009) -[2023-10-17 02:29:57,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 113868800. Throughput: 0: 1780.1, 1: 1759.6. Samples: 28482242. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-17 02:29:57,215][61453] Avg episode reward: [(0, '9.730'), (1, '10.200')] -[2023-10-17 02:29:57,474][62408] Updated weights for policy 1, policy_version 55410 (0.0008) -[2023-10-17 02:29:57,534][62373] Updated weights for policy 0, policy_version 55830 (0.0009) -[2023-10-17 02:29:57,844][62408] Updated weights for policy 1, policy_version 55420 (0.0007) -[2023-10-17 02:29:57,896][62373] Updated weights for policy 0, policy_version 55840 (0.0007) -[2023-10-17 02:30:01,717][62408] Updated weights for policy 1, policy_version 55430 (0.0009) -[2023-10-17 02:30:01,819][62373] Updated weights for policy 0, policy_version 55850 (0.0007) -[2023-10-17 02:30:02,085][62408] Updated weights for policy 1, policy_version 55440 (0.0008) -[2023-10-17 02:30:02,181][62373] Updated weights for policy 0, policy_version 55860 (0.0008) -[2023-10-17 02:30:02,214][61453] Fps is (10 sec: 13106.7, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 113934336. Throughput: 0: 1788.9, 1: 1753.4. Samples: 28503102. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-17 02:30:02,215][61453] Avg episode reward: [(0, '9.600'), (1, '10.280')] -[2023-10-17 02:30:02,459][62408] Updated weights for policy 1, policy_version 55450 (0.0007) -[2023-10-17 02:30:02,550][62373] Updated weights for policy 0, policy_version 55870 (0.0007) -[2023-10-17 02:30:06,243][62373] Updated weights for policy 0, policy_version 55880 (0.0008) -[2023-10-17 02:30:06,447][62408] Updated weights for policy 1, policy_version 55460 (0.0008) -[2023-10-17 02:30:06,612][62373] Updated weights for policy 0, policy_version 55890 (0.0007) -[2023-10-17 02:30:06,814][62408] Updated weights for policy 1, policy_version 55470 (0.0009) -[2023-10-17 02:30:06,973][62373] Updated weights for policy 0, policy_version 55900 (0.0008) -[2023-10-17 02:30:07,177][62408] Updated weights for policy 1, policy_version 55480 (0.0008) -[2023-10-17 02:30:07,214][61453] Fps is (10 sec: 16384.1, 60 sec: 13653.3, 300 sec: 14218.0). Total num frames: 114032640. Throughput: 0: 1771.0, 1: 1741.6. Samples: 28513590. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-17 02:30:07,215][61453] Avg episode reward: [(0, '9.840'), (1, '9.750')] -[2023-10-17 02:30:10,839][62373] Updated weights for policy 0, policy_version 55910 (0.0007) -[2023-10-17 02:30:10,932][62408] Updated weights for policy 1, policy_version 55490 (0.0010) -[2023-10-17 02:30:11,203][62373] Updated weights for policy 0, policy_version 55920 (0.0007) -[2023-10-17 02:30:11,296][62408] Updated weights for policy 1, policy_version 55500 (0.0008) -[2023-10-17 02:30:11,568][62373] Updated weights for policy 0, policy_version 55930 (0.0008) -[2023-10-17 02:30:11,660][62408] Updated weights for policy 1, policy_version 55510 (0.0008) -[2023-10-17 02:30:12,034][62408] Updated weights for policy 1, policy_version 55520 (0.0007) -[2023-10-17 02:30:12,214][61453] Fps is (10 sec: 19661.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 114130944. Throughput: 0: 1787.8, 1: 1762.1. Samples: 28535328. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-17 02:30:12,215][61453] Avg episode reward: [(0, '9.760'), (1, '9.860')] -[2023-10-17 02:30:15,423][62373] Updated weights for policy 0, policy_version 55940 (0.0009) -[2023-10-17 02:30:15,761][62408] Updated weights for policy 1, policy_version 55530 (0.0008) -[2023-10-17 02:30:15,792][62373] Updated weights for policy 0, policy_version 55950 (0.0008) -[2023-10-17 02:30:16,132][62408] Updated weights for policy 1, policy_version 55540 (0.0009) -[2023-10-17 02:30:16,159][62373] Updated weights for policy 0, policy_version 55960 (0.0007) -[2023-10-17 02:30:16,497][62408] Updated weights for policy 1, policy_version 55550 (0.0009) -[2023-10-17 02:30:17,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 114196480. Throughput: 0: 1756.7, 1: 1736.0. Samples: 28554784. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-17 02:30:17,214][61453] Avg episode reward: [(0, '10.270'), (1, '9.290')] -[2023-10-17 02:30:19,915][62373] Updated weights for policy 0, policy_version 55970 (0.0007) -[2023-10-17 02:30:20,291][62373] Updated weights for policy 0, policy_version 55980 (0.0010) -[2023-10-17 02:30:20,469][62408] Updated weights for policy 1, policy_version 55560 (0.0010) -[2023-10-17 02:30:20,667][62373] Updated weights for policy 0, policy_version 55990 (0.0009) -[2023-10-17 02:30:20,837][62408] Updated weights for policy 1, policy_version 55570 (0.0009) -[2023-10-17 02:30:21,033][62373] Updated weights for policy 0, policy_version 56000 (0.0008) -[2023-10-17 02:30:21,193][62408] Updated weights for policy 1, policy_version 55580 (0.0010) -[2023-10-17 02:30:22,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 114262016. Throughput: 0: 1788.4, 1: 1762.8. Samples: 28566960. Policy #0 lag: (min: 23.0, avg: 23.0, max: 23.0) -[2023-10-17 02:30:22,215][61453] Avg episode reward: [(0, '10.410'), (1, '9.640')] -[2023-10-17 02:30:24,711][62373] Updated weights for policy 0, policy_version 56010 (0.0009) -[2023-10-17 02:30:25,033][62408] Updated weights for policy 1, policy_version 55590 (0.0010) -[2023-10-17 02:30:25,087][62373] Updated weights for policy 0, policy_version 56020 (0.0008) -[2023-10-17 02:30:25,402][62408] Updated weights for policy 1, policy_version 55600 (0.0010) -[2023-10-17 02:30:25,449][62373] Updated weights for policy 0, policy_version 56030 (0.0009) -[2023-10-17 02:30:25,778][62408] Updated weights for policy 1, policy_version 55610 (0.0010) -[2023-10-17 02:30:27,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 114327552. Throughput: 0: 1762.0, 1: 1750.6. Samples: 28586706. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:30:27,214][61453] Avg episode reward: [(0, '10.180'), (1, '10.110')] -[2023-10-17 02:30:29,367][62373] Updated weights for policy 0, policy_version 56040 (0.0007) -[2023-10-17 02:30:29,743][62373] Updated weights for policy 0, policy_version 56050 (0.0008) -[2023-10-17 02:30:29,886][62408] Updated weights for policy 1, policy_version 55620 (0.0008) -[2023-10-17 02:30:30,109][62373] Updated weights for policy 0, policy_version 56060 (0.0008) -[2023-10-17 02:30:30,281][62408] Updated weights for policy 1, policy_version 55630 (0.0009) -[2023-10-17 02:30:30,654][62408] Updated weights for policy 1, policy_version 55640 (0.0009) -[2023-10-17 02:30:32,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 114393088. Throughput: 0: 1756.0, 1: 1746.6. Samples: 28608110. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:30:32,215][61453] Avg episode reward: [(0, '10.770'), (1, '10.350')] -[2023-10-17 02:30:33,793][62373] Updated weights for policy 0, policy_version 56070 (0.0007) -[2023-10-17 02:30:34,171][62373] Updated weights for policy 0, policy_version 56080 (0.0008) -[2023-10-17 02:30:34,375][62408] Updated weights for policy 1, policy_version 55650 (0.0007) -[2023-10-17 02:30:34,532][62373] Updated weights for policy 0, policy_version 56090 (0.0007) -[2023-10-17 02:30:34,751][62408] Updated weights for policy 1, policy_version 55660 (0.0009) -[2023-10-17 02:30:35,108][62408] Updated weights for policy 1, policy_version 55670 (0.0010) -[2023-10-17 02:30:35,477][62408] Updated weights for policy 1, policy_version 55680 (0.0009) -[2023-10-17 02:30:37,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 114458624. Throughput: 0: 1756.5, 1: 1765.1. Samples: 28618666. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:30:37,215][61453] Avg episode reward: [(0, '10.420'), (1, '9.920')] -[2023-10-17 02:30:38,299][62373] Updated weights for policy 0, policy_version 56100 (0.0007) -[2023-10-17 02:30:38,668][62373] Updated weights for policy 0, policy_version 56110 (0.0009) -[2023-10-17 02:30:39,040][62373] Updated weights for policy 0, policy_version 56120 (0.0008) -[2023-10-17 02:30:39,250][62408] Updated weights for policy 1, policy_version 55690 (0.0008) -[2023-10-17 02:30:39,622][62408] Updated weights for policy 1, policy_version 55700 (0.0007) -[2023-10-17 02:30:39,992][62408] Updated weights for policy 1, policy_version 55710 (0.0008) -[2023-10-17 02:30:42,214][61453] Fps is (10 sec: 13107.6, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 114524160. Throughput: 0: 1762.8, 1: 1742.5. Samples: 28639982. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:30:42,215][61453] Avg episode reward: [(0, '10.460'), (1, '10.260')] -[2023-10-17 02:30:42,753][62373] Updated weights for policy 0, policy_version 56130 (0.0008) -[2023-10-17 02:30:43,109][62373] Updated weights for policy 0, policy_version 56140 (0.0007) -[2023-10-17 02:30:43,483][62373] Updated weights for policy 0, policy_version 56150 (0.0008) -[2023-10-17 02:30:43,710][62408] Updated weights for policy 1, policy_version 55720 (0.0008) -[2023-10-17 02:30:43,843][62373] Updated weights for policy 0, policy_version 56160 (0.0007) -[2023-10-17 02:30:44,067][62408] Updated weights for policy 1, policy_version 55730 (0.0008) -[2023-10-17 02:30:44,446][62408] Updated weights for policy 1, policy_version 55740 (0.0010) -[2023-10-17 02:30:47,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 114589696. Throughput: 0: 1785.2, 1: 1758.1. Samples: 28662546. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:30:47,215][61453] Avg episode reward: [(0, '10.280'), (1, '10.720')] -[2023-10-17 02:30:47,607][62373] Updated weights for policy 0, policy_version 56170 (0.0007) -[2023-10-17 02:30:47,986][62373] Updated weights for policy 0, policy_version 56180 (0.0008) -[2023-10-17 02:30:48,206][62408] Updated weights for policy 1, policy_version 55750 (0.0009) -[2023-10-17 02:30:48,351][62373] Updated weights for policy 0, policy_version 56190 (0.0009) -[2023-10-17 02:30:48,571][62408] Updated weights for policy 1, policy_version 55760 (0.0009) -[2023-10-17 02:30:48,933][62408] Updated weights for policy 1, policy_version 55770 (0.0010) -[2023-10-17 02:30:52,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 114655232. Throughput: 0: 1769.5, 1: 1753.6. Samples: 28672128. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:30:52,214][61453] Avg episode reward: [(0, '10.530'), (1, '10.440')] -[2023-10-17 02:30:52,253][62373] Updated weights for policy 0, policy_version 56200 (0.0008) -[2023-10-17 02:30:52,636][62373] Updated weights for policy 0, policy_version 56210 (0.0008) -[2023-10-17 02:30:52,658][62408] Updated weights for policy 1, policy_version 55780 (0.0007) -[2023-10-17 02:30:53,009][62373] Updated weights for policy 0, policy_version 56220 (0.0008) -[2023-10-17 02:30:53,027][62408] Updated weights for policy 1, policy_version 55790 (0.0007) -[2023-10-17 02:30:53,386][62408] Updated weights for policy 1, policy_version 55800 (0.0009) -[2023-10-17 02:30:56,734][62373] Updated weights for policy 0, policy_version 56230 (0.0009) -[2023-10-17 02:30:57,101][62373] Updated weights for policy 0, policy_version 56240 (0.0009) -[2023-10-17 02:30:57,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 114720768. Throughput: 0: 1778.0, 1: 1749.7. Samples: 28694072. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:30:57,215][61453] Avg episode reward: [(0, '9.810'), (1, '10.000')] -[2023-10-17 02:30:57,324][62408] Updated weights for policy 1, policy_version 55810 (0.0008) -[2023-10-17 02:30:57,476][62373] Updated weights for policy 0, policy_version 56250 (0.0008) -[2023-10-17 02:30:57,694][62408] Updated weights for policy 1, policy_version 55820 (0.0007) -[2023-10-17 02:30:58,077][62408] Updated weights for policy 1, policy_version 55830 (0.0008) -[2023-10-17 02:30:58,444][62408] Updated weights for policy 1, policy_version 55840 (0.0007) -[2023-10-17 02:31:01,346][62373] Updated weights for policy 0, policy_version 56260 (0.0009) -[2023-10-17 02:31:01,712][62373] Updated weights for policy 0, policy_version 56270 (0.0008) -[2023-10-17 02:31:02,091][62373] Updated weights for policy 0, policy_version 56280 (0.0007) -[2023-10-17 02:31:02,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 114786304. Throughput: 0: 1785.2, 1: 1781.2. Samples: 28715272. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:31:02,215][61453] Avg episode reward: [(0, '10.000'), (1, '9.600')] -[2023-10-17 02:31:02,296][62408] Updated weights for policy 1, policy_version 55850 (0.0008) -[2023-10-17 02:31:02,675][62408] Updated weights for policy 1, policy_version 55860 (0.0008) -[2023-10-17 02:31:03,046][62408] Updated weights for policy 1, policy_version 55870 (0.0008) -[2023-10-17 02:31:05,973][62373] Updated weights for policy 0, policy_version 56290 (0.0008) -[2023-10-17 02:31:06,357][62373] Updated weights for policy 0, policy_version 56300 (0.0011) -[2023-10-17 02:31:06,734][62373] Updated weights for policy 0, policy_version 56310 (0.0010) -[2023-10-17 02:31:06,990][62408] Updated weights for policy 1, policy_version 55880 (0.0009) -[2023-10-17 02:31:07,098][62373] Updated weights for policy 0, policy_version 56320 (0.0009) -[2023-10-17 02:31:07,214][61453] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 114884608. Throughput: 0: 1772.2, 1: 1750.1. Samples: 28725466. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-17 02:31:07,214][61453] Avg episode reward: [(0, '9.700'), (1, '9.720')] -[2023-10-17 02:31:07,358][62408] Updated weights for policy 1, policy_version 55890 (0.0007) -[2023-10-17 02:31:07,731][62408] Updated weights for policy 1, policy_version 55900 (0.0008) -[2023-10-17 02:31:10,848][62373] Updated weights for policy 0, policy_version 56330 (0.0010) -[2023-10-17 02:31:11,223][62373] Updated weights for policy 0, policy_version 56340 (0.0011) -[2023-10-17 02:31:11,595][62373] Updated weights for policy 0, policy_version 56350 (0.0008) -[2023-10-17 02:31:11,691][62408] Updated weights for policy 1, policy_version 55910 (0.0008) -[2023-10-17 02:31:12,051][62408] Updated weights for policy 1, policy_version 55920 (0.0008) -[2023-10-17 02:31:12,214][61453] Fps is (10 sec: 16384.0, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 114950144. Throughput: 0: 1792.3, 1: 1766.9. Samples: 28746870. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-17 02:31:12,215][61453] Avg episode reward: [(0, '9.860'), (1, '9.590')] -[2023-10-17 02:31:12,416][62408] Updated weights for policy 1, policy_version 55930 (0.0008) -[2023-10-17 02:31:15,250][62373] Updated weights for policy 0, policy_version 56360 (0.0009) -[2023-10-17 02:31:15,625][62373] Updated weights for policy 0, policy_version 56370 (0.0008) -[2023-10-17 02:31:16,002][62373] Updated weights for policy 0, policy_version 56380 (0.0008) -[2023-10-17 02:31:16,253][62408] Updated weights for policy 1, policy_version 55940 (0.0007) -[2023-10-17 02:31:16,619][62408] Updated weights for policy 1, policy_version 55950 (0.0008) -[2023-10-17 02:31:16,999][62408] Updated weights for policy 1, policy_version 55960 (0.0010) -[2023-10-17 02:31:17,214][61453] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 115015680. Throughput: 0: 1775.9, 1: 1756.6. Samples: 28767070. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-17 02:31:17,215][61453] Avg episode reward: [(0, '10.170'), (1, '10.230')] -[2023-10-17 02:31:19,937][62373] Updated weights for policy 0, policy_version 56390 (0.0007) -[2023-10-17 02:31:20,305][62373] Updated weights for policy 0, policy_version 56400 (0.0008) -[2023-10-17 02:31:20,671][62373] Updated weights for policy 0, policy_version 56410 (0.0009) -[2023-10-17 02:31:20,763][62408] Updated weights for policy 1, policy_version 55970 (0.0010) -[2023-10-17 02:31:21,132][62408] Updated weights for policy 1, policy_version 55980 (0.0008) -[2023-10-17 02:31:21,488][62408] Updated weights for policy 1, policy_version 55990 (0.0010) -[2023-10-17 02:31:21,856][62408] Updated weights for policy 1, policy_version 56000 (0.0008) -[2023-10-17 02:31:22,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 115113984. Throughput: 0: 1799.0, 1: 1755.7. Samples: 28778630. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-17 02:31:22,215][61453] Avg episode reward: [(0, '10.780'), (1, '10.620')] -[2023-10-17 02:31:24,408][62373] Updated weights for policy 0, policy_version 56420 (0.0007) -[2023-10-17 02:31:24,781][62373] Updated weights for policy 0, policy_version 56430 (0.0009) -[2023-10-17 02:31:25,157][62373] Updated weights for policy 0, policy_version 56440 (0.0009) -[2023-10-17 02:31:25,690][62408] Updated weights for policy 1, policy_version 56010 (0.0008) -[2023-10-17 02:31:26,070][62408] Updated weights for policy 1, policy_version 56020 (0.0009) -[2023-10-17 02:31:26,438][62408] Updated weights for policy 1, policy_version 56030 (0.0007) -[2023-10-17 02:31:27,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 115179520. Throughput: 0: 1771.3, 1: 1766.6. Samples: 28799188. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-17 02:31:27,215][61453] Avg episode reward: [(0, '10.000'), (1, '10.080')] -[2023-10-17 02:31:29,083][62373] Updated weights for policy 0, policy_version 56450 (0.0008) -[2023-10-17 02:31:29,445][62373] Updated weights for policy 0, policy_version 56460 (0.0010) -[2023-10-17 02:31:29,812][62373] Updated weights for policy 0, policy_version 56470 (0.0007) -[2023-10-17 02:31:30,182][62373] Updated weights for policy 0, policy_version 56480 (0.0007) -[2023-10-17 02:31:30,338][62408] Updated weights for policy 1, policy_version 56040 (0.0009) -[2023-10-17 02:31:30,708][62408] Updated weights for policy 1, policy_version 56050 (0.0009) -[2023-10-17 02:31:31,079][62408] Updated weights for policy 1, policy_version 56060 (0.0008) -[2023-10-17 02:31:32,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 115245056. Throughput: 0: 1764.0, 1: 1744.8. Samples: 28820444. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-17 02:31:32,215][61453] Avg episode reward: [(0, '10.060'), (1, '9.930')] -[2023-10-17 02:31:32,223][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000056480_57835520.pth... -[2023-10-17 02:31:32,223][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000056064_57409536.pth... -[2023-10-17 02:31:32,263][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000054816_56131584.pth -[2023-10-17 02:31:32,264][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000054400_55705600.pth -[2023-10-17 02:31:33,996][62373] Updated weights for policy 0, policy_version 56490 (0.0008) -[2023-10-17 02:31:34,374][62373] Updated weights for policy 0, policy_version 56500 (0.0008) -[2023-10-17 02:31:34,750][62373] Updated weights for policy 0, policy_version 56510 (0.0009) -[2023-10-17 02:31:34,819][62408] Updated weights for policy 1, policy_version 56070 (0.0007) -[2023-10-17 02:31:35,192][62408] Updated weights for policy 1, policy_version 56080 (0.0009) -[2023-10-17 02:31:35,546][62408] Updated weights for policy 1, policy_version 56090 (0.0009) -[2023-10-17 02:31:37,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 115310592. Throughput: 0: 1762.7, 1: 1773.8. Samples: 28831272. Policy #0 lag: (min: 11.0, avg: 11.0, max: 11.0) -[2023-10-17 02:31:37,214][61453] Avg episode reward: [(0, '10.560'), (1, '9.700')] -[2023-10-17 02:31:38,436][62373] Updated weights for policy 0, policy_version 56520 (0.0009) -[2023-10-17 02:31:38,804][62373] Updated weights for policy 0, policy_version 56530 (0.0009) -[2023-10-17 02:31:39,170][62373] Updated weights for policy 0, policy_version 56540 (0.0009) -[2023-10-17 02:31:39,494][62408] Updated weights for policy 1, policy_version 56100 (0.0009) -[2023-10-17 02:31:39,864][62408] Updated weights for policy 1, policy_version 56110 (0.0008) -[2023-10-17 02:31:40,236][62408] Updated weights for policy 1, policy_version 56120 (0.0008) -[2023-10-17 02:31:42,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 115376128. Throughput: 0: 1767.2, 1: 1748.5. Samples: 28852276. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:31:42,215][61453] Avg episode reward: [(0, '10.960'), (1, '9.990')] -[2023-10-17 02:31:43,042][62373] Updated weights for policy 0, policy_version 56550 (0.0010) -[2023-10-17 02:31:43,405][62373] Updated weights for policy 0, policy_version 56560 (0.0011) -[2023-10-17 02:31:43,773][62373] Updated weights for policy 0, policy_version 56570 (0.0008) -[2023-10-17 02:31:43,984][62408] Updated weights for policy 1, policy_version 56130 (0.0008) -[2023-10-17 02:31:44,349][62408] Updated weights for policy 1, policy_version 56140 (0.0007) -[2023-10-17 02:31:44,719][62408] Updated weights for policy 1, policy_version 56150 (0.0008) -[2023-10-17 02:31:45,086][62408] Updated weights for policy 1, policy_version 56160 (0.0008) -[2023-10-17 02:31:47,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 115441664. Throughput: 0: 1787.0, 1: 1752.1. Samples: 28874532. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:31:47,215][61453] Avg episode reward: [(0, '10.850'), (1, '9.490')] -[2023-10-17 02:31:47,578][62373] Updated weights for policy 0, policy_version 56580 (0.0008) -[2023-10-17 02:31:47,949][62373] Updated weights for policy 0, policy_version 56590 (0.0008) -[2023-10-17 02:31:48,324][62373] Updated weights for policy 0, policy_version 56600 (0.0010) -[2023-10-17 02:31:48,879][62408] Updated weights for policy 1, policy_version 56170 (0.0008) -[2023-10-17 02:31:49,249][62408] Updated weights for policy 1, policy_version 56180 (0.0007) -[2023-10-17 02:31:49,615][62408] Updated weights for policy 1, policy_version 56190 (0.0010) -[2023-10-17 02:31:52,089][62373] Updated weights for policy 0, policy_version 56610 (0.0007) -[2023-10-17 02:31:52,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 115507200. Throughput: 0: 1771.7, 1: 1759.6. Samples: 28884376. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:31:52,215][61453] Avg episode reward: [(0, '11.020'), (1, '8.780')] -[2023-10-17 02:31:52,456][62373] Updated weights for policy 0, policy_version 56620 (0.0008) -[2023-10-17 02:31:52,822][62373] Updated weights for policy 0, policy_version 56630 (0.0008) -[2023-10-17 02:31:53,185][62373] Updated weights for policy 0, policy_version 56640 (0.0007) -[2023-10-17 02:31:53,288][62408] Updated weights for policy 1, policy_version 56200 (0.0008) -[2023-10-17 02:31:53,648][62408] Updated weights for policy 1, policy_version 56210 (0.0008) -[2023-10-17 02:31:54,018][62408] Updated weights for policy 1, policy_version 56220 (0.0010) -[2023-10-17 02:31:57,026][62373] Updated weights for policy 0, policy_version 56650 (0.0008) -[2023-10-17 02:31:57,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 115572736. Throughput: 0: 1778.1, 1: 1773.5. Samples: 28906690. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:31:57,215][61453] Avg episode reward: [(0, '10.610'), (1, '9.480')] -[2023-10-17 02:31:57,402][62373] Updated weights for policy 0, policy_version 56660 (0.0009) -[2023-10-17 02:31:57,759][62373] Updated weights for policy 0, policy_version 56670 (0.0007) -[2023-10-17 02:31:57,784][62408] Updated weights for policy 1, policy_version 56230 (0.0008) -[2023-10-17 02:31:58,144][62408] Updated weights for policy 1, policy_version 56240 (0.0007) -[2023-10-17 02:31:58,510][62408] Updated weights for policy 1, policy_version 56250 (0.0009) -[2023-10-17 02:32:01,586][62373] Updated weights for policy 0, policy_version 56680 (0.0009) -[2023-10-17 02:32:01,963][62373] Updated weights for policy 0, policy_version 56690 (0.0007) -[2023-10-17 02:32:02,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 115638272. Throughput: 0: 1778.8, 1: 1795.2. Samples: 28927904. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:32:02,215][61453] Avg episode reward: [(0, '10.830'), (1, '9.190')] -[2023-10-17 02:32:02,327][62373] Updated weights for policy 0, policy_version 56700 (0.0007) -[2023-10-17 02:32:02,360][62408] Updated weights for policy 1, policy_version 56260 (0.0008) -[2023-10-17 02:32:02,761][62408] Updated weights for policy 1, policy_version 56270 (0.0009) -[2023-10-17 02:32:03,138][62408] Updated weights for policy 1, policy_version 56280 (0.0008) -[2023-10-17 02:32:06,084][62373] Updated weights for policy 0, policy_version 56710 (0.0008) -[2023-10-17 02:32:06,457][62373] Updated weights for policy 0, policy_version 56720 (0.0008) -[2023-10-17 02:32:06,836][62373] Updated weights for policy 0, policy_version 56730 (0.0008) -[2023-10-17 02:32:06,917][62408] Updated weights for policy 1, policy_version 56290 (0.0008) -[2023-10-17 02:32:07,214][61453] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 115736576. Throughput: 0: 1774.1, 1: 1772.5. Samples: 28938228. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:32:07,215][61453] Avg episode reward: [(0, '11.330'), (1, '8.660')] -[2023-10-17 02:32:07,215][62094] Saving new best policy, reward=11.330! -[2023-10-17 02:32:07,289][62408] Updated weights for policy 1, policy_version 56300 (0.0007) -[2023-10-17 02:32:07,655][62408] Updated weights for policy 1, policy_version 56310 (0.0009) -[2023-10-17 02:32:08,019][62408] Updated weights for policy 1, policy_version 56320 (0.0008) -[2023-10-17 02:32:10,573][62373] Updated weights for policy 0, policy_version 56740 (0.0008) -[2023-10-17 02:32:10,935][62373] Updated weights for policy 0, policy_version 56750 (0.0010) -[2023-10-17 02:32:11,299][62373] Updated weights for policy 0, policy_version 56760 (0.0009) -[2023-10-17 02:32:11,845][62408] Updated weights for policy 1, policy_version 56330 (0.0008) -[2023-10-17 02:32:12,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 115802112. Throughput: 0: 1788.8, 1: 1790.2. Samples: 28960246. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:32:12,215][61453] Avg episode reward: [(0, '9.930'), (1, '8.380')] -[2023-10-17 02:32:12,217][62408] Updated weights for policy 1, policy_version 56340 (0.0007) -[2023-10-17 02:32:12,589][62408] Updated weights for policy 1, policy_version 56350 (0.0008) -[2023-10-17 02:32:15,111][62373] Updated weights for policy 0, policy_version 56770 (0.0009) -[2023-10-17 02:32:15,481][62373] Updated weights for policy 0, policy_version 56780 (0.0008) -[2023-10-17 02:32:15,855][62373] Updated weights for policy 0, policy_version 56790 (0.0008) -[2023-10-17 02:32:16,229][62373] Updated weights for policy 0, policy_version 56800 (0.0009) -[2023-10-17 02:32:16,421][62408] Updated weights for policy 1, policy_version 56360 (0.0010) -[2023-10-17 02:32:16,788][62408] Updated weights for policy 1, policy_version 56370 (0.0010) -[2023-10-17 02:32:17,150][62408] Updated weights for policy 1, policy_version 56380 (0.0009) -[2023-10-17 02:32:17,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 115867648. Throughput: 0: 1769.9, 1: 1793.1. Samples: 28980776. Policy #0 lag: (min: 31.0, avg: 45.7, max: 63.0) -[2023-10-17 02:32:17,214][61453] Avg episode reward: [(0, '10.280'), (1, '9.410')] -[2023-10-17 02:32:20,008][62373] Updated weights for policy 0, policy_version 56810 (0.0009) -[2023-10-17 02:32:20,385][62373] Updated weights for policy 0, policy_version 56820 (0.0007) -[2023-10-17 02:32:20,749][62373] Updated weights for policy 0, policy_version 56830 (0.0008) -[2023-10-17 02:32:21,012][62408] Updated weights for policy 1, policy_version 56390 (0.0009) -[2023-10-17 02:32:21,380][62408] Updated weights for policy 1, policy_version 56400 (0.0008) -[2023-10-17 02:32:21,751][62408] Updated weights for policy 1, policy_version 56410 (0.0009) -[2023-10-17 02:32:22,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 115965952. Throughput: 0: 1795.0, 1: 1780.8. Samples: 28992186. Policy #0 lag: (min: 31.0, avg: 45.7, max: 63.0) -[2023-10-17 02:32:22,215][61453] Avg episode reward: [(0, '11.020'), (1, '10.130')] -[2023-10-17 02:32:24,492][62373] Updated weights for policy 0, policy_version 56840 (0.0007) -[2023-10-17 02:32:24,871][62373] Updated weights for policy 0, policy_version 56850 (0.0010) -[2023-10-17 02:32:25,245][62373] Updated weights for policy 0, policy_version 56860 (0.0007) -[2023-10-17 02:32:25,472][62408] Updated weights for policy 1, policy_version 56420 (0.0009) -[2023-10-17 02:32:25,839][62408] Updated weights for policy 1, policy_version 56430 (0.0008) -[2023-10-17 02:32:26,220][62408] Updated weights for policy 1, policy_version 56440 (0.0012) -[2023-10-17 02:32:27,214][61453] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 116031488. Throughput: 0: 1766.9, 1: 1797.0. Samples: 29012652. Policy #0 lag: (min: 31.0, avg: 45.7, max: 63.0) -[2023-10-17 02:32:27,215][61453] Avg episode reward: [(0, '10.730'), (1, '10.010')] -[2023-10-17 02:32:29,040][62373] Updated weights for policy 0, policy_version 56870 (0.0007) -[2023-10-17 02:32:29,420][62373] Updated weights for policy 0, policy_version 56880 (0.0011) -[2023-10-17 02:32:29,786][62373] Updated weights for policy 0, policy_version 56890 (0.0011) -[2023-10-17 02:32:30,104][62408] Updated weights for policy 1, policy_version 56450 (0.0011) -[2023-10-17 02:32:30,474][62408] Updated weights for policy 1, policy_version 56460 (0.0008) -[2023-10-17 02:32:30,833][62408] Updated weights for policy 1, policy_version 56470 (0.0007) -[2023-10-17 02:32:31,204][62408] Updated weights for policy 1, policy_version 56480 (0.0009) -[2023-10-17 02:32:32,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 116097024. Throughput: 0: 1766.8, 1: 1774.5. Samples: 29033892. Policy #0 lag: (min: 31.0, avg: 45.7, max: 63.0) -[2023-10-17 02:32:32,214][61453] Avg episode reward: [(0, '11.430'), (1, '9.960')] -[2023-10-17 02:32:32,222][62094] Saving new best policy, reward=11.430! -[2023-10-17 02:32:33,519][62373] Updated weights for policy 0, policy_version 56900 (0.0009) -[2023-10-17 02:32:33,887][62373] Updated weights for policy 0, policy_version 56910 (0.0008) -[2023-10-17 02:32:34,255][62373] Updated weights for policy 0, policy_version 56920 (0.0008) -[2023-10-17 02:32:35,042][62408] Updated weights for policy 1, policy_version 56490 (0.0007) -[2023-10-17 02:32:35,417][62408] Updated weights for policy 1, policy_version 56500 (0.0007) -[2023-10-17 02:32:35,790][62408] Updated weights for policy 1, policy_version 56510 (0.0008) -[2023-10-17 02:32:37,214][61453] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 116162560. Throughput: 0: 1765.1, 1: 1798.7. Samples: 29044744. Policy #0 lag: (min: 31.0, avg: 45.7, max: 63.0) -[2023-10-17 02:32:37,214][61453] Avg episode reward: [(0, '11.080'), (1, '9.710')] -[2023-10-17 02:32:38,110][62373] Updated weights for policy 0, policy_version 56930 (0.0008) -[2023-10-17 02:32:38,475][62373] Updated weights for policy 0, policy_version 56940 (0.0008) -[2023-10-17 02:32:38,849][62373] Updated weights for policy 0, policy_version 56950 (0.0007) -[2023-10-17 02:32:39,213][62373] Updated weights for policy 0, policy_version 56960 (0.0008) -[2023-10-17 02:32:39,565][62408] Updated weights for policy 1, policy_version 56520 (0.0008) -[2023-10-17 02:32:39,938][62408] Updated weights for policy 1, policy_version 56530 (0.0008) -[2023-10-17 02:32:40,301][62408] Updated weights for policy 1, policy_version 56540 (0.0007) -[2023-10-17 02:32:42,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 116228096. Throughput: 0: 1767.4, 1: 1763.6. Samples: 29065584. Policy #0 lag: (min: 31.0, avg: 45.7, max: 63.0) -[2023-10-17 02:32:42,215][61453] Avg episode reward: [(0, '10.530'), (1, '10.500')] -[2023-10-17 02:32:42,953][62373] Updated weights for policy 0, policy_version 56970 (0.0008) -[2023-10-17 02:32:43,327][62373] Updated weights for policy 0, policy_version 56980 (0.0011) -[2023-10-17 02:32:43,699][62373] Updated weights for policy 0, policy_version 56990 (0.0009) -[2023-10-17 02:32:44,034][62408] Updated weights for policy 1, policy_version 56550 (0.0009) -[2023-10-17 02:32:44,397][62408] Updated weights for policy 1, policy_version 56560 (0.0010) -[2023-10-17 02:32:44,761][62408] Updated weights for policy 1, policy_version 56570 (0.0009) -[2023-10-17 02:32:47,214][61453] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 116293632. Throughput: 0: 1793.1, 1: 1766.8. Samples: 29088102. Policy #0 lag: (min: 31.0, avg: 45.7, max: 63.0) -[2023-10-17 02:32:47,215][61453] Avg episode reward: [(0, '10.670'), (1, '10.800')] -[2023-10-17 02:32:47,472][62373] Updated weights for policy 0, policy_version 57000 (0.0009) -[2023-10-17 02:32:47,847][62373] Updated weights for policy 0, policy_version 57010 (0.0009) -[2023-10-17 02:32:48,217][62373] Updated weights for policy 0, policy_version 57020 (0.0010) -[2023-10-17 02:32:48,616][62408] Updated weights for policy 1, policy_version 56580 (0.0007) -[2023-10-17 02:32:49,009][62408] Updated weights for policy 1, policy_version 56590 (0.0010) -[2023-10-17 02:32:49,378][62408] Updated weights for policy 1, policy_version 56600 (0.0010) -[2023-10-17 02:32:52,125][62373] Updated weights for policy 0, policy_version 57030 (0.0009) -[2023-10-17 02:32:52,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 116359168. Throughput: 0: 1772.1, 1: 1767.7. Samples: 29097522. Policy #0 lag: (min: 31.0, avg: 45.7, max: 63.0) -[2023-10-17 02:32:52,214][61453] Avg episode reward: [(0, '11.210'), (1, '9.790')] -[2023-10-17 02:32:52,490][62373] Updated weights for policy 0, policy_version 57040 (0.0008) -[2023-10-17 02:32:52,856][62373] Updated weights for policy 0, policy_version 57050 (0.0010) -[2023-10-17 02:32:53,100][62408] Updated weights for policy 1, policy_version 56610 (0.0008) -[2023-10-17 02:32:53,472][62408] Updated weights for policy 1, policy_version 56620 (0.0009) -[2023-10-17 02:32:53,838][62408] Updated weights for policy 1, policy_version 56630 (0.0009) -[2023-10-17 02:32:54,210][62408] Updated weights for policy 1, policy_version 56640 (0.0010) -[2023-10-17 02:32:56,590][62373] Updated weights for policy 0, policy_version 57060 (0.0010) -[2023-10-17 02:32:56,957][62373] Updated weights for policy 0, policy_version 57070 (0.0011) -[2023-10-17 02:32:57,214][61453] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 116424704. Throughput: 0: 1781.2, 1: 1760.4. Samples: 29119618. Policy #0 lag: (min: 16.0, avg: 39.0, max: 48.0) -[2023-10-17 02:32:57,214][61453] Avg episode reward: [(0, '10.990'), (1, '9.100')] -[2023-10-17 02:32:57,329][62373] Updated weights for policy 0, policy_version 57080 (0.0008) -[2023-10-17 02:32:57,962][62408] Updated weights for policy 1, policy_version 56650 (0.0008) -[2023-10-17 02:32:58,334][62408] Updated weights for policy 1, policy_version 56660 (0.0011) -[2023-10-17 02:32:58,695][62408] Updated weights for policy 1, policy_version 56670 (0.0007) -[2023-10-17 02:33:01,072][62373] Updated weights for policy 0, policy_version 57090 (0.0010) -[2023-10-17 02:33:01,446][62373] Updated weights for policy 0, policy_version 57100 (0.0010) -[2023-10-17 02:33:01,815][62373] Updated weights for policy 0, policy_version 57110 (0.0007) -[2023-10-17 02:33:02,182][62373] Updated weights for policy 0, policy_version 57120 (0.0007) -[2023-10-17 02:33:02,214][61453] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14218.0). Total num frames: 116523008. Throughput: 0: 1774.7, 1: 1778.9. Samples: 29140692. Policy #0 lag: (min: 16.0, avg: 39.0, max: 48.0) -[2023-10-17 02:33:02,215][61453] Avg episode reward: [(0, '10.910'), (1, '10.660')] -[2023-10-17 02:33:02,600][62408] Updated weights for policy 1, policy_version 56680 (0.0008) -[2023-10-17 02:33:02,979][62408] Updated weights for policy 1, policy_version 56690 (0.0008) -[2023-10-17 02:33:03,347][62408] Updated weights for policy 1, policy_version 56700 (0.0009) -[2023-10-17 02:33:06,069][62373] Updated weights for policy 0, policy_version 57130 (0.0008) -[2023-10-17 02:33:06,451][62373] Updated weights for policy 0, policy_version 57140 (0.0008) -[2023-10-17 02:33:06,814][62373] Updated weights for policy 0, policy_version 57150 (0.0007) -[2023-10-17 02:33:07,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 116588544. Throughput: 0: 1779.5, 1: 1762.1. Samples: 29151556. Policy #0 lag: (min: 16.0, avg: 39.0, max: 48.0) -[2023-10-17 02:33:07,214][61453] Avg episode reward: [(0, '10.620'), (1, '10.180')] -[2023-10-17 02:33:07,290][62408] Updated weights for policy 1, policy_version 56710 (0.0008) -[2023-10-17 02:33:07,663][62408] Updated weights for policy 1, policy_version 56720 (0.0007) -[2023-10-17 02:33:08,033][62408] Updated weights for policy 1, policy_version 56730 (0.0008) -[2023-10-17 02:33:10,479][62373] Updated weights for policy 0, policy_version 57160 (0.0010) -[2023-10-17 02:33:10,854][62373] Updated weights for policy 0, policy_version 57170 (0.0009) -[2023-10-17 02:33:11,219][62373] Updated weights for policy 0, policy_version 57180 (0.0011) -[2023-10-17 02:33:11,785][62408] Updated weights for policy 1, policy_version 56740 (0.0007) -[2023-10-17 02:33:12,156][62408] Updated weights for policy 1, policy_version 56750 (0.0008) -[2023-10-17 02:33:12,214][61453] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 116654080. Throughput: 0: 1783.0, 1: 1770.4. Samples: 29172556. Policy #0 lag: (min: 16.0, avg: 39.0, max: 48.0) -[2023-10-17 02:33:12,214][61453] Avg episode reward: [(0, '10.890'), (1, '10.030')] -[2023-10-17 02:33:12,527][62408] Updated weights for policy 1, policy_version 56760 (0.0007) -[2023-10-17 02:33:15,030][62373] Updated weights for policy 0, policy_version 57190 (0.0010) -[2023-10-17 02:33:15,392][62373] Updated weights for policy 0, policy_version 57200 (0.0007) -[2023-10-17 02:33:15,772][62373] Updated weights for policy 0, policy_version 57210 (0.0007) -[2023-10-17 02:33:16,355][62408] Updated weights for policy 1, policy_version 56770 (0.0008) -[2023-10-17 02:33:16,726][62408] Updated weights for policy 1, policy_version 56780 (0.0007) -[2023-10-17 02:33:17,085][62408] Updated weights for policy 1, policy_version 56790 (0.0009) -[2023-10-17 02:33:17,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 116719616. Throughput: 0: 1774.9, 1: 1772.3. Samples: 29193520. Policy #0 lag: (min: 16.0, avg: 39.0, max: 48.0) -[2023-10-17 02:33:17,215][61453] Avg episode reward: [(0, '11.130'), (1, '10.150')] -[2023-10-17 02:33:17,454][62408] Updated weights for policy 1, policy_version 56800 (0.0010) -[2023-10-17 02:33:19,451][62373] Updated weights for policy 0, policy_version 57220 (0.0009) -[2023-10-17 02:33:19,823][62373] Updated weights for policy 0, policy_version 57230 (0.0007) -[2023-10-17 02:33:20,189][62373] Updated weights for policy 0, policy_version 57240 (0.0008) -[2023-10-17 02:33:21,317][62408] Updated weights for policy 1, policy_version 56810 (0.0008) -[2023-10-17 02:33:21,695][62408] Updated weights for policy 1, policy_version 56820 (0.0009) -[2023-10-17 02:33:22,062][62408] Updated weights for policy 1, policy_version 56830 (0.0009) -[2023-10-17 02:33:22,214][61453] Fps is (10 sec: 16383.5, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 116817920. Throughput: 0: 1793.2, 1: 1759.1. Samples: 29204602. Policy #0 lag: (min: 16.0, avg: 39.0, max: 48.0) -[2023-10-17 02:33:22,215][61453] Avg episode reward: [(0, '11.720'), (1, '9.930')] -[2023-10-17 02:33:22,216][62094] Saving new best policy, reward=11.720! -[2023-10-17 02:33:24,040][62373] Updated weights for policy 0, policy_version 57250 (0.0008) -[2023-10-17 02:33:24,414][62373] Updated weights for policy 0, policy_version 57260 (0.0009) -[2023-10-17 02:33:24,789][62373] Updated weights for policy 0, policy_version 57270 (0.0009) -[2023-10-17 02:33:25,153][62373] Updated weights for policy 0, policy_version 57280 (0.0008) -[2023-10-17 02:33:25,842][62408] Updated weights for policy 1, policy_version 56840 (0.0007) -[2023-10-17 02:33:26,212][62408] Updated weights for policy 1, policy_version 56850 (0.0008) -[2023-10-17 02:33:26,579][62408] Updated weights for policy 1, policy_version 56860 (0.0007) -[2023-10-17 02:33:27,214][61453] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 116883456. Throughput: 0: 1773.6, 1: 1777.1. Samples: 29225368. Policy #0 lag: (min: 16.0, avg: 39.0, max: 48.0) -[2023-10-17 02:33:27,215][61453] Avg episode reward: [(0, '10.720'), (1, '10.240')] -[2023-10-17 02:33:28,952][62373] Updated weights for policy 0, policy_version 57290 (0.0009) -[2023-10-17 02:33:29,321][62373] Updated weights for policy 0, policy_version 57300 (0.0008) -[2023-10-17 02:33:29,695][62373] Updated weights for policy 0, policy_version 57310 (0.0008) -[2023-10-17 02:33:30,431][62408] Updated weights for policy 1, policy_version 56870 (0.0010) -[2023-10-17 02:33:30,797][62408] Updated weights for policy 1, policy_version 56880 (0.0009) -[2023-10-17 02:33:31,165][62408] Updated weights for policy 1, policy_version 56890 (0.0009) -[2023-10-17 02:33:32,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 116948992. Throughput: 0: 1777.4, 1: 1749.0. Samples: 29246790. Policy #0 lag: (min: 31.0, avg: 31.8, max: 49.0) -[2023-10-17 02:33:32,214][61453] Avg episode reward: [(0, '11.070'), (1, '8.840')] -[2023-10-17 02:33:32,226][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000056896_58261504.pth... -[2023-10-17 02:33:32,227][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000057312_58687488.pth... -[2023-10-17 02:33:32,263][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000055648_56983552.pth -[2023-10-17 02:33:32,266][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000055232_56557568.pth -[2023-10-17 02:33:33,244][62373] Updated weights for policy 0, policy_version 57320 (0.0010) -[2023-10-17 02:33:33,619][62373] Updated weights for policy 0, policy_version 57330 (0.0009) -[2023-10-17 02:33:33,981][62373] Updated weights for policy 0, policy_version 57340 (0.0010) -[2023-10-17 02:33:35,003][62408] Updated weights for policy 1, policy_version 56900 (0.0009) -[2023-10-17 02:33:35,393][62408] Updated weights for policy 1, policy_version 56910 (0.0007) -[2023-10-17 02:33:35,756][62408] Updated weights for policy 1, policy_version 56920 (0.0009) -[2023-10-17 02:33:37,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 117014528. Throughput: 0: 1780.9, 1: 1782.1. Samples: 29257856. Policy #0 lag: (min: 31.0, avg: 31.8, max: 49.0) -[2023-10-17 02:33:37,214][61453] Avg episode reward: [(0, '10.670'), (1, '9.280')] -[2023-10-17 02:33:37,850][62373] Updated weights for policy 0, policy_version 57350 (0.0007) -[2023-10-17 02:33:38,221][62373] Updated weights for policy 0, policy_version 57360 (0.0007) -[2023-10-17 02:33:38,588][62373] Updated weights for policy 0, policy_version 57370 (0.0007) -[2023-10-17 02:33:39,801][62408] Updated weights for policy 1, policy_version 56930 (0.0010) -[2023-10-17 02:33:40,166][62408] Updated weights for policy 1, policy_version 56940 (0.0012) -[2023-10-17 02:33:40,528][62408] Updated weights for policy 1, policy_version 56950 (0.0010) -[2023-10-17 02:33:40,897][62408] Updated weights for policy 1, policy_version 56960 (0.0008) -[2023-10-17 02:33:42,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 117080064. Throughput: 0: 1781.0, 1: 1752.5. Samples: 29278628. Policy #0 lag: (min: 31.0, avg: 31.8, max: 49.0) -[2023-10-17 02:33:42,215][61453] Avg episode reward: [(0, '10.280'), (1, '9.080')] -[2023-10-17 02:33:42,434][62373] Updated weights for policy 0, policy_version 57380 (0.0007) -[2023-10-17 02:33:42,809][62373] Updated weights for policy 0, policy_version 57390 (0.0007) -[2023-10-17 02:33:43,178][62373] Updated weights for policy 0, policy_version 57400 (0.0008) -[2023-10-17 02:33:44,661][62408] Updated weights for policy 1, policy_version 56970 (0.0010) -[2023-10-17 02:33:45,021][62408] Updated weights for policy 1, policy_version 56980 (0.0011) -[2023-10-17 02:33:45,390][62408] Updated weights for policy 1, policy_version 56990 (0.0010) -[2023-10-17 02:33:47,019][62373] Updated weights for policy 0, policy_version 57410 (0.0010) -[2023-10-17 02:33:47,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.6, 300 sec: 14218.0). Total num frames: 117145600. Throughput: 0: 1802.9, 1: 1742.9. Samples: 29300250. Policy #0 lag: (min: 31.0, avg: 31.8, max: 49.0) -[2023-10-17 02:33:47,214][61453] Avg episode reward: [(0, '10.670'), (1, '9.580')] -[2023-10-17 02:33:47,379][62373] Updated weights for policy 0, policy_version 57420 (0.0007) -[2023-10-17 02:33:47,754][62373] Updated weights for policy 0, policy_version 57430 (0.0007) -[2023-10-17 02:33:48,118][62373] Updated weights for policy 0, policy_version 57440 (0.0007) -[2023-10-17 02:33:49,245][62408] Updated weights for policy 1, policy_version 57000 (0.0010) -[2023-10-17 02:33:49,624][62408] Updated weights for policy 1, policy_version 57010 (0.0007) -[2023-10-17 02:33:50,000][62408] Updated weights for policy 1, policy_version 57020 (0.0009) -[2023-10-17 02:33:51,931][62373] Updated weights for policy 0, policy_version 57450 (0.0008) -[2023-10-17 02:33:52,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 117211136. Throughput: 0: 1778.3, 1: 1754.2. Samples: 29310518. Policy #0 lag: (min: 31.0, avg: 31.8, max: 49.0) -[2023-10-17 02:33:52,214][61453] Avg episode reward: [(0, '10.440'), (1, '8.760')] -[2023-10-17 02:33:52,301][62373] Updated weights for policy 0, policy_version 57460 (0.0008) -[2023-10-17 02:33:52,675][62373] Updated weights for policy 0, policy_version 57470 (0.0010) -[2023-10-17 02:33:53,855][62408] Updated weights for policy 1, policy_version 57030 (0.0010) -[2023-10-17 02:33:54,218][62408] Updated weights for policy 1, policy_version 57040 (0.0008) -[2023-10-17 02:33:54,589][62408] Updated weights for policy 1, policy_version 57050 (0.0009) -[2023-10-17 02:33:56,421][62373] Updated weights for policy 0, policy_version 57480 (0.0011) -[2023-10-17 02:33:56,792][62373] Updated weights for policy 0, policy_version 57490 (0.0008) -[2023-10-17 02:33:57,160][62373] Updated weights for policy 0, policy_version 57500 (0.0008) -[2023-10-17 02:33:57,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 117276672. Throughput: 0: 1799.6, 1: 1750.3. Samples: 29332300. Policy #0 lag: (min: 31.0, avg: 31.8, max: 49.0) -[2023-10-17 02:33:57,214][61453] Avg episode reward: [(0, '11.460'), (1, '8.670')] -[2023-10-17 02:33:58,232][62408] Updated weights for policy 1, policy_version 57060 (0.0009) -[2023-10-17 02:33:58,593][62408] Updated weights for policy 1, policy_version 57070 (0.0011) -[2023-10-17 02:33:58,957][62408] Updated weights for policy 1, policy_version 57080 (0.0008) -[2023-10-17 02:34:01,010][62373] Updated weights for policy 0, policy_version 57510 (0.0009) -[2023-10-17 02:34:01,376][62373] Updated weights for policy 0, policy_version 57520 (0.0010) -[2023-10-17 02:34:01,750][62373] Updated weights for policy 0, policy_version 57530 (0.0007) -[2023-10-17 02:34:02,214][61453] Fps is (10 sec: 16383.6, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 117374976. Throughput: 0: 1774.8, 1: 1772.2. Samples: 29353134. Policy #0 lag: (min: 31.0, avg: 31.8, max: 49.0) -[2023-10-17 02:34:02,215][61453] Avg episode reward: [(0, '10.850'), (1, '9.460')] -[2023-10-17 02:34:02,780][62408] Updated weights for policy 1, policy_version 57090 (0.0010) -[2023-10-17 02:34:03,157][62408] Updated weights for policy 1, policy_version 57100 (0.0010) -[2023-10-17 02:34:03,522][62408] Updated weights for policy 1, policy_version 57110 (0.0010) -[2023-10-17 02:34:03,887][62408] Updated weights for policy 1, policy_version 57120 (0.0007) -[2023-10-17 02:34:05,542][62373] Updated weights for policy 0, policy_version 57540 (0.0008) -[2023-10-17 02:34:05,904][62373] Updated weights for policy 0, policy_version 57550 (0.0010) -[2023-10-17 02:34:06,278][62373] Updated weights for policy 0, policy_version 57560 (0.0009) -[2023-10-17 02:34:07,214][61453] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 117440512. Throughput: 0: 1788.4, 1: 1760.8. Samples: 29364318. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) -[2023-10-17 02:34:07,215][61453] Avg episode reward: [(0, '11.170'), (1, '9.550')] -[2023-10-17 02:34:07,698][62408] Updated weights for policy 1, policy_version 57130 (0.0010) -[2023-10-17 02:34:08,062][62408] Updated weights for policy 1, policy_version 57140 (0.0008) -[2023-10-17 02:34:08,429][62408] Updated weights for policy 1, policy_version 57150 (0.0008) -[2023-10-17 02:34:10,040][62373] Updated weights for policy 0, policy_version 57570 (0.0009) -[2023-10-17 02:34:10,411][62373] Updated weights for policy 0, policy_version 57580 (0.0007) -[2023-10-17 02:34:10,781][62373] Updated weights for policy 0, policy_version 57590 (0.0011) -[2023-10-17 02:34:11,153][62373] Updated weights for policy 0, policy_version 57600 (0.0011) -[2023-10-17 02:34:12,210][62408] Updated weights for policy 1, policy_version 57160 (0.0010) -[2023-10-17 02:34:12,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 117506048. Throughput: 0: 1788.4, 1: 1771.3. Samples: 29385556. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) -[2023-10-17 02:34:12,215][61453] Avg episode reward: [(0, '11.040'), (1, '9.500')] -[2023-10-17 02:34:12,580][62408] Updated weights for policy 1, policy_version 57170 (0.0008) -[2023-10-17 02:34:12,951][62408] Updated weights for policy 1, policy_version 57180 (0.0008) -[2023-10-17 02:34:14,992][62373] Updated weights for policy 0, policy_version 57610 (0.0008) -[2023-10-17 02:34:15,366][62373] Updated weights for policy 0, policy_version 57620 (0.0008) -[2023-10-17 02:34:15,732][62373] Updated weights for policy 0, policy_version 57630 (0.0010) -[2023-10-17 02:34:16,627][62408] Updated weights for policy 1, policy_version 57190 (0.0010) -[2023-10-17 02:34:16,999][62408] Updated weights for policy 1, policy_version 57200 (0.0009) -[2023-10-17 02:34:17,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 117571584. Throughput: 0: 1768.9, 1: 1784.4. Samples: 29406692. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) -[2023-10-17 02:34:17,215][61453] Avg episode reward: [(0, '11.140'), (1, '9.250')] -[2023-10-17 02:34:17,372][62408] Updated weights for policy 1, policy_version 57210 (0.0008) -[2023-10-17 02:34:19,655][62373] Updated weights for policy 0, policy_version 57640 (0.0009) -[2023-10-17 02:34:20,028][62373] Updated weights for policy 0, policy_version 57650 (0.0009) -[2023-10-17 02:34:20,398][62373] Updated weights for policy 0, policy_version 57660 (0.0008) -[2023-10-17 02:34:21,255][62408] Updated weights for policy 1, policy_version 57220 (0.0009) -[2023-10-17 02:34:21,655][62408] Updated weights for policy 1, policy_version 57230 (0.0008) -[2023-10-17 02:34:22,017][62408] Updated weights for policy 1, policy_version 57240 (0.0008) -[2023-10-17 02:34:22,214][61453] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 117637120. Throughput: 0: 1780.5, 1: 1768.1. Samples: 29417544. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) -[2023-10-17 02:34:22,215][61453] Avg episode reward: [(0, '10.950'), (1, '10.080')] -[2023-10-17 02:34:24,267][62373] Updated weights for policy 0, policy_version 57670 (0.0010) -[2023-10-17 02:34:24,640][62373] Updated weights for policy 0, policy_version 57680 (0.0009) -[2023-10-17 02:34:25,015][62373] Updated weights for policy 0, policy_version 57690 (0.0009) -[2023-10-17 02:34:25,924][62408] Updated weights for policy 1, policy_version 57250 (0.0008) -[2023-10-17 02:34:26,295][62408] Updated weights for policy 1, policy_version 57260 (0.0008) -[2023-10-17 02:34:26,655][62408] Updated weights for policy 1, policy_version 57270 (0.0009) -[2023-10-17 02:34:27,032][62408] Updated weights for policy 1, policy_version 57280 (0.0007) -[2023-10-17 02:34:27,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 117735424. Throughput: 0: 1760.9, 1: 1790.0. Samples: 29438418. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) -[2023-10-17 02:34:27,215][61453] Avg episode reward: [(0, '9.370'), (1, '10.010')] -[2023-10-17 02:34:28,744][62373] Updated weights for policy 0, policy_version 57700 (0.0009) -[2023-10-17 02:34:29,112][62373] Updated weights for policy 0, policy_version 57710 (0.0008) -[2023-10-17 02:34:29,489][62373] Updated weights for policy 0, policy_version 57720 (0.0007) -[2023-10-17 02:34:30,883][62408] Updated weights for policy 1, policy_version 57290 (0.0010) -[2023-10-17 02:34:31,256][62408] Updated weights for policy 1, policy_version 57300 (0.0010) -[2023-10-17 02:34:31,621][62408] Updated weights for policy 1, policy_version 57310 (0.0009) -[2023-10-17 02:34:32,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 117800960. Throughput: 0: 1768.3, 1: 1765.1. Samples: 29459252. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) -[2023-10-17 02:34:32,215][61453] Avg episode reward: [(0, '9.270'), (1, '9.630')] -[2023-10-17 02:34:33,307][62373] Updated weights for policy 0, policy_version 57730 (0.0007) -[2023-10-17 02:34:33,675][62373] Updated weights for policy 0, policy_version 57740 (0.0010) -[2023-10-17 02:34:34,044][62373] Updated weights for policy 0, policy_version 57750 (0.0011) -[2023-10-17 02:34:34,407][62373] Updated weights for policy 0, policy_version 57760 (0.0010) -[2023-10-17 02:34:35,458][62408] Updated weights for policy 1, policy_version 57320 (0.0009) -[2023-10-17 02:34:35,827][62408] Updated weights for policy 1, policy_version 57330 (0.0008) -[2023-10-17 02:34:36,195][62408] Updated weights for policy 1, policy_version 57340 (0.0008) -[2023-10-17 02:34:37,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 117866496. Throughput: 0: 1765.2, 1: 1786.3. Samples: 29470332. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) -[2023-10-17 02:34:37,214][61453] Avg episode reward: [(0, '9.310'), (1, '9.460')] -[2023-10-17 02:34:38,107][62373] Updated weights for policy 0, policy_version 57770 (0.0007) -[2023-10-17 02:34:38,471][62373] Updated weights for policy 0, policy_version 57780 (0.0009) -[2023-10-17 02:34:38,849][62373] Updated weights for policy 0, policy_version 57790 (0.0010) -[2023-10-17 02:34:39,941][62408] Updated weights for policy 1, policy_version 57350 (0.0008) -[2023-10-17 02:34:40,309][62408] Updated weights for policy 1, policy_version 57360 (0.0008) -[2023-10-17 02:34:40,668][62408] Updated weights for policy 1, policy_version 57370 (0.0009) -[2023-10-17 02:34:42,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 117932032. Throughput: 0: 1772.5, 1: 1768.1. Samples: 29491626. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) -[2023-10-17 02:34:42,215][61453] Avg episode reward: [(0, '9.510'), (1, '9.920')] -[2023-10-17 02:34:42,622][62373] Updated weights for policy 0, policy_version 57800 (0.0009) -[2023-10-17 02:34:42,984][62373] Updated weights for policy 0, policy_version 57810 (0.0008) -[2023-10-17 02:34:43,351][62373] Updated weights for policy 0, policy_version 57820 (0.0008) -[2023-10-17 02:34:44,449][62408] Updated weights for policy 1, policy_version 57380 (0.0009) -[2023-10-17 02:34:44,822][62408] Updated weights for policy 1, policy_version 57390 (0.0007) -[2023-10-17 02:34:45,179][62408] Updated weights for policy 1, policy_version 57400 (0.0007) -[2023-10-17 02:34:47,048][62373] Updated weights for policy 0, policy_version 57830 (0.0007) -[2023-10-17 02:34:47,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 117997568. Throughput: 0: 1802.4, 1: 1761.6. Samples: 29513514. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-17 02:34:47,214][61453] Avg episode reward: [(0, '8.800'), (1, '10.150')] -[2023-10-17 02:34:47,411][62373] Updated weights for policy 0, policy_version 57840 (0.0008) -[2023-10-17 02:34:47,785][62373] Updated weights for policy 0, policy_version 57850 (0.0009) -[2023-10-17 02:34:48,895][62408] Updated weights for policy 1, policy_version 57410 (0.0008) -[2023-10-17 02:34:49,252][62408] Updated weights for policy 1, policy_version 57420 (0.0010) -[2023-10-17 02:34:49,622][62408] Updated weights for policy 1, policy_version 57430 (0.0009) -[2023-10-17 02:34:49,992][62408] Updated weights for policy 1, policy_version 57440 (0.0007) -[2023-10-17 02:34:51,615][62373] Updated weights for policy 0, policy_version 57860 (0.0007) -[2023-10-17 02:34:51,981][62373] Updated weights for policy 0, policy_version 57870 (0.0008) -[2023-10-17 02:34:52,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 118063104. Throughput: 0: 1774.6, 1: 1767.2. Samples: 29523698. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-17 02:34:52,215][61453] Avg episode reward: [(0, '9.270'), (1, '10.700')] -[2023-10-17 02:34:52,346][62373] Updated weights for policy 0, policy_version 57880 (0.0007) -[2023-10-17 02:34:53,743][62408] Updated weights for policy 1, policy_version 57450 (0.0008) -[2023-10-17 02:34:54,109][62408] Updated weights for policy 1, policy_version 57460 (0.0008) -[2023-10-17 02:34:54,471][62408] Updated weights for policy 1, policy_version 57470 (0.0009) -[2023-10-17 02:34:56,097][62373] Updated weights for policy 0, policy_version 57890 (0.0007) -[2023-10-17 02:34:56,464][62373] Updated weights for policy 0, policy_version 57900 (0.0009) -[2023-10-17 02:34:56,825][62373] Updated weights for policy 0, policy_version 57910 (0.0008) -[2023-10-17 02:34:57,194][62373] Updated weights for policy 0, policy_version 57920 (0.0008) -[2023-10-17 02:34:57,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 118161408. Throughput: 0: 1796.3, 1: 1766.2. Samples: 29545866. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-17 02:34:57,214][61453] Avg episode reward: [(0, '9.340'), (1, '10.290')] -[2023-10-17 02:34:58,297][62408] Updated weights for policy 1, policy_version 57480 (0.0009) -[2023-10-17 02:34:58,661][62408] Updated weights for policy 1, policy_version 57490 (0.0008) -[2023-10-17 02:34:59,026][62408] Updated weights for policy 1, policy_version 57500 (0.0007) -[2023-10-17 02:35:00,986][62373] Updated weights for policy 0, policy_version 57930 (0.0008) -[2023-10-17 02:35:01,355][62373] Updated weights for policy 0, policy_version 57940 (0.0008) -[2023-10-17 02:35:01,725][62373] Updated weights for policy 0, policy_version 57950 (0.0007) -[2023-10-17 02:35:02,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 118226944. Throughput: 0: 1777.4, 1: 1775.8. Samples: 29566586. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-17 02:35:02,215][61453] Avg episode reward: [(0, '10.340'), (1, '10.570')] -[2023-10-17 02:35:02,780][62408] Updated weights for policy 1, policy_version 57510 (0.0009) -[2023-10-17 02:35:03,152][62408] Updated weights for policy 1, policy_version 57520 (0.0008) -[2023-10-17 02:35:03,506][62408] Updated weights for policy 1, policy_version 57530 (0.0009) -[2023-10-17 02:35:05,469][62373] Updated weights for policy 0, policy_version 57960 (0.0008) -[2023-10-17 02:35:05,836][62373] Updated weights for policy 0, policy_version 57970 (0.0007) -[2023-10-17 02:35:06,214][62373] Updated weights for policy 0, policy_version 57980 (0.0010) -[2023-10-17 02:35:07,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 118292480. Throughput: 0: 1797.1, 1: 1764.2. Samples: 29577804. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-17 02:35:07,214][61453] Avg episode reward: [(0, '10.270'), (1, '10.390')] -[2023-10-17 02:35:07,238][62408] Updated weights for policy 1, policy_version 57540 (0.0009) -[2023-10-17 02:35:07,625][62408] Updated weights for policy 1, policy_version 57550 (0.0009) -[2023-10-17 02:35:07,995][62408] Updated weights for policy 1, policy_version 57560 (0.0010) -[2023-10-17 02:35:10,063][62373] Updated weights for policy 0, policy_version 57990 (0.0009) -[2023-10-17 02:35:10,433][62373] Updated weights for policy 0, policy_version 58000 (0.0010) -[2023-10-17 02:35:10,805][62373] Updated weights for policy 0, policy_version 58010 (0.0008) -[2023-10-17 02:35:11,749][62408] Updated weights for policy 1, policy_version 57570 (0.0009) -[2023-10-17 02:35:12,120][62408] Updated weights for policy 1, policy_version 57580 (0.0011) -[2023-10-17 02:35:12,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 118358016. Throughput: 0: 1786.0, 1: 1770.0. Samples: 29598436. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-17 02:35:12,214][61453] Avg episode reward: [(0, '9.490'), (1, '10.030')] -[2023-10-17 02:35:12,493][62408] Updated weights for policy 1, policy_version 57590 (0.0009) -[2023-10-17 02:35:12,864][62408] Updated weights for policy 1, policy_version 57600 (0.0007) -[2023-10-17 02:35:14,503][62373] Updated weights for policy 0, policy_version 58020 (0.0008) -[2023-10-17 02:35:14,877][62373] Updated weights for policy 0, policy_version 58030 (0.0008) -[2023-10-17 02:35:15,236][62373] Updated weights for policy 0, policy_version 58040 (0.0007) -[2023-10-17 02:35:16,676][62408] Updated weights for policy 1, policy_version 57610 (0.0007) -[2023-10-17 02:35:17,043][62408] Updated weights for policy 1, policy_version 57620 (0.0008) -[2023-10-17 02:35:17,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 118423552. Throughput: 0: 1783.0, 1: 1789.9. Samples: 29620032. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-10-17 02:35:17,214][61453] Avg episode reward: [(0, '10.040'), (1, '10.510')] -[2023-10-17 02:35:17,414][62408] Updated weights for policy 1, policy_version 57630 (0.0007) -[2023-10-17 02:35:18,979][62373] Updated weights for policy 0, policy_version 58050 (0.0008) -[2023-10-17 02:35:19,347][62373] Updated weights for policy 0, policy_version 58060 (0.0009) -[2023-10-17 02:35:19,719][62373] Updated weights for policy 0, policy_version 58070 (0.0007) -[2023-10-17 02:35:20,091][62373] Updated weights for policy 0, policy_version 58080 (0.0008) -[2023-10-17 02:35:21,321][62408] Updated weights for policy 1, policy_version 57640 (0.0008) -[2023-10-17 02:35:21,690][62408] Updated weights for policy 1, policy_version 57650 (0.0007) -[2023-10-17 02:35:22,061][62408] Updated weights for policy 1, policy_version 57660 (0.0008) -[2023-10-17 02:35:22,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14218.0). Total num frames: 118521856. Throughput: 0: 1791.1, 1: 1775.0. Samples: 29630808. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:35:22,215][61453] Avg episode reward: [(0, '10.280'), (1, '10.440')] -[2023-10-17 02:35:24,054][62373] Updated weights for policy 0, policy_version 58090 (0.0007) -[2023-10-17 02:35:24,419][62373] Updated weights for policy 0, policy_version 58100 (0.0007) -[2023-10-17 02:35:24,795][62373] Updated weights for policy 0, policy_version 58110 (0.0008) -[2023-10-17 02:35:25,801][62408] Updated weights for policy 1, policy_version 57670 (0.0008) -[2023-10-17 02:35:26,162][62408] Updated weights for policy 1, policy_version 57680 (0.0010) -[2023-10-17 02:35:26,534][62408] Updated weights for policy 1, policy_version 57690 (0.0009) -[2023-10-17 02:35:27,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 118587392. Throughput: 0: 1773.8, 1: 1796.1. Samples: 29652274. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:35:27,215][61453] Avg episode reward: [(0, '10.000'), (1, '10.610')] -[2023-10-17 02:35:28,652][62373] Updated weights for policy 0, policy_version 58120 (0.0007) -[2023-10-17 02:35:29,023][62373] Updated weights for policy 0, policy_version 58130 (0.0007) -[2023-10-17 02:35:29,385][62373] Updated weights for policy 0, policy_version 58140 (0.0007) -[2023-10-17 02:35:30,389][62408] Updated weights for policy 1, policy_version 57700 (0.0011) -[2023-10-17 02:35:30,750][62408] Updated weights for policy 1, policy_version 57710 (0.0010) -[2023-10-17 02:35:31,116][62408] Updated weights for policy 1, policy_version 57720 (0.0008) -[2023-10-17 02:35:32,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 118652928. Throughput: 0: 1779.2, 1: 1772.6. Samples: 29673346. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:35:32,214][61453] Avg episode reward: [(0, '10.170'), (1, '10.630')] -[2023-10-17 02:35:32,223][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000057728_59113472.pth... -[2023-10-17 02:35:32,223][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000058144_59539456.pth... -[2023-10-17 02:35:32,261][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000056480_57835520.pth -[2023-10-17 02:35:32,264][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000056064_57409536.pth -[2023-10-17 02:35:32,265][62094] Saving a milestone ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/milestones/checkpoint_000058144_59539456.pth -[2023-10-17 02:35:32,270][62252] Saving a milestone ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/milestones/checkpoint_000057728_59113472.pth -[2023-10-17 02:35:33,182][62373] Updated weights for policy 0, policy_version 58150 (0.0007) -[2023-10-17 02:35:33,556][62373] Updated weights for policy 0, policy_version 58160 (0.0010) -[2023-10-17 02:35:33,925][62373] Updated weights for policy 0, policy_version 58170 (0.0009) -[2023-10-17 02:35:35,089][62408] Updated weights for policy 1, policy_version 57730 (0.0009) -[2023-10-17 02:35:35,454][62408] Updated weights for policy 1, policy_version 57740 (0.0008) -[2023-10-17 02:35:35,819][62408] Updated weights for policy 1, policy_version 57750 (0.0011) -[2023-10-17 02:35:36,182][62408] Updated weights for policy 1, policy_version 57760 (0.0008) -[2023-10-17 02:35:37,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 118718464. Throughput: 0: 1774.0, 1: 1792.0. Samples: 29684168. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:35:37,215][61453] Avg episode reward: [(0, '10.270'), (1, '10.210')] -[2023-10-17 02:35:37,690][62373] Updated weights for policy 0, policy_version 58180 (0.0009) -[2023-10-17 02:35:38,064][62373] Updated weights for policy 0, policy_version 58190 (0.0010) -[2023-10-17 02:35:38,428][62373] Updated weights for policy 0, policy_version 58200 (0.0009) -[2023-10-17 02:35:39,893][62408] Updated weights for policy 1, policy_version 57770 (0.0008) -[2023-10-17 02:35:40,258][62408] Updated weights for policy 1, policy_version 57780 (0.0011) -[2023-10-17 02:35:40,634][62408] Updated weights for policy 1, policy_version 57790 (0.0008) -[2023-10-17 02:35:42,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 118784000. Throughput: 0: 1772.4, 1: 1765.3. Samples: 29705064. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:35:42,215][61453] Avg episode reward: [(0, '10.470'), (1, '9.940')] -[2023-10-17 02:35:42,280][62373] Updated weights for policy 0, policy_version 58210 (0.0007) -[2023-10-17 02:35:42,641][62373] Updated weights for policy 0, policy_version 58220 (0.0008) -[2023-10-17 02:35:43,007][62373] Updated weights for policy 0, policy_version 58230 (0.0008) -[2023-10-17 02:35:43,380][62373] Updated weights for policy 0, policy_version 58240 (0.0009) -[2023-10-17 02:35:44,402][62408] Updated weights for policy 1, policy_version 57800 (0.0008) -[2023-10-17 02:35:44,768][62408] Updated weights for policy 1, policy_version 57810 (0.0008) -[2023-10-17 02:35:45,147][62408] Updated weights for policy 1, policy_version 57820 (0.0007) -[2023-10-17 02:35:47,074][62373] Updated weights for policy 0, policy_version 58250 (0.0008) -[2023-10-17 02:35:47,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 118849536. Throughput: 0: 1801.8, 1: 1770.8. Samples: 29727352. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:35:47,215][61453] Avg episode reward: [(0, '10.810'), (1, '10.590')] -[2023-10-17 02:35:47,444][62373] Updated weights for policy 0, policy_version 58260 (0.0009) -[2023-10-17 02:35:47,826][62373] Updated weights for policy 0, policy_version 58270 (0.0010) -[2023-10-17 02:35:48,847][62408] Updated weights for policy 1, policy_version 57830 (0.0009) -[2023-10-17 02:35:49,222][62408] Updated weights for policy 1, policy_version 57840 (0.0010) -[2023-10-17 02:35:49,596][62408] Updated weights for policy 1, policy_version 57850 (0.0009) -[2023-10-17 02:35:51,710][62373] Updated weights for policy 0, policy_version 58280 (0.0008) -[2023-10-17 02:35:52,084][62373] Updated weights for policy 0, policy_version 58290 (0.0007) -[2023-10-17 02:35:52,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 118915072. Throughput: 0: 1772.6, 1: 1770.3. Samples: 29737234. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:35:52,215][61453] Avg episode reward: [(0, '10.840'), (1, '10.840')] -[2023-10-17 02:35:52,445][62373] Updated weights for policy 0, policy_version 58300 (0.0007) -[2023-10-17 02:35:53,343][62408] Updated weights for policy 1, policy_version 57860 (0.0009) -[2023-10-17 02:35:53,753][62408] Updated weights for policy 1, policy_version 57870 (0.0007) -[2023-10-17 02:35:54,118][62408] Updated weights for policy 1, policy_version 57880 (0.0008) -[2023-10-17 02:35:56,240][62373] Updated weights for policy 0, policy_version 58310 (0.0010) -[2023-10-17 02:35:56,603][62373] Updated weights for policy 0, policy_version 58320 (0.0008) -[2023-10-17 02:35:56,969][62373] Updated weights for policy 0, policy_version 58330 (0.0007) -[2023-10-17 02:35:57,214][61453] Fps is (10 sec: 16384.3, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 119013376. Throughput: 0: 1801.6, 1: 1771.2. Samples: 29759214. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-17 02:35:57,215][61453] Avg episode reward: [(0, '10.510'), (1, '9.750')] -[2023-10-17 02:35:57,779][62408] Updated weights for policy 1, policy_version 57890 (0.0008) -[2023-10-17 02:35:58,154][62408] Updated weights for policy 1, policy_version 57900 (0.0011) -[2023-10-17 02:35:58,518][62408] Updated weights for policy 1, policy_version 57910 (0.0008) -[2023-10-17 02:35:58,880][62408] Updated weights for policy 1, policy_version 57920 (0.0007) -[2023-10-17 02:36:00,623][62373] Updated weights for policy 0, policy_version 58340 (0.0008) -[2023-10-17 02:36:00,996][62373] Updated weights for policy 0, policy_version 58350 (0.0009) -[2023-10-17 02:36:01,375][62373] Updated weights for policy 0, policy_version 58360 (0.0009) -[2023-10-17 02:36:02,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 119078912. Throughput: 0: 1770.7, 1: 1786.3. Samples: 29780096. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-17 02:36:02,215][61453] Avg episode reward: [(0, '10.270'), (1, '10.300')] -[2023-10-17 02:36:02,834][62408] Updated weights for policy 1, policy_version 57930 (0.0009) -[2023-10-17 02:36:03,201][62408] Updated weights for policy 1, policy_version 57940 (0.0009) -[2023-10-17 02:36:03,562][62408] Updated weights for policy 1, policy_version 57950 (0.0008) -[2023-10-17 02:36:05,060][62373] Updated weights for policy 0, policy_version 58370 (0.0008) -[2023-10-17 02:36:05,421][62373] Updated weights for policy 0, policy_version 58380 (0.0009) -[2023-10-17 02:36:05,799][62373] Updated weights for policy 0, policy_version 58390 (0.0008) -[2023-10-17 02:36:06,164][62373] Updated weights for policy 0, policy_version 58400 (0.0008) -[2023-10-17 02:36:07,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 119144448. Throughput: 0: 1796.2, 1: 1766.9. Samples: 29791150. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-17 02:36:07,215][61453] Avg episode reward: [(0, '10.920'), (1, '10.420')] -[2023-10-17 02:36:07,517][62408] Updated weights for policy 1, policy_version 57960 (0.0008) -[2023-10-17 02:36:07,889][62408] Updated weights for policy 1, policy_version 57970 (0.0008) -[2023-10-17 02:36:08,257][62408] Updated weights for policy 1, policy_version 57980 (0.0011) -[2023-10-17 02:36:09,895][62373] Updated weights for policy 0, policy_version 58410 (0.0008) -[2023-10-17 02:36:10,264][62373] Updated weights for policy 0, policy_version 58420 (0.0007) -[2023-10-17 02:36:10,628][62373] Updated weights for policy 0, policy_version 58430 (0.0007) -[2023-10-17 02:36:12,108][62408] Updated weights for policy 1, policy_version 57990 (0.0010) -[2023-10-17 02:36:12,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 119209984. Throughput: 0: 1781.3, 1: 1769.2. Samples: 29812044. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-17 02:36:12,215][61453] Avg episode reward: [(0, '10.540'), (1, '9.740')] -[2023-10-17 02:36:12,483][62408] Updated weights for policy 1, policy_version 58000 (0.0008) -[2023-10-17 02:36:12,851][62408] Updated weights for policy 1, policy_version 58010 (0.0007) -[2023-10-17 02:36:14,346][62373] Updated weights for policy 0, policy_version 58440 (0.0009) -[2023-10-17 02:36:14,735][62373] Updated weights for policy 0, policy_version 58450 (0.0008) -[2023-10-17 02:36:15,096][62373] Updated weights for policy 0, policy_version 58460 (0.0009) -[2023-10-17 02:36:16,657][62408] Updated weights for policy 1, policy_version 58020 (0.0008) -[2023-10-17 02:36:17,021][62408] Updated weights for policy 1, policy_version 58030 (0.0009) -[2023-10-17 02:36:17,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 119275520. Throughput: 0: 1782.5, 1: 1788.1. Samples: 29834024. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-17 02:36:17,215][61453] Avg episode reward: [(0, '10.750'), (1, '10.940')] -[2023-10-17 02:36:17,393][62408] Updated weights for policy 1, policy_version 58040 (0.0008) -[2023-10-17 02:36:18,789][62373] Updated weights for policy 0, policy_version 58470 (0.0009) -[2023-10-17 02:36:19,163][62373] Updated weights for policy 0, policy_version 58480 (0.0008) -[2023-10-17 02:36:19,537][62373] Updated weights for policy 0, policy_version 58490 (0.0011) -[2023-10-17 02:36:21,237][62408] Updated weights for policy 1, policy_version 58050 (0.0009) -[2023-10-17 02:36:21,612][62408] Updated weights for policy 1, policy_version 58060 (0.0007) -[2023-10-17 02:36:21,996][62408] Updated weights for policy 1, policy_version 58070 (0.0009) -[2023-10-17 02:36:22,214][61453] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 119341056. Throughput: 0: 1783.4, 1: 1769.3. Samples: 29844040. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-17 02:36:22,215][61453] Avg episode reward: [(0, '10.340'), (1, '10.280')] -[2023-10-17 02:36:22,363][62408] Updated weights for policy 1, policy_version 58080 (0.0010) -[2023-10-17 02:36:23,449][62373] Updated weights for policy 0, policy_version 58500 (0.0010) -[2023-10-17 02:36:23,834][62373] Updated weights for policy 0, policy_version 58510 (0.0009) -[2023-10-17 02:36:24,197][62373] Updated weights for policy 0, policy_version 58520 (0.0009) -[2023-10-17 02:36:26,062][62408] Updated weights for policy 1, policy_version 58090 (0.0008) -[2023-10-17 02:36:26,436][62408] Updated weights for policy 1, policy_version 58100 (0.0008) -[2023-10-17 02:36:26,805][62408] Updated weights for policy 1, policy_version 58110 (0.0008) -[2023-10-17 02:36:27,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 119439360. Throughput: 0: 1780.0, 1: 1789.7. Samples: 29865698. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-17 02:36:27,215][61453] Avg episode reward: [(0, '10.170'), (1, '10.040')] -[2023-10-17 02:36:27,924][62373] Updated weights for policy 0, policy_version 58530 (0.0009) -[2023-10-17 02:36:28,304][62373] Updated weights for policy 0, policy_version 58540 (0.0009) -[2023-10-17 02:36:28,679][62373] Updated weights for policy 0, policy_version 58550 (0.0008) -[2023-10-17 02:36:29,038][62373] Updated weights for policy 0, policy_version 58560 (0.0008) -[2023-10-17 02:36:30,660][62408] Updated weights for policy 1, policy_version 58120 (0.0008) -[2023-10-17 02:36:31,028][62408] Updated weights for policy 1, policy_version 58130 (0.0011) -[2023-10-17 02:36:31,404][62408] Updated weights for policy 1, policy_version 58140 (0.0009) -[2023-10-17 02:36:32,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 119504896. Throughput: 0: 1784.9, 1: 1762.9. Samples: 29887000. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-17 02:36:32,215][61453] Avg episode reward: [(0, '10.240'), (1, '9.530')] -[2023-10-17 02:36:32,792][62373] Updated weights for policy 0, policy_version 58570 (0.0008) -[2023-10-17 02:36:33,158][62373] Updated weights for policy 0, policy_version 58580 (0.0010) -[2023-10-17 02:36:33,525][62373] Updated weights for policy 0, policy_version 58590 (0.0010) -[2023-10-17 02:36:35,216][62408] Updated weights for policy 1, policy_version 58150 (0.0009) -[2023-10-17 02:36:35,577][62408] Updated weights for policy 1, policy_version 58160 (0.0008) -[2023-10-17 02:36:35,938][62408] Updated weights for policy 1, policy_version 58170 (0.0007) -[2023-10-17 02:36:37,214][61453] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 119570432. Throughput: 0: 1779.6, 1: 1796.0. Samples: 29898132. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-17 02:36:37,214][61453] Avg episode reward: [(0, '10.520'), (1, '9.630')] -[2023-10-17 02:36:37,474][62373] Updated weights for policy 0, policy_version 58600 (0.0008) -[2023-10-17 02:36:37,848][62373] Updated weights for policy 0, policy_version 58610 (0.0007) -[2023-10-17 02:36:38,217][62373] Updated weights for policy 0, policy_version 58620 (0.0008) -[2023-10-17 02:36:39,683][62408] Updated weights for policy 1, policy_version 58180 (0.0008) -[2023-10-17 02:36:40,054][62408] Updated weights for policy 1, policy_version 58190 (0.0007) -[2023-10-17 02:36:40,427][62408] Updated weights for policy 1, policy_version 58200 (0.0009) -[2023-10-17 02:36:42,038][62373] Updated weights for policy 0, policy_version 58630 (0.0007) -[2023-10-17 02:36:42,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 119635968. Throughput: 0: 1778.8, 1: 1769.7. Samples: 29918898. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-17 02:36:42,214][61453] Avg episode reward: [(0, '10.630'), (1, '9.760')] -[2023-10-17 02:36:42,406][62373] Updated weights for policy 0, policy_version 58640 (0.0009) -[2023-10-17 02:36:42,791][62373] Updated weights for policy 0, policy_version 58650 (0.0009) -[2023-10-17 02:36:44,230][62408] Updated weights for policy 1, policy_version 58210 (0.0012) -[2023-10-17 02:36:44,642][62408] Updated weights for policy 1, policy_version 58220 (0.0010) -[2023-10-17 02:36:45,021][62408] Updated weights for policy 1, policy_version 58230 (0.0007) -[2023-10-17 02:36:45,389][62408] Updated weights for policy 1, policy_version 58240 (0.0008) -[2023-10-17 02:36:46,362][62373] Updated weights for policy 0, policy_version 58660 (0.0008) -[2023-10-17 02:36:46,743][62373] Updated weights for policy 0, policy_version 58670 (0.0008) -[2023-10-17 02:36:47,111][62373] Updated weights for policy 0, policy_version 58680 (0.0009) -[2023-10-17 02:36:47,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 119701504. Throughput: 0: 1794.9, 1: 1762.8. Samples: 29940196. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-17 02:36:47,215][61453] Avg episode reward: [(0, '10.110'), (1, '9.050')] -[2023-10-17 02:36:49,318][62408] Updated weights for policy 1, policy_version 58250 (0.0007) -[2023-10-17 02:36:49,690][62408] Updated weights for policy 1, policy_version 58260 (0.0007) -[2023-10-17 02:36:50,059][62408] Updated weights for policy 1, policy_version 58270 (0.0009) -[2023-10-17 02:36:50,889][62373] Updated weights for policy 0, policy_version 58690 (0.0008) -[2023-10-17 02:36:51,253][62373] Updated weights for policy 0, policy_version 58700 (0.0009) -[2023-10-17 02:36:51,625][62373] Updated weights for policy 0, policy_version 58710 (0.0010) -[2023-10-17 02:36:51,997][62373] Updated weights for policy 0, policy_version 58720 (0.0008) -[2023-10-17 02:36:52,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 119799808. Throughput: 0: 1783.7, 1: 1768.5. Samples: 29950998. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-17 02:36:52,214][61453] Avg episode reward: [(0, '9.760'), (1, '10.130')] -[2023-10-17 02:36:53,949][62408] Updated weights for policy 1, policy_version 58280 (0.0007) -[2023-10-17 02:36:54,314][62408] Updated weights for policy 1, policy_version 58290 (0.0008) -[2023-10-17 02:36:54,691][62408] Updated weights for policy 1, policy_version 58300 (0.0007) -[2023-10-17 02:36:55,722][62373] Updated weights for policy 0, policy_version 58730 (0.0009) -[2023-10-17 02:36:56,088][62373] Updated weights for policy 0, policy_version 58740 (0.0009) -[2023-10-17 02:36:56,465][62373] Updated weights for policy 0, policy_version 58750 (0.0008) -[2023-10-17 02:36:57,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 119865344. Throughput: 0: 1799.6, 1: 1760.0. Samples: 29972226. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-17 02:36:57,215][61453] Avg episode reward: [(0, '10.360'), (1, '10.400')] -[2023-10-17 02:36:58,587][62408] Updated weights for policy 1, policy_version 58310 (0.0008) -[2023-10-17 02:36:58,957][62408] Updated weights for policy 1, policy_version 58320 (0.0008) -[2023-10-17 02:36:59,317][62408] Updated weights for policy 1, policy_version 58330 (0.0008) -[2023-10-17 02:37:00,253][62373] Updated weights for policy 0, policy_version 58760 (0.0008) -[2023-10-17 02:37:00,631][62373] Updated weights for policy 0, policy_version 58770 (0.0008) -[2023-10-17 02:37:01,011][62373] Updated weights for policy 0, policy_version 58780 (0.0009) -[2023-10-17 02:37:02,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 119930880. Throughput: 0: 1779.5, 1: 1765.9. Samples: 29993564. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-17 02:37:02,215][61453] Avg episode reward: [(0, '11.140'), (1, '10.320')] -[2023-10-17 02:37:03,112][62408] Updated weights for policy 1, policy_version 58340 (0.0010) -[2023-10-17 02:37:03,484][62408] Updated weights for policy 1, policy_version 58350 (0.0008) -[2023-10-17 02:37:03,847][62408] Updated weights for policy 1, policy_version 58360 (0.0007) -[2023-10-17 02:37:04,886][62373] Updated weights for policy 0, policy_version 58790 (0.0008) -[2023-10-17 02:37:05,251][62373] Updated weights for policy 0, policy_version 58800 (0.0008) -[2023-10-17 02:37:05,620][62373] Updated weights for policy 0, policy_version 58810 (0.0010) -[2023-10-17 02:37:07,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 119996416. Throughput: 0: 1802.5, 1: 1756.6. Samples: 30004200. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-17 02:37:07,215][61453] Avg episode reward: [(0, '10.710'), (1, '10.720')] -[2023-10-17 02:37:07,602][62408] Updated weights for policy 1, policy_version 58370 (0.0008) -[2023-10-17 02:37:07,970][62408] Updated weights for policy 1, policy_version 58380 (0.0010) -[2023-10-17 02:37:08,332][62408] Updated weights for policy 1, policy_version 58390 (0.0008) -[2023-10-17 02:37:08,700][62408] Updated weights for policy 1, policy_version 58400 (0.0009) -[2023-10-17 02:37:09,442][62373] Updated weights for policy 0, policy_version 58820 (0.0010) -[2023-10-17 02:37:09,811][62373] Updated weights for policy 0, policy_version 58830 (0.0009) -[2023-10-17 02:37:10,184][62373] Updated weights for policy 0, policy_version 58840 (0.0007) -[2023-10-17 02:37:12,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 120061952. Throughput: 0: 1777.7, 1: 1764.3. Samples: 30025088. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-17 02:37:12,215][61453] Avg episode reward: [(0, '9.730'), (1, '10.930')] -[2023-10-17 02:37:12,623][62408] Updated weights for policy 1, policy_version 58410 (0.0010) -[2023-10-17 02:37:12,998][62408] Updated weights for policy 1, policy_version 58420 (0.0010) -[2023-10-17 02:37:13,372][62408] Updated weights for policy 1, policy_version 58430 (0.0008) -[2023-10-17 02:37:13,950][62373] Updated weights for policy 0, policy_version 58850 (0.0007) -[2023-10-17 02:37:14,326][62373] Updated weights for policy 0, policy_version 58860 (0.0007) -[2023-10-17 02:37:14,693][62373] Updated weights for policy 0, policy_version 58870 (0.0009) -[2023-10-17 02:37:15,062][62373] Updated weights for policy 0, policy_version 58880 (0.0009) -[2023-10-17 02:37:17,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 120127488. Throughput: 0: 1769.6, 1: 1786.5. Samples: 30047022. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-17 02:37:17,214][61453] Avg episode reward: [(0, '10.140'), (1, '10.920')] -[2023-10-17 02:37:17,278][62408] Updated weights for policy 1, policy_version 58440 (0.0009) -[2023-10-17 02:37:17,653][62408] Updated weights for policy 1, policy_version 58450 (0.0007) -[2023-10-17 02:37:18,026][62408] Updated weights for policy 1, policy_version 58460 (0.0008) -[2023-10-17 02:37:18,980][62373] Updated weights for policy 0, policy_version 58890 (0.0010) -[2023-10-17 02:37:19,351][62373] Updated weights for policy 0, policy_version 58900 (0.0007) -[2023-10-17 02:37:19,724][62373] Updated weights for policy 0, policy_version 58910 (0.0008) -[2023-10-17 02:37:21,834][62408] Updated weights for policy 1, policy_version 58470 (0.0008) -[2023-10-17 02:37:22,192][62408] Updated weights for policy 1, policy_version 58480 (0.0008) -[2023-10-17 02:37:22,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 120193024. Throughput: 0: 1769.3, 1: 1748.9. Samples: 30056452. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-17 02:37:22,214][61453] Avg episode reward: [(0, '10.670'), (1, '11.160')] -[2023-10-17 02:37:22,566][62408] Updated weights for policy 1, policy_version 58490 (0.0009) -[2023-10-17 02:37:23,443][62373] Updated weights for policy 0, policy_version 58920 (0.0009) -[2023-10-17 02:37:23,811][62373] Updated weights for policy 0, policy_version 58930 (0.0007) -[2023-10-17 02:37:24,177][62373] Updated weights for policy 0, policy_version 58940 (0.0008) -[2023-10-17 02:37:26,517][62408] Updated weights for policy 1, policy_version 58500 (0.0007) -[2023-10-17 02:37:26,880][62408] Updated weights for policy 1, policy_version 58510 (0.0007) -[2023-10-17 02:37:27,214][61453] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 120258560. Throughput: 0: 1772.2, 1: 1773.0. Samples: 30078432. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-17 02:37:27,215][61453] Avg episode reward: [(0, '10.160'), (1, '10.440')] -[2023-10-17 02:37:27,247][62408] Updated weights for policy 1, policy_version 58520 (0.0008) -[2023-10-17 02:37:27,953][62373] Updated weights for policy 0, policy_version 58950 (0.0008) -[2023-10-17 02:37:28,339][62373] Updated weights for policy 0, policy_version 58960 (0.0008) -[2023-10-17 02:37:28,697][62373] Updated weights for policy 0, policy_version 58970 (0.0009) -[2023-10-17 02:37:31,092][62408] Updated weights for policy 1, policy_version 58530 (0.0008) -[2023-10-17 02:37:31,505][62408] Updated weights for policy 1, policy_version 58540 (0.0008) -[2023-10-17 02:37:31,874][62408] Updated weights for policy 1, policy_version 58550 (0.0007) -[2023-10-17 02:37:32,214][61453] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 120324096. Throughput: 0: 1786.1, 1: 1756.5. Samples: 30099612. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-17 02:37:32,214][61453] Avg episode reward: [(0, '10.190'), (1, '10.540')] -[2023-10-17 02:37:32,224][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000058976_60391424.pth... -[2023-10-17 02:37:32,239][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000058560_59965440.pth... -[2023-10-17 02:37:32,242][62408] Updated weights for policy 1, policy_version 58560 (0.0010) -[2023-10-17 02:37:32,253][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000057312_58687488.pth -[2023-10-17 02:37:32,268][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000056896_58261504.pth -[2023-10-17 02:37:32,541][62373] Updated weights for policy 0, policy_version 58980 (0.0009) -[2023-10-17 02:37:32,914][62373] Updated weights for policy 0, policy_version 58990 (0.0010) -[2023-10-17 02:37:33,279][62373] Updated weights for policy 0, policy_version 59000 (0.0008) -[2023-10-17 02:37:35,946][62408] Updated weights for policy 1, policy_version 58570 (0.0008) -[2023-10-17 02:37:36,313][62408] Updated weights for policy 1, policy_version 58580 (0.0007) -[2023-10-17 02:37:36,672][62408] Updated weights for policy 1, policy_version 58590 (0.0007) -[2023-10-17 02:37:37,172][62373] Updated weights for policy 0, policy_version 59010 (0.0008) -[2023-10-17 02:37:37,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 120422400. Throughput: 0: 1762.4, 1: 1774.2. Samples: 30110142. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-17 02:37:37,215][61453] Avg episode reward: [(0, '10.220'), (1, '10.490')] -[2023-10-17 02:37:37,545][62373] Updated weights for policy 0, policy_version 59020 (0.0008) -[2023-10-17 02:37:37,904][62373] Updated weights for policy 0, policy_version 59030 (0.0009) -[2023-10-17 02:37:38,269][62373] Updated weights for policy 0, policy_version 59040 (0.0010) -[2023-10-17 02:37:40,363][62408] Updated weights for policy 1, policy_version 58600 (0.0007) -[2023-10-17 02:37:40,731][62408] Updated weights for policy 1, policy_version 58610 (0.0009) -[2023-10-17 02:37:41,096][62408] Updated weights for policy 1, policy_version 58620 (0.0011) -[2023-10-17 02:37:42,020][62373] Updated weights for policy 0, policy_version 59050 (0.0007) -[2023-10-17 02:37:42,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 120487936. Throughput: 0: 1772.5, 1: 1768.1. Samples: 30131550. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-17 02:37:42,215][61453] Avg episode reward: [(0, '10.570'), (1, '10.560')] -[2023-10-17 02:37:42,390][62373] Updated weights for policy 0, policy_version 59060 (0.0008) -[2023-10-17 02:37:42,745][62373] Updated weights for policy 0, policy_version 59070 (0.0007) -[2023-10-17 02:37:44,785][62408] Updated weights for policy 1, policy_version 58630 (0.0009) -[2023-10-17 02:37:45,162][62408] Updated weights for policy 1, policy_version 58640 (0.0010) -[2023-10-17 02:37:45,524][62408] Updated weights for policy 1, policy_version 58650 (0.0008) -[2023-10-17 02:37:46,571][62373] Updated weights for policy 0, policy_version 59080 (0.0008) -[2023-10-17 02:37:46,940][62373] Updated weights for policy 0, policy_version 59090 (0.0008) -[2023-10-17 02:37:47,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 120553472. Throughput: 0: 1771.9, 1: 1760.9. Samples: 30152542. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-17 02:37:47,215][61453] Avg episode reward: [(0, '10.840'), (1, '10.410')] -[2023-10-17 02:37:47,311][62373] Updated weights for policy 0, policy_version 59100 (0.0008) -[2023-10-17 02:37:49,504][62408] Updated weights for policy 1, policy_version 58660 (0.0007) -[2023-10-17 02:37:49,879][62408] Updated weights for policy 1, policy_version 58670 (0.0008) -[2023-10-17 02:37:50,244][62408] Updated weights for policy 1, policy_version 58680 (0.0008) -[2023-10-17 02:37:51,141][62373] Updated weights for policy 0, policy_version 59110 (0.0009) -[2023-10-17 02:37:51,509][62373] Updated weights for policy 0, policy_version 59120 (0.0008) -[2023-10-17 02:37:51,881][62373] Updated weights for policy 0, policy_version 59130 (0.0007) -[2023-10-17 02:37:52,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 120651776. Throughput: 0: 1764.8, 1: 1775.7. Samples: 30163518. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-17 02:37:52,214][61453] Avg episode reward: [(0, '11.070'), (1, '10.340')] -[2023-10-17 02:37:54,236][62408] Updated weights for policy 1, policy_version 58690 (0.0008) -[2023-10-17 02:37:54,611][62408] Updated weights for policy 1, policy_version 58700 (0.0007) -[2023-10-17 02:37:54,978][62408] Updated weights for policy 1, policy_version 58710 (0.0008) -[2023-10-17 02:37:55,342][62408] Updated weights for policy 1, policy_version 58720 (0.0007) -[2023-10-17 02:37:55,696][62373] Updated weights for policy 0, policy_version 59140 (0.0008) -[2023-10-17 02:37:56,065][62373] Updated weights for policy 0, policy_version 59150 (0.0008) -[2023-10-17 02:37:56,434][62373] Updated weights for policy 0, policy_version 59160 (0.0008) -[2023-10-17 02:37:57,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 120717312. Throughput: 0: 1784.0, 1: 1753.2. Samples: 30184264. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-17 02:37:57,214][61453] Avg episode reward: [(0, '10.640'), (1, '10.110')] -[2023-10-17 02:37:59,231][62408] Updated weights for policy 1, policy_version 58730 (0.0008) -[2023-10-17 02:37:59,599][62408] Updated weights for policy 1, policy_version 58740 (0.0010) -[2023-10-17 02:37:59,975][62408] Updated weights for policy 1, policy_version 58750 (0.0007) -[2023-10-17 02:38:00,249][62373] Updated weights for policy 0, policy_version 59170 (0.0009) -[2023-10-17 02:38:00,615][62373] Updated weights for policy 0, policy_version 59180 (0.0009) -[2023-10-17 02:38:01,001][62373] Updated weights for policy 0, policy_version 59190 (0.0009) -[2023-10-17 02:38:01,370][62373] Updated weights for policy 0, policy_version 59200 (0.0009) -[2023-10-17 02:38:02,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 120782848. Throughput: 0: 1767.0, 1: 1748.0. Samples: 30205200. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-17 02:38:02,215][61453] Avg episode reward: [(0, '10.550'), (1, '10.270')] -[2023-10-17 02:38:03,808][62408] Updated weights for policy 1, policy_version 58760 (0.0007) -[2023-10-17 02:38:04,174][62408] Updated weights for policy 1, policy_version 58770 (0.0007) -[2023-10-17 02:38:04,527][62408] Updated weights for policy 1, policy_version 58780 (0.0009) -[2023-10-17 02:38:05,169][62373] Updated weights for policy 0, policy_version 59210 (0.0011) -[2023-10-17 02:38:05,546][62373] Updated weights for policy 0, policy_version 59220 (0.0010) -[2023-10-17 02:38:05,921][62373] Updated weights for policy 0, policy_version 59230 (0.0010) -[2023-10-17 02:38:07,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 120848384. Throughput: 0: 1798.1, 1: 1750.7. Samples: 30216148. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-17 02:38:07,215][61453] Avg episode reward: [(0, '10.860'), (1, '10.010')] -[2023-10-17 02:38:08,336][62408] Updated weights for policy 1, policy_version 58790 (0.0009) -[2023-10-17 02:38:08,716][62408] Updated weights for policy 1, policy_version 58800 (0.0008) -[2023-10-17 02:38:09,078][62408] Updated weights for policy 1, policy_version 58810 (0.0008) -[2023-10-17 02:38:09,746][62373] Updated weights for policy 0, policy_version 59240 (0.0011) -[2023-10-17 02:38:10,121][62373] Updated weights for policy 0, policy_version 59250 (0.0008) -[2023-10-17 02:38:10,496][62373] Updated weights for policy 0, policy_version 59260 (0.0009) -[2023-10-17 02:38:12,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 120913920. Throughput: 0: 1766.5, 1: 1753.4. Samples: 30236826. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-17 02:38:12,215][61453] Avg episode reward: [(0, '10.990'), (1, '9.970')] -[2023-10-17 02:38:12,940][62408] Updated weights for policy 1, policy_version 58820 (0.0009) -[2023-10-17 02:38:13,304][62408] Updated weights for policy 1, policy_version 58830 (0.0010) -[2023-10-17 02:38:13,674][62408] Updated weights for policy 1, policy_version 58840 (0.0009) -[2023-10-17 02:38:14,122][62373] Updated weights for policy 0, policy_version 59270 (0.0009) -[2023-10-17 02:38:14,491][62373] Updated weights for policy 0, policy_version 59280 (0.0010) -[2023-10-17 02:38:14,868][62373] Updated weights for policy 0, policy_version 59290 (0.0008) -[2023-10-17 02:38:17,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 120979456. Throughput: 0: 1771.0, 1: 1773.2. Samples: 30259104. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-17 02:38:17,215][61453] Avg episode reward: [(0, '10.200'), (1, '9.450')] -[2023-10-17 02:38:17,642][62408] Updated weights for policy 1, policy_version 58850 (0.0009) -[2023-10-17 02:38:18,057][62408] Updated weights for policy 1, policy_version 58860 (0.0009) -[2023-10-17 02:38:18,429][62408] Updated weights for policy 1, policy_version 58870 (0.0010) -[2023-10-17 02:38:18,677][62373] Updated weights for policy 0, policy_version 59300 (0.0009) -[2023-10-17 02:38:18,787][62408] Updated weights for policy 1, policy_version 58880 (0.0007) -[2023-10-17 02:38:19,054][62373] Updated weights for policy 0, policy_version 59310 (0.0008) -[2023-10-17 02:38:19,424][62373] Updated weights for policy 0, policy_version 59320 (0.0011) -[2023-10-17 02:38:22,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 121044992. Throughput: 0: 1776.2, 1: 1745.7. Samples: 30268628. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-17 02:38:22,214][61453] Avg episode reward: [(0, '10.160'), (1, '9.470')] -[2023-10-17 02:38:22,529][62408] Updated weights for policy 1, policy_version 58890 (0.0009) -[2023-10-17 02:38:22,900][62408] Updated weights for policy 1, policy_version 58900 (0.0008) -[2023-10-17 02:38:23,213][62373] Updated weights for policy 0, policy_version 59330 (0.0008) -[2023-10-17 02:38:23,265][62408] Updated weights for policy 1, policy_version 58910 (0.0009) -[2023-10-17 02:38:23,590][62373] Updated weights for policy 0, policy_version 59340 (0.0011) -[2023-10-17 02:38:23,954][62373] Updated weights for policy 0, policy_version 59350 (0.0009) -[2023-10-17 02:38:24,319][62373] Updated weights for policy 0, policy_version 59360 (0.0009) -[2023-10-17 02:38:27,018][62408] Updated weights for policy 1, policy_version 58920 (0.0009) -[2023-10-17 02:38:27,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 121110528. Throughput: 0: 1774.1, 1: 1765.3. Samples: 30290824. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-17 02:38:27,215][61453] Avg episode reward: [(0, '10.330'), (1, '9.490')] -[2023-10-17 02:38:27,395][62408] Updated weights for policy 1, policy_version 58930 (0.0009) -[2023-10-17 02:38:27,765][62408] Updated weights for policy 1, policy_version 58940 (0.0009) -[2023-10-17 02:38:28,089][62373] Updated weights for policy 0, policy_version 59370 (0.0009) -[2023-10-17 02:38:28,465][62373] Updated weights for policy 0, policy_version 59380 (0.0008) -[2023-10-17 02:38:28,840][62373] Updated weights for policy 0, policy_version 59390 (0.0010) -[2023-10-17 02:38:31,492][62408] Updated weights for policy 1, policy_version 58950 (0.0009) -[2023-10-17 02:38:31,865][62408] Updated weights for policy 1, policy_version 58960 (0.0008) -[2023-10-17 02:38:32,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 121176064. Throughput: 0: 1789.7, 1: 1761.4. Samples: 30312340. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-17 02:38:32,215][61453] Avg episode reward: [(0, '10.340'), (1, '9.510')] -[2023-10-17 02:38:32,230][62408] Updated weights for policy 1, policy_version 58970 (0.0008) -[2023-10-17 02:38:32,854][62373] Updated weights for policy 0, policy_version 59400 (0.0009) -[2023-10-17 02:38:33,228][62373] Updated weights for policy 0, policy_version 59410 (0.0008) -[2023-10-17 02:38:33,606][62373] Updated weights for policy 0, policy_version 59420 (0.0008) -[2023-10-17 02:38:35,970][62408] Updated weights for policy 1, policy_version 58980 (0.0008) -[2023-10-17 02:38:36,334][62408] Updated weights for policy 1, policy_version 58990 (0.0009) -[2023-10-17 02:38:36,694][62408] Updated weights for policy 1, policy_version 59000 (0.0010) -[2023-10-17 02:38:37,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 121274368. Throughput: 0: 1770.4, 1: 1762.7. Samples: 30322510. Policy #0 lag: (min: 31.0, avg: 33.6, max: 63.0) -[2023-10-17 02:38:37,215][61453] Avg episode reward: [(0, '10.600'), (1, '9.460')] -[2023-10-17 02:38:37,346][62373] Updated weights for policy 0, policy_version 59430 (0.0008) -[2023-10-17 02:38:37,723][62373] Updated weights for policy 0, policy_version 59440 (0.0009) -[2023-10-17 02:38:38,094][62373] Updated weights for policy 0, policy_version 59450 (0.0007) -[2023-10-17 02:38:40,525][62408] Updated weights for policy 1, policy_version 59010 (0.0008) -[2023-10-17 02:38:40,885][62408] Updated weights for policy 1, policy_version 59020 (0.0007) -[2023-10-17 02:38:41,259][62408] Updated weights for policy 1, policy_version 59030 (0.0007) -[2023-10-17 02:38:41,623][62408] Updated weights for policy 1, policy_version 59040 (0.0008) -[2023-10-17 02:38:41,870][62373] Updated weights for policy 0, policy_version 59460 (0.0008) -[2023-10-17 02:38:42,214][61453] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 121339904. Throughput: 0: 1777.9, 1: 1772.7. Samples: 30344038. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:38:42,214][61453] Avg episode reward: [(0, '10.610'), (1, '10.190')] -[2023-10-17 02:38:42,241][62373] Updated weights for policy 0, policy_version 59470 (0.0008) -[2023-10-17 02:38:42,616][62373] Updated weights for policy 0, policy_version 59480 (0.0008) -[2023-10-17 02:38:45,433][62408] Updated weights for policy 1, policy_version 59050 (0.0010) -[2023-10-17 02:38:45,801][62408] Updated weights for policy 1, policy_version 59060 (0.0007) -[2023-10-17 02:38:46,171][62408] Updated weights for policy 1, policy_version 59070 (0.0011) -[2023-10-17 02:38:46,494][62373] Updated weights for policy 0, policy_version 59490 (0.0007) -[2023-10-17 02:38:46,874][62373] Updated weights for policy 0, policy_version 59500 (0.0009) -[2023-10-17 02:38:47,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 121405440. Throughput: 0: 1788.4, 1: 1757.1. Samples: 30364748. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:38:47,215][61453] Avg episode reward: [(0, '10.520'), (1, '10.090')] -[2023-10-17 02:38:47,244][62373] Updated weights for policy 0, policy_version 59510 (0.0008) -[2023-10-17 02:38:47,618][62373] Updated weights for policy 0, policy_version 59520 (0.0009) -[2023-10-17 02:38:49,908][62408] Updated weights for policy 1, policy_version 59080 (0.0008) -[2023-10-17 02:38:50,280][62408] Updated weights for policy 1, policy_version 59090 (0.0009) -[2023-10-17 02:38:50,640][62408] Updated weights for policy 1, policy_version 59100 (0.0010) -[2023-10-17 02:38:51,352][62373] Updated weights for policy 0, policy_version 59530 (0.0009) -[2023-10-17 02:38:51,711][62373] Updated weights for policy 0, policy_version 59540 (0.0007) -[2023-10-17 02:38:52,084][62373] Updated weights for policy 0, policy_version 59550 (0.0009) -[2023-10-17 02:38:52,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 121503744. Throughput: 0: 1769.8, 1: 1784.2. Samples: 30376076. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:38:52,214][61453] Avg episode reward: [(0, '10.600'), (1, '10.230')] -[2023-10-17 02:38:54,276][62408] Updated weights for policy 1, policy_version 59110 (0.0009) -[2023-10-17 02:38:54,643][62408] Updated weights for policy 1, policy_version 59120 (0.0009) -[2023-10-17 02:38:55,014][62408] Updated weights for policy 1, policy_version 59130 (0.0008) -[2023-10-17 02:38:55,869][62373] Updated weights for policy 0, policy_version 59560 (0.0009) -[2023-10-17 02:38:56,247][62373] Updated weights for policy 0, policy_version 59570 (0.0009) -[2023-10-17 02:38:56,608][62373] Updated weights for policy 0, policy_version 59580 (0.0007) -[2023-10-17 02:38:57,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 121569280. Throughput: 0: 1793.6, 1: 1768.2. Samples: 30397108. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:38:57,215][61453] Avg episode reward: [(0, '10.490'), (1, '10.340')] -[2023-10-17 02:38:58,908][62408] Updated weights for policy 1, policy_version 59140 (0.0009) -[2023-10-17 02:38:59,282][62408] Updated weights for policy 1, policy_version 59150 (0.0010) -[2023-10-17 02:38:59,653][62408] Updated weights for policy 1, policy_version 59160 (0.0009) -[2023-10-17 02:39:00,453][62373] Updated weights for policy 0, policy_version 59590 (0.0007) -[2023-10-17 02:39:00,823][62373] Updated weights for policy 0, policy_version 59600 (0.0008) -[2023-10-17 02:39:01,190][62373] Updated weights for policy 0, policy_version 59610 (0.0007) -[2023-10-17 02:39:02,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 121634816. Throughput: 0: 1766.1, 1: 1773.3. Samples: 30418380. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:39:02,215][61453] Avg episode reward: [(0, '10.520'), (1, '10.380')] -[2023-10-17 02:39:03,347][62408] Updated weights for policy 1, policy_version 59170 (0.0008) -[2023-10-17 02:39:03,745][62408] Updated weights for policy 1, policy_version 59180 (0.0008) -[2023-10-17 02:39:04,116][62408] Updated weights for policy 1, policy_version 59190 (0.0009) -[2023-10-17 02:39:04,474][62408] Updated weights for policy 1, policy_version 59200 (0.0009) -[2023-10-17 02:39:04,938][62373] Updated weights for policy 0, policy_version 59620 (0.0008) -[2023-10-17 02:39:05,317][62373] Updated weights for policy 0, policy_version 59630 (0.0010) -[2023-10-17 02:39:05,687][62373] Updated weights for policy 0, policy_version 59640 (0.0009) -[2023-10-17 02:39:07,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 121700352. Throughput: 0: 1794.2, 1: 1776.1. Samples: 30429294. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:39:07,214][61453] Avg episode reward: [(0, '11.060'), (1, '10.620')] -[2023-10-17 02:39:08,429][62408] Updated weights for policy 1, policy_version 59210 (0.0008) -[2023-10-17 02:39:08,800][62408] Updated weights for policy 1, policy_version 59220 (0.0009) -[2023-10-17 02:39:09,166][62408] Updated weights for policy 1, policy_version 59230 (0.0009) -[2023-10-17 02:39:09,272][62373] Updated weights for policy 0, policy_version 59650 (0.0008) -[2023-10-17 02:39:09,646][62373] Updated weights for policy 0, policy_version 59660 (0.0009) -[2023-10-17 02:39:10,006][62373] Updated weights for policy 0, policy_version 59670 (0.0007) -[2023-10-17 02:39:10,381][62373] Updated weights for policy 0, policy_version 59680 (0.0010) -[2023-10-17 02:39:12,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 121765888. Throughput: 0: 1770.9, 1: 1772.0. Samples: 30450258. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:39:12,215][61453] Avg episode reward: [(0, '11.360'), (1, '9.670')] -[2023-10-17 02:39:12,894][62408] Updated weights for policy 1, policy_version 59240 (0.0008) -[2023-10-17 02:39:13,264][62408] Updated weights for policy 1, policy_version 59250 (0.0008) -[2023-10-17 02:39:13,625][62408] Updated weights for policy 1, policy_version 59260 (0.0008) -[2023-10-17 02:39:14,112][62373] Updated weights for policy 0, policy_version 59690 (0.0008) -[2023-10-17 02:39:14,476][62373] Updated weights for policy 0, policy_version 59700 (0.0007) -[2023-10-17 02:39:14,846][62373] Updated weights for policy 0, policy_version 59710 (0.0007) -[2023-10-17 02:39:17,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 121831424. Throughput: 0: 1778.2, 1: 1784.3. Samples: 30472654. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:39:17,215][61453] Avg episode reward: [(0, '11.290'), (1, '9.820')] -[2023-10-17 02:39:17,537][62408] Updated weights for policy 1, policy_version 59270 (0.0007) -[2023-10-17 02:39:17,910][62408] Updated weights for policy 1, policy_version 59280 (0.0008) -[2023-10-17 02:39:18,281][62408] Updated weights for policy 1, policy_version 59290 (0.0007) -[2023-10-17 02:39:18,738][62373] Updated weights for policy 0, policy_version 59720 (0.0007) -[2023-10-17 02:39:19,115][62373] Updated weights for policy 0, policy_version 59730 (0.0008) -[2023-10-17 02:39:19,473][62373] Updated weights for policy 0, policy_version 59740 (0.0008) -[2023-10-17 02:39:22,154][62408] Updated weights for policy 1, policy_version 59300 (0.0008) -[2023-10-17 02:39:22,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 121896960. Throughput: 0: 1782.3, 1: 1768.8. Samples: 30482306. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:39:22,214][61453] Avg episode reward: [(0, '11.450'), (1, '10.180')] -[2023-10-17 02:39:22,526][62408] Updated weights for policy 1, policy_version 59310 (0.0007) -[2023-10-17 02:39:22,890][62408] Updated weights for policy 1, policy_version 59320 (0.0007) -[2023-10-17 02:39:23,147][62373] Updated weights for policy 0, policy_version 59750 (0.0007) -[2023-10-17 02:39:23,509][62373] Updated weights for policy 0, policy_version 59760 (0.0008) -[2023-10-17 02:39:23,885][62373] Updated weights for policy 0, policy_version 59770 (0.0008) -[2023-10-17 02:39:26,764][62408] Updated weights for policy 1, policy_version 59330 (0.0009) -[2023-10-17 02:39:27,129][62408] Updated weights for policy 1, policy_version 59340 (0.0008) -[2023-10-17 02:39:27,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 121962496. Throughput: 0: 1789.8, 1: 1777.2. Samples: 30504554. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:39:27,215][61453] Avg episode reward: [(0, '11.070'), (1, '9.420')] -[2023-10-17 02:39:27,484][62373] Updated weights for policy 0, policy_version 59780 (0.0008) -[2023-10-17 02:39:27,486][62408] Updated weights for policy 1, policy_version 59350 (0.0009) -[2023-10-17 02:39:27,851][62408] Updated weights for policy 1, policy_version 59360 (0.0007) -[2023-10-17 02:39:27,855][62373] Updated weights for policy 0, policy_version 59790 (0.0009) -[2023-10-17 02:39:28,220][62373] Updated weights for policy 0, policy_version 59800 (0.0009) -[2023-10-17 02:39:31,704][62408] Updated weights for policy 1, policy_version 59370 (0.0009) -[2023-10-17 02:39:32,054][62373] Updated weights for policy 0, policy_version 59810 (0.0007) -[2023-10-17 02:39:32,066][62408] Updated weights for policy 1, policy_version 59380 (0.0009) -[2023-10-17 02:39:32,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 122028032. Throughput: 0: 1805.9, 1: 1782.3. Samples: 30526218. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:39:32,214][61453] Avg episode reward: [(0, '11.170'), (1, '9.710')] -[2023-10-17 02:39:32,432][62373] Updated weights for policy 0, policy_version 59820 (0.0008) -[2023-10-17 02:39:32,432][62408] Updated weights for policy 1, policy_version 59390 (0.0008) -[2023-10-17 02:39:32,500][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000059392_60817408.pth... -[2023-10-17 02:39:32,528][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000057728_59113472.pth -[2023-10-17 02:39:32,803][62373] Updated weights for policy 0, policy_version 59830 (0.0009) -[2023-10-17 02:39:33,174][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000059840_61276160.pth... -[2023-10-17 02:39:33,177][62373] Updated weights for policy 0, policy_version 59840 (0.0009) -[2023-10-17 02:39:33,211][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000058144_59539456.pth -[2023-10-17 02:39:36,399][62408] Updated weights for policy 1, policy_version 59400 (0.0007) -[2023-10-17 02:39:36,760][62408] Updated weights for policy 1, policy_version 59410 (0.0010) -[2023-10-17 02:39:37,133][62408] Updated weights for policy 1, policy_version 59420 (0.0009) -[2023-10-17 02:39:37,145][62373] Updated weights for policy 0, policy_version 59850 (0.0008) -[2023-10-17 02:39:37,214][61453] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 122093568. Throughput: 0: 1790.6, 1: 1766.1. Samples: 30536130. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:39:37,214][61453] Avg episode reward: [(0, '10.670'), (1, '10.430')] -[2023-10-17 02:39:37,522][62373] Updated weights for policy 0, policy_version 59860 (0.0008) -[2023-10-17 02:39:37,897][62373] Updated weights for policy 0, policy_version 59870 (0.0008) -[2023-10-17 02:39:41,015][62408] Updated weights for policy 1, policy_version 59430 (0.0010) -[2023-10-17 02:39:41,393][62408] Updated weights for policy 1, policy_version 59440 (0.0010) -[2023-10-17 02:39:41,751][62408] Updated weights for policy 1, policy_version 59450 (0.0008) -[2023-10-17 02:39:41,769][62373] Updated weights for policy 0, policy_version 59880 (0.0008) -[2023-10-17 02:39:42,134][62373] Updated weights for policy 0, policy_version 59890 (0.0008) -[2023-10-17 02:39:42,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 122191872. Throughput: 0: 1794.0, 1: 1774.4. Samples: 30557688. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:39:42,215][61453] Avg episode reward: [(0, '9.880'), (1, '9.700')] -[2023-10-17 02:39:42,504][62373] Updated weights for policy 0, policy_version 59900 (0.0011) -[2023-10-17 02:39:45,641][62408] Updated weights for policy 1, policy_version 59460 (0.0008) -[2023-10-17 02:39:46,012][62408] Updated weights for policy 1, policy_version 59470 (0.0009) -[2023-10-17 02:39:46,382][62373] Updated weights for policy 0, policy_version 59910 (0.0007) -[2023-10-17 02:39:46,383][62408] Updated weights for policy 1, policy_version 59480 (0.0008) -[2023-10-17 02:39:46,749][62373] Updated weights for policy 0, policy_version 59920 (0.0007) -[2023-10-17 02:39:47,120][62373] Updated weights for policy 0, policy_version 59930 (0.0008) -[2023-10-17 02:39:47,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 122257408. Throughput: 0: 1795.3, 1: 1739.6. Samples: 30577450. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:39:47,215][61453] Avg episode reward: [(0, '10.030'), (1, '9.600')] -[2023-10-17 02:39:50,141][62408] Updated weights for policy 1, policy_version 59490 (0.0008) -[2023-10-17 02:39:50,526][62408] Updated weights for policy 1, policy_version 59500 (0.0009) -[2023-10-17 02:39:50,793][62373] Updated weights for policy 0, policy_version 59940 (0.0008) -[2023-10-17 02:39:50,898][62408] Updated weights for policy 1, policy_version 59510 (0.0007) -[2023-10-17 02:39:51,159][62373] Updated weights for policy 0, policy_version 59950 (0.0010) -[2023-10-17 02:39:51,257][62408] Updated weights for policy 1, policy_version 59520 (0.0007) -[2023-10-17 02:39:51,527][62373] Updated weights for policy 0, policy_version 59960 (0.0007) -[2023-10-17 02:39:52,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 122355712. Throughput: 0: 1783.3, 1: 1776.4. Samples: 30589480. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:39:52,215][61453] Avg episode reward: [(0, '10.010'), (1, '10.190')] -[2023-10-17 02:39:55,184][62408] Updated weights for policy 1, policy_version 59530 (0.0009) -[2023-10-17 02:39:55,307][62373] Updated weights for policy 0, policy_version 59970 (0.0007) -[2023-10-17 02:39:55,552][62408] Updated weights for policy 1, policy_version 59540 (0.0009) -[2023-10-17 02:39:55,668][62373] Updated weights for policy 0, policy_version 59980 (0.0008) -[2023-10-17 02:39:55,914][62408] Updated weights for policy 1, policy_version 59550 (0.0007) -[2023-10-17 02:39:56,041][62373] Updated weights for policy 0, policy_version 59990 (0.0009) -[2023-10-17 02:39:56,400][62373] Updated weights for policy 0, policy_version 60000 (0.0011) -[2023-10-17 02:39:57,214][61453] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 122421248. Throughput: 0: 1792.5, 1: 1747.5. Samples: 30609556. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:39:57,214][61453] Avg episode reward: [(0, '10.120'), (1, '10.030')] -[2023-10-17 02:39:59,692][62408] Updated weights for policy 1, policy_version 59560 (0.0007) -[2023-10-17 02:40:00,054][62408] Updated weights for policy 1, policy_version 59570 (0.0009) -[2023-10-17 02:40:00,260][62373] Updated weights for policy 0, policy_version 60010 (0.0008) -[2023-10-17 02:40:00,413][62408] Updated weights for policy 1, policy_version 59580 (0.0008) -[2023-10-17 02:40:00,637][62373] Updated weights for policy 0, policy_version 60020 (0.0009) -[2023-10-17 02:40:01,002][62373] Updated weights for policy 0, policy_version 60030 (0.0010) -[2023-10-17 02:40:02,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 122486784. Throughput: 0: 1771.2, 1: 1741.9. Samples: 30630746. Policy #0 lag: (min: 3.0, avg: 18.4, max: 35.0) -[2023-10-17 02:40:02,215][61453] Avg episode reward: [(0, '9.870'), (1, '10.480')] -[2023-10-17 02:40:04,318][62408] Updated weights for policy 1, policy_version 59590 (0.0010) -[2023-10-17 02:40:04,682][62408] Updated weights for policy 1, policy_version 59600 (0.0009) -[2023-10-17 02:40:04,904][62373] Updated weights for policy 0, policy_version 60040 (0.0008) -[2023-10-17 02:40:05,044][62408] Updated weights for policy 1, policy_version 59610 (0.0007) -[2023-10-17 02:40:05,276][62373] Updated weights for policy 0, policy_version 60050 (0.0007) -[2023-10-17 02:40:05,648][62373] Updated weights for policy 0, policy_version 60060 (0.0007) -[2023-10-17 02:40:07,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 122552320. Throughput: 0: 1790.3, 1: 1749.7. Samples: 30641606. Policy #0 lag: (min: 3.0, avg: 18.4, max: 35.0) -[2023-10-17 02:40:07,215][61453] Avg episode reward: [(0, '9.700'), (1, '9.520')] -[2023-10-17 02:40:08,897][62408] Updated weights for policy 1, policy_version 59620 (0.0009) -[2023-10-17 02:40:09,259][62373] Updated weights for policy 0, policy_version 60070 (0.0008) -[2023-10-17 02:40:09,265][62408] Updated weights for policy 1, policy_version 59630 (0.0007) -[2023-10-17 02:40:09,622][62373] Updated weights for policy 0, policy_version 60080 (0.0007) -[2023-10-17 02:40:09,630][62408] Updated weights for policy 1, policy_version 59640 (0.0008) -[2023-10-17 02:40:09,988][62373] Updated weights for policy 0, policy_version 60090 (0.0007) -[2023-10-17 02:40:12,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 122617856. Throughput: 0: 1762.6, 1: 1741.8. Samples: 30662254. Policy #0 lag: (min: 3.0, avg: 18.4, max: 35.0) -[2023-10-17 02:40:12,215][61453] Avg episode reward: [(0, '10.300'), (1, '9.580')] -[2023-10-17 02:40:13,494][62408] Updated weights for policy 1, policy_version 59650 (0.0009) -[2023-10-17 02:40:13,819][62373] Updated weights for policy 0, policy_version 60100 (0.0009) -[2023-10-17 02:40:13,867][62408] Updated weights for policy 1, policy_version 59660 (0.0009) -[2023-10-17 02:40:14,189][62373] Updated weights for policy 0, policy_version 60110 (0.0009) -[2023-10-17 02:40:14,236][62408] Updated weights for policy 1, policy_version 59670 (0.0008) -[2023-10-17 02:40:14,548][62373] Updated weights for policy 0, policy_version 60120 (0.0008) -[2023-10-17 02:40:14,592][62408] Updated weights for policy 1, policy_version 59680 (0.0007) -[2023-10-17 02:40:17,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.6, 300 sec: 14106.9). Total num frames: 122683392. Throughput: 0: 1758.3, 1: 1752.3. Samples: 30684194. Policy #0 lag: (min: 3.0, avg: 18.4, max: 35.0) -[2023-10-17 02:40:17,214][61453] Avg episode reward: [(0, '10.580'), (1, '10.840')] -[2023-10-17 02:40:18,434][62373] Updated weights for policy 0, policy_version 60130 (0.0009) -[2023-10-17 02:40:18,602][62408] Updated weights for policy 1, policy_version 59690 (0.0007) -[2023-10-17 02:40:18,802][62373] Updated weights for policy 0, policy_version 60140 (0.0008) -[2023-10-17 02:40:18,963][62408] Updated weights for policy 1, policy_version 59700 (0.0008) -[2023-10-17 02:40:19,166][62373] Updated weights for policy 0, policy_version 60150 (0.0007) -[2023-10-17 02:40:19,337][62408] Updated weights for policy 1, policy_version 59710 (0.0009) -[2023-10-17 02:40:19,526][62373] Updated weights for policy 0, policy_version 60160 (0.0008) -[2023-10-17 02:40:22,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 122748928. Throughput: 0: 1761.6, 1: 1739.7. Samples: 30693692. Policy #0 lag: (min: 3.0, avg: 18.4, max: 35.0) -[2023-10-17 02:40:22,215][61453] Avg episode reward: [(0, '9.440'), (1, '10.050')] -[2023-10-17 02:40:23,211][62408] Updated weights for policy 1, policy_version 59720 (0.0009) -[2023-10-17 02:40:23,272][62373] Updated weights for policy 0, policy_version 60170 (0.0007) -[2023-10-17 02:40:23,578][62408] Updated weights for policy 1, policy_version 59730 (0.0009) -[2023-10-17 02:40:23,649][62373] Updated weights for policy 0, policy_version 60180 (0.0007) -[2023-10-17 02:40:23,955][62408] Updated weights for policy 1, policy_version 59740 (0.0009) -[2023-10-17 02:40:24,021][62373] Updated weights for policy 0, policy_version 60190 (0.0008) -[2023-10-17 02:40:27,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 122814464. Throughput: 0: 1761.9, 1: 1743.6. Samples: 30715438. Policy #0 lag: (min: 3.0, avg: 18.4, max: 35.0) -[2023-10-17 02:40:27,215][61453] Avg episode reward: [(0, '9.740'), (1, '10.090')] -[2023-10-17 02:40:27,814][62373] Updated weights for policy 0, policy_version 60200 (0.0007) -[2023-10-17 02:40:27,867][62408] Updated weights for policy 1, policy_version 59750 (0.0008) -[2023-10-17 02:40:28,192][62373] Updated weights for policy 0, policy_version 60210 (0.0008) -[2023-10-17 02:40:28,236][62408] Updated weights for policy 1, policy_version 59760 (0.0008) -[2023-10-17 02:40:28,560][62373] Updated weights for policy 0, policy_version 60220 (0.0009) -[2023-10-17 02:40:28,605][62408] Updated weights for policy 1, policy_version 59770 (0.0008) -[2023-10-17 02:40:32,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 122880000. Throughput: 0: 1780.1, 1: 1770.1. Samples: 30737210. Policy #0 lag: (min: 3.0, avg: 18.4, max: 35.0) -[2023-10-17 02:40:32,214][61453] Avg episode reward: [(0, '9.590'), (1, '11.230')] -[2023-10-17 02:40:32,392][62408] Updated weights for policy 1, policy_version 59780 (0.0008) -[2023-10-17 02:40:32,422][62373] Updated weights for policy 0, policy_version 60230 (0.0009) -[2023-10-17 02:40:32,766][62408] Updated weights for policy 1, policy_version 59790 (0.0007) -[2023-10-17 02:40:32,788][62373] Updated weights for policy 0, policy_version 60240 (0.0008) -[2023-10-17 02:40:33,124][62408] Updated weights for policy 1, policy_version 59800 (0.0009) -[2023-10-17 02:40:33,168][62373] Updated weights for policy 0, policy_version 60250 (0.0007) -[2023-10-17 02:40:36,863][62373] Updated weights for policy 0, policy_version 60260 (0.0008) -[2023-10-17 02:40:37,101][62408] Updated weights for policy 1, policy_version 59810 (0.0010) -[2023-10-17 02:40:37,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 122945536. Throughput: 0: 1764.3, 1: 1734.6. Samples: 30746930. Policy #0 lag: (min: 3.0, avg: 18.4, max: 35.0) -[2023-10-17 02:40:37,215][61453] Avg episode reward: [(0, '9.210'), (1, '10.890')] -[2023-10-17 02:40:37,237][62373] Updated weights for policy 0, policy_version 60270 (0.0008) -[2023-10-17 02:40:37,490][62408] Updated weights for policy 1, policy_version 59820 (0.0008) -[2023-10-17 02:40:37,604][62373] Updated weights for policy 0, policy_version 60280 (0.0008) -[2023-10-17 02:40:37,853][62408] Updated weights for policy 1, policy_version 59830 (0.0008) -[2023-10-17 02:40:38,220][62408] Updated weights for policy 1, policy_version 59840 (0.0011) -[2023-10-17 02:40:41,289][62373] Updated weights for policy 0, policy_version 60290 (0.0008) -[2023-10-17 02:40:41,664][62373] Updated weights for policy 0, policy_version 60300 (0.0009) -[2023-10-17 02:40:42,033][62373] Updated weights for policy 0, policy_version 60310 (0.0009) -[2023-10-17 02:40:42,065][62408] Updated weights for policy 1, policy_version 59850 (0.0008) -[2023-10-17 02:40:42,214][61453] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 123011072. Throughput: 0: 1781.6, 1: 1760.3. Samples: 30768942. Policy #0 lag: (min: 3.0, avg: 18.4, max: 35.0) -[2023-10-17 02:40:42,214][61453] Avg episode reward: [(0, '9.620'), (1, '11.190')] -[2023-10-17 02:40:42,402][62373] Updated weights for policy 0, policy_version 60320 (0.0008) -[2023-10-17 02:40:42,436][62408] Updated weights for policy 1, policy_version 59860 (0.0007) -[2023-10-17 02:40:42,809][62408] Updated weights for policy 1, policy_version 59870 (0.0007) -[2023-10-17 02:40:46,346][62373] Updated weights for policy 0, policy_version 60330 (0.0008) -[2023-10-17 02:40:46,712][62373] Updated weights for policy 0, policy_version 60340 (0.0009) -[2023-10-17 02:40:46,795][62408] Updated weights for policy 1, policy_version 59880 (0.0008) -[2023-10-17 02:40:47,078][62373] Updated weights for policy 0, policy_version 60350 (0.0009) -[2023-10-17 02:40:47,154][62408] Updated weights for policy 1, policy_version 59890 (0.0007) -[2023-10-17 02:40:47,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 123109376. Throughput: 0: 1766.7, 1: 1749.8. Samples: 30788988. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:40:47,215][61453] Avg episode reward: [(0, '9.270'), (1, '10.820')] -[2023-10-17 02:40:47,524][62408] Updated weights for policy 1, policy_version 59900 (0.0008) -[2023-10-17 02:40:50,838][62373] Updated weights for policy 0, policy_version 60360 (0.0009) -[2023-10-17 02:40:51,215][62373] Updated weights for policy 0, policy_version 60370 (0.0007) -[2023-10-17 02:40:51,429][62408] Updated weights for policy 1, policy_version 59910 (0.0008) -[2023-10-17 02:40:51,586][62373] Updated weights for policy 0, policy_version 60380 (0.0008) -[2023-10-17 02:40:51,785][62408] Updated weights for policy 1, policy_version 59920 (0.0008) -[2023-10-17 02:40:52,147][62408] Updated weights for policy 1, policy_version 59930 (0.0010) -[2023-10-17 02:40:52,214][61453] Fps is (10 sec: 16383.8, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 123174912. Throughput: 0: 1776.6, 1: 1748.8. Samples: 30800246. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:40:52,215][61453] Avg episode reward: [(0, '10.380'), (1, '10.120')] -[2023-10-17 02:40:55,545][62373] Updated weights for policy 0, policy_version 60390 (0.0008) -[2023-10-17 02:40:55,907][62373] Updated weights for policy 0, policy_version 60400 (0.0007) -[2023-10-17 02:40:56,079][62408] Updated weights for policy 1, policy_version 59940 (0.0009) -[2023-10-17 02:40:56,275][62373] Updated weights for policy 0, policy_version 60410 (0.0008) -[2023-10-17 02:40:56,448][62408] Updated weights for policy 1, policy_version 59950 (0.0009) -[2023-10-17 02:40:56,815][62408] Updated weights for policy 1, policy_version 59960 (0.0009) -[2023-10-17 02:40:57,214][61453] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 123273216. Throughput: 0: 1771.4, 1: 1754.3. Samples: 30820908. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:40:57,214][61453] Avg episode reward: [(0, '10.740'), (1, '10.470')] -[2023-10-17 02:40:59,998][62373] Updated weights for policy 0, policy_version 60420 (0.0010) -[2023-10-17 02:41:00,368][62373] Updated weights for policy 0, policy_version 60430 (0.0009) -[2023-10-17 02:41:00,607][62408] Updated weights for policy 1, policy_version 59970 (0.0008) -[2023-10-17 02:41:00,728][62373] Updated weights for policy 0, policy_version 60440 (0.0009) -[2023-10-17 02:41:00,975][62408] Updated weights for policy 1, policy_version 59980 (0.0008) -[2023-10-17 02:41:01,335][62408] Updated weights for policy 1, policy_version 59990 (0.0008) -[2023-10-17 02:41:01,697][62408] Updated weights for policy 1, policy_version 60000 (0.0010) -[2023-10-17 02:41:02,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 123338752. Throughput: 0: 1758.3, 1: 1723.7. Samples: 30840882. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:41:02,215][61453] Avg episode reward: [(0, '11.100'), (1, '10.710')] -[2023-10-17 02:41:04,558][62373] Updated weights for policy 0, policy_version 60450 (0.0008) -[2023-10-17 02:41:04,923][62373] Updated weights for policy 0, policy_version 60460 (0.0008) -[2023-10-17 02:41:05,300][62373] Updated weights for policy 0, policy_version 60470 (0.0007) -[2023-10-17 02:41:05,601][62408] Updated weights for policy 1, policy_version 60010 (0.0010) -[2023-10-17 02:41:05,663][62373] Updated weights for policy 0, policy_version 60480 (0.0010) -[2023-10-17 02:41:05,971][62408] Updated weights for policy 1, policy_version 60020 (0.0009) -[2023-10-17 02:41:06,353][62408] Updated weights for policy 1, policy_version 60030 (0.0009) -[2023-10-17 02:41:07,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 123404288. Throughput: 0: 1779.6, 1: 1757.4. Samples: 30852856. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:41:07,214][61453] Avg episode reward: [(0, '11.090'), (1, '10.380')] -[2023-10-17 02:41:09,342][62373] Updated weights for policy 0, policy_version 60490 (0.0011) -[2023-10-17 02:41:09,714][62373] Updated weights for policy 0, policy_version 60500 (0.0009) -[2023-10-17 02:41:10,082][62373] Updated weights for policy 0, policy_version 60510 (0.0008) -[2023-10-17 02:41:10,242][62408] Updated weights for policy 1, policy_version 60040 (0.0009) -[2023-10-17 02:41:10,610][62408] Updated weights for policy 1, policy_version 60050 (0.0008) -[2023-10-17 02:41:10,982][62408] Updated weights for policy 1, policy_version 60060 (0.0010) -[2023-10-17 02:41:12,214][61453] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 123469824. Throughput: 0: 1764.1, 1: 1736.9. Samples: 30872982. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:41:12,214][61453] Avg episode reward: [(0, '12.070'), (1, '10.250')] -[2023-10-17 02:41:12,215][62094] Saving new best policy, reward=12.070! -[2023-10-17 02:41:13,954][62373] Updated weights for policy 0, policy_version 60520 (0.0007) -[2023-10-17 02:41:14,326][62373] Updated weights for policy 0, policy_version 60530 (0.0009) -[2023-10-17 02:41:14,697][62373] Updated weights for policy 0, policy_version 60540 (0.0007) -[2023-10-17 02:41:14,787][62408] Updated weights for policy 1, policy_version 60070 (0.0009) -[2023-10-17 02:41:15,154][62408] Updated weights for policy 1, policy_version 60080 (0.0009) -[2023-10-17 02:41:15,518][62408] Updated weights for policy 1, policy_version 60090 (0.0008) -[2023-10-17 02:41:17,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 123535360. Throughput: 0: 1767.7, 1: 1732.8. Samples: 30894732. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:41:17,215][61453] Avg episode reward: [(0, '11.860'), (1, '9.890')] -[2023-10-17 02:41:18,534][62373] Updated weights for policy 0, policy_version 60550 (0.0010) -[2023-10-17 02:41:18,894][62373] Updated weights for policy 0, policy_version 60560 (0.0007) -[2023-10-17 02:41:19,265][62373] Updated weights for policy 0, policy_version 60570 (0.0010) -[2023-10-17 02:41:19,374][62408] Updated weights for policy 1, policy_version 60100 (0.0009) -[2023-10-17 02:41:19,742][62408] Updated weights for policy 1, policy_version 60110 (0.0008) -[2023-10-17 02:41:20,115][62408] Updated weights for policy 1, policy_version 60120 (0.0008) -[2023-10-17 02:41:22,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 123600896. Throughput: 0: 1762.4, 1: 1749.7. Samples: 30904978. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:41:22,215][61453] Avg episode reward: [(0, '11.670'), (1, '9.990')] -[2023-10-17 02:41:23,012][62373] Updated weights for policy 0, policy_version 60580 (0.0008) -[2023-10-17 02:41:23,377][62373] Updated weights for policy 0, policy_version 60590 (0.0010) -[2023-10-17 02:41:23,756][62373] Updated weights for policy 0, policy_version 60600 (0.0009) -[2023-10-17 02:41:23,938][62408] Updated weights for policy 1, policy_version 60130 (0.0008) -[2023-10-17 02:41:24,336][62408] Updated weights for policy 1, policy_version 60140 (0.0010) -[2023-10-17 02:41:24,715][62408] Updated weights for policy 1, policy_version 60150 (0.0011) -[2023-10-17 02:41:25,080][62408] Updated weights for policy 1, policy_version 60160 (0.0011) -[2023-10-17 02:41:27,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 123666432. Throughput: 0: 1762.9, 1: 1733.7. Samples: 30926290. Policy #0 lag: (min: 9.0, avg: 29.2, max: 41.0) -[2023-10-17 02:41:27,215][61453] Avg episode reward: [(0, '10.860'), (1, '9.630')] -[2023-10-17 02:41:27,446][62373] Updated weights for policy 0, policy_version 60610 (0.0007) -[2023-10-17 02:41:27,821][62373] Updated weights for policy 0, policy_version 60620 (0.0007) -[2023-10-17 02:41:28,197][62373] Updated weights for policy 0, policy_version 60630 (0.0009) -[2023-10-17 02:41:28,568][62373] Updated weights for policy 0, policy_version 60640 (0.0009) -[2023-10-17 02:41:28,946][62408] Updated weights for policy 1, policy_version 60170 (0.0009) -[2023-10-17 02:41:29,307][62408] Updated weights for policy 1, policy_version 60180 (0.0010) -[2023-10-17 02:41:29,678][62408] Updated weights for policy 1, policy_version 60190 (0.0009) -[2023-10-17 02:41:32,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 123731968. Throughput: 0: 1796.7, 1: 1751.5. Samples: 30948656. Policy #0 lag: (min: 9.0, avg: 29.2, max: 41.0) -[2023-10-17 02:41:32,214][61453] Avg episode reward: [(0, '10.540'), (1, '9.980')] -[2023-10-17 02:41:32,223][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000060192_61636608.pth... -[2023-10-17 02:41:32,263][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000058560_59965440.pth -[2023-10-17 02:41:32,390][62373] Updated weights for policy 0, policy_version 60650 (0.0008) -[2023-10-17 02:41:32,750][62373] Updated weights for policy 0, policy_version 60660 (0.0008) -[2023-10-17 02:41:33,117][62373] Updated weights for policy 0, policy_version 60670 (0.0008) -[2023-10-17 02:41:33,190][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000060672_62128128.pth... -[2023-10-17 02:41:33,233][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000058976_60391424.pth -[2023-10-17 02:41:33,430][62408] Updated weights for policy 1, policy_version 60200 (0.0008) -[2023-10-17 02:41:33,799][62408] Updated weights for policy 1, policy_version 60210 (0.0007) -[2023-10-17 02:41:34,168][62408] Updated weights for policy 1, policy_version 60220 (0.0008) -[2023-10-17 02:41:36,960][62373] Updated weights for policy 0, policy_version 60680 (0.0009) -[2023-10-17 02:41:37,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 123797504. Throughput: 0: 1767.9, 1: 1748.2. Samples: 30958472. Policy #0 lag: (min: 9.0, avg: 29.2, max: 41.0) -[2023-10-17 02:41:37,214][61453] Avg episode reward: [(0, '10.370'), (1, '9.490')] -[2023-10-17 02:41:37,329][62373] Updated weights for policy 0, policy_version 60690 (0.0011) -[2023-10-17 02:41:37,700][62373] Updated weights for policy 0, policy_version 60700 (0.0009) -[2023-10-17 02:41:37,897][62408] Updated weights for policy 1, policy_version 60230 (0.0007) -[2023-10-17 02:41:38,266][62408] Updated weights for policy 1, policy_version 60240 (0.0009) -[2023-10-17 02:41:38,625][62408] Updated weights for policy 1, policy_version 60250 (0.0009) -[2023-10-17 02:41:41,525][62373] Updated weights for policy 0, policy_version 60710 (0.0008) -[2023-10-17 02:41:41,906][62373] Updated weights for policy 0, policy_version 60720 (0.0007) -[2023-10-17 02:41:42,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 123863040. Throughput: 0: 1791.7, 1: 1750.2. Samples: 30980292. Policy #0 lag: (min: 9.0, avg: 29.2, max: 41.0) -[2023-10-17 02:41:42,215][61453] Avg episode reward: [(0, '10.370'), (1, '10.300')] -[2023-10-17 02:41:42,273][62373] Updated weights for policy 0, policy_version 60730 (0.0008) -[2023-10-17 02:41:42,475][62408] Updated weights for policy 1, policy_version 60260 (0.0009) -[2023-10-17 02:41:42,838][62408] Updated weights for policy 1, policy_version 60270 (0.0008) -[2023-10-17 02:41:43,206][62408] Updated weights for policy 1, policy_version 60280 (0.0012) -[2023-10-17 02:41:46,117][62373] Updated weights for policy 0, policy_version 60740 (0.0009) -[2023-10-17 02:41:46,485][62373] Updated weights for policy 0, policy_version 60750 (0.0008) -[2023-10-17 02:41:46,863][62373] Updated weights for policy 0, policy_version 60760 (0.0007) -[2023-10-17 02:41:47,135][62408] Updated weights for policy 1, policy_version 60290 (0.0008) -[2023-10-17 02:41:47,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 123961344. Throughput: 0: 1775.1, 1: 1782.1. Samples: 31000952. Policy #0 lag: (min: 9.0, avg: 29.2, max: 41.0) -[2023-10-17 02:41:47,214][61453] Avg episode reward: [(0, '9.630'), (1, '9.150')] -[2023-10-17 02:41:47,498][62408] Updated weights for policy 1, policy_version 60300 (0.0009) -[2023-10-17 02:41:47,871][62408] Updated weights for policy 1, policy_version 60310 (0.0008) -[2023-10-17 02:41:48,231][62408] Updated weights for policy 1, policy_version 60320 (0.0009) -[2023-10-17 02:41:50,733][62373] Updated weights for policy 0, policy_version 60770 (0.0009) -[2023-10-17 02:41:51,104][62373] Updated weights for policy 0, policy_version 60780 (0.0010) -[2023-10-17 02:41:51,472][62373] Updated weights for policy 0, policy_version 60790 (0.0009) -[2023-10-17 02:41:51,844][62373] Updated weights for policy 0, policy_version 60800 (0.0008) -[2023-10-17 02:41:52,043][62408] Updated weights for policy 1, policy_version 60330 (0.0010) -[2023-10-17 02:41:52,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 124026880. Throughput: 0: 1777.7, 1: 1749.6. Samples: 31011586. Policy #0 lag: (min: 9.0, avg: 29.2, max: 41.0) -[2023-10-17 02:41:52,215][61453] Avg episode reward: [(0, '9.980'), (1, '9.670')] -[2023-10-17 02:41:52,421][62408] Updated weights for policy 1, policy_version 60340 (0.0010) -[2023-10-17 02:41:52,798][62408] Updated weights for policy 1, policy_version 60350 (0.0009) -[2023-10-17 02:41:55,564][62373] Updated weights for policy 0, policy_version 60810 (0.0007) -[2023-10-17 02:41:55,942][62373] Updated weights for policy 0, policy_version 60820 (0.0009) -[2023-10-17 02:41:56,316][62373] Updated weights for policy 0, policy_version 60830 (0.0008) -[2023-10-17 02:41:56,796][62408] Updated weights for policy 1, policy_version 60360 (0.0008) -[2023-10-17 02:41:57,160][62408] Updated weights for policy 1, policy_version 60370 (0.0008) -[2023-10-17 02:41:57,214][61453] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 124092416. Throughput: 0: 1777.8, 1: 1772.8. Samples: 31032758. Policy #0 lag: (min: 9.0, avg: 29.2, max: 41.0) -[2023-10-17 02:41:57,214][61453] Avg episode reward: [(0, '10.100'), (1, '9.150')] -[2023-10-17 02:41:57,531][62408] Updated weights for policy 1, policy_version 60380 (0.0010) -[2023-10-17 02:42:00,164][62373] Updated weights for policy 0, policy_version 60840 (0.0008) -[2023-10-17 02:42:00,532][62373] Updated weights for policy 0, policy_version 60850 (0.0008) -[2023-10-17 02:42:00,908][62373] Updated weights for policy 0, policy_version 60860 (0.0008) -[2023-10-17 02:42:01,450][62408] Updated weights for policy 1, policy_version 60390 (0.0008) -[2023-10-17 02:42:01,818][62408] Updated weights for policy 1, policy_version 60400 (0.0008) -[2023-10-17 02:42:02,190][62408] Updated weights for policy 1, policy_version 60410 (0.0009) -[2023-10-17 02:42:02,214][61453] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 124157952. Throughput: 0: 1765.6, 1: 1763.9. Samples: 31053562. Policy #0 lag: (min: 9.0, avg: 29.2, max: 41.0) -[2023-10-17 02:42:02,215][61453] Avg episode reward: [(0, '9.900'), (1, '9.580')] -[2023-10-17 02:42:04,642][62373] Updated weights for policy 0, policy_version 60870 (0.0008) -[2023-10-17 02:42:05,018][62373] Updated weights for policy 0, policy_version 60880 (0.0009) -[2023-10-17 02:42:05,381][62373] Updated weights for policy 0, policy_version 60890 (0.0008) -[2023-10-17 02:42:06,045][62408] Updated weights for policy 1, policy_version 60420 (0.0009) -[2023-10-17 02:42:06,417][62408] Updated weights for policy 1, policy_version 60430 (0.0007) -[2023-10-17 02:42:06,775][62408] Updated weights for policy 1, policy_version 60440 (0.0009) -[2023-10-17 02:42:07,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 124256256. Throughput: 0: 1789.2, 1: 1765.3. Samples: 31064930. Policy #0 lag: (min: 18.0, avg: 18.4, max: 30.0) -[2023-10-17 02:42:07,214][61453] Avg episode reward: [(0, '10.850'), (1, '9.580')] -[2023-10-17 02:42:09,140][62373] Updated weights for policy 0, policy_version 60900 (0.0009) -[2023-10-17 02:42:09,505][62373] Updated weights for policy 0, policy_version 60910 (0.0009) -[2023-10-17 02:42:09,874][62373] Updated weights for policy 0, policy_version 60920 (0.0008) -[2023-10-17 02:42:10,586][62408] Updated weights for policy 1, policy_version 60450 (0.0009) -[2023-10-17 02:42:11,011][62408] Updated weights for policy 1, policy_version 60460 (0.0010) -[2023-10-17 02:42:11,389][62408] Updated weights for policy 1, policy_version 60470 (0.0011) -[2023-10-17 02:42:11,753][62408] Updated weights for policy 1, policy_version 60480 (0.0008) -[2023-10-17 02:42:12,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 124321792. Throughput: 0: 1767.1, 1: 1774.4. Samples: 31085656. Policy #0 lag: (min: 18.0, avg: 18.4, max: 30.0) -[2023-10-17 02:42:12,215][61453] Avg episode reward: [(0, '10.890'), (1, '8.730')] -[2023-10-17 02:42:13,683][62373] Updated weights for policy 0, policy_version 60930 (0.0009) -[2023-10-17 02:42:14,050][62373] Updated weights for policy 0, policy_version 60940 (0.0009) -[2023-10-17 02:42:14,419][62373] Updated weights for policy 0, policy_version 60950 (0.0011) -[2023-10-17 02:42:14,789][62373] Updated weights for policy 0, policy_version 60960 (0.0009) -[2023-10-17 02:42:15,587][62408] Updated weights for policy 1, policy_version 60490 (0.0010) -[2023-10-17 02:42:15,946][62408] Updated weights for policy 1, policy_version 60500 (0.0010) -[2023-10-17 02:42:16,314][62408] Updated weights for policy 1, policy_version 60510 (0.0010) -[2023-10-17 02:42:17,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 124387328. Throughput: 0: 1760.3, 1: 1744.8. Samples: 31106386. Policy #0 lag: (min: 18.0, avg: 18.4, max: 30.0) -[2023-10-17 02:42:17,215][61453] Avg episode reward: [(0, '10.560'), (1, '8.970')] -[2023-10-17 02:42:18,689][62373] Updated weights for policy 0, policy_version 60970 (0.0010) -[2023-10-17 02:42:19,062][62373] Updated weights for policy 0, policy_version 60980 (0.0007) -[2023-10-17 02:42:19,434][62373] Updated weights for policy 0, policy_version 60990 (0.0008) -[2023-10-17 02:42:20,195][62408] Updated weights for policy 1, policy_version 60520 (0.0008) -[2023-10-17 02:42:20,552][62408] Updated weights for policy 1, policy_version 60530 (0.0009) -[2023-10-17 02:42:20,917][62408] Updated weights for policy 1, policy_version 60540 (0.0010) -[2023-10-17 02:42:22,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 124452864. Throughput: 0: 1758.7, 1: 1774.3. Samples: 31117458. Policy #0 lag: (min: 18.0, avg: 18.4, max: 30.0) -[2023-10-17 02:42:22,215][61453] Avg episode reward: [(0, '11.120'), (1, '9.000')] -[2023-10-17 02:42:23,272][62373] Updated weights for policy 0, policy_version 61000 (0.0008) -[2023-10-17 02:42:23,650][62373] Updated weights for policy 0, policy_version 61010 (0.0007) -[2023-10-17 02:42:24,019][62373] Updated weights for policy 0, policy_version 61020 (0.0009) -[2023-10-17 02:42:24,808][62408] Updated weights for policy 1, policy_version 60550 (0.0010) -[2023-10-17 02:42:25,180][62408] Updated weights for policy 1, policy_version 60560 (0.0007) -[2023-10-17 02:42:25,551][62408] Updated weights for policy 1, policy_version 60570 (0.0007) -[2023-10-17 02:42:27,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 124518400. Throughput: 0: 1760.4, 1: 1746.0. Samples: 31138082. Policy #0 lag: (min: 18.0, avg: 18.4, max: 30.0) -[2023-10-17 02:42:27,215][61453] Avg episode reward: [(0, '11.090'), (1, '9.330')] -[2023-10-17 02:42:27,881][62373] Updated weights for policy 0, policy_version 61030 (0.0007) -[2023-10-17 02:42:28,249][62373] Updated weights for policy 0, policy_version 61040 (0.0008) -[2023-10-17 02:42:28,624][62373] Updated weights for policy 0, policy_version 61050 (0.0011) -[2023-10-17 02:42:29,348][62408] Updated weights for policy 1, policy_version 60580 (0.0007) -[2023-10-17 02:42:29,714][62408] Updated weights for policy 1, policy_version 60590 (0.0010) -[2023-10-17 02:42:30,083][62408] Updated weights for policy 1, policy_version 60600 (0.0008) -[2023-10-17 02:42:32,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 124583936. Throughput: 0: 1786.7, 1: 1741.8. Samples: 31159734. Policy #0 lag: (min: 18.0, avg: 18.4, max: 30.0) -[2023-10-17 02:42:32,214][61453] Avg episode reward: [(0, '11.920'), (1, '9.890')] -[2023-10-17 02:42:32,449][62373] Updated weights for policy 0, policy_version 61060 (0.0010) -[2023-10-17 02:42:32,813][62373] Updated weights for policy 0, policy_version 61070 (0.0009) -[2023-10-17 02:42:33,187][62373] Updated weights for policy 0, policy_version 61080 (0.0009) -[2023-10-17 02:42:33,988][62408] Updated weights for policy 1, policy_version 60610 (0.0010) -[2023-10-17 02:42:34,347][62408] Updated weights for policy 1, policy_version 60620 (0.0008) -[2023-10-17 02:42:34,715][62408] Updated weights for policy 1, policy_version 60630 (0.0008) -[2023-10-17 02:42:35,085][62408] Updated weights for policy 1, policy_version 60640 (0.0008) -[2023-10-17 02:42:37,027][62373] Updated weights for policy 0, policy_version 61090 (0.0009) -[2023-10-17 02:42:37,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 124649472. Throughput: 0: 1764.6, 1: 1749.4. Samples: 31169718. Policy #0 lag: (min: 18.0, avg: 18.4, max: 30.0) -[2023-10-17 02:42:37,215][61453] Avg episode reward: [(0, '11.560'), (1, '9.550')] -[2023-10-17 02:42:37,403][62373] Updated weights for policy 0, policy_version 61100 (0.0007) -[2023-10-17 02:42:37,766][62373] Updated weights for policy 0, policy_version 61110 (0.0008) -[2023-10-17 02:42:38,139][62373] Updated weights for policy 0, policy_version 61120 (0.0008) -[2023-10-17 02:42:38,874][62408] Updated weights for policy 1, policy_version 60650 (0.0010) -[2023-10-17 02:42:39,239][62408] Updated weights for policy 1, policy_version 60660 (0.0010) -[2023-10-17 02:42:39,616][62408] Updated weights for policy 1, policy_version 60670 (0.0011) -[2023-10-17 02:42:41,941][62373] Updated weights for policy 0, policy_version 61130 (0.0008) -[2023-10-17 02:42:42,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 124715008. Throughput: 0: 1783.8, 1: 1744.7. Samples: 31191544. Policy #0 lag: (min: 18.0, avg: 18.4, max: 30.0) -[2023-10-17 02:42:42,215][61453] Avg episode reward: [(0, '11.030'), (1, '10.090')] -[2023-10-17 02:42:42,310][62373] Updated weights for policy 0, policy_version 61140 (0.0009) -[2023-10-17 02:42:42,684][62373] Updated weights for policy 0, policy_version 61150 (0.0009) -[2023-10-17 02:42:43,361][62408] Updated weights for policy 1, policy_version 60680 (0.0009) -[2023-10-17 02:42:43,729][62408] Updated weights for policy 1, policy_version 60690 (0.0008) -[2023-10-17 02:42:44,107][62408] Updated weights for policy 1, policy_version 60700 (0.0007) -[2023-10-17 02:42:46,526][62373] Updated weights for policy 0, policy_version 61160 (0.0007) -[2023-10-17 02:42:46,892][62373] Updated weights for policy 0, policy_version 61170 (0.0007) -[2023-10-17 02:42:47,214][61453] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 13995.8). Total num frames: 124780544. Throughput: 0: 1770.7, 1: 1766.1. Samples: 31212716. Policy #0 lag: (min: 18.0, avg: 18.4, max: 30.0) -[2023-10-17 02:42:47,215][61453] Avg episode reward: [(0, '10.990'), (1, '9.730')] -[2023-10-17 02:42:47,268][62373] Updated weights for policy 0, policy_version 61180 (0.0007) -[2023-10-17 02:42:47,804][62408] Updated weights for policy 1, policy_version 60710 (0.0008) -[2023-10-17 02:42:48,168][62408] Updated weights for policy 1, policy_version 60720 (0.0007) -[2023-10-17 02:42:48,542][62408] Updated weights for policy 1, policy_version 60730 (0.0009) -[2023-10-17 02:42:51,153][62373] Updated weights for policy 0, policy_version 61190 (0.0007) -[2023-10-17 02:42:51,513][62373] Updated weights for policy 0, policy_version 61200 (0.0007) -[2023-10-17 02:42:51,886][62373] Updated weights for policy 0, policy_version 61210 (0.0008) -[2023-10-17 02:42:52,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 124878848. Throughput: 0: 1765.6, 1: 1749.2. Samples: 31223096. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-17 02:42:52,214][61453] Avg episode reward: [(0, '10.320'), (1, '10.450')] -[2023-10-17 02:42:52,433][62408] Updated weights for policy 1, policy_version 60740 (0.0010) -[2023-10-17 02:42:52,800][62408] Updated weights for policy 1, policy_version 60750 (0.0010) -[2023-10-17 02:42:53,174][62408] Updated weights for policy 1, policy_version 60760 (0.0010) -[2023-10-17 02:42:55,589][62373] Updated weights for policy 0, policy_version 61220 (0.0008) -[2023-10-17 02:42:55,956][62373] Updated weights for policy 0, policy_version 61230 (0.0009) -[2023-10-17 02:42:56,322][62373] Updated weights for policy 0, policy_version 61240 (0.0010) -[2023-10-17 02:42:57,114][62408] Updated weights for policy 1, policy_version 60770 (0.0011) -[2023-10-17 02:42:57,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 124944384. Throughput: 0: 1770.8, 1: 1755.3. Samples: 31244332. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-17 02:42:57,215][61453] Avg episode reward: [(0, '9.570'), (1, '10.460')] -[2023-10-17 02:42:57,530][62408] Updated weights for policy 1, policy_version 60780 (0.0008) -[2023-10-17 02:42:57,898][62408] Updated weights for policy 1, policy_version 60790 (0.0008) -[2023-10-17 02:42:58,272][62408] Updated weights for policy 1, policy_version 60800 (0.0009) -[2023-10-17 02:43:00,119][62373] Updated weights for policy 0, policy_version 61250 (0.0008) -[2023-10-17 02:43:00,489][62373] Updated weights for policy 0, policy_version 61260 (0.0007) -[2023-10-17 02:43:00,853][62373] Updated weights for policy 0, policy_version 61270 (0.0010) -[2023-10-17 02:43:01,223][62373] Updated weights for policy 0, policy_version 61280 (0.0011) -[2023-10-17 02:43:02,168][62408] Updated weights for policy 1, policy_version 60810 (0.0009) -[2023-10-17 02:43:02,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 125009920. Throughput: 0: 1754.5, 1: 1774.5. Samples: 31265188. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-17 02:43:02,214][61453] Avg episode reward: [(0, '9.240'), (1, '9.740')] -[2023-10-17 02:43:02,543][62408] Updated weights for policy 1, policy_version 60820 (0.0009) -[2023-10-17 02:43:02,905][62408] Updated weights for policy 1, policy_version 60830 (0.0009) -[2023-10-17 02:43:05,005][62373] Updated weights for policy 0, policy_version 61290 (0.0009) -[2023-10-17 02:43:05,381][62373] Updated weights for policy 0, policy_version 61300 (0.0011) -[2023-10-17 02:43:05,745][62373] Updated weights for policy 0, policy_version 61310 (0.0007) -[2023-10-17 02:43:06,837][62408] Updated weights for policy 1, policy_version 60840 (0.0010) -[2023-10-17 02:43:07,206][62408] Updated weights for policy 1, policy_version 60850 (0.0011) -[2023-10-17 02:43:07,214][61453] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 125075456. Throughput: 0: 1781.8, 1: 1738.3. Samples: 31275864. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-17 02:43:07,215][61453] Avg episode reward: [(0, '9.020'), (1, '10.110')] -[2023-10-17 02:43:07,577][62408] Updated weights for policy 1, policy_version 60860 (0.0008) -[2023-10-17 02:43:09,595][62373] Updated weights for policy 0, policy_version 61320 (0.0010) -[2023-10-17 02:43:09,961][62373] Updated weights for policy 0, policy_version 61330 (0.0010) -[2023-10-17 02:43:10,330][62373] Updated weights for policy 0, policy_version 61340 (0.0009) -[2023-10-17 02:43:11,402][62408] Updated weights for policy 1, policy_version 60870 (0.0008) -[2023-10-17 02:43:11,774][62408] Updated weights for policy 1, policy_version 60880 (0.0007) -[2023-10-17 02:43:12,147][62408] Updated weights for policy 1, policy_version 60890 (0.0007) -[2023-10-17 02:43:12,214][61453] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 125140992. Throughput: 0: 1757.9, 1: 1773.0. Samples: 31296972. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-17 02:43:12,215][61453] Avg episode reward: [(0, '9.370'), (1, '10.150')] -[2023-10-17 02:43:14,300][62373] Updated weights for policy 0, policy_version 61350 (0.0010) -[2023-10-17 02:43:14,680][62373] Updated weights for policy 0, policy_version 61360 (0.0009) -[2023-10-17 02:43:15,049][62373] Updated weights for policy 0, policy_version 61370 (0.0008) -[2023-10-17 02:43:15,883][62408] Updated weights for policy 1, policy_version 60900 (0.0011) -[2023-10-17 02:43:16,250][62408] Updated weights for policy 1, policy_version 60910 (0.0008) -[2023-10-17 02:43:16,604][62408] Updated weights for policy 1, policy_version 60920 (0.0007) -[2023-10-17 02:43:17,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 125239296. Throughput: 0: 1758.9, 1: 1751.0. Samples: 31317678. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-17 02:43:17,215][61453] Avg episode reward: [(0, '8.960'), (1, '10.170')] -[2023-10-17 02:43:18,748][62373] Updated weights for policy 0, policy_version 61380 (0.0008) -[2023-10-17 02:43:19,117][62373] Updated weights for policy 0, policy_version 61390 (0.0007) -[2023-10-17 02:43:19,483][62373] Updated weights for policy 0, policy_version 61400 (0.0008) -[2023-10-17 02:43:20,383][62408] Updated weights for policy 1, policy_version 60930 (0.0010) -[2023-10-17 02:43:20,751][62408] Updated weights for policy 1, policy_version 60940 (0.0009) -[2023-10-17 02:43:21,126][62408] Updated weights for policy 1, policy_version 60950 (0.0010) -[2023-10-17 02:43:21,492][62408] Updated weights for policy 1, policy_version 60960 (0.0009) -[2023-10-17 02:43:22,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 125304832. Throughput: 0: 1757.9, 1: 1774.1. Samples: 31328660. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-17 02:43:22,215][61453] Avg episode reward: [(0, '9.340'), (1, '10.210')] -[2023-10-17 02:43:23,354][62373] Updated weights for policy 0, policy_version 61410 (0.0008) -[2023-10-17 02:43:23,714][62373] Updated weights for policy 0, policy_version 61420 (0.0011) -[2023-10-17 02:43:24,085][62373] Updated weights for policy 0, policy_version 61430 (0.0010) -[2023-10-17 02:43:24,456][62373] Updated weights for policy 0, policy_version 61440 (0.0010) -[2023-10-17 02:43:25,252][62408] Updated weights for policy 1, policy_version 60970 (0.0009) -[2023-10-17 02:43:25,619][62408] Updated weights for policy 1, policy_version 60980 (0.0010) -[2023-10-17 02:43:25,986][62408] Updated weights for policy 1, policy_version 60990 (0.0010) -[2023-10-17 02:43:27,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 125370368. Throughput: 0: 1757.3, 1: 1757.9. Samples: 31349730. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-10-17 02:43:27,215][61453] Avg episode reward: [(0, '9.430'), (1, '9.190')] -[2023-10-17 02:43:28,237][62373] Updated weights for policy 0, policy_version 61450 (0.0009) -[2023-10-17 02:43:28,600][62373] Updated weights for policy 0, policy_version 61460 (0.0009) -[2023-10-17 02:43:28,967][62373] Updated weights for policy 0, policy_version 61470 (0.0010) -[2023-10-17 02:43:29,829][62408] Updated weights for policy 1, policy_version 61000 (0.0009) -[2023-10-17 02:43:30,202][62408] Updated weights for policy 1, policy_version 61010 (0.0010) -[2023-10-17 02:43:30,577][62408] Updated weights for policy 1, policy_version 61020 (0.0008) -[2023-10-17 02:43:32,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 125435904. Throughput: 0: 1785.6, 1: 1744.9. Samples: 31371592. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:43:32,215][61453] Avg episode reward: [(0, '9.480'), (1, '10.230')] -[2023-10-17 02:43:32,222][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000061472_62947328.pth... -[2023-10-17 02:43:32,222][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000061024_62488576.pth... -[2023-10-17 02:43:32,260][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000059392_60817408.pth -[2023-10-17 02:43:32,261][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000059840_61276160.pth -[2023-10-17 02:43:32,719][62373] Updated weights for policy 0, policy_version 61480 (0.0008) -[2023-10-17 02:43:33,094][62373] Updated weights for policy 0, policy_version 61490 (0.0009) -[2023-10-17 02:43:33,459][62373] Updated weights for policy 0, policy_version 61500 (0.0009) -[2023-10-17 02:43:34,173][62408] Updated weights for policy 1, policy_version 61030 (0.0010) -[2023-10-17 02:43:34,540][62408] Updated weights for policy 1, policy_version 61040 (0.0008) -[2023-10-17 02:43:34,919][62408] Updated weights for policy 1, policy_version 61050 (0.0010) -[2023-10-17 02:43:37,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 125501440. Throughput: 0: 1766.5, 1: 1757.7. Samples: 31381684. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:43:37,214][62373] Updated weights for policy 0, policy_version 61510 (0.0008) -[2023-10-17 02:43:37,215][61453] Avg episode reward: [(0, '9.930'), (1, '10.170')] -[2023-10-17 02:43:37,587][62373] Updated weights for policy 0, policy_version 61520 (0.0007) -[2023-10-17 02:43:37,962][62373] Updated weights for policy 0, policy_version 61530 (0.0009) -[2023-10-17 02:43:38,781][62408] Updated weights for policy 1, policy_version 61060 (0.0009) -[2023-10-17 02:43:39,141][62408] Updated weights for policy 1, policy_version 61070 (0.0011) -[2023-10-17 02:43:39,509][62408] Updated weights for policy 1, policy_version 61080 (0.0010) -[2023-10-17 02:43:41,730][62373] Updated weights for policy 0, policy_version 61540 (0.0011) -[2023-10-17 02:43:42,095][62373] Updated weights for policy 0, policy_version 61550 (0.0010) -[2023-10-17 02:43:42,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 125566976. Throughput: 0: 1780.6, 1: 1752.8. Samples: 31403334. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:43:42,215][61453] Avg episode reward: [(0, '10.090'), (1, '10.330')] -[2023-10-17 02:43:42,469][62373] Updated weights for policy 0, policy_version 61560 (0.0008) -[2023-10-17 02:43:43,339][62408] Updated weights for policy 1, policy_version 61090 (0.0010) -[2023-10-17 02:43:43,746][62408] Updated weights for policy 1, policy_version 61100 (0.0011) -[2023-10-17 02:43:44,113][62408] Updated weights for policy 1, policy_version 61110 (0.0009) -[2023-10-17 02:43:44,486][62408] Updated weights for policy 1, policy_version 61120 (0.0009) -[2023-10-17 02:43:46,185][62373] Updated weights for policy 0, policy_version 61570 (0.0008) -[2023-10-17 02:43:46,554][62373] Updated weights for policy 0, policy_version 61580 (0.0009) -[2023-10-17 02:43:46,922][62373] Updated weights for policy 0, policy_version 61590 (0.0008) -[2023-10-17 02:43:47,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 125632512. Throughput: 0: 1777.4, 1: 1759.3. Samples: 31424340. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:43:47,215][61453] Avg episode reward: [(0, '9.880'), (1, '9.680')] -[2023-10-17 02:43:47,287][62373] Updated weights for policy 0, policy_version 61600 (0.0009) -[2023-10-17 02:43:48,331][62408] Updated weights for policy 1, policy_version 61130 (0.0010) -[2023-10-17 02:43:48,702][62408] Updated weights for policy 1, policy_version 61140 (0.0009) -[2023-10-17 02:43:49,062][62408] Updated weights for policy 1, policy_version 61150 (0.0009) -[2023-10-17 02:43:51,141][62373] Updated weights for policy 0, policy_version 61610 (0.0009) -[2023-10-17 02:43:51,499][62373] Updated weights for policy 0, policy_version 61620 (0.0008) -[2023-10-17 02:43:51,875][62373] Updated weights for policy 0, policy_version 61630 (0.0007) -[2023-10-17 02:43:52,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 125730816. Throughput: 0: 1774.0, 1: 1761.6. Samples: 31434968. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:43:52,215][61453] Avg episode reward: [(0, '10.330'), (1, '10.440')] -[2023-10-17 02:43:53,095][62408] Updated weights for policy 1, policy_version 61160 (0.0009) -[2023-10-17 02:43:53,459][62408] Updated weights for policy 1, policy_version 61170 (0.0009) -[2023-10-17 02:43:53,826][62408] Updated weights for policy 1, policy_version 61180 (0.0008) -[2023-10-17 02:43:55,576][62373] Updated weights for policy 0, policy_version 61640 (0.0007) -[2023-10-17 02:43:55,945][62373] Updated weights for policy 0, policy_version 61650 (0.0009) -[2023-10-17 02:43:56,307][62373] Updated weights for policy 0, policy_version 61660 (0.0011) -[2023-10-17 02:43:57,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 125796352. Throughput: 0: 1786.6, 1: 1756.0. Samples: 31456392. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:43:57,215][61453] Avg episode reward: [(0, '10.160'), (1, '10.040')] -[2023-10-17 02:43:57,639][62408] Updated weights for policy 1, policy_version 61190 (0.0008) -[2023-10-17 02:43:57,998][62408] Updated weights for policy 1, policy_version 61200 (0.0008) -[2023-10-17 02:43:58,366][62408] Updated weights for policy 1, policy_version 61210 (0.0008) -[2023-10-17 02:44:00,156][62373] Updated weights for policy 0, policy_version 61670 (0.0011) -[2023-10-17 02:44:00,540][62373] Updated weights for policy 0, policy_version 61680 (0.0010) -[2023-10-17 02:44:00,914][62373] Updated weights for policy 0, policy_version 61690 (0.0009) -[2023-10-17 02:44:02,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 125861888. Throughput: 0: 1769.8, 1: 1786.3. Samples: 31477704. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:44:02,215][61453] Avg episode reward: [(0, '10.120'), (1, '10.190')] -[2023-10-17 02:44:02,218][62408] Updated weights for policy 1, policy_version 61220 (0.0008) -[2023-10-17 02:44:02,584][62408] Updated weights for policy 1, policy_version 61230 (0.0008) -[2023-10-17 02:44:02,961][62408] Updated weights for policy 1, policy_version 61240 (0.0009) -[2023-10-17 02:44:04,737][62373] Updated weights for policy 0, policy_version 61700 (0.0009) -[2023-10-17 02:44:05,114][62373] Updated weights for policy 0, policy_version 61710 (0.0007) -[2023-10-17 02:44:05,489][62373] Updated weights for policy 0, policy_version 61720 (0.0010) -[2023-10-17 02:44:06,926][62408] Updated weights for policy 1, policy_version 61250 (0.0009) -[2023-10-17 02:44:07,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 125927424. Throughput: 0: 1794.0, 1: 1755.3. Samples: 31488376. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:44:07,215][61453] Avg episode reward: [(0, '10.390'), (1, '10.290')] -[2023-10-17 02:44:07,303][62408] Updated weights for policy 1, policy_version 61260 (0.0009) -[2023-10-17 02:44:07,678][62408] Updated weights for policy 1, policy_version 61270 (0.0008) -[2023-10-17 02:44:08,037][62408] Updated weights for policy 1, policy_version 61280 (0.0009) -[2023-10-17 02:44:09,376][62373] Updated weights for policy 0, policy_version 61730 (0.0009) -[2023-10-17 02:44:09,742][62373] Updated weights for policy 0, policy_version 61740 (0.0007) -[2023-10-17 02:44:10,112][62373] Updated weights for policy 0, policy_version 61750 (0.0008) -[2023-10-17 02:44:10,480][62373] Updated weights for policy 0, policy_version 61760 (0.0007) -[2023-10-17 02:44:11,889][62408] Updated weights for policy 1, policy_version 61290 (0.0009) -[2023-10-17 02:44:12,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 125992960. Throughput: 0: 1770.3, 1: 1776.6. Samples: 31509340. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:44:12,215][61453] Avg episode reward: [(0, '10.350'), (1, '10.300')] -[2023-10-17 02:44:12,261][62408] Updated weights for policy 1, policy_version 61300 (0.0008) -[2023-10-17 02:44:12,635][62408] Updated weights for policy 1, policy_version 61310 (0.0009) -[2023-10-17 02:44:14,221][62373] Updated weights for policy 0, policy_version 61770 (0.0008) -[2023-10-17 02:44:14,580][62373] Updated weights for policy 0, policy_version 61780 (0.0008) -[2023-10-17 02:44:14,955][62373] Updated weights for policy 0, policy_version 61790 (0.0009) -[2023-10-17 02:44:16,394][62408] Updated weights for policy 1, policy_version 61320 (0.0009) -[2023-10-17 02:44:16,761][62408] Updated weights for policy 1, policy_version 61330 (0.0007) -[2023-10-17 02:44:17,135][62408] Updated weights for policy 1, policy_version 61340 (0.0009) -[2023-10-17 02:44:17,214][61453] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 126058496. Throughput: 0: 1771.3, 1: 1767.8. Samples: 31530850. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:44:17,215][61453] Avg episode reward: [(0, '9.770'), (1, '10.020')] -[2023-10-17 02:44:18,745][62373] Updated weights for policy 0, policy_version 61800 (0.0007) -[2023-10-17 02:44:19,116][62373] Updated weights for policy 0, policy_version 61810 (0.0009) -[2023-10-17 02:44:19,488][62373] Updated weights for policy 0, policy_version 61820 (0.0009) -[2023-10-17 02:44:20,924][62408] Updated weights for policy 1, policy_version 61350 (0.0009) -[2023-10-17 02:44:21,285][62408] Updated weights for policy 1, policy_version 61360 (0.0008) -[2023-10-17 02:44:21,644][62408] Updated weights for policy 1, policy_version 61370 (0.0008) -[2023-10-17 02:44:22,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 126156800. Throughput: 0: 1774.8, 1: 1776.3. Samples: 31541484. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:44:22,215][61453] Avg episode reward: [(0, '10.460'), (1, '10.750')] -[2023-10-17 02:44:23,155][62373] Updated weights for policy 0, policy_version 61830 (0.0008) -[2023-10-17 02:44:23,525][62373] Updated weights for policy 0, policy_version 61840 (0.0008) -[2023-10-17 02:44:23,892][62373] Updated weights for policy 0, policy_version 61850 (0.0008) -[2023-10-17 02:44:25,447][62408] Updated weights for policy 1, policy_version 61380 (0.0009) -[2023-10-17 02:44:25,817][62408] Updated weights for policy 1, policy_version 61390 (0.0009) -[2023-10-17 02:44:26,187][62408] Updated weights for policy 1, policy_version 61400 (0.0008) -[2023-10-17 02:44:27,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 126222336. Throughput: 0: 1773.9, 1: 1771.6. Samples: 31562884. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:44:27,215][61453] Avg episode reward: [(0, '9.940'), (1, '10.640')] -[2023-10-17 02:44:27,719][62373] Updated weights for policy 0, policy_version 61860 (0.0010) -[2023-10-17 02:44:28,083][62373] Updated weights for policy 0, policy_version 61870 (0.0009) -[2023-10-17 02:44:28,456][62373] Updated weights for policy 0, policy_version 61880 (0.0008) -[2023-10-17 02:44:30,034][62408] Updated weights for policy 1, policy_version 61410 (0.0008) -[2023-10-17 02:44:30,451][62408] Updated weights for policy 1, policy_version 61420 (0.0007) -[2023-10-17 02:44:30,819][62408] Updated weights for policy 1, policy_version 61430 (0.0007) -[2023-10-17 02:44:31,188][62408] Updated weights for policy 1, policy_version 61440 (0.0008) -[2023-10-17 02:44:32,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 126287872. Throughput: 0: 1792.6, 1: 1753.4. Samples: 31583908. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:44:32,215][61453] Avg episode reward: [(0, '10.060'), (1, '11.050')] -[2023-10-17 02:44:32,344][62373] Updated weights for policy 0, policy_version 61890 (0.0008) -[2023-10-17 02:44:32,717][62373] Updated weights for policy 0, policy_version 61900 (0.0007) -[2023-10-17 02:44:33,085][62373] Updated weights for policy 0, policy_version 61910 (0.0007) -[2023-10-17 02:44:33,454][62373] Updated weights for policy 0, policy_version 61920 (0.0010) -[2023-10-17 02:44:34,906][62408] Updated weights for policy 1, policy_version 61450 (0.0007) -[2023-10-17 02:44:35,271][62408] Updated weights for policy 1, policy_version 61460 (0.0009) -[2023-10-17 02:44:35,645][62408] Updated weights for policy 1, policy_version 61470 (0.0010) -[2023-10-17 02:44:37,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 126353408. Throughput: 0: 1770.8, 1: 1781.8. Samples: 31594838. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:44:37,215][61453] Avg episode reward: [(0, '9.410'), (1, '11.490')] -[2023-10-17 02:44:37,216][62252] Saving new best policy, reward=11.490! -[2023-10-17 02:44:37,333][62373] Updated weights for policy 0, policy_version 61930 (0.0008) -[2023-10-17 02:44:37,714][62373] Updated weights for policy 0, policy_version 61940 (0.0007) -[2023-10-17 02:44:38,080][62373] Updated weights for policy 0, policy_version 61950 (0.0008) -[2023-10-17 02:44:39,546][62408] Updated weights for policy 1, policy_version 61480 (0.0009) -[2023-10-17 02:44:39,919][62408] Updated weights for policy 1, policy_version 61490 (0.0012) -[2023-10-17 02:44:40,288][62408] Updated weights for policy 1, policy_version 61500 (0.0009) -[2023-10-17 02:44:41,784][62373] Updated weights for policy 0, policy_version 61960 (0.0008) -[2023-10-17 02:44:42,158][62373] Updated weights for policy 0, policy_version 61970 (0.0009) -[2023-10-17 02:44:42,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 126418944. Throughput: 0: 1787.1, 1: 1759.1. Samples: 31615972. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:44:42,214][61453] Avg episode reward: [(0, '9.140'), (1, '11.320')] -[2023-10-17 02:44:42,542][62373] Updated weights for policy 0, policy_version 61980 (0.0010) -[2023-10-17 02:44:44,115][62408] Updated weights for policy 1, policy_version 61510 (0.0011) -[2023-10-17 02:44:44,488][62408] Updated weights for policy 1, policy_version 61520 (0.0011) -[2023-10-17 02:44:44,865][62408] Updated weights for policy 1, policy_version 61530 (0.0009) -[2023-10-17 02:44:46,212][62373] Updated weights for policy 0, policy_version 61990 (0.0010) -[2023-10-17 02:44:46,593][62373] Updated weights for policy 0, policy_version 62000 (0.0007) -[2023-10-17 02:44:46,960][62373] Updated weights for policy 0, policy_version 62010 (0.0009) -[2023-10-17 02:44:47,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14745.5, 300 sec: 14106.9). Total num frames: 126517248. Throughput: 0: 1782.6, 1: 1762.3. Samples: 31637222. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:44:47,215][61453] Avg episode reward: [(0, '9.180'), (1, '11.510')] -[2023-10-17 02:44:47,227][62252] Saving new best policy, reward=11.510! -[2023-10-17 02:44:48,706][62408] Updated weights for policy 1, policy_version 61540 (0.0008) -[2023-10-17 02:44:49,071][62408] Updated weights for policy 1, policy_version 61550 (0.0008) -[2023-10-17 02:44:49,434][62408] Updated weights for policy 1, policy_version 61560 (0.0009) -[2023-10-17 02:44:50,862][62373] Updated weights for policy 0, policy_version 62020 (0.0008) -[2023-10-17 02:44:51,228][62373] Updated weights for policy 0, policy_version 62030 (0.0011) -[2023-10-17 02:44:51,594][62373] Updated weights for policy 0, policy_version 62040 (0.0008) -[2023-10-17 02:44:52,214][61453] Fps is (10 sec: 16383.6, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 126582784. Throughput: 0: 1780.5, 1: 1758.2. Samples: 31647620. Policy #0 lag: (min: 26.0, avg: 27.9, max: 56.0) -[2023-10-17 02:44:52,215][61453] Avg episode reward: [(0, '8.780'), (1, '11.470')] -[2023-10-17 02:44:53,294][62408] Updated weights for policy 1, policy_version 61570 (0.0010) -[2023-10-17 02:44:53,661][62408] Updated weights for policy 1, policy_version 61580 (0.0009) -[2023-10-17 02:44:54,028][62408] Updated weights for policy 1, policy_version 61590 (0.0008) -[2023-10-17 02:44:54,395][62408] Updated weights for policy 1, policy_version 61600 (0.0009) -[2023-10-17 02:44:55,446][62373] Updated weights for policy 0, policy_version 62050 (0.0010) -[2023-10-17 02:44:55,821][62373] Updated weights for policy 0, policy_version 62060 (0.0009) -[2023-10-17 02:44:56,181][62373] Updated weights for policy 0, policy_version 62070 (0.0011) -[2023-10-17 02:44:56,556][62373] Updated weights for policy 0, policy_version 62080 (0.0008) -[2023-10-17 02:44:57,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 126648320. Throughput: 0: 1783.6, 1: 1760.9. Samples: 31668842. Policy #0 lag: (min: 26.0, avg: 27.9, max: 56.0) -[2023-10-17 02:44:57,215][61453] Avg episode reward: [(0, '8.730'), (1, '10.970')] -[2023-10-17 02:44:58,085][62408] Updated weights for policy 1, policy_version 61610 (0.0007) -[2023-10-17 02:44:58,455][62408] Updated weights for policy 1, policy_version 61620 (0.0008) -[2023-10-17 02:44:58,818][62408] Updated weights for policy 1, policy_version 61630 (0.0008) -[2023-10-17 02:45:00,296][62373] Updated weights for policy 0, policy_version 62090 (0.0009) -[2023-10-17 02:45:00,656][62373] Updated weights for policy 0, policy_version 62100 (0.0011) -[2023-10-17 02:45:01,036][62373] Updated weights for policy 0, policy_version 62110 (0.0009) -[2023-10-17 02:45:02,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 126713856. Throughput: 0: 1759.1, 1: 1781.2. Samples: 31690164. Policy #0 lag: (min: 26.0, avg: 27.9, max: 56.0) -[2023-10-17 02:45:02,215][61453] Avg episode reward: [(0, '9.520'), (1, '10.540')] -[2023-10-17 02:45:02,689][62408] Updated weights for policy 1, policy_version 61640 (0.0007) -[2023-10-17 02:45:03,056][62408] Updated weights for policy 1, policy_version 61650 (0.0008) -[2023-10-17 02:45:03,424][62408] Updated weights for policy 1, policy_version 61660 (0.0010) -[2023-10-17 02:45:04,826][62373] Updated weights for policy 0, policy_version 62120 (0.0009) -[2023-10-17 02:45:05,183][62373] Updated weights for policy 0, policy_version 62130 (0.0008) -[2023-10-17 02:45:05,555][62373] Updated weights for policy 0, policy_version 62140 (0.0009) -[2023-10-17 02:45:07,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 126779392. Throughput: 0: 1779.6, 1: 1757.7. Samples: 31700662. Policy #0 lag: (min: 26.0, avg: 27.9, max: 56.0) -[2023-10-17 02:45:07,215][61453] Avg episode reward: [(0, '9.380'), (1, '9.640')] -[2023-10-17 02:45:07,222][62408] Updated weights for policy 1, policy_version 61670 (0.0008) -[2023-10-17 02:45:07,588][62408] Updated weights for policy 1, policy_version 61680 (0.0008) -[2023-10-17 02:45:07,963][62408] Updated weights for policy 1, policy_version 61690 (0.0008) -[2023-10-17 02:45:09,388][62373] Updated weights for policy 0, policy_version 62150 (0.0009) -[2023-10-17 02:45:09,756][62373] Updated weights for policy 0, policy_version 62160 (0.0008) -[2023-10-17 02:45:10,128][62373] Updated weights for policy 0, policy_version 62170 (0.0007) -[2023-10-17 02:45:11,811][62408] Updated weights for policy 1, policy_version 61700 (0.0009) -[2023-10-17 02:45:12,178][62408] Updated weights for policy 1, policy_version 61710 (0.0012) -[2023-10-17 02:45:12,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 126844928. Throughput: 0: 1761.8, 1: 1773.4. Samples: 31721968. Policy #0 lag: (min: 26.0, avg: 27.9, max: 56.0) -[2023-10-17 02:45:12,215][61453] Avg episode reward: [(0, '9.850'), (1, '9.900')] -[2023-10-17 02:45:12,547][62408] Updated weights for policy 1, policy_version 61720 (0.0011) -[2023-10-17 02:45:13,893][62373] Updated weights for policy 0, policy_version 62180 (0.0007) -[2023-10-17 02:45:14,258][62373] Updated weights for policy 0, policy_version 62190 (0.0007) -[2023-10-17 02:45:14,626][62373] Updated weights for policy 0, policy_version 62200 (0.0007) -[2023-10-17 02:45:16,269][62408] Updated weights for policy 1, policy_version 61730 (0.0009) -[2023-10-17 02:45:16,666][62408] Updated weights for policy 1, policy_version 61740 (0.0007) -[2023-10-17 02:45:17,037][62408] Updated weights for policy 1, policy_version 61750 (0.0007) -[2023-10-17 02:45:17,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 126910464. Throughput: 0: 1768.5, 1: 1778.4. Samples: 31743520. Policy #0 lag: (min: 26.0, avg: 27.9, max: 56.0) -[2023-10-17 02:45:17,215][61453] Avg episode reward: [(0, '9.910'), (1, '9.220')] -[2023-10-17 02:45:17,401][62408] Updated weights for policy 1, policy_version 61760 (0.0008) -[2023-10-17 02:45:18,456][62373] Updated weights for policy 0, policy_version 62210 (0.0008) -[2023-10-17 02:45:18,813][62373] Updated weights for policy 0, policy_version 62220 (0.0011) -[2023-10-17 02:45:19,180][62373] Updated weights for policy 0, policy_version 62230 (0.0008) -[2023-10-17 02:45:19,552][62373] Updated weights for policy 0, policy_version 62240 (0.0008) -[2023-10-17 02:45:21,118][62408] Updated weights for policy 1, policy_version 61770 (0.0009) -[2023-10-17 02:45:21,486][62408] Updated weights for policy 1, policy_version 61780 (0.0008) -[2023-10-17 02:45:21,849][62408] Updated weights for policy 1, policy_version 61790 (0.0010) -[2023-10-17 02:45:22,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 127008768. Throughput: 0: 1766.8, 1: 1772.3. Samples: 31754094. Policy #0 lag: (min: 26.0, avg: 27.9, max: 56.0) -[2023-10-17 02:45:22,214][61453] Avg episode reward: [(0, '10.340'), (1, '9.730')] -[2023-10-17 02:45:23,407][62373] Updated weights for policy 0, policy_version 62250 (0.0009) -[2023-10-17 02:45:23,780][62373] Updated weights for policy 0, policy_version 62260 (0.0009) -[2023-10-17 02:45:24,155][62373] Updated weights for policy 0, policy_version 62270 (0.0009) -[2023-10-17 02:45:25,684][62408] Updated weights for policy 1, policy_version 61800 (0.0010) -[2023-10-17 02:45:26,052][62408] Updated weights for policy 1, policy_version 61810 (0.0011) -[2023-10-17 02:45:26,421][62408] Updated weights for policy 1, policy_version 61820 (0.0011) -[2023-10-17 02:45:27,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 127074304. Throughput: 0: 1760.2, 1: 1785.6. Samples: 31775534. Policy #0 lag: (min: 26.0, avg: 27.9, max: 56.0) -[2023-10-17 02:45:27,215][61453] Avg episode reward: [(0, '10.250'), (1, '9.430')] -[2023-10-17 02:45:27,955][62373] Updated weights for policy 0, policy_version 62280 (0.0007) -[2023-10-17 02:45:28,328][62373] Updated weights for policy 0, policy_version 62290 (0.0009) -[2023-10-17 02:45:28,699][62373] Updated weights for policy 0, policy_version 62300 (0.0008) -[2023-10-17 02:45:30,311][62408] Updated weights for policy 1, policy_version 61830 (0.0009) -[2023-10-17 02:45:30,672][62408] Updated weights for policy 1, policy_version 61840 (0.0009) -[2023-10-17 02:45:31,043][62408] Updated weights for policy 1, policy_version 61850 (0.0010) -[2023-10-17 02:45:32,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 127139840. Throughput: 0: 1786.8, 1: 1758.3. Samples: 31796748. Policy #0 lag: (min: 26.0, avg: 27.9, max: 56.0) -[2023-10-17 02:45:32,215][61453] Avg episode reward: [(0, '10.100'), (1, '9.940')] -[2023-10-17 02:45:32,227][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000061856_63340544.pth... -[2023-10-17 02:45:32,227][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000062304_63799296.pth... -[2023-10-17 02:45:32,261][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000060672_62128128.pth -[2023-10-17 02:45:32,265][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000060192_61636608.pth -[2023-10-17 02:45:32,640][62373] Updated weights for policy 0, policy_version 62310 (0.0008) -[2023-10-17 02:45:33,015][62373] Updated weights for policy 0, policy_version 62320 (0.0010) -[2023-10-17 02:45:33,380][62373] Updated weights for policy 0, policy_version 62330 (0.0011) -[2023-10-17 02:45:34,819][62408] Updated weights for policy 1, policy_version 61860 (0.0010) -[2023-10-17 02:45:35,195][62408] Updated weights for policy 1, policy_version 61870 (0.0009) -[2023-10-17 02:45:35,561][62408] Updated weights for policy 1, policy_version 61880 (0.0010) -[2023-10-17 02:45:37,134][62373] Updated weights for policy 0, policy_version 62340 (0.0011) -[2023-10-17 02:45:37,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 127205376. Throughput: 0: 1760.8, 1: 1793.8. Samples: 31807574. Policy #0 lag: (min: 31.0, avg: 34.6, max: 63.0) -[2023-10-17 02:45:37,215][61453] Avg episode reward: [(0, '9.520'), (1, '10.940')] -[2023-10-17 02:45:37,501][62373] Updated weights for policy 0, policy_version 62350 (0.0011) -[2023-10-17 02:45:37,869][62373] Updated weights for policy 0, policy_version 62360 (0.0009) -[2023-10-17 02:45:39,388][62408] Updated weights for policy 1, policy_version 61890 (0.0009) -[2023-10-17 02:45:39,751][62408] Updated weights for policy 1, policy_version 61900 (0.0010) -[2023-10-17 02:45:40,118][62408] Updated weights for policy 1, policy_version 61910 (0.0009) -[2023-10-17 02:45:40,484][62408] Updated weights for policy 1, policy_version 61920 (0.0007) -[2023-10-17 02:45:41,815][62373] Updated weights for policy 0, policy_version 62370 (0.0011) -[2023-10-17 02:45:42,180][62373] Updated weights for policy 0, policy_version 62380 (0.0009) -[2023-10-17 02:45:42,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 127270912. Throughput: 0: 1776.2, 1: 1762.8. Samples: 31828098. Policy #0 lag: (min: 31.0, avg: 34.6, max: 63.0) -[2023-10-17 02:45:42,215][61453] Avg episode reward: [(0, '9.320'), (1, '10.940')] -[2023-10-17 02:45:42,549][62373] Updated weights for policy 0, policy_version 62390 (0.0010) -[2023-10-17 02:45:42,925][62373] Updated weights for policy 0, policy_version 62400 (0.0007) -[2023-10-17 02:45:44,195][62408] Updated weights for policy 1, policy_version 61930 (0.0007) -[2023-10-17 02:45:44,558][62408] Updated weights for policy 1, policy_version 61940 (0.0008) -[2023-10-17 02:45:44,915][62408] Updated weights for policy 1, policy_version 61950 (0.0008) -[2023-10-17 02:45:46,703][62373] Updated weights for policy 0, policy_version 62410 (0.0007) -[2023-10-17 02:45:47,076][62373] Updated weights for policy 0, policy_version 62420 (0.0008) -[2023-10-17 02:45:47,214][61453] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 127336448. Throughput: 0: 1779.4, 1: 1761.6. Samples: 31849506. Policy #0 lag: (min: 31.0, avg: 34.6, max: 63.0) -[2023-10-17 02:45:47,215][61453] Avg episode reward: [(0, '9.820'), (1, '10.990')] -[2023-10-17 02:45:47,449][62373] Updated weights for policy 0, policy_version 62430 (0.0007) -[2023-10-17 02:45:48,866][62408] Updated weights for policy 1, policy_version 61960 (0.0011) -[2023-10-17 02:45:49,230][62408] Updated weights for policy 1, policy_version 61970 (0.0009) -[2023-10-17 02:45:49,601][62408] Updated weights for policy 1, policy_version 61980 (0.0009) -[2023-10-17 02:45:51,320][62373] Updated weights for policy 0, policy_version 62440 (0.0008) -[2023-10-17 02:45:51,701][62373] Updated weights for policy 0, policy_version 62450 (0.0007) -[2023-10-17 02:45:52,062][62373] Updated weights for policy 0, policy_version 62460 (0.0007) -[2023-10-17 02:45:52,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 127434752. Throughput: 0: 1771.8, 1: 1761.1. Samples: 31859644. Policy #0 lag: (min: 31.0, avg: 34.6, max: 63.0) -[2023-10-17 02:45:52,215][61453] Avg episode reward: [(0, '9.640'), (1, '11.410')] -[2023-10-17 02:45:53,393][62408] Updated weights for policy 1, policy_version 61990 (0.0009) -[2023-10-17 02:45:53,755][62408] Updated weights for policy 1, policy_version 62000 (0.0008) -[2023-10-17 02:45:54,115][62408] Updated weights for policy 1, policy_version 62010 (0.0009) -[2023-10-17 02:45:55,923][62373] Updated weights for policy 0, policy_version 62470 (0.0008) -[2023-10-17 02:45:56,299][62373] Updated weights for policy 0, policy_version 62480 (0.0009) -[2023-10-17 02:45:56,670][62373] Updated weights for policy 0, policy_version 62490 (0.0007) -[2023-10-17 02:45:57,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 127500288. Throughput: 0: 1785.2, 1: 1761.3. Samples: 31881560. Policy #0 lag: (min: 31.0, avg: 34.6, max: 63.0) -[2023-10-17 02:45:57,215][61453] Avg episode reward: [(0, '8.700'), (1, '10.540')] -[2023-10-17 02:45:58,020][62408] Updated weights for policy 1, policy_version 62020 (0.0009) -[2023-10-17 02:45:58,387][62408] Updated weights for policy 1, policy_version 62030 (0.0010) -[2023-10-17 02:45:58,755][62408] Updated weights for policy 1, policy_version 62040 (0.0010) -[2023-10-17 02:46:00,451][62373] Updated weights for policy 0, policy_version 62500 (0.0010) -[2023-10-17 02:46:00,825][62373] Updated weights for policy 0, policy_version 62510 (0.0008) -[2023-10-17 02:46:01,190][62373] Updated weights for policy 0, policy_version 62520 (0.0008) -[2023-10-17 02:46:02,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 127565824. Throughput: 0: 1762.2, 1: 1778.1. Samples: 31902832. Policy #0 lag: (min: 31.0, avg: 34.6, max: 63.0) -[2023-10-17 02:46:02,215][61453] Avg episode reward: [(0, '8.710'), (1, '10.860')] -[2023-10-17 02:46:02,555][62408] Updated weights for policy 1, policy_version 62050 (0.0009) -[2023-10-17 02:46:02,964][62408] Updated weights for policy 1, policy_version 62060 (0.0008) -[2023-10-17 02:46:03,328][62408] Updated weights for policy 1, policy_version 62070 (0.0009) -[2023-10-17 02:46:03,686][62408] Updated weights for policy 1, policy_version 62080 (0.0008) -[2023-10-17 02:46:04,887][62373] Updated weights for policy 0, policy_version 62530 (0.0008) -[2023-10-17 02:46:05,256][62373] Updated weights for policy 0, policy_version 62540 (0.0011) -[2023-10-17 02:46:05,632][62373] Updated weights for policy 0, policy_version 62550 (0.0008) -[2023-10-17 02:46:05,999][62373] Updated weights for policy 0, policy_version 62560 (0.0008) -[2023-10-17 02:46:07,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 127631360. Throughput: 0: 1793.0, 1: 1754.6. Samples: 31913736. Policy #0 lag: (min: 31.0, avg: 34.6, max: 63.0) -[2023-10-17 02:46:07,214][61453] Avg episode reward: [(0, '8.390'), (1, '10.800')] -[2023-10-17 02:46:07,424][62408] Updated weights for policy 1, policy_version 62090 (0.0008) -[2023-10-17 02:46:07,798][62408] Updated weights for policy 1, policy_version 62100 (0.0007) -[2023-10-17 02:46:08,167][62408] Updated weights for policy 1, policy_version 62110 (0.0008) -[2023-10-17 02:46:09,688][62373] Updated weights for policy 0, policy_version 62570 (0.0008) -[2023-10-17 02:46:10,062][62373] Updated weights for policy 0, policy_version 62580 (0.0011) -[2023-10-17 02:46:10,437][62373] Updated weights for policy 0, policy_version 62590 (0.0011) -[2023-10-17 02:46:12,058][62408] Updated weights for policy 1, policy_version 62120 (0.0010) -[2023-10-17 02:46:12,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 127696896. Throughput: 0: 1771.4, 1: 1767.3. Samples: 31934776. Policy #0 lag: (min: 31.0, avg: 34.6, max: 63.0) -[2023-10-17 02:46:12,215][61453] Avg episode reward: [(0, '9.100'), (1, '9.680')] -[2023-10-17 02:46:12,430][62408] Updated weights for policy 1, policy_version 62130 (0.0009) -[2023-10-17 02:46:12,807][62408] Updated weights for policy 1, policy_version 62140 (0.0009) -[2023-10-17 02:46:14,056][62373] Updated weights for policy 0, policy_version 62600 (0.0009) -[2023-10-17 02:46:14,430][62373] Updated weights for policy 0, policy_version 62610 (0.0007) -[2023-10-17 02:46:14,800][62373] Updated weights for policy 0, policy_version 62620 (0.0007) -[2023-10-17 02:46:16,629][62408] Updated weights for policy 1, policy_version 62150 (0.0008) -[2023-10-17 02:46:16,992][62408] Updated weights for policy 1, policy_version 62160 (0.0007) -[2023-10-17 02:46:17,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 127762432. Throughput: 0: 1770.0, 1: 1779.1. Samples: 31956454. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-17 02:46:17,214][61453] Avg episode reward: [(0, '8.530'), (1, '10.030')] -[2023-10-17 02:46:17,360][62408] Updated weights for policy 1, policy_version 62170 (0.0007) -[2023-10-17 02:46:18,704][62373] Updated weights for policy 0, policy_version 62630 (0.0007) -[2023-10-17 02:46:19,087][62373] Updated weights for policy 0, policy_version 62640 (0.0008) -[2023-10-17 02:46:19,461][62373] Updated weights for policy 0, policy_version 62650 (0.0008) -[2023-10-17 02:46:20,923][62408] Updated weights for policy 1, policy_version 62180 (0.0008) -[2023-10-17 02:46:21,288][62408] Updated weights for policy 1, policy_version 62190 (0.0007) -[2023-10-17 02:46:21,655][62408] Updated weights for policy 1, policy_version 62200 (0.0011) -[2023-10-17 02:46:22,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 127860736. Throughput: 0: 1771.9, 1: 1764.5. Samples: 31966712. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-17 02:46:22,215][61453] Avg episode reward: [(0, '8.400'), (1, '9.870')] -[2023-10-17 02:46:23,154][62373] Updated weights for policy 0, policy_version 62660 (0.0008) -[2023-10-17 02:46:23,523][62373] Updated weights for policy 0, policy_version 62670 (0.0009) -[2023-10-17 02:46:23,893][62373] Updated weights for policy 0, policy_version 62680 (0.0007) -[2023-10-17 02:46:25,659][62408] Updated weights for policy 1, policy_version 62210 (0.0010) -[2023-10-17 02:46:26,026][62408] Updated weights for policy 1, policy_version 62220 (0.0008) -[2023-10-17 02:46:26,389][62408] Updated weights for policy 1, policy_version 62230 (0.0008) -[2023-10-17 02:46:26,761][62408] Updated weights for policy 1, policy_version 62240 (0.0007) -[2023-10-17 02:46:27,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 127926272. Throughput: 0: 1776.7, 1: 1785.9. Samples: 31988416. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-17 02:46:27,214][61453] Avg episode reward: [(0, '8.510'), (1, '9.720')] -[2023-10-17 02:46:27,799][62373] Updated weights for policy 0, policy_version 62690 (0.0008) -[2023-10-17 02:46:28,167][62373] Updated weights for policy 0, policy_version 62700 (0.0008) -[2023-10-17 02:46:28,537][62373] Updated weights for policy 0, policy_version 62710 (0.0007) -[2023-10-17 02:46:28,905][62373] Updated weights for policy 0, policy_version 62720 (0.0007) -[2023-10-17 02:46:30,403][62408] Updated weights for policy 1, policy_version 62250 (0.0011) -[2023-10-17 02:46:30,774][62408] Updated weights for policy 1, policy_version 62260 (0.0011) -[2023-10-17 02:46:31,139][62408] Updated weights for policy 1, policy_version 62270 (0.0011) -[2023-10-17 02:46:32,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 127991808. Throughput: 0: 1800.3, 1: 1764.8. Samples: 32009932. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-17 02:46:32,214][61453] Avg episode reward: [(0, '9.200'), (1, '10.120')] -[2023-10-17 02:46:32,545][62373] Updated weights for policy 0, policy_version 62730 (0.0010) -[2023-10-17 02:46:32,918][62373] Updated weights for policy 0, policy_version 62740 (0.0007) -[2023-10-17 02:46:33,281][62373] Updated weights for policy 0, policy_version 62750 (0.0007) -[2023-10-17 02:46:34,986][62408] Updated weights for policy 1, policy_version 62280 (0.0010) -[2023-10-17 02:46:35,358][62408] Updated weights for policy 1, policy_version 62290 (0.0008) -[2023-10-17 02:46:35,728][62408] Updated weights for policy 1, policy_version 62300 (0.0007) -[2023-10-17 02:46:36,978][62373] Updated weights for policy 0, policy_version 62760 (0.0010) -[2023-10-17 02:46:37,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 128057344. Throughput: 0: 1788.3, 1: 1797.4. Samples: 32021004. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-17 02:46:37,215][61453] Avg episode reward: [(0, '9.250'), (1, '10.090')] -[2023-10-17 02:46:37,337][62373] Updated weights for policy 0, policy_version 62770 (0.0010) -[2023-10-17 02:46:37,712][62373] Updated weights for policy 0, policy_version 62780 (0.0011) -[2023-10-17 02:46:39,460][62408] Updated weights for policy 1, policy_version 62310 (0.0008) -[2023-10-17 02:46:39,831][62408] Updated weights for policy 1, policy_version 62320 (0.0007) -[2023-10-17 02:46:40,191][62408] Updated weights for policy 1, policy_version 62330 (0.0007) -[2023-10-17 02:46:41,529][62373] Updated weights for policy 0, policy_version 62790 (0.0010) -[2023-10-17 02:46:41,903][62373] Updated weights for policy 0, policy_version 62800 (0.0010) -[2023-10-17 02:46:42,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 128122880. Throughput: 0: 1793.3, 1: 1769.2. Samples: 32041872. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-17 02:46:42,215][61453] Avg episode reward: [(0, '9.270'), (1, '10.470')] -[2023-10-17 02:46:42,269][62373] Updated weights for policy 0, policy_version 62810 (0.0007) -[2023-10-17 02:46:43,990][62408] Updated weights for policy 1, policy_version 62340 (0.0008) -[2023-10-17 02:46:44,357][62408] Updated weights for policy 1, policy_version 62350 (0.0010) -[2023-10-17 02:46:44,726][62408] Updated weights for policy 1, policy_version 62360 (0.0009) -[2023-10-17 02:46:46,063][62373] Updated weights for policy 0, policy_version 62820 (0.0007) -[2023-10-17 02:46:46,439][62373] Updated weights for policy 0, policy_version 62830 (0.0008) -[2023-10-17 02:46:46,809][62373] Updated weights for policy 0, policy_version 62840 (0.0008) -[2023-10-17 02:46:47,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14218.0). Total num frames: 128221184. Throughput: 0: 1786.4, 1: 1770.0. Samples: 32062872. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-17 02:46:47,215][61453] Avg episode reward: [(0, '8.970'), (1, '10.290')] -[2023-10-17 02:46:48,550][62408] Updated weights for policy 1, policy_version 62370 (0.0008) -[2023-10-17 02:46:48,964][62408] Updated weights for policy 1, policy_version 62380 (0.0009) -[2023-10-17 02:46:49,330][62408] Updated weights for policy 1, policy_version 62390 (0.0009) -[2023-10-17 02:46:49,691][62408] Updated weights for policy 1, policy_version 62400 (0.0009) -[2023-10-17 02:46:50,770][62373] Updated weights for policy 0, policy_version 62850 (0.0008) -[2023-10-17 02:46:51,139][62373] Updated weights for policy 0, policy_version 62860 (0.0008) -[2023-10-17 02:46:51,505][62373] Updated weights for policy 0, policy_version 62870 (0.0009) -[2023-10-17 02:46:51,881][62373] Updated weights for policy 0, policy_version 62880 (0.0007) -[2023-10-17 02:46:52,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 128286720. Throughput: 0: 1781.3, 1: 1773.3. Samples: 32073694. Policy #0 lag: (min: 30.0, avg: 30.0, max: 30.0) -[2023-10-17 02:46:52,215][61453] Avg episode reward: [(0, '9.420'), (1, '10.510')] -[2023-10-17 02:46:53,433][62408] Updated weights for policy 1, policy_version 62410 (0.0008) -[2023-10-17 02:46:53,805][62408] Updated weights for policy 1, policy_version 62420 (0.0008) -[2023-10-17 02:46:54,172][62408] Updated weights for policy 1, policy_version 62430 (0.0007) -[2023-10-17 02:46:55,722][62373] Updated weights for policy 0, policy_version 62890 (0.0008) -[2023-10-17 02:46:56,101][62373] Updated weights for policy 0, policy_version 62900 (0.0008) -[2023-10-17 02:46:56,469][62373] Updated weights for policy 0, policy_version 62910 (0.0007) -[2023-10-17 02:46:57,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 128352256. Throughput: 0: 1790.2, 1: 1777.1. Samples: 32095306. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-10-17 02:46:57,215][61453] Avg episode reward: [(0, '9.580'), (1, '10.770')] -[2023-10-17 02:46:58,038][62408] Updated weights for policy 1, policy_version 62440 (0.0008) -[2023-10-17 02:46:58,405][62408] Updated weights for policy 1, policy_version 62450 (0.0008) -[2023-10-17 02:46:58,784][62408] Updated weights for policy 1, policy_version 62460 (0.0008) -[2023-10-17 02:47:00,088][62373] Updated weights for policy 0, policy_version 62920 (0.0011) -[2023-10-17 02:47:00,457][62373] Updated weights for policy 0, policy_version 62930 (0.0010) -[2023-10-17 02:47:00,828][62373] Updated weights for policy 0, policy_version 62940 (0.0008) -[2023-10-17 02:47:02,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 128417792. Throughput: 0: 1775.2, 1: 1787.9. Samples: 32116794. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-10-17 02:47:02,215][61453] Avg episode reward: [(0, '10.490'), (1, '9.780')] -[2023-10-17 02:47:02,466][62408] Updated weights for policy 1, policy_version 62470 (0.0007) -[2023-10-17 02:47:02,841][62408] Updated weights for policy 1, policy_version 62480 (0.0009) -[2023-10-17 02:47:03,207][62408] Updated weights for policy 1, policy_version 62490 (0.0010) -[2023-10-17 02:47:04,533][62373] Updated weights for policy 0, policy_version 62950 (0.0008) -[2023-10-17 02:47:04,910][62373] Updated weights for policy 0, policy_version 62960 (0.0009) -[2023-10-17 02:47:05,290][62373] Updated weights for policy 0, policy_version 62970 (0.0007) -[2023-10-17 02:47:07,029][62408] Updated weights for policy 1, policy_version 62500 (0.0008) -[2023-10-17 02:47:07,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 128483328. Throughput: 0: 1796.8, 1: 1773.0. Samples: 32127354. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-10-17 02:47:07,215][61453] Avg episode reward: [(0, '9.920'), (1, '10.200')] -[2023-10-17 02:47:07,398][62408] Updated weights for policy 1, policy_version 62510 (0.0008) -[2023-10-17 02:47:07,766][62408] Updated weights for policy 1, policy_version 62520 (0.0007) -[2023-10-17 02:47:09,092][62373] Updated weights for policy 0, policy_version 62980 (0.0009) -[2023-10-17 02:47:09,456][62373] Updated weights for policy 0, policy_version 62990 (0.0009) -[2023-10-17 02:47:09,832][62373] Updated weights for policy 0, policy_version 63000 (0.0009) -[2023-10-17 02:47:11,634][62408] Updated weights for policy 1, policy_version 62530 (0.0008) -[2023-10-17 02:47:11,998][62408] Updated weights for policy 1, policy_version 62540 (0.0009) -[2023-10-17 02:47:12,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 128548864. Throughput: 0: 1780.3, 1: 1781.8. Samples: 32148708. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-10-17 02:47:12,215][61453] Avg episode reward: [(0, '9.690'), (1, '9.680')] -[2023-10-17 02:47:12,369][62408] Updated weights for policy 1, policy_version 62550 (0.0007) -[2023-10-17 02:47:12,738][62408] Updated weights for policy 1, policy_version 62560 (0.0008) -[2023-10-17 02:47:13,443][62373] Updated weights for policy 0, policy_version 63010 (0.0008) -[2023-10-17 02:47:13,807][62373] Updated weights for policy 0, policy_version 63020 (0.0009) -[2023-10-17 02:47:14,168][62373] Updated weights for policy 0, policy_version 63030 (0.0009) -[2023-10-17 02:47:14,531][62373] Updated weights for policy 0, policy_version 63040 (0.0007) -[2023-10-17 02:47:16,684][62408] Updated weights for policy 1, policy_version 62570 (0.0007) -[2023-10-17 02:47:17,058][62408] Updated weights for policy 1, policy_version 62580 (0.0009) -[2023-10-17 02:47:17,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 128614400. Throughput: 0: 1778.1, 1: 1786.2. Samples: 32170326. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-10-17 02:47:17,215][61453] Avg episode reward: [(0, '9.860'), (1, '10.060')] -[2023-10-17 02:47:17,429][62408] Updated weights for policy 1, policy_version 62590 (0.0009) -[2023-10-17 02:47:18,501][62373] Updated weights for policy 0, policy_version 63050 (0.0009) -[2023-10-17 02:47:18,877][62373] Updated weights for policy 0, policy_version 63060 (0.0007) -[2023-10-17 02:47:19,249][62373] Updated weights for policy 0, policy_version 63070 (0.0007) -[2023-10-17 02:47:21,429][62408] Updated weights for policy 1, policy_version 62600 (0.0007) -[2023-10-17 02:47:21,794][62408] Updated weights for policy 1, policy_version 62610 (0.0007) -[2023-10-17 02:47:22,161][62408] Updated weights for policy 1, policy_version 62620 (0.0008) -[2023-10-17 02:47:22,214][61453] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 128679936. Throughput: 0: 1774.5, 1: 1768.6. Samples: 32180442. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-10-17 02:47:22,214][61453] Avg episode reward: [(0, '10.140'), (1, '10.320')] -[2023-10-17 02:47:22,963][62373] Updated weights for policy 0, policy_version 63080 (0.0008) -[2023-10-17 02:47:23,344][62373] Updated weights for policy 0, policy_version 63090 (0.0010) -[2023-10-17 02:47:23,706][62373] Updated weights for policy 0, policy_version 63100 (0.0008) -[2023-10-17 02:47:25,980][62408] Updated weights for policy 1, policy_version 62630 (0.0008) -[2023-10-17 02:47:26,359][62408] Updated weights for policy 1, policy_version 62640 (0.0009) -[2023-10-17 02:47:26,733][62408] Updated weights for policy 1, policy_version 62650 (0.0007) -[2023-10-17 02:47:27,214][61453] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 128778240. Throughput: 0: 1776.0, 1: 1793.7. Samples: 32202508. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-10-17 02:47:27,214][61453] Avg episode reward: [(0, '10.190'), (1, '9.860')] -[2023-10-17 02:47:27,436][62373] Updated weights for policy 0, policy_version 63110 (0.0007) -[2023-10-17 02:47:27,810][62373] Updated weights for policy 0, policy_version 63120 (0.0008) -[2023-10-17 02:47:28,170][62373] Updated weights for policy 0, policy_version 63130 (0.0008) -[2023-10-17 02:47:30,409][62408] Updated weights for policy 1, policy_version 62660 (0.0008) -[2023-10-17 02:47:30,778][62408] Updated weights for policy 1, policy_version 62670 (0.0007) -[2023-10-17 02:47:31,148][62408] Updated weights for policy 1, policy_version 62680 (0.0008) -[2023-10-17 02:47:31,975][62373] Updated weights for policy 0, policy_version 63140 (0.0007) -[2023-10-17 02:47:32,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 128843776. Throughput: 0: 1800.6, 1: 1766.6. Samples: 32223396. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-10-17 02:47:32,214][61453] Avg episode reward: [(0, '9.490'), (1, '10.590')] -[2023-10-17 02:47:32,222][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000062688_64192512.pth... -[2023-10-17 02:47:32,262][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000061024_62488576.pth -[2023-10-17 02:47:32,347][62373] Updated weights for policy 0, policy_version 63150 (0.0008) -[2023-10-17 02:47:32,718][62373] Updated weights for policy 0, policy_version 63160 (0.0010) -[2023-10-17 02:47:33,007][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000063168_64684032.pth... -[2023-10-17 02:47:33,044][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000061472_62947328.pth -[2023-10-17 02:47:34,976][62408] Updated weights for policy 1, policy_version 62690 (0.0009) -[2023-10-17 02:47:35,350][62408] Updated weights for policy 1, policy_version 62700 (0.0011) -[2023-10-17 02:47:35,728][62408] Updated weights for policy 1, policy_version 62710 (0.0010) -[2023-10-17 02:47:36,091][62408] Updated weights for policy 1, policy_version 62720 (0.0011) -[2023-10-17 02:47:36,528][62373] Updated weights for policy 0, policy_version 63170 (0.0010) -[2023-10-17 02:47:36,910][62373] Updated weights for policy 0, policy_version 63180 (0.0007) -[2023-10-17 02:47:37,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 128909312. Throughput: 0: 1778.9, 1: 1796.8. Samples: 32234600. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-10-17 02:47:37,215][61453] Avg episode reward: [(0, '9.040'), (1, '10.900')] -[2023-10-17 02:47:37,276][62373] Updated weights for policy 0, policy_version 63190 (0.0009) -[2023-10-17 02:47:37,642][62373] Updated weights for policy 0, policy_version 63200 (0.0009) -[2023-10-17 02:47:39,939][62408] Updated weights for policy 1, policy_version 62730 (0.0009) -[2023-10-17 02:47:40,311][62408] Updated weights for policy 1, policy_version 62740 (0.0008) -[2023-10-17 02:47:40,676][62408] Updated weights for policy 1, policy_version 62750 (0.0010) -[2023-10-17 02:47:41,545][62373] Updated weights for policy 0, policy_version 63210 (0.0008) -[2023-10-17 02:47:41,912][62373] Updated weights for policy 0, policy_version 63220 (0.0008) -[2023-10-17 02:47:42,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 128974848. Throughput: 0: 1794.1, 1: 1756.9. Samples: 32255100. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-17 02:47:42,214][61453] Avg episode reward: [(0, '8.940'), (1, '10.790')] -[2023-10-17 02:47:42,289][62373] Updated weights for policy 0, policy_version 63230 (0.0008) -[2023-10-17 02:47:44,240][62408] Updated weights for policy 1, policy_version 62760 (0.0008) -[2023-10-17 02:47:44,602][62408] Updated weights for policy 1, policy_version 62770 (0.0008) -[2023-10-17 02:47:44,977][62408] Updated weights for policy 1, policy_version 62780 (0.0009) -[2023-10-17 02:47:46,072][62373] Updated weights for policy 0, policy_version 63240 (0.0008) -[2023-10-17 02:47:46,441][62373] Updated weights for policy 0, policy_version 63250 (0.0009) -[2023-10-17 02:47:46,823][62373] Updated weights for policy 0, policy_version 63260 (0.0011) -[2023-10-17 02:47:47,214][61453] Fps is (10 sec: 16383.5, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 129073152. Throughput: 0: 1774.4, 1: 1762.8. Samples: 32275968. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-17 02:47:47,215][61453] Avg episode reward: [(0, '8.960'), (1, '10.620')] -[2023-10-17 02:47:48,856][62408] Updated weights for policy 1, policy_version 62790 (0.0010) -[2023-10-17 02:47:49,225][62408] Updated weights for policy 1, policy_version 62800 (0.0011) -[2023-10-17 02:47:49,594][62408] Updated weights for policy 1, policy_version 62810 (0.0010) -[2023-10-17 02:47:50,814][62373] Updated weights for policy 0, policy_version 63270 (0.0009) -[2023-10-17 02:47:51,188][62373] Updated weights for policy 0, policy_version 63280 (0.0007) -[2023-10-17 02:47:51,562][62373] Updated weights for policy 0, policy_version 63290 (0.0009) -[2023-10-17 02:47:52,214][61453] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 129138688. Throughput: 0: 1784.4, 1: 1761.9. Samples: 32286942. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-17 02:47:52,215][61453] Avg episode reward: [(0, '8.680'), (1, '10.430')] -[2023-10-17 02:47:53,330][62408] Updated weights for policy 1, policy_version 62820 (0.0010) -[2023-10-17 02:47:53,702][62408] Updated weights for policy 1, policy_version 62830 (0.0011) -[2023-10-17 02:47:54,059][62408] Updated weights for policy 1, policy_version 62840 (0.0010) -[2023-10-17 02:47:55,329][62373] Updated weights for policy 0, policy_version 63300 (0.0011) -[2023-10-17 02:47:55,701][62373] Updated weights for policy 0, policy_version 63310 (0.0009) -[2023-10-17 02:47:56,067][62373] Updated weights for policy 0, policy_version 63320 (0.0009) -[2023-10-17 02:47:57,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 129204224. Throughput: 0: 1777.3, 1: 1759.7. Samples: 32307876. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-17 02:47:57,215][61453] Avg episode reward: [(0, '8.380'), (1, '9.530')] -[2023-10-17 02:47:58,069][62408] Updated weights for policy 1, policy_version 62850 (0.0011) -[2023-10-17 02:47:58,428][62408] Updated weights for policy 1, policy_version 62860 (0.0010) -[2023-10-17 02:47:58,795][62408] Updated weights for policy 1, policy_version 62870 (0.0009) -[2023-10-17 02:47:59,160][62408] Updated weights for policy 1, policy_version 62880 (0.0010) -[2023-10-17 02:47:59,796][62373] Updated weights for policy 0, policy_version 63330 (0.0008) -[2023-10-17 02:48:00,167][62373] Updated weights for policy 0, policy_version 63340 (0.0008) -[2023-10-17 02:48:00,530][62373] Updated weights for policy 0, policy_version 63350 (0.0011) -[2023-10-17 02:48:00,901][62373] Updated weights for policy 0, policy_version 63360 (0.0009) -[2023-10-17 02:48:02,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 129269760. Throughput: 0: 1757.7, 1: 1770.5. Samples: 32329096. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-17 02:48:02,215][61453] Avg episode reward: [(0, '8.090'), (1, '8.260')] -[2023-10-17 02:48:02,983][62408] Updated weights for policy 1, policy_version 62890 (0.0010) -[2023-10-17 02:48:03,350][62408] Updated weights for policy 1, policy_version 62900 (0.0009) -[2023-10-17 02:48:03,725][62408] Updated weights for policy 1, policy_version 62910 (0.0011) -[2023-10-17 02:48:04,782][62373] Updated weights for policy 0, policy_version 63370 (0.0008) -[2023-10-17 02:48:05,159][62373] Updated weights for policy 0, policy_version 63380 (0.0009) -[2023-10-17 02:48:05,520][62373] Updated weights for policy 0, policy_version 63390 (0.0010) -[2023-10-17 02:48:07,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 129335296. Throughput: 0: 1778.5, 1: 1757.4. Samples: 32339556. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-17 02:48:07,215][61453] Avg episode reward: [(0, '8.370'), (1, '8.580')] -[2023-10-17 02:48:07,607][62408] Updated weights for policy 1, policy_version 62920 (0.0010) -[2023-10-17 02:48:07,977][62408] Updated weights for policy 1, policy_version 62930 (0.0009) -[2023-10-17 02:48:08,344][62408] Updated weights for policy 1, policy_version 62940 (0.0010) -[2023-10-17 02:48:09,116][62373] Updated weights for policy 0, policy_version 63400 (0.0008) -[2023-10-17 02:48:09,494][62373] Updated weights for policy 0, policy_version 63410 (0.0010) -[2023-10-17 02:48:09,861][62373] Updated weights for policy 0, policy_version 63420 (0.0009) -[2023-10-17 02:48:12,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 129400832. Throughput: 0: 1760.3, 1: 1757.4. Samples: 32360806. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-17 02:48:12,215][61453] Avg episode reward: [(0, '8.560'), (1, '7.350')] -[2023-10-17 02:48:12,216][62408] Updated weights for policy 1, policy_version 62950 (0.0011) -[2023-10-17 02:48:12,586][62408] Updated weights for policy 1, policy_version 62960 (0.0011) -[2023-10-17 02:48:12,957][62408] Updated weights for policy 1, policy_version 62970 (0.0010) -[2023-10-17 02:48:13,561][62373] Updated weights for policy 0, policy_version 63430 (0.0009) -[2023-10-17 02:48:13,935][62373] Updated weights for policy 0, policy_version 63440 (0.0008) -[2023-10-17 02:48:14,295][62373] Updated weights for policy 0, policy_version 63450 (0.0010) -[2023-10-17 02:48:16,780][62408] Updated weights for policy 1, policy_version 62980 (0.0008) -[2023-10-17 02:48:17,142][62408] Updated weights for policy 1, policy_version 62990 (0.0009) -[2023-10-17 02:48:17,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 129466368. Throughput: 0: 1764.7, 1: 1778.4. Samples: 32382832. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-17 02:48:17,214][61453] Avg episode reward: [(0, '9.400'), (1, '7.160')] -[2023-10-17 02:48:17,520][62408] Updated weights for policy 1, policy_version 63000 (0.0010) -[2023-10-17 02:48:18,077][62373] Updated weights for policy 0, policy_version 63460 (0.0010) -[2023-10-17 02:48:18,450][62373] Updated weights for policy 0, policy_version 63470 (0.0008) -[2023-10-17 02:48:18,819][62373] Updated weights for policy 0, policy_version 63480 (0.0008) -[2023-10-17 02:48:21,375][62408] Updated weights for policy 1, policy_version 63010 (0.0008) -[2023-10-17 02:48:21,770][62408] Updated weights for policy 1, policy_version 63020 (0.0009) -[2023-10-17 02:48:22,134][62408] Updated weights for policy 1, policy_version 63030 (0.0011) -[2023-10-17 02:48:22,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 129531904. Throughput: 0: 1762.9, 1: 1754.0. Samples: 32392864. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) -[2023-10-17 02:48:22,214][61453] Avg episode reward: [(0, '9.630'), (1, '6.830')] -[2023-10-17 02:48:22,496][62408] Updated weights for policy 1, policy_version 63040 (0.0007) -[2023-10-17 02:48:22,608][62373] Updated weights for policy 0, policy_version 63490 (0.0008) -[2023-10-17 02:48:22,979][62373] Updated weights for policy 0, policy_version 63500 (0.0009) -[2023-10-17 02:48:23,350][62373] Updated weights for policy 0, policy_version 63510 (0.0007) -[2023-10-17 02:48:23,721][62373] Updated weights for policy 0, policy_version 63520 (0.0008) -[2023-10-17 02:48:26,387][62408] Updated weights for policy 1, policy_version 63050 (0.0009) -[2023-10-17 02:48:26,762][62408] Updated weights for policy 1, policy_version 63060 (0.0008) -[2023-10-17 02:48:27,119][62408] Updated weights for policy 1, policy_version 63070 (0.0009) -[2023-10-17 02:48:27,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 129630208. Throughput: 0: 1760.7, 1: 1782.9. Samples: 32414564. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) -[2023-10-17 02:48:27,215][61453] Avg episode reward: [(0, '9.390'), (1, '7.070')] -[2023-10-17 02:48:27,543][62373] Updated weights for policy 0, policy_version 63530 (0.0008) -[2023-10-17 02:48:27,919][62373] Updated weights for policy 0, policy_version 63540 (0.0007) -[2023-10-17 02:48:28,295][62373] Updated weights for policy 0, policy_version 63550 (0.0007) -[2023-10-17 02:48:30,766][62408] Updated weights for policy 1, policy_version 63080 (0.0009) -[2023-10-17 02:48:31,136][62408] Updated weights for policy 1, policy_version 63090 (0.0010) -[2023-10-17 02:48:31,505][62408] Updated weights for policy 1, policy_version 63100 (0.0008) -[2023-10-17 02:48:32,152][62373] Updated weights for policy 0, policy_version 63560 (0.0009) -[2023-10-17 02:48:32,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 129695744. Throughput: 0: 1790.1, 1: 1748.6. Samples: 32435206. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) -[2023-10-17 02:48:32,215][61453] Avg episode reward: [(0, '9.850'), (1, '7.090')] -[2023-10-17 02:48:32,511][62373] Updated weights for policy 0, policy_version 63570 (0.0010) -[2023-10-17 02:48:32,888][62373] Updated weights for policy 0, policy_version 63580 (0.0007) -[2023-10-17 02:48:35,277][62408] Updated weights for policy 1, policy_version 63110 (0.0008) -[2023-10-17 02:48:35,637][62408] Updated weights for policy 1, policy_version 63120 (0.0009) -[2023-10-17 02:48:36,013][62408] Updated weights for policy 1, policy_version 63130 (0.0010) -[2023-10-17 02:48:36,838][62373] Updated weights for policy 0, policy_version 63590 (0.0009) -[2023-10-17 02:48:37,211][62373] Updated weights for policy 0, policy_version 63600 (0.0010) -[2023-10-17 02:48:37,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 129761280. Throughput: 0: 1763.9, 1: 1782.2. Samples: 32446518. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) -[2023-10-17 02:48:37,215][61453] Avg episode reward: [(0, '10.110'), (1, '7.930')] -[2023-10-17 02:48:37,581][62373] Updated weights for policy 0, policy_version 63610 (0.0011) -[2023-10-17 02:48:39,814][62408] Updated weights for policy 1, policy_version 63140 (0.0008) -[2023-10-17 02:48:40,183][62408] Updated weights for policy 1, policy_version 63150 (0.0009) -[2023-10-17 02:48:40,546][62408] Updated weights for policy 1, policy_version 63160 (0.0008) -[2023-10-17 02:48:41,544][62373] Updated weights for policy 0, policy_version 63620 (0.0009) -[2023-10-17 02:48:41,910][62373] Updated weights for policy 0, policy_version 63630 (0.0007) -[2023-10-17 02:48:42,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 129826816. Throughput: 0: 1780.5, 1: 1752.0. Samples: 32466842. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) -[2023-10-17 02:48:42,215][61453] Avg episode reward: [(0, '10.400'), (1, '8.170')] -[2023-10-17 02:48:42,287][62373] Updated weights for policy 0, policy_version 63640 (0.0008) -[2023-10-17 02:48:44,578][62408] Updated weights for policy 1, policy_version 63170 (0.0008) -[2023-10-17 02:48:44,949][62408] Updated weights for policy 1, policy_version 63180 (0.0007) -[2023-10-17 02:48:45,319][62408] Updated weights for policy 1, policy_version 63190 (0.0007) -[2023-10-17 02:48:45,690][62408] Updated weights for policy 1, policy_version 63200 (0.0007) -[2023-10-17 02:48:45,863][62373] Updated weights for policy 0, policy_version 63650 (0.0009) -[2023-10-17 02:48:46,228][62373] Updated weights for policy 0, policy_version 63660 (0.0008) -[2023-10-17 02:48:46,598][62373] Updated weights for policy 0, policy_version 63670 (0.0007) -[2023-10-17 02:48:46,960][62373] Updated weights for policy 0, policy_version 63680 (0.0007) -[2023-10-17 02:48:47,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 129925120. Throughput: 0: 1773.3, 1: 1754.5. Samples: 32487844. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) -[2023-10-17 02:48:47,215][61453] Avg episode reward: [(0, '10.270'), (1, '9.030')] -[2023-10-17 02:48:49,582][62408] Updated weights for policy 1, policy_version 63210 (0.0009) -[2023-10-17 02:48:49,952][62408] Updated weights for policy 1, policy_version 63220 (0.0009) -[2023-10-17 02:48:50,314][62408] Updated weights for policy 1, policy_version 63230 (0.0007) -[2023-10-17 02:48:50,753][62373] Updated weights for policy 0, policy_version 63690 (0.0009) -[2023-10-17 02:48:51,110][62373] Updated weights for policy 0, policy_version 63700 (0.0010) -[2023-10-17 02:48:51,481][62373] Updated weights for policy 0, policy_version 63710 (0.0009) -[2023-10-17 02:48:52,214][61453] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 129990656. Throughput: 0: 1785.6, 1: 1769.2. Samples: 32499520. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) -[2023-10-17 02:48:52,215][61453] Avg episode reward: [(0, '9.560'), (1, '9.220')] -[2023-10-17 02:48:54,026][62408] Updated weights for policy 1, policy_version 63240 (0.0009) -[2023-10-17 02:48:54,388][62408] Updated weights for policy 1, policy_version 63250 (0.0009) -[2023-10-17 02:48:54,767][62408] Updated weights for policy 1, policy_version 63260 (0.0009) -[2023-10-17 02:48:55,227][62373] Updated weights for policy 0, policy_version 63720 (0.0008) -[2023-10-17 02:48:55,600][62373] Updated weights for policy 0, policy_version 63730 (0.0008) -[2023-10-17 02:48:55,966][62373] Updated weights for policy 0, policy_version 63740 (0.0008) -[2023-10-17 02:48:57,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 130056192. Throughput: 0: 1777.1, 1: 1759.0. Samples: 32519930. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) -[2023-10-17 02:48:57,214][61453] Avg episode reward: [(0, '9.110'), (1, '9.800')] -[2023-10-17 02:48:58,645][62408] Updated weights for policy 1, policy_version 63270 (0.0007) -[2023-10-17 02:48:59,010][62408] Updated weights for policy 1, policy_version 63280 (0.0010) -[2023-10-17 02:48:59,380][62408] Updated weights for policy 1, policy_version 63290 (0.0009) -[2023-10-17 02:48:59,610][62373] Updated weights for policy 0, policy_version 63750 (0.0008) -[2023-10-17 02:48:59,985][62373] Updated weights for policy 0, policy_version 63760 (0.0007) -[2023-10-17 02:49:00,351][62373] Updated weights for policy 0, policy_version 63770 (0.0007) -[2023-10-17 02:49:02,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 130121728. Throughput: 0: 1771.7, 1: 1763.2. Samples: 32541902. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:49:02,215][61453] Avg episode reward: [(0, '9.530'), (1, '10.000')] -[2023-10-17 02:49:03,113][62408] Updated weights for policy 1, policy_version 63300 (0.0009) -[2023-10-17 02:49:03,485][62408] Updated weights for policy 1, policy_version 63310 (0.0007) -[2023-10-17 02:49:03,848][62408] Updated weights for policy 1, policy_version 63320 (0.0007) -[2023-10-17 02:49:04,256][62373] Updated weights for policy 0, policy_version 63780 (0.0008) -[2023-10-17 02:49:04,628][62373] Updated weights for policy 0, policy_version 63790 (0.0008) -[2023-10-17 02:49:04,999][62373] Updated weights for policy 0, policy_version 63800 (0.0008) -[2023-10-17 02:49:07,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 130187264. Throughput: 0: 1780.5, 1: 1761.0. Samples: 32552232. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:49:07,214][61453] Avg episode reward: [(0, '9.210'), (1, '9.890')] -[2023-10-17 02:49:07,815][62408] Updated weights for policy 1, policy_version 63330 (0.0010) -[2023-10-17 02:49:08,187][62408] Updated weights for policy 1, policy_version 63340 (0.0011) -[2023-10-17 02:49:08,551][62408] Updated weights for policy 1, policy_version 63350 (0.0008) -[2023-10-17 02:49:08,816][62373] Updated weights for policy 0, policy_version 63810 (0.0007) -[2023-10-17 02:49:08,919][62408] Updated weights for policy 1, policy_version 63360 (0.0008) -[2023-10-17 02:49:09,186][62373] Updated weights for policy 0, policy_version 63820 (0.0008) -[2023-10-17 02:49:09,564][62373] Updated weights for policy 0, policy_version 63830 (0.0009) -[2023-10-17 02:49:09,929][62373] Updated weights for policy 0, policy_version 63840 (0.0008) -[2023-10-17 02:49:12,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 130252800. Throughput: 0: 1773.3, 1: 1764.8. Samples: 32573780. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:49:12,215][61453] Avg episode reward: [(0, '9.500'), (1, '9.880')] -[2023-10-17 02:49:12,894][62408] Updated weights for policy 1, policy_version 63370 (0.0008) -[2023-10-17 02:49:13,257][62408] Updated weights for policy 1, policy_version 63380 (0.0007) -[2023-10-17 02:49:13,629][62408] Updated weights for policy 1, policy_version 63390 (0.0008) -[2023-10-17 02:49:13,686][62373] Updated weights for policy 0, policy_version 63850 (0.0007) -[2023-10-17 02:49:14,064][62373] Updated weights for policy 0, policy_version 63860 (0.0010) -[2023-10-17 02:49:14,445][62373] Updated weights for policy 0, policy_version 63870 (0.0010) -[2023-10-17 02:49:17,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 130318336. Throughput: 0: 1778.0, 1: 1787.3. Samples: 32595644. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:49:17,215][61453] Avg episode reward: [(0, '9.290'), (1, '9.750')] -[2023-10-17 02:49:17,406][62408] Updated weights for policy 1, policy_version 63400 (0.0008) -[2023-10-17 02:49:17,781][62408] Updated weights for policy 1, policy_version 63410 (0.0007) -[2023-10-17 02:49:18,148][62408] Updated weights for policy 1, policy_version 63420 (0.0007) -[2023-10-17 02:49:18,273][62373] Updated weights for policy 0, policy_version 63880 (0.0007) -[2023-10-17 02:49:18,640][62373] Updated weights for policy 0, policy_version 63890 (0.0010) -[2023-10-17 02:49:19,016][62373] Updated weights for policy 0, policy_version 63900 (0.0011) -[2023-10-17 02:49:21,940][62408] Updated weights for policy 1, policy_version 63430 (0.0007) -[2023-10-17 02:49:22,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 130383872. Throughput: 0: 1774.2, 1: 1757.0. Samples: 32605424. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:49:22,215][61453] Avg episode reward: [(0, '9.340'), (1, '9.210')] -[2023-10-17 02:49:22,307][62408] Updated weights for policy 1, policy_version 63440 (0.0007) -[2023-10-17 02:49:22,680][62408] Updated weights for policy 1, policy_version 63450 (0.0007) -[2023-10-17 02:49:22,916][62373] Updated weights for policy 0, policy_version 63910 (0.0007) -[2023-10-17 02:49:23,291][62373] Updated weights for policy 0, policy_version 63920 (0.0009) -[2023-10-17 02:49:23,662][62373] Updated weights for policy 0, policy_version 63930 (0.0008) -[2023-10-17 02:49:26,510][62408] Updated weights for policy 1, policy_version 63460 (0.0008) -[2023-10-17 02:49:26,878][62408] Updated weights for policy 1, policy_version 63470 (0.0008) -[2023-10-17 02:49:27,214][61453] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 130449408. Throughput: 0: 1772.8, 1: 1786.6. Samples: 32627014. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:49:27,214][61453] Avg episode reward: [(0, '8.950'), (1, '9.740')] -[2023-10-17 02:49:27,251][62408] Updated weights for policy 1, policy_version 63480 (0.0009) -[2023-10-17 02:49:27,524][62373] Updated weights for policy 0, policy_version 63940 (0.0008) -[2023-10-17 02:49:27,891][62373] Updated weights for policy 0, policy_version 63950 (0.0007) -[2023-10-17 02:49:28,265][62373] Updated weights for policy 0, policy_version 63960 (0.0008) -[2023-10-17 02:49:31,111][62408] Updated weights for policy 1, policy_version 63490 (0.0008) -[2023-10-17 02:49:31,484][62408] Updated weights for policy 1, policy_version 63500 (0.0008) -[2023-10-17 02:49:31,847][62408] Updated weights for policy 1, policy_version 63510 (0.0011) -[2023-10-17 02:49:32,036][62373] Updated weights for policy 0, policy_version 63970 (0.0008) -[2023-10-17 02:49:32,214][62408] Updated weights for policy 1, policy_version 63520 (0.0009) -[2023-10-17 02:49:32,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 130547712. Throughput: 0: 1798.4, 1: 1763.6. Samples: 32648132. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:49:32,215][61453] Avg episode reward: [(0, '9.780'), (1, '9.710')] -[2023-10-17 02:49:32,224][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000063520_65044480.pth... -[2023-10-17 02:49:32,265][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000061856_63340544.pth -[2023-10-17 02:49:32,410][62373] Updated weights for policy 0, policy_version 63980 (0.0008) -[2023-10-17 02:49:32,779][62373] Updated weights for policy 0, policy_version 63990 (0.0007) -[2023-10-17 02:49:33,155][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000064000_65536000.pth... -[2023-10-17 02:49:33,160][62373] Updated weights for policy 0, policy_version 64000 (0.0007) -[2023-10-17 02:49:33,194][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000062304_63799296.pth -[2023-10-17 02:49:35,953][62408] Updated weights for policy 1, policy_version 63530 (0.0011) -[2023-10-17 02:49:36,313][62408] Updated weights for policy 1, policy_version 63540 (0.0008) -[2023-10-17 02:49:36,679][62408] Updated weights for policy 1, policy_version 63550 (0.0007) -[2023-10-17 02:49:36,988][62373] Updated weights for policy 0, policy_version 64010 (0.0008) -[2023-10-17 02:49:37,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 130613248. Throughput: 0: 1764.8, 1: 1773.2. Samples: 32658728. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:49:37,215][61453] Avg episode reward: [(0, '8.610'), (1, '9.930')] -[2023-10-17 02:49:37,363][62373] Updated weights for policy 0, policy_version 64020 (0.0008) -[2023-10-17 02:49:37,742][62373] Updated weights for policy 0, policy_version 64030 (0.0007) -[2023-10-17 02:49:40,502][62408] Updated weights for policy 1, policy_version 63560 (0.0010) -[2023-10-17 02:49:40,870][62408] Updated weights for policy 1, policy_version 63570 (0.0010) -[2023-10-17 02:49:41,237][62408] Updated weights for policy 1, policy_version 63580 (0.0008) -[2023-10-17 02:49:41,470][62373] Updated weights for policy 0, policy_version 64040 (0.0009) -[2023-10-17 02:49:41,840][62373] Updated weights for policy 0, policy_version 64050 (0.0011) -[2023-10-17 02:49:42,205][62373] Updated weights for policy 0, policy_version 64060 (0.0007) -[2023-10-17 02:49:42,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 130678784. Throughput: 0: 1792.5, 1: 1770.3. Samples: 32680254. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:49:42,214][61453] Avg episode reward: [(0, '8.580'), (1, '9.820')] -[2023-10-17 02:49:45,011][62408] Updated weights for policy 1, policy_version 63590 (0.0009) -[2023-10-17 02:49:45,384][62408] Updated weights for policy 1, policy_version 63600 (0.0008) -[2023-10-17 02:49:45,746][62408] Updated weights for policy 1, policy_version 63610 (0.0008) -[2023-10-17 02:49:45,975][62373] Updated weights for policy 0, policy_version 64070 (0.0008) -[2023-10-17 02:49:46,337][62373] Updated weights for policy 0, policy_version 64080 (0.0007) -[2023-10-17 02:49:46,713][62373] Updated weights for policy 0, policy_version 64090 (0.0008) -[2023-10-17 02:49:47,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 130777088. Throughput: 0: 1767.3, 1: 1757.6. Samples: 32700522. Policy #0 lag: (min: 16.0, avg: 35.7, max: 48.0) -[2023-10-17 02:49:47,214][61453] Avg episode reward: [(0, '8.970'), (1, '9.800')] -[2023-10-17 02:49:49,477][62408] Updated weights for policy 1, policy_version 63620 (0.0007) -[2023-10-17 02:49:49,837][62408] Updated weights for policy 1, policy_version 63630 (0.0007) -[2023-10-17 02:49:50,212][62408] Updated weights for policy 1, policy_version 63640 (0.0008) -[2023-10-17 02:49:50,662][62373] Updated weights for policy 0, policy_version 64100 (0.0008) -[2023-10-17 02:49:51,040][62373] Updated weights for policy 0, policy_version 64110 (0.0009) -[2023-10-17 02:49:51,409][62373] Updated weights for policy 0, policy_version 64120 (0.0008) -[2023-10-17 02:49:52,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 130842624. Throughput: 0: 1783.0, 1: 1770.2. Samples: 32712126. Policy #0 lag: (min: 16.0, avg: 35.7, max: 48.0) -[2023-10-17 02:49:52,215][61453] Avg episode reward: [(0, '9.550'), (1, '10.550')] -[2023-10-17 02:49:53,976][62408] Updated weights for policy 1, policy_version 63650 (0.0007) -[2023-10-17 02:49:54,353][62408] Updated weights for policy 1, policy_version 63660 (0.0008) -[2023-10-17 02:49:54,716][62408] Updated weights for policy 1, policy_version 63670 (0.0008) -[2023-10-17 02:49:55,090][62408] Updated weights for policy 1, policy_version 63680 (0.0009) -[2023-10-17 02:49:55,180][62373] Updated weights for policy 0, policy_version 64130 (0.0009) -[2023-10-17 02:49:55,546][62373] Updated weights for policy 0, policy_version 64140 (0.0009) -[2023-10-17 02:49:55,920][62373] Updated weights for policy 0, policy_version 64150 (0.0010) -[2023-10-17 02:49:56,284][62373] Updated weights for policy 0, policy_version 64160 (0.0009) -[2023-10-17 02:49:57,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 130908160. Throughput: 0: 1768.0, 1: 1754.0. Samples: 32732272. Policy #0 lag: (min: 16.0, avg: 35.7, max: 48.0) -[2023-10-17 02:49:57,215][61453] Avg episode reward: [(0, '9.060'), (1, '10.600')] -[2023-10-17 02:49:59,091][62408] Updated weights for policy 1, policy_version 63690 (0.0007) -[2023-10-17 02:49:59,459][62408] Updated weights for policy 1, policy_version 63700 (0.0007) -[2023-10-17 02:49:59,825][62408] Updated weights for policy 1, policy_version 63710 (0.0007) -[2023-10-17 02:50:00,223][62373] Updated weights for policy 0, policy_version 64170 (0.0009) -[2023-10-17 02:50:00,594][62373] Updated weights for policy 0, policy_version 64180 (0.0008) -[2023-10-17 02:50:00,968][62373] Updated weights for policy 0, policy_version 64190 (0.0008) -[2023-10-17 02:50:02,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 130973696. Throughput: 0: 1758.4, 1: 1754.4. Samples: 32753722. Policy #0 lag: (min: 16.0, avg: 35.7, max: 48.0) -[2023-10-17 02:50:02,215][61453] Avg episode reward: [(0, '8.900'), (1, '10.440')] -[2023-10-17 02:50:03,679][62408] Updated weights for policy 1, policy_version 63720 (0.0007) -[2023-10-17 02:50:04,050][62408] Updated weights for policy 1, policy_version 63730 (0.0007) -[2023-10-17 02:50:04,419][62408] Updated weights for policy 1, policy_version 63740 (0.0007) -[2023-10-17 02:50:04,819][62373] Updated weights for policy 0, policy_version 64200 (0.0010) -[2023-10-17 02:50:05,186][62373] Updated weights for policy 0, policy_version 64210 (0.0010) -[2023-10-17 02:50:05,552][62373] Updated weights for policy 0, policy_version 64220 (0.0010) -[2023-10-17 02:50:07,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 131039232. Throughput: 0: 1777.2, 1: 1751.2. Samples: 32764200. Policy #0 lag: (min: 16.0, avg: 35.7, max: 48.0) -[2023-10-17 02:50:07,215][61453] Avg episode reward: [(0, '9.190'), (1, '10.220')] -[2023-10-17 02:50:08,175][62408] Updated weights for policy 1, policy_version 63750 (0.0010) -[2023-10-17 02:50:08,542][62408] Updated weights for policy 1, policy_version 63760 (0.0008) -[2023-10-17 02:50:08,906][62408] Updated weights for policy 1, policy_version 63770 (0.0008) -[2023-10-17 02:50:09,315][62373] Updated weights for policy 0, policy_version 64230 (0.0007) -[2023-10-17 02:50:09,677][62373] Updated weights for policy 0, policy_version 64240 (0.0008) -[2023-10-17 02:50:10,061][62373] Updated weights for policy 0, policy_version 64250 (0.0009) -[2023-10-17 02:50:12,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 131104768. Throughput: 0: 1763.7, 1: 1759.7. Samples: 32785568. Policy #0 lag: (min: 16.0, avg: 35.7, max: 48.0) -[2023-10-17 02:50:12,214][61453] Avg episode reward: [(0, '9.650'), (1, '10.160')] -[2023-10-17 02:50:12,602][62408] Updated weights for policy 1, policy_version 63780 (0.0009) -[2023-10-17 02:50:12,975][62408] Updated weights for policy 1, policy_version 63790 (0.0009) -[2023-10-17 02:50:13,342][62408] Updated weights for policy 1, policy_version 63800 (0.0007) -[2023-10-17 02:50:13,829][62373] Updated weights for policy 0, policy_version 64260 (0.0007) -[2023-10-17 02:50:14,215][62373] Updated weights for policy 0, policy_version 64270 (0.0007) -[2023-10-17 02:50:14,579][62373] Updated weights for policy 0, policy_version 64280 (0.0008) -[2023-10-17 02:50:17,049][62408] Updated weights for policy 1, policy_version 63810 (0.0007) -[2023-10-17 02:50:17,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 131170304. Throughput: 0: 1759.2, 1: 1792.0. Samples: 32807934. Policy #0 lag: (min: 16.0, avg: 35.7, max: 48.0) -[2023-10-17 02:50:17,214][61453] Avg episode reward: [(0, '10.220'), (1, '11.070')] -[2023-10-17 02:50:17,421][62408] Updated weights for policy 1, policy_version 63820 (0.0007) -[2023-10-17 02:50:17,786][62408] Updated weights for policy 1, policy_version 63830 (0.0008) -[2023-10-17 02:50:18,145][62408] Updated weights for policy 1, policy_version 63840 (0.0010) -[2023-10-17 02:50:18,206][62373] Updated weights for policy 0, policy_version 64290 (0.0009) -[2023-10-17 02:50:18,572][62373] Updated weights for policy 0, policy_version 64300 (0.0011) -[2023-10-17 02:50:18,947][62373] Updated weights for policy 0, policy_version 64310 (0.0010) -[2023-10-17 02:50:19,321][62373] Updated weights for policy 0, policy_version 64320 (0.0009) -[2023-10-17 02:50:21,996][62408] Updated weights for policy 1, policy_version 63850 (0.0008) -[2023-10-17 02:50:22,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 131235840. Throughput: 0: 1763.9, 1: 1768.9. Samples: 32817706. Policy #0 lag: (min: 16.0, avg: 35.7, max: 48.0) -[2023-10-17 02:50:22,215][61453] Avg episode reward: [(0, '9.010'), (1, '9.840')] -[2023-10-17 02:50:22,375][62408] Updated weights for policy 1, policy_version 63860 (0.0008) -[2023-10-17 02:50:22,740][62408] Updated weights for policy 1, policy_version 63870 (0.0010) -[2023-10-17 02:50:23,170][62373] Updated weights for policy 0, policy_version 64330 (0.0008) -[2023-10-17 02:50:23,533][62373] Updated weights for policy 0, policy_version 64340 (0.0010) -[2023-10-17 02:50:23,898][62373] Updated weights for policy 0, policy_version 64350 (0.0007) -[2023-10-17 02:50:26,720][62408] Updated weights for policy 1, policy_version 63880 (0.0010) -[2023-10-17 02:50:27,084][62408] Updated weights for policy 1, policy_version 63890 (0.0009) -[2023-10-17 02:50:27,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 131301376. Throughput: 0: 1763.5, 1: 1777.5. Samples: 32839600. Policy #0 lag: (min: 17.0, avg: 31.6, max: 49.0) -[2023-10-17 02:50:27,215][61453] Avg episode reward: [(0, '9.260'), (1, '9.940')] -[2023-10-17 02:50:27,452][62408] Updated weights for policy 1, policy_version 63900 (0.0009) -[2023-10-17 02:50:27,709][62373] Updated weights for policy 0, policy_version 64360 (0.0007) -[2023-10-17 02:50:28,083][62373] Updated weights for policy 0, policy_version 64370 (0.0007) -[2023-10-17 02:50:28,446][62373] Updated weights for policy 0, policy_version 64380 (0.0009) -[2023-10-17 02:50:31,395][62408] Updated weights for policy 1, policy_version 63910 (0.0008) -[2023-10-17 02:50:31,769][62408] Updated weights for policy 1, policy_version 63920 (0.0008) -[2023-10-17 02:50:32,138][62408] Updated weights for policy 1, policy_version 63930 (0.0007) -[2023-10-17 02:50:32,212][62373] Updated weights for policy 0, policy_version 64390 (0.0011) -[2023-10-17 02:50:32,214][61453] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 131366912. Throughput: 0: 1794.0, 1: 1768.5. Samples: 32860836. Policy #0 lag: (min: 17.0, avg: 31.6, max: 49.0) -[2023-10-17 02:50:32,214][61453] Avg episode reward: [(0, '9.360'), (1, '11.020')] -[2023-10-17 02:50:32,598][62373] Updated weights for policy 0, policy_version 64400 (0.0010) -[2023-10-17 02:50:32,965][62373] Updated weights for policy 0, policy_version 64410 (0.0010) -[2023-10-17 02:50:35,977][62408] Updated weights for policy 1, policy_version 63940 (0.0008) -[2023-10-17 02:50:36,342][62408] Updated weights for policy 1, policy_version 63950 (0.0007) -[2023-10-17 02:50:36,691][62373] Updated weights for policy 0, policy_version 64420 (0.0009) -[2023-10-17 02:50:36,693][62408] Updated weights for policy 1, policy_version 63960 (0.0007) -[2023-10-17 02:50:37,056][62373] Updated weights for policy 0, policy_version 64430 (0.0008) -[2023-10-17 02:50:37,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 131465216. Throughput: 0: 1763.7, 1: 1767.3. Samples: 32871022. Policy #0 lag: (min: 17.0, avg: 31.6, max: 49.0) -[2023-10-17 02:50:37,215][61453] Avg episode reward: [(0, '9.050'), (1, '10.090')] -[2023-10-17 02:50:37,426][62373] Updated weights for policy 0, policy_version 64440 (0.0007) -[2023-10-17 02:50:40,645][62408] Updated weights for policy 1, policy_version 63970 (0.0008) -[2023-10-17 02:50:41,016][62408] Updated weights for policy 1, policy_version 63980 (0.0008) -[2023-10-17 02:50:41,381][62408] Updated weights for policy 1, policy_version 63990 (0.0008) -[2023-10-17 02:50:41,395][62373] Updated weights for policy 0, policy_version 64450 (0.0008) -[2023-10-17 02:50:41,742][62408] Updated weights for policy 1, policy_version 64000 (0.0007) -[2023-10-17 02:50:41,764][62373] Updated weights for policy 0, policy_version 64460 (0.0008) -[2023-10-17 02:50:42,137][62373] Updated weights for policy 0, policy_version 64470 (0.0008) -[2023-10-17 02:50:42,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 131530752. Throughput: 0: 1784.9, 1: 1773.9. Samples: 32892416. Policy #0 lag: (min: 17.0, avg: 31.6, max: 49.0) -[2023-10-17 02:50:42,214][61453] Avg episode reward: [(0, '9.220'), (1, '10.960')] -[2023-10-17 02:50:42,508][62373] Updated weights for policy 0, policy_version 64480 (0.0007) -[2023-10-17 02:50:45,831][62408] Updated weights for policy 1, policy_version 64010 (0.0007) -[2023-10-17 02:50:46,201][62408] Updated weights for policy 1, policy_version 64020 (0.0007) -[2023-10-17 02:50:46,359][62373] Updated weights for policy 0, policy_version 64490 (0.0009) -[2023-10-17 02:50:46,566][62408] Updated weights for policy 1, policy_version 64030 (0.0009) -[2023-10-17 02:50:46,724][62373] Updated weights for policy 0, policy_version 64500 (0.0008) -[2023-10-17 02:50:47,094][62373] Updated weights for policy 0, policy_version 64510 (0.0010) -[2023-10-17 02:50:47,214][61453] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 131629056. Throughput: 0: 1768.2, 1: 1747.1. Samples: 32911908. Policy #0 lag: (min: 17.0, avg: 31.6, max: 49.0) -[2023-10-17 02:50:47,214][61453] Avg episode reward: [(0, '9.100'), (1, '10.850')] -[2023-10-17 02:50:50,344][62408] Updated weights for policy 1, policy_version 64040 (0.0007) -[2023-10-17 02:50:50,717][62408] Updated weights for policy 1, policy_version 64050 (0.0008) -[2023-10-17 02:50:51,008][62373] Updated weights for policy 0, policy_version 64520 (0.0008) -[2023-10-17 02:50:51,082][62408] Updated weights for policy 1, policy_version 64060 (0.0008) -[2023-10-17 02:50:51,378][62373] Updated weights for policy 0, policy_version 64530 (0.0007) -[2023-10-17 02:50:51,751][62373] Updated weights for policy 0, policy_version 64540 (0.0008) -[2023-10-17 02:50:52,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 131694592. Throughput: 0: 1771.5, 1: 1781.4. Samples: 32924078. Policy #0 lag: (min: 17.0, avg: 31.6, max: 49.0) -[2023-10-17 02:50:52,215][61453] Avg episode reward: [(0, '8.470'), (1, '10.740')] -[2023-10-17 02:50:54,762][62408] Updated weights for policy 1, policy_version 64070 (0.0007) -[2023-10-17 02:50:55,132][62408] Updated weights for policy 1, policy_version 64080 (0.0008) -[2023-10-17 02:50:55,374][62373] Updated weights for policy 0, policy_version 64550 (0.0007) -[2023-10-17 02:50:55,494][62408] Updated weights for policy 1, policy_version 64090 (0.0007) -[2023-10-17 02:50:55,737][62373] Updated weights for policy 0, policy_version 64560 (0.0008) -[2023-10-17 02:50:56,107][62373] Updated weights for policy 0, policy_version 64570 (0.0010) -[2023-10-17 02:50:57,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 131760128. Throughput: 0: 1778.1, 1: 1746.8. Samples: 32944192. Policy #0 lag: (min: 17.0, avg: 31.6, max: 49.0) -[2023-10-17 02:50:57,214][61453] Avg episode reward: [(0, '9.040'), (1, '10.570')] -[2023-10-17 02:50:59,478][62408] Updated weights for policy 1, policy_version 64100 (0.0009) -[2023-10-17 02:50:59,844][62408] Updated weights for policy 1, policy_version 64110 (0.0009) -[2023-10-17 02:51:00,042][62373] Updated weights for policy 0, policy_version 64580 (0.0009) -[2023-10-17 02:51:00,217][62408] Updated weights for policy 1, policy_version 64120 (0.0008) -[2023-10-17 02:51:00,423][62373] Updated weights for policy 0, policy_version 64590 (0.0007) -[2023-10-17 02:51:00,795][62373] Updated weights for policy 0, policy_version 64600 (0.0010) -[2023-10-17 02:51:02,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 131825664. Throughput: 0: 1762.3, 1: 1734.3. Samples: 32965286. Policy #0 lag: (min: 17.0, avg: 31.6, max: 49.0) -[2023-10-17 02:51:02,215][61453] Avg episode reward: [(0, '9.410'), (1, '10.850')] -[2023-10-17 02:51:04,037][62408] Updated weights for policy 1, policy_version 64130 (0.0008) -[2023-10-17 02:51:04,416][62408] Updated weights for policy 1, policy_version 64140 (0.0009) -[2023-10-17 02:51:04,548][62373] Updated weights for policy 0, policy_version 64610 (0.0011) -[2023-10-17 02:51:04,779][62408] Updated weights for policy 1, policy_version 64150 (0.0007) -[2023-10-17 02:51:04,920][62373] Updated weights for policy 0, policy_version 64620 (0.0007) -[2023-10-17 02:51:05,156][62408] Updated weights for policy 1, policy_version 64160 (0.0008) -[2023-10-17 02:51:05,286][62373] Updated weights for policy 0, policy_version 64630 (0.0007) -[2023-10-17 02:51:05,663][62373] Updated weights for policy 0, policy_version 64640 (0.0010) -[2023-10-17 02:51:07,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 131891200. Throughput: 0: 1786.8, 1: 1741.8. Samples: 32976492. Policy #0 lag: (min: 23.0, avg: 27.5, max: 55.0) -[2023-10-17 02:51:07,215][61453] Avg episode reward: [(0, '9.670'), (1, '10.780')] -[2023-10-17 02:51:09,014][62408] Updated weights for policy 1, policy_version 64170 (0.0007) -[2023-10-17 02:51:09,383][62408] Updated weights for policy 1, policy_version 64180 (0.0008) -[2023-10-17 02:51:09,427][62373] Updated weights for policy 0, policy_version 64650 (0.0007) -[2023-10-17 02:51:09,747][62408] Updated weights for policy 1, policy_version 64190 (0.0008) -[2023-10-17 02:51:09,795][62373] Updated weights for policy 0, policy_version 64660 (0.0008) -[2023-10-17 02:51:10,170][62373] Updated weights for policy 0, policy_version 64670 (0.0008) -[2023-10-17 02:51:12,214][61453] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 131956736. Throughput: 0: 1764.0, 1: 1735.6. Samples: 32997082. Policy #0 lag: (min: 23.0, avg: 27.5, max: 55.0) -[2023-10-17 02:51:12,214][61453] Avg episode reward: [(0, '9.550'), (1, '10.710')] -[2023-10-17 02:51:13,468][62408] Updated weights for policy 1, policy_version 64200 (0.0007) -[2023-10-17 02:51:13,841][62408] Updated weights for policy 1, policy_version 64210 (0.0008) -[2023-10-17 02:51:14,099][62373] Updated weights for policy 0, policy_version 64680 (0.0009) -[2023-10-17 02:51:14,207][62408] Updated weights for policy 1, policy_version 64220 (0.0009) -[2023-10-17 02:51:14,466][62373] Updated weights for policy 0, policy_version 64690 (0.0008) -[2023-10-17 02:51:14,832][62373] Updated weights for policy 0, policy_version 64700 (0.0011) -[2023-10-17 02:51:17,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 132022272. Throughput: 0: 1753.8, 1: 1759.2. Samples: 33018922. Policy #0 lag: (min: 23.0, avg: 27.5, max: 55.0) -[2023-10-17 02:51:17,215][61453] Avg episode reward: [(0, '9.420'), (1, '10.200')] -[2023-10-17 02:51:18,177][62408] Updated weights for policy 1, policy_version 64230 (0.0009) -[2023-10-17 02:51:18,536][62408] Updated weights for policy 1, policy_version 64240 (0.0009) -[2023-10-17 02:51:18,749][62373] Updated weights for policy 0, policy_version 64710 (0.0009) -[2023-10-17 02:51:18,909][62408] Updated weights for policy 1, policy_version 64250 (0.0008) -[2023-10-17 02:51:19,124][62373] Updated weights for policy 0, policy_version 64720 (0.0008) -[2023-10-17 02:51:19,481][62373] Updated weights for policy 0, policy_version 64730 (0.0009) -[2023-10-17 02:51:22,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 132087808. Throughput: 0: 1757.8, 1: 1739.3. Samples: 33028392. Policy #0 lag: (min: 23.0, avg: 27.5, max: 55.0) -[2023-10-17 02:51:22,214][61453] Avg episode reward: [(0, '9.660'), (1, '10.420')] -[2023-10-17 02:51:22,765][62408] Updated weights for policy 1, policy_version 64260 (0.0008) -[2023-10-17 02:51:23,138][62408] Updated weights for policy 1, policy_version 64270 (0.0009) -[2023-10-17 02:51:23,249][62373] Updated weights for policy 0, policy_version 64740 (0.0009) -[2023-10-17 02:51:23,505][62408] Updated weights for policy 1, policy_version 64280 (0.0008) -[2023-10-17 02:51:23,629][62373] Updated weights for policy 0, policy_version 64750 (0.0009) -[2023-10-17 02:51:23,995][62373] Updated weights for policy 0, policy_version 64760 (0.0007) -[2023-10-17 02:51:27,177][62408] Updated weights for policy 1, policy_version 64290 (0.0007) -[2023-10-17 02:51:27,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 132153344. Throughput: 0: 1762.7, 1: 1752.8. Samples: 33050614. Policy #0 lag: (min: 23.0, avg: 27.5, max: 55.0) -[2023-10-17 02:51:27,214][61453] Avg episode reward: [(0, '9.770'), (1, '10.210')] -[2023-10-17 02:51:27,549][62408] Updated weights for policy 1, policy_version 64300 (0.0009) -[2023-10-17 02:51:27,901][62373] Updated weights for policy 0, policy_version 64770 (0.0009) -[2023-10-17 02:51:27,911][62408] Updated weights for policy 1, policy_version 64310 (0.0008) -[2023-10-17 02:51:28,270][62373] Updated weights for policy 0, policy_version 64780 (0.0008) -[2023-10-17 02:51:28,282][62408] Updated weights for policy 1, policy_version 64320 (0.0009) -[2023-10-17 02:51:28,644][62373] Updated weights for policy 0, policy_version 64790 (0.0009) -[2023-10-17 02:51:29,014][62373] Updated weights for policy 0, policy_version 64800 (0.0009) -[2023-10-17 02:51:32,172][62408] Updated weights for policy 1, policy_version 64330 (0.0008) -[2023-10-17 02:51:32,214][61453] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 132218880. Throughput: 0: 1785.2, 1: 1779.2. Samples: 33072308. Policy #0 lag: (min: 23.0, avg: 27.5, max: 55.0) -[2023-10-17 02:51:32,215][61453] Avg episode reward: [(0, '9.600'), (1, '9.900')] -[2023-10-17 02:51:32,224][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000064800_66355200.pth... -[2023-10-17 02:51:32,259][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000063168_64684032.pth -[2023-10-17 02:51:32,548][62408] Updated weights for policy 1, policy_version 64340 (0.0007) -[2023-10-17 02:51:32,785][62373] Updated weights for policy 0, policy_version 64810 (0.0008) -[2023-10-17 02:51:32,918][62408] Updated weights for policy 1, policy_version 64350 (0.0008) -[2023-10-17 02:51:32,987][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000064352_65896448.pth... -[2023-10-17 02:51:33,017][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000062688_64192512.pth -[2023-10-17 02:51:33,150][62373] Updated weights for policy 0, policy_version 64820 (0.0009) -[2023-10-17 02:51:33,519][62373] Updated weights for policy 0, policy_version 64830 (0.0008) -[2023-10-17 02:51:36,757][62408] Updated weights for policy 1, policy_version 64360 (0.0011) -[2023-10-17 02:51:37,125][62408] Updated weights for policy 1, policy_version 64370 (0.0010) -[2023-10-17 02:51:37,214][61453] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 132284416. Throughput: 0: 1763.5, 1: 1748.4. Samples: 33082118. Policy #0 lag: (min: 23.0, avg: 27.5, max: 55.0) -[2023-10-17 02:51:37,215][61453] Avg episode reward: [(0, '9.060'), (1, '10.550')] -[2023-10-17 02:51:37,423][62373] Updated weights for policy 0, policy_version 64840 (0.0007) -[2023-10-17 02:51:37,497][62408] Updated weights for policy 1, policy_version 64380 (0.0009) -[2023-10-17 02:51:37,788][62373] Updated weights for policy 0, policy_version 64850 (0.0007) -[2023-10-17 02:51:38,161][62373] Updated weights for policy 0, policy_version 64860 (0.0007) -[2023-10-17 02:51:41,422][62408] Updated weights for policy 1, policy_version 64390 (0.0008) -[2023-10-17 02:51:41,787][62408] Updated weights for policy 1, policy_version 64400 (0.0009) -[2023-10-17 02:51:42,019][62373] Updated weights for policy 0, policy_version 64870 (0.0007) -[2023-10-17 02:51:42,161][62408] Updated weights for policy 1, policy_version 64410 (0.0009) -[2023-10-17 02:51:42,214][61453] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 13995.8). Total num frames: 132349952. Throughput: 0: 1774.7, 1: 1774.0. Samples: 33103886. Policy #0 lag: (min: 23.0, avg: 27.5, max: 55.0) -[2023-10-17 02:51:42,215][61453] Avg episode reward: [(0, '8.870'), (1, '9.760')] -[2023-10-17 02:51:42,385][62373] Updated weights for policy 0, policy_version 64880 (0.0007) -[2023-10-17 02:51:42,764][62373] Updated weights for policy 0, policy_version 64890 (0.0008) -[2023-10-17 02:51:46,031][62408] Updated weights for policy 1, policy_version 64420 (0.0010) -[2023-10-17 02:51:46,389][62408] Updated weights for policy 1, policy_version 64430 (0.0010) -[2023-10-17 02:51:46,727][62373] Updated weights for policy 0, policy_version 64900 (0.0008) -[2023-10-17 02:51:46,757][62408] Updated weights for policy 1, policy_version 64440 (0.0007) -[2023-10-17 02:51:47,107][62373] Updated weights for policy 0, policy_version 64910 (0.0008) -[2023-10-17 02:51:47,214][61453] Fps is (10 sec: 16384.2, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 132448256. Throughput: 0: 1775.2, 1: 1751.6. Samples: 33123990. Policy #0 lag: (min: 23.0, avg: 27.5, max: 55.0) -[2023-10-17 02:51:47,215][61453] Avg episode reward: [(0, '9.310'), (1, '9.870')] -[2023-10-17 02:51:47,474][62373] Updated weights for policy 0, policy_version 64920 (0.0009) -[2023-10-17 02:51:50,554][62408] Updated weights for policy 1, policy_version 64450 (0.0007) -[2023-10-17 02:51:50,928][62408] Updated weights for policy 1, policy_version 64460 (0.0008) -[2023-10-17 02:51:51,218][62373] Updated weights for policy 0, policy_version 64930 (0.0010) -[2023-10-17 02:51:51,288][62408] Updated weights for policy 1, policy_version 64470 (0.0007) -[2023-10-17 02:51:51,586][62373] Updated weights for policy 0, policy_version 64940 (0.0007) -[2023-10-17 02:51:51,667][62408] Updated weights for policy 1, policy_version 64480 (0.0007) -[2023-10-17 02:51:51,946][62373] Updated weights for policy 0, policy_version 64950 (0.0009) -[2023-10-17 02:51:52,214][61453] Fps is (10 sec: 16384.3, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 132513792. Throughput: 0: 1755.7, 1: 1765.7. Samples: 33134956. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-10-17 02:51:52,214][61453] Avg episode reward: [(0, '8.930'), (1, '9.840')] -[2023-10-17 02:51:52,314][62373] Updated weights for policy 0, policy_version 64960 (0.0008) -[2023-10-17 02:51:55,353][62408] Updated weights for policy 1, policy_version 64490 (0.0008) -[2023-10-17 02:51:55,726][62408] Updated weights for policy 1, policy_version 64500 (0.0008) -[2023-10-17 02:51:56,001][62373] Updated weights for policy 0, policy_version 64970 (0.0008) -[2023-10-17 02:51:56,087][62408] Updated weights for policy 1, policy_version 64510 (0.0008) -[2023-10-17 02:51:56,364][62373] Updated weights for policy 0, policy_version 64980 (0.0009) -[2023-10-17 02:51:56,733][62373] Updated weights for policy 0, policy_version 64990 (0.0009) -[2023-10-17 02:51:57,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 132612096. Throughput: 0: 1772.6, 1: 1760.4. Samples: 33156070. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-10-17 02:51:57,215][61453] Avg episode reward: [(0, '8.820'), (1, '10.100')] -[2023-10-17 02:52:00,013][62408] Updated weights for policy 1, policy_version 64520 (0.0008) -[2023-10-17 02:52:00,389][62408] Updated weights for policy 1, policy_version 64530 (0.0007) -[2023-10-17 02:52:00,587][62373] Updated weights for policy 0, policy_version 65000 (0.0008) -[2023-10-17 02:52:00,746][62408] Updated weights for policy 1, policy_version 64540 (0.0009) -[2023-10-17 02:52:00,959][62373] Updated weights for policy 0, policy_version 65010 (0.0008) -[2023-10-17 02:52:01,329][62373] Updated weights for policy 0, policy_version 65020 (0.0010) -[2023-10-17 02:52:02,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 132677632. Throughput: 0: 1752.4, 1: 1746.8. Samples: 33176388. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-10-17 02:52:02,214][61453] Avg episode reward: [(0, '8.430'), (1, '10.220')] -[2023-10-17 02:52:04,593][62408] Updated weights for policy 1, policy_version 64550 (0.0008) -[2023-10-17 02:52:04,962][62408] Updated weights for policy 1, policy_version 64560 (0.0007) -[2023-10-17 02:52:05,227][62373] Updated weights for policy 0, policy_version 65030 (0.0009) -[2023-10-17 02:52:05,323][62408] Updated weights for policy 1, policy_version 64570 (0.0008) -[2023-10-17 02:52:05,586][62373] Updated weights for policy 0, policy_version 65040 (0.0008) -[2023-10-17 02:52:05,953][62373] Updated weights for policy 0, policy_version 65050 (0.0008) -[2023-10-17 02:52:07,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 132743168. Throughput: 0: 1782.3, 1: 1771.3. Samples: 33188302. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-10-17 02:52:07,215][61453] Avg episode reward: [(0, '8.310'), (1, '9.970')] -[2023-10-17 02:52:09,260][62408] Updated weights for policy 1, policy_version 64580 (0.0008) -[2023-10-17 02:52:09,615][62408] Updated weights for policy 1, policy_version 64590 (0.0007) -[2023-10-17 02:52:09,694][62373] Updated weights for policy 0, policy_version 65060 (0.0008) -[2023-10-17 02:52:09,986][62408] Updated weights for policy 1, policy_version 64600 (0.0007) -[2023-10-17 02:52:10,066][62373] Updated weights for policy 0, policy_version 65070 (0.0009) -[2023-10-17 02:52:10,431][62373] Updated weights for policy 0, policy_version 65080 (0.0009) -[2023-10-17 02:52:12,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 132808704. Throughput: 0: 1751.2, 1: 1749.9. Samples: 33208166. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-10-17 02:52:12,215][61453] Avg episode reward: [(0, '8.270'), (1, '10.320')] -[2023-10-17 02:52:13,821][62408] Updated weights for policy 1, policy_version 64610 (0.0008) -[2023-10-17 02:52:14,143][62373] Updated weights for policy 0, policy_version 65090 (0.0009) -[2023-10-17 02:52:14,181][62408] Updated weights for policy 1, policy_version 64620 (0.0008) -[2023-10-17 02:52:14,507][62373] Updated weights for policy 0, policy_version 65100 (0.0008) -[2023-10-17 02:52:14,546][62408] Updated weights for policy 1, policy_version 64630 (0.0009) -[2023-10-17 02:52:14,883][62373] Updated weights for policy 0, policy_version 65110 (0.0007) -[2023-10-17 02:52:14,913][62408] Updated weights for policy 1, policy_version 64640 (0.0010) -[2023-10-17 02:52:15,253][62373] Updated weights for policy 0, policy_version 65120 (0.0007) -[2023-10-17 02:52:17,214][61453] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 132874240. Throughput: 0: 1757.8, 1: 1755.4. Samples: 33230404. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-10-17 02:52:17,214][61453] Avg episode reward: [(0, '8.620'), (1, '9.770')] -[2023-10-17 02:52:18,862][62408] Updated weights for policy 1, policy_version 64650 (0.0010) -[2023-10-17 02:52:18,945][62373] Updated weights for policy 0, policy_version 65130 (0.0009) -[2023-10-17 02:52:19,236][62408] Updated weights for policy 1, policy_version 64660 (0.0008) -[2023-10-17 02:52:19,313][62373] Updated weights for policy 0, policy_version 65140 (0.0010) -[2023-10-17 02:52:19,609][62408] Updated weights for policy 1, policy_version 64670 (0.0008) -[2023-10-17 02:52:19,673][62373] Updated weights for policy 0, policy_version 65150 (0.0009) -[2023-10-17 02:52:22,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 132939776. Throughput: 0: 1759.7, 1: 1748.1. Samples: 33239968. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-10-17 02:52:22,215][61453] Avg episode reward: [(0, '8.360'), (1, '10.310')] -[2023-10-17 02:52:23,359][62373] Updated weights for policy 0, policy_version 65160 (0.0009) -[2023-10-17 02:52:23,370][62408] Updated weights for policy 1, policy_version 64680 (0.0007) -[2023-10-17 02:52:23,727][62408] Updated weights for policy 1, policy_version 64690 (0.0007) -[2023-10-17 02:52:23,733][62373] Updated weights for policy 0, policy_version 65170 (0.0009) -[2023-10-17 02:52:24,092][62408] Updated weights for policy 1, policy_version 64700 (0.0009) -[2023-10-17 02:52:24,101][62373] Updated weights for policy 0, policy_version 65180 (0.0009) -[2023-10-17 02:52:27,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 133005312. Throughput: 0: 1764.3, 1: 1752.0. Samples: 33262118. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-10-17 02:52:27,215][61453] Avg episode reward: [(0, '8.320'), (1, '10.270')] -[2023-10-17 02:52:27,956][62408] Updated weights for policy 1, policy_version 64710 (0.0009) -[2023-10-17 02:52:28,059][62373] Updated weights for policy 0, policy_version 65190 (0.0007) -[2023-10-17 02:52:28,318][62408] Updated weights for policy 1, policy_version 64720 (0.0007) -[2023-10-17 02:52:28,436][62373] Updated weights for policy 0, policy_version 65200 (0.0007) -[2023-10-17 02:52:28,690][62408] Updated weights for policy 1, policy_version 64730 (0.0007) -[2023-10-17 02:52:28,803][62373] Updated weights for policy 0, policy_version 65210 (0.0010) -[2023-10-17 02:52:32,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 133070848. Throughput: 0: 1769.7, 1: 1783.6. Samples: 33283892. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:52:32,215][61453] Avg episode reward: [(0, '8.210'), (1, '9.990')] -[2023-10-17 02:52:32,433][62408] Updated weights for policy 1, policy_version 64740 (0.0008) -[2023-10-17 02:52:32,772][62373] Updated weights for policy 0, policy_version 65220 (0.0008) -[2023-10-17 02:52:32,811][62408] Updated weights for policy 1, policy_version 64750 (0.0009) -[2023-10-17 02:52:33,158][62373] Updated weights for policy 0, policy_version 65230 (0.0009) -[2023-10-17 02:52:33,185][62408] Updated weights for policy 1, policy_version 64760 (0.0008) -[2023-10-17 02:52:33,525][62373] Updated weights for policy 0, policy_version 65240 (0.0009) -[2023-10-17 02:52:37,043][62408] Updated weights for policy 1, policy_version 64770 (0.0008) -[2023-10-17 02:52:37,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 133136384. Throughput: 0: 1758.4, 1: 1761.2. Samples: 33293340. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:52:37,214][61453] Avg episode reward: [(0, '8.310'), (1, '9.690')] -[2023-10-17 02:52:37,407][62408] Updated weights for policy 1, policy_version 64780 (0.0007) -[2023-10-17 02:52:37,460][62373] Updated weights for policy 0, policy_version 65250 (0.0009) -[2023-10-17 02:52:37,776][62408] Updated weights for policy 1, policy_version 64790 (0.0007) -[2023-10-17 02:52:37,831][62373] Updated weights for policy 0, policy_version 65260 (0.0007) -[2023-10-17 02:52:38,138][62408] Updated weights for policy 1, policy_version 64800 (0.0008) -[2023-10-17 02:52:38,190][62373] Updated weights for policy 0, policy_version 65270 (0.0007) -[2023-10-17 02:52:38,557][62373] Updated weights for policy 0, policy_version 65280 (0.0008) -[2023-10-17 02:52:41,928][62408] Updated weights for policy 1, policy_version 64810 (0.0009) -[2023-10-17 02:52:42,214][61453] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 133201920. Throughput: 0: 1757.5, 1: 1777.2. Samples: 33315130. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:52:42,214][61453] Avg episode reward: [(0, '7.890'), (1, '9.310')] -[2023-10-17 02:52:42,292][62408] Updated weights for policy 1, policy_version 64820 (0.0008) -[2023-10-17 02:52:42,346][62373] Updated weights for policy 0, policy_version 65290 (0.0008) -[2023-10-17 02:52:42,662][62408] Updated weights for policy 1, policy_version 64830 (0.0007) -[2023-10-17 02:52:42,716][62373] Updated weights for policy 0, policy_version 65300 (0.0010) -[2023-10-17 02:52:43,087][62373] Updated weights for policy 0, policy_version 65310 (0.0008) -[2023-10-17 02:52:46,512][62408] Updated weights for policy 1, policy_version 64840 (0.0007) -[2023-10-17 02:52:46,872][62373] Updated weights for policy 0, policy_version 65320 (0.0010) -[2023-10-17 02:52:46,878][62408] Updated weights for policy 1, policy_version 64850 (0.0007) -[2023-10-17 02:52:47,214][61453] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 13995.8). Total num frames: 133267456. Throughput: 0: 1781.2, 1: 1770.6. Samples: 33336222. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:52:47,214][61453] Avg episode reward: [(0, '8.310'), (1, '9.330')] -[2023-10-17 02:52:47,234][62373] Updated weights for policy 0, policy_version 65330 (0.0010) -[2023-10-17 02:52:47,243][62408] Updated weights for policy 1, policy_version 64860 (0.0008) -[2023-10-17 02:52:47,598][62373] Updated weights for policy 0, policy_version 65340 (0.0008) -[2023-10-17 02:52:50,979][62408] Updated weights for policy 1, policy_version 64870 (0.0009) -[2023-10-17 02:52:51,346][62408] Updated weights for policy 1, policy_version 64880 (0.0007) -[2023-10-17 02:52:51,459][62373] Updated weights for policy 0, policy_version 65350 (0.0008) -[2023-10-17 02:52:51,711][62408] Updated weights for policy 1, policy_version 64890 (0.0007) -[2023-10-17 02:52:51,822][62373] Updated weights for policy 0, policy_version 65360 (0.0008) -[2023-10-17 02:52:52,196][62373] Updated weights for policy 0, policy_version 65370 (0.0007) -[2023-10-17 02:52:52,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 133365760. Throughput: 0: 1760.1, 1: 1767.5. Samples: 33347040. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:52:52,214][61453] Avg episode reward: [(0, '8.940'), (1, '9.510')] -[2023-10-17 02:52:55,450][62408] Updated weights for policy 1, policy_version 64900 (0.0007) -[2023-10-17 02:52:55,817][62408] Updated weights for policy 1, policy_version 64910 (0.0008) -[2023-10-17 02:52:55,959][62373] Updated weights for policy 0, policy_version 65380 (0.0007) -[2023-10-17 02:52:56,186][62408] Updated weights for policy 1, policy_version 64920 (0.0007) -[2023-10-17 02:52:56,323][62373] Updated weights for policy 0, policy_version 65390 (0.0008) -[2023-10-17 02:52:56,697][62373] Updated weights for policy 0, policy_version 65400 (0.0007) -[2023-10-17 02:52:57,214][61453] Fps is (10 sec: 19660.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 133464064. Throughput: 0: 1788.6, 1: 1780.0. Samples: 33368756. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:52:57,215][61453] Avg episode reward: [(0, '9.770'), (1, '9.580')] -[2023-10-17 02:53:00,131][62408] Updated weights for policy 1, policy_version 64930 (0.0008) -[2023-10-17 02:53:00,499][62408] Updated weights for policy 1, policy_version 64940 (0.0011) -[2023-10-17 02:53:00,567][62373] Updated weights for policy 0, policy_version 65410 (0.0007) -[2023-10-17 02:53:00,870][62408] Updated weights for policy 1, policy_version 64950 (0.0008) -[2023-10-17 02:53:00,937][62373] Updated weights for policy 0, policy_version 65420 (0.0007) -[2023-10-17 02:53:01,229][62408] Updated weights for policy 1, policy_version 64960 (0.0007) -[2023-10-17 02:53:01,311][62373] Updated weights for policy 0, policy_version 65430 (0.0008) -[2023-10-17 02:53:01,684][62373] Updated weights for policy 0, policy_version 65440 (0.0009) -[2023-10-17 02:53:02,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 133529600. Throughput: 0: 1753.5, 1: 1758.8. Samples: 33388458. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:53:02,214][61453] Avg episode reward: [(0, '10.010'), (1, '9.680')] -[2023-10-17 02:53:05,157][62408] Updated weights for policy 1, policy_version 64970 (0.0009) -[2023-10-17 02:53:05,466][62373] Updated weights for policy 0, policy_version 65450 (0.0007) -[2023-10-17 02:53:05,518][62408] Updated weights for policy 1, policy_version 64980 (0.0009) -[2023-10-17 02:53:05,837][62373] Updated weights for policy 0, policy_version 65460 (0.0008) -[2023-10-17 02:53:05,889][62408] Updated weights for policy 1, policy_version 64990 (0.0009) -[2023-10-17 02:53:06,212][62373] Updated weights for policy 0, policy_version 65470 (0.0011) -[2023-10-17 02:53:07,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 133595136. Throughput: 0: 1786.3, 1: 1788.6. Samples: 33400838. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:53:07,215][61453] Avg episode reward: [(0, '10.030'), (1, '10.240')] -[2023-10-17 02:53:09,810][62408] Updated weights for policy 1, policy_version 65000 (0.0008) -[2023-10-17 02:53:10,080][62373] Updated weights for policy 0, policy_version 65480 (0.0008) -[2023-10-17 02:53:10,186][62408] Updated weights for policy 1, policy_version 65010 (0.0009) -[2023-10-17 02:53:10,456][62373] Updated weights for policy 0, policy_version 65490 (0.0008) -[2023-10-17 02:53:10,549][62408] Updated weights for policy 1, policy_version 65020 (0.0008) -[2023-10-17 02:53:10,813][62373] Updated weights for policy 0, policy_version 65500 (0.0010) -[2023-10-17 02:53:12,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 133660672. Throughput: 0: 1753.7, 1: 1752.7. Samples: 33419906. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-10-17 02:53:12,214][61453] Avg episode reward: [(0, '9.910'), (1, '10.480')] -[2023-10-17 02:53:14,445][62408] Updated weights for policy 1, policy_version 65030 (0.0008) -[2023-10-17 02:53:14,737][62373] Updated weights for policy 0, policy_version 65510 (0.0009) -[2023-10-17 02:53:14,810][62408] Updated weights for policy 1, policy_version 65040 (0.0008) -[2023-10-17 02:53:15,103][62373] Updated weights for policy 0, policy_version 65520 (0.0010) -[2023-10-17 02:53:15,182][62408] Updated weights for policy 1, policy_version 65050 (0.0008) -[2023-10-17 02:53:15,479][62373] Updated weights for policy 0, policy_version 65530 (0.0009) -[2023-10-17 02:53:17,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 133726208. Throughput: 0: 1759.7, 1: 1747.8. Samples: 33441730. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-10-17 02:53:17,215][61453] Avg episode reward: [(0, '10.440'), (1, '11.120')] -[2023-10-17 02:53:18,966][62408] Updated weights for policy 1, policy_version 65060 (0.0008) -[2023-10-17 02:53:19,238][62373] Updated weights for policy 0, policy_version 65540 (0.0009) -[2023-10-17 02:53:19,328][62408] Updated weights for policy 1, policy_version 65070 (0.0009) -[2023-10-17 02:53:19,603][62373] Updated weights for policy 0, policy_version 65550 (0.0009) -[2023-10-17 02:53:19,705][62408] Updated weights for policy 1, policy_version 65080 (0.0009) -[2023-10-17 02:53:19,973][62373] Updated weights for policy 0, policy_version 65560 (0.0008) -[2023-10-17 02:53:22,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 133791744. Throughput: 0: 1774.9, 1: 1753.4. Samples: 33452116. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-10-17 02:53:22,215][61453] Avg episode reward: [(0, '10.210'), (1, '10.660')] -[2023-10-17 02:53:23,516][62408] Updated weights for policy 1, policy_version 65090 (0.0007) -[2023-10-17 02:53:23,750][62373] Updated weights for policy 0, policy_version 65570 (0.0007) -[2023-10-17 02:53:23,883][62408] Updated weights for policy 1, policy_version 65100 (0.0008) -[2023-10-17 02:53:24,119][62373] Updated weights for policy 0, policy_version 65580 (0.0007) -[2023-10-17 02:53:24,243][62408] Updated weights for policy 1, policy_version 65110 (0.0008) -[2023-10-17 02:53:24,490][62373] Updated weights for policy 0, policy_version 65590 (0.0009) -[2023-10-17 02:53:24,613][62408] Updated weights for policy 1, policy_version 65120 (0.0007) -[2023-10-17 02:53:24,857][62373] Updated weights for policy 0, policy_version 65600 (0.0010) -[2023-10-17 02:53:27,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 133857280. Throughput: 0: 1766.7, 1: 1751.2. Samples: 33473438. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-10-17 02:53:27,215][61453] Avg episode reward: [(0, '10.500'), (1, '10.930')] -[2023-10-17 02:53:28,387][62408] Updated weights for policy 1, policy_version 65130 (0.0007) -[2023-10-17 02:53:28,755][62408] Updated weights for policy 1, policy_version 65140 (0.0009) -[2023-10-17 02:53:28,773][62373] Updated weights for policy 0, policy_version 65610 (0.0008) -[2023-10-17 02:53:29,113][62408] Updated weights for policy 1, policy_version 65150 (0.0007) -[2023-10-17 02:53:29,139][62373] Updated weights for policy 0, policy_version 65620 (0.0008) -[2023-10-17 02:53:29,519][62373] Updated weights for policy 0, policy_version 65630 (0.0009) -[2023-10-17 02:53:32,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 133922816. Throughput: 0: 1774.5, 1: 1769.2. Samples: 33495692. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-10-17 02:53:32,215][61453] Avg episode reward: [(0, '9.890'), (1, '10.940')] -[2023-10-17 02:53:32,228][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000065632_67207168.pth... -[2023-10-17 02:53:32,229][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000065152_66715648.pth... -[2023-10-17 02:53:32,260][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000063520_65044480.pth -[2023-10-17 02:53:32,268][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000064000_65536000.pth -[2023-10-17 02:53:32,847][62408] Updated weights for policy 1, policy_version 65160 (0.0009) -[2023-10-17 02:53:33,201][62373] Updated weights for policy 0, policy_version 65640 (0.0009) -[2023-10-17 02:53:33,224][62408] Updated weights for policy 1, policy_version 65170 (0.0007) -[2023-10-17 02:53:33,559][62373] Updated weights for policy 0, policy_version 65650 (0.0009) -[2023-10-17 02:53:33,583][62408] Updated weights for policy 1, policy_version 65180 (0.0007) -[2023-10-17 02:53:33,932][62373] Updated weights for policy 0, policy_version 65660 (0.0008) -[2023-10-17 02:53:37,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 133988352. Throughput: 0: 1764.2, 1: 1751.5. Samples: 33505246. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-10-17 02:53:37,215][61453] Avg episode reward: [(0, '9.710'), (1, '9.980')] -[2023-10-17 02:53:37,460][62408] Updated weights for policy 1, policy_version 65190 (0.0008) -[2023-10-17 02:53:37,666][62373] Updated weights for policy 0, policy_version 65670 (0.0008) -[2023-10-17 02:53:37,815][62408] Updated weights for policy 1, policy_version 65200 (0.0007) -[2023-10-17 02:53:38,035][62373] Updated weights for policy 0, policy_version 65680 (0.0007) -[2023-10-17 02:53:38,186][62408] Updated weights for policy 1, policy_version 65210 (0.0008) -[2023-10-17 02:53:38,396][62373] Updated weights for policy 0, policy_version 65690 (0.0009) -[2023-10-17 02:53:42,066][62408] Updated weights for policy 1, policy_version 65220 (0.0009) -[2023-10-17 02:53:42,214][61453] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 134053888. Throughput: 0: 1768.4, 1: 1753.6. Samples: 33527244. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-10-17 02:53:42,214][61453] Avg episode reward: [(0, '9.780'), (1, '9.680')] -[2023-10-17 02:53:42,220][62373] Updated weights for policy 0, policy_version 65700 (0.0009) -[2023-10-17 02:53:42,428][62408] Updated weights for policy 1, policy_version 65230 (0.0008) -[2023-10-17 02:53:42,586][62373] Updated weights for policy 0, policy_version 65710 (0.0009) -[2023-10-17 02:53:42,795][62408] Updated weights for policy 1, policy_version 65240 (0.0007) -[2023-10-17 02:53:42,956][62373] Updated weights for policy 0, policy_version 65720 (0.0007) -[2023-10-17 02:53:46,777][62408] Updated weights for policy 1, policy_version 65250 (0.0007) -[2023-10-17 02:53:46,878][62373] Updated weights for policy 0, policy_version 65730 (0.0008) -[2023-10-17 02:53:47,146][62408] Updated weights for policy 1, policy_version 65260 (0.0008) -[2023-10-17 02:53:47,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 134119424. Throughput: 0: 1789.8, 1: 1771.6. Samples: 33548720. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-10-17 02:53:47,215][61453] Avg episode reward: [(0, '10.180'), (1, '9.790')] -[2023-10-17 02:53:47,261][62373] Updated weights for policy 0, policy_version 65740 (0.0008) -[2023-10-17 02:53:47,503][62408] Updated weights for policy 1, policy_version 65270 (0.0008) -[2023-10-17 02:53:47,628][62373] Updated weights for policy 0, policy_version 65750 (0.0008) -[2023-10-17 02:53:47,873][62408] Updated weights for policy 1, policy_version 65280 (0.0007) -[2023-10-17 02:53:47,994][62373] Updated weights for policy 0, policy_version 65760 (0.0007) -[2023-10-17 02:53:51,817][62408] Updated weights for policy 1, policy_version 65290 (0.0007) -[2023-10-17 02:53:51,840][62373] Updated weights for policy 0, policy_version 65770 (0.0008) -[2023-10-17 02:53:52,192][62408] Updated weights for policy 1, policy_version 65300 (0.0009) -[2023-10-17 02:53:52,208][62373] Updated weights for policy 0, policy_version 65780 (0.0009) -[2023-10-17 02:53:52,214][61453] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 13995.8). Total num frames: 134184960. Throughput: 0: 1758.3, 1: 1748.2. Samples: 33558628. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-10-17 02:53:52,215][61453] Avg episode reward: [(0, '10.490'), (1, '10.060')] -[2023-10-17 02:53:52,568][62408] Updated weights for policy 1, policy_version 65310 (0.0009) -[2023-10-17 02:53:52,570][62373] Updated weights for policy 0, policy_version 65790 (0.0008) -[2023-10-17 02:53:56,385][62373] Updated weights for policy 0, policy_version 65800 (0.0008) -[2023-10-17 02:53:56,414][62408] Updated weights for policy 1, policy_version 65320 (0.0009) -[2023-10-17 02:53:56,760][62373] Updated weights for policy 0, policy_version 65810 (0.0008) -[2023-10-17 02:53:56,776][62408] Updated weights for policy 1, policy_version 65330 (0.0009) -[2023-10-17 02:53:57,131][62373] Updated weights for policy 0, policy_version 65820 (0.0007) -[2023-10-17 02:53:57,147][62408] Updated weights for policy 1, policy_version 65340 (0.0009) -[2023-10-17 02:53:57,214][61453] Fps is (10 sec: 13107.5, 60 sec: 13107.2, 300 sec: 13995.8). Total num frames: 134250496. Throughput: 0: 1788.0, 1: 1778.9. Samples: 33580416. Policy #0 lag: (min: 2.0, avg: 6.5, max: 34.0) -[2023-10-17 02:53:57,214][61453] Avg episode reward: [(0, '10.260'), (1, '10.210')] -[2023-10-17 02:54:00,825][62373] Updated weights for policy 0, policy_version 65830 (0.0008) -[2023-10-17 02:54:01,160][62408] Updated weights for policy 1, policy_version 65350 (0.0009) -[2023-10-17 02:54:01,199][62373] Updated weights for policy 0, policy_version 65840 (0.0008) -[2023-10-17 02:54:01,524][62408] Updated weights for policy 1, policy_version 65360 (0.0009) -[2023-10-17 02:54:01,560][62373] Updated weights for policy 0, policy_version 65850 (0.0009) -[2023-10-17 02:54:01,905][62408] Updated weights for policy 1, policy_version 65370 (0.0009) -[2023-10-17 02:54:02,214][61453] Fps is (10 sec: 19661.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 134381568. Throughput: 0: 1766.4, 1: 1753.4. Samples: 33600118. Policy #0 lag: (min: 2.0, avg: 6.5, max: 34.0) -[2023-10-17 02:54:02,215][61453] Avg episode reward: [(0, '10.740'), (1, '10.370')] -[2023-10-17 02:54:05,406][62373] Updated weights for policy 0, policy_version 65860 (0.0008) -[2023-10-17 02:54:05,615][62408] Updated weights for policy 1, policy_version 65380 (0.0009) -[2023-10-17 02:54:05,795][62373] Updated weights for policy 0, policy_version 65870 (0.0008) -[2023-10-17 02:54:05,972][62408] Updated weights for policy 1, policy_version 65390 (0.0008) -[2023-10-17 02:54:06,160][62373] Updated weights for policy 0, policy_version 65880 (0.0007) -[2023-10-17 02:54:06,334][62408] Updated weights for policy 1, policy_version 65400 (0.0008) -[2023-10-17 02:54:07,214][61453] Fps is (10 sec: 19660.4, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 134447104. Throughput: 0: 1786.1, 1: 1770.7. Samples: 33612172. Policy #0 lag: (min: 2.0, avg: 6.5, max: 34.0) -[2023-10-17 02:54:07,215][61453] Avg episode reward: [(0, '10.630'), (1, '10.450')] -[2023-10-17 02:54:09,935][62373] Updated weights for policy 0, policy_version 65890 (0.0008) -[2023-10-17 02:54:10,306][62373] Updated weights for policy 0, policy_version 65900 (0.0007) -[2023-10-17 02:54:10,341][62408] Updated weights for policy 1, policy_version 65410 (0.0009) -[2023-10-17 02:54:10,671][62373] Updated weights for policy 0, policy_version 65910 (0.0009) -[2023-10-17 02:54:10,710][62408] Updated weights for policy 1, policy_version 65420 (0.0009) -[2023-10-17 02:54:11,042][62373] Updated weights for policy 0, policy_version 65920 (0.0007) -[2023-10-17 02:54:11,073][62408] Updated weights for policy 1, policy_version 65430 (0.0008) -[2023-10-17 02:54:11,434][62408] Updated weights for policy 1, policy_version 65440 (0.0009) -[2023-10-17 02:54:12,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 134512640. Throughput: 0: 1770.4, 1: 1756.7. Samples: 33632160. Policy #0 lag: (min: 2.0, avg: 6.5, max: 34.0) -[2023-10-17 02:54:12,215][61453] Avg episode reward: [(0, '10.050'), (1, '9.900')] -[2023-10-17 02:54:14,765][62373] Updated weights for policy 0, policy_version 65930 (0.0008) -[2023-10-17 02:54:15,135][62373] Updated weights for policy 0, policy_version 65940 (0.0008) -[2023-10-17 02:54:15,283][62408] Updated weights for policy 1, policy_version 65450 (0.0007) -[2023-10-17 02:54:15,498][62373] Updated weights for policy 0, policy_version 65950 (0.0008) -[2023-10-17 02:54:15,644][62408] Updated weights for policy 1, policy_version 65460 (0.0010) -[2023-10-17 02:54:16,014][62408] Updated weights for policy 1, policy_version 65470 (0.0007) -[2023-10-17 02:54:17,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 134578176. Throughput: 0: 1761.6, 1: 1737.7. Samples: 33653162. Policy #0 lag: (min: 2.0, avg: 6.5, max: 34.0) -[2023-10-17 02:54:17,215][61453] Avg episode reward: [(0, '9.770'), (1, '11.040')] -[2023-10-17 02:54:19,280][62373] Updated weights for policy 0, policy_version 65960 (0.0010) -[2023-10-17 02:54:19,653][62373] Updated weights for policy 0, policy_version 65970 (0.0010) -[2023-10-17 02:54:19,766][62408] Updated weights for policy 1, policy_version 65480 (0.0007) -[2023-10-17 02:54:20,019][62373] Updated weights for policy 0, policy_version 65980 (0.0008) -[2023-10-17 02:54:20,133][62408] Updated weights for policy 1, policy_version 65490 (0.0008) -[2023-10-17 02:54:20,509][62408] Updated weights for policy 1, policy_version 65500 (0.0009) -[2023-10-17 02:54:22,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 134643712. Throughput: 0: 1771.5, 1: 1760.8. Samples: 33664200. Policy #0 lag: (min: 2.0, avg: 6.5, max: 34.0) -[2023-10-17 02:54:22,215][61453] Avg episode reward: [(0, '9.900'), (1, '11.110')] -[2023-10-17 02:54:23,807][62373] Updated weights for policy 0, policy_version 65990 (0.0009) -[2023-10-17 02:54:24,186][62373] Updated weights for policy 0, policy_version 66000 (0.0011) -[2023-10-17 02:54:24,292][62408] Updated weights for policy 1, policy_version 65510 (0.0007) -[2023-10-17 02:54:24,553][62373] Updated weights for policy 0, policy_version 66010 (0.0009) -[2023-10-17 02:54:24,658][62408] Updated weights for policy 1, policy_version 65520 (0.0007) -[2023-10-17 02:54:25,028][62408] Updated weights for policy 1, policy_version 65530 (0.0007) -[2023-10-17 02:54:27,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 134709248. Throughput: 0: 1763.3, 1: 1747.8. Samples: 33685246. Policy #0 lag: (min: 2.0, avg: 6.5, max: 34.0) -[2023-10-17 02:54:27,215][61453] Avg episode reward: [(0, '10.100'), (1, '10.760')] -[2023-10-17 02:54:28,368][62373] Updated weights for policy 0, policy_version 66020 (0.0007) -[2023-10-17 02:54:28,735][62373] Updated weights for policy 0, policy_version 66030 (0.0007) -[2023-10-17 02:54:28,881][62408] Updated weights for policy 1, policy_version 65540 (0.0007) -[2023-10-17 02:54:29,095][62373] Updated weights for policy 0, policy_version 66040 (0.0007) -[2023-10-17 02:54:29,252][62408] Updated weights for policy 1, policy_version 65550 (0.0007) -[2023-10-17 02:54:29,627][62408] Updated weights for policy 1, policy_version 65560 (0.0011) -[2023-10-17 02:54:32,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 134774784. Throughput: 0: 1779.3, 1: 1750.1. Samples: 33707542. Policy #0 lag: (min: 2.0, avg: 6.5, max: 34.0) -[2023-10-17 02:54:32,214][61453] Avg episode reward: [(0, '9.850'), (1, '11.090')] -[2023-10-17 02:54:32,739][62373] Updated weights for policy 0, policy_version 66050 (0.0008) -[2023-10-17 02:54:33,115][62373] Updated weights for policy 0, policy_version 66060 (0.0007) -[2023-10-17 02:54:33,485][62408] Updated weights for policy 1, policy_version 65570 (0.0011) -[2023-10-17 02:54:33,487][62373] Updated weights for policy 0, policy_version 66070 (0.0007) -[2023-10-17 02:54:33,849][62373] Updated weights for policy 0, policy_version 66080 (0.0007) -[2023-10-17 02:54:33,854][62408] Updated weights for policy 1, policy_version 65580 (0.0009) -[2023-10-17 02:54:34,225][62408] Updated weights for policy 1, policy_version 65590 (0.0009) -[2023-10-17 02:54:34,579][62408] Updated weights for policy 1, policy_version 65600 (0.0010) -[2023-10-17 02:54:37,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 134840320. Throughput: 0: 1780.4, 1: 1741.8. Samples: 33717124. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:54:37,214][61453] Avg episode reward: [(0, '9.440'), (1, '10.570')] -[2023-10-17 02:54:37,644][62373] Updated weights for policy 0, policy_version 66090 (0.0008) -[2023-10-17 02:54:38,016][62373] Updated weights for policy 0, policy_version 66100 (0.0008) -[2023-10-17 02:54:38,379][62373] Updated weights for policy 0, policy_version 66110 (0.0008) -[2023-10-17 02:54:38,411][62408] Updated weights for policy 1, policy_version 65610 (0.0008) -[2023-10-17 02:54:38,772][62408] Updated weights for policy 1, policy_version 65620 (0.0008) -[2023-10-17 02:54:39,147][62408] Updated weights for policy 1, policy_version 65630 (0.0008) -[2023-10-17 02:54:42,156][62373] Updated weights for policy 0, policy_version 66120 (0.0007) -[2023-10-17 02:54:42,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 134905856. Throughput: 0: 1780.9, 1: 1745.4. Samples: 33739100. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:54:42,214][61453] Avg episode reward: [(0, '8.790'), (1, '10.820')] -[2023-10-17 02:54:42,512][62373] Updated weights for policy 0, policy_version 66130 (0.0007) -[2023-10-17 02:54:42,890][62373] Updated weights for policy 0, policy_version 66140 (0.0007) -[2023-10-17 02:54:42,985][62408] Updated weights for policy 1, policy_version 65640 (0.0008) -[2023-10-17 02:54:43,359][62408] Updated weights for policy 1, policy_version 65650 (0.0007) -[2023-10-17 02:54:43,732][62408] Updated weights for policy 1, policy_version 65660 (0.0010) -[2023-10-17 02:54:46,551][62373] Updated weights for policy 0, policy_version 66150 (0.0009) -[2023-10-17 02:54:46,926][62373] Updated weights for policy 0, policy_version 66160 (0.0009) -[2023-10-17 02:54:47,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 134971392. Throughput: 0: 1795.1, 1: 1766.6. Samples: 33760394. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:54:47,215][61453] Avg episode reward: [(0, '9.210'), (1, '10.530')] -[2023-10-17 02:54:47,285][62373] Updated weights for policy 0, policy_version 66170 (0.0007) -[2023-10-17 02:54:47,620][62408] Updated weights for policy 1, policy_version 65670 (0.0007) -[2023-10-17 02:54:47,992][62408] Updated weights for policy 1, policy_version 65680 (0.0007) -[2023-10-17 02:54:48,361][62408] Updated weights for policy 1, policy_version 65690 (0.0007) -[2023-10-17 02:54:51,108][62373] Updated weights for policy 0, policy_version 66180 (0.0007) -[2023-10-17 02:54:51,502][62373] Updated weights for policy 0, policy_version 66190 (0.0008) -[2023-10-17 02:54:51,878][62373] Updated weights for policy 0, policy_version 66200 (0.0007) -[2023-10-17 02:54:52,096][62408] Updated weights for policy 1, policy_version 65700 (0.0008) -[2023-10-17 02:54:52,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14106.9). Total num frames: 135069696. Throughput: 0: 1782.9, 1: 1742.9. Samples: 33770834. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:54:52,215][61453] Avg episode reward: [(0, '9.630'), (1, '10.250')] -[2023-10-17 02:54:52,473][62408] Updated weights for policy 1, policy_version 65710 (0.0009) -[2023-10-17 02:54:52,845][62408] Updated weights for policy 1, policy_version 65720 (0.0008) -[2023-10-17 02:54:55,638][62373] Updated weights for policy 0, policy_version 66210 (0.0007) -[2023-10-17 02:54:56,007][62373] Updated weights for policy 0, policy_version 66220 (0.0008) -[2023-10-17 02:54:56,376][62373] Updated weights for policy 0, policy_version 66230 (0.0008) -[2023-10-17 02:54:56,717][62408] Updated weights for policy 1, policy_version 65730 (0.0009) -[2023-10-17 02:54:56,751][62373] Updated weights for policy 0, policy_version 66240 (0.0007) -[2023-10-17 02:54:57,083][62408] Updated weights for policy 1, policy_version 65740 (0.0008) -[2023-10-17 02:54:57,214][61453] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14106.9). Total num frames: 135135232. Throughput: 0: 1800.3, 1: 1763.7. Samples: 33792540. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:54:57,214][61453] Avg episode reward: [(0, '9.220'), (1, '10.210')] -[2023-10-17 02:54:57,458][62408] Updated weights for policy 1, policy_version 65750 (0.0007) -[2023-10-17 02:54:57,832][62408] Updated weights for policy 1, policy_version 65760 (0.0008) -[2023-10-17 02:55:00,589][62373] Updated weights for policy 0, policy_version 66250 (0.0010) -[2023-10-17 02:55:00,955][62373] Updated weights for policy 0, policy_version 66260 (0.0007) -[2023-10-17 02:55:01,328][62373] Updated weights for policy 0, policy_version 66270 (0.0009) -[2023-10-17 02:55:01,525][62408] Updated weights for policy 1, policy_version 65770 (0.0010) -[2023-10-17 02:55:01,884][62408] Updated weights for policy 1, policy_version 65780 (0.0011) -[2023-10-17 02:55:02,214][61453] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 135200768. Throughput: 0: 1784.3, 1: 1768.0. Samples: 33813018. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:55:02,215][61453] Avg episode reward: [(0, '8.870'), (1, '10.350')] -[2023-10-17 02:55:02,254][62408] Updated weights for policy 1, policy_version 65790 (0.0009) -[2023-10-17 02:55:05,191][62373] Updated weights for policy 0, policy_version 66280 (0.0009) -[2023-10-17 02:55:05,554][62373] Updated weights for policy 0, policy_version 66290 (0.0008) -[2023-10-17 02:55:05,918][62373] Updated weights for policy 0, policy_version 66300 (0.0008) -[2023-10-17 02:55:06,048][62408] Updated weights for policy 1, policy_version 65800 (0.0008) -[2023-10-17 02:55:06,423][62408] Updated weights for policy 1, policy_version 65810 (0.0011) -[2023-10-17 02:55:06,783][62408] Updated weights for policy 1, policy_version 65820 (0.0010) -[2023-10-17 02:55:07,214][61453] Fps is (10 sec: 16383.5, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 135299072. Throughput: 0: 1802.7, 1: 1763.4. Samples: 33824674. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:55:07,216][61453] Avg episode reward: [(0, '9.220'), (1, '10.520')] -[2023-10-17 02:55:09,768][62373] Updated weights for policy 0, policy_version 66310 (0.0008) -[2023-10-17 02:55:10,132][62373] Updated weights for policy 0, policy_version 66320 (0.0008) -[2023-10-17 02:55:10,465][62408] Updated weights for policy 1, policy_version 65830 (0.0009) -[2023-10-17 02:55:10,502][62373] Updated weights for policy 0, policy_version 66330 (0.0008) -[2023-10-17 02:55:10,829][62408] Updated weights for policy 1, policy_version 65840 (0.0008) -[2023-10-17 02:55:11,205][62408] Updated weights for policy 1, policy_version 65850 (0.0008) -[2023-10-17 02:55:12,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 135364608. Throughput: 0: 1774.2, 1: 1770.3. Samples: 33844750. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:55:12,215][61453] Avg episode reward: [(0, '10.480'), (1, '10.250')] -[2023-10-17 02:55:14,370][62373] Updated weights for policy 0, policy_version 66340 (0.0008) -[2023-10-17 02:55:14,742][62373] Updated weights for policy 0, policy_version 66350 (0.0007) -[2023-10-17 02:55:15,085][62408] Updated weights for policy 1, policy_version 65860 (0.0007) -[2023-10-17 02:55:15,108][62373] Updated weights for policy 0, policy_version 66360 (0.0008) -[2023-10-17 02:55:15,449][62408] Updated weights for policy 1, policy_version 65870 (0.0008) -[2023-10-17 02:55:15,812][62408] Updated weights for policy 1, policy_version 65880 (0.0010) -[2023-10-17 02:55:17,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 135430144. Throughput: 0: 1768.3, 1: 1753.7. Samples: 33866030. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:55:17,215][61453] Avg episode reward: [(0, '9.810'), (1, '10.390')] -[2023-10-17 02:55:18,874][62373] Updated weights for policy 0, policy_version 66370 (0.0007) -[2023-10-17 02:55:19,234][62373] Updated weights for policy 0, policy_version 66380 (0.0009) -[2023-10-17 02:55:19,604][62373] Updated weights for policy 0, policy_version 66390 (0.0008) -[2023-10-17 02:55:19,662][62408] Updated weights for policy 1, policy_version 65890 (0.0009) -[2023-10-17 02:55:19,976][62373] Updated weights for policy 0, policy_version 66400 (0.0007) -[2023-10-17 02:55:20,027][62408] Updated weights for policy 1, policy_version 65900 (0.0007) -[2023-10-17 02:55:20,399][62408] Updated weights for policy 1, policy_version 65910 (0.0009) -[2023-10-17 02:55:20,765][62408] Updated weights for policy 1, policy_version 65920 (0.0008) -[2023-10-17 02:55:22,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 135495680. Throughput: 0: 1767.1, 1: 1784.3. Samples: 33876938. Policy #0 lag: (min: 28.0, avg: 29.3, max: 52.0) -[2023-10-17 02:55:22,215][61453] Avg episode reward: [(0, '10.180'), (1, '10.800')] -[2023-10-17 02:55:23,708][62373] Updated weights for policy 0, policy_version 66410 (0.0012) -[2023-10-17 02:55:24,079][62373] Updated weights for policy 0, policy_version 66420 (0.0010) -[2023-10-17 02:55:24,438][62373] Updated weights for policy 0, policy_version 66430 (0.0011) -[2023-10-17 02:55:24,697][62408] Updated weights for policy 1, policy_version 65930 (0.0009) -[2023-10-17 02:55:25,065][62408] Updated weights for policy 1, policy_version 65940 (0.0008) -[2023-10-17 02:55:25,431][62408] Updated weights for policy 1, policy_version 65950 (0.0007) -[2023-10-17 02:55:27,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 135561216. Throughput: 0: 1772.2, 1: 1759.4. Samples: 33898024. Policy #0 lag: (min: 28.0, avg: 29.3, max: 52.0) -[2023-10-17 02:55:27,215][61453] Avg episode reward: [(0, '9.460'), (1, '11.450')] -[2023-10-17 02:55:28,257][62373] Updated weights for policy 0, policy_version 66440 (0.0009) -[2023-10-17 02:55:28,632][62373] Updated weights for policy 0, policy_version 66450 (0.0009) -[2023-10-17 02:55:29,001][62373] Updated weights for policy 0, policy_version 66460 (0.0008) -[2023-10-17 02:55:29,194][62408] Updated weights for policy 1, policy_version 65960 (0.0008) -[2023-10-17 02:55:29,550][62408] Updated weights for policy 1, policy_version 65970 (0.0009) -[2023-10-17 02:55:29,916][62408] Updated weights for policy 1, policy_version 65980 (0.0009) -[2023-10-17 02:55:32,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 135626752. Throughput: 0: 1789.2, 1: 1767.1. Samples: 33920426. Policy #0 lag: (min: 28.0, avg: 29.3, max: 52.0) -[2023-10-17 02:55:32,214][61453] Avg episode reward: [(0, '9.400'), (1, '10.740')] -[2023-10-17 02:55:32,221][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000066464_68059136.pth... -[2023-10-17 02:55:32,222][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000065984_67567616.pth... -[2023-10-17 02:55:32,252][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000064800_66355200.pth -[2023-10-17 02:55:32,256][62094] Saving a milestone ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/milestones/checkpoint_000066464_68059136.pth -[2023-10-17 02:55:32,261][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000064352_65896448.pth -[2023-10-17 02:55:32,267][62252] Saving a milestone ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/milestones/checkpoint_000065984_67567616.pth -[2023-10-17 02:55:32,659][62373] Updated weights for policy 0, policy_version 66470 (0.0009) -[2023-10-17 02:55:33,031][62373] Updated weights for policy 0, policy_version 66480 (0.0009) -[2023-10-17 02:55:33,398][62373] Updated weights for policy 0, policy_version 66490 (0.0007) -[2023-10-17 02:55:33,740][62408] Updated weights for policy 1, policy_version 65990 (0.0009) -[2023-10-17 02:55:34,120][62408] Updated weights for policy 1, policy_version 66000 (0.0010) -[2023-10-17 02:55:34,481][62408] Updated weights for policy 1, policy_version 66010 (0.0009) -[2023-10-17 02:55:37,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 135692288. Throughput: 0: 1770.8, 1: 1769.9. Samples: 33930166. Policy #0 lag: (min: 28.0, avg: 29.3, max: 52.0) -[2023-10-17 02:55:37,214][61453] Avg episode reward: [(0, '8.310'), (1, '10.960')] -[2023-10-17 02:55:37,346][62373] Updated weights for policy 0, policy_version 66500 (0.0008) -[2023-10-17 02:55:37,714][62373] Updated weights for policy 0, policy_version 66510 (0.0009) -[2023-10-17 02:55:38,074][62373] Updated weights for policy 0, policy_version 66520 (0.0009) -[2023-10-17 02:55:38,333][62408] Updated weights for policy 1, policy_version 66020 (0.0009) -[2023-10-17 02:55:38,699][62408] Updated weights for policy 1, policy_version 66030 (0.0009) -[2023-10-17 02:55:39,065][62408] Updated weights for policy 1, policy_version 66040 (0.0010) -[2023-10-17 02:55:41,857][62373] Updated weights for policy 0, policy_version 66530 (0.0008) -[2023-10-17 02:55:42,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 135757824. Throughput: 0: 1781.4, 1: 1768.2. Samples: 33952272. Policy #0 lag: (min: 28.0, avg: 29.3, max: 52.0) -[2023-10-17 02:55:42,215][61453] Avg episode reward: [(0, '7.810'), (1, '10.310')] -[2023-10-17 02:55:42,223][62373] Updated weights for policy 0, policy_version 66540 (0.0011) -[2023-10-17 02:55:42,602][62373] Updated weights for policy 0, policy_version 66550 (0.0010) -[2023-10-17 02:55:42,860][62408] Updated weights for policy 1, policy_version 66050 (0.0010) -[2023-10-17 02:55:42,974][62373] Updated weights for policy 0, policy_version 66560 (0.0010) -[2023-10-17 02:55:43,229][62408] Updated weights for policy 1, policy_version 66060 (0.0008) -[2023-10-17 02:55:43,597][62408] Updated weights for policy 1, policy_version 66070 (0.0010) -[2023-10-17 02:55:43,967][62408] Updated weights for policy 1, policy_version 66080 (0.0009) -[2023-10-17 02:55:46,757][62373] Updated weights for policy 0, policy_version 66570 (0.0007) -[2023-10-17 02:55:47,139][62373] Updated weights for policy 0, policy_version 66580 (0.0008) -[2023-10-17 02:55:47,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 135823360. Throughput: 0: 1787.8, 1: 1788.4. Samples: 33973946. Policy #0 lag: (min: 28.0, avg: 29.3, max: 52.0) -[2023-10-17 02:55:47,215][61453] Avg episode reward: [(0, '7.700'), (1, '10.340')] -[2023-10-17 02:55:47,507][62373] Updated weights for policy 0, policy_version 66590 (0.0007) -[2023-10-17 02:55:47,631][62408] Updated weights for policy 1, policy_version 66090 (0.0009) -[2023-10-17 02:55:48,000][62408] Updated weights for policy 1, policy_version 66100 (0.0009) -[2023-10-17 02:55:48,378][62408] Updated weights for policy 1, policy_version 66110 (0.0011) -[2023-10-17 02:55:51,293][62373] Updated weights for policy 0, policy_version 66600 (0.0011) -[2023-10-17 02:55:51,661][62373] Updated weights for policy 0, policy_version 66610 (0.0010) -[2023-10-17 02:55:52,039][62373] Updated weights for policy 0, policy_version 66620 (0.0008) -[2023-10-17 02:55:52,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 135921664. Throughput: 0: 1775.7, 1: 1765.5. Samples: 33984028. Policy #0 lag: (min: 28.0, avg: 29.3, max: 52.0) -[2023-10-17 02:55:52,214][61453] Avg episode reward: [(0, '8.130'), (1, '9.910')] -[2023-10-17 02:55:52,250][62408] Updated weights for policy 1, policy_version 66120 (0.0008) -[2023-10-17 02:55:52,612][62408] Updated weights for policy 1, policy_version 66130 (0.0009) -[2023-10-17 02:55:52,995][62408] Updated weights for policy 1, policy_version 66140 (0.0008) -[2023-10-17 02:55:55,775][62373] Updated weights for policy 0, policy_version 66630 (0.0007) -[2023-10-17 02:55:56,145][62373] Updated weights for policy 0, policy_version 66640 (0.0008) -[2023-10-17 02:55:56,518][62373] Updated weights for policy 0, policy_version 66650 (0.0008) -[2023-10-17 02:55:56,878][62408] Updated weights for policy 1, policy_version 66150 (0.0009) -[2023-10-17 02:55:57,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 135987200. Throughput: 0: 1800.6, 1: 1784.4. Samples: 34006074. Policy #0 lag: (min: 28.0, avg: 29.3, max: 52.0) -[2023-10-17 02:55:57,214][61453] Avg episode reward: [(0, '8.700'), (1, '9.360')] -[2023-10-17 02:55:57,256][62408] Updated weights for policy 1, policy_version 66160 (0.0010) -[2023-10-17 02:55:57,621][62408] Updated weights for policy 1, policy_version 66170 (0.0010) -[2023-10-17 02:56:00,315][62373] Updated weights for policy 0, policy_version 66660 (0.0008) -[2023-10-17 02:56:00,688][62373] Updated weights for policy 0, policy_version 66670 (0.0009) -[2023-10-17 02:56:01,066][62373] Updated weights for policy 0, policy_version 66680 (0.0009) -[2023-10-17 02:56:01,409][62408] Updated weights for policy 1, policy_version 66180 (0.0009) -[2023-10-17 02:56:01,774][62408] Updated weights for policy 1, policy_version 66190 (0.0010) -[2023-10-17 02:56:02,147][62408] Updated weights for policy 1, policy_version 66200 (0.0010) -[2023-10-17 02:56:02,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 136052736. Throughput: 0: 1778.6, 1: 1790.0. Samples: 34026618. Policy #0 lag: (min: 28.0, avg: 29.3, max: 52.0) -[2023-10-17 02:56:02,215][61453] Avg episode reward: [(0, '9.090'), (1, '9.220')] -[2023-10-17 02:56:04,812][62373] Updated weights for policy 0, policy_version 66690 (0.0009) -[2023-10-17 02:56:05,194][62373] Updated weights for policy 0, policy_version 66700 (0.0010) -[2023-10-17 02:56:05,558][62373] Updated weights for policy 0, policy_version 66710 (0.0008) -[2023-10-17 02:56:05,930][62373] Updated weights for policy 0, policy_version 66720 (0.0009) -[2023-10-17 02:56:05,941][62408] Updated weights for policy 1, policy_version 66210 (0.0011) -[2023-10-17 02:56:06,310][62408] Updated weights for policy 1, policy_version 66220 (0.0009) -[2023-10-17 02:56:06,681][62408] Updated weights for policy 1, policy_version 66230 (0.0008) -[2023-10-17 02:56:07,045][62408] Updated weights for policy 1, policy_version 66240 (0.0008) -[2023-10-17 02:56:07,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 136151040. Throughput: 0: 1803.4, 1: 1780.5. Samples: 34038214. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-17 02:56:07,215][61453] Avg episode reward: [(0, '9.870'), (1, '9.490')] -[2023-10-17 02:56:09,664][62373] Updated weights for policy 0, policy_version 66730 (0.0008) -[2023-10-17 02:56:10,038][62373] Updated weights for policy 0, policy_version 66740 (0.0008) -[2023-10-17 02:56:10,409][62373] Updated weights for policy 0, policy_version 66750 (0.0007) -[2023-10-17 02:56:10,680][62408] Updated weights for policy 1, policy_version 66250 (0.0009) -[2023-10-17 02:56:11,046][62408] Updated weights for policy 1, policy_version 66260 (0.0007) -[2023-10-17 02:56:11,415][62408] Updated weights for policy 1, policy_version 66270 (0.0007) -[2023-10-17 02:56:12,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 136216576. Throughput: 0: 1769.3, 1: 1792.4. Samples: 34058302. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-17 02:56:12,215][61453] Avg episode reward: [(0, '9.620'), (1, '9.910')] -[2023-10-17 02:56:14,157][62373] Updated weights for policy 0, policy_version 66760 (0.0008) -[2023-10-17 02:56:14,530][62373] Updated weights for policy 0, policy_version 66770 (0.0009) -[2023-10-17 02:56:14,890][62373] Updated weights for policy 0, policy_version 66780 (0.0008) -[2023-10-17 02:56:15,236][62408] Updated weights for policy 1, policy_version 66280 (0.0008) -[2023-10-17 02:56:15,612][62408] Updated weights for policy 1, policy_version 66290 (0.0009) -[2023-10-17 02:56:15,983][62408] Updated weights for policy 1, policy_version 66300 (0.0007) -[2023-10-17 02:56:17,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 136282112. Throughput: 0: 1769.8, 1: 1774.8. Samples: 34079936. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-17 02:56:17,215][61453] Avg episode reward: [(0, '10.820'), (1, '10.050')] -[2023-10-17 02:56:18,710][62373] Updated weights for policy 0, policy_version 66790 (0.0008) -[2023-10-17 02:56:19,077][62373] Updated weights for policy 0, policy_version 66800 (0.0008) -[2023-10-17 02:56:19,446][62373] Updated weights for policy 0, policy_version 66810 (0.0010) -[2023-10-17 02:56:19,750][62408] Updated weights for policy 1, policy_version 66310 (0.0008) -[2023-10-17 02:56:20,116][62408] Updated weights for policy 1, policy_version 66320 (0.0009) -[2023-10-17 02:56:20,486][62408] Updated weights for policy 1, policy_version 66330 (0.0009) -[2023-10-17 02:56:22,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 136347648. Throughput: 0: 1768.3, 1: 1798.6. Samples: 34090678. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-17 02:56:22,215][61453] Avg episode reward: [(0, '11.680'), (1, '10.160')] -[2023-10-17 02:56:23,233][62373] Updated weights for policy 0, policy_version 66820 (0.0007) -[2023-10-17 02:56:23,618][62373] Updated weights for policy 0, policy_version 66830 (0.0009) -[2023-10-17 02:56:23,997][62373] Updated weights for policy 0, policy_version 66840 (0.0008) -[2023-10-17 02:56:24,170][62408] Updated weights for policy 1, policy_version 66340 (0.0009) -[2023-10-17 02:56:24,535][62408] Updated weights for policy 1, policy_version 66350 (0.0009) -[2023-10-17 02:56:24,910][62408] Updated weights for policy 1, policy_version 66360 (0.0007) -[2023-10-17 02:56:27,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 136413184. Throughput: 0: 1773.2, 1: 1776.7. Samples: 34112018. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-17 02:56:27,215][61453] Avg episode reward: [(0, '11.370'), (1, '10.070')] -[2023-10-17 02:56:27,706][62373] Updated weights for policy 0, policy_version 66850 (0.0008) -[2023-10-17 02:56:28,067][62373] Updated weights for policy 0, policy_version 66860 (0.0008) -[2023-10-17 02:56:28,432][62373] Updated weights for policy 0, policy_version 66870 (0.0008) -[2023-10-17 02:56:28,781][62408] Updated weights for policy 1, policy_version 66370 (0.0007) -[2023-10-17 02:56:28,795][62373] Updated weights for policy 0, policy_version 66880 (0.0008) -[2023-10-17 02:56:29,143][62408] Updated weights for policy 1, policy_version 66380 (0.0007) -[2023-10-17 02:56:29,505][62408] Updated weights for policy 1, policy_version 66390 (0.0007) -[2023-10-17 02:56:29,868][62408] Updated weights for policy 1, policy_version 66400 (0.0007) -[2023-10-17 02:56:32,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 136478720. Throughput: 0: 1794.2, 1: 1770.5. Samples: 34134360. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-17 02:56:32,214][61453] Avg episode reward: [(0, '11.120'), (1, '10.520')] -[2023-10-17 02:56:32,517][62373] Updated weights for policy 0, policy_version 66890 (0.0007) -[2023-10-17 02:56:32,884][62373] Updated weights for policy 0, policy_version 66900 (0.0010) -[2023-10-17 02:56:33,266][62373] Updated weights for policy 0, policy_version 66910 (0.0010) -[2023-10-17 02:56:33,763][62408] Updated weights for policy 1, policy_version 66410 (0.0007) -[2023-10-17 02:56:34,129][62408] Updated weights for policy 1, policy_version 66420 (0.0007) -[2023-10-17 02:56:34,499][62408] Updated weights for policy 1, policy_version 66430 (0.0008) -[2023-10-17 02:56:37,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 136544256. Throughput: 0: 1781.5, 1: 1775.6. Samples: 34144100. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-17 02:56:37,215][61453] Avg episode reward: [(0, '11.110'), (1, '10.630')] -[2023-10-17 02:56:37,265][62373] Updated weights for policy 0, policy_version 66920 (0.0010) -[2023-10-17 02:56:37,644][62373] Updated weights for policy 0, policy_version 66930 (0.0008) -[2023-10-17 02:56:38,007][62373] Updated weights for policy 0, policy_version 66940 (0.0009) -[2023-10-17 02:56:38,391][62408] Updated weights for policy 1, policy_version 66440 (0.0009) -[2023-10-17 02:56:38,761][62408] Updated weights for policy 1, policy_version 66450 (0.0009) -[2023-10-17 02:56:39,132][62408] Updated weights for policy 1, policy_version 66460 (0.0008) -[2023-10-17 02:56:41,723][62373] Updated weights for policy 0, policy_version 66950 (0.0008) -[2023-10-17 02:56:42,096][62373] Updated weights for policy 0, policy_version 66960 (0.0009) -[2023-10-17 02:56:42,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 136609792. Throughput: 0: 1787.1, 1: 1762.8. Samples: 34165822. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-17 02:56:42,215][61453] Avg episode reward: [(0, '11.560'), (1, '10.260')] -[2023-10-17 02:56:42,469][62373] Updated weights for policy 0, policy_version 66970 (0.0007) -[2023-10-17 02:56:42,969][62408] Updated weights for policy 1, policy_version 66470 (0.0008) -[2023-10-17 02:56:43,338][62408] Updated weights for policy 1, policy_version 66480 (0.0007) -[2023-10-17 02:56:43,715][62408] Updated weights for policy 1, policy_version 66490 (0.0007) -[2023-10-17 02:56:46,301][62373] Updated weights for policy 0, policy_version 66980 (0.0008) -[2023-10-17 02:56:46,667][62373] Updated weights for policy 0, policy_version 66990 (0.0008) -[2023-10-17 02:56:47,036][62373] Updated weights for policy 0, policy_version 67000 (0.0010) -[2023-10-17 02:56:47,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 136675328. Throughput: 0: 1790.4, 1: 1779.9. Samples: 34187280. Policy #0 lag: (min: 31.0, avg: 34.0, max: 63.0) -[2023-10-17 02:56:47,215][61453] Avg episode reward: [(0, '11.610'), (1, '9.650')] -[2023-10-17 02:56:47,550][62408] Updated weights for policy 1, policy_version 66500 (0.0007) -[2023-10-17 02:56:47,912][62408] Updated weights for policy 1, policy_version 66510 (0.0010) -[2023-10-17 02:56:48,288][62408] Updated weights for policy 1, policy_version 66520 (0.0007) -[2023-10-17 02:56:50,877][62373] Updated weights for policy 0, policy_version 67010 (0.0008) -[2023-10-17 02:56:51,246][62373] Updated weights for policy 0, policy_version 67020 (0.0007) -[2023-10-17 02:56:51,621][62373] Updated weights for policy 0, policy_version 67030 (0.0009) -[2023-10-17 02:56:51,988][62373] Updated weights for policy 0, policy_version 67040 (0.0007) -[2023-10-17 02:56:52,137][62408] Updated weights for policy 1, policy_version 66530 (0.0009) -[2023-10-17 02:56:52,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 136773632. Throughput: 0: 1781.4, 1: 1761.9. Samples: 34197660. Policy #0 lag: (min: 10.0, avg: 13.7, max: 42.0) -[2023-10-17 02:56:52,214][61453] Avg episode reward: [(0, '11.120'), (1, '10.080')] -[2023-10-17 02:56:52,506][62408] Updated weights for policy 1, policy_version 66540 (0.0010) -[2023-10-17 02:56:52,876][62408] Updated weights for policy 1, policy_version 66550 (0.0007) -[2023-10-17 02:56:53,242][62408] Updated weights for policy 1, policy_version 66560 (0.0008) -[2023-10-17 02:56:55,860][62373] Updated weights for policy 0, policy_version 67050 (0.0009) -[2023-10-17 02:56:56,234][62373] Updated weights for policy 0, policy_version 67060 (0.0007) -[2023-10-17 02:56:56,604][62373] Updated weights for policy 0, policy_version 67070 (0.0011) -[2023-10-17 02:56:57,136][62408] Updated weights for policy 1, policy_version 66570 (0.0009) -[2023-10-17 02:56:57,214][61453] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 136839168. Throughput: 0: 1797.7, 1: 1773.2. Samples: 34218992. Policy #0 lag: (min: 10.0, avg: 13.7, max: 42.0) -[2023-10-17 02:56:57,214][61453] Avg episode reward: [(0, '9.800'), (1, '10.030')] -[2023-10-17 02:56:57,509][62408] Updated weights for policy 1, policy_version 66580 (0.0008) -[2023-10-17 02:56:57,877][62408] Updated weights for policy 1, policy_version 66590 (0.0008) -[2023-10-17 02:57:00,321][62373] Updated weights for policy 0, policy_version 67080 (0.0008) -[2023-10-17 02:57:00,688][62373] Updated weights for policy 0, policy_version 67090 (0.0008) -[2023-10-17 02:57:01,050][62373] Updated weights for policy 0, policy_version 67100 (0.0007) -[2023-10-17 02:57:01,658][62408] Updated weights for policy 1, policy_version 66600 (0.0008) -[2023-10-17 02:57:02,025][62408] Updated weights for policy 1, policy_version 66610 (0.0008) -[2023-10-17 02:57:02,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 136904704. Throughput: 0: 1779.1, 1: 1775.6. Samples: 34239898. Policy #0 lag: (min: 10.0, avg: 13.7, max: 42.0) -[2023-10-17 02:57:02,214][61453] Avg episode reward: [(0, '10.280'), (1, '10.210')] -[2023-10-17 02:57:02,393][62408] Updated weights for policy 1, policy_version 66620 (0.0008) -[2023-10-17 02:57:04,887][62373] Updated weights for policy 0, policy_version 67110 (0.0008) -[2023-10-17 02:57:05,246][62373] Updated weights for policy 0, policy_version 67120 (0.0009) -[2023-10-17 02:57:05,614][62373] Updated weights for policy 0, policy_version 67130 (0.0010) -[2023-10-17 02:57:06,269][62408] Updated weights for policy 1, policy_version 66630 (0.0011) -[2023-10-17 02:57:06,639][62408] Updated weights for policy 1, policy_version 66640 (0.0010) -[2023-10-17 02:57:07,017][62408] Updated weights for policy 1, policy_version 66650 (0.0009) -[2023-10-17 02:57:07,214][61453] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 136970240. Throughput: 0: 1803.7, 1: 1759.4. Samples: 34251020. Policy #0 lag: (min: 10.0, avg: 13.7, max: 42.0) -[2023-10-17 02:57:07,215][61453] Avg episode reward: [(0, '10.820'), (1, '10.750')] -[2023-10-17 02:57:09,391][62373] Updated weights for policy 0, policy_version 67140 (0.0009) -[2023-10-17 02:57:09,755][62373] Updated weights for policy 0, policy_version 67150 (0.0009) -[2023-10-17 02:57:10,128][62373] Updated weights for policy 0, policy_version 67160 (0.0009) -[2023-10-17 02:57:10,689][62408] Updated weights for policy 1, policy_version 66660 (0.0011) -[2023-10-17 02:57:11,066][62408] Updated weights for policy 1, policy_version 66670 (0.0009) -[2023-10-17 02:57:11,432][62408] Updated weights for policy 1, policy_version 66680 (0.0011) -[2023-10-17 02:57:12,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 137068544. Throughput: 0: 1771.6, 1: 1773.9. Samples: 34271564. Policy #0 lag: (min: 10.0, avg: 13.7, max: 42.0) -[2023-10-17 02:57:12,215][61453] Avg episode reward: [(0, '10.230'), (1, '9.810')] -[2023-10-17 02:57:13,894][62373] Updated weights for policy 0, policy_version 67170 (0.0011) -[2023-10-17 02:57:14,270][62373] Updated weights for policy 0, policy_version 67180 (0.0009) -[2023-10-17 02:57:14,639][62373] Updated weights for policy 0, policy_version 67190 (0.0008) -[2023-10-17 02:57:15,019][62373] Updated weights for policy 0, policy_version 67200 (0.0008) -[2023-10-17 02:57:15,393][62408] Updated weights for policy 1, policy_version 66690 (0.0010) -[2023-10-17 02:57:15,764][62408] Updated weights for policy 1, policy_version 66700 (0.0008) -[2023-10-17 02:57:16,126][62408] Updated weights for policy 1, policy_version 66710 (0.0007) -[2023-10-17 02:57:16,494][62408] Updated weights for policy 1, policy_version 66720 (0.0007) -[2023-10-17 02:57:17,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 137134080. Throughput: 0: 1773.1, 1: 1747.6. Samples: 34292790. Policy #0 lag: (min: 10.0, avg: 13.7, max: 42.0) -[2023-10-17 02:57:17,215][61453] Avg episode reward: [(0, '9.960'), (1, '9.780')] -[2023-10-17 02:57:18,640][62373] Updated weights for policy 0, policy_version 67210 (0.0007) -[2023-10-17 02:57:19,006][62373] Updated weights for policy 0, policy_version 67220 (0.0008) -[2023-10-17 02:57:19,374][62373] Updated weights for policy 0, policy_version 67230 (0.0007) -[2023-10-17 02:57:20,385][62408] Updated weights for policy 1, policy_version 66730 (0.0009) -[2023-10-17 02:57:20,748][62408] Updated weights for policy 1, policy_version 66740 (0.0008) -[2023-10-17 02:57:21,111][62408] Updated weights for policy 1, policy_version 66750 (0.0010) -[2023-10-17 02:57:22,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 137199616. Throughput: 0: 1768.9, 1: 1778.0. Samples: 34303710. Policy #0 lag: (min: 10.0, avg: 13.7, max: 42.0) -[2023-10-17 02:57:22,215][61453] Avg episode reward: [(0, '9.470'), (1, '9.930')] -[2023-10-17 02:57:23,139][62373] Updated weights for policy 0, policy_version 67240 (0.0009) -[2023-10-17 02:57:23,517][62373] Updated weights for policy 0, policy_version 67250 (0.0010) -[2023-10-17 02:57:23,884][62373] Updated weights for policy 0, policy_version 67260 (0.0008) -[2023-10-17 02:57:24,859][62408] Updated weights for policy 1, policy_version 66760 (0.0008) -[2023-10-17 02:57:25,226][62408] Updated weights for policy 1, policy_version 66770 (0.0010) -[2023-10-17 02:57:25,592][62408] Updated weights for policy 1, policy_version 66780 (0.0009) -[2023-10-17 02:57:27,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 137265152. Throughput: 0: 1772.3, 1: 1751.5. Samples: 34324392. Policy #0 lag: (min: 10.0, avg: 13.7, max: 42.0) -[2023-10-17 02:57:27,214][61453] Avg episode reward: [(0, '9.760'), (1, '10.560')] -[2023-10-17 02:57:27,829][62373] Updated weights for policy 0, policy_version 67270 (0.0009) -[2023-10-17 02:57:28,190][62373] Updated weights for policy 0, policy_version 67280 (0.0009) -[2023-10-17 02:57:28,562][62373] Updated weights for policy 0, policy_version 67290 (0.0010) -[2023-10-17 02:57:29,477][62408] Updated weights for policy 1, policy_version 66790 (0.0008) -[2023-10-17 02:57:29,835][62408] Updated weights for policy 1, policy_version 66800 (0.0008) -[2023-10-17 02:57:30,199][62408] Updated weights for policy 1, policy_version 66810 (0.0008) -[2023-10-17 02:57:32,215][61453] Fps is (10 sec: 13106.6, 60 sec: 14199.3, 300 sec: 14218.0). Total num frames: 137330688. Throughput: 0: 1789.7, 1: 1748.5. Samples: 34346502. Policy #0 lag: (min: 10.0, avg: 13.7, max: 42.0) -[2023-10-17 02:57:32,216][61453] Avg episode reward: [(0, '8.940'), (1, '9.840')] -[2023-10-17 02:57:32,225][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000066816_68419584.pth... -[2023-10-17 02:57:32,233][62373] Updated weights for policy 0, policy_version 67300 (0.0009) -[2023-10-17 02:57:32,262][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000065152_66715648.pth -[2023-10-17 02:57:32,602][62373] Updated weights for policy 0, policy_version 67310 (0.0007) -[2023-10-17 02:57:32,968][62373] Updated weights for policy 0, policy_version 67320 (0.0010) -[2023-10-17 02:57:33,260][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000067328_68943872.pth... -[2023-10-17 02:57:33,289][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000065632_67207168.pth -[2023-10-17 02:57:34,131][62408] Updated weights for policy 1, policy_version 66820 (0.0008) -[2023-10-17 02:57:34,497][62408] Updated weights for policy 1, policy_version 66830 (0.0010) -[2023-10-17 02:57:34,871][62408] Updated weights for policy 1, policy_version 66840 (0.0010) -[2023-10-17 02:57:36,799][62373] Updated weights for policy 0, policy_version 67330 (0.0009) -[2023-10-17 02:57:37,161][62373] Updated weights for policy 0, policy_version 67340 (0.0011) -[2023-10-17 02:57:37,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 137396224. Throughput: 0: 1772.9, 1: 1757.3. Samples: 34356520. Policy #0 lag: (min: 10.0, avg: 13.7, max: 42.0) -[2023-10-17 02:57:37,214][61453] Avg episode reward: [(0, '8.640'), (1, '10.960')] -[2023-10-17 02:57:37,531][62373] Updated weights for policy 0, policy_version 67350 (0.0008) -[2023-10-17 02:57:37,912][62373] Updated weights for policy 0, policy_version 67360 (0.0010) -[2023-10-17 02:57:38,579][62408] Updated weights for policy 1, policy_version 66850 (0.0011) -[2023-10-17 02:57:38,948][62408] Updated weights for policy 1, policy_version 66860 (0.0011) -[2023-10-17 02:57:39,323][62408] Updated weights for policy 1, policy_version 66870 (0.0008) -[2023-10-17 02:57:39,687][62408] Updated weights for policy 1, policy_version 66880 (0.0008) -[2023-10-17 02:57:41,698][62373] Updated weights for policy 0, policy_version 67370 (0.0011) -[2023-10-17 02:57:42,067][62373] Updated weights for policy 0, policy_version 67380 (0.0007) -[2023-10-17 02:57:42,214][61453] Fps is (10 sec: 13107.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 137461760. Throughput: 0: 1783.4, 1: 1755.6. Samples: 34378248. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:57:42,215][61453] Avg episode reward: [(0, '8.700'), (1, '10.970')] -[2023-10-17 02:57:42,444][62373] Updated weights for policy 0, policy_version 67390 (0.0007) -[2023-10-17 02:57:43,460][62408] Updated weights for policy 1, policy_version 66890 (0.0010) -[2023-10-17 02:57:43,828][62408] Updated weights for policy 1, policy_version 66900 (0.0008) -[2023-10-17 02:57:44,195][62408] Updated weights for policy 1, policy_version 66910 (0.0008) -[2023-10-17 02:57:46,146][62373] Updated weights for policy 0, policy_version 67400 (0.0009) -[2023-10-17 02:57:46,515][62373] Updated weights for policy 0, policy_version 67410 (0.0008) -[2023-10-17 02:57:46,886][62373] Updated weights for policy 0, policy_version 67420 (0.0008) -[2023-10-17 02:57:47,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14745.7, 300 sec: 14218.0). Total num frames: 137560064. Throughput: 0: 1772.8, 1: 1772.4. Samples: 34399430. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:57:47,214][61453] Avg episode reward: [(0, '8.400'), (1, '10.980')] -[2023-10-17 02:57:48,051][62408] Updated weights for policy 1, policy_version 66920 (0.0008) -[2023-10-17 02:57:48,431][62408] Updated weights for policy 1, policy_version 66930 (0.0008) -[2023-10-17 02:57:48,791][62408] Updated weights for policy 1, policy_version 66940 (0.0008) -[2023-10-17 02:57:50,680][62373] Updated weights for policy 0, policy_version 67430 (0.0008) -[2023-10-17 02:57:51,064][62373] Updated weights for policy 0, policy_version 67440 (0.0008) -[2023-10-17 02:57:51,435][62373] Updated weights for policy 0, policy_version 67450 (0.0009) -[2023-10-17 02:57:52,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 137625600. Throughput: 0: 1776.2, 1: 1759.3. Samples: 34410118. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:57:52,215][61453] Avg episode reward: [(0, '8.490'), (1, '10.760')] -[2023-10-17 02:57:52,691][62408] Updated weights for policy 1, policy_version 66950 (0.0009) -[2023-10-17 02:57:53,064][62408] Updated weights for policy 1, policy_version 66960 (0.0008) -[2023-10-17 02:57:53,432][62408] Updated weights for policy 1, policy_version 66970 (0.0010) -[2023-10-17 02:57:55,229][62373] Updated weights for policy 0, policy_version 67460 (0.0007) -[2023-10-17 02:57:55,598][62373] Updated weights for policy 0, policy_version 67470 (0.0009) -[2023-10-17 02:57:55,981][62373] Updated weights for policy 0, policy_version 67480 (0.0009) -[2023-10-17 02:57:57,001][62408] Updated weights for policy 1, policy_version 66980 (0.0007) -[2023-10-17 02:57:57,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 137691136. Throughput: 0: 1780.0, 1: 1770.6. Samples: 34431340. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:57:57,214][61453] Avg episode reward: [(0, '9.020'), (1, '10.810')] -[2023-10-17 02:57:57,362][62408] Updated weights for policy 1, policy_version 66990 (0.0007) -[2023-10-17 02:57:57,733][62408] Updated weights for policy 1, policy_version 67000 (0.0007) -[2023-10-17 02:57:59,790][62373] Updated weights for policy 0, policy_version 67490 (0.0010) -[2023-10-17 02:58:00,179][62373] Updated weights for policy 0, policy_version 67500 (0.0008) -[2023-10-17 02:58:00,560][62373] Updated weights for policy 0, policy_version 67510 (0.0008) -[2023-10-17 02:58:00,919][62373] Updated weights for policy 0, policy_version 67520 (0.0008) -[2023-10-17 02:58:01,509][62408] Updated weights for policy 1, policy_version 67010 (0.0007) -[2023-10-17 02:58:01,885][62408] Updated weights for policy 1, policy_version 67020 (0.0007) -[2023-10-17 02:58:02,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 137756672. Throughput: 0: 1771.3, 1: 1788.3. Samples: 34452972. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:58:02,214][61453] Avg episode reward: [(0, '9.020'), (1, '11.240')] -[2023-10-17 02:58:02,252][62408] Updated weights for policy 1, policy_version 67030 (0.0007) -[2023-10-17 02:58:02,626][62408] Updated weights for policy 1, policy_version 67040 (0.0007) -[2023-10-17 02:58:04,646][62373] Updated weights for policy 0, policy_version 67530 (0.0007) -[2023-10-17 02:58:05,024][62373] Updated weights for policy 0, policy_version 67540 (0.0008) -[2023-10-17 02:58:05,387][62373] Updated weights for policy 0, policy_version 67550 (0.0011) -[2023-10-17 02:58:06,602][62408] Updated weights for policy 1, policy_version 67050 (0.0008) -[2023-10-17 02:58:06,975][62408] Updated weights for policy 1, policy_version 67060 (0.0010) -[2023-10-17 02:58:07,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 137822208. Throughput: 0: 1788.3, 1: 1765.0. Samples: 34463610. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:58:07,214][61453] Avg episode reward: [(0, '9.570'), (1, '11.200')] -[2023-10-17 02:58:07,338][62408] Updated weights for policy 1, policy_version 67070 (0.0007) -[2023-10-17 02:58:09,215][62373] Updated weights for policy 0, policy_version 67560 (0.0009) -[2023-10-17 02:58:09,579][62373] Updated weights for policy 0, policy_version 67570 (0.0007) -[2023-10-17 02:58:09,961][62373] Updated weights for policy 0, policy_version 67580 (0.0010) -[2023-10-17 02:58:11,182][62408] Updated weights for policy 1, policy_version 67080 (0.0009) -[2023-10-17 02:58:11,555][62408] Updated weights for policy 1, policy_version 67090 (0.0008) -[2023-10-17 02:58:11,931][62408] Updated weights for policy 1, policy_version 67100 (0.0008) -[2023-10-17 02:58:12,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 137920512. Throughput: 0: 1773.0, 1: 1799.2. Samples: 34485142. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:58:12,215][61453] Avg episode reward: [(0, '9.420'), (1, '10.920')] -[2023-10-17 02:58:13,440][62373] Updated weights for policy 0, policy_version 67590 (0.0007) -[2023-10-17 02:58:13,805][62373] Updated weights for policy 0, policy_version 67600 (0.0008) -[2023-10-17 02:58:14,178][62373] Updated weights for policy 0, policy_version 67610 (0.0007) -[2023-10-17 02:58:15,781][62408] Updated weights for policy 1, policy_version 67110 (0.0008) -[2023-10-17 02:58:16,148][62408] Updated weights for policy 1, policy_version 67120 (0.0009) -[2023-10-17 02:58:16,526][62408] Updated weights for policy 1, policy_version 67130 (0.0009) -[2023-10-17 02:58:17,214][61453] Fps is (10 sec: 16383.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 137986048. Throughput: 0: 1781.8, 1: 1768.1. Samples: 34506246. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:58:17,215][61453] Avg episode reward: [(0, '9.160'), (1, '10.150')] -[2023-10-17 02:58:18,060][62373] Updated weights for policy 0, policy_version 67620 (0.0007) -[2023-10-17 02:58:18,438][62373] Updated weights for policy 0, policy_version 67630 (0.0007) -[2023-10-17 02:58:18,812][62373] Updated weights for policy 0, policy_version 67640 (0.0007) -[2023-10-17 02:58:20,369][62408] Updated weights for policy 1, policy_version 67140 (0.0011) -[2023-10-17 02:58:20,740][62408] Updated weights for policy 1, policy_version 67150 (0.0010) -[2023-10-17 02:58:21,098][62408] Updated weights for policy 1, policy_version 67160 (0.0007) -[2023-10-17 02:58:22,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 138051584. Throughput: 0: 1778.2, 1: 1795.0. Samples: 34517314. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:58:22,215][61453] Avg episode reward: [(0, '10.350'), (1, '10.370')] -[2023-10-17 02:58:22,550][62373] Updated weights for policy 0, policy_version 67650 (0.0008) -[2023-10-17 02:58:22,908][62373] Updated weights for policy 0, policy_version 67660 (0.0008) -[2023-10-17 02:58:23,280][62373] Updated weights for policy 0, policy_version 67670 (0.0010) -[2023-10-17 02:58:23,656][62373] Updated weights for policy 0, policy_version 67680 (0.0009) -[2023-10-17 02:58:24,810][62408] Updated weights for policy 1, policy_version 67170 (0.0011) -[2023-10-17 02:58:25,185][62408] Updated weights for policy 1, policy_version 67180 (0.0008) -[2023-10-17 02:58:25,554][62408] Updated weights for policy 1, policy_version 67190 (0.0007) -[2023-10-17 02:58:25,925][62408] Updated weights for policy 1, policy_version 67200 (0.0010) -[2023-10-17 02:58:27,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 138117120. Throughput: 0: 1780.8, 1: 1775.9. Samples: 34538300. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:58:27,214][61453] Avg episode reward: [(0, '9.940'), (1, '10.000')] -[2023-10-17 02:58:27,539][62373] Updated weights for policy 0, policy_version 67690 (0.0008) -[2023-10-17 02:58:27,900][62373] Updated weights for policy 0, policy_version 67700 (0.0007) -[2023-10-17 02:58:28,273][62373] Updated weights for policy 0, policy_version 67710 (0.0008) -[2023-10-17 02:58:29,576][62408] Updated weights for policy 1, policy_version 67210 (0.0008) -[2023-10-17 02:58:29,937][62408] Updated weights for policy 1, policy_version 67220 (0.0008) -[2023-10-17 02:58:30,315][62408] Updated weights for policy 1, policy_version 67230 (0.0009) -[2023-10-17 02:58:32,055][62373] Updated weights for policy 0, policy_version 67720 (0.0007) -[2023-10-17 02:58:32,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.6, 300 sec: 14218.0). Total num frames: 138182656. Throughput: 0: 1804.0, 1: 1771.0. Samples: 34560302. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:58:32,215][61453] Avg episode reward: [(0, '10.100'), (1, '9.640')] -[2023-10-17 02:58:32,425][62373] Updated weights for policy 0, policy_version 67730 (0.0007) -[2023-10-17 02:58:32,791][62373] Updated weights for policy 0, policy_version 67740 (0.0007) -[2023-10-17 02:58:34,162][62408] Updated weights for policy 1, policy_version 67240 (0.0008) -[2023-10-17 02:58:34,543][62408] Updated weights for policy 1, policy_version 67250 (0.0009) -[2023-10-17 02:58:34,919][62408] Updated weights for policy 1, policy_version 67260 (0.0010) -[2023-10-17 02:58:36,528][62373] Updated weights for policy 0, policy_version 67750 (0.0007) -[2023-10-17 02:58:36,895][62373] Updated weights for policy 0, policy_version 67760 (0.0008) -[2023-10-17 02:58:37,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 138248192. Throughput: 0: 1781.7, 1: 1780.9. Samples: 34570434. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:58:37,214][61453] Avg episode reward: [(0, '9.940'), (1, '9.650')] -[2023-10-17 02:58:37,273][62373] Updated weights for policy 0, policy_version 67770 (0.0010) -[2023-10-17 02:58:38,595][62408] Updated weights for policy 1, policy_version 67270 (0.0011) -[2023-10-17 02:58:38,967][62408] Updated weights for policy 1, policy_version 67280 (0.0009) -[2023-10-17 02:58:39,327][62408] Updated weights for policy 1, policy_version 67290 (0.0010) -[2023-10-17 02:58:41,209][62373] Updated weights for policy 0, policy_version 67780 (0.0009) -[2023-10-17 02:58:41,572][62373] Updated weights for policy 0, policy_version 67790 (0.0008) -[2023-10-17 02:58:41,949][62373] Updated weights for policy 0, policy_version 67800 (0.0009) -[2023-10-17 02:58:42,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 138313728. Throughput: 0: 1803.0, 1: 1769.5. Samples: 34592102. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:58:42,214][61453] Avg episode reward: [(0, '10.430'), (1, '9.720')] -[2023-10-17 02:58:43,169][62408] Updated weights for policy 1, policy_version 67300 (0.0009) -[2023-10-17 02:58:43,537][62408] Updated weights for policy 1, policy_version 67310 (0.0009) -[2023-10-17 02:58:43,904][62408] Updated weights for policy 1, policy_version 67320 (0.0008) -[2023-10-17 02:58:45,943][62373] Updated weights for policy 0, policy_version 67810 (0.0008) -[2023-10-17 02:58:46,351][62373] Updated weights for policy 0, policy_version 67820 (0.0008) -[2023-10-17 02:58:46,721][62373] Updated weights for policy 0, policy_version 67830 (0.0007) -[2023-10-17 02:58:47,085][62373] Updated weights for policy 0, policy_version 67840 (0.0008) -[2023-10-17 02:58:47,214][61453] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 138412032. Throughput: 0: 1770.6, 1: 1775.0. Samples: 34612526. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:58:47,215][61453] Avg episode reward: [(0, '10.300'), (1, '9.920')] -[2023-10-17 02:58:47,799][62408] Updated weights for policy 1, policy_version 67330 (0.0008) -[2023-10-17 02:58:48,175][62408] Updated weights for policy 1, policy_version 67340 (0.0008) -[2023-10-17 02:58:48,532][62408] Updated weights for policy 1, policy_version 67350 (0.0008) -[2023-10-17 02:58:48,902][62408] Updated weights for policy 1, policy_version 67360 (0.0009) -[2023-10-17 02:58:50,890][62373] Updated weights for policy 0, policy_version 67850 (0.0008) -[2023-10-17 02:58:51,256][62373] Updated weights for policy 0, policy_version 67860 (0.0007) -[2023-10-17 02:58:51,633][62373] Updated weights for policy 0, policy_version 67870 (0.0010) -[2023-10-17 02:58:52,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 138477568. Throughput: 0: 1783.2, 1: 1766.9. Samples: 34623362. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:58:52,215][61453] Avg episode reward: [(0, '10.650'), (1, '10.160')] -[2023-10-17 02:58:52,641][62408] Updated weights for policy 1, policy_version 67370 (0.0008) -[2023-10-17 02:58:53,005][62408] Updated weights for policy 1, policy_version 67380 (0.0008) -[2023-10-17 02:58:53,372][62408] Updated weights for policy 1, policy_version 67390 (0.0010) -[2023-10-17 02:58:55,391][62373] Updated weights for policy 0, policy_version 67880 (0.0007) -[2023-10-17 02:58:55,764][62373] Updated weights for policy 0, policy_version 67890 (0.0008) -[2023-10-17 02:58:56,139][62373] Updated weights for policy 0, policy_version 67900 (0.0009) -[2023-10-17 02:58:57,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 138543104. Throughput: 0: 1777.9, 1: 1770.3. Samples: 34644812. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:58:57,214][61453] Avg episode reward: [(0, '9.480'), (1, '9.680')] -[2023-10-17 02:58:57,239][62408] Updated weights for policy 1, policy_version 67400 (0.0008) -[2023-10-17 02:58:57,604][62408] Updated weights for policy 1, policy_version 67410 (0.0009) -[2023-10-17 02:58:57,965][62408] Updated weights for policy 1, policy_version 67420 (0.0007) -[2023-10-17 02:58:59,877][62373] Updated weights for policy 0, policy_version 67910 (0.0009) -[2023-10-17 02:59:00,251][62373] Updated weights for policy 0, policy_version 67920 (0.0007) -[2023-10-17 02:59:00,615][62373] Updated weights for policy 0, policy_version 67930 (0.0010) -[2023-10-17 02:59:01,749][62408] Updated weights for policy 1, policy_version 67430 (0.0010) -[2023-10-17 02:59:02,125][62408] Updated weights for policy 1, policy_version 67440 (0.0008) -[2023-10-17 02:59:02,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 138608640. Throughput: 0: 1763.0, 1: 1791.3. Samples: 34666186. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:59:02,214][61453] Avg episode reward: [(0, '9.940'), (1, '9.900')] -[2023-10-17 02:59:02,496][62408] Updated weights for policy 1, policy_version 67450 (0.0007) -[2023-10-17 02:59:04,489][62373] Updated weights for policy 0, policy_version 67940 (0.0010) -[2023-10-17 02:59:04,858][62373] Updated weights for policy 0, policy_version 67950 (0.0009) -[2023-10-17 02:59:05,233][62373] Updated weights for policy 0, policy_version 67960 (0.0010) -[2023-10-17 02:59:06,398][62408] Updated weights for policy 1, policy_version 67460 (0.0009) -[2023-10-17 02:59:06,770][62408] Updated weights for policy 1, policy_version 67470 (0.0008) -[2023-10-17 02:59:07,126][62408] Updated weights for policy 1, policy_version 67480 (0.0008) -[2023-10-17 02:59:07,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 138674176. Throughput: 0: 1778.1, 1: 1766.0. Samples: 34676796. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 02:59:07,214][61453] Avg episode reward: [(0, '9.890'), (1, '9.670')] -[2023-10-17 02:59:08,958][62373] Updated weights for policy 0, policy_version 67970 (0.0011) -[2023-10-17 02:59:09,320][62373] Updated weights for policy 0, policy_version 67980 (0.0007) -[2023-10-17 02:59:09,693][62373] Updated weights for policy 0, policy_version 67990 (0.0009) -[2023-10-17 02:59:10,064][62373] Updated weights for policy 0, policy_version 68000 (0.0009) -[2023-10-17 02:59:11,063][62408] Updated weights for policy 1, policy_version 67490 (0.0008) -[2023-10-17 02:59:11,433][62408] Updated weights for policy 1, policy_version 67500 (0.0007) -[2023-10-17 02:59:11,799][62408] Updated weights for policy 1, policy_version 67510 (0.0007) -[2023-10-17 02:59:12,171][62408] Updated weights for policy 1, policy_version 67520 (0.0008) -[2023-10-17 02:59:12,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 138772480. Throughput: 0: 1762.6, 1: 1783.3. Samples: 34697866. Policy #0 lag: (min: 31.0, avg: 31.7, max: 49.0) -[2023-10-17 02:59:12,215][61453] Avg episode reward: [(0, '9.550'), (1, '9.990')] -[2023-10-17 02:59:13,892][62373] Updated weights for policy 0, policy_version 68010 (0.0009) -[2023-10-17 02:59:14,262][62373] Updated weights for policy 0, policy_version 68020 (0.0008) -[2023-10-17 02:59:14,637][62373] Updated weights for policy 0, policy_version 68030 (0.0007) -[2023-10-17 02:59:15,914][62408] Updated weights for policy 1, policy_version 67530 (0.0007) -[2023-10-17 02:59:16,276][62408] Updated weights for policy 1, policy_version 67540 (0.0008) -[2023-10-17 02:59:16,638][62408] Updated weights for policy 1, policy_version 67550 (0.0008) -[2023-10-17 02:59:17,214][61453] Fps is (10 sec: 16383.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 138838016. Throughput: 0: 1767.4, 1: 1751.3. Samples: 34718644. Policy #0 lag: (min: 31.0, avg: 31.7, max: 49.0) -[2023-10-17 02:59:17,215][61453] Avg episode reward: [(0, '9.680'), (1, '8.990')] -[2023-10-17 02:59:18,441][62373] Updated weights for policy 0, policy_version 68040 (0.0008) -[2023-10-17 02:59:18,808][62373] Updated weights for policy 0, policy_version 68050 (0.0009) -[2023-10-17 02:59:19,184][62373] Updated weights for policy 0, policy_version 68060 (0.0008) -[2023-10-17 02:59:20,602][62408] Updated weights for policy 1, policy_version 67560 (0.0008) -[2023-10-17 02:59:20,987][62408] Updated weights for policy 1, policy_version 67570 (0.0008) -[2023-10-17 02:59:21,344][62408] Updated weights for policy 1, policy_version 67580 (0.0009) -[2023-10-17 02:59:22,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 138903552. Throughput: 0: 1760.1, 1: 1777.0. Samples: 34729602. Policy #0 lag: (min: 31.0, avg: 31.7, max: 49.0) -[2023-10-17 02:59:22,215][61453] Avg episode reward: [(0, '9.270'), (1, '8.960')] -[2023-10-17 02:59:22,952][62373] Updated weights for policy 0, policy_version 68070 (0.0010) -[2023-10-17 02:59:23,315][62373] Updated weights for policy 0, policy_version 68080 (0.0011) -[2023-10-17 02:59:23,696][62373] Updated weights for policy 0, policy_version 68090 (0.0008) -[2023-10-17 02:59:25,114][62408] Updated weights for policy 1, policy_version 67590 (0.0009) -[2023-10-17 02:59:25,486][62408] Updated weights for policy 1, policy_version 67600 (0.0010) -[2023-10-17 02:59:25,847][62408] Updated weights for policy 1, policy_version 67610 (0.0009) -[2023-10-17 02:59:27,214][61453] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 138969088. Throughput: 0: 1765.7, 1: 1756.8. Samples: 34750614. Policy #0 lag: (min: 31.0, avg: 31.7, max: 49.0) -[2023-10-17 02:59:27,214][61453] Avg episode reward: [(0, '9.590'), (1, '10.110')] -[2023-10-17 02:59:27,398][62373] Updated weights for policy 0, policy_version 68100 (0.0008) -[2023-10-17 02:59:27,772][62373] Updated weights for policy 0, policy_version 68110 (0.0011) -[2023-10-17 02:59:28,147][62373] Updated weights for policy 0, policy_version 68120 (0.0007) -[2023-10-17 02:59:29,627][62408] Updated weights for policy 1, policy_version 67620 (0.0009) -[2023-10-17 02:59:29,983][62408] Updated weights for policy 1, policy_version 67630 (0.0008) -[2023-10-17 02:59:30,346][62408] Updated weights for policy 1, policy_version 67640 (0.0008) -[2023-10-17 02:59:31,967][62373] Updated weights for policy 0, policy_version 68130 (0.0008) -[2023-10-17 02:59:32,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 139034624. Throughput: 0: 1799.3, 1: 1756.7. Samples: 34772544. Policy #0 lag: (min: 31.0, avg: 31.7, max: 49.0) -[2023-10-17 02:59:32,214][61453] Avg episode reward: [(0, '10.010'), (1, '9.750')] -[2023-10-17 02:59:32,224][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000067648_69271552.pth... -[2023-10-17 02:59:32,253][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000065984_67567616.pth -[2023-10-17 02:59:32,375][62373] Updated weights for policy 0, policy_version 68140 (0.0008) -[2023-10-17 02:59:32,747][62373] Updated weights for policy 0, policy_version 68150 (0.0009) -[2023-10-17 02:59:33,113][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000068160_69795840.pth... -[2023-10-17 02:59:33,117][62373] Updated weights for policy 0, policy_version 68160 (0.0007) -[2023-10-17 02:59:33,152][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000066464_68059136.pth -[2023-10-17 02:59:34,209][62408] Updated weights for policy 1, policy_version 67650 (0.0009) -[2023-10-17 02:59:34,593][62408] Updated weights for policy 1, policy_version 67660 (0.0011) -[2023-10-17 02:59:34,956][62408] Updated weights for policy 1, policy_version 67670 (0.0010) -[2023-10-17 02:59:35,325][62408] Updated weights for policy 1, policy_version 67680 (0.0008) -[2023-10-17 02:59:36,929][62373] Updated weights for policy 0, policy_version 68170 (0.0010) -[2023-10-17 02:59:37,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 139100160. Throughput: 0: 1775.0, 1: 1771.1. Samples: 34782938. Policy #0 lag: (min: 31.0, avg: 31.7, max: 49.0) -[2023-10-17 02:59:37,215][61453] Avg episode reward: [(0, '10.050'), (1, '10.590')] -[2023-10-17 02:59:37,296][62373] Updated weights for policy 0, policy_version 68180 (0.0011) -[2023-10-17 02:59:37,669][62373] Updated weights for policy 0, policy_version 68190 (0.0009) -[2023-10-17 02:59:39,006][62408] Updated weights for policy 1, policy_version 67690 (0.0009) -[2023-10-17 02:59:39,376][62408] Updated weights for policy 1, policy_version 67700 (0.0009) -[2023-10-17 02:59:39,743][62408] Updated weights for policy 1, policy_version 67710 (0.0009) -[2023-10-17 02:59:41,448][62373] Updated weights for policy 0, policy_version 68200 (0.0008) -[2023-10-17 02:59:41,820][62373] Updated weights for policy 0, policy_version 68210 (0.0009) -[2023-10-17 02:59:42,201][62373] Updated weights for policy 0, policy_version 68220 (0.0011) -[2023-10-17 02:59:42,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 139165696. Throughput: 0: 1789.0, 1: 1749.8. Samples: 34804060. Policy #0 lag: (min: 31.0, avg: 31.7, max: 49.0) -[2023-10-17 02:59:42,215][61453] Avg episode reward: [(0, '10.070'), (1, '10.640')] -[2023-10-17 02:59:43,566][62408] Updated weights for policy 1, policy_version 67720 (0.0010) -[2023-10-17 02:59:43,930][62408] Updated weights for policy 1, policy_version 67730 (0.0008) -[2023-10-17 02:59:44,299][62408] Updated weights for policy 1, policy_version 67740 (0.0008) -[2023-10-17 02:59:45,953][62373] Updated weights for policy 0, policy_version 68230 (0.0010) -[2023-10-17 02:59:46,318][62373] Updated weights for policy 0, policy_version 68240 (0.0007) -[2023-10-17 02:59:46,694][62373] Updated weights for policy 0, policy_version 68250 (0.0008) -[2023-10-17 02:59:47,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 139264000. Throughput: 0: 1767.6, 1: 1760.5. Samples: 34824952. Policy #0 lag: (min: 31.0, avg: 31.7, max: 49.0) -[2023-10-17 02:59:47,214][61453] Avg episode reward: [(0, '10.500'), (1, '10.250')] -[2023-10-17 02:59:48,067][62408] Updated weights for policy 1, policy_version 67750 (0.0008) -[2023-10-17 02:59:48,432][62408] Updated weights for policy 1, policy_version 67760 (0.0010) -[2023-10-17 02:59:48,792][62408] Updated weights for policy 1, policy_version 67770 (0.0009) -[2023-10-17 02:59:50,526][62373] Updated weights for policy 0, policy_version 68260 (0.0010) -[2023-10-17 02:59:50,886][62373] Updated weights for policy 0, policy_version 68270 (0.0007) -[2023-10-17 02:59:51,258][62373] Updated weights for policy 0, policy_version 68280 (0.0007) -[2023-10-17 02:59:52,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 139329536. Throughput: 0: 1782.4, 1: 1750.0. Samples: 34835754. Policy #0 lag: (min: 31.0, avg: 31.7, max: 49.0) -[2023-10-17 02:59:52,215][61453] Avg episode reward: [(0, '10.570'), (1, '10.400')] -[2023-10-17 02:59:52,715][62408] Updated weights for policy 1, policy_version 67780 (0.0011) -[2023-10-17 02:59:53,089][62408] Updated weights for policy 1, policy_version 67790 (0.0007) -[2023-10-17 02:59:53,463][62408] Updated weights for policy 1, policy_version 67800 (0.0008) -[2023-10-17 02:59:54,916][62373] Updated weights for policy 0, policy_version 68290 (0.0007) -[2023-10-17 02:59:55,298][62373] Updated weights for policy 0, policy_version 68300 (0.0007) -[2023-10-17 02:59:55,674][62373] Updated weights for policy 0, policy_version 68310 (0.0007) -[2023-10-17 02:59:56,036][62373] Updated weights for policy 0, policy_version 68320 (0.0007) -[2023-10-17 02:59:57,214][61453] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 139395072. Throughput: 0: 1778.0, 1: 1760.3. Samples: 34857092. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-10-17 02:59:57,215][61453] Avg episode reward: [(0, '11.200'), (1, '9.830')] -[2023-10-17 02:59:57,277][62408] Updated weights for policy 1, policy_version 67810 (0.0007) -[2023-10-17 02:59:57,651][62408] Updated weights for policy 1, policy_version 67820 (0.0008) -[2023-10-17 02:59:58,016][62408] Updated weights for policy 1, policy_version 67830 (0.0008) -[2023-10-17 02:59:58,388][62408] Updated weights for policy 1, policy_version 67840 (0.0007) -[2023-10-17 02:59:59,792][62373] Updated weights for policy 0, policy_version 68330 (0.0010) -[2023-10-17 03:00:00,166][62373] Updated weights for policy 0, policy_version 68340 (0.0007) -[2023-10-17 03:00:00,532][62373] Updated weights for policy 0, policy_version 68350 (0.0008) -[2023-10-17 03:00:02,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 139460608. Throughput: 0: 1773.6, 1: 1789.7. Samples: 34878990. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-10-17 03:00:02,214][61453] Avg episode reward: [(0, '10.700'), (1, '9.530')] -[2023-10-17 03:00:02,285][62408] Updated weights for policy 1, policy_version 67850 (0.0008) -[2023-10-17 03:00:02,651][62408] Updated weights for policy 1, policy_version 67860 (0.0010) -[2023-10-17 03:00:03,016][62408] Updated weights for policy 1, policy_version 67870 (0.0008) -[2023-10-17 03:00:04,225][62373] Updated weights for policy 0, policy_version 68360 (0.0009) -[2023-10-17 03:00:04,595][62373] Updated weights for policy 0, policy_version 68370 (0.0007) -[2023-10-17 03:00:04,962][62373] Updated weights for policy 0, policy_version 68380 (0.0009) -[2023-10-17 03:00:06,947][62408] Updated weights for policy 1, policy_version 67880 (0.0010) -[2023-10-17 03:00:07,214][61453] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 139526144. Throughput: 0: 1784.2, 1: 1758.4. Samples: 34889020. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-10-17 03:00:07,214][61453] Avg episode reward: [(0, '10.190'), (1, '8.840')] -[2023-10-17 03:00:07,326][62408] Updated weights for policy 1, policy_version 67890 (0.0009) -[2023-10-17 03:00:07,700][62408] Updated weights for policy 1, policy_version 67900 (0.0011) -[2023-10-17 03:00:08,938][62373] Updated weights for policy 0, policy_version 68390 (0.0009) -[2023-10-17 03:00:09,316][62373] Updated weights for policy 0, policy_version 68400 (0.0009) -[2023-10-17 03:00:09,680][62373] Updated weights for policy 0, policy_version 68410 (0.0007) -[2023-10-17 03:00:11,536][62408] Updated weights for policy 1, policy_version 67910 (0.0009) -[2023-10-17 03:00:11,909][62408] Updated weights for policy 1, policy_version 67920 (0.0009) -[2023-10-17 03:00:12,214][61453] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 139591680. Throughput: 0: 1769.0, 1: 1781.6. Samples: 34910394. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-10-17 03:00:12,214][61453] Avg episode reward: [(0, '9.440'), (1, '8.240')] -[2023-10-17 03:00:12,280][62408] Updated weights for policy 1, policy_version 67930 (0.0008) -[2023-10-17 03:00:13,408][62373] Updated weights for policy 0, policy_version 68420 (0.0008) -[2023-10-17 03:00:13,774][62373] Updated weights for policy 0, policy_version 68430 (0.0008) -[2023-10-17 03:00:14,156][62373] Updated weights for policy 0, policy_version 68440 (0.0008) -[2023-10-17 03:00:16,233][62408] Updated weights for policy 1, policy_version 67940 (0.0009) -[2023-10-17 03:00:16,603][62408] Updated weights for policy 1, policy_version 67950 (0.0008) -[2023-10-17 03:00:16,972][62408] Updated weights for policy 1, policy_version 67960 (0.0007) -[2023-10-17 03:00:17,214][61453] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 139657216. Throughput: 0: 1770.8, 1: 1763.6. Samples: 34931592. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-10-17 03:00:17,215][61453] Avg episode reward: [(0, '10.270'), (1, '8.230')] -[2023-10-17 03:00:18,065][62373] Updated weights for policy 0, policy_version 68450 (0.0009) -[2023-10-17 03:00:18,466][62373] Updated weights for policy 0, policy_version 68460 (0.0008) -[2023-10-17 03:00:18,836][62373] Updated weights for policy 0, policy_version 68470 (0.0010) -[2023-10-17 03:00:19,213][62373] Updated weights for policy 0, policy_version 68480 (0.0010) -[2023-10-17 03:00:20,531][62408] Updated weights for policy 1, policy_version 67970 (0.0007) -[2023-10-17 03:00:20,893][62408] Updated weights for policy 1, policy_version 67980 (0.0009) -[2023-10-17 03:00:21,265][62408] Updated weights for policy 1, policy_version 67990 (0.0009) -[2023-10-17 03:00:21,644][62408] Updated weights for policy 1, policy_version 68000 (0.0009) -[2023-10-17 03:00:22,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 139755520. Throughput: 0: 1763.1, 1: 1771.8. Samples: 34942010. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-10-17 03:00:22,215][61453] Avg episode reward: [(0, '9.470'), (1, '8.330')] -[2023-10-17 03:00:22,898][62373] Updated weights for policy 0, policy_version 68490 (0.0010) -[2023-10-17 03:00:23,275][62373] Updated weights for policy 0, policy_version 68500 (0.0009) -[2023-10-17 03:00:23,649][62373] Updated weights for policy 0, policy_version 68510 (0.0008) -[2023-10-17 03:00:25,348][62408] Updated weights for policy 1, policy_version 68010 (0.0009) -[2023-10-17 03:00:25,709][62408] Updated weights for policy 1, policy_version 68020 (0.0008) -[2023-10-17 03:00:26,077][62408] Updated weights for policy 1, policy_version 68030 (0.0008) -[2023-10-17 03:00:27,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 139821056. Throughput: 0: 1776.6, 1: 1770.7. Samples: 34963688. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-10-17 03:00:27,215][61453] Avg episode reward: [(0, '9.240'), (1, '8.500')] -[2023-10-17 03:00:27,357][62373] Updated weights for policy 0, policy_version 68520 (0.0010) -[2023-10-17 03:00:27,727][62373] Updated weights for policy 0, policy_version 68530 (0.0009) -[2023-10-17 03:00:28,094][62373] Updated weights for policy 0, policy_version 68540 (0.0009) -[2023-10-17 03:00:29,818][62408] Updated weights for policy 1, policy_version 68040 (0.0007) -[2023-10-17 03:00:30,189][62408] Updated weights for policy 1, policy_version 68050 (0.0009) -[2023-10-17 03:00:30,563][62408] Updated weights for policy 1, policy_version 68060 (0.0009) -[2023-10-17 03:00:31,858][62373] Updated weights for policy 0, policy_version 68550 (0.0007) -[2023-10-17 03:00:32,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 139886592. Throughput: 0: 1800.8, 1: 1765.3. Samples: 34985428. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-10-17 03:00:32,214][61453] Avg episode reward: [(0, '9.710'), (1, '8.970')] -[2023-10-17 03:00:32,230][62373] Updated weights for policy 0, policy_version 68560 (0.0007) -[2023-10-17 03:00:32,603][62373] Updated weights for policy 0, policy_version 68570 (0.0007) -[2023-10-17 03:00:34,366][62408] Updated weights for policy 1, policy_version 68070 (0.0007) -[2023-10-17 03:00:34,740][62408] Updated weights for policy 1, policy_version 68080 (0.0008) -[2023-10-17 03:00:35,095][62408] Updated weights for policy 1, policy_version 68090 (0.0010) -[2023-10-17 03:00:36,485][62373] Updated weights for policy 0, policy_version 68580 (0.0010) -[2023-10-17 03:00:36,850][62373] Updated weights for policy 0, policy_version 68590 (0.0010) -[2023-10-17 03:00:37,211][62373] Updated weights for policy 0, policy_version 68600 (0.0008) -[2023-10-17 03:00:37,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 139952128. Throughput: 0: 1778.6, 1: 1780.4. Samples: 34995908. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-10-17 03:00:37,214][61453] Avg episode reward: [(0, '10.140'), (1, '8.910')] -[2023-10-17 03:00:38,960][62408] Updated weights for policy 1, policy_version 68100 (0.0011) -[2023-10-17 03:00:39,331][62408] Updated weights for policy 1, policy_version 68110 (0.0008) -[2023-10-17 03:00:39,701][62408] Updated weights for policy 1, policy_version 68120 (0.0008) -[2023-10-17 03:00:41,016][62373] Updated weights for policy 0, policy_version 68610 (0.0009) -[2023-10-17 03:00:41,391][62373] Updated weights for policy 0, policy_version 68620 (0.0008) -[2023-10-17 03:00:41,761][62373] Updated weights for policy 0, policy_version 68630 (0.0007) -[2023-10-17 03:00:42,145][62373] Updated weights for policy 0, policy_version 68640 (0.0009) -[2023-10-17 03:00:42,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 140050432. Throughput: 0: 1798.9, 1: 1760.4. Samples: 35017256. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:00:42,215][61453] Avg episode reward: [(0, '9.900'), (1, '9.720')] -[2023-10-17 03:00:43,590][62408] Updated weights for policy 1, policy_version 68130 (0.0008) -[2023-10-17 03:00:43,966][62408] Updated weights for policy 1, policy_version 68140 (0.0008) -[2023-10-17 03:00:44,332][62408] Updated weights for policy 1, policy_version 68150 (0.0009) -[2023-10-17 03:00:44,700][62408] Updated weights for policy 1, policy_version 68160 (0.0011) -[2023-10-17 03:00:45,798][62373] Updated weights for policy 0, policy_version 68650 (0.0008) -[2023-10-17 03:00:46,167][62373] Updated weights for policy 0, policy_version 68660 (0.0008) -[2023-10-17 03:00:46,533][62373] Updated weights for policy 0, policy_version 68670 (0.0009) -[2023-10-17 03:00:47,214][61453] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 140115968. Throughput: 0: 1771.4, 1: 1764.5. Samples: 35038104. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:00:47,215][61453] Avg episode reward: [(0, '9.770'), (1, '10.540')] -[2023-10-17 03:00:48,519][62408] Updated weights for policy 1, policy_version 68170 (0.0008) -[2023-10-17 03:00:48,880][62408] Updated weights for policy 1, policy_version 68180 (0.0009) -[2023-10-17 03:00:49,251][62408] Updated weights for policy 1, policy_version 68190 (0.0009) -[2023-10-17 03:00:50,329][62373] Updated weights for policy 0, policy_version 68680 (0.0007) -[2023-10-17 03:00:50,696][62373] Updated weights for policy 0, policy_version 68690 (0.0009) -[2023-10-17 03:00:51,069][62373] Updated weights for policy 0, policy_version 68700 (0.0008) -[2023-10-17 03:00:52,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 140181504. Throughput: 0: 1796.4, 1: 1764.6. Samples: 35049266. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:00:52,215][61453] Avg episode reward: [(0, '9.280'), (1, '10.890')] -[2023-10-17 03:00:53,093][62408] Updated weights for policy 1, policy_version 68200 (0.0009) -[2023-10-17 03:00:53,458][62408] Updated weights for policy 1, policy_version 68210 (0.0011) -[2023-10-17 03:00:53,821][62408] Updated weights for policy 1, policy_version 68220 (0.0010) -[2023-10-17 03:00:54,994][62373] Updated weights for policy 0, policy_version 68710 (0.0007) -[2023-10-17 03:00:55,364][62373] Updated weights for policy 0, policy_version 68720 (0.0007) -[2023-10-17 03:00:55,735][62373] Updated weights for policy 0, policy_version 68730 (0.0010) -[2023-10-17 03:00:57,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 140247040. Throughput: 0: 1776.2, 1: 1766.5. Samples: 35069816. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:00:57,215][61453] Avg episode reward: [(0, '10.030'), (1, '11.020')] -[2023-10-17 03:00:57,788][62408] Updated weights for policy 1, policy_version 68230 (0.0010) -[2023-10-17 03:00:58,151][62408] Updated weights for policy 1, policy_version 68240 (0.0011) -[2023-10-17 03:00:58,516][62408] Updated weights for policy 1, policy_version 68250 (0.0011) -[2023-10-17 03:00:59,549][62373] Updated weights for policy 0, policy_version 68740 (0.0011) -[2023-10-17 03:00:59,919][62373] Updated weights for policy 0, policy_version 68750 (0.0007) -[2023-10-17 03:01:00,286][62373] Updated weights for policy 0, policy_version 68760 (0.0009) -[2023-10-17 03:01:02,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 140312576. Throughput: 0: 1775.0, 1: 1784.2. Samples: 35091756. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:01:02,214][61453] Avg episode reward: [(0, '9.640'), (1, '10.780')] -[2023-10-17 03:01:02,397][62408] Updated weights for policy 1, policy_version 68260 (0.0009) -[2023-10-17 03:01:02,768][62408] Updated weights for policy 1, policy_version 68270 (0.0009) -[2023-10-17 03:01:03,131][62408] Updated weights for policy 1, policy_version 68280 (0.0010) -[2023-10-17 03:01:03,901][62373] Updated weights for policy 0, policy_version 68770 (0.0008) -[2023-10-17 03:01:04,308][62373] Updated weights for policy 0, policy_version 68780 (0.0009) -[2023-10-17 03:01:04,687][62373] Updated weights for policy 0, policy_version 68790 (0.0009) -[2023-10-17 03:01:05,061][62373] Updated weights for policy 0, policy_version 68800 (0.0008) -[2023-10-17 03:01:07,100][62408] Updated weights for policy 1, policy_version 68290 (0.0008) -[2023-10-17 03:01:07,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 140378112. Throughput: 0: 1785.8, 1: 1763.9. Samples: 35101744. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:01:07,215][61453] Avg episode reward: [(0, '10.010'), (1, '11.050')] -[2023-10-17 03:01:07,478][62408] Updated weights for policy 1, policy_version 68300 (0.0008) -[2023-10-17 03:01:07,844][62408] Updated weights for policy 1, policy_version 68310 (0.0007) -[2023-10-17 03:01:08,220][62408] Updated weights for policy 1, policy_version 68320 (0.0008) -[2023-10-17 03:01:08,801][62373] Updated weights for policy 0, policy_version 68810 (0.0010) -[2023-10-17 03:01:09,180][62373] Updated weights for policy 0, policy_version 68820 (0.0010) -[2023-10-17 03:01:09,542][62373] Updated weights for policy 0, policy_version 68830 (0.0007) -[2023-10-17 03:01:11,967][62408] Updated weights for policy 1, policy_version 68330 (0.0007) -[2023-10-17 03:01:12,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 140443648. Throughput: 0: 1771.5, 1: 1778.6. Samples: 35123444. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:01:12,215][61453] Avg episode reward: [(0, '9.480'), (1, '10.490')] -[2023-10-17 03:01:12,332][62408] Updated weights for policy 1, policy_version 68340 (0.0007) -[2023-10-17 03:01:12,693][62408] Updated weights for policy 1, policy_version 68350 (0.0007) -[2023-10-17 03:01:13,377][62373] Updated weights for policy 0, policy_version 68840 (0.0010) -[2023-10-17 03:01:13,742][62373] Updated weights for policy 0, policy_version 68850 (0.0007) -[2023-10-17 03:01:14,121][62373] Updated weights for policy 0, policy_version 68860 (0.0007) -[2023-10-17 03:01:16,397][62408] Updated weights for policy 1, policy_version 68360 (0.0008) -[2023-10-17 03:01:16,761][62408] Updated weights for policy 1, policy_version 68370 (0.0007) -[2023-10-17 03:01:17,135][62408] Updated weights for policy 1, policy_version 68380 (0.0007) -[2023-10-17 03:01:17,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 140509184. Throughput: 0: 1777.5, 1: 1762.9. Samples: 35144748. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:01:17,214][61453] Avg episode reward: [(0, '10.020'), (1, '10.180')] -[2023-10-17 03:01:17,840][62373] Updated weights for policy 0, policy_version 68870 (0.0008) -[2023-10-17 03:01:18,203][62373] Updated weights for policy 0, policy_version 68880 (0.0007) -[2023-10-17 03:01:18,574][62373] Updated weights for policy 0, policy_version 68890 (0.0007) -[2023-10-17 03:01:20,781][62408] Updated weights for policy 1, policy_version 68390 (0.0010) -[2023-10-17 03:01:21,152][62408] Updated weights for policy 1, policy_version 68400 (0.0010) -[2023-10-17 03:01:21,515][62408] Updated weights for policy 1, policy_version 68410 (0.0010) -[2023-10-17 03:01:22,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 140607488. Throughput: 0: 1771.1, 1: 1770.7. Samples: 35155290. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:01:22,215][61453] Avg episode reward: [(0, '9.450'), (1, '9.750')] -[2023-10-17 03:01:22,418][62373] Updated weights for policy 0, policy_version 68900 (0.0010) -[2023-10-17 03:01:22,789][62373] Updated weights for policy 0, policy_version 68910 (0.0011) -[2023-10-17 03:01:23,166][62373] Updated weights for policy 0, policy_version 68920 (0.0010) -[2023-10-17 03:01:25,349][62408] Updated weights for policy 1, policy_version 68420 (0.0008) -[2023-10-17 03:01:25,715][62408] Updated weights for policy 1, policy_version 68430 (0.0009) -[2023-10-17 03:01:26,079][62408] Updated weights for policy 1, policy_version 68440 (0.0009) -[2023-10-17 03:01:26,992][62373] Updated weights for policy 0, policy_version 68930 (0.0010) -[2023-10-17 03:01:27,214][61453] Fps is (10 sec: 16383.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 140673024. Throughput: 0: 1773.9, 1: 1774.2. Samples: 35176924. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:01:27,215][61453] Avg episode reward: [(0, '9.670'), (1, '9.350')] -[2023-10-17 03:01:27,366][62373] Updated weights for policy 0, policy_version 68940 (0.0007) -[2023-10-17 03:01:27,742][62373] Updated weights for policy 0, policy_version 68950 (0.0010) -[2023-10-17 03:01:28,112][62373] Updated weights for policy 0, policy_version 68960 (0.0009) -[2023-10-17 03:01:29,851][62408] Updated weights for policy 1, policy_version 68450 (0.0008) -[2023-10-17 03:01:30,212][62408] Updated weights for policy 1, policy_version 68460 (0.0007) -[2023-10-17 03:01:30,575][62408] Updated weights for policy 1, policy_version 68470 (0.0007) -[2023-10-17 03:01:30,945][62408] Updated weights for policy 1, policy_version 68480 (0.0009) -[2023-10-17 03:01:31,797][62373] Updated weights for policy 0, policy_version 68970 (0.0007) -[2023-10-17 03:01:32,165][62373] Updated weights for policy 0, policy_version 68980 (0.0007) -[2023-10-17 03:01:32,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 140738560. Throughput: 0: 1792.5, 1: 1756.0. Samples: 35197788. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:01:32,215][61453] Avg episode reward: [(0, '9.440'), (1, '9.960')] -[2023-10-17 03:01:32,226][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000068480_70123520.pth... -[2023-10-17 03:01:32,254][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000066816_68419584.pth -[2023-10-17 03:01:32,532][62373] Updated weights for policy 0, policy_version 68990 (0.0009) -[2023-10-17 03:01:32,605][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000068992_70647808.pth... -[2023-10-17 03:01:32,644][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000067328_68943872.pth -[2023-10-17 03:01:34,848][62408] Updated weights for policy 1, policy_version 68490 (0.0008) -[2023-10-17 03:01:35,216][62408] Updated weights for policy 1, policy_version 68500 (0.0008) -[2023-10-17 03:01:35,571][62408] Updated weights for policy 1, policy_version 68510 (0.0007) -[2023-10-17 03:01:36,360][62373] Updated weights for policy 0, policy_version 69000 (0.0007) -[2023-10-17 03:01:36,730][62373] Updated weights for policy 0, policy_version 69010 (0.0009) -[2023-10-17 03:01:37,097][62373] Updated weights for policy 0, policy_version 69020 (0.0008) -[2023-10-17 03:01:37,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 140804096. Throughput: 0: 1772.3, 1: 1778.9. Samples: 35209072. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:01:37,215][61453] Avg episode reward: [(0, '9.570'), (1, '9.780')] -[2023-10-17 03:01:39,297][62408] Updated weights for policy 1, policy_version 68520 (0.0010) -[2023-10-17 03:01:39,655][62408] Updated weights for policy 1, policy_version 68530 (0.0010) -[2023-10-17 03:01:40,026][62408] Updated weights for policy 1, policy_version 68540 (0.0008) -[2023-10-17 03:01:40,816][62373] Updated weights for policy 0, policy_version 69030 (0.0009) -[2023-10-17 03:01:41,186][62373] Updated weights for policy 0, policy_version 69040 (0.0010) -[2023-10-17 03:01:41,560][62373] Updated weights for policy 0, policy_version 69050 (0.0010) -[2023-10-17 03:01:42,214][61453] Fps is (10 sec: 16384.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 140902400. Throughput: 0: 1800.6, 1: 1757.1. Samples: 35229914. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:01:42,214][61453] Avg episode reward: [(0, '9.510'), (1, '9.910')] -[2023-10-17 03:01:44,161][62408] Updated weights for policy 1, policy_version 68550 (0.0008) -[2023-10-17 03:01:44,548][62408] Updated weights for policy 1, policy_version 68560 (0.0009) -[2023-10-17 03:01:44,918][62408] Updated weights for policy 1, policy_version 68570 (0.0008) -[2023-10-17 03:01:45,412][62373] Updated weights for policy 0, policy_version 69060 (0.0010) -[2023-10-17 03:01:45,785][62373] Updated weights for policy 0, policy_version 69070 (0.0010) -[2023-10-17 03:01:46,166][62373] Updated weights for policy 0, policy_version 69080 (0.0011) -[2023-10-17 03:01:47,214][61453] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 140967936. Throughput: 0: 1777.0, 1: 1758.3. Samples: 35250842. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:01:47,215][61453] Avg episode reward: [(0, '10.620'), (1, '9.760')] -[2023-10-17 03:01:48,712][62408] Updated weights for policy 1, policy_version 68580 (0.0008) -[2023-10-17 03:01:49,087][62408] Updated weights for policy 1, policy_version 68590 (0.0009) -[2023-10-17 03:01:49,450][62408] Updated weights for policy 1, policy_version 68600 (0.0008) -[2023-10-17 03:01:49,931][62373] Updated weights for policy 0, policy_version 69090 (0.0010) -[2023-10-17 03:01:50,350][62373] Updated weights for policy 0, policy_version 69100 (0.0008) -[2023-10-17 03:01:50,717][62373] Updated weights for policy 0, policy_version 69110 (0.0007) -[2023-10-17 03:01:51,093][62373] Updated weights for policy 0, policy_version 69120 (0.0009) -[2023-10-17 03:01:52,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 141033472. Throughput: 0: 1802.3, 1: 1756.9. Samples: 35261908. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:01:52,215][61453] Avg episode reward: [(0, '10.880'), (1, '9.870')] -[2023-10-17 03:01:53,256][62408] Updated weights for policy 1, policy_version 68610 (0.0007) -[2023-10-17 03:01:53,621][62408] Updated weights for policy 1, policy_version 68620 (0.0007) -[2023-10-17 03:01:53,991][62408] Updated weights for policy 1, policy_version 68630 (0.0008) -[2023-10-17 03:01:54,356][62408] Updated weights for policy 1, policy_version 68640 (0.0008) -[2023-10-17 03:01:54,858][62373] Updated weights for policy 0, policy_version 69130 (0.0007) -[2023-10-17 03:01:55,224][62373] Updated weights for policy 0, policy_version 69140 (0.0007) -[2023-10-17 03:01:55,601][62373] Updated weights for policy 0, policy_version 69150 (0.0008) -[2023-10-17 03:01:57,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 141099008. Throughput: 0: 1775.4, 1: 1757.2. Samples: 35282410. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:01:57,215][61453] Avg episode reward: [(0, '10.720'), (1, '9.990')] -[2023-10-17 03:01:58,211][62408] Updated weights for policy 1, policy_version 68650 (0.0010) -[2023-10-17 03:01:58,569][62408] Updated weights for policy 1, policy_version 68660 (0.0009) -[2023-10-17 03:01:58,931][62408] Updated weights for policy 1, policy_version 68670 (0.0008) -[2023-10-17 03:01:59,450][62373] Updated weights for policy 0, policy_version 69160 (0.0008) -[2023-10-17 03:01:59,815][62373] Updated weights for policy 0, policy_version 69170 (0.0009) -[2023-10-17 03:02:00,186][62373] Updated weights for policy 0, policy_version 69180 (0.0008) -[2023-10-17 03:02:02,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 141164544. Throughput: 0: 1768.3, 1: 1776.6. Samples: 35304266. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:02:02,215][61453] Avg episode reward: [(0, '10.580'), (1, '9.630')] -[2023-10-17 03:02:02,764][62408] Updated weights for policy 1, policy_version 68680 (0.0010) -[2023-10-17 03:02:03,140][62408] Updated weights for policy 1, policy_version 68690 (0.0009) -[2023-10-17 03:02:03,505][62408] Updated weights for policy 1, policy_version 68700 (0.0010) -[2023-10-17 03:02:04,059][62373] Updated weights for policy 0, policy_version 69190 (0.0007) -[2023-10-17 03:02:04,428][62373] Updated weights for policy 0, policy_version 69200 (0.0008) -[2023-10-17 03:02:04,792][62373] Updated weights for policy 0, policy_version 69210 (0.0007) -[2023-10-17 03:02:07,075][62408] Updated weights for policy 1, policy_version 68710 (0.0011) -[2023-10-17 03:02:07,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 141230080. Throughput: 0: 1772.4, 1: 1758.9. Samples: 35314196. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:02:07,215][61453] Avg episode reward: [(0, '11.110'), (1, '10.140')] -[2023-10-17 03:02:07,454][62408] Updated weights for policy 1, policy_version 68720 (0.0008) -[2023-10-17 03:02:07,821][62408] Updated weights for policy 1, policy_version 68730 (0.0009) -[2023-10-17 03:02:08,511][62373] Updated weights for policy 0, policy_version 69220 (0.0007) -[2023-10-17 03:02:08,888][62373] Updated weights for policy 0, policy_version 69230 (0.0008) -[2023-10-17 03:02:09,257][62373] Updated weights for policy 0, policy_version 69240 (0.0009) -[2023-10-17 03:02:11,742][62408] Updated weights for policy 1, policy_version 68740 (0.0008) -[2023-10-17 03:02:12,107][62408] Updated weights for policy 1, policy_version 68750 (0.0009) -[2023-10-17 03:02:12,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 141295616. Throughput: 0: 1771.4, 1: 1773.2. Samples: 35336428. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:02:12,214][61453] Avg episode reward: [(0, '11.200'), (1, '10.260')] -[2023-10-17 03:02:12,486][62408] Updated weights for policy 1, policy_version 68760 (0.0008) -[2023-10-17 03:02:12,967][62373] Updated weights for policy 0, policy_version 69250 (0.0009) -[2023-10-17 03:02:13,341][62373] Updated weights for policy 0, policy_version 69260 (0.0009) -[2023-10-17 03:02:13,708][62373] Updated weights for policy 0, policy_version 69270 (0.0010) -[2023-10-17 03:02:14,083][62373] Updated weights for policy 0, policy_version 69280 (0.0008) -[2023-10-17 03:02:16,366][62408] Updated weights for policy 1, policy_version 68770 (0.0009) -[2023-10-17 03:02:16,724][62408] Updated weights for policy 1, policy_version 68780 (0.0010) -[2023-10-17 03:02:17,100][62408] Updated weights for policy 1, policy_version 68790 (0.0009) -[2023-10-17 03:02:17,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 141361152. Throughput: 0: 1784.1, 1: 1778.7. Samples: 35358114. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:02:17,215][61453] Avg episode reward: [(0, '10.600'), (1, '10.070')] -[2023-10-17 03:02:17,479][62408] Updated weights for policy 1, policy_version 68800 (0.0007) -[2023-10-17 03:02:17,875][62373] Updated weights for policy 0, policy_version 69290 (0.0009) -[2023-10-17 03:02:18,258][62373] Updated weights for policy 0, policy_version 69300 (0.0009) -[2023-10-17 03:02:18,623][62373] Updated weights for policy 0, policy_version 69310 (0.0008) -[2023-10-17 03:02:21,096][62408] Updated weights for policy 1, policy_version 68810 (0.0009) -[2023-10-17 03:02:21,476][62408] Updated weights for policy 1, policy_version 68820 (0.0008) -[2023-10-17 03:02:21,839][62408] Updated weights for policy 1, policy_version 68830 (0.0007) -[2023-10-17 03:02:22,214][61453] Fps is (10 sec: 16383.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 141459456. Throughput: 0: 1769.4, 1: 1772.5. Samples: 35368458. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:02:22,215][61453] Avg episode reward: [(0, '9.830'), (1, '10.060')] -[2023-10-17 03:02:22,578][62373] Updated weights for policy 0, policy_version 69320 (0.0009) -[2023-10-17 03:02:22,940][62373] Updated weights for policy 0, policy_version 69330 (0.0010) -[2023-10-17 03:02:23,308][62373] Updated weights for policy 0, policy_version 69340 (0.0007) -[2023-10-17 03:02:25,768][62408] Updated weights for policy 1, policy_version 68840 (0.0009) -[2023-10-17 03:02:26,143][62408] Updated weights for policy 1, policy_version 68850 (0.0009) -[2023-10-17 03:02:26,506][62408] Updated weights for policy 1, policy_version 68860 (0.0007) -[2023-10-17 03:02:27,192][62373] Updated weights for policy 0, policy_version 69350 (0.0009) -[2023-10-17 03:02:27,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 141524992. Throughput: 0: 1771.8, 1: 1785.1. Samples: 35389974. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:02:27,215][61453] Avg episode reward: [(0, '9.870'), (1, '9.850')] -[2023-10-17 03:02:27,562][62373] Updated weights for policy 0, policy_version 69360 (0.0011) -[2023-10-17 03:02:27,929][62373] Updated weights for policy 0, policy_version 69370 (0.0008) -[2023-10-17 03:02:30,410][62408] Updated weights for policy 1, policy_version 68870 (0.0008) -[2023-10-17 03:02:30,785][62408] Updated weights for policy 1, policy_version 68880 (0.0010) -[2023-10-17 03:02:31,156][62408] Updated weights for policy 1, policy_version 68890 (0.0009) -[2023-10-17 03:02:31,826][62373] Updated weights for policy 0, policy_version 69380 (0.0009) -[2023-10-17 03:02:32,199][62373] Updated weights for policy 0, policy_version 69390 (0.0007) -[2023-10-17 03:02:32,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 141590528. Throughput: 0: 1786.9, 1: 1763.4. Samples: 35410604. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:02:32,214][61453] Avg episode reward: [(0, '9.740'), (1, '9.610')] -[2023-10-17 03:02:32,571][62373] Updated weights for policy 0, policy_version 69400 (0.0007) -[2023-10-17 03:02:34,847][62408] Updated weights for policy 1, policy_version 68900 (0.0008) -[2023-10-17 03:02:35,215][62408] Updated weights for policy 1, policy_version 68910 (0.0008) -[2023-10-17 03:02:35,589][62408] Updated weights for policy 1, policy_version 68920 (0.0009) -[2023-10-17 03:02:36,351][62373] Updated weights for policy 0, policy_version 69410 (0.0008) -[2023-10-17 03:02:36,756][62373] Updated weights for policy 0, policy_version 69420 (0.0009) -[2023-10-17 03:02:37,131][62373] Updated weights for policy 0, policy_version 69430 (0.0008) -[2023-10-17 03:02:37,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 141656064. Throughput: 0: 1762.2, 1: 1796.8. Samples: 35422062. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:02:37,215][61453] Avg episode reward: [(0, '9.280'), (1, '10.060')] -[2023-10-17 03:02:37,495][62373] Updated weights for policy 0, policy_version 69440 (0.0007) -[2023-10-17 03:02:39,475][62408] Updated weights for policy 1, policy_version 68930 (0.0009) -[2023-10-17 03:02:39,841][62408] Updated weights for policy 1, policy_version 68940 (0.0009) -[2023-10-17 03:02:40,207][62408] Updated weights for policy 1, policy_version 68950 (0.0007) -[2023-10-17 03:02:40,571][62408] Updated weights for policy 1, policy_version 68960 (0.0010) -[2023-10-17 03:02:41,203][62373] Updated weights for policy 0, policy_version 69450 (0.0008) -[2023-10-17 03:02:41,572][62373] Updated weights for policy 0, policy_version 69460 (0.0011) -[2023-10-17 03:02:41,945][62373] Updated weights for policy 0, policy_version 69470 (0.0008) -[2023-10-17 03:02:42,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 141754368. Throughput: 0: 1788.8, 1: 1769.7. Samples: 35442540. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:02:42,214][61453] Avg episode reward: [(0, '8.620'), (1, '8.880')] -[2023-10-17 03:02:44,224][62408] Updated weights for policy 1, policy_version 68970 (0.0007) -[2023-10-17 03:02:44,595][62408] Updated weights for policy 1, policy_version 68980 (0.0007) -[2023-10-17 03:02:44,958][62408] Updated weights for policy 1, policy_version 68990 (0.0008) -[2023-10-17 03:02:45,712][62373] Updated weights for policy 0, policy_version 69480 (0.0007) -[2023-10-17 03:02:46,085][62373] Updated weights for policy 0, policy_version 69490 (0.0008) -[2023-10-17 03:02:46,452][62373] Updated weights for policy 0, policy_version 69500 (0.0009) -[2023-10-17 03:02:47,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 141819904. Throughput: 0: 1766.3, 1: 1775.9. Samples: 35463664. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:02:47,215][61453] Avg episode reward: [(0, '8.940'), (1, '9.180')] -[2023-10-17 03:02:48,927][62408] Updated weights for policy 1, policy_version 69000 (0.0009) -[2023-10-17 03:02:49,301][62408] Updated weights for policy 1, policy_version 69010 (0.0008) -[2023-10-17 03:02:49,676][62408] Updated weights for policy 1, policy_version 69020 (0.0007) -[2023-10-17 03:02:50,242][62373] Updated weights for policy 0, policy_version 69510 (0.0008) -[2023-10-17 03:02:50,608][62373] Updated weights for policy 0, policy_version 69520 (0.0007) -[2023-10-17 03:02:50,977][62373] Updated weights for policy 0, policy_version 69530 (0.0010) -[2023-10-17 03:02:52,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 141885440. Throughput: 0: 1795.3, 1: 1772.1. Samples: 35474728. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:02:52,214][61453] Avg episode reward: [(0, '8.880'), (1, '9.930')] -[2023-10-17 03:02:53,441][62408] Updated weights for policy 1, policy_version 69030 (0.0010) -[2023-10-17 03:02:53,817][62408] Updated weights for policy 1, policy_version 69040 (0.0010) -[2023-10-17 03:02:54,185][62408] Updated weights for policy 1, policy_version 69050 (0.0007) -[2023-10-17 03:02:54,737][62373] Updated weights for policy 0, policy_version 69540 (0.0009) -[2023-10-17 03:02:55,113][62373] Updated weights for policy 0, policy_version 69550 (0.0007) -[2023-10-17 03:02:55,482][62373] Updated weights for policy 0, policy_version 69560 (0.0008) -[2023-10-17 03:02:57,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 141950976. Throughput: 0: 1763.9, 1: 1766.7. Samples: 35495304. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:02:57,215][61453] Avg episode reward: [(0, '8.650'), (1, '9.740')] -[2023-10-17 03:02:58,036][62408] Updated weights for policy 1, policy_version 69060 (0.0012) -[2023-10-17 03:02:58,405][62408] Updated weights for policy 1, policy_version 69070 (0.0010) -[2023-10-17 03:02:58,779][62408] Updated weights for policy 1, policy_version 69080 (0.0010) -[2023-10-17 03:02:59,109][62373] Updated weights for policy 0, policy_version 69570 (0.0009) -[2023-10-17 03:02:59,476][62373] Updated weights for policy 0, policy_version 69580 (0.0007) -[2023-10-17 03:02:59,849][62373] Updated weights for policy 0, policy_version 69590 (0.0010) -[2023-10-17 03:03:00,220][62373] Updated weights for policy 0, policy_version 69600 (0.0010) -[2023-10-17 03:03:02,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 142016512. Throughput: 0: 1762.9, 1: 1777.3. Samples: 35517422. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) -[2023-10-17 03:03:02,214][61453] Avg episode reward: [(0, '8.800'), (1, '10.440')] -[2023-10-17 03:03:02,594][62408] Updated weights for policy 1, policy_version 69090 (0.0009) -[2023-10-17 03:03:02,969][62408] Updated weights for policy 1, policy_version 69100 (0.0007) -[2023-10-17 03:03:03,331][62408] Updated weights for policy 1, policy_version 69110 (0.0007) -[2023-10-17 03:03:03,687][62408] Updated weights for policy 1, policy_version 69120 (0.0008) -[2023-10-17 03:03:04,050][62373] Updated weights for policy 0, policy_version 69610 (0.0009) -[2023-10-17 03:03:04,409][62373] Updated weights for policy 0, policy_version 69620 (0.0008) -[2023-10-17 03:03:04,796][62373] Updated weights for policy 0, policy_version 69630 (0.0008) -[2023-10-17 03:03:07,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 142082048. Throughput: 0: 1766.7, 1: 1759.2. Samples: 35527126. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) -[2023-10-17 03:03:07,215][61453] Avg episode reward: [(0, '9.400'), (1, '10.350')] -[2023-10-17 03:03:07,537][62408] Updated weights for policy 1, policy_version 69130 (0.0009) -[2023-10-17 03:03:07,914][62408] Updated weights for policy 1, policy_version 69140 (0.0008) -[2023-10-17 03:03:08,281][62408] Updated weights for policy 1, policy_version 69150 (0.0007) -[2023-10-17 03:03:08,533][62373] Updated weights for policy 0, policy_version 69640 (0.0009) -[2023-10-17 03:03:08,899][62373] Updated weights for policy 0, policy_version 69650 (0.0008) -[2023-10-17 03:03:09,279][62373] Updated weights for policy 0, policy_version 69660 (0.0010) -[2023-10-17 03:03:12,175][62408] Updated weights for policy 1, policy_version 69160 (0.0007) -[2023-10-17 03:03:12,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 142147584. Throughput: 0: 1768.1, 1: 1766.8. Samples: 35549046. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) -[2023-10-17 03:03:12,215][61453] Avg episode reward: [(0, '9.860'), (1, '10.120')] -[2023-10-17 03:03:12,547][62408] Updated weights for policy 1, policy_version 69170 (0.0007) -[2023-10-17 03:03:12,906][62408] Updated weights for policy 1, policy_version 69180 (0.0007) -[2023-10-17 03:03:13,074][62373] Updated weights for policy 0, policy_version 69670 (0.0008) -[2023-10-17 03:03:13,440][62373] Updated weights for policy 0, policy_version 69680 (0.0009) -[2023-10-17 03:03:13,802][62373] Updated weights for policy 0, policy_version 69690 (0.0009) -[2023-10-17 03:03:16,848][62408] Updated weights for policy 1, policy_version 69190 (0.0008) -[2023-10-17 03:03:17,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 142213120. Throughput: 0: 1774.7, 1: 1782.7. Samples: 35570688. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) -[2023-10-17 03:03:17,216][61453] Avg episode reward: [(0, '9.750'), (1, '10.390')] -[2023-10-17 03:03:17,241][62408] Updated weights for policy 1, policy_version 69200 (0.0009) -[2023-10-17 03:03:17,619][62408] Updated weights for policy 1, policy_version 69210 (0.0009) -[2023-10-17 03:03:17,734][62373] Updated weights for policy 0, policy_version 69700 (0.0009) -[2023-10-17 03:03:18,105][62373] Updated weights for policy 0, policy_version 69710 (0.0008) -[2023-10-17 03:03:18,482][62373] Updated weights for policy 0, policy_version 69720 (0.0007) -[2023-10-17 03:03:21,362][62408] Updated weights for policy 1, policy_version 69220 (0.0010) -[2023-10-17 03:03:21,730][62408] Updated weights for policy 1, policy_version 69230 (0.0007) -[2023-10-17 03:03:22,093][62408] Updated weights for policy 1, policy_version 69240 (0.0009) -[2023-10-17 03:03:22,214][61453] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 142278656. Throughput: 0: 1768.1, 1: 1756.2. Samples: 35580658. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) -[2023-10-17 03:03:22,214][61453] Avg episode reward: [(0, '10.100'), (1, '9.700')] -[2023-10-17 03:03:22,305][62373] Updated weights for policy 0, policy_version 69730 (0.0008) -[2023-10-17 03:03:22,683][62373] Updated weights for policy 0, policy_version 69740 (0.0011) -[2023-10-17 03:03:23,049][62373] Updated weights for policy 0, policy_version 69750 (0.0011) -[2023-10-17 03:03:23,416][62373] Updated weights for policy 0, policy_version 69760 (0.0010) -[2023-10-17 03:03:25,947][62408] Updated weights for policy 1, policy_version 69250 (0.0009) -[2023-10-17 03:03:26,305][62408] Updated weights for policy 1, policy_version 69260 (0.0009) -[2023-10-17 03:03:26,673][62408] Updated weights for policy 1, policy_version 69270 (0.0007) -[2023-10-17 03:03:27,037][62408] Updated weights for policy 1, policy_version 69280 (0.0007) -[2023-10-17 03:03:27,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 142376960. Throughput: 0: 1771.5, 1: 1781.6. Samples: 35602432. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) -[2023-10-17 03:03:27,215][61453] Avg episode reward: [(0, '9.650'), (1, '10.280')] -[2023-10-17 03:03:27,286][62373] Updated weights for policy 0, policy_version 69770 (0.0009) -[2023-10-17 03:03:27,653][62373] Updated weights for policy 0, policy_version 69780 (0.0009) -[2023-10-17 03:03:28,021][62373] Updated weights for policy 0, policy_version 69790 (0.0009) -[2023-10-17 03:03:30,859][62408] Updated weights for policy 1, policy_version 69290 (0.0008) -[2023-10-17 03:03:31,229][62408] Updated weights for policy 1, policy_version 69300 (0.0009) -[2023-10-17 03:03:31,600][62408] Updated weights for policy 1, policy_version 69310 (0.0009) -[2023-10-17 03:03:31,793][62373] Updated weights for policy 0, policy_version 69800 (0.0007) -[2023-10-17 03:03:32,163][62373] Updated weights for policy 0, policy_version 69810 (0.0008) -[2023-10-17 03:03:32,215][61453] Fps is (10 sec: 16382.0, 60 sec: 14199.2, 300 sec: 14217.9). Total num frames: 142442496. Throughput: 0: 1787.9, 1: 1741.7. Samples: 35622496. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) -[2023-10-17 03:03:32,216][61453] Avg episode reward: [(0, '10.430'), (1, '9.850')] -[2023-10-17 03:03:32,225][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000069312_70975488.pth... -[2023-10-17 03:03:32,254][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000067648_69271552.pth -[2023-10-17 03:03:32,531][62373] Updated weights for policy 0, policy_version 69820 (0.0010) -[2023-10-17 03:03:32,676][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000069824_71499776.pth... -[2023-10-17 03:03:32,716][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000068160_69795840.pth -[2023-10-17 03:03:35,426][62408] Updated weights for policy 1, policy_version 69320 (0.0009) -[2023-10-17 03:03:35,791][62408] Updated weights for policy 1, policy_version 69330 (0.0009) -[2023-10-17 03:03:36,160][62408] Updated weights for policy 1, policy_version 69340 (0.0007) -[2023-10-17 03:03:36,305][62373] Updated weights for policy 0, policy_version 69830 (0.0008) -[2023-10-17 03:03:36,681][62373] Updated weights for policy 0, policy_version 69840 (0.0007) -[2023-10-17 03:03:37,056][62373] Updated weights for policy 0, policy_version 69850 (0.0009) -[2023-10-17 03:03:37,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 142508032. Throughput: 0: 1763.1, 1: 1772.3. Samples: 35633822. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) -[2023-10-17 03:03:37,215][61453] Avg episode reward: [(0, '11.050'), (1, '10.310')] -[2023-10-17 03:03:39,952][62408] Updated weights for policy 1, policy_version 69350 (0.0008) -[2023-10-17 03:03:40,328][62408] Updated weights for policy 1, policy_version 69360 (0.0010) -[2023-10-17 03:03:40,687][62408] Updated weights for policy 1, policy_version 69370 (0.0009) -[2023-10-17 03:03:40,757][62373] Updated weights for policy 0, policy_version 69860 (0.0010) -[2023-10-17 03:03:41,132][62373] Updated weights for policy 0, policy_version 69870 (0.0008) -[2023-10-17 03:03:41,502][62373] Updated weights for policy 0, policy_version 69880 (0.0007) -[2023-10-17 03:03:42,214][61453] Fps is (10 sec: 16385.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 142606336. Throughput: 0: 1791.6, 1: 1749.2. Samples: 35654640. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) -[2023-10-17 03:03:42,214][61453] Avg episode reward: [(0, '10.180'), (1, '9.610')] -[2023-10-17 03:03:44,487][62408] Updated weights for policy 1, policy_version 69380 (0.0008) -[2023-10-17 03:03:44,858][62408] Updated weights for policy 1, policy_version 69390 (0.0007) -[2023-10-17 03:03:45,227][62408] Updated weights for policy 1, policy_version 69400 (0.0009) -[2023-10-17 03:03:45,360][62373] Updated weights for policy 0, policy_version 69890 (0.0008) -[2023-10-17 03:03:45,718][62373] Updated weights for policy 0, policy_version 69900 (0.0009) -[2023-10-17 03:03:46,089][62373] Updated weights for policy 0, policy_version 69910 (0.0008) -[2023-10-17 03:03:46,456][62373] Updated weights for policy 0, policy_version 69920 (0.0007) -[2023-10-17 03:03:47,214][61453] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 142671872. Throughput: 0: 1765.4, 1: 1746.3. Samples: 35675450. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-17 03:03:47,214][61453] Avg episode reward: [(0, '10.170'), (1, '10.500')] -[2023-10-17 03:03:49,135][62408] Updated weights for policy 1, policy_version 69410 (0.0008) -[2023-10-17 03:03:49,512][62408] Updated weights for policy 1, policy_version 69420 (0.0010) -[2023-10-17 03:03:49,871][62408] Updated weights for policy 1, policy_version 69430 (0.0010) -[2023-10-17 03:03:50,241][62408] Updated weights for policy 1, policy_version 69440 (0.0009) -[2023-10-17 03:03:50,320][62373] Updated weights for policy 0, policy_version 69930 (0.0007) -[2023-10-17 03:03:50,685][62373] Updated weights for policy 0, policy_version 69940 (0.0009) -[2023-10-17 03:03:51,064][62373] Updated weights for policy 0, policy_version 69950 (0.0010) -[2023-10-17 03:03:52,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 142737408. Throughput: 0: 1792.9, 1: 1754.8. Samples: 35686770. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-17 03:03:52,214][61453] Avg episode reward: [(0, '9.790'), (1, '10.300')] -[2023-10-17 03:03:54,096][62408] Updated weights for policy 1, policy_version 69450 (0.0009) -[2023-10-17 03:03:54,453][62408] Updated weights for policy 1, policy_version 69460 (0.0008) -[2023-10-17 03:03:54,729][62373] Updated weights for policy 0, policy_version 69960 (0.0008) -[2023-10-17 03:03:54,818][62408] Updated weights for policy 1, policy_version 69470 (0.0009) -[2023-10-17 03:03:55,095][62373] Updated weights for policy 0, policy_version 69970 (0.0008) -[2023-10-17 03:03:55,454][62373] Updated weights for policy 0, policy_version 69980 (0.0009) -[2023-10-17 03:03:57,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 142802944. Throughput: 0: 1765.0, 1: 1748.5. Samples: 35707152. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-17 03:03:57,215][61453] Avg episode reward: [(0, '9.430'), (1, '10.520')] -[2023-10-17 03:03:58,639][62408] Updated weights for policy 1, policy_version 69480 (0.0007) -[2023-10-17 03:03:59,004][62408] Updated weights for policy 1, policy_version 69490 (0.0010) -[2023-10-17 03:03:59,240][62373] Updated weights for policy 0, policy_version 69990 (0.0007) -[2023-10-17 03:03:59,371][62408] Updated weights for policy 1, policy_version 69500 (0.0007) -[2023-10-17 03:03:59,606][62373] Updated weights for policy 0, policy_version 70000 (0.0008) -[2023-10-17 03:03:59,984][62373] Updated weights for policy 0, policy_version 70010 (0.0009) -[2023-10-17 03:04:02,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 142868480. Throughput: 0: 1772.5, 1: 1756.2. Samples: 35729478. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-17 03:04:02,214][61453] Avg episode reward: [(0, '9.710'), (1, '10.320')] -[2023-10-17 03:04:03,252][62408] Updated weights for policy 1, policy_version 69510 (0.0008) -[2023-10-17 03:04:03,613][62408] Updated weights for policy 1, policy_version 69520 (0.0011) -[2023-10-17 03:04:03,849][62373] Updated weights for policy 0, policy_version 70020 (0.0009) -[2023-10-17 03:04:03,979][62408] Updated weights for policy 1, policy_version 69530 (0.0008) -[2023-10-17 03:04:04,210][62373] Updated weights for policy 0, policy_version 70030 (0.0009) -[2023-10-17 03:04:04,583][62373] Updated weights for policy 0, policy_version 70040 (0.0010) -[2023-10-17 03:04:07,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 142934016. Throughput: 0: 1772.1, 1: 1752.7. Samples: 35739276. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-17 03:04:07,215][61453] Avg episode reward: [(0, '8.620'), (1, '10.620')] -[2023-10-17 03:04:07,724][62408] Updated weights for policy 1, policy_version 69540 (0.0009) -[2023-10-17 03:04:08,084][62408] Updated weights for policy 1, policy_version 69550 (0.0010) -[2023-10-17 03:04:08,452][62408] Updated weights for policy 1, policy_version 69560 (0.0009) -[2023-10-17 03:04:08,576][62373] Updated weights for policy 0, policy_version 70050 (0.0010) -[2023-10-17 03:04:08,950][62373] Updated weights for policy 0, policy_version 70060 (0.0008) -[2023-10-17 03:04:09,321][62373] Updated weights for policy 0, policy_version 70070 (0.0007) -[2023-10-17 03:04:09,692][62373] Updated weights for policy 0, policy_version 70080 (0.0009) -[2023-10-17 03:04:12,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 142999552. Throughput: 0: 1770.1, 1: 1763.4. Samples: 35761440. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-17 03:04:12,215][61453] Avg episode reward: [(0, '8.720'), (1, '10.420')] -[2023-10-17 03:04:12,411][62408] Updated weights for policy 1, policy_version 69570 (0.0008) -[2023-10-17 03:04:12,771][62408] Updated weights for policy 1, policy_version 69580 (0.0008) -[2023-10-17 03:04:13,145][62408] Updated weights for policy 1, policy_version 69590 (0.0009) -[2023-10-17 03:04:13,332][62373] Updated weights for policy 0, policy_version 70090 (0.0011) -[2023-10-17 03:04:13,506][62408] Updated weights for policy 1, policy_version 69600 (0.0008) -[2023-10-17 03:04:13,703][62373] Updated weights for policy 0, policy_version 70100 (0.0009) -[2023-10-17 03:04:14,073][62373] Updated weights for policy 0, policy_version 70110 (0.0008) -[2023-10-17 03:04:17,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 143065088. Throughput: 0: 1779.2, 1: 1792.0. Samples: 35783196. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-17 03:04:17,215][61453] Avg episode reward: [(0, '8.980'), (1, '10.010')] -[2023-10-17 03:04:17,314][62408] Updated weights for policy 1, policy_version 69610 (0.0010) -[2023-10-17 03:04:17,684][62408] Updated weights for policy 1, policy_version 69620 (0.0010) -[2023-10-17 03:04:17,935][62373] Updated weights for policy 0, policy_version 70120 (0.0009) -[2023-10-17 03:04:18,044][62408] Updated weights for policy 1, policy_version 69630 (0.0008) -[2023-10-17 03:04:18,305][62373] Updated weights for policy 0, policy_version 70130 (0.0008) -[2023-10-17 03:04:18,676][62373] Updated weights for policy 0, policy_version 70140 (0.0007) -[2023-10-17 03:04:21,853][62408] Updated weights for policy 1, policy_version 69640 (0.0007) -[2023-10-17 03:04:22,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 143130624. Throughput: 0: 1773.0, 1: 1762.1. Samples: 35792904. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-17 03:04:22,214][61453] Avg episode reward: [(0, '9.350'), (1, '9.750')] -[2023-10-17 03:04:22,229][62408] Updated weights for policy 1, policy_version 69650 (0.0008) -[2023-10-17 03:04:22,451][62373] Updated weights for policy 0, policy_version 70150 (0.0007) -[2023-10-17 03:04:22,589][62408] Updated weights for policy 1, policy_version 69660 (0.0008) -[2023-10-17 03:04:22,824][62373] Updated weights for policy 0, policy_version 70160 (0.0008) -[2023-10-17 03:04:23,202][62373] Updated weights for policy 0, policy_version 70170 (0.0011) -[2023-10-17 03:04:26,535][62408] Updated weights for policy 1, policy_version 69670 (0.0008) -[2023-10-17 03:04:26,892][62408] Updated weights for policy 1, policy_version 69680 (0.0009) -[2023-10-17 03:04:27,151][62373] Updated weights for policy 0, policy_version 70180 (0.0009) -[2023-10-17 03:04:27,214][61453] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 143196160. Throughput: 0: 1769.8, 1: 1785.5. Samples: 35814626. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-17 03:04:27,215][61453] Avg episode reward: [(0, '9.780'), (1, '10.500')] -[2023-10-17 03:04:27,266][62408] Updated weights for policy 1, policy_version 69690 (0.0007) -[2023-10-17 03:04:27,524][62373] Updated weights for policy 0, policy_version 70190 (0.0008) -[2023-10-17 03:04:27,887][62373] Updated weights for policy 0, policy_version 70200 (0.0008) -[2023-10-17 03:04:31,042][62408] Updated weights for policy 1, policy_version 69700 (0.0007) -[2023-10-17 03:04:31,406][62408] Updated weights for policy 1, policy_version 69710 (0.0007) -[2023-10-17 03:04:31,760][62373] Updated weights for policy 0, policy_version 70210 (0.0008) -[2023-10-17 03:04:31,772][62408] Updated weights for policy 1, policy_version 69720 (0.0007) -[2023-10-17 03:04:32,128][62373] Updated weights for policy 0, policy_version 70220 (0.0009) -[2023-10-17 03:04:32,214][61453] Fps is (10 sec: 16383.6, 60 sec: 14199.7, 300 sec: 14218.0). Total num frames: 143294464. Throughput: 0: 1788.3, 1: 1769.1. Samples: 35835534. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-17 03:04:32,215][61453] Avg episode reward: [(0, '9.950'), (1, '9.870')] -[2023-10-17 03:04:32,506][62373] Updated weights for policy 0, policy_version 70230 (0.0009) -[2023-10-17 03:04:32,874][62373] Updated weights for policy 0, policy_version 70240 (0.0007) -[2023-10-17 03:04:35,447][62408] Updated weights for policy 1, policy_version 69730 (0.0008) -[2023-10-17 03:04:35,809][62408] Updated weights for policy 1, policy_version 69740 (0.0009) -[2023-10-17 03:04:36,175][62408] Updated weights for policy 1, policy_version 69750 (0.0008) -[2023-10-17 03:04:36,536][62408] Updated weights for policy 1, policy_version 69760 (0.0008) -[2023-10-17 03:04:36,723][62373] Updated weights for policy 0, policy_version 70250 (0.0007) -[2023-10-17 03:04:37,091][62373] Updated weights for policy 0, policy_version 70260 (0.0008) -[2023-10-17 03:04:37,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 143360000. Throughput: 0: 1765.3, 1: 1788.7. Samples: 35846700. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:04:37,215][61453] Avg episode reward: [(0, '9.930'), (1, '10.110')] -[2023-10-17 03:04:37,466][62373] Updated weights for policy 0, policy_version 70270 (0.0007) -[2023-10-17 03:04:40,369][62408] Updated weights for policy 1, policy_version 69770 (0.0008) -[2023-10-17 03:04:40,742][62408] Updated weights for policy 1, policy_version 69780 (0.0009) -[2023-10-17 03:04:41,094][62373] Updated weights for policy 0, policy_version 70280 (0.0008) -[2023-10-17 03:04:41,119][62408] Updated weights for policy 1, policy_version 69790 (0.0009) -[2023-10-17 03:04:41,466][62373] Updated weights for policy 0, policy_version 70290 (0.0008) -[2023-10-17 03:04:41,833][62373] Updated weights for policy 0, policy_version 70300 (0.0007) -[2023-10-17 03:04:42,214][61453] Fps is (10 sec: 16384.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 143458304. Throughput: 0: 1793.0, 1: 1775.2. Samples: 35867722. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:04:42,214][61453] Avg episode reward: [(0, '10.290'), (1, '10.720')] -[2023-10-17 03:04:44,867][62408] Updated weights for policy 1, policy_version 69800 (0.0009) -[2023-10-17 03:04:45,225][62408] Updated weights for policy 1, policy_version 69810 (0.0008) -[2023-10-17 03:04:45,587][62408] Updated weights for policy 1, policy_version 69820 (0.0008) -[2023-10-17 03:04:45,692][62373] Updated weights for policy 0, policy_version 70310 (0.0008) -[2023-10-17 03:04:46,059][62373] Updated weights for policy 0, policy_version 70320 (0.0009) -[2023-10-17 03:04:46,426][62373] Updated weights for policy 0, policy_version 70330 (0.0008) -[2023-10-17 03:04:47,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 143523840. Throughput: 0: 1760.3, 1: 1768.1. Samples: 35888256. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:04:47,215][61453] Avg episode reward: [(0, '10.540'), (1, '9.860')] -[2023-10-17 03:04:49,273][62408] Updated weights for policy 1, policy_version 69830 (0.0009) -[2023-10-17 03:04:49,645][62408] Updated weights for policy 1, policy_version 69840 (0.0008) -[2023-10-17 03:04:50,011][62408] Updated weights for policy 1, policy_version 69850 (0.0007) -[2023-10-17 03:04:50,184][62373] Updated weights for policy 0, policy_version 70340 (0.0009) -[2023-10-17 03:04:50,555][62373] Updated weights for policy 0, policy_version 70350 (0.0009) -[2023-10-17 03:04:50,932][62373] Updated weights for policy 0, policy_version 70360 (0.0009) -[2023-10-17 03:04:52,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 143589376. Throughput: 0: 1793.4, 1: 1770.9. Samples: 35899670. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:04:52,214][61453] Avg episode reward: [(0, '10.270'), (1, '10.300')] -[2023-10-17 03:04:53,748][62408] Updated weights for policy 1, policy_version 69860 (0.0007) -[2023-10-17 03:04:54,111][62408] Updated weights for policy 1, policy_version 69870 (0.0007) -[2023-10-17 03:04:54,481][62408] Updated weights for policy 1, policy_version 69880 (0.0010) -[2023-10-17 03:04:54,668][62373] Updated weights for policy 0, policy_version 70370 (0.0007) -[2023-10-17 03:04:55,052][62373] Updated weights for policy 0, policy_version 70380 (0.0008) -[2023-10-17 03:04:55,422][62373] Updated weights for policy 0, policy_version 70390 (0.0010) -[2023-10-17 03:04:55,796][62373] Updated weights for policy 0, policy_version 70400 (0.0008) -[2023-10-17 03:04:57,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 143654912. Throughput: 0: 1766.5, 1: 1759.7. Samples: 35920122. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:04:57,215][61453] Avg episode reward: [(0, '9.790'), (1, '10.830')] -[2023-10-17 03:04:58,420][62408] Updated weights for policy 1, policy_version 69890 (0.0008) -[2023-10-17 03:04:58,782][62408] Updated weights for policy 1, policy_version 69900 (0.0008) -[2023-10-17 03:04:59,147][62408] Updated weights for policy 1, policy_version 69910 (0.0010) -[2023-10-17 03:04:59,515][62373] Updated weights for policy 0, policy_version 70410 (0.0007) -[2023-10-17 03:04:59,517][62408] Updated weights for policy 1, policy_version 69920 (0.0009) -[2023-10-17 03:04:59,886][62373] Updated weights for policy 0, policy_version 70420 (0.0009) -[2023-10-17 03:05:00,262][62373] Updated weights for policy 0, policy_version 70430 (0.0007) -[2023-10-17 03:05:02,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 143720448. Throughput: 0: 1773.5, 1: 1762.8. Samples: 35942330. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:05:02,215][61453] Avg episode reward: [(0, '10.500'), (1, '10.100')] -[2023-10-17 03:05:03,223][62408] Updated weights for policy 1, policy_version 69930 (0.0008) -[2023-10-17 03:05:03,593][62408] Updated weights for policy 1, policy_version 69940 (0.0009) -[2023-10-17 03:05:03,960][62373] Updated weights for policy 0, policy_version 70440 (0.0008) -[2023-10-17 03:05:03,962][62408] Updated weights for policy 1, policy_version 69950 (0.0008) -[2023-10-17 03:05:04,327][62373] Updated weights for policy 0, policy_version 70450 (0.0008) -[2023-10-17 03:05:04,701][62373] Updated weights for policy 0, policy_version 70460 (0.0009) -[2023-10-17 03:05:07,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 143785984. Throughput: 0: 1771.2, 1: 1767.2. Samples: 35952134. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:05:07,215][61453] Avg episode reward: [(0, '10.520'), (1, '10.720')] -[2023-10-17 03:05:07,909][62408] Updated weights for policy 1, policy_version 69960 (0.0008) -[2023-10-17 03:05:08,274][62408] Updated weights for policy 1, policy_version 69970 (0.0010) -[2023-10-17 03:05:08,575][62373] Updated weights for policy 0, policy_version 70470 (0.0008) -[2023-10-17 03:05:08,638][62408] Updated weights for policy 1, policy_version 69980 (0.0007) -[2023-10-17 03:05:08,946][62373] Updated weights for policy 0, policy_version 70480 (0.0008) -[2023-10-17 03:05:09,311][62373] Updated weights for policy 0, policy_version 70490 (0.0011) -[2023-10-17 03:05:12,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 143851520. Throughput: 0: 1777.3, 1: 1765.0. Samples: 35974030. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:05:12,215][61453] Avg episode reward: [(0, '11.140'), (1, '9.990')] -[2023-10-17 03:05:12,609][62408] Updated weights for policy 1, policy_version 69990 (0.0009) -[2023-10-17 03:05:12,972][62408] Updated weights for policy 1, policy_version 70000 (0.0008) -[2023-10-17 03:05:13,143][62373] Updated weights for policy 0, policy_version 70500 (0.0009) -[2023-10-17 03:05:13,342][62408] Updated weights for policy 1, policy_version 70010 (0.0008) -[2023-10-17 03:05:13,511][62373] Updated weights for policy 0, policy_version 70510 (0.0008) -[2023-10-17 03:05:13,888][62373] Updated weights for policy 0, policy_version 70520 (0.0008) -[2023-10-17 03:05:17,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 143917056. Throughput: 0: 1781.6, 1: 1787.3. Samples: 35996136. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:05:17,215][61453] Avg episode reward: [(0, '10.690'), (1, '10.230')] -[2023-10-17 03:05:17,252][62408] Updated weights for policy 1, policy_version 70020 (0.0008) -[2023-10-17 03:05:17,626][62408] Updated weights for policy 1, policy_version 70030 (0.0012) -[2023-10-17 03:05:17,821][62373] Updated weights for policy 0, policy_version 70530 (0.0008) -[2023-10-17 03:05:17,981][62408] Updated weights for policy 1, policy_version 70040 (0.0008) -[2023-10-17 03:05:18,191][62373] Updated weights for policy 0, policy_version 70540 (0.0007) -[2023-10-17 03:05:18,556][62373] Updated weights for policy 0, policy_version 70550 (0.0007) -[2023-10-17 03:05:18,931][62373] Updated weights for policy 0, policy_version 70560 (0.0009) -[2023-10-17 03:05:21,718][62408] Updated weights for policy 1, policy_version 70050 (0.0007) -[2023-10-17 03:05:22,083][62408] Updated weights for policy 1, policy_version 70060 (0.0007) -[2023-10-17 03:05:22,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 143982592. Throughput: 0: 1772.6, 1: 1759.0. Samples: 36005624. Policy #0 lag: (min: 31.0, avg: 32.9, max: 59.0) -[2023-10-17 03:05:22,215][61453] Avg episode reward: [(0, '10.620'), (1, '10.680')] -[2023-10-17 03:05:22,447][62408] Updated weights for policy 1, policy_version 70070 (0.0007) -[2023-10-17 03:05:22,704][62373] Updated weights for policy 0, policy_version 70570 (0.0007) -[2023-10-17 03:05:22,814][62408] Updated weights for policy 1, policy_version 70080 (0.0008) -[2023-10-17 03:05:23,070][62373] Updated weights for policy 0, policy_version 70580 (0.0007) -[2023-10-17 03:05:23,438][62373] Updated weights for policy 0, policy_version 70590 (0.0010) -[2023-10-17 03:05:26,609][62408] Updated weights for policy 1, policy_version 70090 (0.0007) -[2023-10-17 03:05:26,973][62408] Updated weights for policy 1, policy_version 70100 (0.0007) -[2023-10-17 03:05:27,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 144048128. Throughput: 0: 1770.8, 1: 1783.8. Samples: 36027678. Policy #0 lag: (min: 31.0, avg: 32.9, max: 59.0) -[2023-10-17 03:05:27,214][61453] Avg episode reward: [(0, '10.240'), (1, '10.530')] -[2023-10-17 03:05:27,325][62373] Updated weights for policy 0, policy_version 70600 (0.0008) -[2023-10-17 03:05:27,340][62408] Updated weights for policy 1, policy_version 70110 (0.0008) -[2023-10-17 03:05:27,690][62373] Updated weights for policy 0, policy_version 70610 (0.0009) -[2023-10-17 03:05:28,060][62373] Updated weights for policy 0, policy_version 70620 (0.0009) -[2023-10-17 03:05:31,137][62408] Updated weights for policy 1, policy_version 70120 (0.0007) -[2023-10-17 03:05:31,500][62408] Updated weights for policy 1, policy_version 70130 (0.0007) -[2023-10-17 03:05:31,862][62408] Updated weights for policy 1, policy_version 70140 (0.0008) -[2023-10-17 03:05:31,865][62373] Updated weights for policy 0, policy_version 70630 (0.0009) -[2023-10-17 03:05:32,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 144146432. Throughput: 0: 1790.2, 1: 1763.6. Samples: 36048178. Policy #0 lag: (min: 31.0, avg: 32.9, max: 59.0) -[2023-10-17 03:05:32,215][61453] Avg episode reward: [(0, '10.850'), (1, '9.990')] -[2023-10-17 03:05:32,226][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000070144_71827456.pth... -[2023-10-17 03:05:32,242][62373] Updated weights for policy 0, policy_version 70640 (0.0009) -[2023-10-17 03:05:32,260][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000068480_70123520.pth -[2023-10-17 03:05:32,613][62373] Updated weights for policy 0, policy_version 70650 (0.0010) -[2023-10-17 03:05:32,827][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000070656_72351744.pth... -[2023-10-17 03:05:32,865][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000068992_70647808.pth -[2023-10-17 03:05:35,887][62408] Updated weights for policy 1, policy_version 70150 (0.0008) -[2023-10-17 03:05:36,265][62408] Updated weights for policy 1, policy_version 70160 (0.0007) -[2023-10-17 03:05:36,444][62373] Updated weights for policy 0, policy_version 70660 (0.0008) -[2023-10-17 03:05:36,635][62408] Updated weights for policy 1, policy_version 70170 (0.0009) -[2023-10-17 03:05:36,809][62373] Updated weights for policy 0, policy_version 70670 (0.0009) -[2023-10-17 03:05:37,180][62373] Updated weights for policy 0, policy_version 70680 (0.0008) -[2023-10-17 03:05:37,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 144211968. Throughput: 0: 1764.9, 1: 1783.6. Samples: 36059350. Policy #0 lag: (min: 31.0, avg: 32.9, max: 59.0) -[2023-10-17 03:05:37,215][61453] Avg episode reward: [(0, '10.140'), (1, '9.990')] -[2023-10-17 03:05:40,333][62408] Updated weights for policy 1, policy_version 70180 (0.0008) -[2023-10-17 03:05:40,700][62408] Updated weights for policy 1, policy_version 70190 (0.0008) -[2023-10-17 03:05:40,972][62373] Updated weights for policy 0, policy_version 70690 (0.0008) -[2023-10-17 03:05:41,073][62408] Updated weights for policy 1, policy_version 70200 (0.0008) -[2023-10-17 03:05:41,374][62373] Updated weights for policy 0, policy_version 70700 (0.0009) -[2023-10-17 03:05:41,755][62373] Updated weights for policy 0, policy_version 70710 (0.0010) -[2023-10-17 03:05:42,118][62373] Updated weights for policy 0, policy_version 70720 (0.0011) -[2023-10-17 03:05:42,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 144310272. Throughput: 0: 1798.7, 1: 1768.0. Samples: 36080624. Policy #0 lag: (min: 31.0, avg: 32.9, max: 59.0) -[2023-10-17 03:05:42,215][61453] Avg episode reward: [(0, '8.950'), (1, '10.210')] -[2023-10-17 03:05:44,794][62408] Updated weights for policy 1, policy_version 70210 (0.0008) -[2023-10-17 03:05:45,163][62408] Updated weights for policy 1, policy_version 70220 (0.0010) -[2023-10-17 03:05:45,529][62408] Updated weights for policy 1, policy_version 70230 (0.0010) -[2023-10-17 03:05:45,899][62408] Updated weights for policy 1, policy_version 70240 (0.0008) -[2023-10-17 03:05:45,956][62373] Updated weights for policy 0, policy_version 70730 (0.0008) -[2023-10-17 03:05:46,326][62373] Updated weights for policy 0, policy_version 70740 (0.0008) -[2023-10-17 03:05:46,709][62373] Updated weights for policy 0, policy_version 70750 (0.0008) -[2023-10-17 03:05:47,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 144375808. Throughput: 0: 1762.0, 1: 1755.3. Samples: 36100606. Policy #0 lag: (min: 31.0, avg: 32.9, max: 59.0) -[2023-10-17 03:05:47,214][61453] Avg episode reward: [(0, '8.860'), (1, '10.310')] -[2023-10-17 03:05:49,927][62408] Updated weights for policy 1, policy_version 70250 (0.0011) -[2023-10-17 03:05:50,293][62408] Updated weights for policy 1, policy_version 70260 (0.0010) -[2023-10-17 03:05:50,574][62373] Updated weights for policy 0, policy_version 70760 (0.0008) -[2023-10-17 03:05:50,671][62408] Updated weights for policy 1, policy_version 70270 (0.0009) -[2023-10-17 03:05:50,942][62373] Updated weights for policy 0, policy_version 70770 (0.0007) -[2023-10-17 03:05:51,317][62373] Updated weights for policy 0, policy_version 70780 (0.0007) -[2023-10-17 03:05:52,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 144441344. Throughput: 0: 1792.5, 1: 1768.4. Samples: 36112376. Policy #0 lag: (min: 31.0, avg: 32.9, max: 59.0) -[2023-10-17 03:05:52,215][61453] Avg episode reward: [(0, '9.220'), (1, '10.160')] -[2023-10-17 03:05:54,403][62408] Updated weights for policy 1, policy_version 70280 (0.0010) -[2023-10-17 03:05:54,770][62408] Updated weights for policy 1, policy_version 70290 (0.0010) -[2023-10-17 03:05:55,072][62373] Updated weights for policy 0, policy_version 70790 (0.0007) -[2023-10-17 03:05:55,136][62408] Updated weights for policy 1, policy_version 70300 (0.0008) -[2023-10-17 03:05:55,436][62373] Updated weights for policy 0, policy_version 70800 (0.0009) -[2023-10-17 03:05:55,810][62373] Updated weights for policy 0, policy_version 70810 (0.0009) -[2023-10-17 03:05:57,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 144506880. Throughput: 0: 1760.3, 1: 1751.8. Samples: 36132072. Policy #0 lag: (min: 31.0, avg: 32.9, max: 59.0) -[2023-10-17 03:05:57,215][61453] Avg episode reward: [(0, '8.940'), (1, '10.490')] -[2023-10-17 03:05:58,907][62408] Updated weights for policy 1, policy_version 70310 (0.0008) -[2023-10-17 03:05:59,275][62408] Updated weights for policy 1, policy_version 70320 (0.0010) -[2023-10-17 03:05:59,568][62373] Updated weights for policy 0, policy_version 70820 (0.0008) -[2023-10-17 03:05:59,636][62408] Updated weights for policy 1, policy_version 70330 (0.0007) -[2023-10-17 03:05:59,950][62373] Updated weights for policy 0, policy_version 70830 (0.0008) -[2023-10-17 03:06:00,315][62373] Updated weights for policy 0, policy_version 70840 (0.0009) -[2023-10-17 03:06:02,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 144572416. Throughput: 0: 1762.7, 1: 1752.8. Samples: 36154332. Policy #0 lag: (min: 31.0, avg: 32.9, max: 59.0) -[2023-10-17 03:06:02,215][61453] Avg episode reward: [(0, '9.130'), (1, '10.290')] -[2023-10-17 03:06:03,386][62408] Updated weights for policy 1, policy_version 70340 (0.0009) -[2023-10-17 03:06:03,759][62408] Updated weights for policy 1, policy_version 70350 (0.0011) -[2023-10-17 03:06:03,962][62373] Updated weights for policy 0, policy_version 70850 (0.0009) -[2023-10-17 03:06:04,115][62408] Updated weights for policy 1, policy_version 70360 (0.0008) -[2023-10-17 03:06:04,331][62373] Updated weights for policy 0, policy_version 70860 (0.0009) -[2023-10-17 03:06:04,699][62373] Updated weights for policy 0, policy_version 70870 (0.0009) -[2023-10-17 03:06:05,069][62373] Updated weights for policy 0, policy_version 70880 (0.0009) -[2023-10-17 03:06:07,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 144637952. Throughput: 0: 1770.4, 1: 1754.3. Samples: 36164232. Policy #0 lag: (min: 2.0, avg: 3.5, max: 29.0) -[2023-10-17 03:06:07,215][61453] Avg episode reward: [(0, '8.760'), (1, '10.330')] -[2023-10-17 03:06:07,985][62408] Updated weights for policy 1, policy_version 70370 (0.0007) -[2023-10-17 03:06:08,345][62408] Updated weights for policy 1, policy_version 70380 (0.0007) -[2023-10-17 03:06:08,718][62408] Updated weights for policy 1, policy_version 70390 (0.0007) -[2023-10-17 03:06:08,867][62373] Updated weights for policy 0, policy_version 70890 (0.0007) -[2023-10-17 03:06:09,081][62408] Updated weights for policy 1, policy_version 70400 (0.0010) -[2023-10-17 03:06:09,241][62373] Updated weights for policy 0, policy_version 70900 (0.0008) -[2023-10-17 03:06:09,602][62373] Updated weights for policy 0, policy_version 70910 (0.0009) -[2023-10-17 03:06:12,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 144703488. Throughput: 0: 1770.4, 1: 1754.4. Samples: 36186298. Policy #0 lag: (min: 2.0, avg: 3.5, max: 29.0) -[2023-10-17 03:06:12,215][61453] Avg episode reward: [(0, '8.870'), (1, '10.330')] -[2023-10-17 03:06:12,908][62408] Updated weights for policy 1, policy_version 70410 (0.0011) -[2023-10-17 03:06:13,273][62408] Updated weights for policy 1, policy_version 70420 (0.0009) -[2023-10-17 03:06:13,439][62373] Updated weights for policy 0, policy_version 70920 (0.0009) -[2023-10-17 03:06:13,638][62408] Updated weights for policy 1, policy_version 70430 (0.0007) -[2023-10-17 03:06:13,808][62373] Updated weights for policy 0, policy_version 70930 (0.0008) -[2023-10-17 03:06:14,172][62373] Updated weights for policy 0, policy_version 70940 (0.0010) -[2023-10-17 03:06:17,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 144769024. Throughput: 0: 1775.1, 1: 1784.4. Samples: 36208356. Policy #0 lag: (min: 2.0, avg: 3.5, max: 29.0) -[2023-10-17 03:06:17,215][61453] Avg episode reward: [(0, '9.760'), (1, '11.090')] -[2023-10-17 03:06:17,525][62408] Updated weights for policy 1, policy_version 70440 (0.0007) -[2023-10-17 03:06:17,879][62373] Updated weights for policy 0, policy_version 70950 (0.0009) -[2023-10-17 03:06:17,893][62408] Updated weights for policy 1, policy_version 70450 (0.0007) -[2023-10-17 03:06:18,236][62373] Updated weights for policy 0, policy_version 70960 (0.0008) -[2023-10-17 03:06:18,263][62408] Updated weights for policy 1, policy_version 70460 (0.0007) -[2023-10-17 03:06:18,602][62373] Updated weights for policy 0, policy_version 70970 (0.0007) -[2023-10-17 03:06:22,212][62408] Updated weights for policy 1, policy_version 70470 (0.0009) -[2023-10-17 03:06:22,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 144834560. Throughput: 0: 1768.9, 1: 1757.0. Samples: 36218016. Policy #0 lag: (min: 2.0, avg: 3.5, max: 29.0) -[2023-10-17 03:06:22,215][61453] Avg episode reward: [(0, '9.790'), (1, '11.500')] -[2023-10-17 03:06:22,457][62373] Updated weights for policy 0, policy_version 70980 (0.0007) -[2023-10-17 03:06:22,610][62408] Updated weights for policy 1, policy_version 70480 (0.0008) -[2023-10-17 03:06:22,832][62373] Updated weights for policy 0, policy_version 70990 (0.0007) -[2023-10-17 03:06:22,970][62408] Updated weights for policy 1, policy_version 70490 (0.0007) -[2023-10-17 03:06:23,198][62373] Updated weights for policy 0, policy_version 71000 (0.0009) -[2023-10-17 03:06:26,871][62408] Updated weights for policy 1, policy_version 70500 (0.0009) -[2023-10-17 03:06:27,065][62373] Updated weights for policy 0, policy_version 71010 (0.0010) -[2023-10-17 03:06:27,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 144900096. Throughput: 0: 1764.6, 1: 1770.4. Samples: 36239700. Policy #0 lag: (min: 2.0, avg: 3.5, max: 29.0) -[2023-10-17 03:06:27,215][61453] Avg episode reward: [(0, '9.760'), (1, '11.250')] -[2023-10-17 03:06:27,245][62408] Updated weights for policy 1, policy_version 70510 (0.0009) -[2023-10-17 03:06:27,427][62373] Updated weights for policy 0, policy_version 71020 (0.0007) -[2023-10-17 03:06:27,605][62408] Updated weights for policy 1, policy_version 70520 (0.0008) -[2023-10-17 03:06:27,792][62373] Updated weights for policy 0, policy_version 71030 (0.0007) -[2023-10-17 03:06:28,162][62373] Updated weights for policy 0, policy_version 71040 (0.0007) -[2023-10-17 03:06:31,385][62408] Updated weights for policy 1, policy_version 70530 (0.0009) -[2023-10-17 03:06:31,752][62408] Updated weights for policy 1, policy_version 70540 (0.0008) -[2023-10-17 03:06:32,034][62373] Updated weights for policy 0, policy_version 71050 (0.0008) -[2023-10-17 03:06:32,119][62408] Updated weights for policy 1, policy_version 70550 (0.0007) -[2023-10-17 03:06:32,214][61453] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 144965632. Throughput: 0: 1786.0, 1: 1768.6. Samples: 36260564. Policy #0 lag: (min: 2.0, avg: 3.5, max: 29.0) -[2023-10-17 03:06:32,215][61453] Avg episode reward: [(0, '9.780'), (1, '10.920')] -[2023-10-17 03:06:32,399][62373] Updated weights for policy 0, policy_version 71060 (0.0007) -[2023-10-17 03:06:32,482][62408] Updated weights for policy 1, policy_version 70560 (0.0008) -[2023-10-17 03:06:32,774][62373] Updated weights for policy 0, policy_version 71070 (0.0008) -[2023-10-17 03:06:36,335][62408] Updated weights for policy 1, policy_version 70570 (0.0010) -[2023-10-17 03:06:36,569][62373] Updated weights for policy 0, policy_version 71080 (0.0008) -[2023-10-17 03:06:36,697][62408] Updated weights for policy 1, policy_version 70580 (0.0007) -[2023-10-17 03:06:36,940][62373] Updated weights for policy 0, policy_version 71090 (0.0009) -[2023-10-17 03:06:37,057][62408] Updated weights for policy 1, policy_version 70590 (0.0008) -[2023-10-17 03:06:37,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 145063936. Throughput: 0: 1760.8, 1: 1762.9. Samples: 36270944. Policy #0 lag: (min: 2.0, avg: 3.5, max: 29.0) -[2023-10-17 03:06:37,215][61453] Avg episode reward: [(0, '9.120'), (1, '10.680')] -[2023-10-17 03:06:37,314][62373] Updated weights for policy 0, policy_version 71100 (0.0008) -[2023-10-17 03:06:41,013][62408] Updated weights for policy 1, policy_version 70600 (0.0008) -[2023-10-17 03:06:41,130][62373] Updated weights for policy 0, policy_version 71110 (0.0009) -[2023-10-17 03:06:41,387][62408] Updated weights for policy 1, policy_version 70610 (0.0009) -[2023-10-17 03:06:41,500][62373] Updated weights for policy 0, policy_version 71120 (0.0008) -[2023-10-17 03:06:41,754][62408] Updated weights for policy 1, policy_version 70620 (0.0008) -[2023-10-17 03:06:41,867][62373] Updated weights for policy 0, policy_version 71130 (0.0009) -[2023-10-17 03:06:42,214][61453] Fps is (10 sec: 19660.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 145162240. Throughput: 0: 1792.7, 1: 1777.1. Samples: 36292710. Policy #0 lag: (min: 2.0, avg: 3.5, max: 29.0) -[2023-10-17 03:06:42,215][61453] Avg episode reward: [(0, '9.820'), (1, '11.310')] -[2023-10-17 03:06:45,644][62373] Updated weights for policy 0, policy_version 71140 (0.0008) -[2023-10-17 03:06:45,783][62408] Updated weights for policy 1, policy_version 70630 (0.0009) -[2023-10-17 03:06:46,016][62373] Updated weights for policy 0, policy_version 71150 (0.0008) -[2023-10-17 03:06:46,147][62408] Updated weights for policy 1, policy_version 70640 (0.0008) -[2023-10-17 03:06:46,384][62373] Updated weights for policy 0, policy_version 71160 (0.0009) -[2023-10-17 03:06:46,518][62408] Updated weights for policy 1, policy_version 70650 (0.0008) -[2023-10-17 03:06:47,214][61453] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 145227776. Throughput: 0: 1762.6, 1: 1743.0. Samples: 36312082. Policy #0 lag: (min: 2.0, avg: 3.5, max: 29.0) -[2023-10-17 03:06:47,214][61453] Avg episode reward: [(0, '9.990'), (1, '10.580')] -[2023-10-17 03:06:50,321][62373] Updated weights for policy 0, policy_version 71170 (0.0007) -[2023-10-17 03:06:50,391][62408] Updated weights for policy 1, policy_version 70660 (0.0008) -[2023-10-17 03:06:50,685][62373] Updated weights for policy 0, policy_version 71180 (0.0009) -[2023-10-17 03:06:50,757][62408] Updated weights for policy 1, policy_version 70670 (0.0010) -[2023-10-17 03:06:51,052][62373] Updated weights for policy 0, policy_version 71190 (0.0007) -[2023-10-17 03:06:51,124][62408] Updated weights for policy 1, policy_version 70680 (0.0007) -[2023-10-17 03:06:51,424][62373] Updated weights for policy 0, policy_version 71200 (0.0008) -[2023-10-17 03:06:52,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 145293312. Throughput: 0: 1786.2, 1: 1770.6. Samples: 36324288. Policy #0 lag: (min: 0.0, avg: 26.2, max: 32.0) -[2023-10-17 03:06:52,215][61453] Avg episode reward: [(0, '9.890'), (1, '10.260')] -[2023-10-17 03:06:54,713][62408] Updated weights for policy 1, policy_version 70690 (0.0008) -[2023-10-17 03:06:55,074][62408] Updated weights for policy 1, policy_version 70700 (0.0007) -[2023-10-17 03:06:55,156][62373] Updated weights for policy 0, policy_version 71210 (0.0008) -[2023-10-17 03:06:55,448][62408] Updated weights for policy 1, policy_version 70710 (0.0007) -[2023-10-17 03:06:55,524][62373] Updated weights for policy 0, policy_version 71220 (0.0008) -[2023-10-17 03:06:55,813][62408] Updated weights for policy 1, policy_version 70720 (0.0008) -[2023-10-17 03:06:55,891][62373] Updated weights for policy 0, policy_version 71230 (0.0007) -[2023-10-17 03:06:57,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 145358848. Throughput: 0: 1758.7, 1: 1741.9. Samples: 36343826. Policy #0 lag: (min: 0.0, avg: 26.2, max: 32.0) -[2023-10-17 03:06:57,215][61453] Avg episode reward: [(0, '9.710'), (1, '9.820')] -[2023-10-17 03:06:59,542][62373] Updated weights for policy 0, policy_version 71240 (0.0008) -[2023-10-17 03:06:59,612][62408] Updated weights for policy 1, policy_version 70730 (0.0009) -[2023-10-17 03:06:59,909][62373] Updated weights for policy 0, policy_version 71250 (0.0009) -[2023-10-17 03:06:59,992][62408] Updated weights for policy 1, policy_version 70740 (0.0009) -[2023-10-17 03:07:00,268][62373] Updated weights for policy 0, policy_version 71260 (0.0007) -[2023-10-17 03:07:00,360][62408] Updated weights for policy 1, policy_version 70750 (0.0007) -[2023-10-17 03:07:02,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 145424384. Throughput: 0: 1765.2, 1: 1738.7. Samples: 36366032. Policy #0 lag: (min: 0.0, avg: 26.2, max: 32.0) -[2023-10-17 03:07:02,215][61453] Avg episode reward: [(0, '9.830'), (1, '9.990')] -[2023-10-17 03:07:04,082][62373] Updated weights for policy 0, policy_version 71270 (0.0008) -[2023-10-17 03:07:04,197][62408] Updated weights for policy 1, policy_version 70760 (0.0008) -[2023-10-17 03:07:04,448][62373] Updated weights for policy 0, policy_version 71280 (0.0007) -[2023-10-17 03:07:04,561][62408] Updated weights for policy 1, policy_version 70770 (0.0010) -[2023-10-17 03:07:04,813][62373] Updated weights for policy 0, policy_version 71290 (0.0009) -[2023-10-17 03:07:04,924][62408] Updated weights for policy 1, policy_version 70780 (0.0008) -[2023-10-17 03:07:07,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 145489920. Throughput: 0: 1764.0, 1: 1747.5. Samples: 36376030. Policy #0 lag: (min: 0.0, avg: 26.2, max: 32.0) -[2023-10-17 03:07:07,214][61453] Avg episode reward: [(0, '9.820'), (1, '10.400')] -[2023-10-17 03:07:08,764][62373] Updated weights for policy 0, policy_version 71300 (0.0008) -[2023-10-17 03:07:08,789][62408] Updated weights for policy 1, policy_version 70790 (0.0007) -[2023-10-17 03:07:09,139][62373] Updated weights for policy 0, policy_version 71310 (0.0008) -[2023-10-17 03:07:09,150][62408] Updated weights for policy 1, policy_version 70800 (0.0008) -[2023-10-17 03:07:09,509][62373] Updated weights for policy 0, policy_version 71320 (0.0008) -[2023-10-17 03:07:09,513][62408] Updated weights for policy 1, policy_version 70810 (0.0007) -[2023-10-17 03:07:12,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 145555456. Throughput: 0: 1759.2, 1: 1748.8. Samples: 36397564. Policy #0 lag: (min: 0.0, avg: 26.2, max: 32.0) -[2023-10-17 03:07:12,215][61453] Avg episode reward: [(0, '9.190'), (1, '10.570')] -[2023-10-17 03:07:13,380][62408] Updated weights for policy 1, policy_version 70820 (0.0007) -[2023-10-17 03:07:13,387][62373] Updated weights for policy 0, policy_version 71330 (0.0009) -[2023-10-17 03:07:13,743][62408] Updated weights for policy 1, policy_version 70830 (0.0007) -[2023-10-17 03:07:13,788][62373] Updated weights for policy 0, policy_version 71340 (0.0008) -[2023-10-17 03:07:14,110][62408] Updated weights for policy 1, policy_version 70840 (0.0007) -[2023-10-17 03:07:14,153][62373] Updated weights for policy 0, policy_version 71350 (0.0009) -[2023-10-17 03:07:14,523][62373] Updated weights for policy 0, policy_version 71360 (0.0009) -[2023-10-17 03:07:17,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 145620992. Throughput: 0: 1762.5, 1: 1761.9. Samples: 36419162. Policy #0 lag: (min: 0.0, avg: 26.2, max: 32.0) -[2023-10-17 03:07:17,215][61453] Avg episode reward: [(0, '8.660'), (1, '10.640')] -[2023-10-17 03:07:18,056][62408] Updated weights for policy 1, policy_version 70850 (0.0009) -[2023-10-17 03:07:18,373][62373] Updated weights for policy 0, policy_version 71370 (0.0007) -[2023-10-17 03:07:18,419][62408] Updated weights for policy 1, policy_version 70860 (0.0010) -[2023-10-17 03:07:18,739][62373] Updated weights for policy 0, policy_version 71380 (0.0008) -[2023-10-17 03:07:18,789][62408] Updated weights for policy 1, policy_version 70870 (0.0008) -[2023-10-17 03:07:19,105][62373] Updated weights for policy 0, policy_version 71390 (0.0008) -[2023-10-17 03:07:19,153][62408] Updated weights for policy 1, policy_version 70880 (0.0009) -[2023-10-17 03:07:22,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 145686528. Throughput: 0: 1756.1, 1: 1748.4. Samples: 36428646. Policy #0 lag: (min: 0.0, avg: 26.2, max: 32.0) -[2023-10-17 03:07:22,215][61453] Avg episode reward: [(0, '8.440'), (1, '11.830')] -[2023-10-17 03:07:22,217][62252] Saving new best policy, reward=11.830! -[2023-10-17 03:07:22,990][62373] Updated weights for policy 0, policy_version 71400 (0.0007) -[2023-10-17 03:07:23,065][62408] Updated weights for policy 1, policy_version 70890 (0.0007) -[2023-10-17 03:07:23,366][62373] Updated weights for policy 0, policy_version 71410 (0.0008) -[2023-10-17 03:07:23,424][62408] Updated weights for policy 1, policy_version 70900 (0.0009) -[2023-10-17 03:07:23,734][62373] Updated weights for policy 0, policy_version 71420 (0.0008) -[2023-10-17 03:07:23,785][62408] Updated weights for policy 1, policy_version 70910 (0.0008) -[2023-10-17 03:07:27,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 145752064. Throughput: 0: 1749.4, 1: 1752.4. Samples: 36450292. Policy #0 lag: (min: 0.0, avg: 26.2, max: 32.0) -[2023-10-17 03:07:27,215][61453] Avg episode reward: [(0, '7.990'), (1, '11.420')] -[2023-10-17 03:07:27,594][62408] Updated weights for policy 1, policy_version 70920 (0.0008) -[2023-10-17 03:07:27,679][62373] Updated weights for policy 0, policy_version 71430 (0.0008) -[2023-10-17 03:07:27,949][62408] Updated weights for policy 1, policy_version 70930 (0.0008) -[2023-10-17 03:07:28,050][62373] Updated weights for policy 0, policy_version 71440 (0.0007) -[2023-10-17 03:07:28,315][62408] Updated weights for policy 1, policy_version 70940 (0.0008) -[2023-10-17 03:07:28,420][62373] Updated weights for policy 0, policy_version 71450 (0.0008) -[2023-10-17 03:07:32,193][62408] Updated weights for policy 1, policy_version 70950 (0.0007) -[2023-10-17 03:07:32,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 145817600. Throughput: 0: 1772.3, 1: 1785.1. Samples: 36472168. Policy #0 lag: (min: 0.0, avg: 26.2, max: 32.0) -[2023-10-17 03:07:32,215][61453] Avg episode reward: [(0, '8.400'), (1, '11.740')] -[2023-10-17 03:07:32,344][62373] Updated weights for policy 0, policy_version 71460 (0.0008) -[2023-10-17 03:07:32,558][62408] Updated weights for policy 1, policy_version 70960 (0.0009) -[2023-10-17 03:07:32,707][62373] Updated weights for policy 0, policy_version 71470 (0.0008) -[2023-10-17 03:07:32,930][62408] Updated weights for policy 1, policy_version 70970 (0.0008) -[2023-10-17 03:07:33,081][62373] Updated weights for policy 0, policy_version 71480 (0.0007) -[2023-10-17 03:07:33,141][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000070976_72679424.pth... -[2023-10-17 03:07:33,171][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000069312_70975488.pth -[2023-10-17 03:07:33,370][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000071488_73203712.pth... -[2023-10-17 03:07:33,411][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000069824_71499776.pth -[2023-10-17 03:07:36,587][62408] Updated weights for policy 1, policy_version 70980 (0.0009) -[2023-10-17 03:07:36,949][62408] Updated weights for policy 1, policy_version 70990 (0.0010) -[2023-10-17 03:07:37,055][62373] Updated weights for policy 0, policy_version 71490 (0.0009) -[2023-10-17 03:07:37,214][61453] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13995.8). Total num frames: 145883136. Throughput: 0: 1741.7, 1: 1759.1. Samples: 36481822. Policy #0 lag: (min: 0.0, avg: 26.2, max: 32.0) -[2023-10-17 03:07:37,214][61453] Avg episode reward: [(0, '9.130'), (1, '11.610')] -[2023-10-17 03:07:37,324][62408] Updated weights for policy 1, policy_version 71000 (0.0009) -[2023-10-17 03:07:37,422][62373] Updated weights for policy 0, policy_version 71500 (0.0010) -[2023-10-17 03:07:37,799][62373] Updated weights for policy 0, policy_version 71510 (0.0009) -[2023-10-17 03:07:38,167][62373] Updated weights for policy 0, policy_version 71520 (0.0011) -[2023-10-17 03:07:41,057][62408] Updated weights for policy 1, policy_version 71010 (0.0008) -[2023-10-17 03:07:41,419][62408] Updated weights for policy 1, policy_version 71020 (0.0007) -[2023-10-17 03:07:41,776][62373] Updated weights for policy 0, policy_version 71530 (0.0008) -[2023-10-17 03:07:41,783][62408] Updated weights for policy 1, policy_version 71030 (0.0008) -[2023-10-17 03:07:42,137][62373] Updated weights for policy 0, policy_version 71540 (0.0007) -[2023-10-17 03:07:42,154][62408] Updated weights for policy 1, policy_version 71040 (0.0007) -[2023-10-17 03:07:42,214][61453] Fps is (10 sec: 16384.3, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 145981440. Throughput: 0: 1771.4, 1: 1791.0. Samples: 36504134. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:07:42,215][61453] Avg episode reward: [(0, '8.980'), (1, '11.750')] -[2023-10-17 03:07:42,508][62373] Updated weights for policy 0, policy_version 71550 (0.0009) -[2023-10-17 03:07:45,889][62408] Updated weights for policy 1, policy_version 71050 (0.0008) -[2023-10-17 03:07:46,255][62408] Updated weights for policy 1, policy_version 71060 (0.0009) -[2023-10-17 03:07:46,405][62373] Updated weights for policy 0, policy_version 71560 (0.0007) -[2023-10-17 03:07:46,620][62408] Updated weights for policy 1, policy_version 71070 (0.0007) -[2023-10-17 03:07:46,771][62373] Updated weights for policy 0, policy_version 71570 (0.0008) -[2023-10-17 03:07:47,147][62373] Updated weights for policy 0, policy_version 71580 (0.0010) -[2023-10-17 03:07:47,214][61453] Fps is (10 sec: 16383.5, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 146046976. Throughput: 0: 1745.5, 1: 1766.5. Samples: 36524074. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:07:47,215][61453] Avg episode reward: [(0, '9.400'), (1, '11.780')] -[2023-10-17 03:07:50,574][62408] Updated weights for policy 1, policy_version 71080 (0.0012) -[2023-10-17 03:07:50,942][62408] Updated weights for policy 1, policy_version 71090 (0.0008) -[2023-10-17 03:07:51,087][62373] Updated weights for policy 0, policy_version 71590 (0.0010) -[2023-10-17 03:07:51,308][62408] Updated weights for policy 1, policy_version 71100 (0.0009) -[2023-10-17 03:07:51,461][62373] Updated weights for policy 0, policy_version 71600 (0.0008) -[2023-10-17 03:07:51,830][62373] Updated weights for policy 0, policy_version 71610 (0.0010) -[2023-10-17 03:07:52,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 146145280. Throughput: 0: 1764.0, 1: 1786.8. Samples: 36535818. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:07:52,214][61453] Avg episode reward: [(0, '9.970'), (1, '11.710')] -[2023-10-17 03:07:55,035][62408] Updated weights for policy 1, policy_version 71110 (0.0011) -[2023-10-17 03:07:55,397][62408] Updated weights for policy 1, policy_version 71120 (0.0009) -[2023-10-17 03:07:55,552][62373] Updated weights for policy 0, policy_version 71620 (0.0009) -[2023-10-17 03:07:55,763][62408] Updated weights for policy 1, policy_version 71130 (0.0008) -[2023-10-17 03:07:55,911][62373] Updated weights for policy 0, policy_version 71630 (0.0008) -[2023-10-17 03:07:56,290][62373] Updated weights for policy 0, policy_version 71640 (0.0009) -[2023-10-17 03:07:57,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 146210816. Throughput: 0: 1754.0, 1: 1767.5. Samples: 36556034. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:07:57,215][61453] Avg episode reward: [(0, '10.180'), (1, '11.130')] -[2023-10-17 03:07:59,635][62408] Updated weights for policy 1, policy_version 71140 (0.0008) -[2023-10-17 03:08:00,002][62408] Updated weights for policy 1, policy_version 71150 (0.0009) -[2023-10-17 03:08:00,220][62373] Updated weights for policy 0, policy_version 71650 (0.0009) -[2023-10-17 03:08:00,362][62408] Updated weights for policy 1, policy_version 71160 (0.0007) -[2023-10-17 03:08:00,602][62373] Updated weights for policy 0, policy_version 71660 (0.0010) -[2023-10-17 03:08:00,965][62373] Updated weights for policy 0, policy_version 71670 (0.0008) -[2023-10-17 03:08:01,335][62373] Updated weights for policy 0, policy_version 71680 (0.0007) -[2023-10-17 03:08:02,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 146276352. Throughput: 0: 1745.5, 1: 1767.1. Samples: 36577228. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:08:02,215][61453] Avg episode reward: [(0, '9.800'), (1, '11.540')] -[2023-10-17 03:08:04,076][62408] Updated weights for policy 1, policy_version 71170 (0.0008) -[2023-10-17 03:08:04,436][62408] Updated weights for policy 1, policy_version 71180 (0.0008) -[2023-10-17 03:08:04,803][62408] Updated weights for policy 1, policy_version 71190 (0.0008) -[2023-10-17 03:08:05,175][62408] Updated weights for policy 1, policy_version 71200 (0.0007) -[2023-10-17 03:08:05,190][62373] Updated weights for policy 0, policy_version 71690 (0.0007) -[2023-10-17 03:08:05,555][62373] Updated weights for policy 0, policy_version 71700 (0.0007) -[2023-10-17 03:08:05,926][62373] Updated weights for policy 0, policy_version 71710 (0.0007) -[2023-10-17 03:08:07,214][61453] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 146341888. Throughput: 0: 1774.1, 1: 1779.3. Samples: 36588552. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:08:07,214][61453] Avg episode reward: [(0, '9.630'), (1, '10.740')] -[2023-10-17 03:08:09,017][62408] Updated weights for policy 1, policy_version 71210 (0.0009) -[2023-10-17 03:08:09,379][62408] Updated weights for policy 1, policy_version 71220 (0.0008) -[2023-10-17 03:08:09,735][62373] Updated weights for policy 0, policy_version 71720 (0.0007) -[2023-10-17 03:08:09,748][62408] Updated weights for policy 1, policy_version 71230 (0.0008) -[2023-10-17 03:08:10,097][62373] Updated weights for policy 0, policy_version 71730 (0.0007) -[2023-10-17 03:08:10,471][62373] Updated weights for policy 0, policy_version 71740 (0.0007) -[2023-10-17 03:08:12,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 146407424. Throughput: 0: 1752.2, 1: 1768.1. Samples: 36608706. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:08:12,215][61453] Avg episode reward: [(0, '9.420'), (1, '10.260')] -[2023-10-17 03:08:13,777][62408] Updated weights for policy 1, policy_version 71240 (0.0008) -[2023-10-17 03:08:14,146][62408] Updated weights for policy 1, policy_version 71250 (0.0009) -[2023-10-17 03:08:14,177][62373] Updated weights for policy 0, policy_version 71750 (0.0008) -[2023-10-17 03:08:14,520][62408] Updated weights for policy 1, policy_version 71260 (0.0008) -[2023-10-17 03:08:14,550][62373] Updated weights for policy 0, policy_version 71760 (0.0008) -[2023-10-17 03:08:14,924][62373] Updated weights for policy 0, policy_version 71770 (0.0008) -[2023-10-17 03:08:17,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 146472960. Throughput: 0: 1761.2, 1: 1760.6. Samples: 36630652. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:08:17,215][61453] Avg episode reward: [(0, '9.170'), (1, '10.930')] -[2023-10-17 03:08:18,475][62408] Updated weights for policy 1, policy_version 71270 (0.0009) -[2023-10-17 03:08:18,745][62373] Updated weights for policy 0, policy_version 71780 (0.0008) -[2023-10-17 03:08:18,831][62408] Updated weights for policy 1, policy_version 71280 (0.0008) -[2023-10-17 03:08:19,107][62373] Updated weights for policy 0, policy_version 71790 (0.0008) -[2023-10-17 03:08:19,201][62408] Updated weights for policy 1, policy_version 71290 (0.0008) -[2023-10-17 03:08:19,484][62373] Updated weights for policy 0, policy_version 71800 (0.0007) -[2023-10-17 03:08:22,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 146538496. Throughput: 0: 1762.7, 1: 1754.1. Samples: 36640078. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:08:22,215][61453] Avg episode reward: [(0, '9.730'), (1, '11.010')] -[2023-10-17 03:08:23,088][62408] Updated weights for policy 1, policy_version 71300 (0.0010) -[2023-10-17 03:08:23,123][62373] Updated weights for policy 0, policy_version 71810 (0.0007) -[2023-10-17 03:08:23,461][62408] Updated weights for policy 1, policy_version 71310 (0.0008) -[2023-10-17 03:08:23,494][62373] Updated weights for policy 0, policy_version 71820 (0.0008) -[2023-10-17 03:08:23,821][62408] Updated weights for policy 1, policy_version 71320 (0.0007) -[2023-10-17 03:08:23,859][62373] Updated weights for policy 0, policy_version 71830 (0.0008) -[2023-10-17 03:08:24,220][62373] Updated weights for policy 0, policy_version 71840 (0.0008) -[2023-10-17 03:08:27,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14107.0). Total num frames: 146604032. Throughput: 0: 1772.6, 1: 1747.4. Samples: 36662532. Policy #0 lag: (min: 31.0, avg: 32.7, max: 60.0) -[2023-10-17 03:08:27,215][61453] Avg episode reward: [(0, '9.940'), (1, '9.820')] -[2023-10-17 03:08:27,662][62408] Updated weights for policy 1, policy_version 71330 (0.0008) -[2023-10-17 03:08:28,036][62408] Updated weights for policy 1, policy_version 71340 (0.0009) -[2023-10-17 03:08:28,066][62373] Updated weights for policy 0, policy_version 71850 (0.0009) -[2023-10-17 03:08:28,406][62408] Updated weights for policy 1, policy_version 71350 (0.0008) -[2023-10-17 03:08:28,435][62373] Updated weights for policy 0, policy_version 71860 (0.0008) -[2023-10-17 03:08:28,768][62408] Updated weights for policy 1, policy_version 71360 (0.0009) -[2023-10-17 03:08:28,796][62373] Updated weights for policy 0, policy_version 71870 (0.0007) -[2023-10-17 03:08:32,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 146669568. Throughput: 0: 1797.0, 1: 1773.7. Samples: 36684758. Policy #0 lag: (min: 31.0, avg: 32.7, max: 60.0) -[2023-10-17 03:08:32,214][61453] Avg episode reward: [(0, '9.980'), (1, '9.890')] -[2023-10-17 03:08:32,501][62373] Updated weights for policy 0, policy_version 71880 (0.0008) -[2023-10-17 03:08:32,534][62408] Updated weights for policy 1, policy_version 71370 (0.0009) -[2023-10-17 03:08:32,864][62373] Updated weights for policy 0, policy_version 71890 (0.0007) -[2023-10-17 03:08:32,904][62408] Updated weights for policy 1, policy_version 71380 (0.0007) -[2023-10-17 03:08:33,239][62373] Updated weights for policy 0, policy_version 71900 (0.0009) -[2023-10-17 03:08:33,266][62408] Updated weights for policy 1, policy_version 71390 (0.0007) -[2023-10-17 03:08:37,047][62408] Updated weights for policy 1, policy_version 71400 (0.0008) -[2023-10-17 03:08:37,203][62373] Updated weights for policy 0, policy_version 71910 (0.0008) -[2023-10-17 03:08:37,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 146735104. Throughput: 0: 1776.8, 1: 1746.5. Samples: 36694368. Policy #0 lag: (min: 31.0, avg: 32.7, max: 60.0) -[2023-10-17 03:08:37,215][61453] Avg episode reward: [(0, '10.470'), (1, '9.770')] -[2023-10-17 03:08:37,414][62408] Updated weights for policy 1, policy_version 71410 (0.0007) -[2023-10-17 03:08:37,574][62373] Updated weights for policy 0, policy_version 71920 (0.0009) -[2023-10-17 03:08:37,788][62408] Updated weights for policy 1, policy_version 71420 (0.0008) -[2023-10-17 03:08:37,931][62373] Updated weights for policy 0, policy_version 71930 (0.0008) -[2023-10-17 03:08:41,662][62373] Updated weights for policy 0, policy_version 71940 (0.0009) -[2023-10-17 03:08:41,829][62408] Updated weights for policy 1, policy_version 71430 (0.0008) -[2023-10-17 03:08:42,024][62373] Updated weights for policy 0, policy_version 71950 (0.0009) -[2023-10-17 03:08:42,214][61453] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13995.8). Total num frames: 146800640. Throughput: 0: 1794.0, 1: 1771.1. Samples: 36716464. Policy #0 lag: (min: 31.0, avg: 32.7, max: 60.0) -[2023-10-17 03:08:42,214][61453] Avg episode reward: [(0, '10.910'), (1, '10.190')] -[2023-10-17 03:08:42,233][62408] Updated weights for policy 1, policy_version 71440 (0.0008) -[2023-10-17 03:08:42,398][62373] Updated weights for policy 0, policy_version 71960 (0.0010) -[2023-10-17 03:08:42,600][62408] Updated weights for policy 1, policy_version 71450 (0.0008) -[2023-10-17 03:08:46,338][62408] Updated weights for policy 1, policy_version 71460 (0.0008) -[2023-10-17 03:08:46,364][62373] Updated weights for policy 0, policy_version 71970 (0.0008) -[2023-10-17 03:08:46,703][62408] Updated weights for policy 1, policy_version 71470 (0.0007) -[2023-10-17 03:08:46,771][62373] Updated weights for policy 0, policy_version 71980 (0.0007) -[2023-10-17 03:08:47,073][62408] Updated weights for policy 1, policy_version 71480 (0.0009) -[2023-10-17 03:08:47,139][62373] Updated weights for policy 0, policy_version 71990 (0.0009) -[2023-10-17 03:08:47,214][61453] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13995.8). Total num frames: 146866176. Throughput: 0: 1786.8, 1: 1753.8. Samples: 36736554. Policy #0 lag: (min: 31.0, avg: 32.7, max: 60.0) -[2023-10-17 03:08:47,214][61453] Avg episode reward: [(0, '11.190'), (1, '9.790')] -[2023-10-17 03:08:47,512][62373] Updated weights for policy 0, policy_version 72000 (0.0010) -[2023-10-17 03:08:51,014][62408] Updated weights for policy 1, policy_version 71490 (0.0009) -[2023-10-17 03:08:51,373][62373] Updated weights for policy 0, policy_version 72010 (0.0008) -[2023-10-17 03:08:51,373][62408] Updated weights for policy 1, policy_version 71500 (0.0009) -[2023-10-17 03:08:51,737][62373] Updated weights for policy 0, policy_version 72020 (0.0008) -[2023-10-17 03:08:51,742][62408] Updated weights for policy 1, policy_version 71510 (0.0007) -[2023-10-17 03:08:52,100][62408] Updated weights for policy 1, policy_version 71520 (0.0008) -[2023-10-17 03:08:52,114][62373] Updated weights for policy 0, policy_version 72030 (0.0008) -[2023-10-17 03:08:52,214][61453] Fps is (10 sec: 19660.8, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 146997248. Throughput: 0: 1774.2, 1: 1757.6. Samples: 36747480. Policy #0 lag: (min: 31.0, avg: 32.7, max: 60.0) -[2023-10-17 03:08:52,214][61453] Avg episode reward: [(0, '11.240'), (1, '9.620')] -[2023-10-17 03:08:55,821][62373] Updated weights for policy 0, policy_version 72040 (0.0007) -[2023-10-17 03:08:55,961][62408] Updated weights for policy 1, policy_version 71530 (0.0007) -[2023-10-17 03:08:56,192][62373] Updated weights for policy 0, policy_version 72050 (0.0009) -[2023-10-17 03:08:56,315][62408] Updated weights for policy 1, policy_version 71540 (0.0009) -[2023-10-17 03:08:56,565][62373] Updated weights for policy 0, policy_version 72060 (0.0008) -[2023-10-17 03:08:56,677][62408] Updated weights for policy 1, policy_version 71550 (0.0010) -[2023-10-17 03:08:57,214][61453] Fps is (10 sec: 19660.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 147062784. Throughput: 0: 1791.5, 1: 1763.1. Samples: 36768662. Policy #0 lag: (min: 31.0, avg: 32.7, max: 60.0) -[2023-10-17 03:08:57,214][61453] Avg episode reward: [(0, '11.960'), (1, '9.790')] -[2023-10-17 03:09:00,348][62373] Updated weights for policy 0, policy_version 72070 (0.0008) -[2023-10-17 03:09:00,465][62408] Updated weights for policy 1, policy_version 71560 (0.0007) -[2023-10-17 03:09:00,717][62373] Updated weights for policy 0, policy_version 72080 (0.0008) -[2023-10-17 03:09:00,836][62408] Updated weights for policy 1, policy_version 71570 (0.0007) -[2023-10-17 03:09:01,090][62373] Updated weights for policy 0, policy_version 72090 (0.0007) -[2023-10-17 03:09:01,207][62408] Updated weights for policy 1, policy_version 71580 (0.0007) -[2023-10-17 03:09:02,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 147128320. Throughput: 0: 1766.9, 1: 1748.6. Samples: 36788848. Policy #0 lag: (min: 31.0, avg: 32.7, max: 60.0) -[2023-10-17 03:09:02,215][61453] Avg episode reward: [(0, '10.740'), (1, '10.660')] -[2023-10-17 03:09:04,960][62373] Updated weights for policy 0, policy_version 72100 (0.0008) -[2023-10-17 03:09:05,051][62408] Updated weights for policy 1, policy_version 71590 (0.0008) -[2023-10-17 03:09:05,329][62373] Updated weights for policy 0, policy_version 72110 (0.0008) -[2023-10-17 03:09:05,416][62408] Updated weights for policy 1, policy_version 71600 (0.0009) -[2023-10-17 03:09:05,695][62373] Updated weights for policy 0, policy_version 72120 (0.0007) -[2023-10-17 03:09:05,788][62408] Updated weights for policy 1, policy_version 71610 (0.0008) -[2023-10-17 03:09:07,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 147193856. Throughput: 0: 1792.8, 1: 1782.4. Samples: 36800964. Policy #0 lag: (min: 31.0, avg: 32.7, max: 60.0) -[2023-10-17 03:09:07,215][61453] Avg episode reward: [(0, '10.650'), (1, '10.810')] -[2023-10-17 03:09:09,563][62373] Updated weights for policy 0, policy_version 72130 (0.0007) -[2023-10-17 03:09:09,604][62408] Updated weights for policy 1, policy_version 71620 (0.0008) -[2023-10-17 03:09:09,925][62373] Updated weights for policy 0, policy_version 72140 (0.0009) -[2023-10-17 03:09:09,966][62408] Updated weights for policy 1, policy_version 71630 (0.0007) -[2023-10-17 03:09:10,292][62373] Updated weights for policy 0, policy_version 72150 (0.0007) -[2023-10-17 03:09:10,337][62408] Updated weights for policy 1, policy_version 71640 (0.0008) -[2023-10-17 03:09:10,660][62373] Updated weights for policy 0, policy_version 72160 (0.0007) -[2023-10-17 03:09:12,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 147259392. Throughput: 0: 1753.6, 1: 1749.7. Samples: 36820178. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-17 03:09:12,214][61453] Avg episode reward: [(0, '11.180'), (1, '10.170')] -[2023-10-17 03:09:14,061][62408] Updated weights for policy 1, policy_version 71650 (0.0008) -[2023-10-17 03:09:14,426][62408] Updated weights for policy 1, policy_version 71660 (0.0008) -[2023-10-17 03:09:14,461][62373] Updated weights for policy 0, policy_version 72170 (0.0008) -[2023-10-17 03:09:14,793][62408] Updated weights for policy 1, policy_version 71670 (0.0008) -[2023-10-17 03:09:14,824][62373] Updated weights for policy 0, policy_version 72180 (0.0007) -[2023-10-17 03:09:15,155][62408] Updated weights for policy 1, policy_version 71680 (0.0007) -[2023-10-17 03:09:15,192][62373] Updated weights for policy 0, policy_version 72190 (0.0009) -[2023-10-17 03:09:17,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 147324928. Throughput: 0: 1749.0, 1: 1751.4. Samples: 36842276. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-17 03:09:17,214][61453] Avg episode reward: [(0, '10.870'), (1, '10.030')] -[2023-10-17 03:09:18,982][62373] Updated weights for policy 0, policy_version 72200 (0.0007) -[2023-10-17 03:09:19,010][62408] Updated weights for policy 1, policy_version 71690 (0.0008) -[2023-10-17 03:09:19,352][62373] Updated weights for policy 0, policy_version 72210 (0.0009) -[2023-10-17 03:09:19,380][62408] Updated weights for policy 1, policy_version 71700 (0.0008) -[2023-10-17 03:09:19,721][62373] Updated weights for policy 0, policy_version 72220 (0.0007) -[2023-10-17 03:09:19,748][62408] Updated weights for policy 1, policy_version 71710 (0.0008) -[2023-10-17 03:09:22,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 147390464. Throughput: 0: 1750.1, 1: 1750.2. Samples: 36851884. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-17 03:09:22,214][61453] Avg episode reward: [(0, '11.060'), (1, '9.820')] -[2023-10-17 03:09:23,564][62408] Updated weights for policy 1, policy_version 71720 (0.0008) -[2023-10-17 03:09:23,634][62373] Updated weights for policy 0, policy_version 72230 (0.0009) -[2023-10-17 03:09:23,934][62408] Updated weights for policy 1, policy_version 71730 (0.0008) -[2023-10-17 03:09:24,001][62373] Updated weights for policy 0, policy_version 72240 (0.0011) -[2023-10-17 03:09:24,304][62408] Updated weights for policy 1, policy_version 71740 (0.0009) -[2023-10-17 03:09:24,374][62373] Updated weights for policy 0, policy_version 72250 (0.0009) -[2023-10-17 03:09:27,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 147456000. Throughput: 0: 1747.5, 1: 1750.7. Samples: 36873880. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-17 03:09:27,215][61453] Avg episode reward: [(0, '11.330'), (1, '10.240')] -[2023-10-17 03:09:28,195][62373] Updated weights for policy 0, policy_version 72260 (0.0009) -[2023-10-17 03:09:28,279][62408] Updated weights for policy 1, policy_version 71750 (0.0009) -[2023-10-17 03:09:28,566][62373] Updated weights for policy 0, policy_version 72270 (0.0009) -[2023-10-17 03:09:28,664][62408] Updated weights for policy 1, policy_version 71760 (0.0008) -[2023-10-17 03:09:28,938][62373] Updated weights for policy 0, policy_version 72280 (0.0008) -[2023-10-17 03:09:29,027][62408] Updated weights for policy 1, policy_version 71770 (0.0008) -[2023-10-17 03:09:32,214][61453] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 147521536. Throughput: 0: 1763.5, 1: 1768.7. Samples: 36895506. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-17 03:09:32,215][61453] Avg episode reward: [(0, '10.940'), (1, '9.930')] -[2023-10-17 03:09:32,224][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000071776_73498624.pth... -[2023-10-17 03:09:32,225][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000072288_74022912.pth... -[2023-10-17 03:09:32,265][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000070656_72351744.pth -[2023-10-17 03:09:32,265][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000070144_71827456.pth -[2023-10-17 03:09:32,803][62408] Updated weights for policy 1, policy_version 71780 (0.0009) -[2023-10-17 03:09:32,985][62373] Updated weights for policy 0, policy_version 72290 (0.0007) -[2023-10-17 03:09:33,166][62408] Updated weights for policy 1, policy_version 71790 (0.0008) -[2023-10-17 03:09:33,368][62373] Updated weights for policy 0, policy_version 72300 (0.0007) -[2023-10-17 03:09:33,528][62408] Updated weights for policy 1, policy_version 71800 (0.0009) -[2023-10-17 03:09:33,736][62373] Updated weights for policy 0, policy_version 72310 (0.0007) -[2023-10-17 03:09:34,104][62373] Updated weights for policy 0, policy_version 72320 (0.0009) -[2023-10-17 03:09:37,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 147587072. Throughput: 0: 1743.1, 1: 1755.3. Samples: 36904908. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-17 03:09:37,215][61453] Avg episode reward: [(0, '10.960'), (1, '10.380')] -[2023-10-17 03:09:37,365][62408] Updated weights for policy 1, policy_version 71810 (0.0009) -[2023-10-17 03:09:37,731][62408] Updated weights for policy 1, policy_version 71820 (0.0009) -[2023-10-17 03:09:37,955][62373] Updated weights for policy 0, policy_version 72330 (0.0008) -[2023-10-17 03:09:38,092][62408] Updated weights for policy 1, policy_version 71830 (0.0007) -[2023-10-17 03:09:38,324][62373] Updated weights for policy 0, policy_version 72340 (0.0007) -[2023-10-17 03:09:38,454][62408] Updated weights for policy 1, policy_version 71840 (0.0007) -[2023-10-17 03:09:38,697][62373] Updated weights for policy 0, policy_version 72350 (0.0008) -[2023-10-17 03:09:42,191][62408] Updated weights for policy 1, policy_version 71850 (0.0008) -[2023-10-17 03:09:42,214][61453] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 147652608. Throughput: 0: 1754.9, 1: 1765.2. Samples: 36927064. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-17 03:09:42,215][61453] Avg episode reward: [(0, '11.410'), (1, '10.240')] -[2023-10-17 03:09:42,496][62373] Updated weights for policy 0, policy_version 72360 (0.0008) -[2023-10-17 03:09:42,554][62408] Updated weights for policy 1, policy_version 71860 (0.0007) -[2023-10-17 03:09:42,857][62373] Updated weights for policy 0, policy_version 72370 (0.0008) -[2023-10-17 03:09:42,917][62408] Updated weights for policy 1, policy_version 71870 (0.0007) -[2023-10-17 03:09:43,230][62373] Updated weights for policy 0, policy_version 72380 (0.0008) -[2023-10-17 03:09:46,826][62408] Updated weights for policy 1, policy_version 71880 (0.0007) -[2023-10-17 03:09:47,194][62408] Updated weights for policy 1, policy_version 71890 (0.0007) -[2023-10-17 03:09:47,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 147718144. Throughput: 0: 1769.1, 1: 1773.2. Samples: 36948252. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-17 03:09:47,214][61453] Avg episode reward: [(0, '11.210'), (1, '11.070')] -[2023-10-17 03:09:47,217][62373] Updated weights for policy 0, policy_version 72390 (0.0008) -[2023-10-17 03:09:47,561][62408] Updated weights for policy 1, policy_version 71900 (0.0009) -[2023-10-17 03:09:47,589][62373] Updated weights for policy 0, policy_version 72400 (0.0008) -[2023-10-17 03:09:47,961][62373] Updated weights for policy 0, policy_version 72410 (0.0008) -[2023-10-17 03:09:51,407][62408] Updated weights for policy 1, policy_version 71910 (0.0008) -[2023-10-17 03:09:51,645][62373] Updated weights for policy 0, policy_version 72420 (0.0010) -[2023-10-17 03:09:51,767][62408] Updated weights for policy 1, policy_version 71920 (0.0009) -[2023-10-17 03:09:52,011][62373] Updated weights for policy 0, policy_version 72430 (0.0007) -[2023-10-17 03:09:52,126][62408] Updated weights for policy 1, policy_version 71930 (0.0008) -[2023-10-17 03:09:52,214][61453] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 13995.8). Total num frames: 147783680. Throughput: 0: 1741.1, 1: 1751.3. Samples: 36958124. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-17 03:09:52,215][61453] Avg episode reward: [(0, '10.430'), (1, '11.010')] -[2023-10-17 03:09:52,384][62373] Updated weights for policy 0, policy_version 72440 (0.0008) -[2023-10-17 03:09:56,035][62408] Updated weights for policy 1, policy_version 71940 (0.0009) -[2023-10-17 03:09:56,245][62373] Updated weights for policy 0, policy_version 72450 (0.0009) -[2023-10-17 03:09:56,409][62408] Updated weights for policy 1, policy_version 71950 (0.0009) -[2023-10-17 03:09:56,615][62373] Updated weights for policy 0, policy_version 72460 (0.0009) -[2023-10-17 03:09:56,773][62408] Updated weights for policy 1, policy_version 71960 (0.0007) -[2023-10-17 03:09:56,986][62373] Updated weights for policy 0, policy_version 72470 (0.0008) -[2023-10-17 03:09:57,214][61453] Fps is (10 sec: 16383.7, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 147881984. Throughput: 0: 1775.4, 1: 1782.4. Samples: 36980278. Policy #0 lag: (min: 31.0, avg: 33.8, max: 63.0) -[2023-10-17 03:09:57,215][61453] Avg episode reward: [(0, '10.260'), (1, '11.460')] -[2023-10-17 03:09:57,362][62373] Updated weights for policy 0, policy_version 72480 (0.0007) -[2023-10-17 03:10:00,644][62408] Updated weights for policy 1, policy_version 71970 (0.0009) -[2023-10-17 03:10:01,017][62408] Updated weights for policy 1, policy_version 71980 (0.0008) -[2023-10-17 03:10:01,088][62373] Updated weights for policy 0, policy_version 72490 (0.0007) -[2023-10-17 03:10:01,371][62408] Updated weights for policy 1, policy_version 71990 (0.0008) -[2023-10-17 03:10:01,468][62373] Updated weights for policy 0, policy_version 72500 (0.0007) -[2023-10-17 03:10:01,742][62408] Updated weights for policy 1, policy_version 72000 (0.0008) -[2023-10-17 03:10:01,838][62373] Updated weights for policy 0, policy_version 72510 (0.0007) -[2023-10-17 03:10:02,214][61453] Fps is (10 sec: 19660.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 147980288. Throughput: 0: 1747.7, 1: 1747.0. Samples: 36999536. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:10:02,215][61453] Avg episode reward: [(0, '9.950'), (1, '11.260')] -[2023-10-17 03:10:05,630][62408] Updated weights for policy 1, policy_version 72010 (0.0009) -[2023-10-17 03:10:05,711][62373] Updated weights for policy 0, policy_version 72520 (0.0010) -[2023-10-17 03:10:05,992][62408] Updated weights for policy 1, policy_version 72020 (0.0008) -[2023-10-17 03:10:06,080][62373] Updated weights for policy 0, policy_version 72530 (0.0007) -[2023-10-17 03:10:06,363][62408] Updated weights for policy 1, policy_version 72030 (0.0008) -[2023-10-17 03:10:06,440][62373] Updated weights for policy 0, policy_version 72540 (0.0007) -[2023-10-17 03:10:07,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 148045824. Throughput: 0: 1779.8, 1: 1782.1. Samples: 37012168. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:10:07,215][61453] Avg episode reward: [(0, '9.710'), (1, '10.850')] -[2023-10-17 03:10:10,105][62373] Updated weights for policy 0, policy_version 72550 (0.0008) -[2023-10-17 03:10:10,171][62408] Updated weights for policy 1, policy_version 72040 (0.0008) -[2023-10-17 03:10:10,474][62373] Updated weights for policy 0, policy_version 72560 (0.0009) -[2023-10-17 03:10:10,535][62408] Updated weights for policy 1, policy_version 72050 (0.0010) -[2023-10-17 03:10:10,838][62373] Updated weights for policy 0, policy_version 72570 (0.0009) -[2023-10-17 03:10:10,905][62408] Updated weights for policy 1, policy_version 72060 (0.0008) -[2023-10-17 03:10:12,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 148111360. Throughput: 0: 1760.7, 1: 1756.0. Samples: 37032130. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:10:12,215][61453] Avg episode reward: [(0, '10.180'), (1, '10.370')] -[2023-10-17 03:10:14,488][62373] Updated weights for policy 0, policy_version 72580 (0.0010) -[2023-10-17 03:10:14,860][62373] Updated weights for policy 0, policy_version 72590 (0.0009) -[2023-10-17 03:10:14,862][62408] Updated weights for policy 1, policy_version 72070 (0.0007) -[2023-10-17 03:10:15,220][62373] Updated weights for policy 0, policy_version 72600 (0.0008) -[2023-10-17 03:10:15,228][62408] Updated weights for policy 1, policy_version 72080 (0.0009) -[2023-10-17 03:10:15,594][62408] Updated weights for policy 1, policy_version 72090 (0.0011) -[2023-10-17 03:10:17,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 148176896. Throughput: 0: 1762.2, 1: 1754.2. Samples: 37053744. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:10:17,215][61453] Avg episode reward: [(0, '10.670'), (1, '10.980')] -[2023-10-17 03:10:18,949][62373] Updated weights for policy 0, policy_version 72610 (0.0009) -[2023-10-17 03:10:19,359][62373] Updated weights for policy 0, policy_version 72620 (0.0009) -[2023-10-17 03:10:19,460][62408] Updated weights for policy 1, policy_version 72100 (0.0010) -[2023-10-17 03:10:19,738][62373] Updated weights for policy 0, policy_version 72630 (0.0007) -[2023-10-17 03:10:19,838][62408] Updated weights for policy 1, policy_version 72110 (0.0009) -[2023-10-17 03:10:20,103][62373] Updated weights for policy 0, policy_version 72640 (0.0009) -[2023-10-17 03:10:20,205][62408] Updated weights for policy 1, policy_version 72120 (0.0008) -[2023-10-17 03:10:22,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 148242432. Throughput: 0: 1772.8, 1: 1767.0. Samples: 37064198. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:10:22,214][61453] Avg episode reward: [(0, '10.120'), (1, '10.020')] -[2023-10-17 03:10:23,891][62373] Updated weights for policy 0, policy_version 72650 (0.0009) -[2023-10-17 03:10:24,019][62408] Updated weights for policy 1, policy_version 72130 (0.0009) -[2023-10-17 03:10:24,255][62373] Updated weights for policy 0, policy_version 72660 (0.0007) -[2023-10-17 03:10:24,380][62408] Updated weights for policy 1, policy_version 72140 (0.0008) -[2023-10-17 03:10:24,623][62373] Updated weights for policy 0, policy_version 72670 (0.0007) -[2023-10-17 03:10:24,753][62408] Updated weights for policy 1, policy_version 72150 (0.0010) -[2023-10-17 03:10:25,117][62408] Updated weights for policy 1, policy_version 72160 (0.0007) -[2023-10-17 03:10:27,214][61453] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 148307968. Throughput: 0: 1770.7, 1: 1745.6. Samples: 37085298. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:10:27,214][61453] Avg episode reward: [(0, '10.580'), (1, '10.370')] -[2023-10-17 03:10:28,499][62373] Updated weights for policy 0, policy_version 72680 (0.0010) -[2023-10-17 03:10:28,865][62373] Updated weights for policy 0, policy_version 72690 (0.0008) -[2023-10-17 03:10:28,875][62408] Updated weights for policy 1, policy_version 72170 (0.0009) -[2023-10-17 03:10:29,229][62408] Updated weights for policy 1, policy_version 72180 (0.0009) -[2023-10-17 03:10:29,243][62373] Updated weights for policy 0, policy_version 72700 (0.0009) -[2023-10-17 03:10:29,596][62408] Updated weights for policy 1, policy_version 72190 (0.0007) -[2023-10-17 03:10:32,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 148373504. Throughput: 0: 1784.7, 1: 1757.3. Samples: 37107644. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:10:32,215][61453] Avg episode reward: [(0, '10.330'), (1, '10.420')] -[2023-10-17 03:10:32,889][62373] Updated weights for policy 0, policy_version 72710 (0.0010) -[2023-10-17 03:10:33,256][62373] Updated weights for policy 0, policy_version 72720 (0.0010) -[2023-10-17 03:10:33,497][62408] Updated weights for policy 1, policy_version 72200 (0.0007) -[2023-10-17 03:10:33,626][62373] Updated weights for policy 0, policy_version 72730 (0.0008) -[2023-10-17 03:10:33,864][62408] Updated weights for policy 1, policy_version 72210 (0.0008) -[2023-10-17 03:10:34,246][62408] Updated weights for policy 1, policy_version 72220 (0.0009) -[2023-10-17 03:10:37,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 148439040. Throughput: 0: 1788.1, 1: 1750.1. Samples: 37117344. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:10:37,215][61453] Avg episode reward: [(0, '11.060'), (1, '10.590')] -[2023-10-17 03:10:37,516][62373] Updated weights for policy 0, policy_version 72740 (0.0010) -[2023-10-17 03:10:37,880][62373] Updated weights for policy 0, policy_version 72750 (0.0010) -[2023-10-17 03:10:38,179][62408] Updated weights for policy 1, policy_version 72230 (0.0009) -[2023-10-17 03:10:38,254][62373] Updated weights for policy 0, policy_version 72760 (0.0009) -[2023-10-17 03:10:38,542][62408] Updated weights for policy 1, policy_version 72240 (0.0009) -[2023-10-17 03:10:38,907][62408] Updated weights for policy 1, policy_version 72250 (0.0008) -[2023-10-17 03:10:41,841][62373] Updated weights for policy 0, policy_version 72770 (0.0008) -[2023-10-17 03:10:42,205][62373] Updated weights for policy 0, policy_version 72780 (0.0009) -[2023-10-17 03:10:42,214][61453] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 148504576. Throughput: 0: 1780.7, 1: 1751.0. Samples: 37139206. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:10:42,214][61453] Avg episode reward: [(0, '9.870'), (1, '10.600')] -[2023-10-17 03:10:42,578][62373] Updated weights for policy 0, policy_version 72790 (0.0008) -[2023-10-17 03:10:42,752][62408] Updated weights for policy 1, policy_version 72260 (0.0007) -[2023-10-17 03:10:42,938][62373] Updated weights for policy 0, policy_version 72800 (0.0007) -[2023-10-17 03:10:43,116][62408] Updated weights for policy 1, policy_version 72270 (0.0009) -[2023-10-17 03:10:43,479][62408] Updated weights for policy 1, policy_version 72280 (0.0010) -[2023-10-17 03:10:46,798][62373] Updated weights for policy 0, policy_version 72810 (0.0010) -[2023-10-17 03:10:47,163][62373] Updated weights for policy 0, policy_version 72820 (0.0009) -[2023-10-17 03:10:47,205][62408] Updated weights for policy 1, policy_version 72290 (0.0008) -[2023-10-17 03:10:47,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 148570112. Throughput: 0: 1797.8, 1: 1784.2. Samples: 37160724. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-17 03:10:47,215][61453] Avg episode reward: [(0, '10.350'), (1, '10.650')] -[2023-10-17 03:10:47,535][62373] Updated weights for policy 0, policy_version 72830 (0.0007) -[2023-10-17 03:10:47,578][62408] Updated weights for policy 1, policy_version 72300 (0.0009) -[2023-10-17 03:10:47,950][62408] Updated weights for policy 1, policy_version 72310 (0.0008) -[2023-10-17 03:10:48,315][62408] Updated weights for policy 1, policy_version 72320 (0.0008) -[2023-10-17 03:10:51,428][62373] Updated weights for policy 0, policy_version 72840 (0.0010) -[2023-10-17 03:10:51,803][62373] Updated weights for policy 0, policy_version 72850 (0.0009) -[2023-10-17 03:10:52,151][62408] Updated weights for policy 1, policy_version 72330 (0.0009) -[2023-10-17 03:10:52,174][62373] Updated weights for policy 0, policy_version 72860 (0.0007) -[2023-10-17 03:10:52,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 148635648. Throughput: 0: 1780.8, 1: 1747.1. Samples: 37170922. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-17 03:10:52,214][61453] Avg episode reward: [(0, '9.700'), (1, '10.460')] -[2023-10-17 03:10:52,524][62408] Updated weights for policy 1, policy_version 72340 (0.0008) -[2023-10-17 03:10:52,886][62408] Updated weights for policy 1, policy_version 72350 (0.0009) -[2023-10-17 03:10:56,052][62373] Updated weights for policy 0, policy_version 72870 (0.0009) -[2023-10-17 03:10:56,421][62373] Updated weights for policy 0, policy_version 72880 (0.0010) -[2023-10-17 03:10:56,605][62408] Updated weights for policy 1, policy_version 72360 (0.0008) -[2023-10-17 03:10:56,797][62373] Updated weights for policy 0, policy_version 72890 (0.0008) -[2023-10-17 03:10:56,969][62408] Updated weights for policy 1, policy_version 72370 (0.0007) -[2023-10-17 03:10:57,214][61453] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 148733952. Throughput: 0: 1797.6, 1: 1772.8. Samples: 37192800. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-17 03:10:57,215][61453] Avg episode reward: [(0, '10.440'), (1, '11.120')] -[2023-10-17 03:10:57,341][62408] Updated weights for policy 1, policy_version 72380 (0.0009) -[2023-10-17 03:11:00,623][62373] Updated weights for policy 0, policy_version 72900 (0.0009) -[2023-10-17 03:11:00,983][62373] Updated weights for policy 0, policy_version 72910 (0.0011) -[2023-10-17 03:11:01,357][62373] Updated weights for policy 0, policy_version 72920 (0.0007) -[2023-10-17 03:11:01,403][62408] Updated weights for policy 1, policy_version 72390 (0.0009) -[2023-10-17 03:11:01,790][62408] Updated weights for policy 1, policy_version 72400 (0.0008) -[2023-10-17 03:11:02,159][62408] Updated weights for policy 1, policy_version 72410 (0.0009) -[2023-10-17 03:11:02,214][61453] Fps is (10 sec: 16383.9, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 148799488. Throughput: 0: 1772.1, 1: 1757.0. Samples: 37212550. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-17 03:11:02,215][61453] Avg episode reward: [(0, '10.160'), (1, '11.260')] -[2023-10-17 03:11:05,099][62373] Updated weights for policy 0, policy_version 72930 (0.0009) -[2023-10-17 03:11:05,491][62373] Updated weights for policy 0, policy_version 72940 (0.0008) -[2023-10-17 03:11:05,852][62373] Updated weights for policy 0, policy_version 72950 (0.0007) -[2023-10-17 03:11:06,010][62408] Updated weights for policy 1, policy_version 72420 (0.0007) -[2023-10-17 03:11:06,227][62373] Updated weights for policy 0, policy_version 72960 (0.0008) -[2023-10-17 03:11:06,377][62408] Updated weights for policy 1, policy_version 72430 (0.0008) -[2023-10-17 03:11:06,748][62408] Updated weights for policy 1, policy_version 72440 (0.0009) -[2023-10-17 03:11:07,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 148897792. Throughput: 0: 1804.2, 1: 1759.2. Samples: 37224548. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-17 03:11:07,214][61453] Avg episode reward: [(0, '10.190'), (1, '10.660')] -[2023-10-17 03:11:09,983][62373] Updated weights for policy 0, policy_version 72970 (0.0010) -[2023-10-17 03:11:10,357][62373] Updated weights for policy 0, policy_version 72980 (0.0007) -[2023-10-17 03:11:10,640][62408] Updated weights for policy 1, policy_version 72450 (0.0009) -[2023-10-17 03:11:10,717][62373] Updated weights for policy 0, policy_version 72990 (0.0009) -[2023-10-17 03:11:11,009][62408] Updated weights for policy 1, policy_version 72460 (0.0009) -[2023-10-17 03:11:11,377][62408] Updated weights for policy 1, policy_version 72470 (0.0008) -[2023-10-17 03:11:11,740][62408] Updated weights for policy 1, policy_version 72480 (0.0008) -[2023-10-17 03:11:12,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 148963328. Throughput: 0: 1773.5, 1: 1773.0. Samples: 37244892. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-17 03:11:12,215][61453] Avg episode reward: [(0, '9.750'), (1, '9.850')] -[2023-10-17 03:11:14,373][62373] Updated weights for policy 0, policy_version 73000 (0.0009) -[2023-10-17 03:11:14,747][62373] Updated weights for policy 0, policy_version 73010 (0.0007) -[2023-10-17 03:11:15,116][62373] Updated weights for policy 0, policy_version 73020 (0.0008) -[2023-10-17 03:11:15,669][62408] Updated weights for policy 1, policy_version 72490 (0.0010) -[2023-10-17 03:11:16,038][62408] Updated weights for policy 1, policy_version 72500 (0.0010) -[2023-10-17 03:11:16,418][62408] Updated weights for policy 1, policy_version 72510 (0.0011) -[2023-10-17 03:11:17,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 149028864. Throughput: 0: 1772.4, 1: 1747.8. Samples: 37266052. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-17 03:11:17,215][61453] Avg episode reward: [(0, '9.800'), (1, '10.560')] -[2023-10-17 03:11:18,745][62373] Updated weights for policy 0, policy_version 73030 (0.0008) -[2023-10-17 03:11:19,119][62373] Updated weights for policy 0, policy_version 73040 (0.0009) -[2023-10-17 03:11:19,488][62373] Updated weights for policy 0, policy_version 73050 (0.0009) -[2023-10-17 03:11:20,057][62408] Updated weights for policy 1, policy_version 72520 (0.0009) -[2023-10-17 03:11:20,430][62408] Updated weights for policy 1, policy_version 72530 (0.0008) -[2023-10-17 03:11:20,793][62408] Updated weights for policy 1, policy_version 72540 (0.0010) -[2023-10-17 03:11:22,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 149094400. Throughput: 0: 1774.3, 1: 1784.0. Samples: 37277466. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-17 03:11:22,215][61453] Avg episode reward: [(0, '9.560'), (1, '10.540')] -[2023-10-17 03:11:23,305][62373] Updated weights for policy 0, policy_version 73060 (0.0007) -[2023-10-17 03:11:23,671][62373] Updated weights for policy 0, policy_version 73070 (0.0007) -[2023-10-17 03:11:24,050][62373] Updated weights for policy 0, policy_version 73080 (0.0008) -[2023-10-17 03:11:24,601][62408] Updated weights for policy 1, policy_version 72550 (0.0011) -[2023-10-17 03:11:24,972][62408] Updated weights for policy 1, policy_version 72560 (0.0008) -[2023-10-17 03:11:25,347][62408] Updated weights for policy 1, policy_version 72570 (0.0008) -[2023-10-17 03:11:27,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 149159936. Throughput: 0: 1785.7, 1: 1757.5. Samples: 37298652. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-10-17 03:11:27,215][61453] Avg episode reward: [(0, '9.390'), (1, '10.300')] -[2023-10-17 03:11:27,638][62373] Updated weights for policy 0, policy_version 73090 (0.0008) -[2023-10-17 03:11:28,007][62373] Updated weights for policy 0, policy_version 73100 (0.0011) -[2023-10-17 03:11:28,383][62373] Updated weights for policy 0, policy_version 73110 (0.0011) -[2023-10-17 03:11:28,743][62373] Updated weights for policy 0, policy_version 73120 (0.0009) -[2023-10-17 03:11:29,231][62408] Updated weights for policy 1, policy_version 72580 (0.0008) -[2023-10-17 03:11:29,597][62408] Updated weights for policy 1, policy_version 72590 (0.0010) -[2023-10-17 03:11:29,965][62408] Updated weights for policy 1, policy_version 72600 (0.0007) -[2023-10-17 03:11:32,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 149225472. Throughput: 0: 1804.3, 1: 1750.5. Samples: 37320688. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-17 03:11:32,215][61453] Avg episode reward: [(0, '10.170'), (1, '10.220')] -[2023-10-17 03:11:32,223][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000072608_74350592.pth... -[2023-10-17 03:11:32,263][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000070976_72679424.pth -[2023-10-17 03:11:32,443][62373] Updated weights for policy 0, policy_version 73130 (0.0009) -[2023-10-17 03:11:32,810][62373] Updated weights for policy 0, policy_version 73140 (0.0009) -[2023-10-17 03:11:33,187][62373] Updated weights for policy 0, policy_version 73150 (0.0008) -[2023-10-17 03:11:33,252][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000073152_74907648.pth... -[2023-10-17 03:11:33,283][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000071488_73203712.pth -[2023-10-17 03:11:33,586][62408] Updated weights for policy 1, policy_version 72610 (0.0007) -[2023-10-17 03:11:33,956][62408] Updated weights for policy 1, policy_version 72620 (0.0009) -[2023-10-17 03:11:34,320][62408] Updated weights for policy 1, policy_version 72630 (0.0011) -[2023-10-17 03:11:34,692][62408] Updated weights for policy 1, policy_version 72640 (0.0008) -[2023-10-17 03:11:36,884][62373] Updated weights for policy 0, policy_version 73160 (0.0010) -[2023-10-17 03:11:37,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 149291008. Throughput: 0: 1793.1, 1: 1753.8. Samples: 37330532. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-17 03:11:37,215][61453] Avg episode reward: [(0, '10.670'), (1, '10.340')] -[2023-10-17 03:11:37,250][62373] Updated weights for policy 0, policy_version 73170 (0.0010) -[2023-10-17 03:11:37,614][62373] Updated weights for policy 0, policy_version 73180 (0.0010) -[2023-10-17 03:11:38,689][62408] Updated weights for policy 1, policy_version 72650 (0.0010) -[2023-10-17 03:11:39,056][62408] Updated weights for policy 1, policy_version 72660 (0.0009) -[2023-10-17 03:11:39,420][62408] Updated weights for policy 1, policy_version 72670 (0.0008) -[2023-10-17 03:11:41,343][62373] Updated weights for policy 0, policy_version 73190 (0.0009) -[2023-10-17 03:11:41,703][62373] Updated weights for policy 0, policy_version 73200 (0.0007) -[2023-10-17 03:11:42,076][62373] Updated weights for policy 0, policy_version 73210 (0.0008) -[2023-10-17 03:11:42,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 149356544. Throughput: 0: 1801.8, 1: 1751.8. Samples: 37352712. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-17 03:11:42,214][61453] Avg episode reward: [(0, '11.140'), (1, '10.390')] -[2023-10-17 03:11:43,125][62408] Updated weights for policy 1, policy_version 72680 (0.0008) -[2023-10-17 03:11:43,489][62408] Updated weights for policy 1, policy_version 72690 (0.0008) -[2023-10-17 03:11:43,859][62408] Updated weights for policy 1, policy_version 72700 (0.0007) -[2023-10-17 03:11:45,919][62373] Updated weights for policy 0, policy_version 73220 (0.0008) -[2023-10-17 03:11:46,294][62373] Updated weights for policy 0, policy_version 73230 (0.0008) -[2023-10-17 03:11:46,658][62373] Updated weights for policy 0, policy_version 73240 (0.0007) -[2023-10-17 03:11:47,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14106.9). Total num frames: 149454848. Throughput: 0: 1804.9, 1: 1778.4. Samples: 37373802. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-17 03:11:47,215][61453] Avg episode reward: [(0, '10.760'), (1, '10.350')] -[2023-10-17 03:11:47,778][62408] Updated weights for policy 1, policy_version 72710 (0.0008) -[2023-10-17 03:11:48,168][62408] Updated weights for policy 1, policy_version 72720 (0.0009) -[2023-10-17 03:11:48,540][62408] Updated weights for policy 1, policy_version 72730 (0.0008) -[2023-10-17 03:11:50,407][62373] Updated weights for policy 0, policy_version 73250 (0.0008) -[2023-10-17 03:11:50,812][62373] Updated weights for policy 0, policy_version 73260 (0.0010) -[2023-10-17 03:11:51,177][62373] Updated weights for policy 0, policy_version 73270 (0.0009) -[2023-10-17 03:11:51,545][62373] Updated weights for policy 0, policy_version 73280 (0.0009) -[2023-10-17 03:11:52,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14106.9). Total num frames: 149520384. Throughput: 0: 1802.8, 1: 1758.0. Samples: 37384782. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-17 03:11:52,214][61453] Avg episode reward: [(0, '10.780'), (1, '9.900')] -[2023-10-17 03:11:52,318][62408] Updated weights for policy 1, policy_version 72740 (0.0008) -[2023-10-17 03:11:52,685][62408] Updated weights for policy 1, policy_version 72750 (0.0009) -[2023-10-17 03:11:53,056][62408] Updated weights for policy 1, policy_version 72760 (0.0010) -[2023-10-17 03:11:55,280][62373] Updated weights for policy 0, policy_version 73290 (0.0007) -[2023-10-17 03:11:55,651][62373] Updated weights for policy 0, policy_version 73300 (0.0009) -[2023-10-17 03:11:56,027][62373] Updated weights for policy 0, policy_version 73310 (0.0007) -[2023-10-17 03:11:56,925][62408] Updated weights for policy 1, policy_version 72770 (0.0007) -[2023-10-17 03:11:57,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 149585920. Throughput: 0: 1806.0, 1: 1762.7. Samples: 37405484. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-17 03:11:57,214][61453] Avg episode reward: [(0, '11.220'), (1, '9.910')] -[2023-10-17 03:11:57,296][62408] Updated weights for policy 1, policy_version 72780 (0.0007) -[2023-10-17 03:11:57,656][62408] Updated weights for policy 1, policy_version 72790 (0.0009) -[2023-10-17 03:11:58,026][62408] Updated weights for policy 1, policy_version 72800 (0.0008) -[2023-10-17 03:11:59,892][62373] Updated weights for policy 0, policy_version 73320 (0.0007) -[2023-10-17 03:12:00,253][62373] Updated weights for policy 0, policy_version 73330 (0.0007) -[2023-10-17 03:12:00,617][62373] Updated weights for policy 0, policy_version 73340 (0.0007) -[2023-10-17 03:12:01,967][62408] Updated weights for policy 1, policy_version 72810 (0.0009) -[2023-10-17 03:12:02,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 149651456. Throughput: 0: 1804.4, 1: 1781.2. Samples: 37427404. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-17 03:12:02,214][61453] Avg episode reward: [(0, '11.140'), (1, '10.250')] -[2023-10-17 03:12:02,334][62408] Updated weights for policy 1, policy_version 72820 (0.0008) -[2023-10-17 03:12:02,707][62408] Updated weights for policy 1, policy_version 72830 (0.0008) -[2023-10-17 03:12:04,078][62373] Updated weights for policy 0, policy_version 73350 (0.0008) -[2023-10-17 03:12:04,437][62373] Updated weights for policy 0, policy_version 73360 (0.0007) -[2023-10-17 03:12:04,808][62373] Updated weights for policy 0, policy_version 73370 (0.0008) -[2023-10-17 03:12:06,493][62408] Updated weights for policy 1, policy_version 72840 (0.0009) -[2023-10-17 03:12:06,859][62408] Updated weights for policy 1, policy_version 72850 (0.0008) -[2023-10-17 03:12:07,214][61453] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 149716992. Throughput: 0: 1809.8, 1: 1749.5. Samples: 37437634. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-17 03:12:07,214][61453] Avg episode reward: [(0, '9.690'), (1, '9.760')] -[2023-10-17 03:12:07,227][62408] Updated weights for policy 1, policy_version 72860 (0.0008) -[2023-10-17 03:12:08,607][62373] Updated weights for policy 0, policy_version 73380 (0.0008) -[2023-10-17 03:12:08,987][62373] Updated weights for policy 0, policy_version 73390 (0.0009) -[2023-10-17 03:12:09,349][62373] Updated weights for policy 0, policy_version 73400 (0.0009) -[2023-10-17 03:12:11,040][62408] Updated weights for policy 1, policy_version 72870 (0.0009) -[2023-10-17 03:12:11,412][62408] Updated weights for policy 1, policy_version 72880 (0.0010) -[2023-10-17 03:12:11,786][62408] Updated weights for policy 1, policy_version 72890 (0.0009) -[2023-10-17 03:12:12,214][61453] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 149815296. Throughput: 0: 1803.7, 1: 1776.6. Samples: 37459764. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-17 03:12:12,215][61453] Avg episode reward: [(0, '8.280'), (1, '9.430')] -[2023-10-17 03:12:12,970][62373] Updated weights for policy 0, policy_version 73410 (0.0009) -[2023-10-17 03:12:13,344][62373] Updated weights for policy 0, policy_version 73420 (0.0010) -[2023-10-17 03:12:13,717][62373] Updated weights for policy 0, policy_version 73430 (0.0009) -[2023-10-17 03:12:14,087][62373] Updated weights for policy 0, policy_version 73440 (0.0009) -[2023-10-17 03:12:15,678][62408] Updated weights for policy 1, policy_version 72900 (0.0009) -[2023-10-17 03:12:16,048][62408] Updated weights for policy 1, policy_version 72910 (0.0008) -[2023-10-17 03:12:16,419][62408] Updated weights for policy 1, policy_version 72920 (0.0007) -[2023-10-17 03:12:17,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 149880832. Throughput: 0: 1799.6, 1: 1751.0. Samples: 37480468. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-17 03:12:17,215][61453] Avg episode reward: [(0, '8.120'), (1, '10.180')] -[2023-10-17 03:12:17,832][62373] Updated weights for policy 0, policy_version 73450 (0.0009) -[2023-10-17 03:12:18,205][62373] Updated weights for policy 0, policy_version 73460 (0.0009) -[2023-10-17 03:12:18,572][62373] Updated weights for policy 0, policy_version 73470 (0.0007) -[2023-10-17 03:12:20,111][62408] Updated weights for policy 1, policy_version 72930 (0.0009) -[2023-10-17 03:12:20,478][62408] Updated weights for policy 1, policy_version 72940 (0.0008) -[2023-10-17 03:12:20,845][62408] Updated weights for policy 1, policy_version 72950 (0.0007) -[2023-10-17 03:12:21,220][62408] Updated weights for policy 1, policy_version 72960 (0.0007) -[2023-10-17 03:12:22,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 149946368. Throughput: 0: 1795.2, 1: 1784.9. Samples: 37491636. Policy #0 lag: (min: 31.0, avg: 31.1, max: 39.0) -[2023-10-17 03:12:22,215][61453] Avg episode reward: [(0, '9.070'), (1, '9.910')] -[2023-10-17 03:12:22,352][62373] Updated weights for policy 0, policy_version 73480 (0.0007) -[2023-10-17 03:12:22,717][62373] Updated weights for policy 0, policy_version 73490 (0.0009) -[2023-10-17 03:12:23,083][62373] Updated weights for policy 0, policy_version 73500 (0.0009) -[2023-10-17 03:12:25,154][62408] Updated weights for policy 1, policy_version 72970 (0.0008) -[2023-10-17 03:12:25,528][62408] Updated weights for policy 1, policy_version 72980 (0.0010) -[2023-10-17 03:12:25,897][62408] Updated weights for policy 1, policy_version 72990 (0.0010) -[2023-10-17 03:12:26,926][62373] Updated weights for policy 0, policy_version 73510 (0.0009) -[2023-10-17 03:12:27,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 150011904. Throughput: 0: 1794.6, 1: 1758.8. Samples: 37512616. Policy #0 lag: (min: 31.0, avg: 31.1, max: 39.0) -[2023-10-17 03:12:27,215][61453] Avg episode reward: [(0, '9.150'), (1, '10.060')] -[2023-10-17 03:12:27,299][62373] Updated weights for policy 0, policy_version 73520 (0.0009) -[2023-10-17 03:12:27,673][62373] Updated weights for policy 0, policy_version 73530 (0.0010) -[2023-10-17 03:12:29,745][62408] Updated weights for policy 1, policy_version 73000 (0.0009) -[2023-10-17 03:12:30,129][62408] Updated weights for policy 1, policy_version 73010 (0.0010) -[2023-10-17 03:12:30,507][62408] Updated weights for policy 1, policy_version 73020 (0.0009) -[2023-10-17 03:12:31,426][62373] Updated weights for policy 0, policy_version 73540 (0.0009) -[2023-10-17 03:12:31,791][62373] Updated weights for policy 0, policy_version 73550 (0.0009) -[2023-10-17 03:12:32,175][62373] Updated weights for policy 0, policy_version 73560 (0.0011) -[2023-10-17 03:12:32,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 150077440. Throughput: 0: 1803.7, 1: 1750.2. Samples: 37533728. Policy #0 lag: (min: 31.0, avg: 31.1, max: 39.0) -[2023-10-17 03:12:32,214][61453] Avg episode reward: [(0, '9.220'), (1, '9.550')] -[2023-10-17 03:12:34,277][62408] Updated weights for policy 1, policy_version 73030 (0.0009) -[2023-10-17 03:12:34,663][62408] Updated weights for policy 1, policy_version 73040 (0.0010) -[2023-10-17 03:12:35,030][62408] Updated weights for policy 1, policy_version 73050 (0.0010) -[2023-10-17 03:12:36,236][62373] Updated weights for policy 0, policy_version 73570 (0.0010) -[2023-10-17 03:12:36,642][62373] Updated weights for policy 0, policy_version 73580 (0.0009) -[2023-10-17 03:12:37,012][62373] Updated weights for policy 0, policy_version 73590 (0.0009) -[2023-10-17 03:12:37,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 150142976. Throughput: 0: 1783.7, 1: 1764.6. Samples: 37544456. Policy #0 lag: (min: 31.0, avg: 31.1, max: 39.0) -[2023-10-17 03:12:37,214][61453] Avg episode reward: [(0, '9.320'), (1, '9.190')] -[2023-10-17 03:12:37,382][62373] Updated weights for policy 0, policy_version 73600 (0.0008) -[2023-10-17 03:12:38,818][62408] Updated weights for policy 1, policy_version 73060 (0.0009) -[2023-10-17 03:12:39,189][62408] Updated weights for policy 1, policy_version 73070 (0.0008) -[2023-10-17 03:12:39,554][62408] Updated weights for policy 1, policy_version 73080 (0.0008) -[2023-10-17 03:12:41,066][62373] Updated weights for policy 0, policy_version 73610 (0.0010) -[2023-10-17 03:12:41,435][62373] Updated weights for policy 0, policy_version 73620 (0.0009) -[2023-10-17 03:12:41,803][62373] Updated weights for policy 0, policy_version 73630 (0.0007) -[2023-10-17 03:12:42,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14745.5, 300 sec: 14218.0). Total num frames: 150241280. Throughput: 0: 1802.2, 1: 1755.3. Samples: 37565570. Policy #0 lag: (min: 31.0, avg: 31.1, max: 39.0) -[2023-10-17 03:12:42,215][61453] Avg episode reward: [(0, '9.470'), (1, '9.540')] -[2023-10-17 03:12:43,278][62408] Updated weights for policy 1, policy_version 73090 (0.0008) -[2023-10-17 03:12:43,655][62408] Updated weights for policy 1, policy_version 73100 (0.0008) -[2023-10-17 03:12:44,022][62408] Updated weights for policy 1, policy_version 73110 (0.0008) -[2023-10-17 03:12:44,381][62408] Updated weights for policy 1, policy_version 73120 (0.0012) -[2023-10-17 03:12:45,546][62373] Updated weights for policy 0, policy_version 73640 (0.0009) -[2023-10-17 03:12:45,916][62373] Updated weights for policy 0, policy_version 73650 (0.0008) -[2023-10-17 03:12:46,277][62373] Updated weights for policy 0, policy_version 73660 (0.0008) -[2023-10-17 03:12:47,214][61453] Fps is (10 sec: 16383.6, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 150306816. Throughput: 0: 1777.7, 1: 1763.0. Samples: 37586738. Policy #0 lag: (min: 31.0, avg: 31.1, max: 39.0) -[2023-10-17 03:12:47,215][61453] Avg episode reward: [(0, '10.040'), (1, '9.140')] -[2023-10-17 03:12:48,368][62408] Updated weights for policy 1, policy_version 73130 (0.0008) -[2023-10-17 03:12:48,733][62408] Updated weights for policy 1, policy_version 73140 (0.0009) -[2023-10-17 03:12:49,104][62408] Updated weights for policy 1, policy_version 73150 (0.0008) -[2023-10-17 03:12:49,955][62373] Updated weights for policy 0, policy_version 73670 (0.0007) -[2023-10-17 03:12:50,330][62373] Updated weights for policy 0, policy_version 73680 (0.0007) -[2023-10-17 03:12:50,702][62373] Updated weights for policy 0, policy_version 73690 (0.0009) -[2023-10-17 03:12:52,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 150372352. Throughput: 0: 1801.2, 1: 1756.3. Samples: 37597722. Policy #0 lag: (min: 31.0, avg: 31.1, max: 39.0) -[2023-10-17 03:12:52,215][61453] Avg episode reward: [(0, '10.400'), (1, '9.540')] -[2023-10-17 03:12:52,770][62408] Updated weights for policy 1, policy_version 73160 (0.0008) -[2023-10-17 03:12:53,131][62408] Updated weights for policy 1, policy_version 73170 (0.0008) -[2023-10-17 03:12:53,496][62408] Updated weights for policy 1, policy_version 73180 (0.0011) -[2023-10-17 03:12:54,566][62373] Updated weights for policy 0, policy_version 73700 (0.0008) -[2023-10-17 03:12:54,942][62373] Updated weights for policy 0, policy_version 73710 (0.0008) -[2023-10-17 03:12:55,311][62373] Updated weights for policy 0, policy_version 73720 (0.0007) -[2023-10-17 03:12:57,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 150437888. Throughput: 0: 1768.8, 1: 1760.6. Samples: 37618586. Policy #0 lag: (min: 31.0, avg: 31.1, max: 39.0) -[2023-10-17 03:12:57,215][61453] Avg episode reward: [(0, '10.630'), (1, '9.830')] -[2023-10-17 03:12:57,423][62408] Updated weights for policy 1, policy_version 73190 (0.0009) -[2023-10-17 03:12:57,779][62408] Updated weights for policy 1, policy_version 73200 (0.0007) -[2023-10-17 03:12:58,151][62408] Updated weights for policy 1, policy_version 73210 (0.0010) -[2023-10-17 03:12:59,035][62373] Updated weights for policy 0, policy_version 73730 (0.0009) -[2023-10-17 03:12:59,413][62373] Updated weights for policy 0, policy_version 73740 (0.0008) -[2023-10-17 03:12:59,784][62373] Updated weights for policy 0, policy_version 73750 (0.0009) -[2023-10-17 03:13:00,154][62373] Updated weights for policy 0, policy_version 73760 (0.0008) -[2023-10-17 03:13:01,996][62408] Updated weights for policy 1, policy_version 73220 (0.0008) -[2023-10-17 03:13:02,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 150503424. Throughput: 0: 1762.8, 1: 1790.8. Samples: 37640382. Policy #0 lag: (min: 31.0, avg: 31.1, max: 39.0) -[2023-10-17 03:13:02,215][61453] Avg episode reward: [(0, '10.500'), (1, '9.670')] -[2023-10-17 03:13:02,364][62408] Updated weights for policy 1, policy_version 73230 (0.0009) -[2023-10-17 03:13:02,734][62408] Updated weights for policy 1, policy_version 73240 (0.0008) -[2023-10-17 03:13:04,068][62373] Updated weights for policy 0, policy_version 73770 (0.0009) -[2023-10-17 03:13:04,440][62373] Updated weights for policy 0, policy_version 73780 (0.0007) -[2023-10-17 03:13:04,811][62373] Updated weights for policy 0, policy_version 73790 (0.0008) -[2023-10-17 03:13:06,500][62408] Updated weights for policy 1, policy_version 73250 (0.0007) -[2023-10-17 03:13:06,858][62408] Updated weights for policy 1, policy_version 73260 (0.0008) -[2023-10-17 03:13:07,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 150568960. Throughput: 0: 1761.4, 1: 1756.6. Samples: 37649944. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-17 03:13:07,214][61453] Avg episode reward: [(0, '10.570'), (1, '10.340')] -[2023-10-17 03:13:07,219][62408] Updated weights for policy 1, policy_version 73270 (0.0011) -[2023-10-17 03:13:07,580][62408] Updated weights for policy 1, policy_version 73280 (0.0010) -[2023-10-17 03:13:08,600][62373] Updated weights for policy 0, policy_version 73800 (0.0007) -[2023-10-17 03:13:08,977][62373] Updated weights for policy 0, policy_version 73810 (0.0010) -[2023-10-17 03:13:09,354][62373] Updated weights for policy 0, policy_version 73820 (0.0008) -[2023-10-17 03:13:11,457][62408] Updated weights for policy 1, policy_version 73290 (0.0009) -[2023-10-17 03:13:11,822][62408] Updated weights for policy 1, policy_version 73300 (0.0010) -[2023-10-17 03:13:12,197][62408] Updated weights for policy 1, policy_version 73310 (0.0010) -[2023-10-17 03:13:12,214][61453] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 150634496. Throughput: 0: 1762.0, 1: 1784.4. Samples: 37672204. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-17 03:13:12,215][61453] Avg episode reward: [(0, '11.030'), (1, '10.460')] -[2023-10-17 03:13:13,154][62373] Updated weights for policy 0, policy_version 73830 (0.0009) -[2023-10-17 03:13:13,535][62373] Updated weights for policy 0, policy_version 73840 (0.0007) -[2023-10-17 03:13:13,897][62373] Updated weights for policy 0, policy_version 73850 (0.0009) -[2023-10-17 03:13:15,912][62408] Updated weights for policy 1, policy_version 73320 (0.0008) -[2023-10-17 03:13:16,281][62408] Updated weights for policy 1, policy_version 73330 (0.0007) -[2023-10-17 03:13:16,642][62408] Updated weights for policy 1, policy_version 73340 (0.0008) -[2023-10-17 03:13:17,214][61453] Fps is (10 sec: 16383.4, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 150732800. Throughput: 0: 1787.6, 1: 1759.1. Samples: 37693328. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-17 03:13:17,215][61453] Avg episode reward: [(0, '11.370'), (1, '10.540')] -[2023-10-17 03:13:17,717][62373] Updated weights for policy 0, policy_version 73860 (0.0009) -[2023-10-17 03:13:18,081][62373] Updated weights for policy 0, policy_version 73870 (0.0008) -[2023-10-17 03:13:18,454][62373] Updated weights for policy 0, policy_version 73880 (0.0007) -[2023-10-17 03:13:20,552][62408] Updated weights for policy 1, policy_version 73350 (0.0008) -[2023-10-17 03:13:20,941][62408] Updated weights for policy 1, policy_version 73360 (0.0007) -[2023-10-17 03:13:21,306][62408] Updated weights for policy 1, policy_version 73370 (0.0011) -[2023-10-17 03:13:22,174][62373] Updated weights for policy 0, policy_version 73890 (0.0008) -[2023-10-17 03:13:22,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 150798336. Throughput: 0: 1770.2, 1: 1782.1. Samples: 37704308. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-17 03:13:22,215][61453] Avg episode reward: [(0, '11.460'), (1, '10.770')] -[2023-10-17 03:13:22,561][62373] Updated weights for policy 0, policy_version 73900 (0.0010) -[2023-10-17 03:13:22,923][62373] Updated weights for policy 0, policy_version 73910 (0.0009) -[2023-10-17 03:13:23,294][62373] Updated weights for policy 0, policy_version 73920 (0.0010) -[2023-10-17 03:13:25,027][62408] Updated weights for policy 1, policy_version 73380 (0.0010) -[2023-10-17 03:13:25,387][62408] Updated weights for policy 1, policy_version 73390 (0.0009) -[2023-10-17 03:13:25,743][62408] Updated weights for policy 1, policy_version 73400 (0.0009) -[2023-10-17 03:13:26,922][62373] Updated weights for policy 0, policy_version 73930 (0.0007) -[2023-10-17 03:13:27,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 150863872. Throughput: 0: 1785.9, 1: 1763.8. Samples: 37725306. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-17 03:13:27,215][61453] Avg episode reward: [(0, '11.740'), (1, '11.130')] -[2023-10-17 03:13:27,284][62373] Updated weights for policy 0, policy_version 73940 (0.0007) -[2023-10-17 03:13:27,655][62373] Updated weights for policy 0, policy_version 73950 (0.0007) -[2023-10-17 03:13:29,537][62408] Updated weights for policy 1, policy_version 73410 (0.0009) -[2023-10-17 03:13:29,904][62408] Updated weights for policy 1, policy_version 73420 (0.0008) -[2023-10-17 03:13:30,278][62408] Updated weights for policy 1, policy_version 73430 (0.0008) -[2023-10-17 03:13:30,637][62408] Updated weights for policy 1, policy_version 73440 (0.0008) -[2023-10-17 03:13:31,524][62373] Updated weights for policy 0, policy_version 73960 (0.0007) -[2023-10-17 03:13:31,887][62373] Updated weights for policy 0, policy_version 73970 (0.0008) -[2023-10-17 03:13:32,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 150929408. Throughput: 0: 1789.9, 1: 1760.0. Samples: 37746480. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-17 03:13:32,215][61453] Avg episode reward: [(0, '11.750'), (1, '10.800')] -[2023-10-17 03:13:32,224][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000073440_75202560.pth... -[2023-10-17 03:13:32,260][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000071776_73498624.pth -[2023-10-17 03:13:32,268][62373] Updated weights for policy 0, policy_version 73980 (0.0010) -[2023-10-17 03:13:32,407][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000073984_75759616.pth... -[2023-10-17 03:13:32,437][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000072288_74022912.pth -[2023-10-17 03:13:34,641][62408] Updated weights for policy 1, policy_version 73450 (0.0007) -[2023-10-17 03:13:35,011][62408] Updated weights for policy 1, policy_version 73460 (0.0007) -[2023-10-17 03:13:35,384][62408] Updated weights for policy 1, policy_version 73470 (0.0007) -[2023-10-17 03:13:35,969][62373] Updated weights for policy 0, policy_version 73990 (0.0010) -[2023-10-17 03:13:36,328][62373] Updated weights for policy 0, policy_version 74000 (0.0008) -[2023-10-17 03:13:36,710][62373] Updated weights for policy 0, policy_version 74010 (0.0008) -[2023-10-17 03:13:37,214][61453] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 151027712. Throughput: 0: 1777.0, 1: 1776.6. Samples: 37757634. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-17 03:13:37,215][61453] Avg episode reward: [(0, '11.370'), (1, '11.050')] -[2023-10-17 03:13:39,344][62408] Updated weights for policy 1, policy_version 73480 (0.0009) -[2023-10-17 03:13:39,714][62408] Updated weights for policy 1, policy_version 73490 (0.0010) -[2023-10-17 03:13:40,090][62408] Updated weights for policy 1, policy_version 73500 (0.0010) -[2023-10-17 03:13:40,503][62373] Updated weights for policy 0, policy_version 74020 (0.0010) -[2023-10-17 03:13:40,871][62373] Updated weights for policy 0, policy_version 74030 (0.0008) -[2023-10-17 03:13:41,241][62373] Updated weights for policy 0, policy_version 74040 (0.0008) -[2023-10-17 03:13:42,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 151093248. Throughput: 0: 1792.3, 1: 1754.4. Samples: 37778186. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-17 03:13:42,215][61453] Avg episode reward: [(0, '11.490'), (1, '11.520')] -[2023-10-17 03:13:43,934][62408] Updated weights for policy 1, policy_version 73510 (0.0009) -[2023-10-17 03:13:44,302][62408] Updated weights for policy 1, policy_version 73520 (0.0009) -[2023-10-17 03:13:44,684][62408] Updated weights for policy 1, policy_version 73530 (0.0010) -[2023-10-17 03:13:45,036][62373] Updated weights for policy 0, policy_version 74050 (0.0008) -[2023-10-17 03:13:45,408][62373] Updated weights for policy 0, policy_version 74060 (0.0008) -[2023-10-17 03:13:45,790][62373] Updated weights for policy 0, policy_version 74070 (0.0010) -[2023-10-17 03:13:46,153][62373] Updated weights for policy 0, policy_version 74080 (0.0012) -[2023-10-17 03:13:47,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 151158784. Throughput: 0: 1783.0, 1: 1756.8. Samples: 37799672. Policy #0 lag: (min: 22.0, avg: 22.0, max: 22.0) -[2023-10-17 03:13:47,214][61453] Avg episode reward: [(0, '11.450'), (1, '11.040')] -[2023-10-17 03:13:48,559][62408] Updated weights for policy 1, policy_version 73540 (0.0009) -[2023-10-17 03:13:48,932][62408] Updated weights for policy 1, policy_version 73550 (0.0009) -[2023-10-17 03:13:49,297][62408] Updated weights for policy 1, policy_version 73560 (0.0007) -[2023-10-17 03:13:49,932][62373] Updated weights for policy 0, policy_version 74090 (0.0008) -[2023-10-17 03:13:50,297][62373] Updated weights for policy 0, policy_version 74100 (0.0009) -[2023-10-17 03:13:50,667][62373] Updated weights for policy 0, policy_version 74110 (0.0008) -[2023-10-17 03:13:52,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 151224320. Throughput: 0: 1806.7, 1: 1753.7. Samples: 37810162. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:13:52,215][61453] Avg episode reward: [(0, '11.240'), (1, '11.180')] -[2023-10-17 03:13:53,096][62408] Updated weights for policy 1, policy_version 73570 (0.0008) -[2023-10-17 03:13:53,464][62408] Updated weights for policy 1, policy_version 73580 (0.0011) -[2023-10-17 03:13:53,836][62408] Updated weights for policy 1, policy_version 73590 (0.0010) -[2023-10-17 03:13:54,202][62408] Updated weights for policy 1, policy_version 73600 (0.0010) -[2023-10-17 03:13:54,511][62373] Updated weights for policy 0, policy_version 74120 (0.0008) -[2023-10-17 03:13:54,883][62373] Updated weights for policy 0, policy_version 74130 (0.0009) -[2023-10-17 03:13:55,251][62373] Updated weights for policy 0, policy_version 74140 (0.0010) -[2023-10-17 03:13:57,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 151289856. Throughput: 0: 1780.1, 1: 1756.6. Samples: 37831356. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:13:57,215][61453] Avg episode reward: [(0, '10.840'), (1, '10.790')] -[2023-10-17 03:13:57,854][62408] Updated weights for policy 1, policy_version 73610 (0.0008) -[2023-10-17 03:13:58,222][62408] Updated weights for policy 1, policy_version 73620 (0.0007) -[2023-10-17 03:13:58,600][62408] Updated weights for policy 1, policy_version 73630 (0.0008) -[2023-10-17 03:13:59,050][62373] Updated weights for policy 0, policy_version 74150 (0.0010) -[2023-10-17 03:13:59,429][62373] Updated weights for policy 0, policy_version 74160 (0.0009) -[2023-10-17 03:13:59,797][62373] Updated weights for policy 0, policy_version 74170 (0.0008) -[2023-10-17 03:14:02,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 151355392. Throughput: 0: 1777.4, 1: 1788.4. Samples: 37853786. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:14:02,214][61453] Avg episode reward: [(0, '10.510'), (1, '11.510')] -[2023-10-17 03:14:02,362][62408] Updated weights for policy 1, policy_version 73640 (0.0009) -[2023-10-17 03:14:02,731][62408] Updated weights for policy 1, policy_version 73650 (0.0008) -[2023-10-17 03:14:03,099][62408] Updated weights for policy 1, policy_version 73660 (0.0011) -[2023-10-17 03:14:03,770][62373] Updated weights for policy 0, policy_version 74180 (0.0008) -[2023-10-17 03:14:04,143][62373] Updated weights for policy 0, policy_version 74190 (0.0008) -[2023-10-17 03:14:04,521][62373] Updated weights for policy 0, policy_version 74200 (0.0009) -[2023-10-17 03:14:07,062][62408] Updated weights for policy 1, policy_version 73670 (0.0009) -[2023-10-17 03:14:07,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 151420928. Throughput: 0: 1777.2, 1: 1754.0. Samples: 37863212. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:14:07,215][61453] Avg episode reward: [(0, '10.360'), (1, '11.240')] -[2023-10-17 03:14:07,455][62408] Updated weights for policy 1, policy_version 73680 (0.0008) -[2023-10-17 03:14:07,820][62408] Updated weights for policy 1, policy_version 73690 (0.0010) -[2023-10-17 03:14:08,341][62373] Updated weights for policy 0, policy_version 74210 (0.0008) -[2023-10-17 03:14:08,724][62373] Updated weights for policy 0, policy_version 74220 (0.0011) -[2023-10-17 03:14:09,094][62373] Updated weights for policy 0, policy_version 74230 (0.0009) -[2023-10-17 03:14:09,459][62373] Updated weights for policy 0, policy_version 74240 (0.0009) -[2023-10-17 03:14:11,811][62408] Updated weights for policy 1, policy_version 73700 (0.0010) -[2023-10-17 03:14:12,182][62408] Updated weights for policy 1, policy_version 73710 (0.0007) -[2023-10-17 03:14:12,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 151486464. Throughput: 0: 1767.1, 1: 1779.6. Samples: 37884904. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:14:12,215][61453] Avg episode reward: [(0, '10.130'), (1, '12.020')] -[2023-10-17 03:14:12,546][62408] Updated weights for policy 1, policy_version 73720 (0.0007) -[2023-10-17 03:14:12,842][62252] Saving new best policy, reward=12.020! -[2023-10-17 03:14:13,350][62373] Updated weights for policy 0, policy_version 74250 (0.0009) -[2023-10-17 03:14:13,714][62373] Updated weights for policy 0, policy_version 74260 (0.0009) -[2023-10-17 03:14:14,080][62373] Updated weights for policy 0, policy_version 74270 (0.0009) -[2023-10-17 03:14:16,372][62408] Updated weights for policy 1, policy_version 73730 (0.0009) -[2023-10-17 03:14:16,746][62408] Updated weights for policy 1, policy_version 73740 (0.0008) -[2023-10-17 03:14:17,109][62408] Updated weights for policy 1, policy_version 73750 (0.0008) -[2023-10-17 03:14:17,214][61453] Fps is (10 sec: 13107.0, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 151552000. Throughput: 0: 1785.0, 1: 1771.0. Samples: 37906498. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:14:17,215][61453] Avg episode reward: [(0, '9.850'), (1, '10.800')] -[2023-10-17 03:14:17,487][62408] Updated weights for policy 1, policy_version 73760 (0.0009) -[2023-10-17 03:14:17,713][62373] Updated weights for policy 0, policy_version 74280 (0.0010) -[2023-10-17 03:14:18,080][62373] Updated weights for policy 0, policy_version 74290 (0.0010) -[2023-10-17 03:14:18,452][62373] Updated weights for policy 0, policy_version 74300 (0.0011) -[2023-10-17 03:14:21,137][62408] Updated weights for policy 1, policy_version 73770 (0.0009) -[2023-10-17 03:14:21,509][62408] Updated weights for policy 1, policy_version 73780 (0.0009) -[2023-10-17 03:14:21,886][62408] Updated weights for policy 1, policy_version 73790 (0.0008) -[2023-10-17 03:14:22,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 151650304. Throughput: 0: 1764.6, 1: 1773.0. Samples: 37916826. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:14:22,215][61453] Avg episode reward: [(0, '9.740'), (1, '10.840')] -[2023-10-17 03:14:22,275][62373] Updated weights for policy 0, policy_version 74310 (0.0008) -[2023-10-17 03:14:22,645][62373] Updated weights for policy 0, policy_version 74320 (0.0008) -[2023-10-17 03:14:23,022][62373] Updated weights for policy 0, policy_version 74330 (0.0010) -[2023-10-17 03:14:25,545][62408] Updated weights for policy 1, policy_version 73800 (0.0009) -[2023-10-17 03:14:25,921][62408] Updated weights for policy 1, policy_version 73810 (0.0010) -[2023-10-17 03:14:26,281][62408] Updated weights for policy 1, policy_version 73820 (0.0010) -[2023-10-17 03:14:26,954][62373] Updated weights for policy 0, policy_version 74340 (0.0010) -[2023-10-17 03:14:27,214][61453] Fps is (10 sec: 16384.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 151715840. Throughput: 0: 1773.2, 1: 1780.7. Samples: 37938110. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:14:27,214][61453] Avg episode reward: [(0, '10.100'), (1, '10.310')] -[2023-10-17 03:14:27,319][62373] Updated weights for policy 0, policy_version 74350 (0.0010) -[2023-10-17 03:14:27,684][62373] Updated weights for policy 0, policy_version 74360 (0.0010) -[2023-10-17 03:14:30,073][62408] Updated weights for policy 1, policy_version 73830 (0.0009) -[2023-10-17 03:14:30,436][62408] Updated weights for policy 1, policy_version 73840 (0.0008) -[2023-10-17 03:14:30,810][62408] Updated weights for policy 1, policy_version 73850 (0.0010) -[2023-10-17 03:14:31,520][62373] Updated weights for policy 0, policy_version 74370 (0.0010) -[2023-10-17 03:14:31,895][62373] Updated weights for policy 0, policy_version 74380 (0.0009) -[2023-10-17 03:14:32,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 151781376. Throughput: 0: 1775.6, 1: 1766.9. Samples: 37959086. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:14:32,215][61453] Avg episode reward: [(0, '10.010'), (1, '10.610')] -[2023-10-17 03:14:32,262][62373] Updated weights for policy 0, policy_version 74390 (0.0010) -[2023-10-17 03:14:32,639][62373] Updated weights for policy 0, policy_version 74400 (0.0010) -[2023-10-17 03:14:34,647][62408] Updated weights for policy 1, policy_version 73860 (0.0008) -[2023-10-17 03:14:35,023][62408] Updated weights for policy 1, policy_version 73870 (0.0008) -[2023-10-17 03:14:35,396][62408] Updated weights for policy 1, policy_version 73880 (0.0008) -[2023-10-17 03:14:36,364][62373] Updated weights for policy 0, policy_version 74410 (0.0007) -[2023-10-17 03:14:36,733][62373] Updated weights for policy 0, policy_version 74420 (0.0008) -[2023-10-17 03:14:37,110][62373] Updated weights for policy 0, policy_version 74430 (0.0008) -[2023-10-17 03:14:37,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 151879680. Throughput: 0: 1766.8, 1: 1789.2. Samples: 37970180. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:14:37,215][61453] Avg episode reward: [(0, '9.880'), (1, '9.790')] -[2023-10-17 03:14:39,196][62408] Updated weights for policy 1, policy_version 73890 (0.0009) -[2023-10-17 03:14:39,569][62408] Updated weights for policy 1, policy_version 73900 (0.0008) -[2023-10-17 03:14:39,935][62408] Updated weights for policy 1, policy_version 73910 (0.0007) -[2023-10-17 03:14:40,296][62408] Updated weights for policy 1, policy_version 73920 (0.0007) -[2023-10-17 03:14:40,889][62373] Updated weights for policy 0, policy_version 74440 (0.0009) -[2023-10-17 03:14:41,260][62373] Updated weights for policy 0, policy_version 74450 (0.0009) -[2023-10-17 03:14:41,627][62373] Updated weights for policy 0, policy_version 74460 (0.0008) -[2023-10-17 03:14:42,214][61453] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 151945216. Throughput: 0: 1784.3, 1: 1763.4. Samples: 37991004. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:14:42,215][61453] Avg episode reward: [(0, '10.230'), (1, '10.320')] -[2023-10-17 03:14:43,999][62408] Updated weights for policy 1, policy_version 73930 (0.0007) -[2023-10-17 03:14:44,367][62408] Updated weights for policy 1, policy_version 73940 (0.0008) -[2023-10-17 03:14:44,739][62408] Updated weights for policy 1, policy_version 73950 (0.0008) -[2023-10-17 03:14:45,408][62373] Updated weights for policy 0, policy_version 74470 (0.0008) -[2023-10-17 03:14:45,779][62373] Updated weights for policy 0, policy_version 74480 (0.0008) -[2023-10-17 03:14:46,151][62373] Updated weights for policy 0, policy_version 74490 (0.0009) -[2023-10-17 03:14:47,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 152010752. Throughput: 0: 1759.2, 1: 1764.0. Samples: 38012332. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:14:47,215][61453] Avg episode reward: [(0, '10.240'), (1, '9.940')] -[2023-10-17 03:14:48,676][62408] Updated weights for policy 1, policy_version 73960 (0.0010) -[2023-10-17 03:14:49,047][62408] Updated weights for policy 1, policy_version 73970 (0.0011) -[2023-10-17 03:14:49,403][62408] Updated weights for policy 1, policy_version 73980 (0.0010) -[2023-10-17 03:14:49,861][62373] Updated weights for policy 0, policy_version 74500 (0.0009) -[2023-10-17 03:14:50,226][62373] Updated weights for policy 0, policy_version 74510 (0.0007) -[2023-10-17 03:14:50,589][62373] Updated weights for policy 0, policy_version 74520 (0.0009) -[2023-10-17 03:14:52,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 152076288. Throughput: 0: 1788.1, 1: 1762.0. Samples: 38022968. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:14:52,215][61453] Avg episode reward: [(0, '10.490'), (1, '10.810')] -[2023-10-17 03:14:53,263][62408] Updated weights for policy 1, policy_version 73990 (0.0009) -[2023-10-17 03:14:53,639][62408] Updated weights for policy 1, policy_version 74000 (0.0010) -[2023-10-17 03:14:54,016][62408] Updated weights for policy 1, policy_version 74010 (0.0010) -[2023-10-17 03:14:54,419][62373] Updated weights for policy 0, policy_version 74530 (0.0009) -[2023-10-17 03:14:54,793][62373] Updated weights for policy 0, policy_version 74540 (0.0011) -[2023-10-17 03:14:55,165][62373] Updated weights for policy 0, policy_version 74550 (0.0008) -[2023-10-17 03:14:55,536][62373] Updated weights for policy 0, policy_version 74560 (0.0007) -[2023-10-17 03:14:57,214][61453] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 152141824. Throughput: 0: 1768.4, 1: 1761.7. Samples: 38043762. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:14:57,214][61453] Avg episode reward: [(0, '10.140'), (1, '10.810')] -[2023-10-17 03:14:57,898][62408] Updated weights for policy 1, policy_version 74020 (0.0008) -[2023-10-17 03:14:58,268][62408] Updated weights for policy 1, policy_version 74030 (0.0007) -[2023-10-17 03:14:58,640][62408] Updated weights for policy 1, policy_version 74040 (0.0009) -[2023-10-17 03:14:59,352][62373] Updated weights for policy 0, policy_version 74570 (0.0008) -[2023-10-17 03:14:59,721][62373] Updated weights for policy 0, policy_version 74580 (0.0007) -[2023-10-17 03:15:00,095][62373] Updated weights for policy 0, policy_version 74590 (0.0009) -[2023-10-17 03:15:02,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 152207360. Throughput: 0: 1768.7, 1: 1774.9. Samples: 38065960. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:15:02,215][61453] Avg episode reward: [(0, '10.050'), (1, '10.350')] -[2023-10-17 03:15:02,334][62408] Updated weights for policy 1, policy_version 74050 (0.0008) -[2023-10-17 03:15:02,710][62408] Updated weights for policy 1, policy_version 74060 (0.0009) -[2023-10-17 03:15:03,071][62408] Updated weights for policy 1, policy_version 74070 (0.0008) -[2023-10-17 03:15:03,437][62408] Updated weights for policy 1, policy_version 74080 (0.0008) -[2023-10-17 03:15:03,793][62373] Updated weights for policy 0, policy_version 74600 (0.0008) -[2023-10-17 03:15:04,155][62373] Updated weights for policy 0, policy_version 74610 (0.0009) -[2023-10-17 03:15:04,533][62373] Updated weights for policy 0, policy_version 74620 (0.0007) -[2023-10-17 03:15:07,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 152272896. Throughput: 0: 1770.7, 1: 1760.5. Samples: 38075732. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:15:07,214][61453] Avg episode reward: [(0, '10.340'), (1, '11.230')] -[2023-10-17 03:15:07,233][62408] Updated weights for policy 1, policy_version 74090 (0.0008) -[2023-10-17 03:15:07,598][62408] Updated weights for policy 1, policy_version 74100 (0.0007) -[2023-10-17 03:15:07,956][62408] Updated weights for policy 1, policy_version 74110 (0.0009) -[2023-10-17 03:15:08,321][62373] Updated weights for policy 0, policy_version 74630 (0.0008) -[2023-10-17 03:15:08,701][62373] Updated weights for policy 0, policy_version 74640 (0.0010) -[2023-10-17 03:15:09,065][62373] Updated weights for policy 0, policy_version 74650 (0.0008) -[2023-10-17 03:15:11,842][62408] Updated weights for policy 1, policy_version 74120 (0.0009) -[2023-10-17 03:15:12,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 152338432. Throughput: 0: 1774.4, 1: 1775.2. Samples: 38097844. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:15:12,215][61453] Avg episode reward: [(0, '10.590'), (1, '11.600')] -[2023-10-17 03:15:12,223][62408] Updated weights for policy 1, policy_version 74130 (0.0007) -[2023-10-17 03:15:12,580][62408] Updated weights for policy 1, policy_version 74140 (0.0007) -[2023-10-17 03:15:12,895][62373] Updated weights for policy 0, policy_version 74660 (0.0009) -[2023-10-17 03:15:13,265][62373] Updated weights for policy 0, policy_version 74670 (0.0008) -[2023-10-17 03:15:13,631][62373] Updated weights for policy 0, policy_version 74680 (0.0008) -[2023-10-17 03:15:16,222][62408] Updated weights for policy 1, policy_version 74150 (0.0008) -[2023-10-17 03:15:16,594][62408] Updated weights for policy 1, policy_version 74160 (0.0007) -[2023-10-17 03:15:16,953][62408] Updated weights for policy 1, policy_version 74170 (0.0008) -[2023-10-17 03:15:17,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14745.7, 300 sec: 14218.0). Total num frames: 152436736. Throughput: 0: 1783.0, 1: 1772.5. Samples: 38119086. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:15:17,215][61453] Avg episode reward: [(0, '9.820'), (1, '12.570')] -[2023-10-17 03:15:17,225][62252] Saving new best policy, reward=12.570! -[2023-10-17 03:15:17,537][62373] Updated weights for policy 0, policy_version 74690 (0.0008) -[2023-10-17 03:15:17,905][62373] Updated weights for policy 0, policy_version 74700 (0.0008) -[2023-10-17 03:15:18,284][62373] Updated weights for policy 0, policy_version 74710 (0.0009) -[2023-10-17 03:15:18,647][62373] Updated weights for policy 0, policy_version 74720 (0.0008) -[2023-10-17 03:15:20,718][62408] Updated weights for policy 1, policy_version 74180 (0.0010) -[2023-10-17 03:15:21,087][62408] Updated weights for policy 1, policy_version 74190 (0.0010) -[2023-10-17 03:15:21,451][62408] Updated weights for policy 1, policy_version 74200 (0.0009) -[2023-10-17 03:15:22,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 152502272. Throughput: 0: 1770.2, 1: 1775.1. Samples: 38129720. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:15:22,214][61453] Avg episode reward: [(0, '9.480'), (1, '11.660')] -[2023-10-17 03:15:22,492][62373] Updated weights for policy 0, policy_version 74730 (0.0008) -[2023-10-17 03:15:22,863][62373] Updated weights for policy 0, policy_version 74740 (0.0009) -[2023-10-17 03:15:23,233][62373] Updated weights for policy 0, policy_version 74750 (0.0007) -[2023-10-17 03:15:25,230][62408] Updated weights for policy 1, policy_version 74210 (0.0007) -[2023-10-17 03:15:25,595][62408] Updated weights for policy 1, policy_version 74220 (0.0009) -[2023-10-17 03:15:25,962][62408] Updated weights for policy 1, policy_version 74230 (0.0008) -[2023-10-17 03:15:26,329][62408] Updated weights for policy 1, policy_version 74240 (0.0008) -[2023-10-17 03:15:26,964][62373] Updated weights for policy 0, policy_version 74760 (0.0011) -[2023-10-17 03:15:27,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 152567808. Throughput: 0: 1774.5, 1: 1783.5. Samples: 38151114. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:15:27,214][61453] Avg episode reward: [(0, '9.740'), (1, '11.700')] -[2023-10-17 03:15:27,334][62373] Updated weights for policy 0, policy_version 74770 (0.0010) -[2023-10-17 03:15:27,716][62373] Updated weights for policy 0, policy_version 74780 (0.0009) -[2023-10-17 03:15:29,922][62408] Updated weights for policy 1, policy_version 74250 (0.0011) -[2023-10-17 03:15:30,292][62408] Updated weights for policy 1, policy_version 74260 (0.0009) -[2023-10-17 03:15:30,659][62408] Updated weights for policy 1, policy_version 74270 (0.0008) -[2023-10-17 03:15:31,533][62373] Updated weights for policy 0, policy_version 74790 (0.0007) -[2023-10-17 03:15:31,902][62373] Updated weights for policy 0, policy_version 74800 (0.0007) -[2023-10-17 03:15:32,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 152633344. Throughput: 0: 1783.4, 1: 1770.4. Samples: 38172254. Policy #0 lag: (min: 21.0, avg: 24.0, max: 53.0) -[2023-10-17 03:15:32,215][61453] Avg episode reward: [(0, '10.060'), (1, '11.740')] -[2023-10-17 03:15:32,224][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000074272_76054528.pth... -[2023-10-17 03:15:32,264][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000072608_74350592.pth -[2023-10-17 03:15:32,269][62252] Saving a milestone ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/milestones/checkpoint_000074272_76054528.pth -[2023-10-17 03:15:32,280][62373] Updated weights for policy 0, policy_version 74810 (0.0007) -[2023-10-17 03:15:32,500][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000074816_76611584.pth... -[2023-10-17 03:15:32,528][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000073152_74907648.pth -[2023-10-17 03:15:32,532][62094] Saving a milestone ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/milestones/checkpoint_000074816_76611584.pth -[2023-10-17 03:15:34,474][62408] Updated weights for policy 1, policy_version 74280 (0.0008) -[2023-10-17 03:15:34,841][62408] Updated weights for policy 1, policy_version 74290 (0.0008) -[2023-10-17 03:15:35,212][62408] Updated weights for policy 1, policy_version 74300 (0.0009) -[2023-10-17 03:15:36,154][62373] Updated weights for policy 0, policy_version 74820 (0.0008) -[2023-10-17 03:15:36,516][62373] Updated weights for policy 0, policy_version 74830 (0.0009) -[2023-10-17 03:15:36,887][62373] Updated weights for policy 0, policy_version 74840 (0.0010) -[2023-10-17 03:15:37,214][61453] Fps is (10 sec: 16383.6, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 152731648. Throughput: 0: 1769.9, 1: 1788.1. Samples: 38183080. Policy #0 lag: (min: 21.0, avg: 24.0, max: 53.0) -[2023-10-17 03:15:37,215][61453] Avg episode reward: [(0, '9.780'), (1, '11.710')] -[2023-10-17 03:15:39,151][62408] Updated weights for policy 1, policy_version 74310 (0.0008) -[2023-10-17 03:15:39,509][62408] Updated weights for policy 1, policy_version 74320 (0.0008) -[2023-10-17 03:15:39,874][62408] Updated weights for policy 1, policy_version 74330 (0.0007) -[2023-10-17 03:15:40,844][62373] Updated weights for policy 0, policy_version 74850 (0.0010) -[2023-10-17 03:15:41,216][62373] Updated weights for policy 0, policy_version 74860 (0.0007) -[2023-10-17 03:15:41,590][62373] Updated weights for policy 0, policy_version 74870 (0.0009) -[2023-10-17 03:15:41,969][62373] Updated weights for policy 0, policy_version 74880 (0.0010) -[2023-10-17 03:15:42,214][61453] Fps is (10 sec: 16384.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 152797184. Throughput: 0: 1785.6, 1: 1778.3. Samples: 38204136. Policy #0 lag: (min: 21.0, avg: 24.0, max: 53.0) -[2023-10-17 03:15:42,214][61453] Avg episode reward: [(0, '9.480'), (1, '11.530')] -[2023-10-17 03:15:43,720][62408] Updated weights for policy 1, policy_version 74340 (0.0008) -[2023-10-17 03:15:44,126][62408] Updated weights for policy 1, policy_version 74350 (0.0007) -[2023-10-17 03:15:44,485][62408] Updated weights for policy 1, policy_version 74360 (0.0007) -[2023-10-17 03:15:45,823][62373] Updated weights for policy 0, policy_version 74890 (0.0010) -[2023-10-17 03:15:46,189][62373] Updated weights for policy 0, policy_version 74900 (0.0011) -[2023-10-17 03:15:46,556][62373] Updated weights for policy 0, policy_version 74910 (0.0009) -[2023-10-17 03:15:47,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 152862720. Throughput: 0: 1755.1, 1: 1776.2. Samples: 38224868. Policy #0 lag: (min: 21.0, avg: 24.0, max: 53.0) -[2023-10-17 03:15:47,215][61453] Avg episode reward: [(0, '8.970'), (1, '11.470')] -[2023-10-17 03:15:48,201][62408] Updated weights for policy 1, policy_version 74370 (0.0010) -[2023-10-17 03:15:48,576][62408] Updated weights for policy 1, policy_version 74380 (0.0008) -[2023-10-17 03:15:48,942][62408] Updated weights for policy 1, policy_version 74390 (0.0008) -[2023-10-17 03:15:49,310][62408] Updated weights for policy 1, policy_version 74400 (0.0008) -[2023-10-17 03:15:50,377][62373] Updated weights for policy 0, policy_version 74920 (0.0009) -[2023-10-17 03:15:50,747][62373] Updated weights for policy 0, policy_version 74930 (0.0011) -[2023-10-17 03:15:51,113][62373] Updated weights for policy 0, policy_version 74940 (0.0010) -[2023-10-17 03:15:52,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 152928256. Throughput: 0: 1786.2, 1: 1773.5. Samples: 38235918. Policy #0 lag: (min: 21.0, avg: 24.0, max: 53.0) -[2023-10-17 03:15:52,215][61453] Avg episode reward: [(0, '9.690'), (1, '11.330')] -[2023-10-17 03:15:53,262][62408] Updated weights for policy 1, policy_version 74410 (0.0010) -[2023-10-17 03:15:53,621][62408] Updated weights for policy 1, policy_version 74420 (0.0008) -[2023-10-17 03:15:53,989][62408] Updated weights for policy 1, policy_version 74430 (0.0009) -[2023-10-17 03:15:54,893][62373] Updated weights for policy 0, policy_version 74950 (0.0009) -[2023-10-17 03:15:55,261][62373] Updated weights for policy 0, policy_version 74960 (0.0008) -[2023-10-17 03:15:55,631][62373] Updated weights for policy 0, policy_version 74970 (0.0008) -[2023-10-17 03:15:57,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 152993792. Throughput: 0: 1757.2, 1: 1766.8. Samples: 38256422. Policy #0 lag: (min: 21.0, avg: 24.0, max: 53.0) -[2023-10-17 03:15:57,215][61453] Avg episode reward: [(0, '10.170'), (1, '11.450')] -[2023-10-17 03:15:58,024][62408] Updated weights for policy 1, policy_version 74440 (0.0008) -[2023-10-17 03:15:58,405][62408] Updated weights for policy 1, policy_version 74450 (0.0009) -[2023-10-17 03:15:58,762][62408] Updated weights for policy 1, policy_version 74460 (0.0009) -[2023-10-17 03:15:59,419][62373] Updated weights for policy 0, policy_version 74980 (0.0011) -[2023-10-17 03:15:59,792][62373] Updated weights for policy 0, policy_version 74990 (0.0011) -[2023-10-17 03:16:00,158][62373] Updated weights for policy 0, policy_version 75000 (0.0008) -[2023-10-17 03:16:02,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 153059328. Throughput: 0: 1756.7, 1: 1779.0. Samples: 38278192. Policy #0 lag: (min: 21.0, avg: 24.0, max: 53.0) -[2023-10-17 03:16:02,215][61453] Avg episode reward: [(0, '10.280'), (1, '10.710')] -[2023-10-17 03:16:02,733][62408] Updated weights for policy 1, policy_version 74470 (0.0007) -[2023-10-17 03:16:03,098][62408] Updated weights for policy 1, policy_version 74480 (0.0007) -[2023-10-17 03:16:03,473][62408] Updated weights for policy 1, policy_version 74490 (0.0009) -[2023-10-17 03:16:03,995][62373] Updated weights for policy 0, policy_version 75010 (0.0009) -[2023-10-17 03:16:04,367][62373] Updated weights for policy 0, policy_version 75020 (0.0007) -[2023-10-17 03:16:04,744][62373] Updated weights for policy 0, policy_version 75030 (0.0008) -[2023-10-17 03:16:05,113][62373] Updated weights for policy 0, policy_version 75040 (0.0008) -[2023-10-17 03:16:07,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 153124864. Throughput: 0: 1763.5, 1: 1756.9. Samples: 38288136. Policy #0 lag: (min: 21.0, avg: 24.0, max: 53.0) -[2023-10-17 03:16:07,214][61453] Avg episode reward: [(0, '9.900'), (1, '10.890')] -[2023-10-17 03:16:07,298][62408] Updated weights for policy 1, policy_version 74500 (0.0007) -[2023-10-17 03:16:07,660][62408] Updated weights for policy 1, policy_version 74510 (0.0009) -[2023-10-17 03:16:08,022][62408] Updated weights for policy 1, policy_version 74520 (0.0010) -[2023-10-17 03:16:08,884][62373] Updated weights for policy 0, policy_version 75050 (0.0009) -[2023-10-17 03:16:09,258][62373] Updated weights for policy 0, policy_version 75060 (0.0009) -[2023-10-17 03:16:09,627][62373] Updated weights for policy 0, policy_version 75070 (0.0009) -[2023-10-17 03:16:11,734][62408] Updated weights for policy 1, policy_version 74530 (0.0009) -[2023-10-17 03:16:12,102][62408] Updated weights for policy 1, policy_version 74540 (0.0008) -[2023-10-17 03:16:12,214][61453] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 153190400. Throughput: 0: 1760.5, 1: 1768.8. Samples: 38309932. Policy #0 lag: (min: 21.0, avg: 24.0, max: 53.0) -[2023-10-17 03:16:12,215][61453] Avg episode reward: [(0, '9.870'), (1, '11.150')] -[2023-10-17 03:16:12,463][62408] Updated weights for policy 1, policy_version 74550 (0.0011) -[2023-10-17 03:16:12,830][62408] Updated weights for policy 1, policy_version 74560 (0.0011) -[2023-10-17 03:16:13,302][62373] Updated weights for policy 0, policy_version 75080 (0.0008) -[2023-10-17 03:16:13,671][62373] Updated weights for policy 0, policy_version 75090 (0.0007) -[2023-10-17 03:16:14,040][62373] Updated weights for policy 0, policy_version 75100 (0.0007) -[2023-10-17 03:16:16,738][62408] Updated weights for policy 1, policy_version 74570 (0.0009) -[2023-10-17 03:16:17,100][62408] Updated weights for policy 1, policy_version 74580 (0.0009) -[2023-10-17 03:16:17,214][61453] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 153255936. Throughput: 0: 1784.3, 1: 1765.8. Samples: 38332010. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-17 03:16:17,215][61453] Avg episode reward: [(0, '10.110'), (1, '11.800')] -[2023-10-17 03:16:17,462][62408] Updated weights for policy 1, policy_version 74590 (0.0009) -[2023-10-17 03:16:17,698][62373] Updated weights for policy 0, policy_version 75110 (0.0007) -[2023-10-17 03:16:18,056][62373] Updated weights for policy 0, policy_version 75120 (0.0007) -[2023-10-17 03:16:18,430][62373] Updated weights for policy 0, policy_version 75130 (0.0007) -[2023-10-17 03:16:21,244][62408] Updated weights for policy 1, policy_version 74600 (0.0007) -[2023-10-17 03:16:21,612][62408] Updated weights for policy 1, policy_version 74610 (0.0010) -[2023-10-17 03:16:21,973][62408] Updated weights for policy 1, policy_version 74620 (0.0007) -[2023-10-17 03:16:22,112][62373] Updated weights for policy 0, policy_version 75140 (0.0008) -[2023-10-17 03:16:22,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 153354240. Throughput: 0: 1772.6, 1: 1767.8. Samples: 38342396. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-17 03:16:22,214][61453] Avg episode reward: [(0, '10.670'), (1, '11.350')] -[2023-10-17 03:16:22,488][62373] Updated weights for policy 0, policy_version 75150 (0.0009) -[2023-10-17 03:16:22,863][62373] Updated weights for policy 0, policy_version 75160 (0.0008) -[2023-10-17 03:16:25,817][62408] Updated weights for policy 1, policy_version 74630 (0.0008) -[2023-10-17 03:16:26,184][62408] Updated weights for policy 1, policy_version 74640 (0.0009) -[2023-10-17 03:16:26,564][62408] Updated weights for policy 1, policy_version 74650 (0.0009) -[2023-10-17 03:16:26,739][62373] Updated weights for policy 0, policy_version 75170 (0.0007) -[2023-10-17 03:16:27,113][62373] Updated weights for policy 0, policy_version 75180 (0.0009) -[2023-10-17 03:16:27,214][61453] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 153419776. Throughput: 0: 1780.5, 1: 1773.2. Samples: 38364052. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-17 03:16:27,214][61453] Avg episode reward: [(0, '10.640'), (1, '10.900')] -[2023-10-17 03:16:27,476][62373] Updated weights for policy 0, policy_version 75190 (0.0009) -[2023-10-17 03:16:27,850][62373] Updated weights for policy 0, policy_version 75200 (0.0009) -[2023-10-17 03:16:30,496][62408] Updated weights for policy 1, policy_version 74660 (0.0008) -[2023-10-17 03:16:30,882][62408] Updated weights for policy 1, policy_version 74670 (0.0010) -[2023-10-17 03:16:31,261][62408] Updated weights for policy 1, policy_version 74680 (0.0012) -[2023-10-17 03:16:31,847][62373] Updated weights for policy 0, policy_version 75210 (0.0007) -[2023-10-17 03:16:32,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 153485312. Throughput: 0: 1793.6, 1: 1747.9. Samples: 38384234. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-17 03:16:32,215][61453] Avg episode reward: [(0, '10.700'), (1, '11.040')] -[2023-10-17 03:16:32,221][62373] Updated weights for policy 0, policy_version 75220 (0.0007) -[2023-10-17 03:16:32,600][62373] Updated weights for policy 0, policy_version 75230 (0.0009) -[2023-10-17 03:16:35,136][62408] Updated weights for policy 1, policy_version 74690 (0.0008) -[2023-10-17 03:16:35,509][62408] Updated weights for policy 1, policy_version 74700 (0.0009) -[2023-10-17 03:16:35,871][62408] Updated weights for policy 1, policy_version 74710 (0.0008) -[2023-10-17 03:16:36,238][62408] Updated weights for policy 1, policy_version 74720 (0.0009) -[2023-10-17 03:16:36,249][62373] Updated weights for policy 0, policy_version 75240 (0.0010) -[2023-10-17 03:16:36,613][62373] Updated weights for policy 0, policy_version 75250 (0.0008) -[2023-10-17 03:16:36,983][62373] Updated weights for policy 0, policy_version 75260 (0.0008) -[2023-10-17 03:16:37,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 153583616. Throughput: 0: 1774.5, 1: 1777.8. Samples: 38395774. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-17 03:16:37,214][61453] Avg episode reward: [(0, '10.710'), (1, '11.030')] -[2023-10-17 03:16:40,176][62408] Updated weights for policy 1, policy_version 74730 (0.0008) -[2023-10-17 03:16:40,547][62408] Updated weights for policy 1, policy_version 74740 (0.0007) -[2023-10-17 03:16:40,679][62373] Updated weights for policy 0, policy_version 75270 (0.0008) -[2023-10-17 03:16:40,911][62408] Updated weights for policy 1, policy_version 74750 (0.0009) -[2023-10-17 03:16:41,043][62373] Updated weights for policy 0, policy_version 75280 (0.0008) -[2023-10-17 03:16:41,421][62373] Updated weights for policy 0, policy_version 75290 (0.0007) -[2023-10-17 03:16:42,214][61453] Fps is (10 sec: 16384.4, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 153649152. Throughput: 0: 1796.4, 1: 1750.1. Samples: 38416014. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-17 03:16:42,215][61453] Avg episode reward: [(0, '9.790'), (1, '10.970')] -[2023-10-17 03:16:44,839][62408] Updated weights for policy 1, policy_version 74760 (0.0007) -[2023-10-17 03:16:45,205][62373] Updated weights for policy 0, policy_version 75300 (0.0010) -[2023-10-17 03:16:45,209][62408] Updated weights for policy 1, policy_version 74770 (0.0008) -[2023-10-17 03:16:45,575][62373] Updated weights for policy 0, policy_version 75310 (0.0007) -[2023-10-17 03:16:45,575][62408] Updated weights for policy 1, policy_version 74780 (0.0008) -[2023-10-17 03:16:45,941][62373] Updated weights for policy 0, policy_version 75320 (0.0010) -[2023-10-17 03:16:47,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 153714688. Throughput: 0: 1782.8, 1: 1742.4. Samples: 38436826. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-17 03:16:47,214][61453] Avg episode reward: [(0, '10.490'), (1, '11.060')] -[2023-10-17 03:16:49,446][62408] Updated weights for policy 1, policy_version 74790 (0.0008) -[2023-10-17 03:16:49,688][62373] Updated weights for policy 0, policy_version 75330 (0.0007) -[2023-10-17 03:16:49,800][62408] Updated weights for policy 1, policy_version 74800 (0.0008) -[2023-10-17 03:16:50,053][62373] Updated weights for policy 0, policy_version 75340 (0.0007) -[2023-10-17 03:16:50,175][62408] Updated weights for policy 1, policy_version 74810 (0.0009) -[2023-10-17 03:16:50,420][62373] Updated weights for policy 0, policy_version 75350 (0.0007) -[2023-10-17 03:16:50,792][62373] Updated weights for policy 0, policy_version 75360 (0.0010) -[2023-10-17 03:16:52,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 153780224. Throughput: 0: 1799.9, 1: 1753.3. Samples: 38448032. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-17 03:16:52,214][61453] Avg episode reward: [(0, '10.390'), (1, '9.660')] -[2023-10-17 03:16:54,058][62408] Updated weights for policy 1, policy_version 74820 (0.0009) -[2023-10-17 03:16:54,426][62408] Updated weights for policy 1, policy_version 74830 (0.0008) -[2023-10-17 03:16:54,504][62373] Updated weights for policy 0, policy_version 75370 (0.0008) -[2023-10-17 03:16:54,788][62408] Updated weights for policy 1, policy_version 74840 (0.0010) -[2023-10-17 03:16:54,885][62373] Updated weights for policy 0, policy_version 75380 (0.0009) -[2023-10-17 03:16:55,250][62373] Updated weights for policy 0, policy_version 75390 (0.0010) -[2023-10-17 03:16:57,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 153845760. Throughput: 0: 1779.6, 1: 1737.9. Samples: 38468220. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-17 03:16:57,215][61453] Avg episode reward: [(0, '9.750'), (1, '10.100')] -[2023-10-17 03:16:58,573][62408] Updated weights for policy 1, policy_version 74850 (0.0007) -[2023-10-17 03:16:58,939][62408] Updated weights for policy 1, policy_version 74860 (0.0011) -[2023-10-17 03:16:58,972][62373] Updated weights for policy 0, policy_version 75400 (0.0008) -[2023-10-17 03:16:59,308][62408] Updated weights for policy 1, policy_version 74870 (0.0009) -[2023-10-17 03:16:59,339][62373] Updated weights for policy 0, policy_version 75410 (0.0009) -[2023-10-17 03:16:59,665][62408] Updated weights for policy 1, policy_version 74880 (0.0009) -[2023-10-17 03:16:59,705][62373] Updated weights for policy 0, policy_version 75420 (0.0008) -[2023-10-17 03:17:02,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 153911296. Throughput: 0: 1773.5, 1: 1751.2. Samples: 38490618. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-17 03:17:02,215][61453] Avg episode reward: [(0, '9.710'), (1, '10.140')] -[2023-10-17 03:17:03,364][62408] Updated weights for policy 1, policy_version 74890 (0.0009) -[2023-10-17 03:17:03,511][62373] Updated weights for policy 0, policy_version 75430 (0.0008) -[2023-10-17 03:17:03,728][62408] Updated weights for policy 1, policy_version 74900 (0.0007) -[2023-10-17 03:17:03,879][62373] Updated weights for policy 0, policy_version 75440 (0.0007) -[2023-10-17 03:17:04,098][62408] Updated weights for policy 1, policy_version 74910 (0.0008) -[2023-10-17 03:17:04,238][62373] Updated weights for policy 0, policy_version 75450 (0.0008) -[2023-10-17 03:17:07,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 153976832. Throughput: 0: 1775.0, 1: 1740.8. Samples: 38500608. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-17 03:17:07,215][61453] Avg episode reward: [(0, '9.380'), (1, '9.510')] -[2023-10-17 03:17:08,152][62373] Updated weights for policy 0, policy_version 75460 (0.0007) -[2023-10-17 03:17:08,161][62408] Updated weights for policy 1, policy_version 74920 (0.0007) -[2023-10-17 03:17:08,515][62373] Updated weights for policy 0, policy_version 75470 (0.0008) -[2023-10-17 03:17:08,532][62408] Updated weights for policy 1, policy_version 74930 (0.0008) -[2023-10-17 03:17:08,886][62373] Updated weights for policy 0, policy_version 75480 (0.0007) -[2023-10-17 03:17:08,899][62408] Updated weights for policy 1, policy_version 74940 (0.0008) -[2023-10-17 03:17:12,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 154042368. Throughput: 0: 1771.8, 1: 1740.2. Samples: 38522092. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-17 03:17:12,216][61453] Avg episode reward: [(0, '10.050'), (1, '10.110')] -[2023-10-17 03:17:12,650][62408] Updated weights for policy 1, policy_version 74950 (0.0008) -[2023-10-17 03:17:12,682][62373] Updated weights for policy 0, policy_version 75490 (0.0009) -[2023-10-17 03:17:13,019][62408] Updated weights for policy 1, policy_version 74960 (0.0007) -[2023-10-17 03:17:13,041][62373] Updated weights for policy 0, policy_version 75500 (0.0008) -[2023-10-17 03:17:13,385][62408] Updated weights for policy 1, policy_version 74970 (0.0009) -[2023-10-17 03:17:13,409][62373] Updated weights for policy 0, policy_version 75510 (0.0008) -[2023-10-17 03:17:13,779][62373] Updated weights for policy 0, policy_version 75520 (0.0008) -[2023-10-17 03:17:17,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 154107904. Throughput: 0: 1789.5, 1: 1765.4. Samples: 38544206. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-17 03:17:17,215][61453] Avg episode reward: [(0, '9.280'), (1, '10.020')] -[2023-10-17 03:17:17,358][62408] Updated weights for policy 1, policy_version 74980 (0.0007) -[2023-10-17 03:17:17,684][62373] Updated weights for policy 0, policy_version 75530 (0.0008) -[2023-10-17 03:17:17,754][62408] Updated weights for policy 1, policy_version 74990 (0.0008) -[2023-10-17 03:17:18,054][62373] Updated weights for policy 0, policy_version 75540 (0.0008) -[2023-10-17 03:17:18,125][62408] Updated weights for policy 1, policy_version 75000 (0.0007) -[2023-10-17 03:17:18,422][62373] Updated weights for policy 0, policy_version 75550 (0.0009) -[2023-10-17 03:17:21,815][62408] Updated weights for policy 1, policy_version 75010 (0.0007) -[2023-10-17 03:17:22,181][62408] Updated weights for policy 1, policy_version 75020 (0.0007) -[2023-10-17 03:17:22,214][61453] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 154173440. Throughput: 0: 1772.1, 1: 1734.9. Samples: 38553592. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-17 03:17:22,215][61453] Avg episode reward: [(0, '8.980'), (1, '10.320')] -[2023-10-17 03:17:22,216][62373] Updated weights for policy 0, policy_version 75560 (0.0008) -[2023-10-17 03:17:22,549][62408] Updated weights for policy 1, policy_version 75030 (0.0008) -[2023-10-17 03:17:22,592][62373] Updated weights for policy 0, policy_version 75570 (0.0007) -[2023-10-17 03:17:22,919][62408] Updated weights for policy 1, policy_version 75040 (0.0008) -[2023-10-17 03:17:22,954][62373] Updated weights for policy 0, policy_version 75580 (0.0007) -[2023-10-17 03:17:26,739][62373] Updated weights for policy 0, policy_version 75590 (0.0008) -[2023-10-17 03:17:26,833][62408] Updated weights for policy 1, policy_version 75050 (0.0008) -[2023-10-17 03:17:27,108][62373] Updated weights for policy 0, policy_version 75600 (0.0007) -[2023-10-17 03:17:27,194][62408] Updated weights for policy 1, policy_version 75060 (0.0009) -[2023-10-17 03:17:27,214][61453] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 154238976. Throughput: 0: 1783.2, 1: 1763.6. Samples: 38575624. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-17 03:17:27,215][61453] Avg episode reward: [(0, '9.340'), (1, '9.840')] -[2023-10-17 03:17:27,469][62373] Updated weights for policy 0, policy_version 75610 (0.0007) -[2023-10-17 03:17:27,567][62408] Updated weights for policy 1, policy_version 75070 (0.0007) -[2023-10-17 03:17:31,298][62408] Updated weights for policy 1, policy_version 75080 (0.0008) -[2023-10-17 03:17:31,478][62373] Updated weights for policy 0, policy_version 75620 (0.0007) -[2023-10-17 03:17:31,670][62408] Updated weights for policy 1, policy_version 75090 (0.0007) -[2023-10-17 03:17:31,844][62373] Updated weights for policy 0, policy_version 75630 (0.0007) -[2023-10-17 03:17:32,047][62408] Updated weights for policy 1, policy_version 75100 (0.0008) -[2023-10-17 03:17:32,214][61453] Fps is (10 sec: 16383.4, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 154337280. Throughput: 0: 1782.0, 1: 1756.0. Samples: 38596040. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-17 03:17:32,216][61453] Avg episode reward: [(0, '9.260'), (1, '9.370')] -[2023-10-17 03:17:32,225][62373] Updated weights for policy 0, policy_version 75640 (0.0007) -[2023-10-17 03:17:32,226][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000075104_76906496.pth... -[2023-10-17 03:17:32,260][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000073440_75202560.pth -[2023-10-17 03:17:32,519][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000075648_77463552.pth... -[2023-10-17 03:17:32,558][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000073984_75759616.pth -[2023-10-17 03:17:35,962][62408] Updated weights for policy 1, policy_version 75110 (0.0010) -[2023-10-17 03:17:36,113][62373] Updated weights for policy 0, policy_version 75650 (0.0007) -[2023-10-17 03:17:36,337][62408] Updated weights for policy 1, policy_version 75120 (0.0010) -[2023-10-17 03:17:36,477][62373] Updated weights for policy 0, policy_version 75660 (0.0008) -[2023-10-17 03:17:36,703][62408] Updated weights for policy 1, policy_version 75130 (0.0007) -[2023-10-17 03:17:36,849][62373] Updated weights for policy 0, policy_version 75670 (0.0008) -[2023-10-17 03:17:37,214][61453] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 154402816. Throughput: 0: 1772.4, 1: 1768.6. Samples: 38607374. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-17 03:17:37,214][61453] Avg episode reward: [(0, '9.310'), (1, '9.770')] -[2023-10-17 03:17:37,220][62373] Updated weights for policy 0, policy_version 75680 (0.0009) -[2023-10-17 03:17:40,607][62408] Updated weights for policy 1, policy_version 75140 (0.0010) -[2023-10-17 03:17:40,974][62408] Updated weights for policy 1, policy_version 75150 (0.0007) -[2023-10-17 03:17:41,089][62373] Updated weights for policy 0, policy_version 75690 (0.0007) -[2023-10-17 03:17:41,338][62408] Updated weights for policy 1, policy_version 75160 (0.0010) -[2023-10-17 03:17:41,450][62373] Updated weights for policy 0, policy_version 75700 (0.0008) -[2023-10-17 03:17:41,818][62373] Updated weights for policy 0, policy_version 75710 (0.0009) -[2023-10-17 03:17:42,214][61453] Fps is (10 sec: 16384.8, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 154501120. Throughput: 0: 1791.7, 1: 1770.3. Samples: 38628510. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-17 03:17:42,215][61453] Avg episode reward: [(0, '9.430'), (1, '8.770')] -[2023-10-17 03:17:45,188][62408] Updated weights for policy 1, policy_version 75170 (0.0007) -[2023-10-17 03:17:45,446][62373] Updated weights for policy 0, policy_version 75720 (0.0008) -[2023-10-17 03:17:45,561][62408] Updated weights for policy 1, policy_version 75180 (0.0007) -[2023-10-17 03:17:45,807][62373] Updated weights for policy 0, policy_version 75730 (0.0008) -[2023-10-17 03:17:45,935][62408] Updated weights for policy 1, policy_version 75190 (0.0009) -[2023-10-17 03:17:46,180][62373] Updated weights for policy 0, policy_version 75740 (0.0009) -[2023-10-17 03:17:46,303][62408] Updated weights for policy 1, policy_version 75200 (0.0009) -[2023-10-17 03:17:47,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 154566656. Throughput: 0: 1766.0, 1: 1741.7. Samples: 38648468. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-17 03:17:47,215][61453] Avg episode reward: [(0, '9.340'), (1, '9.710')] -[2023-10-17 03:17:49,910][62373] Updated weights for policy 0, policy_version 75750 (0.0008) -[2023-10-17 03:17:50,165][62408] Updated weights for policy 1, policy_version 75210 (0.0009) -[2023-10-17 03:17:50,281][62373] Updated weights for policy 0, policy_version 75760 (0.0007) -[2023-10-17 03:17:50,530][62408] Updated weights for policy 1, policy_version 75220 (0.0009) -[2023-10-17 03:17:50,650][62373] Updated weights for policy 0, policy_version 75770 (0.0008) -[2023-10-17 03:17:50,900][62408] Updated weights for policy 1, policy_version 75230 (0.0008) -[2023-10-17 03:17:52,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 154632192. Throughput: 0: 1784.5, 1: 1766.1. Samples: 38660382. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:17:52,215][61453] Avg episode reward: [(0, '9.500'), (1, '9.760')] -[2023-10-17 03:17:54,425][62373] Updated weights for policy 0, policy_version 75780 (0.0009) -[2023-10-17 03:17:54,715][62408] Updated weights for policy 1, policy_version 75240 (0.0009) -[2023-10-17 03:17:54,792][62373] Updated weights for policy 0, policy_version 75790 (0.0007) -[2023-10-17 03:17:55,082][62408] Updated weights for policy 1, policy_version 75250 (0.0007) -[2023-10-17 03:17:55,166][62373] Updated weights for policy 0, policy_version 75800 (0.0007) -[2023-10-17 03:17:55,446][62408] Updated weights for policy 1, policy_version 75260 (0.0008) -[2023-10-17 03:17:57,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 154697728. Throughput: 0: 1763.6, 1: 1746.3. Samples: 38680034. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:17:57,215][61453] Avg episode reward: [(0, '10.010'), (1, '9.560')] -[2023-10-17 03:17:58,893][62373] Updated weights for policy 0, policy_version 75810 (0.0009) -[2023-10-17 03:17:59,247][62408] Updated weights for policy 1, policy_version 75270 (0.0007) -[2023-10-17 03:17:59,262][62373] Updated weights for policy 0, policy_version 75820 (0.0007) -[2023-10-17 03:17:59,607][62408] Updated weights for policy 1, policy_version 75280 (0.0007) -[2023-10-17 03:17:59,632][62373] Updated weights for policy 0, policy_version 75830 (0.0008) -[2023-10-17 03:17:59,970][62408] Updated weights for policy 1, policy_version 75290 (0.0008) -[2023-10-17 03:17:59,999][62373] Updated weights for policy 0, policy_version 75840 (0.0007) -[2023-10-17 03:18:02,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 154763264. Throughput: 0: 1763.6, 1: 1746.9. Samples: 38702176. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:18:02,214][61453] Avg episode reward: [(0, '10.560'), (1, '9.970')] -[2023-10-17 03:18:03,942][62373] Updated weights for policy 0, policy_version 75850 (0.0007) -[2023-10-17 03:18:04,000][62408] Updated weights for policy 1, policy_version 75300 (0.0010) -[2023-10-17 03:18:04,312][62373] Updated weights for policy 0, policy_version 75860 (0.0008) -[2023-10-17 03:18:04,371][62408] Updated weights for policy 1, policy_version 75310 (0.0008) -[2023-10-17 03:18:04,681][62373] Updated weights for policy 0, policy_version 75870 (0.0007) -[2023-10-17 03:18:04,741][62408] Updated weights for policy 1, policy_version 75320 (0.0008) -[2023-10-17 03:18:07,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 154828800. Throughput: 0: 1763.9, 1: 1749.7. Samples: 38711704. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:18:07,215][61453] Avg episode reward: [(0, '10.420'), (1, '10.920')] -[2023-10-17 03:18:08,444][62373] Updated weights for policy 0, policy_version 75880 (0.0009) -[2023-10-17 03:18:08,638][62408] Updated weights for policy 1, policy_version 75330 (0.0010) -[2023-10-17 03:18:08,811][62373] Updated weights for policy 0, policy_version 75890 (0.0008) -[2023-10-17 03:18:09,012][62408] Updated weights for policy 1, policy_version 75340 (0.0008) -[2023-10-17 03:18:09,183][62373] Updated weights for policy 0, policy_version 75900 (0.0007) -[2023-10-17 03:18:09,380][62408] Updated weights for policy 1, policy_version 75350 (0.0010) -[2023-10-17 03:18:09,740][62408] Updated weights for policy 1, policy_version 75360 (0.0010) -[2023-10-17 03:18:12,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 154894336. Throughput: 0: 1763.4, 1: 1744.0. Samples: 38733458. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:18:12,215][61453] Avg episode reward: [(0, '10.770'), (1, '10.900')] -[2023-10-17 03:18:12,963][62373] Updated weights for policy 0, policy_version 75910 (0.0007) -[2023-10-17 03:18:13,340][62373] Updated weights for policy 0, policy_version 75920 (0.0009) -[2023-10-17 03:18:13,682][62408] Updated weights for policy 1, policy_version 75370 (0.0007) -[2023-10-17 03:18:13,707][62373] Updated weights for policy 0, policy_version 75930 (0.0007) -[2023-10-17 03:18:14,048][62408] Updated weights for policy 1, policy_version 75380 (0.0011) -[2023-10-17 03:18:14,421][62408] Updated weights for policy 1, policy_version 75390 (0.0009) -[2023-10-17 03:18:17,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 154959872. Throughput: 0: 1780.2, 1: 1762.7. Samples: 38755470. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:18:17,214][61453] Avg episode reward: [(0, '10.900'), (1, '11.170')] -[2023-10-17 03:18:17,656][62373] Updated weights for policy 0, policy_version 75940 (0.0007) -[2023-10-17 03:18:18,021][62373] Updated weights for policy 0, policy_version 75950 (0.0007) -[2023-10-17 03:18:18,187][62408] Updated weights for policy 1, policy_version 75400 (0.0007) -[2023-10-17 03:18:18,389][62373] Updated weights for policy 0, policy_version 75960 (0.0007) -[2023-10-17 03:18:18,555][62408] Updated weights for policy 1, policy_version 75410 (0.0007) -[2023-10-17 03:18:18,926][62408] Updated weights for policy 1, policy_version 75420 (0.0009) -[2023-10-17 03:18:22,196][62373] Updated weights for policy 0, policy_version 75970 (0.0008) -[2023-10-17 03:18:22,214][61453] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 155025408. Throughput: 0: 1767.2, 1: 1737.3. Samples: 38765078. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:18:22,214][61453] Avg episode reward: [(0, '10.160'), (1, '11.310')] -[2023-10-17 03:18:22,562][62373] Updated weights for policy 0, policy_version 75980 (0.0008) -[2023-10-17 03:18:22,709][62408] Updated weights for policy 1, policy_version 75430 (0.0009) -[2023-10-17 03:18:22,932][62373] Updated weights for policy 0, policy_version 75990 (0.0007) -[2023-10-17 03:18:23,079][62408] Updated weights for policy 1, policy_version 75440 (0.0009) -[2023-10-17 03:18:23,290][62373] Updated weights for policy 0, policy_version 76000 (0.0008) -[2023-10-17 03:18:23,444][62408] Updated weights for policy 1, policy_version 75450 (0.0010) -[2023-10-17 03:18:27,116][62373] Updated weights for policy 0, policy_version 76010 (0.0010) -[2023-10-17 03:18:27,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 155090944. Throughput: 0: 1769.8, 1: 1752.3. Samples: 38787004. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:18:27,214][61453] Avg episode reward: [(0, '10.460'), (1, '10.410')] -[2023-10-17 03:18:27,311][62408] Updated weights for policy 1, policy_version 75460 (0.0010) -[2023-10-17 03:18:27,486][62373] Updated weights for policy 0, policy_version 76020 (0.0008) -[2023-10-17 03:18:27,677][62408] Updated weights for policy 1, policy_version 75470 (0.0007) -[2023-10-17 03:18:27,858][62373] Updated weights for policy 0, policy_version 76030 (0.0009) -[2023-10-17 03:18:28,049][62408] Updated weights for policy 1, policy_version 75480 (0.0009) -[2023-10-17 03:18:31,722][62373] Updated weights for policy 0, policy_version 76040 (0.0007) -[2023-10-17 03:18:31,942][62408] Updated weights for policy 1, policy_version 75490 (0.0007) -[2023-10-17 03:18:32,090][62373] Updated weights for policy 0, policy_version 76050 (0.0007) -[2023-10-17 03:18:32,214][61453] Fps is (10 sec: 13106.9, 60 sec: 13653.4, 300 sec: 13995.8). Total num frames: 155156480. Throughput: 0: 1773.6, 1: 1778.8. Samples: 38808326. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:18:32,215][61453] Avg episode reward: [(0, '10.080'), (1, '10.710')] -[2023-10-17 03:18:32,301][62408] Updated weights for policy 1, policy_version 75500 (0.0008) -[2023-10-17 03:18:32,454][62373] Updated weights for policy 0, policy_version 76060 (0.0008) -[2023-10-17 03:18:32,671][62408] Updated weights for policy 1, policy_version 75510 (0.0007) -[2023-10-17 03:18:33,028][62408] Updated weights for policy 1, policy_version 75520 (0.0010) -[2023-10-17 03:18:36,071][62373] Updated weights for policy 0, policy_version 76070 (0.0009) -[2023-10-17 03:18:36,443][62373] Updated weights for policy 0, policy_version 76080 (0.0009) -[2023-10-17 03:18:36,812][62373] Updated weights for policy 0, policy_version 76090 (0.0008) -[2023-10-17 03:18:36,938][62408] Updated weights for policy 1, policy_version 75530 (0.0009) -[2023-10-17 03:18:37,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 155254784. Throughput: 0: 1768.7, 1: 1746.8. Samples: 38818580. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:18:37,215][61453] Avg episode reward: [(0, '10.130'), (1, '10.970')] -[2023-10-17 03:18:37,307][62408] Updated weights for policy 1, policy_version 75540 (0.0010) -[2023-10-17 03:18:37,690][62408] Updated weights for policy 1, policy_version 75550 (0.0010) -[2023-10-17 03:18:40,662][62373] Updated weights for policy 0, policy_version 76100 (0.0009) -[2023-10-17 03:18:41,019][62373] Updated weights for policy 0, policy_version 76110 (0.0009) -[2023-10-17 03:18:41,396][62373] Updated weights for policy 0, policy_version 76120 (0.0009) -[2023-10-17 03:18:41,554][62408] Updated weights for policy 1, policy_version 75560 (0.0008) -[2023-10-17 03:18:41,924][62408] Updated weights for policy 1, policy_version 75570 (0.0009) -[2023-10-17 03:18:42,214][61453] Fps is (10 sec: 16384.4, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 155320320. Throughput: 0: 1780.9, 1: 1773.2. Samples: 38839966. Policy #0 lag: (min: 5.0, avg: 9.1, max: 37.0) -[2023-10-17 03:18:42,214][61453] Avg episode reward: [(0, '9.700'), (1, '10.870')] -[2023-10-17 03:18:42,295][62408] Updated weights for policy 1, policy_version 75580 (0.0010) -[2023-10-17 03:18:45,072][62373] Updated weights for policy 0, policy_version 76130 (0.0008) -[2023-10-17 03:18:45,445][62373] Updated weights for policy 0, policy_version 76140 (0.0008) -[2023-10-17 03:18:45,813][62373] Updated weights for policy 0, policy_version 76150 (0.0007) -[2023-10-17 03:18:46,062][62408] Updated weights for policy 1, policy_version 75590 (0.0008) -[2023-10-17 03:18:46,177][62373] Updated weights for policy 0, policy_version 76160 (0.0007) -[2023-10-17 03:18:46,420][62408] Updated weights for policy 1, policy_version 75600 (0.0009) -[2023-10-17 03:18:46,780][62408] Updated weights for policy 1, policy_version 75610 (0.0009) -[2023-10-17 03:18:47,214][61453] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 155418624. Throughput: 0: 1766.0, 1: 1749.5. Samples: 38860372. Policy #0 lag: (min: 5.0, avg: 9.1, max: 37.0) -[2023-10-17 03:18:47,214][61453] Avg episode reward: [(0, '10.910'), (1, '11.010')] -[2023-10-17 03:18:50,142][62373] Updated weights for policy 0, policy_version 76170 (0.0008) -[2023-10-17 03:18:50,504][62373] Updated weights for policy 0, policy_version 76180 (0.0007) -[2023-10-17 03:18:50,712][62408] Updated weights for policy 1, policy_version 75620 (0.0008) -[2023-10-17 03:18:50,869][62373] Updated weights for policy 0, policy_version 76190 (0.0007) -[2023-10-17 03:18:51,115][62408] Updated weights for policy 1, policy_version 75630 (0.0008) -[2023-10-17 03:18:51,482][62408] Updated weights for policy 1, policy_version 75640 (0.0010) -[2023-10-17 03:18:52,214][61453] Fps is (10 sec: 16383.5, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 155484160. Throughput: 0: 1791.5, 1: 1769.3. Samples: 38871940. Policy #0 lag: (min: 5.0, avg: 9.1, max: 37.0) -[2023-10-17 03:18:52,215][61453] Avg episode reward: [(0, '11.040'), (1, '11.080')] -[2023-10-17 03:18:54,691][62373] Updated weights for policy 0, policy_version 76200 (0.0008) -[2023-10-17 03:18:55,047][62408] Updated weights for policy 1, policy_version 75650 (0.0011) -[2023-10-17 03:18:55,067][62373] Updated weights for policy 0, policy_version 76210 (0.0008) -[2023-10-17 03:18:55,406][62408] Updated weights for policy 1, policy_version 75660 (0.0008) -[2023-10-17 03:18:55,433][62373] Updated weights for policy 0, policy_version 76220 (0.0008) -[2023-10-17 03:18:55,770][62408] Updated weights for policy 1, policy_version 75670 (0.0009) -[2023-10-17 03:18:56,133][62408] Updated weights for policy 1, policy_version 75680 (0.0010) -[2023-10-17 03:18:57,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 155549696. Throughput: 0: 1763.3, 1: 1761.4. Samples: 38892068. Policy #0 lag: (min: 5.0, avg: 9.1, max: 37.0) -[2023-10-17 03:18:57,214][61453] Avg episode reward: [(0, '10.790'), (1, '11.480')] -[2023-10-17 03:18:59,314][62373] Updated weights for policy 0, policy_version 76230 (0.0009) -[2023-10-17 03:18:59,689][62373] Updated weights for policy 0, policy_version 76240 (0.0008) -[2023-10-17 03:18:59,963][62408] Updated weights for policy 1, policy_version 75690 (0.0007) -[2023-10-17 03:19:00,046][62373] Updated weights for policy 0, policy_version 76250 (0.0008) -[2023-10-17 03:19:00,325][62408] Updated weights for policy 1, policy_version 75700 (0.0007) -[2023-10-17 03:19:00,699][62408] Updated weights for policy 1, policy_version 75710 (0.0010) -[2023-10-17 03:19:02,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 155615232. Throughput: 0: 1766.1, 1: 1751.7. Samples: 38913772. Policy #0 lag: (min: 5.0, avg: 9.1, max: 37.0) -[2023-10-17 03:19:02,215][61453] Avg episode reward: [(0, '11.080'), (1, '11.790')] -[2023-10-17 03:19:03,704][62373] Updated weights for policy 0, policy_version 76260 (0.0007) -[2023-10-17 03:19:04,065][62373] Updated weights for policy 0, policy_version 76270 (0.0008) -[2023-10-17 03:19:04,442][62373] Updated weights for policy 0, policy_version 76280 (0.0008) -[2023-10-17 03:19:04,653][62408] Updated weights for policy 1, policy_version 75720 (0.0008) -[2023-10-17 03:19:05,019][62408] Updated weights for policy 1, policy_version 75730 (0.0007) -[2023-10-17 03:19:05,403][62408] Updated weights for policy 1, policy_version 75740 (0.0008) -[2023-10-17 03:19:07,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 155680768. Throughput: 0: 1766.9, 1: 1770.0. Samples: 38924238. Policy #0 lag: (min: 5.0, avg: 9.1, max: 37.0) -[2023-10-17 03:19:07,215][61453] Avg episode reward: [(0, '10.860'), (1, '10.770')] -[2023-10-17 03:19:08,164][62373] Updated weights for policy 0, policy_version 76290 (0.0008) -[2023-10-17 03:19:08,535][62373] Updated weights for policy 0, policy_version 76300 (0.0007) -[2023-10-17 03:19:08,900][62373] Updated weights for policy 0, policy_version 76310 (0.0007) -[2023-10-17 03:19:09,270][62373] Updated weights for policy 0, policy_version 76320 (0.0009) -[2023-10-17 03:19:09,283][62408] Updated weights for policy 1, policy_version 75750 (0.0008) -[2023-10-17 03:19:09,654][62408] Updated weights for policy 1, policy_version 75760 (0.0010) -[2023-10-17 03:19:10,018][62408] Updated weights for policy 1, policy_version 75770 (0.0009) -[2023-10-17 03:19:12,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 155746304. Throughput: 0: 1771.1, 1: 1747.8. Samples: 38945356. Policy #0 lag: (min: 5.0, avg: 9.1, max: 37.0) -[2023-10-17 03:19:12,215][61453] Avg episode reward: [(0, '10.420'), (1, '10.890')] -[2023-10-17 03:19:13,122][62373] Updated weights for policy 0, policy_version 76330 (0.0008) -[2023-10-17 03:19:13,485][62373] Updated weights for policy 0, policy_version 76340 (0.0008) -[2023-10-17 03:19:13,804][62408] Updated weights for policy 1, policy_version 75780 (0.0008) -[2023-10-17 03:19:13,868][62373] Updated weights for policy 0, policy_version 76350 (0.0008) -[2023-10-17 03:19:14,165][62408] Updated weights for policy 1, policy_version 75790 (0.0008) -[2023-10-17 03:19:14,536][62408] Updated weights for policy 1, policy_version 75800 (0.0007) -[2023-10-17 03:19:17,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 155811840. Throughput: 0: 1789.3, 1: 1750.1. Samples: 38967596. Policy #0 lag: (min: 5.0, avg: 9.1, max: 37.0) -[2023-10-17 03:19:17,215][61453] Avg episode reward: [(0, '10.740'), (1, '11.040')] -[2023-10-17 03:19:17,589][62373] Updated weights for policy 0, policy_version 76360 (0.0008) -[2023-10-17 03:19:17,954][62373] Updated weights for policy 0, policy_version 76370 (0.0009) -[2023-10-17 03:19:18,233][62408] Updated weights for policy 1, policy_version 75810 (0.0008) -[2023-10-17 03:19:18,314][62373] Updated weights for policy 0, policy_version 76380 (0.0009) -[2023-10-17 03:19:18,600][62408] Updated weights for policy 1, policy_version 75820 (0.0008) -[2023-10-17 03:19:18,968][62408] Updated weights for policy 1, policy_version 75830 (0.0008) -[2023-10-17 03:19:19,324][62408] Updated weights for policy 1, policy_version 75840 (0.0009) -[2023-10-17 03:19:22,008][62373] Updated weights for policy 0, policy_version 76390 (0.0007) -[2023-10-17 03:19:22,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 155877376. Throughput: 0: 1777.1, 1: 1753.6. Samples: 38977464. Policy #0 lag: (min: 5.0, avg: 9.1, max: 37.0) -[2023-10-17 03:19:22,215][61453] Avg episode reward: [(0, '9.890'), (1, '11.000')] -[2023-10-17 03:19:22,378][62373] Updated weights for policy 0, policy_version 76400 (0.0007) -[2023-10-17 03:19:22,762][62373] Updated weights for policy 0, policy_version 76410 (0.0007) -[2023-10-17 03:19:23,293][62408] Updated weights for policy 1, policy_version 75850 (0.0010) -[2023-10-17 03:19:23,659][62408] Updated weights for policy 1, policy_version 75860 (0.0008) -[2023-10-17 03:19:24,034][62408] Updated weights for policy 1, policy_version 75870 (0.0009) -[2023-10-17 03:19:26,534][62373] Updated weights for policy 0, policy_version 76420 (0.0008) -[2023-10-17 03:19:26,904][62373] Updated weights for policy 0, policy_version 76430 (0.0011) -[2023-10-17 03:19:27,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 155942912. Throughput: 0: 1789.4, 1: 1754.0. Samples: 38999420. Policy #0 lag: (min: 5.0, avg: 9.1, max: 37.0) -[2023-10-17 03:19:27,214][61453] Avg episode reward: [(0, '9.400'), (1, '10.780')] -[2023-10-17 03:19:27,267][62373] Updated weights for policy 0, policy_version 76440 (0.0010) -[2023-10-17 03:19:27,980][62408] Updated weights for policy 1, policy_version 75880 (0.0009) -[2023-10-17 03:19:28,354][62408] Updated weights for policy 1, policy_version 75890 (0.0008) -[2023-10-17 03:19:28,722][62408] Updated weights for policy 1, policy_version 75900 (0.0008) -[2023-10-17 03:19:31,113][62373] Updated weights for policy 0, policy_version 76450 (0.0010) -[2023-10-17 03:19:31,490][62373] Updated weights for policy 0, policy_version 76460 (0.0007) -[2023-10-17 03:19:31,860][62373] Updated weights for policy 0, policy_version 76470 (0.0008) -[2023-10-17 03:19:32,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 156008448. Throughput: 0: 1779.1, 1: 1784.2. Samples: 39020720. Policy #0 lag: (min: 5.0, avg: 9.1, max: 37.0) -[2023-10-17 03:19:32,215][61453] Avg episode reward: [(0, '10.220'), (1, '10.490')] -[2023-10-17 03:19:32,228][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000076480_78315520.pth... -[2023-10-17 03:19:32,231][62373] Updated weights for policy 0, policy_version 76480 (0.0007) -[2023-10-17 03:19:32,259][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000074816_76611584.pth -[2023-10-17 03:19:32,514][62408] Updated weights for policy 1, policy_version 75910 (0.0010) -[2023-10-17 03:19:32,886][62408] Updated weights for policy 1, policy_version 75920 (0.0010) -[2023-10-17 03:19:33,250][62408] Updated weights for policy 1, policy_version 75930 (0.0008) -[2023-10-17 03:19:33,472][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000075936_77758464.pth... -[2023-10-17 03:19:33,501][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000074272_76054528.pth -[2023-10-17 03:19:36,080][62373] Updated weights for policy 0, policy_version 76490 (0.0009) -[2023-10-17 03:19:36,452][62373] Updated weights for policy 0, policy_version 76500 (0.0007) -[2023-10-17 03:19:36,826][62373] Updated weights for policy 0, policy_version 76510 (0.0008) -[2023-10-17 03:19:37,214][61453] Fps is (10 sec: 16383.6, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 156106752. Throughput: 0: 1779.5, 1: 1761.4. Samples: 39031278. Policy #0 lag: (min: 10.0, avg: 12.5, max: 42.0) -[2023-10-17 03:19:37,215][61453] Avg episode reward: [(0, '9.930'), (1, '10.610')] -[2023-10-17 03:19:37,271][62408] Updated weights for policy 1, policy_version 75940 (0.0008) -[2023-10-17 03:19:37,642][62408] Updated weights for policy 1, policy_version 75950 (0.0008) -[2023-10-17 03:19:38,012][62408] Updated weights for policy 1, policy_version 75960 (0.0010) -[2023-10-17 03:19:40,546][62373] Updated weights for policy 0, policy_version 76520 (0.0007) -[2023-10-17 03:19:40,919][62373] Updated weights for policy 0, policy_version 76530 (0.0007) -[2023-10-17 03:19:41,281][62373] Updated weights for policy 0, policy_version 76540 (0.0010) -[2023-10-17 03:19:41,716][62408] Updated weights for policy 1, policy_version 75970 (0.0008) -[2023-10-17 03:19:42,081][62408] Updated weights for policy 1, policy_version 75980 (0.0011) -[2023-10-17 03:19:42,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 156172288. Throughput: 0: 1790.1, 1: 1773.7. Samples: 39052442. Policy #0 lag: (min: 10.0, avg: 12.5, max: 42.0) -[2023-10-17 03:19:42,214][61453] Avg episode reward: [(0, '10.010'), (1, '10.880')] -[2023-10-17 03:19:42,457][62408] Updated weights for policy 1, policy_version 75990 (0.0011) -[2023-10-17 03:19:42,815][62408] Updated weights for policy 1, policy_version 76000 (0.0011) -[2023-10-17 03:19:45,102][62373] Updated weights for policy 0, policy_version 76550 (0.0009) -[2023-10-17 03:19:45,471][62373] Updated weights for policy 0, policy_version 76560 (0.0009) -[2023-10-17 03:19:45,842][62373] Updated weights for policy 0, policy_version 76570 (0.0008) -[2023-10-17 03:19:46,567][62408] Updated weights for policy 1, policy_version 76010 (0.0010) -[2023-10-17 03:19:46,931][62408] Updated weights for policy 1, policy_version 76020 (0.0009) -[2023-10-17 03:19:47,214][61453] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 156237824. Throughput: 0: 1775.9, 1: 1765.4. Samples: 39073130. Policy #0 lag: (min: 10.0, avg: 12.5, max: 42.0) -[2023-10-17 03:19:47,215][61453] Avg episode reward: [(0, '10.190'), (1, '10.880')] -[2023-10-17 03:19:47,301][62408] Updated weights for policy 1, policy_version 76030 (0.0008) -[2023-10-17 03:19:49,657][62373] Updated weights for policy 0, policy_version 76580 (0.0010) -[2023-10-17 03:19:50,026][62373] Updated weights for policy 0, policy_version 76590 (0.0008) -[2023-10-17 03:19:50,406][62373] Updated weights for policy 0, policy_version 76600 (0.0008) -[2023-10-17 03:19:51,236][62408] Updated weights for policy 1, policy_version 76040 (0.0007) -[2023-10-17 03:19:51,603][62408] Updated weights for policy 1, policy_version 76050 (0.0007) -[2023-10-17 03:19:51,965][62408] Updated weights for policy 1, policy_version 76060 (0.0007) -[2023-10-17 03:19:52,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 156336128. Throughput: 0: 1794.3, 1: 1764.3. Samples: 39084376. Policy #0 lag: (min: 10.0, avg: 12.5, max: 42.0) -[2023-10-17 03:19:52,215][61453] Avg episode reward: [(0, '10.040'), (1, '10.930')] -[2023-10-17 03:19:54,089][62373] Updated weights for policy 0, policy_version 76610 (0.0008) -[2023-10-17 03:19:54,462][62373] Updated weights for policy 0, policy_version 76620 (0.0007) -[2023-10-17 03:19:54,836][62373] Updated weights for policy 0, policy_version 76630 (0.0007) -[2023-10-17 03:19:55,203][62373] Updated weights for policy 0, policy_version 76640 (0.0008) -[2023-10-17 03:19:55,802][62408] Updated weights for policy 1, policy_version 76070 (0.0008) -[2023-10-17 03:19:56,178][62408] Updated weights for policy 1, policy_version 76080 (0.0010) -[2023-10-17 03:19:56,555][62408] Updated weights for policy 1, policy_version 76090 (0.0009) -[2023-10-17 03:19:57,214][61453] Fps is (10 sec: 16384.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 156401664. Throughput: 0: 1775.1, 1: 1783.1. Samples: 39105474. Policy #0 lag: (min: 10.0, avg: 12.5, max: 42.0) -[2023-10-17 03:19:57,214][61453] Avg episode reward: [(0, '10.270'), (1, '11.010')] -[2023-10-17 03:19:59,006][62373] Updated weights for policy 0, policy_version 76650 (0.0009) -[2023-10-17 03:19:59,377][62373] Updated weights for policy 0, policy_version 76660 (0.0007) -[2023-10-17 03:19:59,754][62373] Updated weights for policy 0, policy_version 76670 (0.0008) -[2023-10-17 03:20:00,354][62408] Updated weights for policy 1, policy_version 76100 (0.0008) -[2023-10-17 03:20:00,722][62408] Updated weights for policy 1, policy_version 76110 (0.0008) -[2023-10-17 03:20:01,097][62408] Updated weights for policy 1, policy_version 76120 (0.0009) -[2023-10-17 03:20:02,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 156467200. Throughput: 0: 1777.1, 1: 1754.4. Samples: 39126514. Policy #0 lag: (min: 10.0, avg: 12.5, max: 42.0) -[2023-10-17 03:20:02,215][61453] Avg episode reward: [(0, '9.650'), (1, '10.700')] -[2023-10-17 03:20:03,458][62373] Updated weights for policy 0, policy_version 76680 (0.0009) -[2023-10-17 03:20:03,841][62373] Updated weights for policy 0, policy_version 76690 (0.0010) -[2023-10-17 03:20:04,217][62373] Updated weights for policy 0, policy_version 76700 (0.0010) -[2023-10-17 03:20:04,889][62408] Updated weights for policy 1, policy_version 76130 (0.0009) -[2023-10-17 03:20:05,251][62408] Updated weights for policy 1, policy_version 76140 (0.0008) -[2023-10-17 03:20:05,625][62408] Updated weights for policy 1, policy_version 76150 (0.0009) -[2023-10-17 03:20:05,994][62408] Updated weights for policy 1, policy_version 76160 (0.0009) -[2023-10-17 03:20:07,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 156532736. Throughput: 0: 1771.5, 1: 1784.5. Samples: 39137484. Policy #0 lag: (min: 10.0, avg: 12.5, max: 42.0) -[2023-10-17 03:20:07,215][61453] Avg episode reward: [(0, '10.250'), (1, '10.480')] -[2023-10-17 03:20:08,038][62373] Updated weights for policy 0, policy_version 76710 (0.0010) -[2023-10-17 03:20:08,415][62373] Updated weights for policy 0, policy_version 76720 (0.0010) -[2023-10-17 03:20:08,779][62373] Updated weights for policy 0, policy_version 76730 (0.0009) -[2023-10-17 03:20:09,691][62408] Updated weights for policy 1, policy_version 76170 (0.0007) -[2023-10-17 03:20:10,061][62408] Updated weights for policy 1, policy_version 76180 (0.0008) -[2023-10-17 03:20:10,424][62408] Updated weights for policy 1, policy_version 76190 (0.0007) -[2023-10-17 03:20:12,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 156598272. Throughput: 0: 1772.6, 1: 1762.0. Samples: 39158478. Policy #0 lag: (min: 10.0, avg: 12.5, max: 42.0) -[2023-10-17 03:20:12,215][61453] Avg episode reward: [(0, '10.110'), (1, '10.630')] -[2023-10-17 03:20:12,678][62373] Updated weights for policy 0, policy_version 76740 (0.0008) -[2023-10-17 03:20:13,041][62373] Updated weights for policy 0, policy_version 76750 (0.0007) -[2023-10-17 03:20:13,412][62373] Updated weights for policy 0, policy_version 76760 (0.0009) -[2023-10-17 03:20:14,356][62408] Updated weights for policy 1, policy_version 76200 (0.0008) -[2023-10-17 03:20:14,721][62408] Updated weights for policy 1, policy_version 76210 (0.0010) -[2023-10-17 03:20:15,086][62408] Updated weights for policy 1, policy_version 76220 (0.0007) -[2023-10-17 03:20:17,182][62373] Updated weights for policy 0, policy_version 76770 (0.0009) -[2023-10-17 03:20:17,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 156663808. Throughput: 0: 1797.8, 1: 1758.4. Samples: 39180750. Policy #0 lag: (min: 10.0, avg: 12.5, max: 42.0) -[2023-10-17 03:20:17,214][61453] Avg episode reward: [(0, '9.960'), (1, '10.840')] -[2023-10-17 03:20:17,547][62373] Updated weights for policy 0, policy_version 76780 (0.0011) -[2023-10-17 03:20:17,926][62373] Updated weights for policy 0, policy_version 76790 (0.0010) -[2023-10-17 03:20:18,297][62373] Updated weights for policy 0, policy_version 76800 (0.0010) -[2023-10-17 03:20:18,883][62408] Updated weights for policy 1, policy_version 76230 (0.0008) -[2023-10-17 03:20:19,253][62408] Updated weights for policy 1, policy_version 76240 (0.0009) -[2023-10-17 03:20:19,629][62408] Updated weights for policy 1, policy_version 76250 (0.0008) -[2023-10-17 03:20:22,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 156729344. Throughput: 0: 1775.2, 1: 1764.3. Samples: 39190552. Policy #0 lag: (min: 10.0, avg: 12.5, max: 42.0) -[2023-10-17 03:20:22,215][61453] Avg episode reward: [(0, '10.360'), (1, '10.980')] -[2023-10-17 03:20:22,310][62373] Updated weights for policy 0, policy_version 76810 (0.0010) -[2023-10-17 03:20:22,679][62373] Updated weights for policy 0, policy_version 76820 (0.0009) -[2023-10-17 03:20:23,042][62373] Updated weights for policy 0, policy_version 76830 (0.0008) -[2023-10-17 03:20:23,356][62408] Updated weights for policy 1, policy_version 76260 (0.0010) -[2023-10-17 03:20:23,729][62408] Updated weights for policy 1, policy_version 76270 (0.0009) -[2023-10-17 03:20:24,103][62408] Updated weights for policy 1, policy_version 76280 (0.0009) -[2023-10-17 03:20:26,744][62373] Updated weights for policy 0, policy_version 76840 (0.0007) -[2023-10-17 03:20:27,122][62373] Updated weights for policy 0, policy_version 76850 (0.0008) -[2023-10-17 03:20:27,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 156794880. Throughput: 0: 1786.8, 1: 1764.0. Samples: 39212228. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:20:27,215][61453] Avg episode reward: [(0, '10.110'), (1, '10.220')] -[2023-10-17 03:20:27,484][62373] Updated weights for policy 0, policy_version 76860 (0.0009) -[2023-10-17 03:20:27,863][62408] Updated weights for policy 1, policy_version 76290 (0.0009) -[2023-10-17 03:20:28,231][62408] Updated weights for policy 1, policy_version 76300 (0.0009) -[2023-10-17 03:20:28,607][62408] Updated weights for policy 1, policy_version 76310 (0.0009) -[2023-10-17 03:20:28,969][62408] Updated weights for policy 1, policy_version 76320 (0.0009) -[2023-10-17 03:20:31,217][62373] Updated weights for policy 0, policy_version 76870 (0.0010) -[2023-10-17 03:20:31,593][62373] Updated weights for policy 0, policy_version 76880 (0.0011) -[2023-10-17 03:20:31,957][62373] Updated weights for policy 0, policy_version 76890 (0.0007) -[2023-10-17 03:20:32,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14106.9). Total num frames: 156893184. Throughput: 0: 1778.7, 1: 1784.1. Samples: 39233456. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:20:32,215][61453] Avg episode reward: [(0, '10.140'), (1, '10.510')] -[2023-10-17 03:20:32,777][62408] Updated weights for policy 1, policy_version 76330 (0.0010) -[2023-10-17 03:20:33,146][62408] Updated weights for policy 1, policy_version 76340 (0.0009) -[2023-10-17 03:20:33,510][62408] Updated weights for policy 1, policy_version 76350 (0.0008) -[2023-10-17 03:20:35,910][62373] Updated weights for policy 0, policy_version 76900 (0.0009) -[2023-10-17 03:20:36,276][62373] Updated weights for policy 0, policy_version 76910 (0.0008) -[2023-10-17 03:20:36,644][62373] Updated weights for policy 0, policy_version 76920 (0.0007) -[2023-10-17 03:20:37,214][61453] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 156958720. Throughput: 0: 1781.2, 1: 1765.5. Samples: 39243980. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:20:37,215][61453] Avg episode reward: [(0, '10.130'), (1, '10.660')] -[2023-10-17 03:20:37,351][62408] Updated weights for policy 1, policy_version 76360 (0.0012) -[2023-10-17 03:20:37,717][62408] Updated weights for policy 1, policy_version 76370 (0.0008) -[2023-10-17 03:20:38,088][62408] Updated weights for policy 1, policy_version 76380 (0.0007) -[2023-10-17 03:20:40,534][62373] Updated weights for policy 0, policy_version 76930 (0.0009) -[2023-10-17 03:20:40,896][62373] Updated weights for policy 0, policy_version 76940 (0.0010) -[2023-10-17 03:20:41,263][62373] Updated weights for policy 0, policy_version 76950 (0.0007) -[2023-10-17 03:20:41,631][62373] Updated weights for policy 0, policy_version 76960 (0.0008) -[2023-10-17 03:20:41,717][62408] Updated weights for policy 1, policy_version 76390 (0.0008) -[2023-10-17 03:20:42,089][62408] Updated weights for policy 1, policy_version 76400 (0.0010) -[2023-10-17 03:20:42,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 157024256. Throughput: 0: 1783.4, 1: 1771.5. Samples: 39265444. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:20:42,214][61453] Avg episode reward: [(0, '10.080'), (1, '10.410')] -[2023-10-17 03:20:42,450][62408] Updated weights for policy 1, policy_version 76410 (0.0007) -[2023-10-17 03:20:45,376][62373] Updated weights for policy 0, policy_version 76970 (0.0009) -[2023-10-17 03:20:45,749][62373] Updated weights for policy 0, policy_version 76980 (0.0008) -[2023-10-17 03:20:46,113][62373] Updated weights for policy 0, policy_version 76990 (0.0008) -[2023-10-17 03:20:46,265][62408] Updated weights for policy 1, policy_version 76420 (0.0008) -[2023-10-17 03:20:46,635][62408] Updated weights for policy 1, policy_version 76430 (0.0008) -[2023-10-17 03:20:47,003][62408] Updated weights for policy 1, policy_version 76440 (0.0008) -[2023-10-17 03:20:47,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 157089792. Throughput: 0: 1764.5, 1: 1779.2. Samples: 39285978. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:20:47,215][61453] Avg episode reward: [(0, '10.360'), (1, '10.810')] -[2023-10-17 03:20:49,945][62373] Updated weights for policy 0, policy_version 77000 (0.0008) -[2023-10-17 03:20:50,313][62373] Updated weights for policy 0, policy_version 77010 (0.0007) -[2023-10-17 03:20:50,687][62373] Updated weights for policy 0, policy_version 77020 (0.0011) -[2023-10-17 03:20:50,889][62408] Updated weights for policy 1, policy_version 76450 (0.0007) -[2023-10-17 03:20:51,257][62408] Updated weights for policy 1, policy_version 76460 (0.0008) -[2023-10-17 03:20:51,614][62408] Updated weights for policy 1, policy_version 76470 (0.0009) -[2023-10-17 03:20:51,985][62408] Updated weights for policy 1, policy_version 76480 (0.0010) -[2023-10-17 03:20:52,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 157188096. Throughput: 0: 1787.0, 1: 1766.7. Samples: 39297400. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:20:52,215][61453] Avg episode reward: [(0, '10.830'), (1, '10.480')] -[2023-10-17 03:20:54,452][62373] Updated weights for policy 0, policy_version 77030 (0.0008) -[2023-10-17 03:20:54,819][62373] Updated weights for policy 0, policy_version 77040 (0.0008) -[2023-10-17 03:20:55,189][62373] Updated weights for policy 0, policy_version 77050 (0.0009) -[2023-10-17 03:20:55,853][62408] Updated weights for policy 1, policy_version 76490 (0.0007) -[2023-10-17 03:20:56,215][62408] Updated weights for policy 1, policy_version 76500 (0.0010) -[2023-10-17 03:20:56,595][62408] Updated weights for policy 1, policy_version 76510 (0.0012) -[2023-10-17 03:20:57,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 157253632. Throughput: 0: 1758.5, 1: 1783.7. Samples: 39317876. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:20:57,215][61453] Avg episode reward: [(0, '10.320'), (1, '10.860')] -[2023-10-17 03:20:59,005][62373] Updated weights for policy 0, policy_version 77060 (0.0009) -[2023-10-17 03:20:59,378][62373] Updated weights for policy 0, policy_version 77070 (0.0009) -[2023-10-17 03:20:59,741][62373] Updated weights for policy 0, policy_version 77080 (0.0011) -[2023-10-17 03:21:00,420][62408] Updated weights for policy 1, policy_version 76520 (0.0008) -[2023-10-17 03:21:00,793][62408] Updated weights for policy 1, policy_version 76530 (0.0009) -[2023-10-17 03:21:01,146][62408] Updated weights for policy 1, policy_version 76540 (0.0007) -[2023-10-17 03:21:02,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 157319168. Throughput: 0: 1764.0, 1: 1755.6. Samples: 39339132. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:21:02,214][61453] Avg episode reward: [(0, '10.390'), (1, '10.880')] -[2023-10-17 03:21:03,538][62373] Updated weights for policy 0, policy_version 77090 (0.0010) -[2023-10-17 03:21:03,906][62373] Updated weights for policy 0, policy_version 77100 (0.0009) -[2023-10-17 03:21:04,285][62373] Updated weights for policy 0, policy_version 77110 (0.0011) -[2023-10-17 03:21:04,666][62373] Updated weights for policy 0, policy_version 77120 (0.0008) -[2023-10-17 03:21:04,964][62408] Updated weights for policy 1, policy_version 76550 (0.0011) -[2023-10-17 03:21:05,334][62408] Updated weights for policy 1, policy_version 76560 (0.0009) -[2023-10-17 03:21:05,700][62408] Updated weights for policy 1, policy_version 76570 (0.0010) -[2023-10-17 03:21:07,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 157384704. Throughput: 0: 1764.5, 1: 1779.4. Samples: 39350028. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:21:07,215][61453] Avg episode reward: [(0, '9.930'), (1, '10.550')] -[2023-10-17 03:21:08,436][62373] Updated weights for policy 0, policy_version 77130 (0.0007) -[2023-10-17 03:21:08,807][62373] Updated weights for policy 0, policy_version 77140 (0.0007) -[2023-10-17 03:21:09,175][62373] Updated weights for policy 0, policy_version 77150 (0.0008) -[2023-10-17 03:21:09,354][62408] Updated weights for policy 1, policy_version 76580 (0.0008) -[2023-10-17 03:21:09,724][62408] Updated weights for policy 1, policy_version 76590 (0.0008) -[2023-10-17 03:21:10,089][62408] Updated weights for policy 1, policy_version 76600 (0.0008) -[2023-10-17 03:21:12,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 157450240. Throughput: 0: 1775.6, 1: 1760.7. Samples: 39371362. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:21:12,215][61453] Avg episode reward: [(0, '9.660'), (1, '11.250')] -[2023-10-17 03:21:12,784][62373] Updated weights for policy 0, policy_version 77160 (0.0008) -[2023-10-17 03:21:13,148][62373] Updated weights for policy 0, policy_version 77170 (0.0010) -[2023-10-17 03:21:13,527][62373] Updated weights for policy 0, policy_version 77180 (0.0008) -[2023-10-17 03:21:13,907][62408] Updated weights for policy 1, policy_version 76610 (0.0008) -[2023-10-17 03:21:14,299][62408] Updated weights for policy 1, policy_version 76620 (0.0010) -[2023-10-17 03:21:14,664][62408] Updated weights for policy 1, policy_version 76630 (0.0008) -[2023-10-17 03:21:15,036][62408] Updated weights for policy 1, policy_version 76640 (0.0008) -[2023-10-17 03:21:17,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 157515776. Throughput: 0: 1798.0, 1: 1761.6. Samples: 39393642. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-17 03:21:17,215][61453] Avg episode reward: [(0, '9.430'), (1, '11.240')] -[2023-10-17 03:21:17,243][62373] Updated weights for policy 0, policy_version 77190 (0.0009) -[2023-10-17 03:21:17,603][62373] Updated weights for policy 0, policy_version 77200 (0.0009) -[2023-10-17 03:21:17,969][62373] Updated weights for policy 0, policy_version 77210 (0.0008) -[2023-10-17 03:21:18,820][62408] Updated weights for policy 1, policy_version 76650 (0.0007) -[2023-10-17 03:21:19,178][62408] Updated weights for policy 1, policy_version 76660 (0.0010) -[2023-10-17 03:21:19,555][62408] Updated weights for policy 1, policy_version 76670 (0.0008) -[2023-10-17 03:21:21,635][62373] Updated weights for policy 0, policy_version 77220 (0.0007) -[2023-10-17 03:21:22,006][62373] Updated weights for policy 0, policy_version 77230 (0.0010) -[2023-10-17 03:21:22,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 157581312. Throughput: 0: 1777.4, 1: 1766.0. Samples: 39403432. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-17 03:21:22,214][61453] Avg episode reward: [(0, '9.060'), (1, '11.140')] -[2023-10-17 03:21:22,372][62373] Updated weights for policy 0, policy_version 77240 (0.0008) -[2023-10-17 03:21:23,403][62408] Updated weights for policy 1, policy_version 76680 (0.0009) -[2023-10-17 03:21:23,771][62408] Updated weights for policy 1, policy_version 76690 (0.0011) -[2023-10-17 03:21:24,140][62408] Updated weights for policy 1, policy_version 76700 (0.0011) -[2023-10-17 03:21:26,384][62373] Updated weights for policy 0, policy_version 77250 (0.0009) -[2023-10-17 03:21:26,750][62373] Updated weights for policy 0, policy_version 77260 (0.0009) -[2023-10-17 03:21:27,125][62373] Updated weights for policy 0, policy_version 77270 (0.0009) -[2023-10-17 03:21:27,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 157646848. Throughput: 0: 1791.7, 1: 1767.1. Samples: 39425590. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-17 03:21:27,215][61453] Avg episode reward: [(0, '8.990'), (1, '10.950')] -[2023-10-17 03:21:27,497][62373] Updated weights for policy 0, policy_version 77280 (0.0007) -[2023-10-17 03:21:27,860][62408] Updated weights for policy 1, policy_version 76710 (0.0008) -[2023-10-17 03:21:28,225][62408] Updated weights for policy 1, policy_version 76720 (0.0007) -[2023-10-17 03:21:28,599][62408] Updated weights for policy 1, policy_version 76730 (0.0009) -[2023-10-17 03:21:31,077][62373] Updated weights for policy 0, policy_version 77290 (0.0009) -[2023-10-17 03:21:31,448][62373] Updated weights for policy 0, policy_version 77300 (0.0008) -[2023-10-17 03:21:31,828][62373] Updated weights for policy 0, policy_version 77310 (0.0010) -[2023-10-17 03:21:32,214][61453] Fps is (10 sec: 16383.5, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 157745152. Throughput: 0: 1775.9, 1: 1787.9. Samples: 39446350. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-17 03:21:32,215][61453] Avg episode reward: [(0, '9.520'), (1, '10.290')] -[2023-10-17 03:21:32,226][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000076736_78577664.pth... -[2023-10-17 03:21:32,226][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000077312_79167488.pth... -[2023-10-17 03:21:32,264][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000075648_77463552.pth -[2023-10-17 03:21:32,268][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000075104_76906496.pth -[2023-10-17 03:21:32,563][62408] Updated weights for policy 1, policy_version 76740 (0.0008) -[2023-10-17 03:21:32,926][62408] Updated weights for policy 1, policy_version 76750 (0.0008) -[2023-10-17 03:21:33,300][62408] Updated weights for policy 1, policy_version 76760 (0.0009) -[2023-10-17 03:21:35,670][62373] Updated weights for policy 0, policy_version 77320 (0.0011) -[2023-10-17 03:21:36,041][62373] Updated weights for policy 0, policy_version 77330 (0.0008) -[2023-10-17 03:21:36,398][62373] Updated weights for policy 0, policy_version 77340 (0.0009) -[2023-10-17 03:21:37,150][62408] Updated weights for policy 1, policy_version 76770 (0.0008) -[2023-10-17 03:21:37,214][61453] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 157810688. Throughput: 0: 1789.5, 1: 1768.2. Samples: 39457496. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-17 03:21:37,214][61453] Avg episode reward: [(0, '9.390'), (1, '10.980')] -[2023-10-17 03:21:37,517][62408] Updated weights for policy 1, policy_version 76780 (0.0009) -[2023-10-17 03:21:37,871][62408] Updated weights for policy 1, policy_version 76790 (0.0009) -[2023-10-17 03:21:38,235][62408] Updated weights for policy 1, policy_version 76800 (0.0007) -[2023-10-17 03:21:40,044][62373] Updated weights for policy 0, policy_version 77350 (0.0008) -[2023-10-17 03:21:40,417][62373] Updated weights for policy 0, policy_version 77360 (0.0008) -[2023-10-17 03:21:40,786][62373] Updated weights for policy 0, policy_version 77370 (0.0007) -[2023-10-17 03:21:42,155][62408] Updated weights for policy 1, policy_version 76810 (0.0007) -[2023-10-17 03:21:42,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 157876224. Throughput: 0: 1793.1, 1: 1775.8. Samples: 39478476. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-17 03:21:42,215][61453] Avg episode reward: [(0, '9.430'), (1, '11.260')] -[2023-10-17 03:21:42,519][62408] Updated weights for policy 1, policy_version 76820 (0.0007) -[2023-10-17 03:21:42,893][62408] Updated weights for policy 1, policy_version 76830 (0.0007) -[2023-10-17 03:21:44,501][62373] Updated weights for policy 0, policy_version 77380 (0.0009) -[2023-10-17 03:21:44,867][62373] Updated weights for policy 0, policy_version 77390 (0.0009) -[2023-10-17 03:21:45,243][62373] Updated weights for policy 0, policy_version 77400 (0.0007) -[2023-10-17 03:21:46,758][62408] Updated weights for policy 1, policy_version 76840 (0.0007) -[2023-10-17 03:21:47,123][62408] Updated weights for policy 1, policy_version 76850 (0.0007) -[2023-10-17 03:21:47,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 157941760. Throughput: 0: 1785.3, 1: 1790.0. Samples: 39500022. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-17 03:21:47,215][61453] Avg episode reward: [(0, '9.260'), (1, '10.030')] -[2023-10-17 03:21:47,502][62408] Updated weights for policy 1, policy_version 76860 (0.0007) -[2023-10-17 03:21:49,034][62373] Updated weights for policy 0, policy_version 77410 (0.0007) -[2023-10-17 03:21:49,403][62373] Updated weights for policy 0, policy_version 77420 (0.0008) -[2023-10-17 03:21:49,770][62373] Updated weights for policy 0, policy_version 77430 (0.0009) -[2023-10-17 03:21:50,146][62373] Updated weights for policy 0, policy_version 77440 (0.0009) -[2023-10-17 03:21:51,378][62408] Updated weights for policy 1, policy_version 76870 (0.0009) -[2023-10-17 03:21:51,755][62408] Updated weights for policy 1, policy_version 76880 (0.0011) -[2023-10-17 03:21:52,124][62408] Updated weights for policy 1, policy_version 76890 (0.0009) -[2023-10-17 03:21:52,214][61453] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 158007296. Throughput: 0: 1792.1, 1: 1772.1. Samples: 39510416. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-17 03:21:52,215][61453] Avg episode reward: [(0, '10.090'), (1, '10.290')] -[2023-10-17 03:21:53,891][62373] Updated weights for policy 0, policy_version 77450 (0.0009) -[2023-10-17 03:21:54,256][62373] Updated weights for policy 0, policy_version 77460 (0.0007) -[2023-10-17 03:21:54,625][62373] Updated weights for policy 0, policy_version 77470 (0.0007) -[2023-10-17 03:21:55,750][62408] Updated weights for policy 1, policy_version 76900 (0.0007) -[2023-10-17 03:21:56,122][62408] Updated weights for policy 1, policy_version 76910 (0.0009) -[2023-10-17 03:21:56,483][62408] Updated weights for policy 1, policy_version 76920 (0.0008) -[2023-10-17 03:21:57,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 158105600. Throughput: 0: 1779.4, 1: 1794.4. Samples: 39532182. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-17 03:21:57,215][61453] Avg episode reward: [(0, '9.680'), (1, '10.440')] -[2023-10-17 03:21:58,601][62373] Updated weights for policy 0, policy_version 77480 (0.0010) -[2023-10-17 03:21:58,973][62373] Updated weights for policy 0, policy_version 77490 (0.0008) -[2023-10-17 03:21:59,344][62373] Updated weights for policy 0, policy_version 77500 (0.0007) -[2023-10-17 03:22:00,334][62408] Updated weights for policy 1, policy_version 76930 (0.0007) -[2023-10-17 03:22:00,754][62408] Updated weights for policy 1, policy_version 76940 (0.0009) -[2023-10-17 03:22:01,130][62408] Updated weights for policy 1, policy_version 76950 (0.0008) -[2023-10-17 03:22:01,499][62408] Updated weights for policy 1, policy_version 76960 (0.0008) -[2023-10-17 03:22:02,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 158171136. Throughput: 0: 1778.0, 1: 1759.3. Samples: 39552820. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-10-17 03:22:02,215][61453] Avg episode reward: [(0, '9.980'), (1, '10.340')] -[2023-10-17 03:22:03,138][62373] Updated weights for policy 0, policy_version 77510 (0.0009) -[2023-10-17 03:22:03,505][62373] Updated weights for policy 0, policy_version 77520 (0.0007) -[2023-10-17 03:22:03,878][62373] Updated weights for policy 0, policy_version 77530 (0.0007) -[2023-10-17 03:22:05,340][62408] Updated weights for policy 1, policy_version 76970 (0.0008) -[2023-10-17 03:22:05,700][62408] Updated weights for policy 1, policy_version 76980 (0.0007) -[2023-10-17 03:22:06,072][62408] Updated weights for policy 1, policy_version 76990 (0.0009) -[2023-10-17 03:22:07,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 158236672. Throughput: 0: 1777.1, 1: 1790.0. Samples: 39563952. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:22:07,215][61453] Avg episode reward: [(0, '10.340'), (1, '10.760')] -[2023-10-17 03:22:07,646][62373] Updated weights for policy 0, policy_version 77540 (0.0010) -[2023-10-17 03:22:08,012][62373] Updated weights for policy 0, policy_version 77550 (0.0007) -[2023-10-17 03:22:08,379][62373] Updated weights for policy 0, policy_version 77560 (0.0007) -[2023-10-17 03:22:09,679][62408] Updated weights for policy 1, policy_version 77000 (0.0008) -[2023-10-17 03:22:10,046][62408] Updated weights for policy 1, policy_version 77010 (0.0007) -[2023-10-17 03:22:10,416][62408] Updated weights for policy 1, policy_version 77020 (0.0009) -[2023-10-17 03:22:12,193][62373] Updated weights for policy 0, policy_version 77570 (0.0008) -[2023-10-17 03:22:12,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 158302208. Throughput: 0: 1783.0, 1: 1760.2. Samples: 39585032. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:22:12,215][61453] Avg episode reward: [(0, '10.590'), (1, '11.410')] -[2023-10-17 03:22:12,564][62373] Updated weights for policy 0, policy_version 77580 (0.0008) -[2023-10-17 03:22:12,930][62373] Updated weights for policy 0, policy_version 77590 (0.0008) -[2023-10-17 03:22:13,304][62373] Updated weights for policy 0, policy_version 77600 (0.0008) -[2023-10-17 03:22:14,198][62408] Updated weights for policy 1, policy_version 77030 (0.0007) -[2023-10-17 03:22:14,561][62408] Updated weights for policy 1, policy_version 77040 (0.0007) -[2023-10-17 03:22:14,920][62408] Updated weights for policy 1, policy_version 77050 (0.0009) -[2023-10-17 03:22:16,950][62373] Updated weights for policy 0, policy_version 77610 (0.0009) -[2023-10-17 03:22:17,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 158367744. Throughput: 0: 1809.5, 1: 1765.9. Samples: 39607242. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:22:17,214][61453] Avg episode reward: [(0, '10.540'), (1, '11.690')] -[2023-10-17 03:22:17,320][62373] Updated weights for policy 0, policy_version 77620 (0.0008) -[2023-10-17 03:22:17,686][62373] Updated weights for policy 0, policy_version 77630 (0.0007) -[2023-10-17 03:22:18,744][62408] Updated weights for policy 1, policy_version 77060 (0.0010) -[2023-10-17 03:22:19,117][62408] Updated weights for policy 1, policy_version 77070 (0.0009) -[2023-10-17 03:22:19,490][62408] Updated weights for policy 1, policy_version 77080 (0.0008) -[2023-10-17 03:22:21,455][62373] Updated weights for policy 0, policy_version 77640 (0.0008) -[2023-10-17 03:22:21,827][62373] Updated weights for policy 0, policy_version 77650 (0.0007) -[2023-10-17 03:22:22,200][62373] Updated weights for policy 0, policy_version 77660 (0.0007) -[2023-10-17 03:22:22,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 158433280. Throughput: 0: 1787.5, 1: 1765.9. Samples: 39617398. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:22:22,214][61453] Avg episode reward: [(0, '10.650'), (1, '11.580')] -[2023-10-17 03:22:23,270][62408] Updated weights for policy 1, policy_version 77090 (0.0009) -[2023-10-17 03:22:23,636][62408] Updated weights for policy 1, policy_version 77100 (0.0010) -[2023-10-17 03:22:24,006][62408] Updated weights for policy 1, policy_version 77110 (0.0010) -[2023-10-17 03:22:24,374][62408] Updated weights for policy 1, policy_version 77120 (0.0009) -[2023-10-17 03:22:25,863][62373] Updated weights for policy 0, policy_version 77670 (0.0007) -[2023-10-17 03:22:26,232][62373] Updated weights for policy 0, policy_version 77680 (0.0008) -[2023-10-17 03:22:26,606][62373] Updated weights for policy 0, policy_version 77690 (0.0009) -[2023-10-17 03:22:27,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14218.0). Total num frames: 158531584. Throughput: 0: 1808.3, 1: 1765.0. Samples: 39639274. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:22:27,215][61453] Avg episode reward: [(0, '10.450'), (1, '12.140')] -[2023-10-17 03:22:28,186][62408] Updated weights for policy 1, policy_version 77130 (0.0009) -[2023-10-17 03:22:28,549][62408] Updated weights for policy 1, policy_version 77140 (0.0008) -[2023-10-17 03:22:28,924][62408] Updated weights for policy 1, policy_version 77150 (0.0007) -[2023-10-17 03:22:30,553][62373] Updated weights for policy 0, policy_version 77700 (0.0011) -[2023-10-17 03:22:30,918][62373] Updated weights for policy 0, policy_version 77710 (0.0009) -[2023-10-17 03:22:31,289][62373] Updated weights for policy 0, policy_version 77720 (0.0011) -[2023-10-17 03:22:32,214][61453] Fps is (10 sec: 16383.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 158597120. Throughput: 0: 1779.8, 1: 1784.4. Samples: 39660412. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:22:32,215][61453] Avg episode reward: [(0, '10.800'), (1, '11.760')] -[2023-10-17 03:22:32,597][62408] Updated weights for policy 1, policy_version 77160 (0.0009) -[2023-10-17 03:22:32,966][62408] Updated weights for policy 1, policy_version 77170 (0.0009) -[2023-10-17 03:22:33,333][62408] Updated weights for policy 1, policy_version 77180 (0.0008) -[2023-10-17 03:22:35,075][62373] Updated weights for policy 0, policy_version 77730 (0.0011) -[2023-10-17 03:22:35,447][62373] Updated weights for policy 0, policy_version 77740 (0.0010) -[2023-10-17 03:22:35,816][62373] Updated weights for policy 0, policy_version 77750 (0.0008) -[2023-10-17 03:22:36,189][62373] Updated weights for policy 0, policy_version 77760 (0.0008) -[2023-10-17 03:22:37,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 158662656. Throughput: 0: 1806.2, 1: 1774.6. Samples: 39671552. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:22:37,214][61453] Avg episode reward: [(0, '10.930'), (1, '11.920')] -[2023-10-17 03:22:37,216][62408] Updated weights for policy 1, policy_version 77190 (0.0008) -[2023-10-17 03:22:37,583][62408] Updated weights for policy 1, policy_version 77200 (0.0007) -[2023-10-17 03:22:37,955][62408] Updated weights for policy 1, policy_version 77210 (0.0007) -[2023-10-17 03:22:39,880][62373] Updated weights for policy 0, policy_version 77770 (0.0008) -[2023-10-17 03:22:40,246][62373] Updated weights for policy 0, policy_version 77780 (0.0007) -[2023-10-17 03:22:40,613][62373] Updated weights for policy 0, policy_version 77790 (0.0007) -[2023-10-17 03:22:41,752][62408] Updated weights for policy 1, policy_version 77220 (0.0010) -[2023-10-17 03:22:42,128][62408] Updated weights for policy 1, policy_version 77230 (0.0010) -[2023-10-17 03:22:42,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 158728192. Throughput: 0: 1782.4, 1: 1776.8. Samples: 39692346. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:22:42,215][61453] Avg episode reward: [(0, '10.840'), (1, '11.510')] -[2023-10-17 03:22:42,490][62408] Updated weights for policy 1, policy_version 77240 (0.0008) -[2023-10-17 03:22:44,491][62373] Updated weights for policy 0, policy_version 77800 (0.0008) -[2023-10-17 03:22:44,861][62373] Updated weights for policy 0, policy_version 77810 (0.0009) -[2023-10-17 03:22:45,234][62373] Updated weights for policy 0, policy_version 77820 (0.0009) -[2023-10-17 03:22:46,440][62408] Updated weights for policy 1, policy_version 77250 (0.0007) -[2023-10-17 03:22:46,863][62408] Updated weights for policy 1, policy_version 77260 (0.0008) -[2023-10-17 03:22:47,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 158793728. Throughput: 0: 1779.5, 1: 1790.1. Samples: 39713452. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:22:47,214][61453] Avg episode reward: [(0, '10.570'), (1, '10.800')] -[2023-10-17 03:22:47,230][62408] Updated weights for policy 1, policy_version 77270 (0.0007) -[2023-10-17 03:22:47,594][62408] Updated weights for policy 1, policy_version 77280 (0.0007) -[2023-10-17 03:22:49,060][62373] Updated weights for policy 0, policy_version 77830 (0.0011) -[2023-10-17 03:22:49,430][62373] Updated weights for policy 0, policy_version 77840 (0.0011) -[2023-10-17 03:22:49,795][62373] Updated weights for policy 0, policy_version 77850 (0.0007) -[2023-10-17 03:22:51,360][62408] Updated weights for policy 1, policy_version 77290 (0.0009) -[2023-10-17 03:22:51,719][62408] Updated weights for policy 1, policy_version 77300 (0.0008) -[2023-10-17 03:22:52,090][62408] Updated weights for policy 1, policy_version 77310 (0.0008) -[2023-10-17 03:22:52,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14218.0). Total num frames: 158892032. Throughput: 0: 1780.9, 1: 1770.7. Samples: 39723774. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:22:52,214][61453] Avg episode reward: [(0, '10.400'), (1, '10.820')] -[2023-10-17 03:22:53,457][62373] Updated weights for policy 0, policy_version 77860 (0.0008) -[2023-10-17 03:22:53,825][62373] Updated weights for policy 0, policy_version 77870 (0.0008) -[2023-10-17 03:22:54,196][62373] Updated weights for policy 0, policy_version 77880 (0.0009) -[2023-10-17 03:22:55,980][62408] Updated weights for policy 1, policy_version 77320 (0.0008) -[2023-10-17 03:22:56,345][62408] Updated weights for policy 1, policy_version 77330 (0.0010) -[2023-10-17 03:22:56,715][62408] Updated weights for policy 1, policy_version 77340 (0.0009) -[2023-10-17 03:22:57,214][61453] Fps is (10 sec: 16383.5, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 158957568. Throughput: 0: 1780.1, 1: 1789.2. Samples: 39745650. Policy #0 lag: (min: 9.0, avg: 24.9, max: 41.0) -[2023-10-17 03:22:57,215][61453] Avg episode reward: [(0, '10.740'), (1, '10.630')] -[2023-10-17 03:22:57,924][62373] Updated weights for policy 0, policy_version 77890 (0.0008) -[2023-10-17 03:22:58,296][62373] Updated weights for policy 0, policy_version 77900 (0.0008) -[2023-10-17 03:22:58,673][62373] Updated weights for policy 0, policy_version 77910 (0.0011) -[2023-10-17 03:22:59,037][62373] Updated weights for policy 0, policy_version 77920 (0.0010) -[2023-10-17 03:23:00,652][62408] Updated weights for policy 1, policy_version 77350 (0.0009) -[2023-10-17 03:23:01,017][62408] Updated weights for policy 1, policy_version 77360 (0.0008) -[2023-10-17 03:23:01,390][62408] Updated weights for policy 1, policy_version 77370 (0.0007) -[2023-10-17 03:23:02,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 159023104. Throughput: 0: 1784.8, 1: 1755.4. Samples: 39766554. Policy #0 lag: (min: 9.0, avg: 24.9, max: 41.0) -[2023-10-17 03:23:02,215][61453] Avg episode reward: [(0, '11.200'), (1, '11.100')] -[2023-10-17 03:23:02,870][62373] Updated weights for policy 0, policy_version 77930 (0.0008) -[2023-10-17 03:23:03,247][62373] Updated weights for policy 0, policy_version 77940 (0.0008) -[2023-10-17 03:23:03,618][62373] Updated weights for policy 0, policy_version 77950 (0.0007) -[2023-10-17 03:23:05,125][62408] Updated weights for policy 1, policy_version 77380 (0.0008) -[2023-10-17 03:23:05,489][62408] Updated weights for policy 1, policy_version 77390 (0.0008) -[2023-10-17 03:23:05,864][62408] Updated weights for policy 1, policy_version 77400 (0.0009) -[2023-10-17 03:23:07,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 159088640. Throughput: 0: 1770.7, 1: 1792.7. Samples: 39777750. Policy #0 lag: (min: 9.0, avg: 24.9, max: 41.0) -[2023-10-17 03:23:07,215][61453] Avg episode reward: [(0, '10.870'), (1, '11.240')] -[2023-10-17 03:23:07,410][62373] Updated weights for policy 0, policy_version 77960 (0.0010) -[2023-10-17 03:23:07,789][62373] Updated weights for policy 0, policy_version 77970 (0.0010) -[2023-10-17 03:23:08,156][62373] Updated weights for policy 0, policy_version 77980 (0.0012) -[2023-10-17 03:23:09,678][62408] Updated weights for policy 1, policy_version 77410 (0.0010) -[2023-10-17 03:23:10,049][62408] Updated weights for policy 1, policy_version 77420 (0.0009) -[2023-10-17 03:23:10,406][62408] Updated weights for policy 1, policy_version 77430 (0.0009) -[2023-10-17 03:23:10,777][62408] Updated weights for policy 1, policy_version 77440 (0.0010) -[2023-10-17 03:23:12,017][62373] Updated weights for policy 0, policy_version 77990 (0.0010) -[2023-10-17 03:23:12,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 159154176. Throughput: 0: 1775.9, 1: 1760.0. Samples: 39798390. Policy #0 lag: (min: 9.0, avg: 24.9, max: 41.0) -[2023-10-17 03:23:12,215][61453] Avg episode reward: [(0, '10.690'), (1, '10.930')] -[2023-10-17 03:23:12,392][62373] Updated weights for policy 0, policy_version 78000 (0.0010) -[2023-10-17 03:23:12,758][62373] Updated weights for policy 0, policy_version 78010 (0.0008) -[2023-10-17 03:23:14,557][62408] Updated weights for policy 1, policy_version 77450 (0.0007) -[2023-10-17 03:23:14,931][62408] Updated weights for policy 1, policy_version 77460 (0.0007) -[2023-10-17 03:23:15,295][62408] Updated weights for policy 1, policy_version 77470 (0.0009) -[2023-10-17 03:23:16,374][62373] Updated weights for policy 0, policy_version 78020 (0.0007) -[2023-10-17 03:23:16,748][62373] Updated weights for policy 0, policy_version 78030 (0.0007) -[2023-10-17 03:23:17,115][62373] Updated weights for policy 0, policy_version 78040 (0.0008) -[2023-10-17 03:23:17,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 159219712. Throughput: 0: 1787.5, 1: 1752.2. Samples: 39819698. Policy #0 lag: (min: 9.0, avg: 24.9, max: 41.0) -[2023-10-17 03:23:17,215][61453] Avg episode reward: [(0, '10.770'), (1, '11.740')] -[2023-10-17 03:23:19,200][62408] Updated weights for policy 1, policy_version 77480 (0.0007) -[2023-10-17 03:23:19,565][62408] Updated weights for policy 1, policy_version 77490 (0.0009) -[2023-10-17 03:23:19,931][62408] Updated weights for policy 1, policy_version 77500 (0.0009) -[2023-10-17 03:23:20,963][62373] Updated weights for policy 0, policy_version 78050 (0.0008) -[2023-10-17 03:23:21,340][62373] Updated weights for policy 0, policy_version 78060 (0.0007) -[2023-10-17 03:23:21,704][62373] Updated weights for policy 0, policy_version 78070 (0.0008) -[2023-10-17 03:23:22,072][62373] Updated weights for policy 0, policy_version 78080 (0.0008) -[2023-10-17 03:23:22,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 159318016. Throughput: 0: 1775.8, 1: 1758.3. Samples: 39830586. Policy #0 lag: (min: 9.0, avg: 24.9, max: 41.0) -[2023-10-17 03:23:22,215][61453] Avg episode reward: [(0, '10.450'), (1, '12.540')] -[2023-10-17 03:23:23,661][62408] Updated weights for policy 1, policy_version 77510 (0.0008) -[2023-10-17 03:23:24,028][62408] Updated weights for policy 1, policy_version 77520 (0.0009) -[2023-10-17 03:23:24,397][62408] Updated weights for policy 1, policy_version 77530 (0.0009) -[2023-10-17 03:23:25,832][62373] Updated weights for policy 0, policy_version 78090 (0.0011) -[2023-10-17 03:23:26,199][62373] Updated weights for policy 0, policy_version 78100 (0.0010) -[2023-10-17 03:23:26,566][62373] Updated weights for policy 0, policy_version 78110 (0.0009) -[2023-10-17 03:23:27,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 159383552. Throughput: 0: 1794.8, 1: 1754.2. Samples: 39852054. Policy #0 lag: (min: 9.0, avg: 24.9, max: 41.0) -[2023-10-17 03:23:27,214][61453] Avg episode reward: [(0, '11.030'), (1, '11.950')] -[2023-10-17 03:23:28,180][62408] Updated weights for policy 1, policy_version 77540 (0.0008) -[2023-10-17 03:23:28,551][62408] Updated weights for policy 1, policy_version 77550 (0.0008) -[2023-10-17 03:23:28,906][62408] Updated weights for policy 1, policy_version 77560 (0.0010) -[2023-10-17 03:23:30,417][62373] Updated weights for policy 0, policy_version 78120 (0.0007) -[2023-10-17 03:23:30,794][62373] Updated weights for policy 0, policy_version 78130 (0.0009) -[2023-10-17 03:23:31,171][62373] Updated weights for policy 0, policy_version 78140 (0.0009) -[2023-10-17 03:23:32,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 159449088. Throughput: 0: 1778.1, 1: 1777.6. Samples: 39873460. Policy #0 lag: (min: 9.0, avg: 24.9, max: 41.0) -[2023-10-17 03:23:32,214][61453] Avg episode reward: [(0, '10.710'), (1, '12.010')] -[2023-10-17 03:23:32,224][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000077568_79429632.pth... -[2023-10-17 03:23:32,224][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000078144_80019456.pth... -[2023-10-17 03:23:32,261][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000076480_78315520.pth -[2023-10-17 03:23:32,263][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000075936_77758464.pth -[2023-10-17 03:23:32,771][62408] Updated weights for policy 1, policy_version 77570 (0.0011) -[2023-10-17 03:23:33,193][62408] Updated weights for policy 1, policy_version 77580 (0.0008) -[2023-10-17 03:23:33,561][62408] Updated weights for policy 1, policy_version 77590 (0.0011) -[2023-10-17 03:23:33,924][62408] Updated weights for policy 1, policy_version 77600 (0.0009) -[2023-10-17 03:23:34,808][62373] Updated weights for policy 0, policy_version 78150 (0.0008) -[2023-10-17 03:23:35,184][62373] Updated weights for policy 0, policy_version 78160 (0.0009) -[2023-10-17 03:23:35,559][62373] Updated weights for policy 0, policy_version 78170 (0.0009) -[2023-10-17 03:23:37,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 159514624. Throughput: 0: 1800.9, 1: 1758.0. Samples: 39883926. Policy #0 lag: (min: 9.0, avg: 24.9, max: 41.0) -[2023-10-17 03:23:37,215][61453] Avg episode reward: [(0, '10.790'), (1, '11.310')] -[2023-10-17 03:23:37,735][62408] Updated weights for policy 1, policy_version 77610 (0.0008) -[2023-10-17 03:23:38,109][62408] Updated weights for policy 1, policy_version 77620 (0.0008) -[2023-10-17 03:23:38,469][62408] Updated weights for policy 1, policy_version 77630 (0.0008) -[2023-10-17 03:23:39,275][62373] Updated weights for policy 0, policy_version 78180 (0.0008) -[2023-10-17 03:23:39,638][62373] Updated weights for policy 0, policy_version 78190 (0.0007) -[2023-10-17 03:23:40,021][62373] Updated weights for policy 0, policy_version 78200 (0.0008) -[2023-10-17 03:23:42,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 159580160. Throughput: 0: 1775.2, 1: 1768.9. Samples: 39905132. Policy #0 lag: (min: 9.0, avg: 24.9, max: 41.0) -[2023-10-17 03:23:42,215][61453] Avg episode reward: [(0, '10.850'), (1, '11.530')] -[2023-10-17 03:23:42,351][62408] Updated weights for policy 1, policy_version 77640 (0.0007) -[2023-10-17 03:23:42,727][62408] Updated weights for policy 1, policy_version 77650 (0.0010) -[2023-10-17 03:23:43,088][62408] Updated weights for policy 1, policy_version 77660 (0.0008) -[2023-10-17 03:23:43,866][62373] Updated weights for policy 0, policy_version 78210 (0.0007) -[2023-10-17 03:23:44,235][62373] Updated weights for policy 0, policy_version 78220 (0.0010) -[2023-10-17 03:23:44,604][62373] Updated weights for policy 0, policy_version 78230 (0.0007) -[2023-10-17 03:23:44,977][62373] Updated weights for policy 0, policy_version 78240 (0.0008) -[2023-10-17 03:23:46,887][62408] Updated weights for policy 1, policy_version 77670 (0.0007) -[2023-10-17 03:23:47,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 159645696. Throughput: 0: 1774.7, 1: 1789.2. Samples: 39926930. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:23:47,215][61453] Avg episode reward: [(0, '11.920'), (1, '11.050')] -[2023-10-17 03:23:47,254][62408] Updated weights for policy 1, policy_version 77680 (0.0007) -[2023-10-17 03:23:47,625][62408] Updated weights for policy 1, policy_version 77690 (0.0007) -[2023-10-17 03:23:48,711][62373] Updated weights for policy 0, policy_version 78250 (0.0009) -[2023-10-17 03:23:49,081][62373] Updated weights for policy 0, policy_version 78260 (0.0008) -[2023-10-17 03:23:49,442][62373] Updated weights for policy 0, policy_version 78270 (0.0008) -[2023-10-17 03:23:51,390][62408] Updated weights for policy 1, policy_version 77700 (0.0009) -[2023-10-17 03:23:51,751][62408] Updated weights for policy 1, policy_version 77710 (0.0007) -[2023-10-17 03:23:52,119][62408] Updated weights for policy 1, policy_version 77720 (0.0007) -[2023-10-17 03:23:52,214][61453] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 159711232. Throughput: 0: 1778.9, 1: 1758.6. Samples: 39936940. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:23:52,215][61453] Avg episode reward: [(0, '11.150'), (1, '10.860')] -[2023-10-17 03:23:53,191][62373] Updated weights for policy 0, policy_version 78280 (0.0007) -[2023-10-17 03:23:53,565][62373] Updated weights for policy 0, policy_version 78290 (0.0008) -[2023-10-17 03:23:53,924][62373] Updated weights for policy 0, policy_version 78300 (0.0009) -[2023-10-17 03:23:55,933][62408] Updated weights for policy 1, policy_version 77730 (0.0008) -[2023-10-17 03:23:56,299][62408] Updated weights for policy 1, policy_version 77740 (0.0007) -[2023-10-17 03:23:56,663][62408] Updated weights for policy 1, policy_version 77750 (0.0009) -[2023-10-17 03:23:57,034][62408] Updated weights for policy 1, policy_version 77760 (0.0010) -[2023-10-17 03:23:57,214][61453] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 159809536. Throughput: 0: 1783.6, 1: 1794.8. Samples: 39959416. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:23:57,215][61453] Avg episode reward: [(0, '11.370'), (1, '10.340')] -[2023-10-17 03:23:57,675][62373] Updated weights for policy 0, policy_version 78310 (0.0007) -[2023-10-17 03:23:58,040][62373] Updated weights for policy 0, policy_version 78320 (0.0011) -[2023-10-17 03:23:58,408][62373] Updated weights for policy 0, policy_version 78330 (0.0009) -[2023-10-17 03:24:00,749][62408] Updated weights for policy 1, policy_version 77770 (0.0010) -[2023-10-17 03:24:01,116][62408] Updated weights for policy 1, policy_version 77780 (0.0007) -[2023-10-17 03:24:01,476][62408] Updated weights for policy 1, policy_version 77790 (0.0008) -[2023-10-17 03:24:02,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 159875072. Throughput: 0: 1803.5, 1: 1768.8. Samples: 39980452. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:24:02,214][61453] Avg episode reward: [(0, '11.720'), (1, '10.590')] -[2023-10-17 03:24:02,233][62373] Updated weights for policy 0, policy_version 78340 (0.0009) -[2023-10-17 03:24:02,594][62373] Updated weights for policy 0, policy_version 78350 (0.0009) -[2023-10-17 03:24:02,980][62373] Updated weights for policy 0, policy_version 78360 (0.0010) -[2023-10-17 03:24:05,482][62408] Updated weights for policy 1, policy_version 77800 (0.0010) -[2023-10-17 03:24:05,850][62408] Updated weights for policy 1, policy_version 77810 (0.0010) -[2023-10-17 03:24:06,209][62408] Updated weights for policy 1, policy_version 77820 (0.0010) -[2023-10-17 03:24:06,802][62373] Updated weights for policy 0, policy_version 78370 (0.0009) -[2023-10-17 03:24:07,178][62373] Updated weights for policy 0, policy_version 78380 (0.0008) -[2023-10-17 03:24:07,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 159940608. Throughput: 0: 1781.2, 1: 1788.4. Samples: 39991214. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:24:07,215][61453] Avg episode reward: [(0, '11.930'), (1, '10.740')] -[2023-10-17 03:24:07,547][62373] Updated weights for policy 0, policy_version 78390 (0.0009) -[2023-10-17 03:24:07,912][62373] Updated weights for policy 0, policy_version 78400 (0.0007) -[2023-10-17 03:24:10,063][62408] Updated weights for policy 1, policy_version 77830 (0.0009) -[2023-10-17 03:24:10,429][62408] Updated weights for policy 1, policy_version 77840 (0.0007) -[2023-10-17 03:24:10,793][62408] Updated weights for policy 1, policy_version 77850 (0.0008) -[2023-10-17 03:24:11,657][62373] Updated weights for policy 0, policy_version 78410 (0.0007) -[2023-10-17 03:24:12,025][62373] Updated weights for policy 0, policy_version 78420 (0.0007) -[2023-10-17 03:24:12,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 160006144. Throughput: 0: 1798.9, 1: 1762.9. Samples: 40012338. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:24:12,214][61453] Avg episode reward: [(0, '11.650'), (1, '11.480')] -[2023-10-17 03:24:12,402][62373] Updated weights for policy 0, policy_version 78430 (0.0009) -[2023-10-17 03:24:14,407][62408] Updated weights for policy 1, policy_version 77860 (0.0009) -[2023-10-17 03:24:14,774][62408] Updated weights for policy 1, policy_version 77870 (0.0010) -[2023-10-17 03:24:15,144][62408] Updated weights for policy 1, policy_version 77880 (0.0007) -[2023-10-17 03:24:16,294][62373] Updated weights for policy 0, policy_version 78440 (0.0009) -[2023-10-17 03:24:16,665][62373] Updated weights for policy 0, policy_version 78450 (0.0011) -[2023-10-17 03:24:17,034][62373] Updated weights for policy 0, policy_version 78460 (0.0009) -[2023-10-17 03:24:17,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 160104448. Throughput: 0: 1790.2, 1: 1760.4. Samples: 40033234. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:24:17,215][61453] Avg episode reward: [(0, '11.730'), (1, '11.350')] -[2023-10-17 03:24:18,985][62408] Updated weights for policy 1, policy_version 77890 (0.0009) -[2023-10-17 03:24:19,359][62408] Updated weights for policy 1, policy_version 77900 (0.0010) -[2023-10-17 03:24:19,727][62408] Updated weights for policy 1, policy_version 77910 (0.0011) -[2023-10-17 03:24:20,092][62408] Updated weights for policy 1, policy_version 77920 (0.0009) -[2023-10-17 03:24:20,853][62373] Updated weights for policy 0, policy_version 78470 (0.0008) -[2023-10-17 03:24:21,220][62373] Updated weights for policy 0, policy_version 78480 (0.0007) -[2023-10-17 03:24:21,596][62373] Updated weights for policy 0, policy_version 78490 (0.0009) -[2023-10-17 03:24:22,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 160169984. Throughput: 0: 1789.7, 1: 1771.2. Samples: 40044168. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:24:22,214][61453] Avg episode reward: [(0, '11.230'), (1, '11.530')] -[2023-10-17 03:24:23,986][62408] Updated weights for policy 1, policy_version 77930 (0.0007) -[2023-10-17 03:24:24,349][62408] Updated weights for policy 1, policy_version 77940 (0.0007) -[2023-10-17 03:24:24,721][62408] Updated weights for policy 1, policy_version 77950 (0.0008) -[2023-10-17 03:24:25,266][62373] Updated weights for policy 0, policy_version 78500 (0.0008) -[2023-10-17 03:24:25,632][62373] Updated weights for policy 0, policy_version 78510 (0.0008) -[2023-10-17 03:24:26,008][62373] Updated weights for policy 0, policy_version 78520 (0.0008) -[2023-10-17 03:24:27,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 160235520. Throughput: 0: 1796.7, 1: 1759.8. Samples: 40065174. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:24:27,215][61453] Avg episode reward: [(0, '11.230'), (1, '11.670')] -[2023-10-17 03:24:28,593][62408] Updated weights for policy 1, policy_version 77960 (0.0008) -[2023-10-17 03:24:28,957][62408] Updated weights for policy 1, policy_version 77970 (0.0010) -[2023-10-17 03:24:29,322][62408] Updated weights for policy 1, policy_version 77980 (0.0008) -[2023-10-17 03:24:29,816][62373] Updated weights for policy 0, policy_version 78530 (0.0011) -[2023-10-17 03:24:30,192][62373] Updated weights for policy 0, policy_version 78540 (0.0009) -[2023-10-17 03:24:30,569][62373] Updated weights for policy 0, policy_version 78550 (0.0007) -[2023-10-17 03:24:30,927][62373] Updated weights for policy 0, policy_version 78560 (0.0009) -[2023-10-17 03:24:32,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 160301056. Throughput: 0: 1785.3, 1: 1767.2. Samples: 40086792. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:24:32,215][61453] Avg episode reward: [(0, '11.030'), (1, '11.290')] -[2023-10-17 03:24:33,090][62408] Updated weights for policy 1, policy_version 77990 (0.0009) -[2023-10-17 03:24:33,458][62408] Updated weights for policy 1, policy_version 78000 (0.0008) -[2023-10-17 03:24:33,819][62408] Updated weights for policy 1, policy_version 78010 (0.0007) -[2023-10-17 03:24:34,686][62373] Updated weights for policy 0, policy_version 78570 (0.0009) -[2023-10-17 03:24:35,057][62373] Updated weights for policy 0, policy_version 78580 (0.0007) -[2023-10-17 03:24:35,419][62373] Updated weights for policy 0, policy_version 78590 (0.0009) -[2023-10-17 03:24:37,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 160366592. Throughput: 0: 1799.9, 1: 1764.8. Samples: 40097350. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-17 03:24:37,214][61453] Avg episode reward: [(0, '11.480'), (1, '10.590')] -[2023-10-17 03:24:37,677][62408] Updated weights for policy 1, policy_version 78020 (0.0008) -[2023-10-17 03:24:38,045][62408] Updated weights for policy 1, policy_version 78030 (0.0007) -[2023-10-17 03:24:38,411][62408] Updated weights for policy 1, policy_version 78040 (0.0008) -[2023-10-17 03:24:39,152][62373] Updated weights for policy 0, policy_version 78600 (0.0010) -[2023-10-17 03:24:39,514][62373] Updated weights for policy 0, policy_version 78610 (0.0009) -[2023-10-17 03:24:39,893][62373] Updated weights for policy 0, policy_version 78620 (0.0008) -[2023-10-17 03:24:42,199][62408] Updated weights for policy 1, policy_version 78050 (0.0008) -[2023-10-17 03:24:42,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 160432128. Throughput: 0: 1777.6, 1: 1759.5. Samples: 40118584. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-17 03:24:42,215][61453] Avg episode reward: [(0, '11.440'), (1, '10.880')] -[2023-10-17 03:24:42,571][62408] Updated weights for policy 1, policy_version 78060 (0.0009) -[2023-10-17 03:24:42,931][62408] Updated weights for policy 1, policy_version 78070 (0.0009) -[2023-10-17 03:24:43,299][62408] Updated weights for policy 1, policy_version 78080 (0.0007) -[2023-10-17 03:24:43,847][62373] Updated weights for policy 0, policy_version 78630 (0.0009) -[2023-10-17 03:24:44,223][62373] Updated weights for policy 0, policy_version 78640 (0.0009) -[2023-10-17 03:24:44,595][62373] Updated weights for policy 0, policy_version 78650 (0.0009) -[2023-10-17 03:24:47,047][62408] Updated weights for policy 1, policy_version 78090 (0.0009) -[2023-10-17 03:24:47,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 160497664. Throughput: 0: 1775.7, 1: 1780.1. Samples: 40140464. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-17 03:24:47,214][61453] Avg episode reward: [(0, '11.580'), (1, '9.970')] -[2023-10-17 03:24:47,422][62408] Updated weights for policy 1, policy_version 78100 (0.0010) -[2023-10-17 03:24:47,793][62408] Updated weights for policy 1, policy_version 78110 (0.0008) -[2023-10-17 03:24:48,255][62373] Updated weights for policy 0, policy_version 78660 (0.0009) -[2023-10-17 03:24:48,624][62373] Updated weights for policy 0, policy_version 78670 (0.0009) -[2023-10-17 03:24:48,997][62373] Updated weights for policy 0, policy_version 78680 (0.0010) -[2023-10-17 03:24:51,836][62408] Updated weights for policy 1, policy_version 78120 (0.0008) -[2023-10-17 03:24:52,211][62408] Updated weights for policy 1, policy_version 78130 (0.0009) -[2023-10-17 03:24:52,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 160563200. Throughput: 0: 1777.1, 1: 1755.3. Samples: 40150172. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-17 03:24:52,215][61453] Avg episode reward: [(0, '11.340'), (1, '9.740')] -[2023-10-17 03:24:52,573][62408] Updated weights for policy 1, policy_version 78140 (0.0007) -[2023-10-17 03:24:52,936][62373] Updated weights for policy 0, policy_version 78690 (0.0008) -[2023-10-17 03:24:53,293][62373] Updated weights for policy 0, policy_version 78700 (0.0009) -[2023-10-17 03:24:53,662][62373] Updated weights for policy 0, policy_version 78710 (0.0010) -[2023-10-17 03:24:54,024][62373] Updated weights for policy 0, policy_version 78720 (0.0009) -[2023-10-17 03:24:56,344][62408] Updated weights for policy 1, policy_version 78150 (0.0008) -[2023-10-17 03:24:56,721][62408] Updated weights for policy 1, policy_version 78160 (0.0008) -[2023-10-17 03:24:57,097][62408] Updated weights for policy 1, policy_version 78170 (0.0008) -[2023-10-17 03:24:57,214][61453] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 160628736. Throughput: 0: 1772.4, 1: 1785.0. Samples: 40172420. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-17 03:24:57,215][61453] Avg episode reward: [(0, '11.030'), (1, '9.180')] -[2023-10-17 03:24:57,750][62373] Updated weights for policy 0, policy_version 78730 (0.0007) -[2023-10-17 03:24:58,111][62373] Updated weights for policy 0, policy_version 78740 (0.0008) -[2023-10-17 03:24:58,478][62373] Updated weights for policy 0, policy_version 78750 (0.0007) -[2023-10-17 03:25:00,912][62408] Updated weights for policy 1, policy_version 78180 (0.0009) -[2023-10-17 03:25:01,270][62408] Updated weights for policy 1, policy_version 78190 (0.0010) -[2023-10-17 03:25:01,641][62408] Updated weights for policy 1, policy_version 78200 (0.0007) -[2023-10-17 03:25:02,214][61453] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 160727040. Throughput: 0: 1808.0, 1: 1755.6. Samples: 40193594. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-17 03:25:02,214][61453] Avg episode reward: [(0, '11.010'), (1, '9.770')] -[2023-10-17 03:25:02,321][62373] Updated weights for policy 0, policy_version 78760 (0.0009) -[2023-10-17 03:25:02,690][62373] Updated weights for policy 0, policy_version 78770 (0.0009) -[2023-10-17 03:25:03,052][62373] Updated weights for policy 0, policy_version 78780 (0.0007) -[2023-10-17 03:25:05,462][62408] Updated weights for policy 1, policy_version 78210 (0.0008) -[2023-10-17 03:25:05,861][62408] Updated weights for policy 1, policy_version 78220 (0.0007) -[2023-10-17 03:25:06,227][62408] Updated weights for policy 1, policy_version 78230 (0.0007) -[2023-10-17 03:25:06,594][62408] Updated weights for policy 1, policy_version 78240 (0.0009) -[2023-10-17 03:25:06,773][62373] Updated weights for policy 0, policy_version 78790 (0.0009) -[2023-10-17 03:25:07,141][62373] Updated weights for policy 0, policy_version 78800 (0.0010) -[2023-10-17 03:25:07,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 160792576. Throughput: 0: 1784.0, 1: 1782.2. Samples: 40204650. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-17 03:25:07,215][61453] Avg episode reward: [(0, '10.930'), (1, '10.460')] -[2023-10-17 03:25:07,507][62373] Updated weights for policy 0, policy_version 78810 (0.0011) -[2023-10-17 03:25:10,364][62408] Updated weights for policy 1, policy_version 78250 (0.0008) -[2023-10-17 03:25:10,721][62408] Updated weights for policy 1, policy_version 78260 (0.0009) -[2023-10-17 03:25:11,085][62408] Updated weights for policy 1, policy_version 78270 (0.0009) -[2023-10-17 03:25:11,156][62373] Updated weights for policy 0, policy_version 78820 (0.0009) -[2023-10-17 03:25:11,529][62373] Updated weights for policy 0, policy_version 78830 (0.0008) -[2023-10-17 03:25:11,902][62373] Updated weights for policy 0, policy_version 78840 (0.0007) -[2023-10-17 03:25:12,214][61453] Fps is (10 sec: 16383.6, 60 sec: 14745.5, 300 sec: 14329.0). Total num frames: 160890880. Throughput: 0: 1799.4, 1: 1765.6. Samples: 40225596. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-17 03:25:12,215][61453] Avg episode reward: [(0, '10.920'), (1, '10.430')] -[2023-10-17 03:25:14,856][62408] Updated weights for policy 1, policy_version 78280 (0.0008) -[2023-10-17 03:25:15,219][62408] Updated weights for policy 1, policy_version 78290 (0.0008) -[2023-10-17 03:25:15,587][62408] Updated weights for policy 1, policy_version 78300 (0.0008) -[2023-10-17 03:25:15,704][62373] Updated weights for policy 0, policy_version 78850 (0.0007) -[2023-10-17 03:25:16,063][62373] Updated weights for policy 0, policy_version 78860 (0.0010) -[2023-10-17 03:25:16,432][62373] Updated weights for policy 0, policy_version 78870 (0.0008) -[2023-10-17 03:25:16,796][62373] Updated weights for policy 0, policy_version 78880 (0.0008) -[2023-10-17 03:25:17,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 160956416. Throughput: 0: 1776.0, 1: 1757.3. Samples: 40245790. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-17 03:25:17,215][61453] Avg episode reward: [(0, '11.140'), (1, '10.730')] -[2023-10-17 03:25:19,376][62408] Updated weights for policy 1, policy_version 78310 (0.0008) -[2023-10-17 03:25:19,739][62408] Updated weights for policy 1, policy_version 78320 (0.0011) -[2023-10-17 03:25:20,103][62408] Updated weights for policy 1, policy_version 78330 (0.0009) -[2023-10-17 03:25:20,634][62373] Updated weights for policy 0, policy_version 78890 (0.0007) -[2023-10-17 03:25:21,010][62373] Updated weights for policy 0, policy_version 78900 (0.0010) -[2023-10-17 03:25:21,375][62373] Updated weights for policy 0, policy_version 78910 (0.0011) -[2023-10-17 03:25:22,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 161021952. Throughput: 0: 1790.0, 1: 1768.0. Samples: 40257458. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-17 03:25:22,215][61453] Avg episode reward: [(0, '10.000'), (1, '10.860')] -[2023-10-17 03:25:23,935][62408] Updated weights for policy 1, policy_version 78340 (0.0007) -[2023-10-17 03:25:24,303][62408] Updated weights for policy 1, policy_version 78350 (0.0009) -[2023-10-17 03:25:24,654][62408] Updated weights for policy 1, policy_version 78360 (0.0011) -[2023-10-17 03:25:25,278][62373] Updated weights for policy 0, policy_version 78920 (0.0009) -[2023-10-17 03:25:25,657][62373] Updated weights for policy 0, policy_version 78930 (0.0010) -[2023-10-17 03:25:26,021][62373] Updated weights for policy 0, policy_version 78940 (0.0010) -[2023-10-17 03:25:27,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 161087488. Throughput: 0: 1782.2, 1: 1755.1. Samples: 40277762. Policy #0 lag: (min: 1.0, avg: 6.4, max: 33.0) -[2023-10-17 03:25:27,215][61453] Avg episode reward: [(0, '10.300'), (1, '10.740')] -[2023-10-17 03:25:28,529][62408] Updated weights for policy 1, policy_version 78370 (0.0010) -[2023-10-17 03:25:28,900][62408] Updated weights for policy 1, policy_version 78380 (0.0009) -[2023-10-17 03:25:29,269][62408] Updated weights for policy 1, policy_version 78390 (0.0007) -[2023-10-17 03:25:29,639][62408] Updated weights for policy 1, policy_version 78400 (0.0008) -[2023-10-17 03:25:29,850][62373] Updated weights for policy 0, policy_version 78950 (0.0009) -[2023-10-17 03:25:30,224][62373] Updated weights for policy 0, policy_version 78960 (0.0011) -[2023-10-17 03:25:30,585][62373] Updated weights for policy 0, policy_version 78970 (0.0009) -[2023-10-17 03:25:32,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 161153024. Throughput: 0: 1775.0, 1: 1764.4. Samples: 40299736. Policy #0 lag: (min: 1.0, avg: 6.4, max: 33.0) -[2023-10-17 03:25:32,215][61453] Avg episode reward: [(0, '10.740'), (1, '11.020')] -[2023-10-17 03:25:32,223][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000078976_80871424.pth... -[2023-10-17 03:25:32,223][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000078400_80281600.pth... -[2023-10-17 03:25:32,259][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000077312_79167488.pth -[2023-10-17 03:25:32,259][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000076736_78577664.pth -[2023-10-17 03:25:33,394][62408] Updated weights for policy 1, policy_version 78410 (0.0009) -[2023-10-17 03:25:33,767][62408] Updated weights for policy 1, policy_version 78420 (0.0009) -[2023-10-17 03:25:34,127][62408] Updated weights for policy 1, policy_version 78430 (0.0007) -[2023-10-17 03:25:34,321][62373] Updated weights for policy 0, policy_version 78980 (0.0009) -[2023-10-17 03:25:34,698][62373] Updated weights for policy 0, policy_version 78990 (0.0008) -[2023-10-17 03:25:35,061][62373] Updated weights for policy 0, policy_version 79000 (0.0008) -[2023-10-17 03:25:37,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 161218560. Throughput: 0: 1786.7, 1: 1761.5. Samples: 40309840. Policy #0 lag: (min: 1.0, avg: 6.4, max: 33.0) -[2023-10-17 03:25:37,215][61453] Avg episode reward: [(0, '10.760'), (1, '10.540')] -[2023-10-17 03:25:38,093][62408] Updated weights for policy 1, policy_version 78440 (0.0008) -[2023-10-17 03:25:38,454][62408] Updated weights for policy 1, policy_version 78450 (0.0008) -[2023-10-17 03:25:38,836][62408] Updated weights for policy 1, policy_version 78460 (0.0008) -[2023-10-17 03:25:38,866][62373] Updated weights for policy 0, policy_version 79010 (0.0007) -[2023-10-17 03:25:39,236][62373] Updated weights for policy 0, policy_version 79020 (0.0008) -[2023-10-17 03:25:39,604][62373] Updated weights for policy 0, policy_version 79030 (0.0007) -[2023-10-17 03:25:39,978][62373] Updated weights for policy 0, policy_version 79040 (0.0007) -[2023-10-17 03:25:42,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 161284096. Throughput: 0: 1772.8, 1: 1753.5. Samples: 40331104. Policy #0 lag: (min: 1.0, avg: 6.4, max: 33.0) -[2023-10-17 03:25:42,215][61453] Avg episode reward: [(0, '10.300'), (1, '9.930')] -[2023-10-17 03:25:42,641][62408] Updated weights for policy 1, policy_version 78470 (0.0008) -[2023-10-17 03:25:43,007][62408] Updated weights for policy 1, policy_version 78480 (0.0009) -[2023-10-17 03:25:43,378][62408] Updated weights for policy 1, policy_version 78490 (0.0008) -[2023-10-17 03:25:43,746][62373] Updated weights for policy 0, policy_version 79050 (0.0008) -[2023-10-17 03:25:44,115][62373] Updated weights for policy 0, policy_version 79060 (0.0010) -[2023-10-17 03:25:44,482][62373] Updated weights for policy 0, policy_version 79070 (0.0011) -[2023-10-17 03:25:47,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 161349632. Throughput: 0: 1768.7, 1: 1780.5. Samples: 40353306. Policy #0 lag: (min: 1.0, avg: 6.4, max: 33.0) -[2023-10-17 03:25:47,214][61453] Avg episode reward: [(0, '9.860'), (1, '10.370')] -[2023-10-17 03:25:47,280][62408] Updated weights for policy 1, policy_version 78500 (0.0008) -[2023-10-17 03:25:47,642][62408] Updated weights for policy 1, policy_version 78510 (0.0007) -[2023-10-17 03:25:48,013][62408] Updated weights for policy 1, policy_version 78520 (0.0007) -[2023-10-17 03:25:48,193][62373] Updated weights for policy 0, policy_version 79080 (0.0008) -[2023-10-17 03:25:48,566][62373] Updated weights for policy 0, policy_version 79090 (0.0007) -[2023-10-17 03:25:48,931][62373] Updated weights for policy 0, policy_version 79100 (0.0009) -[2023-10-17 03:25:51,860][62408] Updated weights for policy 1, policy_version 78530 (0.0008) -[2023-10-17 03:25:52,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 161415168. Throughput: 0: 1766.6, 1: 1749.5. Samples: 40362876. Policy #0 lag: (min: 1.0, avg: 6.4, max: 33.0) -[2023-10-17 03:25:52,215][61453] Avg episode reward: [(0, '10.490'), (1, '10.210')] -[2023-10-17 03:25:52,257][62408] Updated weights for policy 1, policy_version 78540 (0.0012) -[2023-10-17 03:25:52,624][62408] Updated weights for policy 1, policy_version 78550 (0.0010) -[2023-10-17 03:25:52,784][62373] Updated weights for policy 0, policy_version 79110 (0.0010) -[2023-10-17 03:25:52,988][62408] Updated weights for policy 1, policy_version 78560 (0.0008) -[2023-10-17 03:25:53,150][62373] Updated weights for policy 0, policy_version 79120 (0.0011) -[2023-10-17 03:25:53,528][62373] Updated weights for policy 0, policy_version 79130 (0.0011) -[2023-10-17 03:25:56,847][62408] Updated weights for policy 1, policy_version 78570 (0.0008) -[2023-10-17 03:25:57,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 161480704. Throughput: 0: 1762.8, 1: 1773.6. Samples: 40384732. Policy #0 lag: (min: 1.0, avg: 6.4, max: 33.0) -[2023-10-17 03:25:57,214][61453] Avg episode reward: [(0, '10.560'), (1, '10.480')] -[2023-10-17 03:25:57,216][62408] Updated weights for policy 1, policy_version 78580 (0.0008) -[2023-10-17 03:25:57,405][62373] Updated weights for policy 0, policy_version 79140 (0.0009) -[2023-10-17 03:25:57,573][62408] Updated weights for policy 1, policy_version 78590 (0.0009) -[2023-10-17 03:25:57,775][62373] Updated weights for policy 0, policy_version 79150 (0.0009) -[2023-10-17 03:25:58,151][62373] Updated weights for policy 0, policy_version 79160 (0.0010) -[2023-10-17 03:26:01,449][62408] Updated weights for policy 1, policy_version 78600 (0.0007) -[2023-10-17 03:26:01,824][62408] Updated weights for policy 1, policy_version 78610 (0.0007) -[2023-10-17 03:26:02,068][62373] Updated weights for policy 0, policy_version 79170 (0.0009) -[2023-10-17 03:26:02,187][62408] Updated weights for policy 1, policy_version 78620 (0.0007) -[2023-10-17 03:26:02,214][61453] Fps is (10 sec: 13107.6, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 161546240. Throughput: 0: 1796.2, 1: 1760.6. Samples: 40405846. Policy #0 lag: (min: 1.0, avg: 6.4, max: 33.0) -[2023-10-17 03:26:02,214][61453] Avg episode reward: [(0, '10.680'), (1, '9.910')] -[2023-10-17 03:26:02,444][62373] Updated weights for policy 0, policy_version 79180 (0.0007) -[2023-10-17 03:26:02,816][62373] Updated weights for policy 0, policy_version 79190 (0.0009) -[2023-10-17 03:26:03,184][62373] Updated weights for policy 0, policy_version 79200 (0.0011) -[2023-10-17 03:26:06,206][62408] Updated weights for policy 1, policy_version 78630 (0.0007) -[2023-10-17 03:26:06,570][62408] Updated weights for policy 1, policy_version 78640 (0.0007) -[2023-10-17 03:26:06,940][62408] Updated weights for policy 1, policy_version 78650 (0.0008) -[2023-10-17 03:26:07,045][62373] Updated weights for policy 0, policy_version 79210 (0.0010) -[2023-10-17 03:26:07,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 161644544. Throughput: 0: 1761.7, 1: 1760.0. Samples: 40415934. Policy #0 lag: (min: 1.0, avg: 6.4, max: 33.0) -[2023-10-17 03:26:07,215][61453] Avg episode reward: [(0, '11.510'), (1, '10.630')] -[2023-10-17 03:26:07,408][62373] Updated weights for policy 0, policy_version 79220 (0.0008) -[2023-10-17 03:26:07,780][62373] Updated weights for policy 0, policy_version 79230 (0.0009) -[2023-10-17 03:26:10,697][62408] Updated weights for policy 1, policy_version 78660 (0.0009) -[2023-10-17 03:26:11,064][62408] Updated weights for policy 1, policy_version 78670 (0.0011) -[2023-10-17 03:26:11,438][62408] Updated weights for policy 1, policy_version 78680 (0.0008) -[2023-10-17 03:26:11,595][62373] Updated weights for policy 0, policy_version 79240 (0.0008) -[2023-10-17 03:26:11,962][62373] Updated weights for policy 0, policy_version 79250 (0.0010) -[2023-10-17 03:26:12,214][61453] Fps is (10 sec: 16384.0, 60 sec: 13653.4, 300 sec: 14218.0). Total num frames: 161710080. Throughput: 0: 1780.9, 1: 1765.2. Samples: 40437336. Policy #0 lag: (min: 1.0, avg: 6.4, max: 33.0) -[2023-10-17 03:26:12,214][61453] Avg episode reward: [(0, '10.380'), (1, '10.230')] -[2023-10-17 03:26:12,336][62373] Updated weights for policy 0, policy_version 79260 (0.0009) -[2023-10-17 03:26:15,225][62408] Updated weights for policy 1, policy_version 78690 (0.0008) -[2023-10-17 03:26:15,594][62408] Updated weights for policy 1, policy_version 78700 (0.0007) -[2023-10-17 03:26:15,948][62408] Updated weights for policy 1, policy_version 78710 (0.0008) -[2023-10-17 03:26:16,034][62373] Updated weights for policy 0, policy_version 79270 (0.0010) -[2023-10-17 03:26:16,315][62408] Updated weights for policy 1, policy_version 78720 (0.0008) -[2023-10-17 03:26:16,400][62373] Updated weights for policy 0, policy_version 79280 (0.0009) -[2023-10-17 03:26:16,763][62373] Updated weights for policy 0, policy_version 79290 (0.0007) -[2023-10-17 03:26:17,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 161808384. Throughput: 0: 1758.5, 1: 1742.4. Samples: 40457276. Policy #0 lag: (min: 4.0, avg: 6.6, max: 36.0) -[2023-10-17 03:26:17,215][61453] Avg episode reward: [(0, '10.870'), (1, '10.000')] -[2023-10-17 03:26:20,100][62408] Updated weights for policy 1, policy_version 78730 (0.0011) -[2023-10-17 03:26:20,443][62373] Updated weights for policy 0, policy_version 79300 (0.0010) -[2023-10-17 03:26:20,477][62408] Updated weights for policy 1, policy_version 78740 (0.0010) -[2023-10-17 03:26:20,810][62373] Updated weights for policy 0, policy_version 79310 (0.0009) -[2023-10-17 03:26:20,845][62408] Updated weights for policy 1, policy_version 78750 (0.0009) -[2023-10-17 03:26:21,182][62373] Updated weights for policy 0, policy_version 79320 (0.0009) -[2023-10-17 03:26:22,214][61453] Fps is (10 sec: 16383.4, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 161873920. Throughput: 0: 1775.9, 1: 1772.4. Samples: 40469514. Policy #0 lag: (min: 4.0, avg: 6.6, max: 36.0) -[2023-10-17 03:26:22,215][61453] Avg episode reward: [(0, '10.780'), (1, '10.380')] -[2023-10-17 03:26:24,634][62408] Updated weights for policy 1, policy_version 78760 (0.0007) -[2023-10-17 03:26:25,010][62408] Updated weights for policy 1, policy_version 78770 (0.0008) -[2023-10-17 03:26:25,171][62373] Updated weights for policy 0, policy_version 79330 (0.0009) -[2023-10-17 03:26:25,379][62408] Updated weights for policy 1, policy_version 78780 (0.0007) -[2023-10-17 03:26:25,541][62373] Updated weights for policy 0, policy_version 79340 (0.0009) -[2023-10-17 03:26:25,910][62373] Updated weights for policy 0, policy_version 79350 (0.0007) -[2023-10-17 03:26:26,280][62373] Updated weights for policy 0, policy_version 79360 (0.0008) -[2023-10-17 03:26:27,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 161939456. Throughput: 0: 1763.0, 1: 1750.1. Samples: 40489196. Policy #0 lag: (min: 4.0, avg: 6.6, max: 36.0) -[2023-10-17 03:26:27,215][61453] Avg episode reward: [(0, '10.830'), (1, '10.710')] -[2023-10-17 03:26:29,240][62408] Updated weights for policy 1, policy_version 78790 (0.0009) -[2023-10-17 03:26:29,597][62408] Updated weights for policy 1, policy_version 78800 (0.0010) -[2023-10-17 03:26:29,960][62408] Updated weights for policy 1, policy_version 78810 (0.0007) -[2023-10-17 03:26:30,059][62373] Updated weights for policy 0, policy_version 79370 (0.0007) -[2023-10-17 03:26:30,424][62373] Updated weights for policy 0, policy_version 79380 (0.0008) -[2023-10-17 03:26:30,790][62373] Updated weights for policy 0, policy_version 79390 (0.0008) -[2023-10-17 03:26:32,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 162004992. Throughput: 0: 1751.2, 1: 1746.7. Samples: 40510708. Policy #0 lag: (min: 4.0, avg: 6.6, max: 36.0) -[2023-10-17 03:26:32,215][61453] Avg episode reward: [(0, '10.400'), (1, '10.730')] -[2023-10-17 03:26:33,986][62408] Updated weights for policy 1, policy_version 78820 (0.0009) -[2023-10-17 03:26:34,361][62408] Updated weights for policy 1, policy_version 78830 (0.0009) -[2023-10-17 03:26:34,649][62373] Updated weights for policy 0, policy_version 79400 (0.0008) -[2023-10-17 03:26:34,722][62408] Updated weights for policy 1, policy_version 78840 (0.0009) -[2023-10-17 03:26:35,025][62373] Updated weights for policy 0, policy_version 79410 (0.0009) -[2023-10-17 03:26:35,385][62373] Updated weights for policy 0, policy_version 79420 (0.0011) -[2023-10-17 03:26:37,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 162070528. Throughput: 0: 1769.2, 1: 1746.3. Samples: 40521072. Policy #0 lag: (min: 4.0, avg: 6.6, max: 36.0) -[2023-10-17 03:26:37,215][61453] Avg episode reward: [(0, '10.640'), (1, '10.860')] -[2023-10-17 03:26:38,608][62408] Updated weights for policy 1, policy_version 78850 (0.0009) -[2023-10-17 03:26:38,978][62408] Updated weights for policy 1, policy_version 78860 (0.0008) -[2023-10-17 03:26:39,219][62373] Updated weights for policy 0, policy_version 79430 (0.0008) -[2023-10-17 03:26:39,335][62408] Updated weights for policy 1, policy_version 78870 (0.0008) -[2023-10-17 03:26:39,592][62373] Updated weights for policy 0, policy_version 79440 (0.0007) -[2023-10-17 03:26:39,704][62408] Updated weights for policy 1, policy_version 78880 (0.0008) -[2023-10-17 03:26:39,965][62373] Updated weights for policy 0, policy_version 79450 (0.0008) -[2023-10-17 03:26:42,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 162136064. Throughput: 0: 1757.1, 1: 1738.2. Samples: 40542018. Policy #0 lag: (min: 4.0, avg: 6.6, max: 36.0) -[2023-10-17 03:26:42,215][61453] Avg episode reward: [(0, '10.380'), (1, '11.170')] -[2023-10-17 03:26:43,643][62408] Updated weights for policy 1, policy_version 78890 (0.0009) -[2023-10-17 03:26:43,715][62373] Updated weights for policy 0, policy_version 79460 (0.0009) -[2023-10-17 03:26:44,022][62408] Updated weights for policy 1, policy_version 78900 (0.0008) -[2023-10-17 03:26:44,086][62373] Updated weights for policy 0, policy_version 79470 (0.0008) -[2023-10-17 03:26:44,385][62408] Updated weights for policy 1, policy_version 78910 (0.0009) -[2023-10-17 03:26:44,447][62373] Updated weights for policy 0, policy_version 79480 (0.0007) -[2023-10-17 03:26:47,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 162201600. Throughput: 0: 1762.5, 1: 1753.9. Samples: 40564086. Policy #0 lag: (min: 4.0, avg: 6.6, max: 36.0) -[2023-10-17 03:26:47,215][61453] Avg episode reward: [(0, '10.800'), (1, '11.680')] -[2023-10-17 03:26:48,152][62408] Updated weights for policy 1, policy_version 78920 (0.0008) -[2023-10-17 03:26:48,188][62373] Updated weights for policy 0, policy_version 79490 (0.0007) -[2023-10-17 03:26:48,521][62408] Updated weights for policy 1, policy_version 78930 (0.0007) -[2023-10-17 03:26:48,557][62373] Updated weights for policy 0, policy_version 79500 (0.0010) -[2023-10-17 03:26:48,892][62408] Updated weights for policy 1, policy_version 78940 (0.0008) -[2023-10-17 03:26:48,922][62373] Updated weights for policy 0, policy_version 79510 (0.0010) -[2023-10-17 03:26:49,292][62373] Updated weights for policy 0, policy_version 79520 (0.0008) -[2023-10-17 03:26:52,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 162267136. Throughput: 0: 1764.5, 1: 1741.4. Samples: 40573702. Policy #0 lag: (min: 4.0, avg: 6.6, max: 36.0) -[2023-10-17 03:26:52,215][61453] Avg episode reward: [(0, '11.080'), (1, '11.840')] -[2023-10-17 03:26:52,793][62408] Updated weights for policy 1, policy_version 78950 (0.0008) -[2023-10-17 03:26:53,159][62373] Updated weights for policy 0, policy_version 79530 (0.0008) -[2023-10-17 03:26:53,164][62408] Updated weights for policy 1, policy_version 78960 (0.0008) -[2023-10-17 03:26:53,520][62408] Updated weights for policy 1, policy_version 78970 (0.0007) -[2023-10-17 03:26:53,533][62373] Updated weights for policy 0, policy_version 79540 (0.0008) -[2023-10-17 03:26:53,903][62373] Updated weights for policy 0, policy_version 79550 (0.0010) -[2023-10-17 03:26:57,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 162332672. Throughput: 0: 1764.0, 1: 1749.5. Samples: 40595446. Policy #0 lag: (min: 4.0, avg: 6.6, max: 36.0) -[2023-10-17 03:26:57,215][61453] Avg episode reward: [(0, '11.460'), (1, '11.370')] -[2023-10-17 03:26:57,365][62408] Updated weights for policy 1, policy_version 78980 (0.0009) -[2023-10-17 03:26:57,741][62408] Updated weights for policy 1, policy_version 78990 (0.0009) -[2023-10-17 03:26:57,822][62373] Updated weights for policy 0, policy_version 79560 (0.0010) -[2023-10-17 03:26:58,106][62408] Updated weights for policy 1, policy_version 79000 (0.0009) -[2023-10-17 03:26:58,190][62373] Updated weights for policy 0, policy_version 79570 (0.0009) -[2023-10-17 03:26:58,558][62373] Updated weights for policy 0, policy_version 79580 (0.0007) -[2023-10-17 03:27:01,953][62408] Updated weights for policy 1, policy_version 79010 (0.0008) -[2023-10-17 03:27:02,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 162398208. Throughput: 0: 1793.3, 1: 1768.4. Samples: 40617556. Policy #0 lag: (min: 4.0, avg: 6.6, max: 36.0) -[2023-10-17 03:27:02,215][61453] Avg episode reward: [(0, '11.360'), (1, '11.140')] -[2023-10-17 03:27:02,335][62408] Updated weights for policy 1, policy_version 79020 (0.0007) -[2023-10-17 03:27:02,397][62373] Updated weights for policy 0, policy_version 79590 (0.0007) -[2023-10-17 03:27:02,709][62408] Updated weights for policy 1, policy_version 79030 (0.0008) -[2023-10-17 03:27:02,761][62373] Updated weights for policy 0, policy_version 79600 (0.0007) -[2023-10-17 03:27:03,074][62408] Updated weights for policy 1, policy_version 79040 (0.0008) -[2023-10-17 03:27:03,130][62373] Updated weights for policy 0, policy_version 79610 (0.0007) -[2023-10-17 03:27:06,820][62408] Updated weights for policy 1, policy_version 79050 (0.0007) -[2023-10-17 03:27:06,980][62373] Updated weights for policy 0, policy_version 79620 (0.0010) -[2023-10-17 03:27:07,175][62408] Updated weights for policy 1, policy_version 79060 (0.0008) -[2023-10-17 03:27:07,214][61453] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 162463744. Throughput: 0: 1763.6, 1: 1742.7. Samples: 40627296. Policy #0 lag: (min: 4.0, avg: 6.6, max: 36.0) -[2023-10-17 03:27:07,214][61453] Avg episode reward: [(0, '11.550'), (1, '10.650')] -[2023-10-17 03:27:07,349][62373] Updated weights for policy 0, policy_version 79630 (0.0009) -[2023-10-17 03:27:07,545][62408] Updated weights for policy 1, policy_version 79070 (0.0008) -[2023-10-17 03:27:07,724][62373] Updated weights for policy 0, policy_version 79640 (0.0009) -[2023-10-17 03:27:11,370][62408] Updated weights for policy 1, policy_version 79080 (0.0008) -[2023-10-17 03:27:11,658][62373] Updated weights for policy 0, policy_version 79650 (0.0008) -[2023-10-17 03:27:11,733][62408] Updated weights for policy 1, policy_version 79090 (0.0009) -[2023-10-17 03:27:12,024][62373] Updated weights for policy 0, policy_version 79660 (0.0009) -[2023-10-17 03:27:12,100][62408] Updated weights for policy 1, policy_version 79100 (0.0008) -[2023-10-17 03:27:12,214][61453] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 162529280. Throughput: 0: 1782.9, 1: 1767.4. Samples: 40648960. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-17 03:27:12,215][61453] Avg episode reward: [(0, '10.800'), (1, '10.490')] -[2023-10-17 03:27:12,397][62373] Updated weights for policy 0, policy_version 79670 (0.0009) -[2023-10-17 03:27:12,768][62373] Updated weights for policy 0, policy_version 79680 (0.0008) -[2023-10-17 03:27:16,016][62408] Updated weights for policy 1, policy_version 79110 (0.0009) -[2023-10-17 03:27:16,382][62408] Updated weights for policy 1, policy_version 79120 (0.0009) -[2023-10-17 03:27:16,527][62373] Updated weights for policy 0, policy_version 79690 (0.0009) -[2023-10-17 03:27:16,748][62408] Updated weights for policy 1, policy_version 79130 (0.0009) -[2023-10-17 03:27:16,905][62373] Updated weights for policy 0, policy_version 79700 (0.0009) -[2023-10-17 03:27:17,214][61453] Fps is (10 sec: 16383.7, 60 sec: 13653.3, 300 sec: 14218.0). Total num frames: 162627584. Throughput: 0: 1774.1, 1: 1741.5. Samples: 40668910. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-17 03:27:17,216][61453] Avg episode reward: [(0, '11.020'), (1, '10.740')] -[2023-10-17 03:27:17,285][62373] Updated weights for policy 0, policy_version 79710 (0.0007) -[2023-10-17 03:27:20,477][62408] Updated weights for policy 1, policy_version 79140 (0.0008) -[2023-10-17 03:27:20,844][62408] Updated weights for policy 1, policy_version 79150 (0.0010) -[2023-10-17 03:27:21,203][62408] Updated weights for policy 1, policy_version 79160 (0.0010) -[2023-10-17 03:27:21,247][62373] Updated weights for policy 0, policy_version 79720 (0.0009) -[2023-10-17 03:27:21,621][62373] Updated weights for policy 0, policy_version 79730 (0.0008) -[2023-10-17 03:27:22,000][62373] Updated weights for policy 0, policy_version 79740 (0.0011) -[2023-10-17 03:27:22,214][61453] Fps is (10 sec: 19660.8, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 162725888. Throughput: 0: 1778.1, 1: 1772.7. Samples: 40680860. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-17 03:27:22,215][61453] Avg episode reward: [(0, '10.920'), (1, '9.890')] -[2023-10-17 03:27:24,962][62408] Updated weights for policy 1, policy_version 79170 (0.0008) -[2023-10-17 03:27:25,341][62408] Updated weights for policy 1, policy_version 79180 (0.0008) -[2023-10-17 03:27:25,663][62373] Updated weights for policy 0, policy_version 79750 (0.0008) -[2023-10-17 03:27:25,695][62408] Updated weights for policy 1, policy_version 79190 (0.0009) -[2023-10-17 03:27:26,030][62373] Updated weights for policy 0, policy_version 79760 (0.0009) -[2023-10-17 03:27:26,061][62408] Updated weights for policy 1, policy_version 79200 (0.0009) -[2023-10-17 03:27:26,404][62373] Updated weights for policy 0, policy_version 79770 (0.0007) -[2023-10-17 03:27:27,214][61453] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 162791424. Throughput: 0: 1777.1, 1: 1762.6. Samples: 40701302. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-17 03:27:27,214][61453] Avg episode reward: [(0, '10.220'), (1, '10.270')] -[2023-10-17 03:27:29,979][62408] Updated weights for policy 1, policy_version 79210 (0.0008) -[2023-10-17 03:27:30,057][62373] Updated weights for policy 0, policy_version 79780 (0.0008) -[2023-10-17 03:27:30,352][62408] Updated weights for policy 1, policy_version 79220 (0.0009) -[2023-10-17 03:27:30,418][62373] Updated weights for policy 0, policy_version 79790 (0.0007) -[2023-10-17 03:27:30,714][62408] Updated weights for policy 1, policy_version 79230 (0.0009) -[2023-10-17 03:27:30,790][62373] Updated weights for policy 0, policy_version 79800 (0.0008) -[2023-10-17 03:27:32,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 162856960. Throughput: 0: 1755.7, 1: 1757.6. Samples: 40722184. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-17 03:27:32,215][61453] Avg episode reward: [(0, '10.220'), (1, '10.650')] -[2023-10-17 03:27:32,228][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000079232_81133568.pth... -[2023-10-17 03:27:32,228][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000079808_81723392.pth... -[2023-10-17 03:27:32,262][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000077568_79429632.pth -[2023-10-17 03:27:32,269][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000078144_80019456.pth -[2023-10-17 03:27:34,691][62373] Updated weights for policy 0, policy_version 79810 (0.0009) -[2023-10-17 03:27:34,757][62408] Updated weights for policy 1, policy_version 79240 (0.0007) -[2023-10-17 03:27:35,052][62373] Updated weights for policy 0, policy_version 79820 (0.0008) -[2023-10-17 03:27:35,119][62408] Updated weights for policy 1, policy_version 79250 (0.0007) -[2023-10-17 03:27:35,417][62373] Updated weights for policy 0, policy_version 79830 (0.0007) -[2023-10-17 03:27:35,492][62408] Updated weights for policy 1, policy_version 79260 (0.0007) -[2023-10-17 03:27:35,784][62373] Updated weights for policy 0, policy_version 79840 (0.0007) -[2023-10-17 03:27:37,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 162922496. Throughput: 0: 1777.4, 1: 1774.9. Samples: 40733558. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-17 03:27:37,215][61453] Avg episode reward: [(0, '10.250'), (1, '11.120')] -[2023-10-17 03:27:39,337][62408] Updated weights for policy 1, policy_version 79270 (0.0010) -[2023-10-17 03:27:39,568][62373] Updated weights for policy 0, policy_version 79850 (0.0008) -[2023-10-17 03:27:39,721][62408] Updated weights for policy 1, policy_version 79280 (0.0008) -[2023-10-17 03:27:39,947][62373] Updated weights for policy 0, policy_version 79860 (0.0007) -[2023-10-17 03:27:40,098][62408] Updated weights for policy 1, policy_version 79290 (0.0007) -[2023-10-17 03:27:40,327][62373] Updated weights for policy 0, policy_version 79870 (0.0009) -[2023-10-17 03:27:42,214][61453] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 162988032. Throughput: 0: 1758.4, 1: 1757.7. Samples: 40753666. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-17 03:27:42,215][61453] Avg episode reward: [(0, '9.770'), (1, '10.910')] -[2023-10-17 03:27:43,966][62408] Updated weights for policy 1, policy_version 79300 (0.0009) -[2023-10-17 03:27:44,290][62373] Updated weights for policy 0, policy_version 79880 (0.0010) -[2023-10-17 03:27:44,332][62408] Updated weights for policy 1, policy_version 79310 (0.0008) -[2023-10-17 03:27:44,656][62373] Updated weights for policy 0, policy_version 79890 (0.0007) -[2023-10-17 03:27:44,697][62408] Updated weights for policy 1, policy_version 79320 (0.0009) -[2023-10-17 03:27:45,033][62373] Updated weights for policy 0, policy_version 79900 (0.0007) -[2023-10-17 03:27:47,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 163053568. Throughput: 0: 1752.3, 1: 1760.4. Samples: 40775630. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-17 03:27:47,215][61453] Avg episode reward: [(0, '9.050'), (1, '11.000')] -[2023-10-17 03:27:48,523][62408] Updated weights for policy 1, policy_version 79330 (0.0008) -[2023-10-17 03:27:48,862][62373] Updated weights for policy 0, policy_version 79910 (0.0008) -[2023-10-17 03:27:48,886][62408] Updated weights for policy 1, policy_version 79340 (0.0008) -[2023-10-17 03:27:49,226][62373] Updated weights for policy 0, policy_version 79920 (0.0007) -[2023-10-17 03:27:49,249][62408] Updated weights for policy 1, policy_version 79350 (0.0007) -[2023-10-17 03:27:49,598][62373] Updated weights for policy 0, policy_version 79930 (0.0007) -[2023-10-17 03:27:49,613][62408] Updated weights for policy 1, policy_version 79360 (0.0007) -[2023-10-17 03:27:52,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 163119104. Throughput: 0: 1754.9, 1: 1755.3. Samples: 40785254. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-17 03:27:52,215][61453] Avg episode reward: [(0, '9.290'), (1, '11.080')] -[2023-10-17 03:27:53,185][62373] Updated weights for policy 0, policy_version 79940 (0.0009) -[2023-10-17 03:27:53,389][62408] Updated weights for policy 1, policy_version 79370 (0.0008) -[2023-10-17 03:27:53,551][62373] Updated weights for policy 0, policy_version 79950 (0.0009) -[2023-10-17 03:27:53,754][62408] Updated weights for policy 1, policy_version 79380 (0.0007) -[2023-10-17 03:27:53,920][62373] Updated weights for policy 0, policy_version 79960 (0.0007) -[2023-10-17 03:27:54,130][62408] Updated weights for policy 1, policy_version 79390 (0.0008) -[2023-10-17 03:27:57,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 163184640. Throughput: 0: 1771.1, 1: 1756.9. Samples: 40807718. Policy #0 lag: (min: 31.0, avg: 33.9, max: 63.0) -[2023-10-17 03:27:57,215][61453] Avg episode reward: [(0, '9.340'), (1, '11.620')] -[2023-10-17 03:27:57,675][62373] Updated weights for policy 0, policy_version 79970 (0.0009) -[2023-10-17 03:27:58,042][62373] Updated weights for policy 0, policy_version 79980 (0.0010) -[2023-10-17 03:27:58,080][62408] Updated weights for policy 1, policy_version 79400 (0.0008) -[2023-10-17 03:27:58,408][62373] Updated weights for policy 0, policy_version 79990 (0.0008) -[2023-10-17 03:27:58,451][62408] Updated weights for policy 1, policy_version 79410 (0.0008) -[2023-10-17 03:27:58,772][62373] Updated weights for policy 0, policy_version 80000 (0.0009) -[2023-10-17 03:27:58,818][62408] Updated weights for policy 1, policy_version 79420 (0.0008) -[2023-10-17 03:28:02,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 163250176. Throughput: 0: 1784.4, 1: 1782.5. Samples: 40829422. Policy #0 lag: (min: 5.0, avg: 5.6, max: 21.0) -[2023-10-17 03:28:02,215][61453] Avg episode reward: [(0, '9.140'), (1, '11.060')] -[2023-10-17 03:28:02,519][62408] Updated weights for policy 1, policy_version 79430 (0.0007) -[2023-10-17 03:28:02,624][62373] Updated weights for policy 0, policy_version 80010 (0.0007) -[2023-10-17 03:28:02,892][62408] Updated weights for policy 1, policy_version 79440 (0.0007) -[2023-10-17 03:28:02,996][62373] Updated weights for policy 0, policy_version 80020 (0.0007) -[2023-10-17 03:28:03,247][62408] Updated weights for policy 1, policy_version 79450 (0.0008) -[2023-10-17 03:28:03,361][62373] Updated weights for policy 0, policy_version 80030 (0.0008) -[2023-10-17 03:28:07,052][62373] Updated weights for policy 0, policy_version 80040 (0.0007) -[2023-10-17 03:28:07,193][62408] Updated weights for policy 1, policy_version 79460 (0.0009) -[2023-10-17 03:28:07,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 163315712. Throughput: 0: 1766.7, 1: 1751.2. Samples: 40839164. Policy #0 lag: (min: 5.0, avg: 5.6, max: 21.0) -[2023-10-17 03:28:07,215][61453] Avg episode reward: [(0, '8.950'), (1, '10.520')] -[2023-10-17 03:28:07,410][62373] Updated weights for policy 0, policy_version 80050 (0.0007) -[2023-10-17 03:28:07,558][62408] Updated weights for policy 1, policy_version 79470 (0.0009) -[2023-10-17 03:28:07,781][62373] Updated weights for policy 0, policy_version 80060 (0.0007) -[2023-10-17 03:28:07,927][62408] Updated weights for policy 1, policy_version 79480 (0.0007) -[2023-10-17 03:28:11,697][62373] Updated weights for policy 0, policy_version 80070 (0.0009) -[2023-10-17 03:28:11,727][62408] Updated weights for policy 1, policy_version 79490 (0.0009) -[2023-10-17 03:28:12,053][62373] Updated weights for policy 0, policy_version 80080 (0.0008) -[2023-10-17 03:28:12,086][62408] Updated weights for policy 1, policy_version 79500 (0.0007) -[2023-10-17 03:28:12,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 163381248. Throughput: 0: 1774.4, 1: 1765.6. Samples: 40860602. Policy #0 lag: (min: 5.0, avg: 5.6, max: 21.0) -[2023-10-17 03:28:12,215][61453] Avg episode reward: [(0, '9.230'), (1, '10.390')] -[2023-10-17 03:28:12,425][62373] Updated weights for policy 0, policy_version 80090 (0.0009) -[2023-10-17 03:28:12,450][62408] Updated weights for policy 1, policy_version 79510 (0.0009) -[2023-10-17 03:28:12,814][62408] Updated weights for policy 1, policy_version 79520 (0.0008) -[2023-10-17 03:28:16,228][62373] Updated weights for policy 0, policy_version 80100 (0.0008) -[2023-10-17 03:28:16,596][62373] Updated weights for policy 0, policy_version 80110 (0.0007) -[2023-10-17 03:28:16,921][62408] Updated weights for policy 1, policy_version 79530 (0.0008) -[2023-10-17 03:28:16,961][62373] Updated weights for policy 0, policy_version 80120 (0.0008) -[2023-10-17 03:28:17,214][61453] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 13995.8). Total num frames: 163446784. Throughput: 0: 1768.7, 1: 1763.4. Samples: 40881128. Policy #0 lag: (min: 5.0, avg: 5.6, max: 21.0) -[2023-10-17 03:28:17,214][61453] Avg episode reward: [(0, '9.390'), (1, '9.710')] -[2023-10-17 03:28:17,281][62408] Updated weights for policy 1, policy_version 79540 (0.0008) -[2023-10-17 03:28:17,651][62408] Updated weights for policy 1, policy_version 79550 (0.0007) -[2023-10-17 03:28:20,839][62373] Updated weights for policy 0, policy_version 80130 (0.0007) -[2023-10-17 03:28:21,198][62373] Updated weights for policy 0, policy_version 80140 (0.0007) -[2023-10-17 03:28:21,428][62408] Updated weights for policy 1, policy_version 79560 (0.0008) -[2023-10-17 03:28:21,569][62373] Updated weights for policy 0, policy_version 80150 (0.0007) -[2023-10-17 03:28:21,789][62408] Updated weights for policy 1, policy_version 79570 (0.0008) -[2023-10-17 03:28:21,934][62373] Updated weights for policy 0, policy_version 80160 (0.0008) -[2023-10-17 03:28:22,156][62408] Updated weights for policy 1, policy_version 79580 (0.0010) -[2023-10-17 03:28:22,214][61453] Fps is (10 sec: 16384.5, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 163545088. Throughput: 0: 1771.4, 1: 1751.4. Samples: 40892086. Policy #0 lag: (min: 5.0, avg: 5.6, max: 21.0) -[2023-10-17 03:28:22,214][61453] Avg episode reward: [(0, '9.710'), (1, '9.610')] -[2023-10-17 03:28:25,746][62373] Updated weights for policy 0, policy_version 80170 (0.0010) -[2023-10-17 03:28:25,972][62408] Updated weights for policy 1, policy_version 79590 (0.0008) -[2023-10-17 03:28:26,111][62373] Updated weights for policy 0, policy_version 80180 (0.0009) -[2023-10-17 03:28:26,337][62408] Updated weights for policy 1, policy_version 79600 (0.0007) -[2023-10-17 03:28:26,481][62373] Updated weights for policy 0, policy_version 80190 (0.0007) -[2023-10-17 03:28:26,708][62408] Updated weights for policy 1, policy_version 79610 (0.0008) -[2023-10-17 03:28:27,214][61453] Fps is (10 sec: 19660.4, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 163643392. Throughput: 0: 1780.2, 1: 1767.9. Samples: 40913330. Policy #0 lag: (min: 5.0, avg: 5.6, max: 21.0) -[2023-10-17 03:28:27,215][61453] Avg episode reward: [(0, '10.870'), (1, '10.530')] -[2023-10-17 03:28:30,109][62373] Updated weights for policy 0, policy_version 80200 (0.0007) -[2023-10-17 03:28:30,484][62373] Updated weights for policy 0, policy_version 80210 (0.0009) -[2023-10-17 03:28:30,543][62408] Updated weights for policy 1, policy_version 79620 (0.0009) -[2023-10-17 03:28:30,851][62373] Updated weights for policy 0, policy_version 80220 (0.0008) -[2023-10-17 03:28:30,901][62408] Updated weights for policy 1, policy_version 79630 (0.0008) -[2023-10-17 03:28:31,268][62408] Updated weights for policy 1, policy_version 79640 (0.0007) -[2023-10-17 03:28:32,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 163708928. Throughput: 0: 1770.0, 1: 1736.4. Samples: 40933416. Policy #0 lag: (min: 5.0, avg: 5.6, max: 21.0) -[2023-10-17 03:28:32,215][61453] Avg episode reward: [(0, '10.320'), (1, '9.840')] -[2023-10-17 03:28:34,862][62373] Updated weights for policy 0, policy_version 80230 (0.0007) -[2023-10-17 03:28:35,227][62373] Updated weights for policy 0, policy_version 80240 (0.0008) -[2023-10-17 03:28:35,307][62408] Updated weights for policy 1, policy_version 79650 (0.0009) -[2023-10-17 03:28:35,592][62373] Updated weights for policy 0, policy_version 80250 (0.0009) -[2023-10-17 03:28:35,682][62408] Updated weights for policy 1, policy_version 79660 (0.0009) -[2023-10-17 03:28:36,038][62408] Updated weights for policy 1, policy_version 79670 (0.0009) -[2023-10-17 03:28:36,409][62408] Updated weights for policy 1, policy_version 79680 (0.0009) -[2023-10-17 03:28:37,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 163774464. Throughput: 0: 1788.8, 1: 1770.8. Samples: 40945436. Policy #0 lag: (min: 5.0, avg: 5.6, max: 21.0) -[2023-10-17 03:28:37,215][61453] Avg episode reward: [(0, '10.030'), (1, '10.680')] -[2023-10-17 03:28:39,258][62373] Updated weights for policy 0, policy_version 80260 (0.0008) -[2023-10-17 03:28:39,631][62373] Updated weights for policy 0, policy_version 80270 (0.0007) -[2023-10-17 03:28:40,001][62373] Updated weights for policy 0, policy_version 80280 (0.0007) -[2023-10-17 03:28:40,276][62408] Updated weights for policy 1, policy_version 79690 (0.0007) -[2023-10-17 03:28:40,647][62408] Updated weights for policy 1, policy_version 79700 (0.0010) -[2023-10-17 03:28:41,007][62408] Updated weights for policy 1, policy_version 79710 (0.0010) -[2023-10-17 03:28:42,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 163840000. Throughput: 0: 1756.9, 1: 1748.7. Samples: 40965470. Policy #0 lag: (min: 5.0, avg: 5.6, max: 21.0) -[2023-10-17 03:28:42,215][61453] Avg episode reward: [(0, '10.510'), (1, '10.880')] -[2023-10-17 03:28:44,015][62373] Updated weights for policy 0, policy_version 80290 (0.0007) -[2023-10-17 03:28:44,385][62373] Updated weights for policy 0, policy_version 80300 (0.0008) -[2023-10-17 03:28:44,749][62373] Updated weights for policy 0, policy_version 80310 (0.0008) -[2023-10-17 03:28:44,829][62408] Updated weights for policy 1, policy_version 79720 (0.0008) -[2023-10-17 03:28:45,113][62373] Updated weights for policy 0, policy_version 80320 (0.0007) -[2023-10-17 03:28:45,196][62408] Updated weights for policy 1, policy_version 79730 (0.0008) -[2023-10-17 03:28:45,566][62408] Updated weights for policy 1, policy_version 79740 (0.0008) -[2023-10-17 03:28:47,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 163905536. Throughput: 0: 1759.4, 1: 1746.8. Samples: 40987202. Policy #0 lag: (min: 5.0, avg: 5.6, max: 21.0) -[2023-10-17 03:28:47,215][61453] Avg episode reward: [(0, '10.730'), (1, '10.330')] -[2023-10-17 03:28:48,865][62373] Updated weights for policy 0, policy_version 80330 (0.0008) -[2023-10-17 03:28:49,232][62373] Updated weights for policy 0, policy_version 80340 (0.0007) -[2023-10-17 03:28:49,274][62408] Updated weights for policy 1, policy_version 79750 (0.0008) -[2023-10-17 03:28:49,599][62373] Updated weights for policy 0, policy_version 80350 (0.0007) -[2023-10-17 03:28:49,642][62408] Updated weights for policy 1, policy_version 79760 (0.0008) -[2023-10-17 03:28:50,008][62408] Updated weights for policy 1, policy_version 79770 (0.0008) -[2023-10-17 03:28:52,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 163971072. Throughput: 0: 1756.4, 1: 1759.8. Samples: 40997392. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:28:52,215][61453] Avg episode reward: [(0, '10.390'), (1, '10.680')] -[2023-10-17 03:28:53,405][62373] Updated weights for policy 0, policy_version 80360 (0.0009) -[2023-10-17 03:28:53,601][62408] Updated weights for policy 1, policy_version 79780 (0.0008) -[2023-10-17 03:28:53,773][62373] Updated weights for policy 0, policy_version 80370 (0.0007) -[2023-10-17 03:28:53,968][62408] Updated weights for policy 1, policy_version 79790 (0.0008) -[2023-10-17 03:28:54,147][62373] Updated weights for policy 0, policy_version 80380 (0.0008) -[2023-10-17 03:28:54,336][62408] Updated weights for policy 1, policy_version 79800 (0.0007) -[2023-10-17 03:28:57,214][61453] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 164036608. Throughput: 0: 1762.9, 1: 1750.2. Samples: 41018692. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:28:57,214][61453] Avg episode reward: [(0, '10.790'), (1, '10.610')] -[2023-10-17 03:28:57,917][62373] Updated weights for policy 0, policy_version 80390 (0.0009) -[2023-10-17 03:28:58,239][62408] Updated weights for policy 1, policy_version 79810 (0.0007) -[2023-10-17 03:28:58,290][62373] Updated weights for policy 0, policy_version 80400 (0.0009) -[2023-10-17 03:28:58,604][62408] Updated weights for policy 1, policy_version 79820 (0.0008) -[2023-10-17 03:28:58,655][62373] Updated weights for policy 0, policy_version 80410 (0.0007) -[2023-10-17 03:28:58,967][62408] Updated weights for policy 1, policy_version 79830 (0.0008) -[2023-10-17 03:28:59,343][62408] Updated weights for policy 1, policy_version 79840 (0.0009) -[2023-10-17 03:29:02,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 164102144. Throughput: 0: 1786.6, 1: 1763.0. Samples: 41040860. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:29:02,215][61453] Avg episode reward: [(0, '9.970'), (1, '10.740')] -[2023-10-17 03:29:02,502][62373] Updated weights for policy 0, policy_version 80420 (0.0008) -[2023-10-17 03:29:02,886][62373] Updated weights for policy 0, policy_version 80430 (0.0008) -[2023-10-17 03:29:03,248][62373] Updated weights for policy 0, policy_version 80440 (0.0007) -[2023-10-17 03:29:03,318][62408] Updated weights for policy 1, policy_version 79850 (0.0008) -[2023-10-17 03:29:03,696][62408] Updated weights for policy 1, policy_version 79860 (0.0009) -[2023-10-17 03:29:04,065][62408] Updated weights for policy 1, policy_version 79870 (0.0008) -[2023-10-17 03:29:07,053][62373] Updated weights for policy 0, policy_version 80450 (0.0010) -[2023-10-17 03:29:07,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 164167680. Throughput: 0: 1762.3, 1: 1753.2. Samples: 41050286. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:29:07,215][61453] Avg episode reward: [(0, '10.370'), (1, '10.920')] -[2023-10-17 03:29:07,419][62373] Updated weights for policy 0, policy_version 80460 (0.0008) -[2023-10-17 03:29:07,789][62373] Updated weights for policy 0, policy_version 80470 (0.0007) -[2023-10-17 03:29:07,873][62408] Updated weights for policy 1, policy_version 79880 (0.0007) -[2023-10-17 03:29:08,160][62373] Updated weights for policy 0, policy_version 80480 (0.0008) -[2023-10-17 03:29:08,238][62408] Updated weights for policy 1, policy_version 79890 (0.0007) -[2023-10-17 03:29:08,609][62408] Updated weights for policy 1, policy_version 79900 (0.0007) -[2023-10-17 03:29:11,835][62373] Updated weights for policy 0, policy_version 80490 (0.0011) -[2023-10-17 03:29:12,206][62373] Updated weights for policy 0, policy_version 80500 (0.0011) -[2023-10-17 03:29:12,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 164233216. Throughput: 0: 1780.9, 1: 1759.7. Samples: 41072654. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:29:12,214][61453] Avg episode reward: [(0, '9.990'), (1, '10.880')] -[2023-10-17 03:29:12,525][62408] Updated weights for policy 1, policy_version 79910 (0.0007) -[2023-10-17 03:29:12,573][62373] Updated weights for policy 0, policy_version 80510 (0.0009) -[2023-10-17 03:29:12,890][62408] Updated weights for policy 1, policy_version 79920 (0.0008) -[2023-10-17 03:29:13,263][62408] Updated weights for policy 1, policy_version 79930 (0.0009) -[2023-10-17 03:29:16,514][62373] Updated weights for policy 0, policy_version 80520 (0.0008) -[2023-10-17 03:29:16,879][62373] Updated weights for policy 0, policy_version 80530 (0.0008) -[2023-10-17 03:29:17,168][62408] Updated weights for policy 1, policy_version 79940 (0.0007) -[2023-10-17 03:29:17,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 164298752. Throughput: 0: 1777.8, 1: 1784.7. Samples: 41093726. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:29:17,214][61453] Avg episode reward: [(0, '10.300'), (1, '10.870')] -[2023-10-17 03:29:17,252][62373] Updated weights for policy 0, policy_version 80540 (0.0009) -[2023-10-17 03:29:17,539][62408] Updated weights for policy 1, policy_version 79950 (0.0008) -[2023-10-17 03:29:17,907][62408] Updated weights for policy 1, policy_version 79960 (0.0010) -[2023-10-17 03:29:21,057][62373] Updated weights for policy 0, policy_version 80550 (0.0009) -[2023-10-17 03:29:21,428][62373] Updated weights for policy 0, policy_version 80560 (0.0007) -[2023-10-17 03:29:21,726][62408] Updated weights for policy 1, policy_version 79970 (0.0010) -[2023-10-17 03:29:21,803][62373] Updated weights for policy 0, policy_version 80570 (0.0008) -[2023-10-17 03:29:22,104][62408] Updated weights for policy 1, policy_version 79980 (0.0009) -[2023-10-17 03:29:22,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 164397056. Throughput: 0: 1775.8, 1: 1749.8. Samples: 41104086. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:29:22,215][61453] Avg episode reward: [(0, '10.090'), (1, '11.670')] -[2023-10-17 03:29:22,485][62408] Updated weights for policy 1, policy_version 79990 (0.0010) -[2023-10-17 03:29:22,854][62408] Updated weights for policy 1, policy_version 80000 (0.0009) -[2023-10-17 03:29:25,465][62373] Updated weights for policy 0, policy_version 80580 (0.0007) -[2023-10-17 03:29:25,835][62373] Updated weights for policy 0, policy_version 80590 (0.0007) -[2023-10-17 03:29:26,201][62373] Updated weights for policy 0, policy_version 80600 (0.0008) -[2023-10-17 03:29:26,647][62408] Updated weights for policy 1, policy_version 80010 (0.0007) -[2023-10-17 03:29:27,017][62408] Updated weights for policy 1, policy_version 80020 (0.0007) -[2023-10-17 03:29:27,214][61453] Fps is (10 sec: 16383.7, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 164462592. Throughput: 0: 1783.5, 1: 1777.2. Samples: 41125700. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:29:27,215][61453] Avg episode reward: [(0, '10.230'), (1, '11.440')] -[2023-10-17 03:29:27,374][62408] Updated weights for policy 1, policy_version 80030 (0.0008) -[2023-10-17 03:29:29,968][62373] Updated weights for policy 0, policy_version 80610 (0.0007) -[2023-10-17 03:29:30,329][62373] Updated weights for policy 0, policy_version 80620 (0.0007) -[2023-10-17 03:29:30,702][62373] Updated weights for policy 0, policy_version 80630 (0.0008) -[2023-10-17 03:29:31,066][62373] Updated weights for policy 0, policy_version 80640 (0.0009) -[2023-10-17 03:29:31,259][62408] Updated weights for policy 1, policy_version 80040 (0.0008) -[2023-10-17 03:29:31,617][62408] Updated weights for policy 1, policy_version 80050 (0.0007) -[2023-10-17 03:29:31,997][62408] Updated weights for policy 1, policy_version 80060 (0.0008) -[2023-10-17 03:29:32,214][61453] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 164560896. Throughput: 0: 1773.5, 1: 1757.1. Samples: 41146078. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:29:32,214][61453] Avg episode reward: [(0, '9.510'), (1, '11.570')] -[2023-10-17 03:29:32,225][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000080640_82575360.pth... -[2023-10-17 03:29:32,225][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000080064_81985536.pth... -[2023-10-17 03:29:32,261][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000078400_80281600.pth -[2023-10-17 03:29:32,261][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000078976_80871424.pth -[2023-10-17 03:29:34,651][62373] Updated weights for policy 0, policy_version 80650 (0.0007) -[2023-10-17 03:29:35,020][62373] Updated weights for policy 0, policy_version 80660 (0.0008) -[2023-10-17 03:29:35,389][62373] Updated weights for policy 0, policy_version 80670 (0.0008) -[2023-10-17 03:29:35,836][62408] Updated weights for policy 1, policy_version 80070 (0.0009) -[2023-10-17 03:29:36,213][62408] Updated weights for policy 1, policy_version 80080 (0.0009) -[2023-10-17 03:29:36,581][62408] Updated weights for policy 1, policy_version 80090 (0.0007) -[2023-10-17 03:29:37,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 164626432. Throughput: 0: 1793.3, 1: 1760.9. Samples: 41157332. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:29:37,215][61453] Avg episode reward: [(0, '9.710'), (1, '11.810')] -[2023-10-17 03:29:39,294][62373] Updated weights for policy 0, policy_version 80680 (0.0010) -[2023-10-17 03:29:39,655][62373] Updated weights for policy 0, policy_version 80690 (0.0011) -[2023-10-17 03:29:40,035][62373] Updated weights for policy 0, policy_version 80700 (0.0010) -[2023-10-17 03:29:40,427][62408] Updated weights for policy 1, policy_version 80100 (0.0007) -[2023-10-17 03:29:40,799][62408] Updated weights for policy 1, policy_version 80110 (0.0009) -[2023-10-17 03:29:41,166][62408] Updated weights for policy 1, policy_version 80120 (0.0008) -[2023-10-17 03:29:42,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 164691968. Throughput: 0: 1776.5, 1: 1764.5. Samples: 41178038. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:29:42,214][61453] Avg episode reward: [(0, '9.250'), (1, '11.530')] -[2023-10-17 03:29:43,924][62373] Updated weights for policy 0, policy_version 80710 (0.0009) -[2023-10-17 03:29:44,295][62373] Updated weights for policy 0, policy_version 80720 (0.0009) -[2023-10-17 03:29:44,652][62373] Updated weights for policy 0, policy_version 80730 (0.0009) -[2023-10-17 03:29:44,851][62408] Updated weights for policy 1, policy_version 80130 (0.0007) -[2023-10-17 03:29:45,221][62408] Updated weights for policy 1, policy_version 80140 (0.0010) -[2023-10-17 03:29:45,587][62408] Updated weights for policy 1, policy_version 80150 (0.0010) -[2023-10-17 03:29:45,967][62408] Updated weights for policy 1, policy_version 80160 (0.0011) -[2023-10-17 03:29:47,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 164757504. Throughput: 0: 1780.9, 1: 1751.2. Samples: 41199804. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:29:47,214][61453] Avg episode reward: [(0, '10.080'), (1, '10.560')] -[2023-10-17 03:29:48,346][62373] Updated weights for policy 0, policy_version 80740 (0.0009) -[2023-10-17 03:29:48,730][62373] Updated weights for policy 0, policy_version 80750 (0.0008) -[2023-10-17 03:29:49,097][62373] Updated weights for policy 0, policy_version 80760 (0.0010) -[2023-10-17 03:29:49,729][62408] Updated weights for policy 1, policy_version 80170 (0.0008) -[2023-10-17 03:29:50,097][62408] Updated weights for policy 1, policy_version 80180 (0.0007) -[2023-10-17 03:29:50,457][62408] Updated weights for policy 1, policy_version 80190 (0.0008) -[2023-10-17 03:29:52,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 164823040. Throughput: 0: 1781.7, 1: 1774.9. Samples: 41210334. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:29:52,214][61453] Avg episode reward: [(0, '9.100'), (1, '10.770')] -[2023-10-17 03:29:52,783][62373] Updated weights for policy 0, policy_version 80770 (0.0008) -[2023-10-17 03:29:53,150][62373] Updated weights for policy 0, policy_version 80780 (0.0007) -[2023-10-17 03:29:53,520][62373] Updated weights for policy 0, policy_version 80790 (0.0008) -[2023-10-17 03:29:53,895][62373] Updated weights for policy 0, policy_version 80800 (0.0008) -[2023-10-17 03:29:54,187][62408] Updated weights for policy 1, policy_version 80200 (0.0008) -[2023-10-17 03:29:54,564][62408] Updated weights for policy 1, policy_version 80210 (0.0010) -[2023-10-17 03:29:54,922][62408] Updated weights for policy 1, policy_version 80220 (0.0009) -[2023-10-17 03:29:57,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 164888576. Throughput: 0: 1781.5, 1: 1756.4. Samples: 41231860. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:29:57,215][61453] Avg episode reward: [(0, '9.200'), (1, '11.060')] -[2023-10-17 03:29:57,733][62373] Updated weights for policy 0, policy_version 80810 (0.0009) -[2023-10-17 03:29:58,098][62373] Updated weights for policy 0, policy_version 80820 (0.0007) -[2023-10-17 03:29:58,458][62373] Updated weights for policy 0, policy_version 80830 (0.0008) -[2023-10-17 03:29:58,640][62408] Updated weights for policy 1, policy_version 80230 (0.0008) -[2023-10-17 03:29:59,014][62408] Updated weights for policy 1, policy_version 80240 (0.0008) -[2023-10-17 03:29:59,376][62408] Updated weights for policy 1, policy_version 80250 (0.0007) -[2023-10-17 03:30:02,163][62373] Updated weights for policy 0, policy_version 80840 (0.0007) -[2023-10-17 03:30:02,214][61453] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 164954112. Throughput: 0: 1799.0, 1: 1761.2. Samples: 41253936. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:30:02,215][61453] Avg episode reward: [(0, '10.000'), (1, '11.120')] -[2023-10-17 03:30:02,531][62373] Updated weights for policy 0, policy_version 80850 (0.0007) -[2023-10-17 03:30:02,908][62373] Updated weights for policy 0, policy_version 80860 (0.0009) -[2023-10-17 03:30:03,219][62408] Updated weights for policy 1, policy_version 80260 (0.0010) -[2023-10-17 03:30:03,591][62408] Updated weights for policy 1, policy_version 80270 (0.0010) -[2023-10-17 03:30:03,958][62408] Updated weights for policy 1, policy_version 80280 (0.0009) -[2023-10-17 03:30:06,800][62373] Updated weights for policy 0, policy_version 80870 (0.0009) -[2023-10-17 03:30:07,171][62373] Updated weights for policy 0, policy_version 80880 (0.0008) -[2023-10-17 03:30:07,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 165019648. Throughput: 0: 1781.3, 1: 1765.0. Samples: 41263672. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:30:07,215][61453] Avg episode reward: [(0, '11.420'), (1, '11.560')] -[2023-10-17 03:30:07,538][62373] Updated weights for policy 0, policy_version 80890 (0.0007) -[2023-10-17 03:30:07,898][62408] Updated weights for policy 1, policy_version 80290 (0.0011) -[2023-10-17 03:30:08,268][62408] Updated weights for policy 1, policy_version 80300 (0.0010) -[2023-10-17 03:30:08,633][62408] Updated weights for policy 1, policy_version 80310 (0.0007) -[2023-10-17 03:30:09,007][62408] Updated weights for policy 1, policy_version 80320 (0.0007) -[2023-10-17 03:30:11,489][62373] Updated weights for policy 0, policy_version 80900 (0.0008) -[2023-10-17 03:30:11,865][62373] Updated weights for policy 0, policy_version 80910 (0.0008) -[2023-10-17 03:30:12,214][61453] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 165085184. Throughput: 0: 1791.2, 1: 1759.4. Samples: 41285478. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:30:12,214][61453] Avg episode reward: [(0, '10.390'), (1, '11.310')] -[2023-10-17 03:30:12,232][62373] Updated weights for policy 0, policy_version 80920 (0.0008) -[2023-10-17 03:30:12,878][62408] Updated weights for policy 1, policy_version 80330 (0.0011) -[2023-10-17 03:30:13,252][62408] Updated weights for policy 1, policy_version 80340 (0.0009) -[2023-10-17 03:30:13,625][62408] Updated weights for policy 1, policy_version 80350 (0.0007) -[2023-10-17 03:30:16,088][62373] Updated weights for policy 0, policy_version 80930 (0.0009) -[2023-10-17 03:30:16,452][62373] Updated weights for policy 0, policy_version 80940 (0.0010) -[2023-10-17 03:30:16,818][62373] Updated weights for policy 0, policy_version 80950 (0.0009) -[2023-10-17 03:30:17,188][62373] Updated weights for policy 0, policy_version 80960 (0.0008) -[2023-10-17 03:30:17,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14106.9). Total num frames: 165183488. Throughput: 0: 1775.8, 1: 1786.9. Samples: 41306398. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:30:17,215][61453] Avg episode reward: [(0, '10.620'), (1, '11.520')] -[2023-10-17 03:30:17,427][62408] Updated weights for policy 1, policy_version 80360 (0.0007) -[2023-10-17 03:30:17,807][62408] Updated weights for policy 1, policy_version 80370 (0.0010) -[2023-10-17 03:30:18,170][62408] Updated weights for policy 1, policy_version 80380 (0.0009) -[2023-10-17 03:30:21,021][62373] Updated weights for policy 0, policy_version 80970 (0.0010) -[2023-10-17 03:30:21,399][62373] Updated weights for policy 0, policy_version 80980 (0.0010) -[2023-10-17 03:30:21,771][62373] Updated weights for policy 0, policy_version 80990 (0.0009) -[2023-10-17 03:30:21,961][62408] Updated weights for policy 1, policy_version 80390 (0.0007) -[2023-10-17 03:30:22,214][61453] Fps is (10 sec: 16383.6, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 165249024. Throughput: 0: 1781.3, 1: 1773.0. Samples: 41317276. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:30:22,215][61453] Avg episode reward: [(0, '9.950'), (1, '11.550')] -[2023-10-17 03:30:22,330][62408] Updated weights for policy 1, policy_version 80400 (0.0008) -[2023-10-17 03:30:22,700][62408] Updated weights for policy 1, policy_version 80410 (0.0008) -[2023-10-17 03:30:25,601][62373] Updated weights for policy 0, policy_version 81000 (0.0010) -[2023-10-17 03:30:25,973][62373] Updated weights for policy 0, policy_version 81010 (0.0010) -[2023-10-17 03:30:26,344][62373] Updated weights for policy 0, policy_version 81020 (0.0008) -[2023-10-17 03:30:26,534][62408] Updated weights for policy 1, policy_version 80420 (0.0010) -[2023-10-17 03:30:26,901][62408] Updated weights for policy 1, policy_version 80430 (0.0009) -[2023-10-17 03:30:27,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 165314560. Throughput: 0: 1781.3, 1: 1784.4. Samples: 41338496. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:30:27,214][61453] Avg episode reward: [(0, '10.660'), (1, '11.840')] -[2023-10-17 03:30:27,268][62408] Updated weights for policy 1, policy_version 80440 (0.0010) -[2023-10-17 03:30:30,142][62373] Updated weights for policy 0, policy_version 81030 (0.0010) -[2023-10-17 03:30:30,516][62373] Updated weights for policy 0, policy_version 81040 (0.0009) -[2023-10-17 03:30:30,877][62373] Updated weights for policy 0, policy_version 81050 (0.0010) -[2023-10-17 03:30:31,114][62408] Updated weights for policy 1, policy_version 80450 (0.0009) -[2023-10-17 03:30:31,492][62408] Updated weights for policy 1, policy_version 80460 (0.0009) -[2023-10-17 03:30:31,856][62408] Updated weights for policy 1, policy_version 80470 (0.0008) -[2023-10-17 03:30:32,214][61453] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 165380096. Throughput: 0: 1756.8, 1: 1775.1. Samples: 41358740. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-17 03:30:32,215][61453] Avg episode reward: [(0, '10.830'), (1, '11.100')] -[2023-10-17 03:30:32,228][62408] Updated weights for policy 1, policy_version 80480 (0.0007) -[2023-10-17 03:30:34,723][62373] Updated weights for policy 0, policy_version 81060 (0.0007) -[2023-10-17 03:30:35,087][62373] Updated weights for policy 0, policy_version 81070 (0.0008) -[2023-10-17 03:30:35,460][62373] Updated weights for policy 0, policy_version 81080 (0.0008) -[2023-10-17 03:30:36,077][62408] Updated weights for policy 1, policy_version 80490 (0.0008) -[2023-10-17 03:30:36,456][62408] Updated weights for policy 1, policy_version 80500 (0.0008) -[2023-10-17 03:30:36,812][62408] Updated weights for policy 1, policy_version 80510 (0.0008) -[2023-10-17 03:30:37,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 165478400. Throughput: 0: 1778.3, 1: 1776.0. Samples: 41370274. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-17 03:30:37,214][61453] Avg episode reward: [(0, '10.030'), (1, '11.190')] -[2023-10-17 03:30:39,401][62373] Updated weights for policy 0, policy_version 81090 (0.0008) -[2023-10-17 03:30:39,776][62373] Updated weights for policy 0, policy_version 81100 (0.0009) -[2023-10-17 03:30:40,139][62373] Updated weights for policy 0, policy_version 81110 (0.0008) -[2023-10-17 03:30:40,509][62373] Updated weights for policy 0, policy_version 81120 (0.0008) -[2023-10-17 03:30:40,626][62408] Updated weights for policy 1, policy_version 80520 (0.0008) -[2023-10-17 03:30:40,991][62408] Updated weights for policy 1, policy_version 80530 (0.0011) -[2023-10-17 03:30:41,367][62408] Updated weights for policy 1, policy_version 80540 (0.0009) -[2023-10-17 03:30:42,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 165543936. Throughput: 0: 1745.5, 1: 1771.5. Samples: 41390126. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-17 03:30:42,215][61453] Avg episode reward: [(0, '9.980'), (1, '11.570')] -[2023-10-17 03:30:44,208][62373] Updated weights for policy 0, policy_version 81130 (0.0008) -[2023-10-17 03:30:44,583][62373] Updated weights for policy 0, policy_version 81140 (0.0009) -[2023-10-17 03:30:44,949][62373] Updated weights for policy 0, policy_version 81150 (0.0009) -[2023-10-17 03:30:45,228][62408] Updated weights for policy 1, policy_version 80550 (0.0008) -[2023-10-17 03:30:45,596][62408] Updated weights for policy 1, policy_version 80560 (0.0007) -[2023-10-17 03:30:45,959][62408] Updated weights for policy 1, policy_version 80570 (0.0007) -[2023-10-17 03:30:47,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 165609472. Throughput: 0: 1746.8, 1: 1754.3. Samples: 41411484. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-17 03:30:47,214][61453] Avg episode reward: [(0, '10.670'), (1, '11.630')] -[2023-10-17 03:30:48,774][62373] Updated weights for policy 0, policy_version 81160 (0.0011) -[2023-10-17 03:30:49,148][62373] Updated weights for policy 0, policy_version 81170 (0.0010) -[2023-10-17 03:30:49,518][62373] Updated weights for policy 0, policy_version 81180 (0.0011) -[2023-10-17 03:30:49,950][62408] Updated weights for policy 1, policy_version 80580 (0.0008) -[2023-10-17 03:30:50,322][62408] Updated weights for policy 1, policy_version 80590 (0.0007) -[2023-10-17 03:30:50,689][62408] Updated weights for policy 1, policy_version 80600 (0.0009) -[2023-10-17 03:30:52,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 165675008. Throughput: 0: 1743.7, 1: 1782.5. Samples: 41422348. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-17 03:30:52,214][61453] Avg episode reward: [(0, '11.240'), (1, '11.310')] -[2023-10-17 03:30:53,345][62373] Updated weights for policy 0, policy_version 81190 (0.0010) -[2023-10-17 03:30:53,711][62373] Updated weights for policy 0, policy_version 81200 (0.0010) -[2023-10-17 03:30:54,081][62373] Updated weights for policy 0, policy_version 81210 (0.0008) -[2023-10-17 03:30:54,470][62408] Updated weights for policy 1, policy_version 80610 (0.0009) -[2023-10-17 03:30:54,842][62408] Updated weights for policy 1, policy_version 80620 (0.0008) -[2023-10-17 03:30:55,205][62408] Updated weights for policy 1, policy_version 80630 (0.0008) -[2023-10-17 03:30:55,569][62408] Updated weights for policy 1, policy_version 80640 (0.0007) -[2023-10-17 03:30:57,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 165740544. Throughput: 0: 1751.7, 1: 1754.7. Samples: 41443266. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-17 03:30:57,215][61453] Avg episode reward: [(0, '11.000'), (1, '11.160')] -[2023-10-17 03:30:57,814][62373] Updated weights for policy 0, policy_version 81220 (0.0008) -[2023-10-17 03:30:58,186][62373] Updated weights for policy 0, policy_version 81230 (0.0010) -[2023-10-17 03:30:58,555][62373] Updated weights for policy 0, policy_version 81240 (0.0008) -[2023-10-17 03:30:59,298][62408] Updated weights for policy 1, policy_version 80650 (0.0010) -[2023-10-17 03:30:59,654][62408] Updated weights for policy 1, policy_version 80660 (0.0009) -[2023-10-17 03:31:00,024][62408] Updated weights for policy 1, policy_version 80670 (0.0008) -[2023-10-17 03:31:02,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 165806080. Throughput: 0: 1779.4, 1: 1755.3. Samples: 41465462. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-17 03:31:02,215][61453] Avg episode reward: [(0, '11.200'), (1, '11.320')] -[2023-10-17 03:31:02,391][62373] Updated weights for policy 0, policy_version 81250 (0.0008) -[2023-10-17 03:31:02,765][62373] Updated weights for policy 0, policy_version 81260 (0.0008) -[2023-10-17 03:31:03,138][62373] Updated weights for policy 0, policy_version 81270 (0.0008) -[2023-10-17 03:31:03,508][62373] Updated weights for policy 0, policy_version 81280 (0.0008) -[2023-10-17 03:31:03,870][62408] Updated weights for policy 1, policy_version 80680 (0.0009) -[2023-10-17 03:31:04,232][62408] Updated weights for policy 1, policy_version 80690 (0.0008) -[2023-10-17 03:31:04,603][62408] Updated weights for policy 1, policy_version 80700 (0.0008) -[2023-10-17 03:31:07,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 165871616. Throughput: 0: 1753.9, 1: 1755.4. Samples: 41475194. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-17 03:31:07,215][61453] Avg episode reward: [(0, '11.700'), (1, '11.730')] -[2023-10-17 03:31:07,237][62373] Updated weights for policy 0, policy_version 81290 (0.0008) -[2023-10-17 03:31:07,597][62373] Updated weights for policy 0, policy_version 81300 (0.0007) -[2023-10-17 03:31:07,961][62373] Updated weights for policy 0, policy_version 81310 (0.0010) -[2023-10-17 03:31:08,296][62408] Updated weights for policy 1, policy_version 80710 (0.0008) -[2023-10-17 03:31:08,655][62408] Updated weights for policy 1, policy_version 80720 (0.0008) -[2023-10-17 03:31:09,019][62408] Updated weights for policy 1, policy_version 80730 (0.0010) -[2023-10-17 03:31:11,906][62373] Updated weights for policy 0, policy_version 81320 (0.0009) -[2023-10-17 03:31:12,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 165937152. Throughput: 0: 1776.1, 1: 1758.5. Samples: 41497554. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-17 03:31:12,214][61453] Avg episode reward: [(0, '11.400'), (1, '12.810')] -[2023-10-17 03:31:12,215][62252] Saving new best policy, reward=12.810! -[2023-10-17 03:31:12,280][62373] Updated weights for policy 0, policy_version 81330 (0.0008) -[2023-10-17 03:31:12,654][62373] Updated weights for policy 0, policy_version 81340 (0.0009) -[2023-10-17 03:31:12,906][62408] Updated weights for policy 1, policy_version 80740 (0.0010) -[2023-10-17 03:31:13,275][62408] Updated weights for policy 1, policy_version 80750 (0.0008) -[2023-10-17 03:31:13,638][62408] Updated weights for policy 1, policy_version 80760 (0.0007) -[2023-10-17 03:31:16,485][62373] Updated weights for policy 0, policy_version 81350 (0.0007) -[2023-10-17 03:31:16,859][62373] Updated weights for policy 0, policy_version 81360 (0.0007) -[2023-10-17 03:31:17,214][61453] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 13995.8). Total num frames: 166002688. Throughput: 0: 1776.0, 1: 1776.6. Samples: 41518606. Policy #0 lag: (min: 31.0, avg: 31.1, max: 37.0) -[2023-10-17 03:31:17,215][61453] Avg episode reward: [(0, '11.090'), (1, '12.290')] -[2023-10-17 03:31:17,227][62373] Updated weights for policy 0, policy_version 81370 (0.0010) -[2023-10-17 03:31:17,514][62408] Updated weights for policy 1, policy_version 80770 (0.0009) -[2023-10-17 03:31:17,889][62408] Updated weights for policy 1, policy_version 80780 (0.0009) -[2023-10-17 03:31:18,261][62408] Updated weights for policy 1, policy_version 80790 (0.0011) -[2023-10-17 03:31:18,625][62408] Updated weights for policy 1, policy_version 80800 (0.0008) -[2023-10-17 03:31:20,977][62373] Updated weights for policy 0, policy_version 81380 (0.0008) -[2023-10-17 03:31:21,351][62373] Updated weights for policy 0, policy_version 81390 (0.0007) -[2023-10-17 03:31:21,715][62373] Updated weights for policy 0, policy_version 81400 (0.0008) -[2023-10-17 03:31:22,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 166100992. Throughput: 0: 1772.2, 1: 1755.1. Samples: 41529002. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:31:22,214][61453] Avg episode reward: [(0, '11.050'), (1, '12.020')] -[2023-10-17 03:31:22,562][62408] Updated weights for policy 1, policy_version 80810 (0.0009) -[2023-10-17 03:31:22,927][62408] Updated weights for policy 1, policy_version 80820 (0.0008) -[2023-10-17 03:31:23,298][62408] Updated weights for policy 1, policy_version 80830 (0.0010) -[2023-10-17 03:31:25,427][62373] Updated weights for policy 0, policy_version 81410 (0.0009) -[2023-10-17 03:31:25,798][62373] Updated weights for policy 0, policy_version 81420 (0.0008) -[2023-10-17 03:31:26,159][62373] Updated weights for policy 0, policy_version 81430 (0.0008) -[2023-10-17 03:31:26,524][62373] Updated weights for policy 0, policy_version 81440 (0.0007) -[2023-10-17 03:31:26,997][62408] Updated weights for policy 1, policy_version 80840 (0.0009) -[2023-10-17 03:31:27,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 166166528. Throughput: 0: 1790.0, 1: 1775.2. Samples: 41550564. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:31:27,215][61453] Avg episode reward: [(0, '11.060'), (1, '11.830')] -[2023-10-17 03:31:27,368][62408] Updated weights for policy 1, policy_version 80850 (0.0008) -[2023-10-17 03:31:27,732][62408] Updated weights for policy 1, policy_version 80860 (0.0007) -[2023-10-17 03:31:30,322][62373] Updated weights for policy 0, policy_version 81450 (0.0010) -[2023-10-17 03:31:30,687][62373] Updated weights for policy 0, policy_version 81460 (0.0010) -[2023-10-17 03:31:31,065][62373] Updated weights for policy 0, policy_version 81470 (0.0009) -[2023-10-17 03:31:31,533][62408] Updated weights for policy 1, policy_version 80870 (0.0008) -[2023-10-17 03:31:31,896][62408] Updated weights for policy 1, policy_version 80880 (0.0007) -[2023-10-17 03:31:32,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 166232064. Throughput: 0: 1777.6, 1: 1779.1. Samples: 41571540. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:31:32,215][61453] Avg episode reward: [(0, '10.650'), (1, '11.630')] -[2023-10-17 03:31:32,225][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000081472_83427328.pth... -[2023-10-17 03:31:32,264][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000079808_81723392.pth -[2023-10-17 03:31:32,266][62408] Updated weights for policy 1, policy_version 80890 (0.0007) -[2023-10-17 03:31:32,481][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000080896_82837504.pth... -[2023-10-17 03:31:32,523][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000079232_81133568.pth -[2023-10-17 03:31:34,841][62373] Updated weights for policy 0, policy_version 81480 (0.0009) -[2023-10-17 03:31:35,217][62373] Updated weights for policy 0, policy_version 81490 (0.0009) -[2023-10-17 03:31:35,582][62373] Updated weights for policy 0, policy_version 81500 (0.0008) -[2023-10-17 03:31:36,029][62408] Updated weights for policy 1, policy_version 80900 (0.0008) -[2023-10-17 03:31:36,403][62408] Updated weights for policy 1, policy_version 80910 (0.0010) -[2023-10-17 03:31:36,771][62408] Updated weights for policy 1, policy_version 80920 (0.0008) -[2023-10-17 03:31:37,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 166330368. Throughput: 0: 1802.2, 1: 1766.2. Samples: 41582926. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:31:37,215][61453] Avg episode reward: [(0, '10.530'), (1, '11.780')] -[2023-10-17 03:31:39,394][62373] Updated weights for policy 0, policy_version 81510 (0.0008) -[2023-10-17 03:31:39,762][62373] Updated weights for policy 0, policy_version 81520 (0.0007) -[2023-10-17 03:31:40,134][62373] Updated weights for policy 0, policy_version 81530 (0.0007) -[2023-10-17 03:31:40,593][62408] Updated weights for policy 1, policy_version 80930 (0.0008) -[2023-10-17 03:31:40,964][62408] Updated weights for policy 1, policy_version 80940 (0.0009) -[2023-10-17 03:31:41,342][62408] Updated weights for policy 1, policy_version 80950 (0.0009) -[2023-10-17 03:31:41,713][62408] Updated weights for policy 1, policy_version 80960 (0.0008) -[2023-10-17 03:31:42,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 166395904. Throughput: 0: 1776.3, 1: 1789.5. Samples: 41603726. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:31:42,215][61453] Avg episode reward: [(0, '10.850'), (1, '12.330')] -[2023-10-17 03:31:43,913][62373] Updated weights for policy 0, policy_version 81540 (0.0007) -[2023-10-17 03:31:44,282][62373] Updated weights for policy 0, policy_version 81550 (0.0008) -[2023-10-17 03:31:44,662][62373] Updated weights for policy 0, policy_version 81560 (0.0008) -[2023-10-17 03:31:45,566][62408] Updated weights for policy 1, policy_version 80970 (0.0009) -[2023-10-17 03:31:45,928][62408] Updated weights for policy 1, policy_version 80980 (0.0007) -[2023-10-17 03:31:46,300][62408] Updated weights for policy 1, policy_version 80990 (0.0008) -[2023-10-17 03:31:47,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 166461440. Throughput: 0: 1777.4, 1: 1759.9. Samples: 41624642. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:31:47,214][61453] Avg episode reward: [(0, '10.680'), (1, '11.120')] -[2023-10-17 03:31:48,355][62373] Updated weights for policy 0, policy_version 81570 (0.0010) -[2023-10-17 03:31:48,730][62373] Updated weights for policy 0, policy_version 81580 (0.0007) -[2023-10-17 03:31:49,089][62373] Updated weights for policy 0, policy_version 81590 (0.0010) -[2023-10-17 03:31:49,455][62373] Updated weights for policy 0, policy_version 81600 (0.0011) -[2023-10-17 03:31:49,966][62408] Updated weights for policy 1, policy_version 81000 (0.0008) -[2023-10-17 03:31:50,331][62408] Updated weights for policy 1, policy_version 81010 (0.0011) -[2023-10-17 03:31:50,690][62408] Updated weights for policy 1, policy_version 81020 (0.0011) -[2023-10-17 03:31:52,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 166526976. Throughput: 0: 1776.6, 1: 1786.8. Samples: 41635548. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:31:52,215][61453] Avg episode reward: [(0, '10.720'), (1, '11.220')] -[2023-10-17 03:31:53,360][62373] Updated weights for policy 0, policy_version 81610 (0.0007) -[2023-10-17 03:31:53,730][62373] Updated weights for policy 0, policy_version 81620 (0.0008) -[2023-10-17 03:31:54,090][62373] Updated weights for policy 0, policy_version 81630 (0.0009) -[2023-10-17 03:31:54,511][62408] Updated weights for policy 1, policy_version 81030 (0.0009) -[2023-10-17 03:31:54,879][62408] Updated weights for policy 1, policy_version 81040 (0.0008) -[2023-10-17 03:31:55,247][62408] Updated weights for policy 1, policy_version 81050 (0.0010) -[2023-10-17 03:31:57,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 166592512. Throughput: 0: 1777.0, 1: 1764.6. Samples: 41656926. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:31:57,215][61453] Avg episode reward: [(0, '10.670'), (1, '11.290')] -[2023-10-17 03:31:57,815][62373] Updated weights for policy 0, policy_version 81640 (0.0008) -[2023-10-17 03:31:58,182][62373] Updated weights for policy 0, policy_version 81650 (0.0009) -[2023-10-17 03:31:58,560][62373] Updated weights for policy 0, policy_version 81660 (0.0008) -[2023-10-17 03:31:59,110][62408] Updated weights for policy 1, policy_version 81060 (0.0008) -[2023-10-17 03:31:59,470][62408] Updated weights for policy 1, policy_version 81070 (0.0008) -[2023-10-17 03:31:59,846][62408] Updated weights for policy 1, policy_version 81080 (0.0010) -[2023-10-17 03:32:02,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 166658048. Throughput: 0: 1796.8, 1: 1768.2. Samples: 41679032. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:32:02,215][61453] Avg episode reward: [(0, '10.950'), (1, '11.840')] -[2023-10-17 03:32:02,364][62373] Updated weights for policy 0, policy_version 81670 (0.0009) -[2023-10-17 03:32:02,738][62373] Updated weights for policy 0, policy_version 81680 (0.0009) -[2023-10-17 03:32:03,106][62373] Updated weights for policy 0, policy_version 81690 (0.0008) -[2023-10-17 03:32:03,574][62408] Updated weights for policy 1, policy_version 81090 (0.0012) -[2023-10-17 03:32:03,940][62408] Updated weights for policy 1, policy_version 81100 (0.0010) -[2023-10-17 03:32:04,309][62408] Updated weights for policy 1, policy_version 81110 (0.0008) -[2023-10-17 03:32:04,678][62408] Updated weights for policy 1, policy_version 81120 (0.0008) -[2023-10-17 03:32:07,088][62373] Updated weights for policy 0, policy_version 81700 (0.0008) -[2023-10-17 03:32:07,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 166723584. Throughput: 0: 1779.7, 1: 1769.7. Samples: 41688728. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:32:07,214][61453] Avg episode reward: [(0, '11.330'), (1, '12.130')] -[2023-10-17 03:32:07,449][62373] Updated weights for policy 0, policy_version 81710 (0.0010) -[2023-10-17 03:32:07,823][62373] Updated weights for policy 0, policy_version 81720 (0.0009) -[2023-10-17 03:32:08,550][62408] Updated weights for policy 1, policy_version 81130 (0.0010) -[2023-10-17 03:32:08,918][62408] Updated weights for policy 1, policy_version 81140 (0.0010) -[2023-10-17 03:32:09,290][62408] Updated weights for policy 1, policy_version 81150 (0.0008) -[2023-10-17 03:32:11,639][62373] Updated weights for policy 0, policy_version 81730 (0.0008) -[2023-10-17 03:32:12,005][62373] Updated weights for policy 0, policy_version 81740 (0.0007) -[2023-10-17 03:32:12,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 166789120. Throughput: 0: 1786.8, 1: 1767.7. Samples: 41710514. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:32:12,214][61453] Avg episode reward: [(0, '11.350'), (1, '12.630')] -[2023-10-17 03:32:12,372][62373] Updated weights for policy 0, policy_version 81750 (0.0008) -[2023-10-17 03:32:12,736][62373] Updated weights for policy 0, policy_version 81760 (0.0007) -[2023-10-17 03:32:13,282][62408] Updated weights for policy 1, policy_version 81160 (0.0008) -[2023-10-17 03:32:13,673][62408] Updated weights for policy 1, policy_version 81170 (0.0008) -[2023-10-17 03:32:14,044][62408] Updated weights for policy 1, policy_version 81180 (0.0009) -[2023-10-17 03:32:16,554][62373] Updated weights for policy 0, policy_version 81770 (0.0008) -[2023-10-17 03:32:16,920][62373] Updated weights for policy 0, policy_version 81780 (0.0008) -[2023-10-17 03:32:17,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 166854656. Throughput: 0: 1783.1, 1: 1778.9. Samples: 41731828. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:32:17,215][61453] Avg episode reward: [(0, '10.880'), (1, '11.840')] -[2023-10-17 03:32:17,297][62373] Updated weights for policy 0, policy_version 81790 (0.0009) -[2023-10-17 03:32:17,615][62408] Updated weights for policy 1, policy_version 81190 (0.0010) -[2023-10-17 03:32:17,973][62408] Updated weights for policy 1, policy_version 81200 (0.0010) -[2023-10-17 03:32:18,348][62408] Updated weights for policy 1, policy_version 81210 (0.0008) -[2023-10-17 03:32:20,992][62373] Updated weights for policy 0, policy_version 81800 (0.0010) -[2023-10-17 03:32:21,365][62373] Updated weights for policy 0, policy_version 81810 (0.0010) -[2023-10-17 03:32:21,731][62373] Updated weights for policy 0, policy_version 81820 (0.0008) -[2023-10-17 03:32:22,214][61453] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 166952960. Throughput: 0: 1779.7, 1: 1761.1. Samples: 41742262. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:32:22,215][61453] Avg episode reward: [(0, '10.970'), (1, '12.180')] -[2023-10-17 03:32:22,234][62408] Updated weights for policy 1, policy_version 81220 (0.0008) -[2023-10-17 03:32:22,609][62408] Updated weights for policy 1, policy_version 81230 (0.0010) -[2023-10-17 03:32:22,978][62408] Updated weights for policy 1, policy_version 81240 (0.0010) -[2023-10-17 03:32:25,415][62373] Updated weights for policy 0, policy_version 81830 (0.0008) -[2023-10-17 03:32:25,784][62373] Updated weights for policy 0, policy_version 81840 (0.0007) -[2023-10-17 03:32:26,157][62373] Updated weights for policy 0, policy_version 81850 (0.0007) -[2023-10-17 03:32:26,642][62408] Updated weights for policy 1, policy_version 81250 (0.0008) -[2023-10-17 03:32:27,002][62408] Updated weights for policy 1, policy_version 81260 (0.0010) -[2023-10-17 03:32:27,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 167018496. Throughput: 0: 1786.8, 1: 1772.0. Samples: 41763874. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:32:27,214][61453] Avg episode reward: [(0, '10.830'), (1, '11.660')] -[2023-10-17 03:32:27,377][62408] Updated weights for policy 1, policy_version 81270 (0.0009) -[2023-10-17 03:32:27,750][62408] Updated weights for policy 1, policy_version 81280 (0.0007) -[2023-10-17 03:32:30,098][62373] Updated weights for policy 0, policy_version 81860 (0.0008) -[2023-10-17 03:32:30,464][62373] Updated weights for policy 0, policy_version 81870 (0.0010) -[2023-10-17 03:32:30,834][62373] Updated weights for policy 0, policy_version 81880 (0.0008) -[2023-10-17 03:32:31,634][62408] Updated weights for policy 1, policy_version 81290 (0.0011) -[2023-10-17 03:32:31,998][62408] Updated weights for policy 1, policy_version 81300 (0.0010) -[2023-10-17 03:32:32,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 167084032. Throughput: 0: 1766.5, 1: 1785.6. Samples: 41784488. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:32:32,215][61453] Avg episode reward: [(0, '11.850'), (1, '11.420')] -[2023-10-17 03:32:32,366][62408] Updated weights for policy 1, policy_version 81310 (0.0007) -[2023-10-17 03:32:34,690][62373] Updated weights for policy 0, policy_version 81890 (0.0008) -[2023-10-17 03:32:35,047][62373] Updated weights for policy 0, policy_version 81900 (0.0007) -[2023-10-17 03:32:35,410][62373] Updated weights for policy 0, policy_version 81910 (0.0010) -[2023-10-17 03:32:35,773][62373] Updated weights for policy 0, policy_version 81920 (0.0010) -[2023-10-17 03:32:36,387][62408] Updated weights for policy 1, policy_version 81320 (0.0009) -[2023-10-17 03:32:36,760][62408] Updated weights for policy 1, policy_version 81330 (0.0007) -[2023-10-17 03:32:37,131][62408] Updated weights for policy 1, policy_version 81340 (0.0008) -[2023-10-17 03:32:37,214][61453] Fps is (10 sec: 13106.8, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 167149568. Throughput: 0: 1789.1, 1: 1769.4. Samples: 41795680. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:32:37,215][61453] Avg episode reward: [(0, '11.690'), (1, '11.780')] -[2023-10-17 03:32:39,486][62373] Updated weights for policy 0, policy_version 81930 (0.0007) -[2023-10-17 03:32:39,859][62373] Updated weights for policy 0, policy_version 81940 (0.0009) -[2023-10-17 03:32:40,231][62373] Updated weights for policy 0, policy_version 81950 (0.0007) -[2023-10-17 03:32:40,907][62408] Updated weights for policy 1, policy_version 81350 (0.0007) -[2023-10-17 03:32:41,287][62408] Updated weights for policy 1, policy_version 81360 (0.0011) -[2023-10-17 03:32:41,660][62408] Updated weights for policy 1, policy_version 81370 (0.0010) -[2023-10-17 03:32:42,214][61453] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 167247872. Throughput: 0: 1764.1, 1: 1782.0. Samples: 41816504. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:32:42,215][61453] Avg episode reward: [(0, '11.690'), (1, '11.320')] -[2023-10-17 03:32:44,038][62373] Updated weights for policy 0, policy_version 81960 (0.0008) -[2023-10-17 03:32:44,416][62373] Updated weights for policy 0, policy_version 81970 (0.0008) -[2023-10-17 03:32:44,778][62373] Updated weights for policy 0, policy_version 81980 (0.0007) -[2023-10-17 03:32:45,549][62408] Updated weights for policy 1, policy_version 81380 (0.0009) -[2023-10-17 03:32:45,918][62408] Updated weights for policy 1, policy_version 81390 (0.0007) -[2023-10-17 03:32:46,283][62408] Updated weights for policy 1, policy_version 81400 (0.0007) -[2023-10-17 03:32:47,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 167313408. Throughput: 0: 1761.4, 1: 1756.2. Samples: 41837326. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:32:47,215][61453] Avg episode reward: [(0, '11.090'), (1, '11.120')] -[2023-10-17 03:32:48,599][62373] Updated weights for policy 0, policy_version 81990 (0.0008) -[2023-10-17 03:32:48,974][62373] Updated weights for policy 0, policy_version 82000 (0.0009) -[2023-10-17 03:32:49,357][62373] Updated weights for policy 0, policy_version 82010 (0.0009) -[2023-10-17 03:32:50,150][62408] Updated weights for policy 1, policy_version 81410 (0.0009) -[2023-10-17 03:32:50,534][62408] Updated weights for policy 1, policy_version 81420 (0.0009) -[2023-10-17 03:32:50,903][62408] Updated weights for policy 1, policy_version 81430 (0.0010) -[2023-10-17 03:32:51,260][62408] Updated weights for policy 1, policy_version 81440 (0.0011) -[2023-10-17 03:32:52,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 167378944. Throughput: 0: 1757.4, 1: 1782.4. Samples: 41848018. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:32:52,215][61453] Avg episode reward: [(0, '10.670'), (1, '10.850')] -[2023-10-17 03:32:53,130][62373] Updated weights for policy 0, policy_version 82020 (0.0008) -[2023-10-17 03:32:53,497][62373] Updated weights for policy 0, policy_version 82030 (0.0009) -[2023-10-17 03:32:53,864][62373] Updated weights for policy 0, policy_version 82040 (0.0007) -[2023-10-17 03:32:55,000][62408] Updated weights for policy 1, policy_version 81450 (0.0010) -[2023-10-17 03:32:55,365][62408] Updated weights for policy 1, policy_version 81460 (0.0010) -[2023-10-17 03:32:55,739][62408] Updated weights for policy 1, policy_version 81470 (0.0011) -[2023-10-17 03:32:57,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 167444480. Throughput: 0: 1763.9, 1: 1755.0. Samples: 41868864. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:32:57,215][61453] Avg episode reward: [(0, '10.290'), (1, '10.760')] -[2023-10-17 03:32:57,617][62373] Updated weights for policy 0, policy_version 82050 (0.0008) -[2023-10-17 03:32:57,986][62373] Updated weights for policy 0, policy_version 82060 (0.0008) -[2023-10-17 03:32:58,356][62373] Updated weights for policy 0, policy_version 82070 (0.0009) -[2023-10-17 03:32:58,723][62373] Updated weights for policy 0, policy_version 82080 (0.0008) -[2023-10-17 03:32:59,620][62408] Updated weights for policy 1, policy_version 81480 (0.0008) -[2023-10-17 03:32:59,990][62408] Updated weights for policy 1, policy_version 81490 (0.0007) -[2023-10-17 03:33:00,358][62408] Updated weights for policy 1, policy_version 81500 (0.0009) -[2023-10-17 03:33:02,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 167510016. Throughput: 0: 1781.1, 1: 1756.5. Samples: 41891020. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:33:02,215][61453] Avg episode reward: [(0, '10.310'), (1, '10.460')] -[2023-10-17 03:33:02,547][62373] Updated weights for policy 0, policy_version 82090 (0.0010) -[2023-10-17 03:33:02,911][62373] Updated weights for policy 0, policy_version 82100 (0.0008) -[2023-10-17 03:33:03,282][62373] Updated weights for policy 0, policy_version 82110 (0.0008) -[2023-10-17 03:33:03,986][62408] Updated weights for policy 1, policy_version 81510 (0.0010) -[2023-10-17 03:33:04,346][62408] Updated weights for policy 1, policy_version 81520 (0.0007) -[2023-10-17 03:33:04,719][62408] Updated weights for policy 1, policy_version 81530 (0.0010) -[2023-10-17 03:33:07,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 167575552. Throughput: 0: 1762.3, 1: 1766.4. Samples: 41901054. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:33:07,215][61453] Avg episode reward: [(0, '9.660'), (1, '11.620')] -[2023-10-17 03:33:07,268][62373] Updated weights for policy 0, policy_version 82120 (0.0010) -[2023-10-17 03:33:07,645][62373] Updated weights for policy 0, policy_version 82130 (0.0007) -[2023-10-17 03:33:08,020][62373] Updated weights for policy 0, policy_version 82140 (0.0007) -[2023-10-17 03:33:08,595][62408] Updated weights for policy 1, policy_version 81540 (0.0010) -[2023-10-17 03:33:08,951][62408] Updated weights for policy 1, policy_version 81550 (0.0009) -[2023-10-17 03:33:09,317][62408] Updated weights for policy 1, policy_version 81560 (0.0010) -[2023-10-17 03:33:11,706][62373] Updated weights for policy 0, policy_version 82150 (0.0007) -[2023-10-17 03:33:12,075][62373] Updated weights for policy 0, policy_version 82160 (0.0007) -[2023-10-17 03:33:12,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 167641088. Throughput: 0: 1777.3, 1: 1757.3. Samples: 41922932. Policy #0 lag: (min: 2.0, avg: 6.2, max: 34.0) -[2023-10-17 03:33:12,215][61453] Avg episode reward: [(0, '10.140'), (1, '11.520')] -[2023-10-17 03:33:12,450][62373] Updated weights for policy 0, policy_version 82170 (0.0007) -[2023-10-17 03:33:13,032][62408] Updated weights for policy 1, policy_version 81570 (0.0007) -[2023-10-17 03:33:13,398][62408] Updated weights for policy 1, policy_version 81580 (0.0011) -[2023-10-17 03:33:13,767][62408] Updated weights for policy 1, policy_version 81590 (0.0011) -[2023-10-17 03:33:14,143][62408] Updated weights for policy 1, policy_version 81600 (0.0008) -[2023-10-17 03:33:15,981][62373] Updated weights for policy 0, policy_version 82180 (0.0011) -[2023-10-17 03:33:16,346][62373] Updated weights for policy 0, policy_version 82190 (0.0009) -[2023-10-17 03:33:16,710][62373] Updated weights for policy 0, policy_version 82200 (0.0009) -[2023-10-17 03:33:17,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14218.0). Total num frames: 167739392. Throughput: 0: 1776.0, 1: 1772.0. Samples: 41944146. Policy #0 lag: (min: 2.0, avg: 6.2, max: 34.0) -[2023-10-17 03:33:17,215][61453] Avg episode reward: [(0, '10.130'), (1, '10.560')] -[2023-10-17 03:33:18,118][62408] Updated weights for policy 1, policy_version 81610 (0.0008) -[2023-10-17 03:33:18,486][62408] Updated weights for policy 1, policy_version 81620 (0.0007) -[2023-10-17 03:33:18,856][62408] Updated weights for policy 1, policy_version 81630 (0.0009) -[2023-10-17 03:33:20,406][62373] Updated weights for policy 0, policy_version 82210 (0.0008) -[2023-10-17 03:33:20,778][62373] Updated weights for policy 0, policy_version 82220 (0.0010) -[2023-10-17 03:33:21,150][62373] Updated weights for policy 0, policy_version 82230 (0.0009) -[2023-10-17 03:33:21,513][62373] Updated weights for policy 0, policy_version 82240 (0.0007) -[2023-10-17 03:33:22,214][61453] Fps is (10 sec: 16383.6, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 167804928. Throughput: 0: 1786.9, 1: 1755.5. Samples: 41955086. Policy #0 lag: (min: 2.0, avg: 6.2, max: 34.0) -[2023-10-17 03:33:22,215][61453] Avg episode reward: [(0, '9.910'), (1, '10.840')] -[2023-10-17 03:33:22,725][62408] Updated weights for policy 1, policy_version 81640 (0.0008) -[2023-10-17 03:33:23,092][62408] Updated weights for policy 1, policy_version 81650 (0.0007) -[2023-10-17 03:33:23,461][62408] Updated weights for policy 1, policy_version 81660 (0.0008) -[2023-10-17 03:33:25,365][62373] Updated weights for policy 0, policy_version 82250 (0.0010) -[2023-10-17 03:33:25,731][62373] Updated weights for policy 0, policy_version 82260 (0.0009) -[2023-10-17 03:33:26,097][62373] Updated weights for policy 0, policy_version 82270 (0.0009) -[2023-10-17 03:33:27,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 167870464. Throughput: 0: 1785.5, 1: 1762.1. Samples: 41976144. Policy #0 lag: (min: 2.0, avg: 6.2, max: 34.0) -[2023-10-17 03:33:27,215][61453] Avg episode reward: [(0, '10.240'), (1, '11.410')] -[2023-10-17 03:33:27,335][62408] Updated weights for policy 1, policy_version 81670 (0.0007) -[2023-10-17 03:33:27,696][62408] Updated weights for policy 1, policy_version 81680 (0.0008) -[2023-10-17 03:33:28,066][62408] Updated weights for policy 1, policy_version 81690 (0.0011) -[2023-10-17 03:33:29,948][62373] Updated weights for policy 0, policy_version 82280 (0.0008) -[2023-10-17 03:33:30,326][62373] Updated weights for policy 0, policy_version 82290 (0.0008) -[2023-10-17 03:33:30,690][62373] Updated weights for policy 0, policy_version 82300 (0.0010) -[2023-10-17 03:33:31,955][62408] Updated weights for policy 1, policy_version 81700 (0.0007) -[2023-10-17 03:33:32,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 167936000. Throughput: 0: 1785.1, 1: 1781.8. Samples: 41997836. Policy #0 lag: (min: 2.0, avg: 6.2, max: 34.0) -[2023-10-17 03:33:32,215][61453] Avg episode reward: [(0, '10.640'), (1, '11.600')] -[2023-10-17 03:33:32,221][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000082304_84279296.pth... -[2023-10-17 03:33:32,252][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000080640_82575360.pth -[2023-10-17 03:33:32,320][62408] Updated weights for policy 1, policy_version 81710 (0.0009) -[2023-10-17 03:33:32,692][62408] Updated weights for policy 1, policy_version 81720 (0.0011) -[2023-10-17 03:33:32,979][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000081728_83689472.pth... -[2023-10-17 03:33:33,008][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000080064_81985536.pth -[2023-10-17 03:33:34,501][62373] Updated weights for policy 0, policy_version 82310 (0.0010) -[2023-10-17 03:33:34,873][62373] Updated weights for policy 0, policy_version 82320 (0.0007) -[2023-10-17 03:33:35,238][62373] Updated weights for policy 0, policy_version 82330 (0.0007) -[2023-10-17 03:33:36,464][62408] Updated weights for policy 1, policy_version 81730 (0.0011) -[2023-10-17 03:33:36,829][62408] Updated weights for policy 1, policy_version 81740 (0.0008) -[2023-10-17 03:33:37,200][62408] Updated weights for policy 1, policy_version 81750 (0.0008) -[2023-10-17 03:33:37,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 168001536. Throughput: 0: 1802.0, 1: 1754.8. Samples: 42008074. Policy #0 lag: (min: 2.0, avg: 6.2, max: 34.0) -[2023-10-17 03:33:37,215][61453] Avg episode reward: [(0, '10.910'), (1, '11.670')] -[2023-10-17 03:33:37,566][62408] Updated weights for policy 1, policy_version 81760 (0.0007) -[2023-10-17 03:33:38,912][62373] Updated weights for policy 0, policy_version 82340 (0.0009) -[2023-10-17 03:33:39,265][62373] Updated weights for policy 0, policy_version 82350 (0.0011) -[2023-10-17 03:33:39,630][62373] Updated weights for policy 0, policy_version 82360 (0.0011) -[2023-10-17 03:33:41,592][62408] Updated weights for policy 1, policy_version 81770 (0.0008) -[2023-10-17 03:33:41,957][62408] Updated weights for policy 1, policy_version 81780 (0.0008) -[2023-10-17 03:33:42,214][61453] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 168067072. Throughput: 0: 1789.9, 1: 1779.1. Samples: 42029466. Policy #0 lag: (min: 2.0, avg: 6.2, max: 34.0) -[2023-10-17 03:33:42,214][61453] Avg episode reward: [(0, '11.110'), (1, '11.110')] -[2023-10-17 03:33:42,322][62408] Updated weights for policy 1, policy_version 81790 (0.0009) -[2023-10-17 03:33:43,420][62373] Updated weights for policy 0, policy_version 82370 (0.0007) -[2023-10-17 03:33:43,787][62373] Updated weights for policy 0, policy_version 82380 (0.0011) -[2023-10-17 03:33:44,163][62373] Updated weights for policy 0, policy_version 82390 (0.0010) -[2023-10-17 03:33:44,529][62373] Updated weights for policy 0, policy_version 82400 (0.0011) -[2023-10-17 03:33:46,336][62408] Updated weights for policy 1, policy_version 81800 (0.0007) -[2023-10-17 03:33:46,724][62408] Updated weights for policy 1, policy_version 81810 (0.0010) -[2023-10-17 03:33:47,086][62408] Updated weights for policy 1, policy_version 81820 (0.0009) -[2023-10-17 03:33:47,214][61453] Fps is (10 sec: 13107.4, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 168132608. Throughput: 0: 1787.1, 1: 1750.4. Samples: 42050210. Policy #0 lag: (min: 2.0, avg: 6.2, max: 34.0) -[2023-10-17 03:33:47,214][61453] Avg episode reward: [(0, '11.470'), (1, '11.800')] -[2023-10-17 03:33:48,366][62373] Updated weights for policy 0, policy_version 82410 (0.0008) -[2023-10-17 03:33:48,743][62373] Updated weights for policy 0, policy_version 82420 (0.0011) -[2023-10-17 03:33:49,110][62373] Updated weights for policy 0, policy_version 82430 (0.0009) -[2023-10-17 03:33:50,873][62408] Updated weights for policy 1, policy_version 81830 (0.0009) -[2023-10-17 03:33:51,236][62408] Updated weights for policy 1, policy_version 81840 (0.0007) -[2023-10-17 03:33:51,606][62408] Updated weights for policy 1, policy_version 81850 (0.0007) -[2023-10-17 03:33:52,214][61453] Fps is (10 sec: 16383.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 168230912. Throughput: 0: 1788.1, 1: 1761.9. Samples: 42060806. Policy #0 lag: (min: 2.0, avg: 6.2, max: 34.0) -[2023-10-17 03:33:52,215][61453] Avg episode reward: [(0, '12.080'), (1, '11.080')] -[2023-10-17 03:33:52,216][62094] Saving new best policy, reward=12.080! -[2023-10-17 03:33:52,880][62373] Updated weights for policy 0, policy_version 82440 (0.0008) -[2023-10-17 03:33:53,257][62373] Updated weights for policy 0, policy_version 82450 (0.0008) -[2023-10-17 03:33:53,626][62373] Updated weights for policy 0, policy_version 82460 (0.0007) -[2023-10-17 03:33:55,392][62408] Updated weights for policy 1, policy_version 81860 (0.0009) -[2023-10-17 03:33:55,762][62408] Updated weights for policy 1, policy_version 81870 (0.0007) -[2023-10-17 03:33:56,121][62408] Updated weights for policy 1, policy_version 81880 (0.0008) -[2023-10-17 03:33:57,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 168296448. Throughput: 0: 1792.6, 1: 1751.9. Samples: 42082434. Policy #0 lag: (min: 2.0, avg: 6.2, max: 34.0) -[2023-10-17 03:33:57,214][61453] Avg episode reward: [(0, '11.850'), (1, '11.700')] -[2023-10-17 03:33:57,348][62373] Updated weights for policy 0, policy_version 82470 (0.0009) -[2023-10-17 03:33:57,720][62373] Updated weights for policy 0, policy_version 82480 (0.0009) -[2023-10-17 03:33:58,095][62373] Updated weights for policy 0, policy_version 82490 (0.0011) -[2023-10-17 03:33:59,883][62408] Updated weights for policy 1, policy_version 81890 (0.0010) -[2023-10-17 03:34:00,255][62408] Updated weights for policy 1, policy_version 81900 (0.0008) -[2023-10-17 03:34:00,628][62408] Updated weights for policy 1, policy_version 81910 (0.0009) -[2023-10-17 03:34:00,987][62408] Updated weights for policy 1, policy_version 81920 (0.0010) -[2023-10-17 03:34:01,722][62373] Updated weights for policy 0, policy_version 82500 (0.0010) -[2023-10-17 03:34:02,093][62373] Updated weights for policy 0, policy_version 82510 (0.0009) -[2023-10-17 03:34:02,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 168361984. Throughput: 0: 1807.4, 1: 1738.9. Samples: 42103728. Policy #0 lag: (min: 13.0, avg: 13.7, max: 31.0) -[2023-10-17 03:34:02,215][61453] Avg episode reward: [(0, '11.870'), (1, '10.970')] -[2023-10-17 03:34:02,466][62373] Updated weights for policy 0, policy_version 82520 (0.0008) -[2023-10-17 03:34:04,789][62408] Updated weights for policy 1, policy_version 81930 (0.0008) -[2023-10-17 03:34:05,163][62408] Updated weights for policy 1, policy_version 81940 (0.0011) -[2023-10-17 03:34:05,532][62408] Updated weights for policy 1, policy_version 81950 (0.0008) -[2023-10-17 03:34:06,376][62373] Updated weights for policy 0, policy_version 82530 (0.0011) -[2023-10-17 03:34:06,759][62373] Updated weights for policy 0, policy_version 82540 (0.0008) -[2023-10-17 03:34:07,121][62373] Updated weights for policy 0, policy_version 82550 (0.0007) -[2023-10-17 03:34:07,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 168427520. Throughput: 0: 1782.5, 1: 1763.0. Samples: 42114636. Policy #0 lag: (min: 13.0, avg: 13.7, max: 31.0) -[2023-10-17 03:34:07,215][61453] Avg episode reward: [(0, '12.870'), (1, '11.610')] -[2023-10-17 03:34:07,488][62094] Saving new best policy, reward=12.870! -[2023-10-17 03:34:07,492][62373] Updated weights for policy 0, policy_version 82560 (0.0007) -[2023-10-17 03:34:09,278][62408] Updated weights for policy 1, policy_version 81960 (0.0007) -[2023-10-17 03:34:09,647][62408] Updated weights for policy 1, policy_version 81970 (0.0007) -[2023-10-17 03:34:10,008][62408] Updated weights for policy 1, policy_version 81980 (0.0007) -[2023-10-17 03:34:11,282][62373] Updated weights for policy 0, policy_version 82570 (0.0008) -[2023-10-17 03:34:11,642][62373] Updated weights for policy 0, policy_version 82580 (0.0009) -[2023-10-17 03:34:12,022][62373] Updated weights for policy 0, policy_version 82590 (0.0008) -[2023-10-17 03:34:12,214][61453] Fps is (10 sec: 16384.5, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 168525824. Throughput: 0: 1804.9, 1: 1741.1. Samples: 42135712. Policy #0 lag: (min: 13.0, avg: 13.7, max: 31.0) -[2023-10-17 03:34:12,214][61453] Avg episode reward: [(0, '13.210'), (1, '11.890')] -[2023-10-17 03:34:12,215][62094] Saving new best policy, reward=13.210! -[2023-10-17 03:34:13,956][62408] Updated weights for policy 1, policy_version 81990 (0.0008) -[2023-10-17 03:34:14,310][62408] Updated weights for policy 1, policy_version 82000 (0.0009) -[2023-10-17 03:34:14,687][62408] Updated weights for policy 1, policy_version 82010 (0.0008) -[2023-10-17 03:34:15,764][62373] Updated weights for policy 0, policy_version 82600 (0.0011) -[2023-10-17 03:34:16,130][62373] Updated weights for policy 0, policy_version 82610 (0.0010) -[2023-10-17 03:34:16,513][62373] Updated weights for policy 0, policy_version 82620 (0.0007) -[2023-10-17 03:34:17,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 168591360. Throughput: 0: 1774.6, 1: 1745.5. Samples: 42156240. Policy #0 lag: (min: 13.0, avg: 13.7, max: 31.0) -[2023-10-17 03:34:17,215][61453] Avg episode reward: [(0, '13.170'), (1, '12.200')] -[2023-10-17 03:34:18,573][62408] Updated weights for policy 1, policy_version 82020 (0.0009) -[2023-10-17 03:34:18,946][62408] Updated weights for policy 1, policy_version 82030 (0.0010) -[2023-10-17 03:34:19,306][62408] Updated weights for policy 1, policy_version 82040 (0.0010) -[2023-10-17 03:34:20,338][62373] Updated weights for policy 0, policy_version 82630 (0.0008) -[2023-10-17 03:34:20,721][62373] Updated weights for policy 0, policy_version 82640 (0.0008) -[2023-10-17 03:34:21,080][62373] Updated weights for policy 0, policy_version 82650 (0.0008) -[2023-10-17 03:34:22,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 168656896. Throughput: 0: 1796.2, 1: 1746.0. Samples: 42167472. Policy #0 lag: (min: 13.0, avg: 13.7, max: 31.0) -[2023-10-17 03:34:22,215][61453] Avg episode reward: [(0, '13.180'), (1, '11.890')] -[2023-10-17 03:34:23,193][62408] Updated weights for policy 1, policy_version 82050 (0.0010) -[2023-10-17 03:34:23,559][62408] Updated weights for policy 1, policy_version 82060 (0.0008) -[2023-10-17 03:34:23,928][62408] Updated weights for policy 1, policy_version 82070 (0.0009) -[2023-10-17 03:34:24,295][62408] Updated weights for policy 1, policy_version 82080 (0.0010) -[2023-10-17 03:34:24,896][62373] Updated weights for policy 0, policy_version 82660 (0.0008) -[2023-10-17 03:34:25,268][62373] Updated weights for policy 0, policy_version 82670 (0.0007) -[2023-10-17 03:34:25,641][62373] Updated weights for policy 0, policy_version 82680 (0.0007) -[2023-10-17 03:34:27,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 168722432. Throughput: 0: 1774.7, 1: 1751.3. Samples: 42188136. Policy #0 lag: (min: 13.0, avg: 13.7, max: 31.0) -[2023-10-17 03:34:27,215][61453] Avg episode reward: [(0, '12.850'), (1, '12.030')] -[2023-10-17 03:34:28,195][62408] Updated weights for policy 1, policy_version 82090 (0.0007) -[2023-10-17 03:34:28,558][62408] Updated weights for policy 1, policy_version 82100 (0.0007) -[2023-10-17 03:34:28,924][62408] Updated weights for policy 1, policy_version 82110 (0.0009) -[2023-10-17 03:34:29,362][62373] Updated weights for policy 0, policy_version 82690 (0.0008) -[2023-10-17 03:34:29,736][62373] Updated weights for policy 0, policy_version 82700 (0.0011) -[2023-10-17 03:34:30,102][62373] Updated weights for policy 0, policy_version 82710 (0.0011) -[2023-10-17 03:34:30,472][62373] Updated weights for policy 0, policy_version 82720 (0.0009) -[2023-10-17 03:34:32,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 168787968. Throughput: 0: 1773.2, 1: 1779.2. Samples: 42210068. Policy #0 lag: (min: 13.0, avg: 13.7, max: 31.0) -[2023-10-17 03:34:32,215][61453] Avg episode reward: [(0, '12.820'), (1, '12.390')] -[2023-10-17 03:34:32,779][62408] Updated weights for policy 1, policy_version 82120 (0.0007) -[2023-10-17 03:34:33,164][62408] Updated weights for policy 1, policy_version 82130 (0.0008) -[2023-10-17 03:34:33,538][62408] Updated weights for policy 1, policy_version 82140 (0.0009) -[2023-10-17 03:34:34,389][62373] Updated weights for policy 0, policy_version 82730 (0.0008) -[2023-10-17 03:34:34,755][62373] Updated weights for policy 0, policy_version 82740 (0.0010) -[2023-10-17 03:34:35,123][62373] Updated weights for policy 0, policy_version 82750 (0.0007) -[2023-10-17 03:34:37,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 168853504. Throughput: 0: 1779.0, 1: 1755.6. Samples: 42219862. Policy #0 lag: (min: 13.0, avg: 13.7, max: 31.0) -[2023-10-17 03:34:37,215][61453] Avg episode reward: [(0, '12.560'), (1, '12.050')] -[2023-10-17 03:34:37,392][62408] Updated weights for policy 1, policy_version 82150 (0.0007) -[2023-10-17 03:34:37,752][62408] Updated weights for policy 1, policy_version 82160 (0.0009) -[2023-10-17 03:34:38,125][62408] Updated weights for policy 1, policy_version 82170 (0.0008) -[2023-10-17 03:34:38,895][62373] Updated weights for policy 0, policy_version 82760 (0.0008) -[2023-10-17 03:34:39,267][62373] Updated weights for policy 0, policy_version 82770 (0.0008) -[2023-10-17 03:34:39,637][62373] Updated weights for policy 0, policy_version 82780 (0.0007) -[2023-10-17 03:34:41,846][62408] Updated weights for policy 1, policy_version 82180 (0.0008) -[2023-10-17 03:34:42,213][62408] Updated weights for policy 1, policy_version 82190 (0.0008) -[2023-10-17 03:34:42,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 168919040. Throughput: 0: 1765.2, 1: 1770.7. Samples: 42241552. Policy #0 lag: (min: 13.0, avg: 13.7, max: 31.0) -[2023-10-17 03:34:42,215][61453] Avg episode reward: [(0, '11.690'), (1, '12.340')] -[2023-10-17 03:34:42,583][62408] Updated weights for policy 1, policy_version 82200 (0.0007) -[2023-10-17 03:34:43,396][62373] Updated weights for policy 0, policy_version 82790 (0.0010) -[2023-10-17 03:34:43,765][62373] Updated weights for policy 0, policy_version 82800 (0.0012) -[2023-10-17 03:34:44,137][62373] Updated weights for policy 0, policy_version 82810 (0.0010) -[2023-10-17 03:34:46,378][62408] Updated weights for policy 1, policy_version 82210 (0.0010) -[2023-10-17 03:34:46,756][62408] Updated weights for policy 1, policy_version 82220 (0.0007) -[2023-10-17 03:34:47,115][62408] Updated weights for policy 1, policy_version 82230 (0.0007) -[2023-10-17 03:34:47,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 168984576. Throughput: 0: 1767.7, 1: 1768.2. Samples: 42262844. Policy #0 lag: (min: 13.0, avg: 13.7, max: 31.0) -[2023-10-17 03:34:47,214][61453] Avg episode reward: [(0, '11.490'), (1, '12.240')] -[2023-10-17 03:34:47,482][62408] Updated weights for policy 1, policy_version 82240 (0.0009) -[2023-10-17 03:34:47,945][62373] Updated weights for policy 0, policy_version 82820 (0.0008) -[2023-10-17 03:34:48,315][62373] Updated weights for policy 0, policy_version 82830 (0.0008) -[2023-10-17 03:34:48,688][62373] Updated weights for policy 0, policy_version 82840 (0.0007) -[2023-10-17 03:34:51,324][62408] Updated weights for policy 1, policy_version 82250 (0.0010) -[2023-10-17 03:34:51,685][62408] Updated weights for policy 1, policy_version 82260 (0.0007) -[2023-10-17 03:34:52,056][62408] Updated weights for policy 1, policy_version 82270 (0.0008) -[2023-10-17 03:34:52,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 169082880. Throughput: 0: 1760.8, 1: 1761.0. Samples: 42273116. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-17 03:34:52,215][61453] Avg episode reward: [(0, '10.920'), (1, '11.720')] -[2023-10-17 03:34:52,428][62373] Updated weights for policy 0, policy_version 82850 (0.0009) -[2023-10-17 03:34:52,801][62373] Updated weights for policy 0, policy_version 82860 (0.0008) -[2023-10-17 03:34:53,167][62373] Updated weights for policy 0, policy_version 82870 (0.0007) -[2023-10-17 03:34:53,528][62373] Updated weights for policy 0, policy_version 82880 (0.0007) -[2023-10-17 03:34:55,763][62408] Updated weights for policy 1, policy_version 82280 (0.0011) -[2023-10-17 03:34:56,136][62408] Updated weights for policy 1, policy_version 82290 (0.0009) -[2023-10-17 03:34:56,513][62408] Updated weights for policy 1, policy_version 82300 (0.0007) -[2023-10-17 03:34:57,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 169148416. Throughput: 0: 1767.1, 1: 1778.1. Samples: 42295244. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-17 03:34:57,214][61453] Avg episode reward: [(0, '9.980'), (1, '11.610')] -[2023-10-17 03:34:57,406][62373] Updated weights for policy 0, policy_version 82890 (0.0009) -[2023-10-17 03:34:57,776][62373] Updated weights for policy 0, policy_version 82900 (0.0008) -[2023-10-17 03:34:58,149][62373] Updated weights for policy 0, policy_version 82910 (0.0008) -[2023-10-17 03:35:00,356][62408] Updated weights for policy 1, policy_version 82310 (0.0007) -[2023-10-17 03:35:00,726][62408] Updated weights for policy 1, policy_version 82320 (0.0010) -[2023-10-17 03:35:01,090][62408] Updated weights for policy 1, policy_version 82330 (0.0007) -[2023-10-17 03:35:01,926][62373] Updated weights for policy 0, policy_version 82920 (0.0007) -[2023-10-17 03:35:02,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 169213952. Throughput: 0: 1795.5, 1: 1760.3. Samples: 42316250. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-17 03:35:02,215][61453] Avg episode reward: [(0, '10.080'), (1, '11.640')] -[2023-10-17 03:35:02,303][62373] Updated weights for policy 0, policy_version 82930 (0.0007) -[2023-10-17 03:35:02,671][62373] Updated weights for policy 0, policy_version 82940 (0.0007) -[2023-10-17 03:35:04,905][62408] Updated weights for policy 1, policy_version 82340 (0.0009) -[2023-10-17 03:35:05,268][62408] Updated weights for policy 1, policy_version 82350 (0.0008) -[2023-10-17 03:35:05,642][62408] Updated weights for policy 1, policy_version 82360 (0.0009) -[2023-10-17 03:35:06,561][62373] Updated weights for policy 0, policy_version 82950 (0.0008) -[2023-10-17 03:35:06,939][62373] Updated weights for policy 0, policy_version 82960 (0.0007) -[2023-10-17 03:35:07,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 169279488. Throughput: 0: 1768.4, 1: 1785.3. Samples: 42327390. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-17 03:35:07,215][61453] Avg episode reward: [(0, '9.730'), (1, '10.870')] -[2023-10-17 03:35:07,304][62373] Updated weights for policy 0, policy_version 82970 (0.0007) -[2023-10-17 03:35:09,332][62408] Updated weights for policy 1, policy_version 82370 (0.0009) -[2023-10-17 03:35:09,697][62408] Updated weights for policy 1, policy_version 82380 (0.0009) -[2023-10-17 03:35:10,082][62408] Updated weights for policy 1, policy_version 82390 (0.0009) -[2023-10-17 03:35:10,450][62408] Updated weights for policy 1, policy_version 82400 (0.0009) -[2023-10-17 03:35:10,966][62373] Updated weights for policy 0, policy_version 82980 (0.0008) -[2023-10-17 03:35:11,330][62373] Updated weights for policy 0, policy_version 82990 (0.0010) -[2023-10-17 03:35:11,699][62373] Updated weights for policy 0, policy_version 83000 (0.0008) -[2023-10-17 03:35:12,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 169377792. Throughput: 0: 1801.2, 1: 1760.5. Samples: 42348412. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-17 03:35:12,215][61453] Avg episode reward: [(0, '9.890'), (1, '11.210')] -[2023-10-17 03:35:14,187][62408] Updated weights for policy 1, policy_version 82410 (0.0007) -[2023-10-17 03:35:14,552][62408] Updated weights for policy 1, policy_version 82420 (0.0007) -[2023-10-17 03:35:14,927][62408] Updated weights for policy 1, policy_version 82430 (0.0009) -[2023-10-17 03:35:15,585][62373] Updated weights for policy 0, policy_version 83010 (0.0008) -[2023-10-17 03:35:15,950][62373] Updated weights for policy 0, policy_version 83020 (0.0010) -[2023-10-17 03:35:16,323][62373] Updated weights for policy 0, policy_version 83030 (0.0010) -[2023-10-17 03:35:16,697][62373] Updated weights for policy 0, policy_version 83040 (0.0010) -[2023-10-17 03:35:17,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 169443328. Throughput: 0: 1772.6, 1: 1758.9. Samples: 42368984. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-17 03:35:17,215][61453] Avg episode reward: [(0, '9.980'), (1, '11.340')] -[2023-10-17 03:35:18,929][62408] Updated weights for policy 1, policy_version 82440 (0.0008) -[2023-10-17 03:35:19,311][62408] Updated weights for policy 1, policy_version 82450 (0.0007) -[2023-10-17 03:35:19,682][62408] Updated weights for policy 1, policy_version 82460 (0.0007) -[2023-10-17 03:35:20,500][62373] Updated weights for policy 0, policy_version 83050 (0.0007) -[2023-10-17 03:35:20,862][62373] Updated weights for policy 0, policy_version 83060 (0.0008) -[2023-10-17 03:35:21,227][62373] Updated weights for policy 0, policy_version 83070 (0.0009) -[2023-10-17 03:35:22,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 169508864. Throughput: 0: 1799.8, 1: 1755.6. Samples: 42379854. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-17 03:35:22,214][61453] Avg episode reward: [(0, '9.550'), (1, '10.350')] -[2023-10-17 03:35:23,587][62408] Updated weights for policy 1, policy_version 82470 (0.0008) -[2023-10-17 03:35:23,959][62408] Updated weights for policy 1, policy_version 82480 (0.0009) -[2023-10-17 03:35:24,333][62408] Updated weights for policy 1, policy_version 82490 (0.0007) -[2023-10-17 03:35:25,026][62373] Updated weights for policy 0, policy_version 83080 (0.0008) -[2023-10-17 03:35:25,400][62373] Updated weights for policy 0, policy_version 83090 (0.0008) -[2023-10-17 03:35:25,767][62373] Updated weights for policy 0, policy_version 83100 (0.0008) -[2023-10-17 03:35:27,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 169574400. Throughput: 0: 1777.3, 1: 1759.2. Samples: 42400692. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-17 03:35:27,214][61453] Avg episode reward: [(0, '9.810'), (1, '10.860')] -[2023-10-17 03:35:28,106][62408] Updated weights for policy 1, policy_version 82500 (0.0009) -[2023-10-17 03:35:28,469][62408] Updated weights for policy 1, policy_version 82510 (0.0009) -[2023-10-17 03:35:28,844][62408] Updated weights for policy 1, policy_version 82520 (0.0010) -[2023-10-17 03:35:29,471][62373] Updated weights for policy 0, policy_version 83110 (0.0008) -[2023-10-17 03:35:29,854][62373] Updated weights for policy 0, policy_version 83120 (0.0008) -[2023-10-17 03:35:30,220][62373] Updated weights for policy 0, policy_version 83130 (0.0008) -[2023-10-17 03:35:32,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 169639936. Throughput: 0: 1781.1, 1: 1770.6. Samples: 42422672. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-17 03:35:32,214][61453] Avg episode reward: [(0, '10.950'), (1, '10.460')] -[2023-10-17 03:35:32,224][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000083136_85131264.pth... -[2023-10-17 03:35:32,224][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000082528_84508672.pth... -[2023-10-17 03:35:32,276][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000081472_83427328.pth -[2023-10-17 03:35:32,277][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000080896_82837504.pth -[2023-10-17 03:35:32,282][62094] Saving a milestone ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/milestones/checkpoint_000083136_85131264.pth -[2023-10-17 03:35:32,282][62252] Saving a milestone ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/milestones/checkpoint_000082528_84508672.pth -[2023-10-17 03:35:32,697][62408] Updated weights for policy 1, policy_version 82530 (0.0010) -[2023-10-17 03:35:33,067][62408] Updated weights for policy 1, policy_version 82540 (0.0009) -[2023-10-17 03:35:33,447][62408] Updated weights for policy 1, policy_version 82550 (0.0009) -[2023-10-17 03:35:33,809][62408] Updated weights for policy 1, policy_version 82560 (0.0009) -[2023-10-17 03:35:33,903][62373] Updated weights for policy 0, policy_version 83140 (0.0008) -[2023-10-17 03:35:34,260][62373] Updated weights for policy 0, policy_version 83150 (0.0009) -[2023-10-17 03:35:34,631][62373] Updated weights for policy 0, policy_version 83160 (0.0008) -[2023-10-17 03:35:37,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 169705472. Throughput: 0: 1782.7, 1: 1754.8. Samples: 42432302. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-17 03:35:37,215][61453] Avg episode reward: [(0, '10.930'), (1, '10.420')] -[2023-10-17 03:35:37,854][62408] Updated weights for policy 1, policy_version 82570 (0.0010) -[2023-10-17 03:35:38,212][62408] Updated weights for policy 1, policy_version 82580 (0.0010) -[2023-10-17 03:35:38,394][62373] Updated weights for policy 0, policy_version 83170 (0.0009) -[2023-10-17 03:35:38,579][62408] Updated weights for policy 1, policy_version 82590 (0.0009) -[2023-10-17 03:35:38,765][62373] Updated weights for policy 0, policy_version 83180 (0.0008) -[2023-10-17 03:35:39,133][62373] Updated weights for policy 0, policy_version 83190 (0.0007) -[2023-10-17 03:35:39,502][62373] Updated weights for policy 0, policy_version 83200 (0.0007) -[2023-10-17 03:35:42,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 169771008. Throughput: 0: 1774.5, 1: 1757.4. Samples: 42454180. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-10-17 03:35:42,214][61453] Avg episode reward: [(0, '10.370'), (1, '10.490')] -[2023-10-17 03:35:42,388][62408] Updated weights for policy 1, policy_version 82600 (0.0008) -[2023-10-17 03:35:42,757][62408] Updated weights for policy 1, policy_version 82610 (0.0008) -[2023-10-17 03:35:43,116][62408] Updated weights for policy 1, policy_version 82620 (0.0008) -[2023-10-17 03:35:43,306][62373] Updated weights for policy 0, policy_version 83210 (0.0009) -[2023-10-17 03:35:43,680][62373] Updated weights for policy 0, policy_version 83220 (0.0010) -[2023-10-17 03:35:44,059][62373] Updated weights for policy 0, policy_version 83230 (0.0009) -[2023-10-17 03:35:47,072][62408] Updated weights for policy 1, policy_version 82630 (0.0009) -[2023-10-17 03:35:47,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 169836544. Throughput: 0: 1781.9, 1: 1778.0. Samples: 42476446. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:35:47,215][61453] Avg episode reward: [(0, '10.690'), (1, '9.930')] -[2023-10-17 03:35:47,441][62408] Updated weights for policy 1, policy_version 82640 (0.0008) -[2023-10-17 03:35:47,808][62373] Updated weights for policy 0, policy_version 83240 (0.0008) -[2023-10-17 03:35:47,816][62408] Updated weights for policy 1, policy_version 82650 (0.0009) -[2023-10-17 03:35:48,174][62373] Updated weights for policy 0, policy_version 83250 (0.0007) -[2023-10-17 03:35:48,546][62373] Updated weights for policy 0, policy_version 83260 (0.0008) -[2023-10-17 03:35:51,525][62408] Updated weights for policy 1, policy_version 82660 (0.0009) -[2023-10-17 03:35:51,903][62408] Updated weights for policy 1, policy_version 82670 (0.0011) -[2023-10-17 03:35:52,214][61453] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 169902080. Throughput: 0: 1776.2, 1: 1753.5. Samples: 42486228. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:35:52,214][61453] Avg episode reward: [(0, '10.480'), (1, '10.850')] -[2023-10-17 03:35:52,261][62408] Updated weights for policy 1, policy_version 82680 (0.0008) -[2023-10-17 03:35:52,353][62373] Updated weights for policy 0, policy_version 83270 (0.0008) -[2023-10-17 03:35:52,744][62373] Updated weights for policy 0, policy_version 83280 (0.0007) -[2023-10-17 03:35:53,122][62373] Updated weights for policy 0, policy_version 83290 (0.0008) -[2023-10-17 03:35:55,959][62408] Updated weights for policy 1, policy_version 82690 (0.0008) -[2023-10-17 03:35:56,332][62408] Updated weights for policy 1, policy_version 82700 (0.0009) -[2023-10-17 03:35:56,700][62408] Updated weights for policy 1, policy_version 82710 (0.0008) -[2023-10-17 03:35:57,018][62373] Updated weights for policy 0, policy_version 83300 (0.0010) -[2023-10-17 03:35:57,061][62408] Updated weights for policy 1, policy_version 82720 (0.0008) -[2023-10-17 03:35:57,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 170000384. Throughput: 0: 1767.3, 1: 1781.9. Samples: 42508126. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:35:57,215][61453] Avg episode reward: [(0, '10.570'), (1, '10.750')] -[2023-10-17 03:35:57,399][62373] Updated weights for policy 0, policy_version 83310 (0.0010) -[2023-10-17 03:35:57,774][62373] Updated weights for policy 0, policy_version 83320 (0.0010) -[2023-10-17 03:36:00,955][62408] Updated weights for policy 1, policy_version 82730 (0.0008) -[2023-10-17 03:36:01,323][62408] Updated weights for policy 1, policy_version 82740 (0.0007) -[2023-10-17 03:36:01,613][62373] Updated weights for policy 0, policy_version 83330 (0.0009) -[2023-10-17 03:36:01,694][62408] Updated weights for policy 1, policy_version 82750 (0.0007) -[2023-10-17 03:36:01,979][62373] Updated weights for policy 0, policy_version 83340 (0.0008) -[2023-10-17 03:36:02,214][61453] Fps is (10 sec: 16383.5, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 170065920. Throughput: 0: 1792.5, 1: 1753.5. Samples: 42528554. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:36:02,215][61453] Avg episode reward: [(0, '10.930'), (1, '10.110')] -[2023-10-17 03:36:02,355][62373] Updated weights for policy 0, policy_version 83350 (0.0007) -[2023-10-17 03:36:02,727][62373] Updated weights for policy 0, policy_version 83360 (0.0008) -[2023-10-17 03:36:05,661][62408] Updated weights for policy 1, policy_version 82760 (0.0008) -[2023-10-17 03:36:06,048][62408] Updated weights for policy 1, policy_version 82770 (0.0008) -[2023-10-17 03:36:06,411][62408] Updated weights for policy 1, policy_version 82780 (0.0008) -[2023-10-17 03:36:06,624][62373] Updated weights for policy 0, policy_version 83370 (0.0008) -[2023-10-17 03:36:06,985][62373] Updated weights for policy 0, policy_version 83380 (0.0010) -[2023-10-17 03:36:07,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 170131456. Throughput: 0: 1768.7, 1: 1791.2. Samples: 42540050. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:36:07,214][61453] Avg episode reward: [(0, '9.830'), (1, '10.610')] -[2023-10-17 03:36:07,355][62373] Updated weights for policy 0, policy_version 83390 (0.0010) -[2023-10-17 03:36:09,886][62408] Updated weights for policy 1, policy_version 82790 (0.0007) -[2023-10-17 03:36:10,261][62408] Updated weights for policy 1, policy_version 82800 (0.0008) -[2023-10-17 03:36:10,620][62408] Updated weights for policy 1, policy_version 82810 (0.0008) -[2023-10-17 03:36:11,224][62373] Updated weights for policy 0, policy_version 83400 (0.0008) -[2023-10-17 03:36:11,600][62373] Updated weights for policy 0, policy_version 83410 (0.0007) -[2023-10-17 03:36:11,973][62373] Updated weights for policy 0, policy_version 83420 (0.0007) -[2023-10-17 03:36:12,214][61453] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 170229760. Throughput: 0: 1794.3, 1: 1755.6. Samples: 42560438. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:36:12,215][61453] Avg episode reward: [(0, '10.220'), (1, '10.770')] -[2023-10-17 03:36:14,469][62408] Updated weights for policy 1, policy_version 82820 (0.0009) -[2023-10-17 03:36:14,834][62408] Updated weights for policy 1, policy_version 82830 (0.0009) -[2023-10-17 03:36:15,210][62408] Updated weights for policy 1, policy_version 82840 (0.0009) -[2023-10-17 03:36:15,752][62373] Updated weights for policy 0, policy_version 83430 (0.0007) -[2023-10-17 03:36:16,118][62373] Updated weights for policy 0, policy_version 83440 (0.0007) -[2023-10-17 03:36:16,491][62373] Updated weights for policy 0, policy_version 83450 (0.0008) -[2023-10-17 03:36:17,214][61453] Fps is (10 sec: 16383.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 170295296. Throughput: 0: 1761.1, 1: 1763.1. Samples: 42581262. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:36:17,215][61453] Avg episode reward: [(0, '10.030'), (1, '10.800')] -[2023-10-17 03:36:19,252][62408] Updated weights for policy 1, policy_version 82850 (0.0009) -[2023-10-17 03:36:19,627][62408] Updated weights for policy 1, policy_version 82860 (0.0008) -[2023-10-17 03:36:19,996][62408] Updated weights for policy 1, policy_version 82870 (0.0010) -[2023-10-17 03:36:20,157][62373] Updated weights for policy 0, policy_version 83460 (0.0008) -[2023-10-17 03:36:20,358][62408] Updated weights for policy 1, policy_version 82880 (0.0007) -[2023-10-17 03:36:20,528][62373] Updated weights for policy 0, policy_version 83470 (0.0010) -[2023-10-17 03:36:20,896][62373] Updated weights for policy 0, policy_version 83480 (0.0010) -[2023-10-17 03:36:22,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 170360832. Throughput: 0: 1793.2, 1: 1776.2. Samples: 42592922. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:36:22,214][61453] Avg episode reward: [(0, '10.490'), (1, '10.730')] -[2023-10-17 03:36:24,184][62408] Updated weights for policy 1, policy_version 82890 (0.0008) -[2023-10-17 03:36:24,551][62408] Updated weights for policy 1, policy_version 82900 (0.0008) -[2023-10-17 03:36:24,629][62373] Updated weights for policy 0, policy_version 83490 (0.0010) -[2023-10-17 03:36:24,920][62408] Updated weights for policy 1, policy_version 82910 (0.0008) -[2023-10-17 03:36:25,008][62373] Updated weights for policy 0, policy_version 83500 (0.0009) -[2023-10-17 03:36:25,381][62373] Updated weights for policy 0, policy_version 83510 (0.0010) -[2023-10-17 03:36:25,747][62373] Updated weights for policy 0, policy_version 83520 (0.0007) -[2023-10-17 03:36:27,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 170426368. Throughput: 0: 1768.4, 1: 1766.3. Samples: 42613246. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:36:27,215][61453] Avg episode reward: [(0, '10.960'), (1, '10.480')] -[2023-10-17 03:36:28,707][62408] Updated weights for policy 1, policy_version 82920 (0.0008) -[2023-10-17 03:36:29,070][62408] Updated weights for policy 1, policy_version 82930 (0.0007) -[2023-10-17 03:36:29,433][62408] Updated weights for policy 1, policy_version 82940 (0.0008) -[2023-10-17 03:36:29,497][62373] Updated weights for policy 0, policy_version 83530 (0.0009) -[2023-10-17 03:36:29,881][62373] Updated weights for policy 0, policy_version 83540 (0.0010) -[2023-10-17 03:36:30,250][62373] Updated weights for policy 0, policy_version 83550 (0.0008) -[2023-10-17 03:36:32,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 170491904. Throughput: 0: 1763.2, 1: 1767.3. Samples: 42635318. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:36:32,215][61453] Avg episode reward: [(0, '10.260'), (1, '10.630')] -[2023-10-17 03:36:33,177][62408] Updated weights for policy 1, policy_version 82950 (0.0009) -[2023-10-17 03:36:33,544][62408] Updated weights for policy 1, policy_version 82960 (0.0010) -[2023-10-17 03:36:33,911][62408] Updated weights for policy 1, policy_version 82970 (0.0008) -[2023-10-17 03:36:34,145][62373] Updated weights for policy 0, policy_version 83560 (0.0008) -[2023-10-17 03:36:34,528][62373] Updated weights for policy 0, policy_version 83570 (0.0011) -[2023-10-17 03:36:34,897][62373] Updated weights for policy 0, policy_version 83580 (0.0008) -[2023-10-17 03:36:37,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 170557440. Throughput: 0: 1767.0, 1: 1766.2. Samples: 42645222. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:36:37,215][61453] Avg episode reward: [(0, '10.770'), (1, '10.740')] -[2023-10-17 03:36:37,667][62408] Updated weights for policy 1, policy_version 82980 (0.0010) -[2023-10-17 03:36:38,034][62408] Updated weights for policy 1, policy_version 82990 (0.0011) -[2023-10-17 03:36:38,400][62408] Updated weights for policy 1, policy_version 83000 (0.0009) -[2023-10-17 03:36:38,668][62373] Updated weights for policy 0, policy_version 83590 (0.0009) -[2023-10-17 03:36:39,045][62373] Updated weights for policy 0, policy_version 83600 (0.0010) -[2023-10-17 03:36:39,406][62373] Updated weights for policy 0, policy_version 83610 (0.0008) -[2023-10-17 03:36:42,131][62408] Updated weights for policy 1, policy_version 83010 (0.0008) -[2023-10-17 03:36:42,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 170622976. Throughput: 0: 1765.3, 1: 1770.7. Samples: 42667246. Policy #0 lag: (min: 31.0, avg: 31.5, max: 46.0) -[2023-10-17 03:36:42,215][61453] Avg episode reward: [(0, '11.080'), (1, '9.890')] -[2023-10-17 03:36:42,499][62408] Updated weights for policy 1, policy_version 83020 (0.0008) -[2023-10-17 03:36:42,872][62408] Updated weights for policy 1, policy_version 83030 (0.0008) -[2023-10-17 03:36:43,236][62373] Updated weights for policy 0, policy_version 83620 (0.0008) -[2023-10-17 03:36:43,239][62408] Updated weights for policy 1, policy_version 83040 (0.0008) -[2023-10-17 03:36:43,625][62373] Updated weights for policy 0, policy_version 83630 (0.0010) -[2023-10-17 03:36:43,990][62373] Updated weights for policy 0, policy_version 83640 (0.0009) -[2023-10-17 03:36:46,889][62408] Updated weights for policy 1, policy_version 83050 (0.0007) -[2023-10-17 03:36:47,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 170688512. Throughput: 0: 1773.8, 1: 1792.9. Samples: 42689052. Policy #0 lag: (min: 31.0, avg: 31.5, max: 46.0) -[2023-10-17 03:36:47,214][61453] Avg episode reward: [(0, '11.070'), (1, '9.890')] -[2023-10-17 03:36:47,263][62408] Updated weights for policy 1, policy_version 83060 (0.0008) -[2023-10-17 03:36:47,626][62408] Updated weights for policy 1, policy_version 83070 (0.0007) -[2023-10-17 03:36:47,747][62373] Updated weights for policy 0, policy_version 83650 (0.0010) -[2023-10-17 03:36:48,119][62373] Updated weights for policy 0, policy_version 83660 (0.0008) -[2023-10-17 03:36:48,482][62373] Updated weights for policy 0, policy_version 83670 (0.0011) -[2023-10-17 03:36:48,851][62373] Updated weights for policy 0, policy_version 83680 (0.0009) -[2023-10-17 03:36:51,556][62408] Updated weights for policy 1, policy_version 83080 (0.0007) -[2023-10-17 03:36:51,938][62408] Updated weights for policy 1, policy_version 83090 (0.0007) -[2023-10-17 03:36:52,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 170754048. Throughput: 0: 1761.2, 1: 1770.8. Samples: 42698986. Policy #0 lag: (min: 31.0, avg: 31.5, max: 46.0) -[2023-10-17 03:36:52,214][61453] Avg episode reward: [(0, '10.650'), (1, '11.430')] -[2023-10-17 03:36:52,303][62408] Updated weights for policy 1, policy_version 83100 (0.0007) -[2023-10-17 03:36:52,640][62373] Updated weights for policy 0, policy_version 83690 (0.0010) -[2023-10-17 03:36:53,017][62373] Updated weights for policy 0, policy_version 83700 (0.0008) -[2023-10-17 03:36:53,382][62373] Updated weights for policy 0, policy_version 83710 (0.0007) -[2023-10-17 03:36:55,952][62408] Updated weights for policy 1, policy_version 83110 (0.0009) -[2023-10-17 03:36:56,319][62408] Updated weights for policy 1, policy_version 83120 (0.0008) -[2023-10-17 03:36:56,699][62408] Updated weights for policy 1, policy_version 83130 (0.0008) -[2023-10-17 03:36:57,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 170852352. Throughput: 0: 1770.1, 1: 1800.4. Samples: 42721112. Policy #0 lag: (min: 31.0, avg: 31.5, max: 46.0) -[2023-10-17 03:36:57,215][61453] Avg episode reward: [(0, '10.020'), (1, '10.890')] -[2023-10-17 03:36:57,326][62373] Updated weights for policy 0, policy_version 83720 (0.0008) -[2023-10-17 03:36:57,704][62373] Updated weights for policy 0, policy_version 83730 (0.0007) -[2023-10-17 03:36:58,069][62373] Updated weights for policy 0, policy_version 83740 (0.0007) -[2023-10-17 03:37:00,477][62408] Updated weights for policy 1, policy_version 83140 (0.0010) -[2023-10-17 03:37:00,845][62408] Updated weights for policy 1, policy_version 83150 (0.0007) -[2023-10-17 03:37:01,211][62408] Updated weights for policy 1, policy_version 83160 (0.0008) -[2023-10-17 03:37:01,734][62373] Updated weights for policy 0, policy_version 83750 (0.0009) -[2023-10-17 03:37:02,102][62373] Updated weights for policy 0, policy_version 83760 (0.0009) -[2023-10-17 03:37:02,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 170917888. Throughput: 0: 1791.9, 1: 1776.3. Samples: 42741832. Policy #0 lag: (min: 31.0, avg: 31.5, max: 46.0) -[2023-10-17 03:37:02,215][61453] Avg episode reward: [(0, '9.900'), (1, '10.790')] -[2023-10-17 03:37:02,472][62373] Updated weights for policy 0, policy_version 83770 (0.0009) -[2023-10-17 03:37:05,045][62408] Updated weights for policy 1, policy_version 83170 (0.0008) -[2023-10-17 03:37:05,416][62408] Updated weights for policy 1, policy_version 83180 (0.0009) -[2023-10-17 03:37:05,769][62408] Updated weights for policy 1, policy_version 83190 (0.0010) -[2023-10-17 03:37:06,139][62408] Updated weights for policy 1, policy_version 83200 (0.0008) -[2023-10-17 03:37:06,227][62373] Updated weights for policy 0, policy_version 83780 (0.0008) -[2023-10-17 03:37:06,605][62373] Updated weights for policy 0, policy_version 83790 (0.0008) -[2023-10-17 03:37:06,966][62373] Updated weights for policy 0, policy_version 83800 (0.0007) -[2023-10-17 03:37:07,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 170983424. Throughput: 0: 1766.8, 1: 1799.2. Samples: 42753396. Policy #0 lag: (min: 31.0, avg: 31.5, max: 46.0) -[2023-10-17 03:37:07,215][61453] Avg episode reward: [(0, '8.790'), (1, '11.440')] -[2023-10-17 03:37:09,952][62408] Updated weights for policy 1, policy_version 83210 (0.0007) -[2023-10-17 03:37:10,316][62408] Updated weights for policy 1, policy_version 83220 (0.0007) -[2023-10-17 03:37:10,679][62408] Updated weights for policy 1, policy_version 83230 (0.0010) -[2023-10-17 03:37:10,972][62373] Updated weights for policy 0, policy_version 83810 (0.0008) -[2023-10-17 03:37:11,340][62373] Updated weights for policy 0, policy_version 83820 (0.0008) -[2023-10-17 03:37:11,704][62373] Updated weights for policy 0, policy_version 83830 (0.0007) -[2023-10-17 03:37:12,068][62373] Updated weights for policy 0, policy_version 83840 (0.0008) -[2023-10-17 03:37:12,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 171081728. Throughput: 0: 1790.7, 1: 1776.1. Samples: 42773752. Policy #0 lag: (min: 31.0, avg: 31.5, max: 46.0) -[2023-10-17 03:37:12,214][61453] Avg episode reward: [(0, '8.810'), (1, '11.150')] -[2023-10-17 03:37:14,511][62408] Updated weights for policy 1, policy_version 83240 (0.0011) -[2023-10-17 03:37:14,879][62408] Updated weights for policy 1, policy_version 83250 (0.0009) -[2023-10-17 03:37:15,248][62408] Updated weights for policy 1, policy_version 83260 (0.0010) -[2023-10-17 03:37:15,776][62373] Updated weights for policy 0, policy_version 83850 (0.0008) -[2023-10-17 03:37:16,141][62373] Updated weights for policy 0, policy_version 83860 (0.0009) -[2023-10-17 03:37:16,508][62373] Updated weights for policy 0, policy_version 83870 (0.0009) -[2023-10-17 03:37:17,214][61453] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 171147264. Throughput: 0: 1765.1, 1: 1771.0. Samples: 42794442. Policy #0 lag: (min: 31.0, avg: 31.5, max: 46.0) -[2023-10-17 03:37:17,214][61453] Avg episode reward: [(0, '9.070'), (1, '11.700')] -[2023-10-17 03:37:19,041][62408] Updated weights for policy 1, policy_version 83270 (0.0008) -[2023-10-17 03:37:19,413][62408] Updated weights for policy 1, policy_version 83280 (0.0007) -[2023-10-17 03:37:19,785][62408] Updated weights for policy 1, policy_version 83290 (0.0007) -[2023-10-17 03:37:20,237][62373] Updated weights for policy 0, policy_version 83880 (0.0008) -[2023-10-17 03:37:20,611][62373] Updated weights for policy 0, policy_version 83890 (0.0009) -[2023-10-17 03:37:20,987][62373] Updated weights for policy 0, policy_version 83900 (0.0008) -[2023-10-17 03:37:22,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 171212800. Throughput: 0: 1794.3, 1: 1774.9. Samples: 42805836. Policy #0 lag: (min: 31.0, avg: 31.5, max: 46.0) -[2023-10-17 03:37:22,215][61453] Avg episode reward: [(0, '9.790'), (1, '12.020')] -[2023-10-17 03:37:23,678][62408] Updated weights for policy 1, policy_version 83300 (0.0007) -[2023-10-17 03:37:24,046][62408] Updated weights for policy 1, policy_version 83310 (0.0008) -[2023-10-17 03:37:24,421][62408] Updated weights for policy 1, policy_version 83320 (0.0008) -[2023-10-17 03:37:24,666][62373] Updated weights for policy 0, policy_version 83910 (0.0008) -[2023-10-17 03:37:25,034][62373] Updated weights for policy 0, policy_version 83920 (0.0008) -[2023-10-17 03:37:25,403][62373] Updated weights for policy 0, policy_version 83930 (0.0009) -[2023-10-17 03:37:27,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 171278336. Throughput: 0: 1774.2, 1: 1761.4. Samples: 42826350. Policy #0 lag: (min: 31.0, avg: 31.5, max: 46.0) -[2023-10-17 03:37:27,215][61453] Avg episode reward: [(0, '9.820'), (1, '11.720')] -[2023-10-17 03:37:28,210][62408] Updated weights for policy 1, policy_version 83330 (0.0008) -[2023-10-17 03:37:28,576][62408] Updated weights for policy 1, policy_version 83340 (0.0008) -[2023-10-17 03:37:28,936][62408] Updated weights for policy 1, policy_version 83350 (0.0009) -[2023-10-17 03:37:29,297][62408] Updated weights for policy 1, policy_version 83360 (0.0008) -[2023-10-17 03:37:29,314][62373] Updated weights for policy 0, policy_version 83940 (0.0009) -[2023-10-17 03:37:29,698][62373] Updated weights for policy 0, policy_version 83950 (0.0008) -[2023-10-17 03:37:30,083][62373] Updated weights for policy 0, policy_version 83960 (0.0009) -[2023-10-17 03:37:32,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 171343872. Throughput: 0: 1767.1, 1: 1767.3. Samples: 42848098. Policy #0 lag: (min: 31.0, avg: 31.5, max: 46.0) -[2023-10-17 03:37:32,215][61453] Avg episode reward: [(0, '9.940'), (1, '10.720')] -[2023-10-17 03:37:32,227][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000083968_85983232.pth... -[2023-10-17 03:37:32,227][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000083360_85360640.pth... -[2023-10-17 03:37:32,267][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000082304_84279296.pth -[2023-10-17 03:37:32,272][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000081728_83689472.pth -[2023-10-17 03:37:33,216][62408] Updated weights for policy 1, policy_version 83370 (0.0009) -[2023-10-17 03:37:33,583][62408] Updated weights for policy 1, policy_version 83380 (0.0011) -[2023-10-17 03:37:33,948][62408] Updated weights for policy 1, policy_version 83390 (0.0010) -[2023-10-17 03:37:33,966][62373] Updated weights for policy 0, policy_version 83970 (0.0009) -[2023-10-17 03:37:34,331][62373] Updated weights for policy 0, policy_version 83980 (0.0007) -[2023-10-17 03:37:34,697][62373] Updated weights for policy 0, policy_version 83990 (0.0007) -[2023-10-17 03:37:35,069][62373] Updated weights for policy 0, policy_version 84000 (0.0010) -[2023-10-17 03:37:37,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 171409408. Throughput: 0: 1775.9, 1: 1758.1. Samples: 42858016. Policy #0 lag: (min: 19.0, avg: 38.6, max: 40.0) -[2023-10-17 03:37:37,214][61453] Avg episode reward: [(0, '10.360'), (1, '10.810')] -[2023-10-17 03:37:38,065][62408] Updated weights for policy 1, policy_version 83400 (0.0008) -[2023-10-17 03:37:38,431][62408] Updated weights for policy 1, policy_version 83410 (0.0008) -[2023-10-17 03:37:38,783][62373] Updated weights for policy 0, policy_version 84010 (0.0007) -[2023-10-17 03:37:38,793][62408] Updated weights for policy 1, policy_version 83420 (0.0007) -[2023-10-17 03:37:39,143][62373] Updated weights for policy 0, policy_version 84020 (0.0010) -[2023-10-17 03:37:39,513][62373] Updated weights for policy 0, policy_version 84030 (0.0010) -[2023-10-17 03:37:42,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 171474944. Throughput: 0: 1763.9, 1: 1752.5. Samples: 42879352. Policy #0 lag: (min: 19.0, avg: 38.6, max: 40.0) -[2023-10-17 03:37:42,215][61453] Avg episode reward: [(0, '10.620'), (1, '10.300')] -[2023-10-17 03:37:42,696][62408] Updated weights for policy 1, policy_version 83430 (0.0010) -[2023-10-17 03:37:43,067][62408] Updated weights for policy 1, policy_version 83440 (0.0009) -[2023-10-17 03:37:43,432][62373] Updated weights for policy 0, policy_version 84040 (0.0009) -[2023-10-17 03:37:43,432][62408] Updated weights for policy 1, policy_version 83450 (0.0010) -[2023-10-17 03:37:43,789][62373] Updated weights for policy 0, policy_version 84050 (0.0008) -[2023-10-17 03:37:44,155][62373] Updated weights for policy 0, policy_version 84060 (0.0009) -[2023-10-17 03:37:47,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 171540480. Throughput: 0: 1772.7, 1: 1762.5. Samples: 42900916. Policy #0 lag: (min: 19.0, avg: 38.6, max: 40.0) -[2023-10-17 03:37:47,215][61453] Avg episode reward: [(0, '9.920'), (1, '11.050')] -[2023-10-17 03:37:47,403][62408] Updated weights for policy 1, policy_version 83460 (0.0007) -[2023-10-17 03:37:47,771][62408] Updated weights for policy 1, policy_version 83470 (0.0007) -[2023-10-17 03:37:47,976][62373] Updated weights for policy 0, policy_version 84070 (0.0009) -[2023-10-17 03:37:48,132][62408] Updated weights for policy 1, policy_version 83480 (0.0007) -[2023-10-17 03:37:48,348][62373] Updated weights for policy 0, policy_version 84080 (0.0007) -[2023-10-17 03:37:48,722][62373] Updated weights for policy 0, policy_version 84090 (0.0010) -[2023-10-17 03:37:52,107][62408] Updated weights for policy 1, policy_version 83490 (0.0009) -[2023-10-17 03:37:52,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 171606016. Throughput: 0: 1764.9, 1: 1725.7. Samples: 42910474. Policy #0 lag: (min: 19.0, avg: 38.6, max: 40.0) -[2023-10-17 03:37:52,214][61453] Avg episode reward: [(0, '10.490'), (1, '9.560')] -[2023-10-17 03:37:52,480][62408] Updated weights for policy 1, policy_version 83500 (0.0008) -[2023-10-17 03:37:52,551][62373] Updated weights for policy 0, policy_version 84100 (0.0010) -[2023-10-17 03:37:52,839][62408] Updated weights for policy 1, policy_version 83510 (0.0007) -[2023-10-17 03:37:52,918][62373] Updated weights for policy 0, policy_version 84110 (0.0007) -[2023-10-17 03:37:53,213][62408] Updated weights for policy 1, policy_version 83520 (0.0009) -[2023-10-17 03:37:53,274][62373] Updated weights for policy 0, policy_version 84120 (0.0007) -[2023-10-17 03:37:57,099][62408] Updated weights for policy 1, policy_version 83530 (0.0008) -[2023-10-17 03:37:57,149][62373] Updated weights for policy 0, policy_version 84130 (0.0010) -[2023-10-17 03:37:57,214][61453] Fps is (10 sec: 13107.3, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 171671552. Throughput: 0: 1765.7, 1: 1760.1. Samples: 42932412. Policy #0 lag: (min: 19.0, avg: 38.6, max: 40.0) -[2023-10-17 03:37:57,214][61453] Avg episode reward: [(0, '10.350'), (1, '9.770')] -[2023-10-17 03:37:57,457][62408] Updated weights for policy 1, policy_version 83540 (0.0008) -[2023-10-17 03:37:57,518][62373] Updated weights for policy 0, policy_version 84140 (0.0009) -[2023-10-17 03:37:57,822][62408] Updated weights for policy 1, policy_version 83550 (0.0008) -[2023-10-17 03:37:57,879][62373] Updated weights for policy 0, policy_version 84150 (0.0007) -[2023-10-17 03:37:58,248][62373] Updated weights for policy 0, policy_version 84160 (0.0009) -[2023-10-17 03:38:01,721][62408] Updated weights for policy 1, policy_version 83560 (0.0009) -[2023-10-17 03:38:01,974][62373] Updated weights for policy 0, policy_version 84170 (0.0008) -[2023-10-17 03:38:02,094][62408] Updated weights for policy 1, policy_version 83570 (0.0008) -[2023-10-17 03:38:02,214][61453] Fps is (10 sec: 13107.2, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 171737088. Throughput: 0: 1786.4, 1: 1748.0. Samples: 42953492. Policy #0 lag: (min: 19.0, avg: 38.6, max: 40.0) -[2023-10-17 03:38:02,214][61453] Avg episode reward: [(0, '10.160'), (1, '9.720')] -[2023-10-17 03:38:02,353][62373] Updated weights for policy 0, policy_version 84180 (0.0009) -[2023-10-17 03:38:02,458][62408] Updated weights for policy 1, policy_version 83580 (0.0007) -[2023-10-17 03:38:02,710][62373] Updated weights for policy 0, policy_version 84190 (0.0010) -[2023-10-17 03:38:06,165][62408] Updated weights for policy 1, policy_version 83590 (0.0008) -[2023-10-17 03:38:06,465][62373] Updated weights for policy 0, policy_version 84200 (0.0010) -[2023-10-17 03:38:06,536][62408] Updated weights for policy 1, policy_version 83600 (0.0007) -[2023-10-17 03:38:06,841][62373] Updated weights for policy 0, policy_version 84210 (0.0008) -[2023-10-17 03:38:06,894][62408] Updated weights for policy 1, policy_version 83610 (0.0007) -[2023-10-17 03:38:07,204][62373] Updated weights for policy 0, policy_version 84220 (0.0008) -[2023-10-17 03:38:07,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 171835392. Throughput: 0: 1759.4, 1: 1757.1. Samples: 42964078. Policy #0 lag: (min: 19.0, avg: 38.6, max: 40.0) -[2023-10-17 03:38:07,215][61453] Avg episode reward: [(0, '9.630'), (1, '10.420')] -[2023-10-17 03:38:10,608][62408] Updated weights for policy 1, policy_version 83620 (0.0009) -[2023-10-17 03:38:10,946][62373] Updated weights for policy 0, policy_version 84230 (0.0007) -[2023-10-17 03:38:10,979][62408] Updated weights for policy 1, policy_version 83630 (0.0008) -[2023-10-17 03:38:11,316][62373] Updated weights for policy 0, policy_version 84240 (0.0009) -[2023-10-17 03:38:11,343][62408] Updated weights for policy 1, policy_version 83640 (0.0008) -[2023-10-17 03:38:11,691][62373] Updated weights for policy 0, policy_version 84250 (0.0008) -[2023-10-17 03:38:12,214][61453] Fps is (10 sec: 19660.8, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 171933696. Throughput: 0: 1785.7, 1: 1753.4. Samples: 42985606. Policy #0 lag: (min: 19.0, avg: 38.6, max: 40.0) -[2023-10-17 03:38:12,214][61453] Avg episode reward: [(0, '10.310'), (1, '11.430')] -[2023-10-17 03:38:15,075][62408] Updated weights for policy 1, policy_version 83650 (0.0008) -[2023-10-17 03:38:15,441][62408] Updated weights for policy 1, policy_version 83660 (0.0008) -[2023-10-17 03:38:15,625][62373] Updated weights for policy 0, policy_version 84260 (0.0008) -[2023-10-17 03:38:15,802][62408] Updated weights for policy 1, policy_version 83670 (0.0007) -[2023-10-17 03:38:16,011][62373] Updated weights for policy 0, policy_version 84270 (0.0007) -[2023-10-17 03:38:16,170][62408] Updated weights for policy 1, policy_version 83680 (0.0007) -[2023-10-17 03:38:16,379][62373] Updated weights for policy 0, policy_version 84280 (0.0009) -[2023-10-17 03:38:17,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 171999232. Throughput: 0: 1763.3, 1: 1737.8. Samples: 43005644. Policy #0 lag: (min: 19.0, avg: 38.6, max: 40.0) -[2023-10-17 03:38:17,214][61453] Avg episode reward: [(0, '10.230'), (1, '11.000')] -[2023-10-17 03:38:19,965][62373] Updated weights for policy 0, policy_version 84290 (0.0008) -[2023-10-17 03:38:20,014][62408] Updated weights for policy 1, policy_version 83690 (0.0009) -[2023-10-17 03:38:20,335][62373] Updated weights for policy 0, policy_version 84300 (0.0008) -[2023-10-17 03:38:20,374][62408] Updated weights for policy 1, policy_version 83700 (0.0009) -[2023-10-17 03:38:20,697][62373] Updated weights for policy 0, policy_version 84310 (0.0008) -[2023-10-17 03:38:20,743][62408] Updated weights for policy 1, policy_version 83710 (0.0008) -[2023-10-17 03:38:21,067][62373] Updated weights for policy 0, policy_version 84320 (0.0008) -[2023-10-17 03:38:22,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 172064768. Throughput: 0: 1790.5, 1: 1760.0. Samples: 43017790. Policy #0 lag: (min: 19.0, avg: 38.6, max: 40.0) -[2023-10-17 03:38:22,214][61453] Avg episode reward: [(0, '10.490'), (1, '10.800')] -[2023-10-17 03:38:24,851][62408] Updated weights for policy 1, policy_version 83720 (0.0008) -[2023-10-17 03:38:24,922][62373] Updated weights for policy 0, policy_version 84330 (0.0007) -[2023-10-17 03:38:25,228][62408] Updated weights for policy 1, policy_version 83730 (0.0007) -[2023-10-17 03:38:25,295][62373] Updated weights for policy 0, policy_version 84340 (0.0007) -[2023-10-17 03:38:25,590][62408] Updated weights for policy 1, policy_version 83740 (0.0007) -[2023-10-17 03:38:25,652][62373] Updated weights for policy 0, policy_version 84350 (0.0008) -[2023-10-17 03:38:27,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 172130304. Throughput: 0: 1768.6, 1: 1733.1. Samples: 43036930. Policy #0 lag: (min: 19.0, avg: 38.6, max: 40.0) -[2023-10-17 03:38:27,214][61453] Avg episode reward: [(0, '10.220'), (1, '11.120')] -[2023-10-17 03:38:29,420][62373] Updated weights for policy 0, policy_version 84360 (0.0008) -[2023-10-17 03:38:29,438][62408] Updated weights for policy 1, policy_version 83750 (0.0009) -[2023-10-17 03:38:29,798][62373] Updated weights for policy 0, policy_version 84370 (0.0009) -[2023-10-17 03:38:29,817][62408] Updated weights for policy 1, policy_version 83760 (0.0008) -[2023-10-17 03:38:30,164][62373] Updated weights for policy 0, policy_version 84380 (0.0007) -[2023-10-17 03:38:30,178][62408] Updated weights for policy 1, policy_version 83770 (0.0007) -[2023-10-17 03:38:32,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 172195840. Throughput: 0: 1770.3, 1: 1745.6. Samples: 43059130. Policy #0 lag: (min: 24.0, avg: 44.7, max: 56.0) -[2023-10-17 03:38:32,215][61453] Avg episode reward: [(0, '10.370'), (1, '12.050')] -[2023-10-17 03:38:33,964][62373] Updated weights for policy 0, policy_version 84390 (0.0008) -[2023-10-17 03:38:34,052][62408] Updated weights for policy 1, policy_version 83780 (0.0008) -[2023-10-17 03:38:34,332][62373] Updated weights for policy 0, policy_version 84400 (0.0008) -[2023-10-17 03:38:34,418][62408] Updated weights for policy 1, policy_version 83790 (0.0007) -[2023-10-17 03:38:34,698][62373] Updated weights for policy 0, policy_version 84410 (0.0009) -[2023-10-17 03:38:34,781][62408] Updated weights for policy 1, policy_version 83800 (0.0008) -[2023-10-17 03:38:37,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 172261376. Throughput: 0: 1772.5, 1: 1753.3. Samples: 43069136. Policy #0 lag: (min: 24.0, avg: 44.7, max: 56.0) -[2023-10-17 03:38:37,214][61453] Avg episode reward: [(0, '10.220'), (1, '11.810')] -[2023-10-17 03:38:38,510][62373] Updated weights for policy 0, policy_version 84420 (0.0009) -[2023-10-17 03:38:38,594][62408] Updated weights for policy 1, policy_version 83810 (0.0008) -[2023-10-17 03:38:38,885][62373] Updated weights for policy 0, policy_version 84430 (0.0008) -[2023-10-17 03:38:38,961][62408] Updated weights for policy 1, policy_version 83820 (0.0007) -[2023-10-17 03:38:39,260][62373] Updated weights for policy 0, policy_version 84440 (0.0007) -[2023-10-17 03:38:39,337][62408] Updated weights for policy 1, policy_version 83830 (0.0008) -[2023-10-17 03:38:39,707][62408] Updated weights for policy 1, policy_version 83840 (0.0009) -[2023-10-17 03:38:42,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 172326912. Throughput: 0: 1772.7, 1: 1747.3. Samples: 43090812. Policy #0 lag: (min: 24.0, avg: 44.7, max: 56.0) -[2023-10-17 03:38:42,214][61453] Avg episode reward: [(0, '9.920'), (1, '11.260')] -[2023-10-17 03:38:42,914][62373] Updated weights for policy 0, policy_version 84450 (0.0008) -[2023-10-17 03:38:43,283][62373] Updated weights for policy 0, policy_version 84460 (0.0008) -[2023-10-17 03:38:43,509][62408] Updated weights for policy 1, policy_version 83850 (0.0009) -[2023-10-17 03:38:43,640][62373] Updated weights for policy 0, policy_version 84470 (0.0008) -[2023-10-17 03:38:43,865][62408] Updated weights for policy 1, policy_version 83860 (0.0007) -[2023-10-17 03:38:44,009][62373] Updated weights for policy 0, policy_version 84480 (0.0008) -[2023-10-17 03:38:44,234][62408] Updated weights for policy 1, policy_version 83870 (0.0008) -[2023-10-17 03:38:47,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 172392448. Throughput: 0: 1792.0, 1: 1765.3. Samples: 43113572. Policy #0 lag: (min: 24.0, avg: 44.7, max: 56.0) -[2023-10-17 03:38:47,215][61453] Avg episode reward: [(0, '9.830'), (1, '10.970')] -[2023-10-17 03:38:47,773][62373] Updated weights for policy 0, policy_version 84490 (0.0008) -[2023-10-17 03:38:48,037][62408] Updated weights for policy 1, policy_version 83880 (0.0008) -[2023-10-17 03:38:48,150][62373] Updated weights for policy 0, policy_version 84500 (0.0009) -[2023-10-17 03:38:48,412][62408] Updated weights for policy 1, policy_version 83890 (0.0009) -[2023-10-17 03:38:48,516][62373] Updated weights for policy 0, policy_version 84510 (0.0008) -[2023-10-17 03:38:48,777][62408] Updated weights for policy 1, policy_version 83900 (0.0010) -[2023-10-17 03:38:52,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 172457984. Throughput: 0: 1784.8, 1: 1753.2. Samples: 43123284. Policy #0 lag: (min: 24.0, avg: 44.7, max: 56.0) -[2023-10-17 03:38:52,214][61453] Avg episode reward: [(0, '9.670'), (1, '10.970')] -[2023-10-17 03:38:52,317][62373] Updated weights for policy 0, policy_version 84520 (0.0008) -[2023-10-17 03:38:52,561][62408] Updated weights for policy 1, policy_version 83910 (0.0007) -[2023-10-17 03:38:52,685][62373] Updated weights for policy 0, policy_version 84530 (0.0008) -[2023-10-17 03:38:52,931][62408] Updated weights for policy 1, policy_version 83920 (0.0007) -[2023-10-17 03:38:53,062][62373] Updated weights for policy 0, policy_version 84540 (0.0009) -[2023-10-17 03:38:53,305][62408] Updated weights for policy 1, policy_version 83930 (0.0008) -[2023-10-17 03:38:56,954][62373] Updated weights for policy 0, policy_version 84550 (0.0008) -[2023-10-17 03:38:57,141][62408] Updated weights for policy 1, policy_version 83940 (0.0009) -[2023-10-17 03:38:57,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 172523520. Throughput: 0: 1790.8, 1: 1765.9. Samples: 43145658. Policy #0 lag: (min: 24.0, avg: 44.7, max: 56.0) -[2023-10-17 03:38:57,215][61453] Avg episode reward: [(0, '9.640'), (1, '10.870')] -[2023-10-17 03:38:57,324][62373] Updated weights for policy 0, policy_version 84560 (0.0007) -[2023-10-17 03:38:57,508][62408] Updated weights for policy 1, policy_version 83950 (0.0008) -[2023-10-17 03:38:57,695][62373] Updated weights for policy 0, policy_version 84570 (0.0009) -[2023-10-17 03:38:57,872][62408] Updated weights for policy 1, policy_version 83960 (0.0008) -[2023-10-17 03:39:01,487][62373] Updated weights for policy 0, policy_version 84580 (0.0008) -[2023-10-17 03:39:01,727][62408] Updated weights for policy 1, policy_version 83970 (0.0010) -[2023-10-17 03:39:01,874][62373] Updated weights for policy 0, policy_version 84590 (0.0007) -[2023-10-17 03:39:02,101][62408] Updated weights for policy 1, policy_version 83980 (0.0008) -[2023-10-17 03:39:02,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 172589056. Throughput: 0: 1803.2, 1: 1779.2. Samples: 43166856. Policy #0 lag: (min: 24.0, avg: 44.7, max: 56.0) -[2023-10-17 03:39:02,214][61453] Avg episode reward: [(0, '9.700'), (1, '11.110')] -[2023-10-17 03:39:02,241][62373] Updated weights for policy 0, policy_version 84600 (0.0008) -[2023-10-17 03:39:02,456][62408] Updated weights for policy 1, policy_version 83990 (0.0008) -[2023-10-17 03:39:02,819][62408] Updated weights for policy 1, policy_version 84000 (0.0009) -[2023-10-17 03:39:06,019][62373] Updated weights for policy 0, policy_version 84610 (0.0009) -[2023-10-17 03:39:06,393][62373] Updated weights for policy 0, policy_version 84620 (0.0008) -[2023-10-17 03:39:06,678][62408] Updated weights for policy 1, policy_version 84010 (0.0007) -[2023-10-17 03:39:06,760][62373] Updated weights for policy 0, policy_version 84630 (0.0010) -[2023-10-17 03:39:07,049][62408] Updated weights for policy 1, policy_version 84020 (0.0008) -[2023-10-17 03:39:07,130][62373] Updated weights for policy 0, policy_version 84640 (0.0008) -[2023-10-17 03:39:07,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 172687360. Throughput: 0: 1785.6, 1: 1765.4. Samples: 43177584. Policy #0 lag: (min: 24.0, avg: 44.7, max: 56.0) -[2023-10-17 03:39:07,214][61453] Avg episode reward: [(0, '9.600'), (1, '10.360')] -[2023-10-17 03:39:07,409][62408] Updated weights for policy 1, policy_version 84030 (0.0008) -[2023-10-17 03:39:10,769][62373] Updated weights for policy 0, policy_version 84650 (0.0009) -[2023-10-17 03:39:11,140][62373] Updated weights for policy 0, policy_version 84660 (0.0009) -[2023-10-17 03:39:11,392][62408] Updated weights for policy 1, policy_version 84040 (0.0008) -[2023-10-17 03:39:11,517][62373] Updated weights for policy 0, policy_version 84670 (0.0009) -[2023-10-17 03:39:11,762][62408] Updated weights for policy 1, policy_version 84050 (0.0009) -[2023-10-17 03:39:12,128][62408] Updated weights for policy 1, policy_version 84060 (0.0011) -[2023-10-17 03:39:12,214][61453] Fps is (10 sec: 16384.0, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 172752896. Throughput: 0: 1805.6, 1: 1799.1. Samples: 43199140. Policy #0 lag: (min: 24.0, avg: 44.7, max: 56.0) -[2023-10-17 03:39:12,214][61453] Avg episode reward: [(0, '9.840'), (1, '10.340')] -[2023-10-17 03:39:15,122][62373] Updated weights for policy 0, policy_version 84680 (0.0007) -[2023-10-17 03:39:15,489][62373] Updated weights for policy 0, policy_version 84690 (0.0009) -[2023-10-17 03:39:15,865][62373] Updated weights for policy 0, policy_version 84700 (0.0007) -[2023-10-17 03:39:15,903][62408] Updated weights for policy 1, policy_version 84070 (0.0009) -[2023-10-17 03:39:16,277][62408] Updated weights for policy 1, policy_version 84080 (0.0007) -[2023-10-17 03:39:16,644][62408] Updated weights for policy 1, policy_version 84090 (0.0007) -[2023-10-17 03:39:17,214][61453] Fps is (10 sec: 16383.6, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 172851200. Throughput: 0: 1791.6, 1: 1761.5. Samples: 43219020. Policy #0 lag: (min: 24.0, avg: 44.7, max: 56.0) -[2023-10-17 03:39:17,215][61453] Avg episode reward: [(0, '10.220'), (1, '10.760')] -[2023-10-17 03:39:19,754][62373] Updated weights for policy 0, policy_version 84710 (0.0009) -[2023-10-17 03:39:20,125][62373] Updated weights for policy 0, policy_version 84720 (0.0010) -[2023-10-17 03:39:20,367][62408] Updated weights for policy 1, policy_version 84100 (0.0010) -[2023-10-17 03:39:20,501][62373] Updated weights for policy 0, policy_version 84730 (0.0007) -[2023-10-17 03:39:20,724][62408] Updated weights for policy 1, policy_version 84110 (0.0008) -[2023-10-17 03:39:21,099][62408] Updated weights for policy 1, policy_version 84120 (0.0008) -[2023-10-17 03:39:22,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 172916736. Throughput: 0: 1805.9, 1: 1791.2. Samples: 43231004. Policy #0 lag: (min: 24.0, avg: 44.7, max: 56.0) -[2023-10-17 03:39:22,214][61453] Avg episode reward: [(0, '10.350'), (1, '11.700')] -[2023-10-17 03:39:24,219][62373] Updated weights for policy 0, policy_version 84740 (0.0008) -[2023-10-17 03:39:24,589][62373] Updated weights for policy 0, policy_version 84750 (0.0008) -[2023-10-17 03:39:24,900][62408] Updated weights for policy 1, policy_version 84130 (0.0007) -[2023-10-17 03:39:24,959][62373] Updated weights for policy 0, policy_version 84760 (0.0007) -[2023-10-17 03:39:25,262][62408] Updated weights for policy 1, policy_version 84140 (0.0007) -[2023-10-17 03:39:25,635][62408] Updated weights for policy 1, policy_version 84150 (0.0008) -[2023-10-17 03:39:25,999][62408] Updated weights for policy 1, policy_version 84160 (0.0008) -[2023-10-17 03:39:27,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 172982272. Throughput: 0: 1787.4, 1: 1774.3. Samples: 43251088. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:39:27,215][61453] Avg episode reward: [(0, '9.640'), (1, '11.440')] -[2023-10-17 03:39:28,761][62373] Updated weights for policy 0, policy_version 84770 (0.0007) -[2023-10-17 03:39:29,126][62373] Updated weights for policy 0, policy_version 84780 (0.0009) -[2023-10-17 03:39:29,494][62373] Updated weights for policy 0, policy_version 84790 (0.0009) -[2023-10-17 03:39:29,702][62408] Updated weights for policy 1, policy_version 84170 (0.0007) -[2023-10-17 03:39:29,860][62373] Updated weights for policy 0, policy_version 84800 (0.0008) -[2023-10-17 03:39:30,070][62408] Updated weights for policy 1, policy_version 84180 (0.0008) -[2023-10-17 03:39:30,435][62408] Updated weights for policy 1, policy_version 84190 (0.0007) -[2023-10-17 03:39:32,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 173047808. Throughput: 0: 1776.2, 1: 1763.3. Samples: 43272848. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:39:32,214][61453] Avg episode reward: [(0, '10.200'), (1, '11.390')] -[2023-10-17 03:39:32,224][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000084800_86835200.pth... -[2023-10-17 03:39:32,224][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000084192_86212608.pth... -[2023-10-17 03:39:32,259][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000083136_85131264.pth -[2023-10-17 03:39:32,260][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000082528_84508672.pth -[2023-10-17 03:39:33,738][62373] Updated weights for policy 0, policy_version 84810 (0.0008) -[2023-10-17 03:39:34,111][62373] Updated weights for policy 0, policy_version 84820 (0.0010) -[2023-10-17 03:39:34,355][62408] Updated weights for policy 1, policy_version 84200 (0.0008) -[2023-10-17 03:39:34,474][62373] Updated weights for policy 0, policy_version 84830 (0.0007) -[2023-10-17 03:39:34,730][62408] Updated weights for policy 1, policy_version 84210 (0.0008) -[2023-10-17 03:39:35,099][62408] Updated weights for policy 1, policy_version 84220 (0.0007) -[2023-10-17 03:39:37,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 173113344. Throughput: 0: 1776.5, 1: 1773.2. Samples: 43283020. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:39:37,215][61453] Avg episode reward: [(0, '9.950'), (1, '11.620')] -[2023-10-17 03:39:38,382][62373] Updated weights for policy 0, policy_version 84840 (0.0011) -[2023-10-17 03:39:38,751][62373] Updated weights for policy 0, policy_version 84850 (0.0010) -[2023-10-17 03:39:38,871][62408] Updated weights for policy 1, policy_version 84230 (0.0009) -[2023-10-17 03:39:39,125][62373] Updated weights for policy 0, policy_version 84860 (0.0010) -[2023-10-17 03:39:39,236][62408] Updated weights for policy 1, policy_version 84240 (0.0009) -[2023-10-17 03:39:39,608][62408] Updated weights for policy 1, policy_version 84250 (0.0010) -[2023-10-17 03:39:42,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 173178880. Throughput: 0: 1772.6, 1: 1754.8. Samples: 43304394. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:39:42,214][61453] Avg episode reward: [(0, '10.780'), (1, '11.760')] -[2023-10-17 03:39:42,855][62373] Updated weights for policy 0, policy_version 84870 (0.0008) -[2023-10-17 03:39:43,220][62373] Updated weights for policy 0, policy_version 84880 (0.0007) -[2023-10-17 03:39:43,583][62373] Updated weights for policy 0, policy_version 84890 (0.0007) -[2023-10-17 03:39:43,630][62408] Updated weights for policy 1, policy_version 84260 (0.0008) -[2023-10-17 03:39:43,995][62408] Updated weights for policy 1, policy_version 84270 (0.0007) -[2023-10-17 03:39:44,368][62408] Updated weights for policy 1, policy_version 84280 (0.0008) -[2023-10-17 03:39:47,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 173244416. Throughput: 0: 1788.1, 1: 1754.5. Samples: 43326274. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:39:47,215][61453] Avg episode reward: [(0, '10.570'), (1, '11.640')] -[2023-10-17 03:39:47,453][62373] Updated weights for policy 0, policy_version 84900 (0.0008) -[2023-10-17 03:39:47,849][62373] Updated weights for policy 0, policy_version 84910 (0.0007) -[2023-10-17 03:39:48,141][62408] Updated weights for policy 1, policy_version 84290 (0.0009) -[2023-10-17 03:39:48,213][62373] Updated weights for policy 0, policy_version 84920 (0.0008) -[2023-10-17 03:39:48,508][62408] Updated weights for policy 1, policy_version 84300 (0.0009) -[2023-10-17 03:39:48,870][62408] Updated weights for policy 1, policy_version 84310 (0.0008) -[2023-10-17 03:39:49,237][62408] Updated weights for policy 1, policy_version 84320 (0.0007) -[2023-10-17 03:39:51,939][62373] Updated weights for policy 0, policy_version 84930 (0.0008) -[2023-10-17 03:39:52,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 173309952. Throughput: 0: 1769.8, 1: 1747.2. Samples: 43335850. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:39:52,214][61453] Avg episode reward: [(0, '10.450'), (1, '11.910')] -[2023-10-17 03:39:52,303][62373] Updated weights for policy 0, policy_version 84940 (0.0009) -[2023-10-17 03:39:52,662][62373] Updated weights for policy 0, policy_version 84950 (0.0007) -[2023-10-17 03:39:53,032][62373] Updated weights for policy 0, policy_version 84960 (0.0007) -[2023-10-17 03:39:53,105][62408] Updated weights for policy 1, policy_version 84330 (0.0008) -[2023-10-17 03:39:53,476][62408] Updated weights for policy 1, policy_version 84340 (0.0008) -[2023-10-17 03:39:53,836][62408] Updated weights for policy 1, policy_version 84350 (0.0009) -[2023-10-17 03:39:56,761][62373] Updated weights for policy 0, policy_version 84970 (0.0008) -[2023-10-17 03:39:57,128][62373] Updated weights for policy 0, policy_version 84980 (0.0008) -[2023-10-17 03:39:57,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 173375488. Throughput: 0: 1783.1, 1: 1749.1. Samples: 43358094. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:39:57,215][61453] Avg episode reward: [(0, '9.970'), (1, '11.830')] -[2023-10-17 03:39:57,496][62373] Updated weights for policy 0, policy_version 84990 (0.0008) -[2023-10-17 03:39:57,745][62408] Updated weights for policy 1, policy_version 84360 (0.0009) -[2023-10-17 03:39:58,121][62408] Updated weights for policy 1, policy_version 84370 (0.0007) -[2023-10-17 03:39:58,483][62408] Updated weights for policy 1, policy_version 84380 (0.0009) -[2023-10-17 03:40:01,298][62373] Updated weights for policy 0, policy_version 85000 (0.0009) -[2023-10-17 03:40:01,664][62373] Updated weights for policy 0, policy_version 85010 (0.0007) -[2023-10-17 03:40:02,035][62373] Updated weights for policy 0, policy_version 85020 (0.0008) -[2023-10-17 03:40:02,151][62408] Updated weights for policy 1, policy_version 84390 (0.0007) -[2023-10-17 03:40:02,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14218.0). Total num frames: 173473792. Throughput: 0: 1769.9, 1: 1790.0. Samples: 43379214. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:40:02,214][61453] Avg episode reward: [(0, '10.310'), (1, '11.080')] -[2023-10-17 03:40:02,518][62408] Updated weights for policy 1, policy_version 84400 (0.0008) -[2023-10-17 03:40:02,894][62408] Updated weights for policy 1, policy_version 84410 (0.0009) -[2023-10-17 03:40:05,875][62373] Updated weights for policy 0, policy_version 85030 (0.0007) -[2023-10-17 03:40:06,239][62373] Updated weights for policy 0, policy_version 85040 (0.0007) -[2023-10-17 03:40:06,618][62373] Updated weights for policy 0, policy_version 85050 (0.0007) -[2023-10-17 03:40:06,850][62408] Updated weights for policy 1, policy_version 84420 (0.0009) -[2023-10-17 03:40:07,214][61453] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 173539328. Throughput: 0: 1776.5, 1: 1751.8. Samples: 43389778. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:40:07,214][61453] Avg episode reward: [(0, '10.100'), (1, '11.510')] -[2023-10-17 03:40:07,217][62408] Updated weights for policy 1, policy_version 84430 (0.0009) -[2023-10-17 03:40:07,591][62408] Updated weights for policy 1, policy_version 84440 (0.0010) -[2023-10-17 03:40:10,540][62373] Updated weights for policy 0, policy_version 85060 (0.0008) -[2023-10-17 03:40:10,900][62373] Updated weights for policy 0, policy_version 85070 (0.0010) -[2023-10-17 03:40:11,263][62373] Updated weights for policy 0, policy_version 85080 (0.0010) -[2023-10-17 03:40:11,543][62408] Updated weights for policy 1, policy_version 84450 (0.0007) -[2023-10-17 03:40:11,922][62408] Updated weights for policy 1, policy_version 84460 (0.0007) -[2023-10-17 03:40:12,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 173604864. Throughput: 0: 1778.7, 1: 1770.4. Samples: 43410794. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:40:12,215][61453] Avg episode reward: [(0, '9.550'), (1, '11.510')] -[2023-10-17 03:40:12,286][62408] Updated weights for policy 1, policy_version 84470 (0.0009) -[2023-10-17 03:40:12,651][62408] Updated weights for policy 1, policy_version 84480 (0.0007) -[2023-10-17 03:40:15,032][62373] Updated weights for policy 0, policy_version 85090 (0.0009) -[2023-10-17 03:40:15,393][62373] Updated weights for policy 0, policy_version 85100 (0.0009) -[2023-10-17 03:40:15,769][62373] Updated weights for policy 0, policy_version 85110 (0.0008) -[2023-10-17 03:40:16,139][62373] Updated weights for policy 0, policy_version 85120 (0.0009) -[2023-10-17 03:40:16,411][62408] Updated weights for policy 1, policy_version 84490 (0.0009) -[2023-10-17 03:40:16,778][62408] Updated weights for policy 1, policy_version 84500 (0.0009) -[2023-10-17 03:40:17,156][62408] Updated weights for policy 1, policy_version 84510 (0.0010) -[2023-10-17 03:40:17,214][61453] Fps is (10 sec: 13106.9, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 173670400. Throughput: 0: 1766.3, 1: 1756.8. Samples: 43431386. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:40:17,215][61453] Avg episode reward: [(0, '9.060'), (1, '11.460')] -[2023-10-17 03:40:20,072][62373] Updated weights for policy 0, policy_version 85130 (0.0010) -[2023-10-17 03:40:20,440][62373] Updated weights for policy 0, policy_version 85140 (0.0010) -[2023-10-17 03:40:20,817][62373] Updated weights for policy 0, policy_version 85150 (0.0009) -[2023-10-17 03:40:21,043][62408] Updated weights for policy 1, policy_version 84520 (0.0009) -[2023-10-17 03:40:21,417][62408] Updated weights for policy 1, policy_version 84530 (0.0009) -[2023-10-17 03:40:21,782][62408] Updated weights for policy 1, policy_version 84540 (0.0008) -[2023-10-17 03:40:22,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 173768704. Throughput: 0: 1788.9, 1: 1763.2. Samples: 43442862. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:40:22,215][61453] Avg episode reward: [(0, '10.000'), (1, '11.080')] -[2023-10-17 03:40:24,504][62373] Updated weights for policy 0, policy_version 85160 (0.0009) -[2023-10-17 03:40:24,872][62373] Updated weights for policy 0, policy_version 85170 (0.0007) -[2023-10-17 03:40:25,243][62373] Updated weights for policy 0, policy_version 85180 (0.0007) -[2023-10-17 03:40:25,696][62408] Updated weights for policy 1, policy_version 84550 (0.0008) -[2023-10-17 03:40:26,065][62408] Updated weights for policy 1, policy_version 84560 (0.0008) -[2023-10-17 03:40:26,431][62408] Updated weights for policy 1, policy_version 84570 (0.0007) -[2023-10-17 03:40:27,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 173834240. Throughput: 0: 1769.6, 1: 1768.9. Samples: 43463626. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:40:27,215][61453] Avg episode reward: [(0, '9.860'), (1, '11.030')] -[2023-10-17 03:40:29,117][62373] Updated weights for policy 0, policy_version 85190 (0.0008) -[2023-10-17 03:40:29,492][62373] Updated weights for policy 0, policy_version 85200 (0.0009) -[2023-10-17 03:40:29,871][62373] Updated weights for policy 0, policy_version 85210 (0.0009) -[2023-10-17 03:40:30,125][62408] Updated weights for policy 1, policy_version 84580 (0.0007) -[2023-10-17 03:40:30,487][62408] Updated weights for policy 1, policy_version 84590 (0.0008) -[2023-10-17 03:40:30,854][62408] Updated weights for policy 1, policy_version 84600 (0.0009) -[2023-10-17 03:40:32,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 173899776. Throughput: 0: 1769.8, 1: 1752.1. Samples: 43484756. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:40:32,214][61453] Avg episode reward: [(0, '10.170'), (1, '10.490')] -[2023-10-17 03:40:33,788][62373] Updated weights for policy 0, policy_version 85220 (0.0008) -[2023-10-17 03:40:34,175][62373] Updated weights for policy 0, policy_version 85230 (0.0009) -[2023-10-17 03:40:34,540][62373] Updated weights for policy 0, policy_version 85240 (0.0007) -[2023-10-17 03:40:34,628][62408] Updated weights for policy 1, policy_version 84610 (0.0008) -[2023-10-17 03:40:34,993][62408] Updated weights for policy 1, policy_version 84620 (0.0007) -[2023-10-17 03:40:35,358][62408] Updated weights for policy 1, policy_version 84630 (0.0010) -[2023-10-17 03:40:35,716][62408] Updated weights for policy 1, policy_version 84640 (0.0009) -[2023-10-17 03:40:37,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 173965312. Throughput: 0: 1769.1, 1: 1777.7. Samples: 43495456. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:40:37,215][61453] Avg episode reward: [(0, '9.840'), (1, '11.840')] -[2023-10-17 03:40:38,309][62373] Updated weights for policy 0, policy_version 85250 (0.0008) -[2023-10-17 03:40:38,675][62373] Updated weights for policy 0, policy_version 85260 (0.0007) -[2023-10-17 03:40:39,052][62373] Updated weights for policy 0, policy_version 85270 (0.0008) -[2023-10-17 03:40:39,422][62373] Updated weights for policy 0, policy_version 85280 (0.0008) -[2023-10-17 03:40:39,488][62408] Updated weights for policy 1, policy_version 84650 (0.0009) -[2023-10-17 03:40:39,848][62408] Updated weights for policy 1, policy_version 84660 (0.0010) -[2023-10-17 03:40:40,226][62408] Updated weights for policy 1, policy_version 84670 (0.0007) -[2023-10-17 03:40:42,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 174030848. Throughput: 0: 1765.6, 1: 1753.7. Samples: 43516466. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:40:42,215][61453] Avg episode reward: [(0, '10.390'), (1, '11.120')] -[2023-10-17 03:40:43,216][62373] Updated weights for policy 0, policy_version 85290 (0.0008) -[2023-10-17 03:40:43,589][62373] Updated weights for policy 0, policy_version 85300 (0.0009) -[2023-10-17 03:40:43,958][62373] Updated weights for policy 0, policy_version 85310 (0.0007) -[2023-10-17 03:40:44,085][62408] Updated weights for policy 1, policy_version 84680 (0.0008) -[2023-10-17 03:40:44,470][62408] Updated weights for policy 1, policy_version 84690 (0.0007) -[2023-10-17 03:40:44,831][62408] Updated weights for policy 1, policy_version 84700 (0.0011) -[2023-10-17 03:40:47,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 174096384. Throughput: 0: 1794.6, 1: 1745.2. Samples: 43538504. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:40:47,214][61453] Avg episode reward: [(0, '10.800'), (1, '11.770')] -[2023-10-17 03:40:47,662][62373] Updated weights for policy 0, policy_version 85320 (0.0008) -[2023-10-17 03:40:48,033][62373] Updated weights for policy 0, policy_version 85330 (0.0009) -[2023-10-17 03:40:48,402][62373] Updated weights for policy 0, policy_version 85340 (0.0010) -[2023-10-17 03:40:48,601][62408] Updated weights for policy 1, policy_version 84710 (0.0009) -[2023-10-17 03:40:48,972][62408] Updated weights for policy 1, policy_version 84720 (0.0010) -[2023-10-17 03:40:49,335][62408] Updated weights for policy 1, policy_version 84730 (0.0009) -[2023-10-17 03:40:52,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 174161920. Throughput: 0: 1770.4, 1: 1749.5. Samples: 43548172. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:40:52,214][61453] Avg episode reward: [(0, '10.050'), (1, '12.000')] -[2023-10-17 03:40:52,285][62373] Updated weights for policy 0, policy_version 85350 (0.0008) -[2023-10-17 03:40:52,653][62373] Updated weights for policy 0, policy_version 85360 (0.0007) -[2023-10-17 03:40:53,025][62373] Updated weights for policy 0, policy_version 85370 (0.0007) -[2023-10-17 03:40:53,098][62408] Updated weights for policy 1, policy_version 84740 (0.0008) -[2023-10-17 03:40:53,467][62408] Updated weights for policy 1, policy_version 84750 (0.0009) -[2023-10-17 03:40:53,832][62408] Updated weights for policy 1, policy_version 84760 (0.0009) -[2023-10-17 03:40:56,720][62373] Updated weights for policy 0, policy_version 85380 (0.0007) -[2023-10-17 03:40:57,087][62373] Updated weights for policy 0, policy_version 85390 (0.0007) -[2023-10-17 03:40:57,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 174227456. Throughput: 0: 1792.3, 1: 1754.9. Samples: 43570418. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:40:57,215][61453] Avg episode reward: [(0, '10.250'), (1, '11.690')] -[2023-10-17 03:40:57,455][62373] Updated weights for policy 0, policy_version 85400 (0.0008) -[2023-10-17 03:40:57,661][62408] Updated weights for policy 1, policy_version 84770 (0.0010) -[2023-10-17 03:40:58,020][62408] Updated weights for policy 1, policy_version 84780 (0.0009) -[2023-10-17 03:40:58,386][62408] Updated weights for policy 1, policy_version 84790 (0.0008) -[2023-10-17 03:40:58,753][62408] Updated weights for policy 1, policy_version 84800 (0.0008) -[2023-10-17 03:41:01,191][62373] Updated weights for policy 0, policy_version 85410 (0.0008) -[2023-10-17 03:41:01,560][62373] Updated weights for policy 0, policy_version 85420 (0.0010) -[2023-10-17 03:41:01,933][62373] Updated weights for policy 0, policy_version 85430 (0.0010) -[2023-10-17 03:41:02,214][61453] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 174292992. Throughput: 0: 1784.8, 1: 1782.0. Samples: 43591890. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:41:02,214][61453] Avg episode reward: [(0, '10.780'), (1, '12.110')] -[2023-10-17 03:41:02,303][62373] Updated weights for policy 0, policy_version 85440 (0.0009) -[2023-10-17 03:41:02,587][62408] Updated weights for policy 1, policy_version 84810 (0.0008) -[2023-10-17 03:41:02,954][62408] Updated weights for policy 1, policy_version 84820 (0.0007) -[2023-10-17 03:41:03,330][62408] Updated weights for policy 1, policy_version 84830 (0.0009) -[2023-10-17 03:41:06,075][62373] Updated weights for policy 0, policy_version 85450 (0.0010) -[2023-10-17 03:41:06,439][62373] Updated weights for policy 0, policy_version 85460 (0.0010) -[2023-10-17 03:41:06,816][62373] Updated weights for policy 0, policy_version 85470 (0.0008) -[2023-10-17 03:41:07,170][62408] Updated weights for policy 1, policy_version 84840 (0.0009) -[2023-10-17 03:41:07,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 174391296. Throughput: 0: 1783.6, 1: 1763.7. Samples: 43602492. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:41:07,215][61453] Avg episode reward: [(0, '10.240'), (1, '11.630')] -[2023-10-17 03:41:07,523][62408] Updated weights for policy 1, policy_version 84850 (0.0011) -[2023-10-17 03:41:07,898][62408] Updated weights for policy 1, policy_version 84860 (0.0010) -[2023-10-17 03:41:10,641][62373] Updated weights for policy 0, policy_version 85480 (0.0007) -[2023-10-17 03:41:11,008][62373] Updated weights for policy 0, policy_version 85490 (0.0008) -[2023-10-17 03:41:11,379][62373] Updated weights for policy 0, policy_version 85500 (0.0009) -[2023-10-17 03:41:11,713][62408] Updated weights for policy 1, policy_version 84870 (0.0009) -[2023-10-17 03:41:12,085][62408] Updated weights for policy 1, policy_version 84880 (0.0007) -[2023-10-17 03:41:12,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 174456832. Throughput: 0: 1789.4, 1: 1773.4. Samples: 43623954. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:41:12,215][61453] Avg episode reward: [(0, '10.110'), (1, '11.540')] -[2023-10-17 03:41:12,453][62408] Updated weights for policy 1, policy_version 84890 (0.0008) -[2023-10-17 03:41:14,986][62373] Updated weights for policy 0, policy_version 85510 (0.0009) -[2023-10-17 03:41:15,359][62373] Updated weights for policy 0, policy_version 85520 (0.0010) -[2023-10-17 03:41:15,728][62373] Updated weights for policy 0, policy_version 85530 (0.0009) -[2023-10-17 03:41:16,293][62408] Updated weights for policy 1, policy_version 84900 (0.0010) -[2023-10-17 03:41:16,661][62408] Updated weights for policy 1, policy_version 84910 (0.0008) -[2023-10-17 03:41:17,026][62408] Updated weights for policy 1, policy_version 84920 (0.0008) -[2023-10-17 03:41:17,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 174522368. Throughput: 0: 1775.7, 1: 1780.1. Samples: 43644768. Policy #0 lag: (min: 22.0, avg: 37.7, max: 54.0) -[2023-10-17 03:41:17,214][61453] Avg episode reward: [(0, '10.330'), (1, '11.540')] -[2023-10-17 03:41:19,623][62373] Updated weights for policy 0, policy_version 85540 (0.0008) -[2023-10-17 03:41:20,020][62373] Updated weights for policy 0, policy_version 85550 (0.0009) -[2023-10-17 03:41:20,389][62373] Updated weights for policy 0, policy_version 85560 (0.0008) -[2023-10-17 03:41:20,647][62408] Updated weights for policy 1, policy_version 84930 (0.0008) -[2023-10-17 03:41:21,016][62408] Updated weights for policy 1, policy_version 84940 (0.0009) -[2023-10-17 03:41:21,378][62408] Updated weights for policy 1, policy_version 84950 (0.0007) -[2023-10-17 03:41:21,738][62408] Updated weights for policy 1, policy_version 84960 (0.0007) -[2023-10-17 03:41:22,214][61453] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 174620672. Throughput: 0: 1794.8, 1: 1770.4. Samples: 43655890. Policy #0 lag: (min: 22.0, avg: 37.7, max: 54.0) -[2023-10-17 03:41:22,214][61453] Avg episode reward: [(0, '9.750'), (1, '11.790')] -[2023-10-17 03:41:24,095][62373] Updated weights for policy 0, policy_version 85570 (0.0008) -[2023-10-17 03:41:24,476][62373] Updated weights for policy 0, policy_version 85580 (0.0009) -[2023-10-17 03:41:24,854][62373] Updated weights for policy 0, policy_version 85590 (0.0009) -[2023-10-17 03:41:25,217][62373] Updated weights for policy 0, policy_version 85600 (0.0009) -[2023-10-17 03:41:25,515][62408] Updated weights for policy 1, policy_version 84970 (0.0008) -[2023-10-17 03:41:25,894][62408] Updated weights for policy 1, policy_version 84980 (0.0007) -[2023-10-17 03:41:26,251][62408] Updated weights for policy 1, policy_version 84990 (0.0008) -[2023-10-17 03:41:27,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 174686208. Throughput: 0: 1779.2, 1: 1782.7. Samples: 43676752. Policy #0 lag: (min: 22.0, avg: 37.7, max: 54.0) -[2023-10-17 03:41:27,214][61453] Avg episode reward: [(0, '10.090'), (1, '11.650')] -[2023-10-17 03:41:28,982][62373] Updated weights for policy 0, policy_version 85610 (0.0010) -[2023-10-17 03:41:29,345][62373] Updated weights for policy 0, policy_version 85620 (0.0008) -[2023-10-17 03:41:29,717][62373] Updated weights for policy 0, policy_version 85630 (0.0007) -[2023-10-17 03:41:30,252][62408] Updated weights for policy 1, policy_version 85000 (0.0008) -[2023-10-17 03:41:30,631][62408] Updated weights for policy 1, policy_version 85010 (0.0008) -[2023-10-17 03:41:31,007][62408] Updated weights for policy 1, policy_version 85020 (0.0008) -[2023-10-17 03:41:32,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 174751744. Throughput: 0: 1781.4, 1: 1768.4. Samples: 43698246. Policy #0 lag: (min: 22.0, avg: 37.7, max: 54.0) -[2023-10-17 03:41:32,215][61453] Avg episode reward: [(0, '10.580'), (1, '11.520')] -[2023-10-17 03:41:32,222][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000085024_87064576.pth... -[2023-10-17 03:41:32,222][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000085632_87687168.pth... -[2023-10-17 03:41:32,258][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000083968_85983232.pth -[2023-10-17 03:41:32,263][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000083360_85360640.pth -[2023-10-17 03:41:33,317][62373] Updated weights for policy 0, policy_version 85640 (0.0010) -[2023-10-17 03:41:33,689][62373] Updated weights for policy 0, policy_version 85650 (0.0008) -[2023-10-17 03:41:34,055][62373] Updated weights for policy 0, policy_version 85660 (0.0008) -[2023-10-17 03:41:34,676][62408] Updated weights for policy 1, policy_version 85030 (0.0008) -[2023-10-17 03:41:35,048][62408] Updated weights for policy 1, policy_version 85040 (0.0009) -[2023-10-17 03:41:35,419][62408] Updated weights for policy 1, policy_version 85050 (0.0008) -[2023-10-17 03:41:37,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 174817280. Throughput: 0: 1783.6, 1: 1791.1. Samples: 43709038. Policy #0 lag: (min: 22.0, avg: 37.7, max: 54.0) -[2023-10-17 03:41:37,215][61453] Avg episode reward: [(0, '10.050'), (1, '11.100')] -[2023-10-17 03:41:37,855][62373] Updated weights for policy 0, policy_version 85670 (0.0008) -[2023-10-17 03:41:38,229][62373] Updated weights for policy 0, policy_version 85680 (0.0007) -[2023-10-17 03:41:38,610][62373] Updated weights for policy 0, policy_version 85690 (0.0009) -[2023-10-17 03:41:39,344][62408] Updated weights for policy 1, policy_version 85060 (0.0008) -[2023-10-17 03:41:39,714][62408] Updated weights for policy 1, policy_version 85070 (0.0007) -[2023-10-17 03:41:40,081][62408] Updated weights for policy 1, policy_version 85080 (0.0009) -[2023-10-17 03:41:42,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 174882816. Throughput: 0: 1782.6, 1: 1767.6. Samples: 43730180. Policy #0 lag: (min: 22.0, avg: 37.7, max: 54.0) -[2023-10-17 03:41:42,215][61453] Avg episode reward: [(0, '10.530'), (1, '11.710')] -[2023-10-17 03:41:42,297][62373] Updated weights for policy 0, policy_version 85700 (0.0007) -[2023-10-17 03:41:42,672][62373] Updated weights for policy 0, policy_version 85710 (0.0007) -[2023-10-17 03:41:43,036][62373] Updated weights for policy 0, policy_version 85720 (0.0008) -[2023-10-17 03:41:43,913][62408] Updated weights for policy 1, policy_version 85090 (0.0008) -[2023-10-17 03:41:44,291][62408] Updated weights for policy 1, policy_version 85100 (0.0009) -[2023-10-17 03:41:44,654][62408] Updated weights for policy 1, policy_version 85110 (0.0009) -[2023-10-17 03:41:45,034][62408] Updated weights for policy 1, policy_version 85120 (0.0010) -[2023-10-17 03:41:46,865][62373] Updated weights for policy 0, policy_version 85730 (0.0007) -[2023-10-17 03:41:47,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 174948352. Throughput: 0: 1797.4, 1: 1760.0. Samples: 43751972. Policy #0 lag: (min: 22.0, avg: 37.7, max: 54.0) -[2023-10-17 03:41:47,215][61453] Avg episode reward: [(0, '10.510'), (1, '11.070')] -[2023-10-17 03:41:47,231][62373] Updated weights for policy 0, policy_version 85740 (0.0008) -[2023-10-17 03:41:47,600][62373] Updated weights for policy 0, policy_version 85750 (0.0007) -[2023-10-17 03:41:47,965][62373] Updated weights for policy 0, policy_version 85760 (0.0007) -[2023-10-17 03:41:48,836][62408] Updated weights for policy 1, policy_version 85130 (0.0008) -[2023-10-17 03:41:49,209][62408] Updated weights for policy 1, policy_version 85140 (0.0009) -[2023-10-17 03:41:49,571][62408] Updated weights for policy 1, policy_version 85150 (0.0008) -[2023-10-17 03:41:51,891][62373] Updated weights for policy 0, policy_version 85770 (0.0009) -[2023-10-17 03:41:52,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 175013888. Throughput: 0: 1780.4, 1: 1758.5. Samples: 43761744. Policy #0 lag: (min: 22.0, avg: 37.7, max: 54.0) -[2023-10-17 03:41:52,214][61453] Avg episode reward: [(0, '11.010'), (1, '10.790')] -[2023-10-17 03:41:52,260][62373] Updated weights for policy 0, policy_version 85780 (0.0008) -[2023-10-17 03:41:52,629][62373] Updated weights for policy 0, policy_version 85790 (0.0007) -[2023-10-17 03:41:53,457][62408] Updated weights for policy 1, policy_version 85160 (0.0009) -[2023-10-17 03:41:53,828][62408] Updated weights for policy 1, policy_version 85170 (0.0007) -[2023-10-17 03:41:54,205][62408] Updated weights for policy 1, policy_version 85180 (0.0008) -[2023-10-17 03:41:56,449][62373] Updated weights for policy 0, policy_version 85800 (0.0007) -[2023-10-17 03:41:56,818][62373] Updated weights for policy 0, policy_version 85810 (0.0009) -[2023-10-17 03:41:57,195][62373] Updated weights for policy 0, policy_version 85820 (0.0007) -[2023-10-17 03:41:57,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 175079424. Throughput: 0: 1790.6, 1: 1763.3. Samples: 43783878. Policy #0 lag: (min: 22.0, avg: 37.7, max: 54.0) -[2023-10-17 03:41:57,214][61453] Avg episode reward: [(0, '10.970'), (1, '10.390')] -[2023-10-17 03:41:58,049][62408] Updated weights for policy 1, policy_version 85190 (0.0008) -[2023-10-17 03:41:58,412][62408] Updated weights for policy 1, policy_version 85200 (0.0007) -[2023-10-17 03:41:58,787][62408] Updated weights for policy 1, policy_version 85210 (0.0008) -[2023-10-17 03:42:00,822][62373] Updated weights for policy 0, policy_version 85830 (0.0008) -[2023-10-17 03:42:01,181][62373] Updated weights for policy 0, policy_version 85840 (0.0009) -[2023-10-17 03:42:01,546][62373] Updated weights for policy 0, policy_version 85850 (0.0010) -[2023-10-17 03:42:02,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14218.0). Total num frames: 175177728. Throughput: 0: 1775.1, 1: 1782.6. Samples: 43804862. Policy #0 lag: (min: 22.0, avg: 37.7, max: 54.0) -[2023-10-17 03:42:02,215][61453] Avg episode reward: [(0, '10.100'), (1, '10.650')] -[2023-10-17 03:42:02,611][62408] Updated weights for policy 1, policy_version 85220 (0.0008) -[2023-10-17 03:42:02,986][62408] Updated weights for policy 1, policy_version 85230 (0.0008) -[2023-10-17 03:42:03,353][62408] Updated weights for policy 1, policy_version 85240 (0.0007) -[2023-10-17 03:42:05,493][62373] Updated weights for policy 0, policy_version 85860 (0.0009) -[2023-10-17 03:42:05,884][62373] Updated weights for policy 0, policy_version 85870 (0.0009) -[2023-10-17 03:42:06,256][62373] Updated weights for policy 0, policy_version 85880 (0.0011) -[2023-10-17 03:42:07,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 175243264. Throughput: 0: 1795.8, 1: 1763.5. Samples: 43816058. Policy #0 lag: (min: 22.0, avg: 37.7, max: 54.0) -[2023-10-17 03:42:07,214][61453] Avg episode reward: [(0, '10.580'), (1, '10.750')] -[2023-10-17 03:42:07,231][62408] Updated weights for policy 1, policy_version 85250 (0.0009) -[2023-10-17 03:42:07,599][62408] Updated weights for policy 1, policy_version 85260 (0.0008) -[2023-10-17 03:42:07,962][62408] Updated weights for policy 1, policy_version 85270 (0.0008) -[2023-10-17 03:42:08,326][62408] Updated weights for policy 1, policy_version 85280 (0.0008) -[2023-10-17 03:42:09,967][62373] Updated weights for policy 0, policy_version 85890 (0.0011) -[2023-10-17 03:42:10,346][62373] Updated weights for policy 0, policy_version 85900 (0.0010) -[2023-10-17 03:42:10,705][62373] Updated weights for policy 0, policy_version 85910 (0.0010) -[2023-10-17 03:42:11,074][62373] Updated weights for policy 0, policy_version 85920 (0.0009) -[2023-10-17 03:42:12,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 175308800. Throughput: 0: 1784.3, 1: 1772.5. Samples: 43836808. Policy #0 lag: (min: 10.0, avg: 13.2, max: 42.0) -[2023-10-17 03:42:12,214][61453] Avg episode reward: [(0, '10.490'), (1, '10.770')] -[2023-10-17 03:42:12,250][62408] Updated weights for policy 1, policy_version 85290 (0.0008) -[2023-10-17 03:42:12,620][62408] Updated weights for policy 1, policy_version 85300 (0.0009) -[2023-10-17 03:42:12,992][62408] Updated weights for policy 1, policy_version 85310 (0.0007) -[2023-10-17 03:42:14,716][62373] Updated weights for policy 0, policy_version 85930 (0.0008) -[2023-10-17 03:42:15,081][62373] Updated weights for policy 0, policy_version 85940 (0.0009) -[2023-10-17 03:42:15,453][62373] Updated weights for policy 0, policy_version 85950 (0.0007) -[2023-10-17 03:42:16,984][62408] Updated weights for policy 1, policy_version 85320 (0.0008) -[2023-10-17 03:42:17,214][61453] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 175374336. Throughput: 0: 1781.0, 1: 1781.3. Samples: 43858550. Policy #0 lag: (min: 10.0, avg: 13.2, max: 42.0) -[2023-10-17 03:42:17,215][61453] Avg episode reward: [(0, '11.160'), (1, '10.660')] -[2023-10-17 03:42:17,367][62408] Updated weights for policy 1, policy_version 85330 (0.0008) -[2023-10-17 03:42:17,736][62408] Updated weights for policy 1, policy_version 85340 (0.0008) -[2023-10-17 03:42:19,189][62373] Updated weights for policy 0, policy_version 85960 (0.0008) -[2023-10-17 03:42:19,554][62373] Updated weights for policy 0, policy_version 85970 (0.0009) -[2023-10-17 03:42:19,921][62373] Updated weights for policy 0, policy_version 85980 (0.0007) -[2023-10-17 03:42:21,329][62408] Updated weights for policy 1, policy_version 85350 (0.0007) -[2023-10-17 03:42:21,693][62408] Updated weights for policy 1, policy_version 85360 (0.0007) -[2023-10-17 03:42:22,056][62408] Updated weights for policy 1, policy_version 85370 (0.0008) -[2023-10-17 03:42:22,214][61453] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 175439872. Throughput: 0: 1783.1, 1: 1767.6. Samples: 43868816. Policy #0 lag: (min: 10.0, avg: 13.2, max: 42.0) -[2023-10-17 03:42:22,214][61453] Avg episode reward: [(0, '11.000'), (1, '10.610')] -[2023-10-17 03:42:23,803][62373] Updated weights for policy 0, policy_version 85990 (0.0008) -[2023-10-17 03:42:24,175][62373] Updated weights for policy 0, policy_version 86000 (0.0008) -[2023-10-17 03:42:24,544][62373] Updated weights for policy 0, policy_version 86010 (0.0008) -[2023-10-17 03:42:25,889][62408] Updated weights for policy 1, policy_version 85380 (0.0008) -[2023-10-17 03:42:26,253][62408] Updated weights for policy 1, policy_version 85390 (0.0008) -[2023-10-17 03:42:26,625][62408] Updated weights for policy 1, policy_version 85400 (0.0008) -[2023-10-17 03:42:27,214][61453] Fps is (10 sec: 16384.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 175538176. Throughput: 0: 1777.1, 1: 1786.1. Samples: 43890524. Policy #0 lag: (min: 10.0, avg: 13.2, max: 42.0) -[2023-10-17 03:42:27,214][61453] Avg episode reward: [(0, '10.170'), (1, '11.240')] -[2023-10-17 03:42:28,206][62373] Updated weights for policy 0, policy_version 86020 (0.0007) -[2023-10-17 03:42:28,580][62373] Updated weights for policy 0, policy_version 86030 (0.0007) -[2023-10-17 03:42:28,941][62373] Updated weights for policy 0, policy_version 86040 (0.0009) -[2023-10-17 03:42:30,357][62408] Updated weights for policy 1, policy_version 85410 (0.0009) -[2023-10-17 03:42:30,731][62408] Updated weights for policy 1, policy_version 85420 (0.0010) -[2023-10-17 03:42:31,096][62408] Updated weights for policy 1, policy_version 85430 (0.0009) -[2023-10-17 03:42:31,462][62408] Updated weights for policy 1, policy_version 85440 (0.0008) -[2023-10-17 03:42:32,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 175603712. Throughput: 0: 1784.7, 1: 1761.9. Samples: 43911566. Policy #0 lag: (min: 10.0, avg: 13.2, max: 42.0) -[2023-10-17 03:42:32,215][61453] Avg episode reward: [(0, '10.510'), (1, '10.610')] -[2023-10-17 03:42:32,794][62373] Updated weights for policy 0, policy_version 86050 (0.0008) -[2023-10-17 03:42:33,177][62373] Updated weights for policy 0, policy_version 86060 (0.0008) -[2023-10-17 03:42:33,546][62373] Updated weights for policy 0, policy_version 86070 (0.0008) -[2023-10-17 03:42:33,912][62373] Updated weights for policy 0, policy_version 86080 (0.0009) -[2023-10-17 03:42:35,091][62408] Updated weights for policy 1, policy_version 85450 (0.0007) -[2023-10-17 03:42:35,466][62408] Updated weights for policy 1, policy_version 85460 (0.0008) -[2023-10-17 03:42:35,823][62408] Updated weights for policy 1, policy_version 85470 (0.0008) -[2023-10-17 03:42:37,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 175669248. Throughput: 0: 1779.8, 1: 1792.2. Samples: 43922486. Policy #0 lag: (min: 10.0, avg: 13.2, max: 42.0) -[2023-10-17 03:42:37,215][61453] Avg episode reward: [(0, '10.940'), (1, '10.180')] -[2023-10-17 03:42:37,597][62373] Updated weights for policy 0, policy_version 86090 (0.0008) -[2023-10-17 03:42:37,965][62373] Updated weights for policy 0, policy_version 86100 (0.0008) -[2023-10-17 03:42:38,346][62373] Updated weights for policy 0, policy_version 86110 (0.0008) -[2023-10-17 03:42:39,656][62408] Updated weights for policy 1, policy_version 85480 (0.0009) -[2023-10-17 03:42:40,025][62408] Updated weights for policy 1, policy_version 85490 (0.0007) -[2023-10-17 03:42:40,389][62408] Updated weights for policy 1, policy_version 85500 (0.0007) -[2023-10-17 03:42:42,091][62373] Updated weights for policy 0, policy_version 86120 (0.0010) -[2023-10-17 03:42:42,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 175734784. Throughput: 0: 1789.2, 1: 1759.0. Samples: 43943550. Policy #0 lag: (min: 10.0, avg: 13.2, max: 42.0) -[2023-10-17 03:42:42,215][61453] Avg episode reward: [(0, '10.250'), (1, '10.430')] -[2023-10-17 03:42:42,460][62373] Updated weights for policy 0, policy_version 86130 (0.0008) -[2023-10-17 03:42:42,832][62373] Updated weights for policy 0, policy_version 86140 (0.0008) -[2023-10-17 03:42:44,114][62408] Updated weights for policy 1, policy_version 85510 (0.0008) -[2023-10-17 03:42:44,489][62408] Updated weights for policy 1, policy_version 85520 (0.0007) -[2023-10-17 03:42:44,849][62408] Updated weights for policy 1, policy_version 85530 (0.0010) -[2023-10-17 03:42:46,711][62373] Updated weights for policy 0, policy_version 86150 (0.0009) -[2023-10-17 03:42:47,076][62373] Updated weights for policy 0, policy_version 86160 (0.0008) -[2023-10-17 03:42:47,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 175800320. Throughput: 0: 1803.1, 1: 1758.4. Samples: 43965128. Policy #0 lag: (min: 10.0, avg: 13.2, max: 42.0) -[2023-10-17 03:42:47,215][61453] Avg episode reward: [(0, '9.900'), (1, '10.240')] -[2023-10-17 03:42:47,440][62373] Updated weights for policy 0, policy_version 86170 (0.0008) -[2023-10-17 03:42:48,633][62408] Updated weights for policy 1, policy_version 85540 (0.0008) -[2023-10-17 03:42:48,995][62408] Updated weights for policy 1, policy_version 85550 (0.0009) -[2023-10-17 03:42:49,364][62408] Updated weights for policy 1, policy_version 85560 (0.0007) -[2023-10-17 03:42:51,279][62373] Updated weights for policy 0, policy_version 86180 (0.0009) -[2023-10-17 03:42:51,652][62373] Updated weights for policy 0, policy_version 86190 (0.0008) -[2023-10-17 03:42:52,011][62373] Updated weights for policy 0, policy_version 86200 (0.0009) -[2023-10-17 03:42:52,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 175865856. Throughput: 0: 1779.8, 1: 1761.9. Samples: 43975432. Policy #0 lag: (min: 10.0, avg: 13.2, max: 42.0) -[2023-10-17 03:42:52,215][61453] Avg episode reward: [(0, '9.990'), (1, '9.950')] -[2023-10-17 03:42:53,361][62408] Updated weights for policy 1, policy_version 85570 (0.0009) -[2023-10-17 03:42:53,733][62408] Updated weights for policy 1, policy_version 85580 (0.0007) -[2023-10-17 03:42:54,092][62408] Updated weights for policy 1, policy_version 85590 (0.0009) -[2023-10-17 03:42:54,460][62408] Updated weights for policy 1, policy_version 85600 (0.0009) -[2023-10-17 03:42:55,911][62373] Updated weights for policy 0, policy_version 86210 (0.0008) -[2023-10-17 03:42:56,277][62373] Updated weights for policy 0, policy_version 86220 (0.0010) -[2023-10-17 03:42:56,642][62373] Updated weights for policy 0, policy_version 86230 (0.0010) -[2023-10-17 03:42:57,004][62373] Updated weights for policy 0, policy_version 86240 (0.0010) -[2023-10-17 03:42:57,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14745.5, 300 sec: 14329.0). Total num frames: 175964160. Throughput: 0: 1801.4, 1: 1761.3. Samples: 43997128. Policy #0 lag: (min: 10.0, avg: 13.2, max: 42.0) -[2023-10-17 03:42:57,215][61453] Avg episode reward: [(0, '9.700'), (1, '10.400')] -[2023-10-17 03:42:58,431][62408] Updated weights for policy 1, policy_version 85610 (0.0008) -[2023-10-17 03:42:58,794][62408] Updated weights for policy 1, policy_version 85620 (0.0008) -[2023-10-17 03:42:59,165][62408] Updated weights for policy 1, policy_version 85630 (0.0010) -[2023-10-17 03:43:00,945][62373] Updated weights for policy 0, policy_version 86250 (0.0009) -[2023-10-17 03:43:01,317][62373] Updated weights for policy 0, policy_version 86260 (0.0007) -[2023-10-17 03:43:01,688][62373] Updated weights for policy 0, policy_version 86270 (0.0007) -[2023-10-17 03:43:02,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 176029696. Throughput: 0: 1769.1, 1: 1770.7. Samples: 44017842. Policy #0 lag: (min: 10.0, avg: 13.2, max: 42.0) -[2023-10-17 03:43:02,215][61453] Avg episode reward: [(0, '10.070'), (1, '9.970')] -[2023-10-17 03:43:02,973][62408] Updated weights for policy 1, policy_version 85640 (0.0010) -[2023-10-17 03:43:03,336][62408] Updated weights for policy 1, policy_version 85650 (0.0011) -[2023-10-17 03:43:03,712][62408] Updated weights for policy 1, policy_version 85660 (0.0011) -[2023-10-17 03:43:05,251][62373] Updated weights for policy 0, policy_version 86280 (0.0011) -[2023-10-17 03:43:05,611][62373] Updated weights for policy 0, policy_version 86290 (0.0008) -[2023-10-17 03:43:05,974][62373] Updated weights for policy 0, policy_version 86300 (0.0008) -[2023-10-17 03:43:07,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 176095232. Throughput: 0: 1799.9, 1: 1759.0. Samples: 44028964. Policy #0 lag: (min: 15.0, avg: 16.5, max: 40.0) -[2023-10-17 03:43:07,215][61453] Avg episode reward: [(0, '9.820'), (1, '9.310')] -[2023-10-17 03:43:07,492][62408] Updated weights for policy 1, policy_version 85670 (0.0008) -[2023-10-17 03:43:07,868][62408] Updated weights for policy 1, policy_version 85680 (0.0007) -[2023-10-17 03:43:08,229][62408] Updated weights for policy 1, policy_version 85690 (0.0009) -[2023-10-17 03:43:09,682][62373] Updated weights for policy 0, policy_version 86310 (0.0007) -[2023-10-17 03:43:10,057][62373] Updated weights for policy 0, policy_version 86320 (0.0008) -[2023-10-17 03:43:10,430][62373] Updated weights for policy 0, policy_version 86330 (0.0007) -[2023-10-17 03:43:12,034][62408] Updated weights for policy 1, policy_version 85700 (0.0007) -[2023-10-17 03:43:12,214][61453] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 176160768. Throughput: 0: 1775.8, 1: 1767.4. Samples: 44049968. Policy #0 lag: (min: 15.0, avg: 16.5, max: 40.0) -[2023-10-17 03:43:12,214][61453] Avg episode reward: [(0, '10.140'), (1, '10.200')] -[2023-10-17 03:43:12,397][62408] Updated weights for policy 1, policy_version 85710 (0.0007) -[2023-10-17 03:43:12,768][62408] Updated weights for policy 1, policy_version 85720 (0.0007) -[2023-10-17 03:43:14,082][62373] Updated weights for policy 0, policy_version 86340 (0.0010) -[2023-10-17 03:43:14,446][62373] Updated weights for policy 0, policy_version 86350 (0.0008) -[2023-10-17 03:43:14,823][62373] Updated weights for policy 0, policy_version 86360 (0.0008) -[2023-10-17 03:43:16,487][62408] Updated weights for policy 1, policy_version 85730 (0.0007) -[2023-10-17 03:43:16,854][62408] Updated weights for policy 1, policy_version 85740 (0.0007) -[2023-10-17 03:43:17,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 176226304. Throughput: 0: 1780.9, 1: 1781.2. Samples: 44071860. Policy #0 lag: (min: 15.0, avg: 16.5, max: 40.0) -[2023-10-17 03:43:17,214][61453] Avg episode reward: [(0, '10.410'), (1, '9.910')] -[2023-10-17 03:43:17,224][62408] Updated weights for policy 1, policy_version 85750 (0.0009) -[2023-10-17 03:43:17,595][62408] Updated weights for policy 1, policy_version 85760 (0.0007) -[2023-10-17 03:43:18,557][62373] Updated weights for policy 0, policy_version 86370 (0.0009) -[2023-10-17 03:43:18,925][62373] Updated weights for policy 0, policy_version 86380 (0.0009) -[2023-10-17 03:43:19,295][62373] Updated weights for policy 0, policy_version 86390 (0.0008) -[2023-10-17 03:43:19,661][62373] Updated weights for policy 0, policy_version 86400 (0.0011) -[2023-10-17 03:43:21,343][62408] Updated weights for policy 1, policy_version 85770 (0.0008) -[2023-10-17 03:43:21,712][62408] Updated weights for policy 1, policy_version 85780 (0.0008) -[2023-10-17 03:43:22,086][62408] Updated weights for policy 1, policy_version 85790 (0.0008) -[2023-10-17 03:43:22,214][61453] Fps is (10 sec: 16383.6, 60 sec: 14745.5, 300 sec: 14218.0). Total num frames: 176324608. Throughput: 0: 1781.1, 1: 1770.2. Samples: 44082296. Policy #0 lag: (min: 15.0, avg: 16.5, max: 40.0) -[2023-10-17 03:43:22,215][61453] Avg episode reward: [(0, '11.100'), (1, '10.440')] -[2023-10-17 03:43:23,393][62373] Updated weights for policy 0, policy_version 86410 (0.0008) -[2023-10-17 03:43:23,763][62373] Updated weights for policy 0, policy_version 86420 (0.0008) -[2023-10-17 03:43:24,138][62373] Updated weights for policy 0, policy_version 86430 (0.0008) -[2023-10-17 03:43:25,969][62408] Updated weights for policy 1, policy_version 85800 (0.0009) -[2023-10-17 03:43:26,338][62408] Updated weights for policy 1, policy_version 85810 (0.0008) -[2023-10-17 03:43:26,704][62408] Updated weights for policy 1, policy_version 85820 (0.0009) -[2023-10-17 03:43:27,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 176390144. Throughput: 0: 1780.4, 1: 1786.9. Samples: 44104076. Policy #0 lag: (min: 15.0, avg: 16.5, max: 40.0) -[2023-10-17 03:43:27,214][61453] Avg episode reward: [(0, '10.940'), (1, '10.620')] -[2023-10-17 03:43:27,961][62373] Updated weights for policy 0, policy_version 86440 (0.0008) -[2023-10-17 03:43:28,336][62373] Updated weights for policy 0, policy_version 86450 (0.0008) -[2023-10-17 03:43:28,706][62373] Updated weights for policy 0, policy_version 86460 (0.0010) -[2023-10-17 03:43:30,597][62408] Updated weights for policy 1, policy_version 85830 (0.0010) -[2023-10-17 03:43:30,966][62408] Updated weights for policy 1, policy_version 85840 (0.0007) -[2023-10-17 03:43:31,333][62408] Updated weights for policy 1, policy_version 85850 (0.0007) -[2023-10-17 03:43:32,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 176455680. Throughput: 0: 1798.6, 1: 1757.4. Samples: 44125146. Policy #0 lag: (min: 15.0, avg: 16.5, max: 40.0) -[2023-10-17 03:43:32,215][61453] Avg episode reward: [(0, '10.980'), (1, '10.580')] -[2023-10-17 03:43:32,225][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000085856_87916544.pth... -[2023-10-17 03:43:32,256][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000084192_86212608.pth -[2023-10-17 03:43:32,348][62373] Updated weights for policy 0, policy_version 86470 (0.0008) -[2023-10-17 03:43:32,716][62373] Updated weights for policy 0, policy_version 86480 (0.0008) -[2023-10-17 03:43:33,096][62373] Updated weights for policy 0, policy_version 86490 (0.0009) -[2023-10-17 03:43:33,311][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000086496_88571904.pth... -[2023-10-17 03:43:33,353][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000084800_86835200.pth -[2023-10-17 03:43:35,026][62408] Updated weights for policy 1, policy_version 85860 (0.0009) -[2023-10-17 03:43:35,396][62408] Updated weights for policy 1, policy_version 85870 (0.0008) -[2023-10-17 03:43:35,752][62408] Updated weights for policy 1, policy_version 85880 (0.0008) -[2023-10-17 03:43:36,982][62373] Updated weights for policy 0, policy_version 86500 (0.0008) -[2023-10-17 03:43:37,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 176521216. Throughput: 0: 1782.4, 1: 1789.7. Samples: 44136174. Policy #0 lag: (min: 15.0, avg: 16.5, max: 40.0) -[2023-10-17 03:43:37,214][61453] Avg episode reward: [(0, '10.790'), (1, '10.350')] -[2023-10-17 03:43:37,363][62373] Updated weights for policy 0, policy_version 86510 (0.0010) -[2023-10-17 03:43:37,732][62373] Updated weights for policy 0, policy_version 86520 (0.0010) -[2023-10-17 03:43:39,699][62408] Updated weights for policy 1, policy_version 85890 (0.0008) -[2023-10-17 03:43:40,067][62408] Updated weights for policy 1, policy_version 85900 (0.0009) -[2023-10-17 03:43:40,429][62408] Updated weights for policy 1, policy_version 85910 (0.0009) -[2023-10-17 03:43:40,801][62408] Updated weights for policy 1, policy_version 85920 (0.0008) -[2023-10-17 03:43:41,521][62373] Updated weights for policy 0, policy_version 86530 (0.0009) -[2023-10-17 03:43:41,897][62373] Updated weights for policy 0, policy_version 86540 (0.0008) -[2023-10-17 03:43:42,214][61453] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 176586752. Throughput: 0: 1788.1, 1: 1762.7. Samples: 44156914. Policy #0 lag: (min: 15.0, avg: 16.5, max: 40.0) -[2023-10-17 03:43:42,214][61453] Avg episode reward: [(0, '10.870'), (1, '10.310')] -[2023-10-17 03:43:42,268][62373] Updated weights for policy 0, policy_version 86550 (0.0008) -[2023-10-17 03:43:42,635][62373] Updated weights for policy 0, policy_version 86560 (0.0010) -[2023-10-17 03:43:44,463][62408] Updated weights for policy 1, policy_version 85930 (0.0009) -[2023-10-17 03:43:44,840][62408] Updated weights for policy 1, policy_version 85940 (0.0009) -[2023-10-17 03:43:45,200][62408] Updated weights for policy 1, policy_version 85950 (0.0010) -[2023-10-17 03:43:46,384][62373] Updated weights for policy 0, policy_version 86570 (0.0007) -[2023-10-17 03:43:46,757][62373] Updated weights for policy 0, policy_version 86580 (0.0008) -[2023-10-17 03:43:47,119][62373] Updated weights for policy 0, policy_version 86590 (0.0008) -[2023-10-17 03:43:47,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 176685056. Throughput: 0: 1796.5, 1: 1760.5. Samples: 44177902. Policy #0 lag: (min: 15.0, avg: 16.5, max: 40.0) -[2023-10-17 03:43:47,215][61453] Avg episode reward: [(0, '10.920'), (1, '10.130')] -[2023-10-17 03:43:49,237][62408] Updated weights for policy 1, policy_version 85960 (0.0010) -[2023-10-17 03:43:49,619][62408] Updated weights for policy 1, policy_version 85970 (0.0007) -[2023-10-17 03:43:49,983][62408] Updated weights for policy 1, policy_version 85980 (0.0007) -[2023-10-17 03:43:50,829][62373] Updated weights for policy 0, policy_version 86600 (0.0008) -[2023-10-17 03:43:51,202][62373] Updated weights for policy 0, policy_version 86610 (0.0008) -[2023-10-17 03:43:51,570][62373] Updated weights for policy 0, policy_version 86620 (0.0010) -[2023-10-17 03:43:52,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 176750592. Throughput: 0: 1785.4, 1: 1764.2. Samples: 44188694. Policy #0 lag: (min: 15.0, avg: 16.5, max: 40.0) -[2023-10-17 03:43:52,215][61453] Avg episode reward: [(0, '11.020'), (1, '10.780')] -[2023-10-17 03:43:53,750][62408] Updated weights for policy 1, policy_version 85990 (0.0009) -[2023-10-17 03:43:54,120][62408] Updated weights for policy 1, policy_version 86000 (0.0009) -[2023-10-17 03:43:54,473][62408] Updated weights for policy 1, policy_version 86010 (0.0007) -[2023-10-17 03:43:55,412][62373] Updated weights for policy 0, policy_version 86630 (0.0008) -[2023-10-17 03:43:55,782][62373] Updated weights for policy 0, policy_version 86640 (0.0008) -[2023-10-17 03:43:56,148][62373] Updated weights for policy 0, policy_version 86650 (0.0009) -[2023-10-17 03:43:57,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 176816128. Throughput: 0: 1793.6, 1: 1758.1. Samples: 44209796. Policy #0 lag: (min: 15.0, avg: 16.5, max: 40.0) -[2023-10-17 03:43:57,215][61453] Avg episode reward: [(0, '11.360'), (1, '11.030')] -[2023-10-17 03:43:58,166][62408] Updated weights for policy 1, policy_version 86020 (0.0010) -[2023-10-17 03:43:58,538][62408] Updated weights for policy 1, policy_version 86030 (0.0007) -[2023-10-17 03:43:58,895][62408] Updated weights for policy 1, policy_version 86040 (0.0010) -[2023-10-17 03:43:59,917][62373] Updated weights for policy 0, policy_version 86660 (0.0010) -[2023-10-17 03:44:00,279][62373] Updated weights for policy 0, policy_version 86670 (0.0010) -[2023-10-17 03:44:00,643][62373] Updated weights for policy 0, policy_version 86680 (0.0010) -[2023-10-17 03:44:02,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 176881664. Throughput: 0: 1773.4, 1: 1778.0. Samples: 44231672. Policy #0 lag: (min: 31.0, avg: 31.4, max: 43.0) -[2023-10-17 03:44:02,214][61453] Avg episode reward: [(0, '11.160'), (1, '10.980')] -[2023-10-17 03:44:02,577][62408] Updated weights for policy 1, policy_version 86050 (0.0009) -[2023-10-17 03:44:02,945][62408] Updated weights for policy 1, policy_version 86060 (0.0007) -[2023-10-17 03:44:03,320][62408] Updated weights for policy 1, policy_version 86070 (0.0009) -[2023-10-17 03:44:03,689][62408] Updated weights for policy 1, policy_version 86080 (0.0010) -[2023-10-17 03:44:04,403][62373] Updated weights for policy 0, policy_version 86690 (0.0009) -[2023-10-17 03:44:04,771][62373] Updated weights for policy 0, policy_version 86700 (0.0008) -[2023-10-17 03:44:05,143][62373] Updated weights for policy 0, policy_version 86710 (0.0008) -[2023-10-17 03:44:05,524][62373] Updated weights for policy 0, policy_version 86720 (0.0008) -[2023-10-17 03:44:07,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 176947200. Throughput: 0: 1793.3, 1: 1763.4. Samples: 44242346. Policy #0 lag: (min: 31.0, avg: 31.4, max: 43.0) -[2023-10-17 03:44:07,215][61453] Avg episode reward: [(0, '11.920'), (1, '10.950')] -[2023-10-17 03:44:07,492][62408] Updated weights for policy 1, policy_version 86090 (0.0007) -[2023-10-17 03:44:07,855][62408] Updated weights for policy 1, policy_version 86100 (0.0008) -[2023-10-17 03:44:08,231][62408] Updated weights for policy 1, policy_version 86110 (0.0008) -[2023-10-17 03:44:09,489][62373] Updated weights for policy 0, policy_version 86730 (0.0007) -[2023-10-17 03:44:09,859][62373] Updated weights for policy 0, policy_version 86740 (0.0007) -[2023-10-17 03:44:10,238][62373] Updated weights for policy 0, policy_version 86750 (0.0007) -[2023-10-17 03:44:11,962][62408] Updated weights for policy 1, policy_version 86120 (0.0010) -[2023-10-17 03:44:12,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 177012736. Throughput: 0: 1766.2, 1: 1780.0. Samples: 44263656. Policy #0 lag: (min: 31.0, avg: 31.4, max: 43.0) -[2023-10-17 03:44:12,214][61453] Avg episode reward: [(0, '11.640'), (1, '11.620')] -[2023-10-17 03:44:12,334][62408] Updated weights for policy 1, policy_version 86130 (0.0011) -[2023-10-17 03:44:12,706][62408] Updated weights for policy 1, policy_version 86140 (0.0008) -[2023-10-17 03:44:13,891][62373] Updated weights for policy 0, policy_version 86760 (0.0007) -[2023-10-17 03:44:14,261][62373] Updated weights for policy 0, policy_version 86770 (0.0009) -[2023-10-17 03:44:14,632][62373] Updated weights for policy 0, policy_version 86780 (0.0010) -[2023-10-17 03:44:16,386][62408] Updated weights for policy 1, policy_version 86150 (0.0009) -[2023-10-17 03:44:16,757][62408] Updated weights for policy 1, policy_version 86160 (0.0008) -[2023-10-17 03:44:17,127][62408] Updated weights for policy 1, policy_version 86170 (0.0008) -[2023-10-17 03:44:17,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 177078272. Throughput: 0: 1768.9, 1: 1791.3. Samples: 44285352. Policy #0 lag: (min: 31.0, avg: 31.4, max: 43.0) -[2023-10-17 03:44:17,215][61453] Avg episode reward: [(0, '11.890'), (1, '12.050')] -[2023-10-17 03:44:18,277][62373] Updated weights for policy 0, policy_version 86790 (0.0008) -[2023-10-17 03:44:18,647][62373] Updated weights for policy 0, policy_version 86800 (0.0010) -[2023-10-17 03:44:19,017][62373] Updated weights for policy 0, policy_version 86810 (0.0011) -[2023-10-17 03:44:20,988][62408] Updated weights for policy 1, policy_version 86180 (0.0008) -[2023-10-17 03:44:21,359][62408] Updated weights for policy 1, policy_version 86190 (0.0007) -[2023-10-17 03:44:21,726][62408] Updated weights for policy 1, policy_version 86200 (0.0008) -[2023-10-17 03:44:22,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 177176576. Throughput: 0: 1776.1, 1: 1771.6. Samples: 44295822. Policy #0 lag: (min: 31.0, avg: 31.4, max: 43.0) -[2023-10-17 03:44:22,214][61453] Avg episode reward: [(0, '12.680'), (1, '12.260')] -[2023-10-17 03:44:22,874][62373] Updated weights for policy 0, policy_version 86820 (0.0008) -[2023-10-17 03:44:23,261][62373] Updated weights for policy 0, policy_version 86830 (0.0009) -[2023-10-17 03:44:23,617][62373] Updated weights for policy 0, policy_version 86840 (0.0011) -[2023-10-17 03:44:25,656][62408] Updated weights for policy 1, policy_version 86210 (0.0010) -[2023-10-17 03:44:26,017][62408] Updated weights for policy 1, policy_version 86220 (0.0009) -[2023-10-17 03:44:26,380][62408] Updated weights for policy 1, policy_version 86230 (0.0008) -[2023-10-17 03:44:26,749][62408] Updated weights for policy 1, policy_version 86240 (0.0009) -[2023-10-17 03:44:27,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 177242112. Throughput: 0: 1776.6, 1: 1792.1. Samples: 44317506. Policy #0 lag: (min: 31.0, avg: 31.4, max: 43.0) -[2023-10-17 03:44:27,214][61453] Avg episode reward: [(0, '11.990'), (1, '12.800')] -[2023-10-17 03:44:27,439][62373] Updated weights for policy 0, policy_version 86850 (0.0007) -[2023-10-17 03:44:27,810][62373] Updated weights for policy 0, policy_version 86860 (0.0007) -[2023-10-17 03:44:28,182][62373] Updated weights for policy 0, policy_version 86870 (0.0008) -[2023-10-17 03:44:28,551][62373] Updated weights for policy 0, policy_version 86880 (0.0009) -[2023-10-17 03:44:30,621][62408] Updated weights for policy 1, policy_version 86250 (0.0008) -[2023-10-17 03:44:30,988][62408] Updated weights for policy 1, policy_version 86260 (0.0008) -[2023-10-17 03:44:31,359][62408] Updated weights for policy 1, policy_version 86270 (0.0008) -[2023-10-17 03:44:32,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 177307648. Throughput: 0: 1803.3, 1: 1770.2. Samples: 44338708. Policy #0 lag: (min: 31.0, avg: 31.4, max: 43.0) -[2023-10-17 03:44:32,215][61453] Avg episode reward: [(0, '11.970'), (1, '12.570')] -[2023-10-17 03:44:32,222][62373] Updated weights for policy 0, policy_version 86890 (0.0009) -[2023-10-17 03:44:32,590][62373] Updated weights for policy 0, policy_version 86900 (0.0008) -[2023-10-17 03:44:32,961][62373] Updated weights for policy 0, policy_version 86910 (0.0007) -[2023-10-17 03:44:35,298][62408] Updated weights for policy 1, policy_version 86280 (0.0010) -[2023-10-17 03:44:35,679][62408] Updated weights for policy 1, policy_version 86290 (0.0008) -[2023-10-17 03:44:36,048][62408] Updated weights for policy 1, policy_version 86300 (0.0008) -[2023-10-17 03:44:36,962][62373] Updated weights for policy 0, policy_version 86920 (0.0009) -[2023-10-17 03:44:37,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 177373184. Throughput: 0: 1779.5, 1: 1803.7. Samples: 44349936. Policy #0 lag: (min: 31.0, avg: 31.4, max: 43.0) -[2023-10-17 03:44:37,214][61453] Avg episode reward: [(0, '12.290'), (1, '11.850')] -[2023-10-17 03:44:37,326][62373] Updated weights for policy 0, policy_version 86930 (0.0008) -[2023-10-17 03:44:37,698][62373] Updated weights for policy 0, policy_version 86940 (0.0008) -[2023-10-17 03:44:39,950][62408] Updated weights for policy 1, policy_version 86310 (0.0008) -[2023-10-17 03:44:40,324][62408] Updated weights for policy 1, policy_version 86320 (0.0009) -[2023-10-17 03:44:40,683][62408] Updated weights for policy 1, policy_version 86330 (0.0010) -[2023-10-17 03:44:41,481][62373] Updated weights for policy 0, policy_version 86950 (0.0009) -[2023-10-17 03:44:41,851][62373] Updated weights for policy 0, policy_version 86960 (0.0009) -[2023-10-17 03:44:42,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 177438720. Throughput: 0: 1803.5, 1: 1773.3. Samples: 44370754. Policy #0 lag: (min: 31.0, avg: 31.4, max: 43.0) -[2023-10-17 03:44:42,215][61453] Avg episode reward: [(0, '12.000'), (1, '11.060')] -[2023-10-17 03:44:42,225][62373] Updated weights for policy 0, policy_version 86970 (0.0007) -[2023-10-17 03:44:44,245][62408] Updated weights for policy 1, policy_version 86340 (0.0010) -[2023-10-17 03:44:44,610][62408] Updated weights for policy 1, policy_version 86350 (0.0010) -[2023-10-17 03:44:44,976][62408] Updated weights for policy 1, policy_version 86360 (0.0008) -[2023-10-17 03:44:45,808][62373] Updated weights for policy 0, policy_version 86980 (0.0008) -[2023-10-17 03:44:46,186][62373] Updated weights for policy 0, policy_version 86990 (0.0009) -[2023-10-17 03:44:46,552][62373] Updated weights for policy 0, policy_version 87000 (0.0010) -[2023-10-17 03:44:47,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 177537024. Throughput: 0: 1789.2, 1: 1767.6. Samples: 44391726. Policy #0 lag: (min: 31.0, avg: 31.4, max: 43.0) -[2023-10-17 03:44:47,215][61453] Avg episode reward: [(0, '11.930'), (1, '10.590')] -[2023-10-17 03:44:48,956][62408] Updated weights for policy 1, policy_version 86370 (0.0008) -[2023-10-17 03:44:49,325][62408] Updated weights for policy 1, policy_version 86380 (0.0008) -[2023-10-17 03:44:49,686][62408] Updated weights for policy 1, policy_version 86390 (0.0009) -[2023-10-17 03:44:50,047][62408] Updated weights for policy 1, policy_version 86400 (0.0010) -[2023-10-17 03:44:50,314][62373] Updated weights for policy 0, policy_version 87010 (0.0008) -[2023-10-17 03:44:50,676][62373] Updated weights for policy 0, policy_version 87020 (0.0009) -[2023-10-17 03:44:51,041][62373] Updated weights for policy 0, policy_version 87030 (0.0010) -[2023-10-17 03:44:51,415][62373] Updated weights for policy 0, policy_version 87040 (0.0010) -[2023-10-17 03:44:52,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 177602560. Throughput: 0: 1800.6, 1: 1768.5. Samples: 44402956. Policy #0 lag: (min: 31.0, avg: 31.4, max: 43.0) -[2023-10-17 03:44:52,215][61453] Avg episode reward: [(0, '11.410'), (1, '10.260')] -[2023-10-17 03:44:53,922][62408] Updated weights for policy 1, policy_version 86410 (0.0009) -[2023-10-17 03:44:54,289][62408] Updated weights for policy 1, policy_version 86420 (0.0008) -[2023-10-17 03:44:54,663][62408] Updated weights for policy 1, policy_version 86430 (0.0008) -[2023-10-17 03:44:55,174][62373] Updated weights for policy 0, policy_version 87050 (0.0008) -[2023-10-17 03:44:55,551][62373] Updated weights for policy 0, policy_version 87060 (0.0008) -[2023-10-17 03:44:55,921][62373] Updated weights for policy 0, policy_version 87070 (0.0009) -[2023-10-17 03:44:57,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 177668096. Throughput: 0: 1792.2, 1: 1760.3. Samples: 44423522. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:44:57,215][61453] Avg episode reward: [(0, '10.860'), (1, '11.060')] -[2023-10-17 03:44:58,625][62408] Updated weights for policy 1, policy_version 86440 (0.0010) -[2023-10-17 03:44:58,988][62408] Updated weights for policy 1, policy_version 86450 (0.0011) -[2023-10-17 03:44:59,366][62408] Updated weights for policy 1, policy_version 86460 (0.0008) -[2023-10-17 03:44:59,677][62373] Updated weights for policy 0, policy_version 87080 (0.0008) -[2023-10-17 03:45:00,046][62373] Updated weights for policy 0, policy_version 87090 (0.0007) -[2023-10-17 03:45:00,418][62373] Updated weights for policy 0, policy_version 87100 (0.0008) -[2023-10-17 03:45:02,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 177733632. Throughput: 0: 1788.8, 1: 1769.1. Samples: 44445458. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:45:02,215][61453] Avg episode reward: [(0, '11.130'), (1, '9.640')] -[2023-10-17 03:45:03,237][62408] Updated weights for policy 1, policy_version 86470 (0.0009) -[2023-10-17 03:45:03,610][62408] Updated weights for policy 1, policy_version 86480 (0.0008) -[2023-10-17 03:45:03,974][62408] Updated weights for policy 1, policy_version 86490 (0.0007) -[2023-10-17 03:45:04,207][62373] Updated weights for policy 0, policy_version 87110 (0.0008) -[2023-10-17 03:45:04,562][62373] Updated weights for policy 0, policy_version 87120 (0.0008) -[2023-10-17 03:45:04,932][62373] Updated weights for policy 0, policy_version 87130 (0.0011) -[2023-10-17 03:45:07,214][61453] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 177799168. Throughput: 0: 1792.0, 1: 1756.1. Samples: 44455486. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:45:07,214][61453] Avg episode reward: [(0, '10.580'), (1, '10.380')] -[2023-10-17 03:45:07,740][62408] Updated weights for policy 1, policy_version 86500 (0.0008) -[2023-10-17 03:45:08,100][62408] Updated weights for policy 1, policy_version 86510 (0.0009) -[2023-10-17 03:45:08,470][62408] Updated weights for policy 1, policy_version 86520 (0.0007) -[2023-10-17 03:45:08,672][62373] Updated weights for policy 0, policy_version 87140 (0.0009) -[2023-10-17 03:45:09,041][62373] Updated weights for policy 0, policy_version 87150 (0.0010) -[2023-10-17 03:45:09,415][62373] Updated weights for policy 0, policy_version 87160 (0.0007) -[2023-10-17 03:45:12,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 177864704. Throughput: 0: 1787.0, 1: 1768.5. Samples: 44477506. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:45:12,215][61453] Avg episode reward: [(0, '10.310'), (1, '11.130')] -[2023-10-17 03:45:12,255][62408] Updated weights for policy 1, policy_version 86530 (0.0007) -[2023-10-17 03:45:12,626][62408] Updated weights for policy 1, policy_version 86540 (0.0009) -[2023-10-17 03:45:12,994][62408] Updated weights for policy 1, policy_version 86550 (0.0009) -[2023-10-17 03:45:13,279][62373] Updated weights for policy 0, policy_version 87170 (0.0008) -[2023-10-17 03:45:13,356][62408] Updated weights for policy 1, policy_version 86560 (0.0008) -[2023-10-17 03:45:13,659][62373] Updated weights for policy 0, policy_version 87180 (0.0007) -[2023-10-17 03:45:14,017][62373] Updated weights for policy 0, policy_version 87190 (0.0012) -[2023-10-17 03:45:14,381][62373] Updated weights for policy 0, policy_version 87200 (0.0009) -[2023-10-17 03:45:17,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 177930240. Throughput: 0: 1779.5, 1: 1787.3. Samples: 44499216. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:45:17,215][61453] Avg episode reward: [(0, '10.150'), (1, '11.480')] -[2023-10-17 03:45:17,263][62408] Updated weights for policy 1, policy_version 86570 (0.0009) -[2023-10-17 03:45:17,624][62408] Updated weights for policy 1, policy_version 86580 (0.0010) -[2023-10-17 03:45:17,989][62408] Updated weights for policy 1, policy_version 86590 (0.0009) -[2023-10-17 03:45:18,123][62373] Updated weights for policy 0, policy_version 87210 (0.0007) -[2023-10-17 03:45:18,492][62373] Updated weights for policy 0, policy_version 87220 (0.0010) -[2023-10-17 03:45:18,855][62373] Updated weights for policy 0, policy_version 87230 (0.0007) -[2023-10-17 03:45:21,920][62408] Updated weights for policy 1, policy_version 86600 (0.0008) -[2023-10-17 03:45:22,214][61453] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 177995776. Throughput: 0: 1779.7, 1: 1752.7. Samples: 44508894. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:45:22,215][61453] Avg episode reward: [(0, '10.360'), (1, '10.980')] -[2023-10-17 03:45:22,295][62408] Updated weights for policy 1, policy_version 86610 (0.0007) -[2023-10-17 03:45:22,609][62373] Updated weights for policy 0, policy_version 87240 (0.0008) -[2023-10-17 03:45:22,656][62408] Updated weights for policy 1, policy_version 86620 (0.0008) -[2023-10-17 03:45:22,973][62373] Updated weights for policy 0, policy_version 87250 (0.0007) -[2023-10-17 03:45:23,348][62373] Updated weights for policy 0, policy_version 87260 (0.0008) -[2023-10-17 03:45:26,375][62408] Updated weights for policy 1, policy_version 86630 (0.0008) -[2023-10-17 03:45:26,736][62408] Updated weights for policy 1, policy_version 86640 (0.0008) -[2023-10-17 03:45:26,991][62373] Updated weights for policy 0, policy_version 87270 (0.0007) -[2023-10-17 03:45:27,110][62408] Updated weights for policy 1, policy_version 86650 (0.0008) -[2023-10-17 03:45:27,214][61453] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 178061312. Throughput: 0: 1783.2, 1: 1780.1. Samples: 44531104. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:45:27,214][61453] Avg episode reward: [(0, '10.630'), (1, '11.440')] -[2023-10-17 03:45:27,361][62373] Updated weights for policy 0, policy_version 87280 (0.0010) -[2023-10-17 03:45:27,748][62373] Updated weights for policy 0, policy_version 87290 (0.0011) -[2023-10-17 03:45:30,971][62408] Updated weights for policy 1, policy_version 86660 (0.0008) -[2023-10-17 03:45:31,351][62408] Updated weights for policy 1, policy_version 86670 (0.0010) -[2023-10-17 03:45:31,542][62373] Updated weights for policy 0, policy_version 87300 (0.0009) -[2023-10-17 03:45:31,719][62408] Updated weights for policy 1, policy_version 86680 (0.0008) -[2023-10-17 03:45:31,905][62373] Updated weights for policy 0, policy_version 87310 (0.0010) -[2023-10-17 03:45:32,214][61453] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 178159616. Throughput: 0: 1797.3, 1: 1750.0. Samples: 44551354. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:45:32,214][61453] Avg episode reward: [(0, '10.660'), (1, '10.970')] -[2023-10-17 03:45:32,224][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000086688_88768512.pth... -[2023-10-17 03:45:32,257][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000085024_87064576.pth -[2023-10-17 03:45:32,264][62373] Updated weights for policy 0, policy_version 87320 (0.0007) -[2023-10-17 03:45:32,561][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000087328_89423872.pth... -[2023-10-17 03:45:32,601][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000085632_87687168.pth -[2023-10-17 03:45:35,477][62408] Updated weights for policy 1, policy_version 86690 (0.0008) -[2023-10-17 03:45:35,851][62408] Updated weights for policy 1, policy_version 86700 (0.0010) -[2023-10-17 03:45:36,090][62373] Updated weights for policy 0, policy_version 87330 (0.0008) -[2023-10-17 03:45:36,215][62408] Updated weights for policy 1, policy_version 86710 (0.0009) -[2023-10-17 03:45:36,460][62373] Updated weights for policy 0, policy_version 87340 (0.0008) -[2023-10-17 03:45:36,581][62408] Updated weights for policy 1, policy_version 86720 (0.0007) -[2023-10-17 03:45:36,820][62373] Updated weights for policy 0, policy_version 87350 (0.0008) -[2023-10-17 03:45:37,188][62373] Updated weights for policy 0, policy_version 87360 (0.0008) -[2023-10-17 03:45:37,214][61453] Fps is (10 sec: 19660.3, 60 sec: 14745.5, 300 sec: 14329.1). Total num frames: 178257920. Throughput: 0: 1778.7, 1: 1774.2. Samples: 44562838. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:45:37,215][61453] Avg episode reward: [(0, '10.500'), (1, '11.090')] -[2023-10-17 03:45:40,568][62408] Updated weights for policy 1, policy_version 86730 (0.0008) -[2023-10-17 03:45:40,942][62408] Updated weights for policy 1, policy_version 86740 (0.0009) -[2023-10-17 03:45:41,223][62373] Updated weights for policy 0, policy_version 87370 (0.0008) -[2023-10-17 03:45:41,306][62408] Updated weights for policy 1, policy_version 86750 (0.0009) -[2023-10-17 03:45:41,585][62373] Updated weights for policy 0, policy_version 87380 (0.0007) -[2023-10-17 03:45:41,957][62373] Updated weights for policy 0, policy_version 87390 (0.0007) -[2023-10-17 03:45:42,214][61453] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 178323456. Throughput: 0: 1803.3, 1: 1756.1. Samples: 44583694. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:45:42,215][61453] Avg episode reward: [(0, '9.730'), (1, '11.660')] -[2023-10-17 03:45:45,145][62408] Updated weights for policy 1, policy_version 86760 (0.0009) -[2023-10-17 03:45:45,507][62408] Updated weights for policy 1, policy_version 86770 (0.0008) -[2023-10-17 03:45:45,632][62373] Updated weights for policy 0, policy_version 87400 (0.0009) -[2023-10-17 03:45:45,871][62408] Updated weights for policy 1, policy_version 86780 (0.0007) -[2023-10-17 03:45:46,004][62373] Updated weights for policy 0, policy_version 87410 (0.0008) -[2023-10-17 03:45:46,369][62373] Updated weights for policy 0, policy_version 87420 (0.0009) -[2023-10-17 03:45:47,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14329.0). Total num frames: 178388992. Throughput: 0: 1770.9, 1: 1747.9. Samples: 44603804. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:45:47,215][61453] Avg episode reward: [(0, '9.910'), (1, '11.370')] -[2023-10-17 03:45:49,730][62408] Updated weights for policy 1, policy_version 86790 (0.0010) -[2023-10-17 03:45:50,089][62373] Updated weights for policy 0, policy_version 87430 (0.0008) -[2023-10-17 03:45:50,093][62408] Updated weights for policy 1, policy_version 86800 (0.0009) -[2023-10-17 03:45:50,455][62373] Updated weights for policy 0, policy_version 87440 (0.0008) -[2023-10-17 03:45:50,462][62408] Updated weights for policy 1, policy_version 86810 (0.0008) -[2023-10-17 03:45:50,831][62373] Updated weights for policy 0, policy_version 87450 (0.0009) -[2023-10-17 03:45:52,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 178454528. Throughput: 0: 1789.0, 1: 1766.6. Samples: 44615486. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:45:52,215][61453] Avg episode reward: [(0, '10.180'), (1, '10.870')] -[2023-10-17 03:45:54,438][62408] Updated weights for policy 1, policy_version 86820 (0.0009) -[2023-10-17 03:45:54,810][62408] Updated weights for policy 1, policy_version 86830 (0.0010) -[2023-10-17 03:45:54,842][62373] Updated weights for policy 0, policy_version 87460 (0.0010) -[2023-10-17 03:45:55,165][62408] Updated weights for policy 1, policy_version 86840 (0.0009) -[2023-10-17 03:45:55,244][62373] Updated weights for policy 0, policy_version 87470 (0.0007) -[2023-10-17 03:45:55,610][62373] Updated weights for policy 0, policy_version 87480 (0.0007) -[2023-10-17 03:45:57,214][61453] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 178520064. Throughput: 0: 1759.4, 1: 1739.6. Samples: 44634960. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:45:57,214][61453] Avg episode reward: [(0, '10.660'), (1, '10.850')] -[2023-10-17 03:45:58,940][62408] Updated weights for policy 1, policy_version 86850 (0.0008) -[2023-10-17 03:45:59,304][62408] Updated weights for policy 1, policy_version 86860 (0.0008) -[2023-10-17 03:45:59,460][62373] Updated weights for policy 0, policy_version 87490 (0.0007) -[2023-10-17 03:45:59,665][62408] Updated weights for policy 1, policy_version 86870 (0.0007) -[2023-10-17 03:45:59,826][62373] Updated weights for policy 0, policy_version 87500 (0.0009) -[2023-10-17 03:46:00,038][62408] Updated weights for policy 1, policy_version 86880 (0.0008) -[2023-10-17 03:46:00,201][62373] Updated weights for policy 0, policy_version 87510 (0.0008) -[2023-10-17 03:46:00,577][62373] Updated weights for policy 0, policy_version 87520 (0.0008) -[2023-10-17 03:46:02,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 178585600. Throughput: 0: 1761.8, 1: 1745.4. Samples: 44657040. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:46:02,214][61453] Avg episode reward: [(0, '10.850'), (1, '11.350')] -[2023-10-17 03:46:03,851][62408] Updated weights for policy 1, policy_version 86890 (0.0008) -[2023-10-17 03:46:04,215][62408] Updated weights for policy 1, policy_version 86900 (0.0009) -[2023-10-17 03:46:04,391][62373] Updated weights for policy 0, policy_version 87530 (0.0008) -[2023-10-17 03:46:04,579][62408] Updated weights for policy 1, policy_version 86910 (0.0007) -[2023-10-17 03:46:04,753][62373] Updated weights for policy 0, policy_version 87540 (0.0007) -[2023-10-17 03:46:05,133][62373] Updated weights for policy 0, policy_version 87550 (0.0008) -[2023-10-17 03:46:07,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 178651136. Throughput: 0: 1772.4, 1: 1745.0. Samples: 44667178. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:46:07,214][61453] Avg episode reward: [(0, '10.530'), (1, '11.420')] -[2023-10-17 03:46:08,559][62408] Updated weights for policy 1, policy_version 86920 (0.0007) -[2023-10-17 03:46:08,928][62408] Updated weights for policy 1, policy_version 86930 (0.0007) -[2023-10-17 03:46:09,077][62373] Updated weights for policy 0, policy_version 87560 (0.0009) -[2023-10-17 03:46:09,291][62408] Updated weights for policy 1, policy_version 86940 (0.0008) -[2023-10-17 03:46:09,451][62373] Updated weights for policy 0, policy_version 87570 (0.0008) -[2023-10-17 03:46:09,817][62373] Updated weights for policy 0, policy_version 87580 (0.0008) -[2023-10-17 03:46:12,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 178716672. Throughput: 0: 1753.7, 1: 1748.2. Samples: 44688690. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:46:12,214][61453] Avg episode reward: [(0, '10.710'), (1, '12.060')] -[2023-10-17 03:46:13,137][62408] Updated weights for policy 1, policy_version 86950 (0.0007) -[2023-10-17 03:46:13,392][62373] Updated weights for policy 0, policy_version 87590 (0.0009) -[2023-10-17 03:46:13,534][62408] Updated weights for policy 1, policy_version 86960 (0.0010) -[2023-10-17 03:46:13,762][62373] Updated weights for policy 0, policy_version 87600 (0.0008) -[2023-10-17 03:46:13,905][62408] Updated weights for policy 1, policy_version 86970 (0.0008) -[2023-10-17 03:46:14,130][62373] Updated weights for policy 0, policy_version 87610 (0.0009) -[2023-10-17 03:46:17,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 178782208. Throughput: 0: 1770.2, 1: 1774.1. Samples: 44710848. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:46:17,215][61453] Avg episode reward: [(0, '10.950'), (1, '11.910')] -[2023-10-17 03:46:17,683][62408] Updated weights for policy 1, policy_version 86980 (0.0009) -[2023-10-17 03:46:18,044][62373] Updated weights for policy 0, policy_version 87620 (0.0008) -[2023-10-17 03:46:18,046][62408] Updated weights for policy 1, policy_version 86990 (0.0007) -[2023-10-17 03:46:18,413][62408] Updated weights for policy 1, policy_version 87000 (0.0007) -[2023-10-17 03:46:18,418][62373] Updated weights for policy 0, policy_version 87630 (0.0009) -[2023-10-17 03:46:18,787][62373] Updated weights for policy 0, policy_version 87640 (0.0007) -[2023-10-17 03:46:22,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 178847744. Throughput: 0: 1754.8, 1: 1746.6. Samples: 44720398. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:46:22,215][61453] Avg episode reward: [(0, '11.260'), (1, '11.270')] -[2023-10-17 03:46:22,250][62408] Updated weights for policy 1, policy_version 87010 (0.0007) -[2023-10-17 03:46:22,612][62408] Updated weights for policy 1, policy_version 87020 (0.0008) -[2023-10-17 03:46:22,757][62373] Updated weights for policy 0, policy_version 87650 (0.0010) -[2023-10-17 03:46:22,981][62408] Updated weights for policy 1, policy_version 87030 (0.0007) -[2023-10-17 03:46:23,122][62373] Updated weights for policy 0, policy_version 87660 (0.0008) -[2023-10-17 03:46:23,337][62408] Updated weights for policy 1, policy_version 87040 (0.0010) -[2023-10-17 03:46:23,486][62373] Updated weights for policy 0, policy_version 87670 (0.0009) -[2023-10-17 03:46:23,857][62373] Updated weights for policy 0, policy_version 87680 (0.0008) -[2023-10-17 03:46:27,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 178913280. Throughput: 0: 1757.3, 1: 1764.7. Samples: 44742182. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:46:27,215][61453] Avg episode reward: [(0, '11.130'), (1, '11.380')] -[2023-10-17 03:46:27,226][62408] Updated weights for policy 1, policy_version 87050 (0.0007) -[2023-10-17 03:46:27,593][62408] Updated weights for policy 1, policy_version 87060 (0.0008) -[2023-10-17 03:46:27,671][62373] Updated weights for policy 0, policy_version 87690 (0.0009) -[2023-10-17 03:46:27,954][62408] Updated weights for policy 1, policy_version 87070 (0.0009) -[2023-10-17 03:46:28,039][62373] Updated weights for policy 0, policy_version 87700 (0.0008) -[2023-10-17 03:46:28,417][62373] Updated weights for policy 0, policy_version 87710 (0.0007) -[2023-10-17 03:46:31,914][62408] Updated weights for policy 1, policy_version 87080 (0.0010) -[2023-10-17 03:46:32,144][62373] Updated weights for policy 0, policy_version 87720 (0.0009) -[2023-10-17 03:46:32,214][61453] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 178978816. Throughput: 0: 1786.4, 1: 1764.3. Samples: 44763582. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:46:32,214][61453] Avg episode reward: [(0, '11.530'), (1, '11.210')] -[2023-10-17 03:46:32,293][62408] Updated weights for policy 1, policy_version 87090 (0.0008) -[2023-10-17 03:46:32,515][62373] Updated weights for policy 0, policy_version 87730 (0.0007) -[2023-10-17 03:46:32,663][62408] Updated weights for policy 1, policy_version 87100 (0.0010) -[2023-10-17 03:46:32,885][62373] Updated weights for policy 0, policy_version 87740 (0.0007) -[2023-10-17 03:46:36,691][62408] Updated weights for policy 1, policy_version 87110 (0.0010) -[2023-10-17 03:46:36,750][62373] Updated weights for policy 0, policy_version 87750 (0.0007) -[2023-10-17 03:46:37,056][62408] Updated weights for policy 1, policy_version 87120 (0.0008) -[2023-10-17 03:46:37,114][62373] Updated weights for policy 0, policy_version 87760 (0.0008) -[2023-10-17 03:46:37,214][61453] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 14106.9). Total num frames: 179044352. Throughput: 0: 1760.3, 1: 1744.6. Samples: 44773206. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:46:37,214][61453] Avg episode reward: [(0, '10.840'), (1, '11.990')] -[2023-10-17 03:46:37,421][62408] Updated weights for policy 1, policy_version 87130 (0.0007) -[2023-10-17 03:46:37,479][62373] Updated weights for policy 0, policy_version 87770 (0.0008) -[2023-10-17 03:46:41,136][62408] Updated weights for policy 1, policy_version 87140 (0.0008) -[2023-10-17 03:46:41,365][62373] Updated weights for policy 0, policy_version 87780 (0.0008) -[2023-10-17 03:46:41,507][62408] Updated weights for policy 1, policy_version 87150 (0.0007) -[2023-10-17 03:46:41,748][62373] Updated weights for policy 0, policy_version 87790 (0.0007) -[2023-10-17 03:46:41,877][62408] Updated weights for policy 1, policy_version 87160 (0.0009) -[2023-10-17 03:46:42,123][62373] Updated weights for policy 0, policy_version 87800 (0.0007) -[2023-10-17 03:46:42,214][61453] Fps is (10 sec: 16384.3, 60 sec: 13653.4, 300 sec: 14218.0). Total num frames: 179142656. Throughput: 0: 1794.2, 1: 1768.0. Samples: 44795260. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:46:42,214][61453] Avg episode reward: [(0, '10.710'), (1, '11.230')] -[2023-10-17 03:46:45,701][62408] Updated weights for policy 1, policy_version 87170 (0.0009) -[2023-10-17 03:46:45,896][62373] Updated weights for policy 0, policy_version 87810 (0.0009) -[2023-10-17 03:46:46,064][62408] Updated weights for policy 1, policy_version 87180 (0.0007) -[2023-10-17 03:46:46,255][62373] Updated weights for policy 0, policy_version 87820 (0.0009) -[2023-10-17 03:46:46,429][62408] Updated weights for policy 1, policy_version 87190 (0.0007) -[2023-10-17 03:46:46,629][62373] Updated weights for policy 0, policy_version 87830 (0.0008) -[2023-10-17 03:46:46,794][62408] Updated weights for policy 1, policy_version 87200 (0.0009) -[2023-10-17 03:46:46,992][62373] Updated weights for policy 0, policy_version 87840 (0.0007) -[2023-10-17 03:46:47,214][61453] Fps is (10 sec: 19660.4, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 179240960. Throughput: 0: 1764.4, 1: 1733.5. Samples: 44814444. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) -[2023-10-17 03:46:47,215][61453] Avg episode reward: [(0, '10.900'), (1, '10.340')] -[2023-10-17 03:46:50,509][62408] Updated weights for policy 1, policy_version 87210 (0.0008) -[2023-10-17 03:46:50,876][62408] Updated weights for policy 1, policy_version 87220 (0.0008) -[2023-10-17 03:46:50,913][62373] Updated weights for policy 0, policy_version 87850 (0.0007) -[2023-10-17 03:46:51,239][62408] Updated weights for policy 1, policy_version 87230 (0.0007) -[2023-10-17 03:46:51,280][62373] Updated weights for policy 0, policy_version 87860 (0.0007) -[2023-10-17 03:46:51,657][62373] Updated weights for policy 0, policy_version 87870 (0.0009) -[2023-10-17 03:46:52,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 179306496. Throughput: 0: 1781.6, 1: 1767.2. Samples: 44826870. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) -[2023-10-17 03:46:52,214][61453] Avg episode reward: [(0, '10.720'), (1, '10.590')] -[2023-10-17 03:46:55,045][62408] Updated weights for policy 1, policy_version 87240 (0.0007) -[2023-10-17 03:46:55,386][62373] Updated weights for policy 0, policy_version 87880 (0.0008) -[2023-10-17 03:46:55,407][62408] Updated weights for policy 1, policy_version 87250 (0.0007) -[2023-10-17 03:46:55,754][62373] Updated weights for policy 0, policy_version 87890 (0.0008) -[2023-10-17 03:46:55,769][62408] Updated weights for policy 1, policy_version 87260 (0.0008) -[2023-10-17 03:46:56,123][62373] Updated weights for policy 0, policy_version 87900 (0.0009) -[2023-10-17 03:46:57,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 179372032. Throughput: 0: 1767.8, 1: 1746.8. Samples: 44846848. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) -[2023-10-17 03:46:57,215][61453] Avg episode reward: [(0, '10.270'), (1, '10.900')] -[2023-10-17 03:46:59,572][62408] Updated weights for policy 1, policy_version 87270 (0.0009) -[2023-10-17 03:46:59,963][62408] Updated weights for policy 1, policy_version 87280 (0.0009) -[2023-10-17 03:47:00,005][62373] Updated weights for policy 0, policy_version 87910 (0.0010) -[2023-10-17 03:47:00,327][62408] Updated weights for policy 1, policy_version 87290 (0.0009) -[2023-10-17 03:47:00,367][62373] Updated weights for policy 0, policy_version 87920 (0.0008) -[2023-10-17 03:47:00,742][62373] Updated weights for policy 0, policy_version 87930 (0.0009) -[2023-10-17 03:47:02,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 179437568. Throughput: 0: 1753.2, 1: 1744.1. Samples: 44868230. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) -[2023-10-17 03:47:02,215][61453] Avg episode reward: [(0, '10.250'), (1, '11.930')] -[2023-10-17 03:47:04,246][62408] Updated weights for policy 1, policy_version 87300 (0.0008) -[2023-10-17 03:47:04,508][62373] Updated weights for policy 0, policy_version 87940 (0.0008) -[2023-10-17 03:47:04,611][62408] Updated weights for policy 1, policy_version 87310 (0.0007) -[2023-10-17 03:47:04,880][62373] Updated weights for policy 0, policy_version 87950 (0.0008) -[2023-10-17 03:47:04,978][62408] Updated weights for policy 1, policy_version 87320 (0.0009) -[2023-10-17 03:47:05,244][62373] Updated weights for policy 0, policy_version 87960 (0.0009) -[2023-10-17 03:47:07,214][61453] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 179503104. Throughput: 0: 1772.6, 1: 1753.8. Samples: 44879088. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) -[2023-10-17 03:47:07,214][61453] Avg episode reward: [(0, '10.500'), (1, '11.260')] -[2023-10-17 03:47:08,862][62408] Updated weights for policy 1, policy_version 87330 (0.0007) -[2023-10-17 03:47:09,052][62373] Updated weights for policy 0, policy_version 87970 (0.0008) -[2023-10-17 03:47:09,227][62408] Updated weights for policy 1, policy_version 87340 (0.0007) -[2023-10-17 03:47:09,425][62373] Updated weights for policy 0, policy_version 87980 (0.0009) -[2023-10-17 03:47:09,598][62408] Updated weights for policy 1, policy_version 87350 (0.0008) -[2023-10-17 03:47:09,779][62373] Updated weights for policy 0, policy_version 87990 (0.0007) -[2023-10-17 03:47:09,969][62408] Updated weights for policy 1, policy_version 87360 (0.0008) -[2023-10-17 03:47:10,143][62373] Updated weights for policy 0, policy_version 88000 (0.0009) -[2023-10-17 03:47:12,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 179568640. Throughput: 0: 1758.5, 1: 1744.8. Samples: 44899830. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) -[2023-10-17 03:47:12,215][61453] Avg episode reward: [(0, '10.520'), (1, '10.200')] -[2023-10-17 03:47:13,875][62408] Updated weights for policy 1, policy_version 87370 (0.0008) -[2023-10-17 03:47:13,930][62373] Updated weights for policy 0, policy_version 88010 (0.0008) -[2023-10-17 03:47:14,238][62408] Updated weights for policy 1, policy_version 87380 (0.0008) -[2023-10-17 03:47:14,286][62373] Updated weights for policy 0, policy_version 88020 (0.0008) -[2023-10-17 03:47:14,604][62408] Updated weights for policy 1, policy_version 87390 (0.0008) -[2023-10-17 03:47:14,651][62373] Updated weights for policy 0, policy_version 88030 (0.0010) -[2023-10-17 03:47:17,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 179634176. Throughput: 0: 1759.2, 1: 1755.6. Samples: 44921750. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) -[2023-10-17 03:47:17,214][61453] Avg episode reward: [(0, '11.490'), (1, '11.030')] -[2023-10-17 03:47:18,458][62408] Updated weights for policy 1, policy_version 87400 (0.0007) -[2023-10-17 03:47:18,467][62373] Updated weights for policy 0, policy_version 88040 (0.0009) -[2023-10-17 03:47:18,823][62408] Updated weights for policy 1, policy_version 87410 (0.0008) -[2023-10-17 03:47:18,842][62373] Updated weights for policy 0, policy_version 88050 (0.0008) -[2023-10-17 03:47:19,187][62408] Updated weights for policy 1, policy_version 87420 (0.0008) -[2023-10-17 03:47:19,208][62373] Updated weights for policy 0, policy_version 88060 (0.0008) -[2023-10-17 03:47:22,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 179699712. Throughput: 0: 1756.2, 1: 1754.5. Samples: 44931188. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) -[2023-10-17 03:47:22,215][61453] Avg episode reward: [(0, '12.340'), (1, '11.750')] -[2023-10-17 03:47:23,032][62373] Updated weights for policy 0, policy_version 88070 (0.0007) -[2023-10-17 03:47:23,134][62408] Updated weights for policy 1, policy_version 87430 (0.0009) -[2023-10-17 03:47:23,398][62373] Updated weights for policy 0, policy_version 88080 (0.0009) -[2023-10-17 03:47:23,502][62408] Updated weights for policy 1, policy_version 87440 (0.0008) -[2023-10-17 03:47:23,774][62373] Updated weights for policy 0, policy_version 88090 (0.0008) -[2023-10-17 03:47:23,875][62408] Updated weights for policy 1, policy_version 87450 (0.0007) -[2023-10-17 03:47:27,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 179765248. Throughput: 0: 1759.3, 1: 1750.4. Samples: 44953198. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) -[2023-10-17 03:47:27,215][61453] Avg episode reward: [(0, '12.230'), (1, '11.420')] -[2023-10-17 03:47:27,634][62373] Updated weights for policy 0, policy_version 88100 (0.0008) -[2023-10-17 03:47:27,738][62408] Updated weights for policy 1, policy_version 87460 (0.0008) -[2023-10-17 03:47:28,020][62373] Updated weights for policy 0, policy_version 88110 (0.0009) -[2023-10-17 03:47:28,105][62408] Updated weights for policy 1, policy_version 87470 (0.0007) -[2023-10-17 03:47:28,391][62373] Updated weights for policy 0, policy_version 88120 (0.0009) -[2023-10-17 03:47:28,478][62408] Updated weights for policy 1, policy_version 87480 (0.0007) -[2023-10-17 03:47:32,184][62373] Updated weights for policy 0, policy_version 88130 (0.0008) -[2023-10-17 03:47:32,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 179830784. Throughput: 0: 1789.4, 1: 1783.0. Samples: 44975204. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) -[2023-10-17 03:47:32,215][61453] Avg episode reward: [(0, '12.120'), (1, '11.700')] -[2023-10-17 03:47:32,297][62408] Updated weights for policy 1, policy_version 87490 (0.0008) -[2023-10-17 03:47:32,541][62373] Updated weights for policy 0, policy_version 88140 (0.0007) -[2023-10-17 03:47:32,669][62408] Updated weights for policy 1, policy_version 87500 (0.0008) -[2023-10-17 03:47:32,908][62373] Updated weights for policy 0, policy_version 88150 (0.0008) -[2023-10-17 03:47:33,037][62408] Updated weights for policy 1, policy_version 87510 (0.0007) -[2023-10-17 03:47:33,271][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000088160_90275840.pth... -[2023-10-17 03:47:33,274][62373] Updated weights for policy 0, policy_version 88160 (0.0010) -[2023-10-17 03:47:33,303][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000086496_88571904.pth -[2023-10-17 03:47:33,403][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000087520_89620480.pth... -[2023-10-17 03:47:33,404][62408] Updated weights for policy 1, policy_version 87520 (0.0009) -[2023-10-17 03:47:33,444][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000085856_87916544.pth -[2023-10-17 03:47:37,184][62373] Updated weights for policy 0, policy_version 88170 (0.0009) -[2023-10-17 03:47:37,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 179896320. Throughput: 0: 1760.7, 1: 1750.4. Samples: 44984868. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) -[2023-10-17 03:47:37,214][61453] Avg episode reward: [(0, '12.180'), (1, '10.920')] -[2023-10-17 03:47:37,320][62408] Updated weights for policy 1, policy_version 87530 (0.0009) -[2023-10-17 03:47:37,554][62373] Updated weights for policy 0, policy_version 88180 (0.0008) -[2023-10-17 03:47:37,694][62408] Updated weights for policy 1, policy_version 87540 (0.0008) -[2023-10-17 03:47:37,914][62373] Updated weights for policy 0, policy_version 88190 (0.0007) -[2023-10-17 03:47:38,066][62408] Updated weights for policy 1, policy_version 87550 (0.0007) -[2023-10-17 03:47:41,632][62373] Updated weights for policy 0, policy_version 88200 (0.0007) -[2023-10-17 03:47:41,785][62408] Updated weights for policy 1, policy_version 87560 (0.0009) -[2023-10-17 03:47:42,002][62373] Updated weights for policy 0, policy_version 88210 (0.0007) -[2023-10-17 03:47:42,143][62408] Updated weights for policy 1, policy_version 87570 (0.0007) -[2023-10-17 03:47:42,214][61453] Fps is (10 sec: 13107.7, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 179961856. Throughput: 0: 1783.3, 1: 1767.6. Samples: 45006638. Policy #0 lag: (min: 31.0, avg: 31.0, max: 32.0) -[2023-10-17 03:47:42,214][61453] Avg episode reward: [(0, '12.090'), (1, '11.500')] -[2023-10-17 03:47:42,372][62373] Updated weights for policy 0, policy_version 88220 (0.0008) -[2023-10-17 03:47:42,514][62408] Updated weights for policy 1, policy_version 87580 (0.0008) -[2023-10-17 03:47:46,285][62373] Updated weights for policy 0, policy_version 88230 (0.0008) -[2023-10-17 03:47:46,422][62408] Updated weights for policy 1, policy_version 87590 (0.0010) -[2023-10-17 03:47:46,651][62373] Updated weights for policy 0, policy_version 88240 (0.0008) -[2023-10-17 03:47:46,789][62408] Updated weights for policy 1, policy_version 87600 (0.0008) -[2023-10-17 03:47:47,032][62373] Updated weights for policy 0, policy_version 88250 (0.0008) -[2023-10-17 03:47:47,163][62408] Updated weights for policy 1, policy_version 87610 (0.0009) -[2023-10-17 03:47:47,214][61453] Fps is (10 sec: 13106.9, 60 sec: 13107.2, 300 sec: 14106.9). Total num frames: 180027392. Throughput: 0: 1771.6, 1: 1752.0. Samples: 45026794. Policy #0 lag: (min: 31.0, avg: 39.9, max: 63.0) -[2023-10-17 03:47:47,215][61453] Avg episode reward: [(0, '11.870'), (1, '12.390')] -[2023-10-17 03:47:50,835][62373] Updated weights for policy 0, policy_version 88260 (0.0008) -[2023-10-17 03:47:50,989][62408] Updated weights for policy 1, policy_version 87620 (0.0008) -[2023-10-17 03:47:51,197][62373] Updated weights for policy 0, policy_version 88270 (0.0007) -[2023-10-17 03:47:51,350][62408] Updated weights for policy 1, policy_version 87630 (0.0009) -[2023-10-17 03:47:51,572][62373] Updated weights for policy 0, policy_version 88280 (0.0008) -[2023-10-17 03:47:51,719][62408] Updated weights for policy 1, policy_version 87640 (0.0008) -[2023-10-17 03:47:52,214][61453] Fps is (10 sec: 19660.6, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 180158464. Throughput: 0: 1774.7, 1: 1756.7. Samples: 45038002. Policy #0 lag: (min: 31.0, avg: 39.9, max: 63.0) -[2023-10-17 03:47:52,215][61453] Avg episode reward: [(0, '11.020'), (1, '11.800')] -[2023-10-17 03:47:55,459][62373] Updated weights for policy 0, policy_version 88290 (0.0008) -[2023-10-17 03:47:55,536][62408] Updated weights for policy 1, policy_version 87650 (0.0008) -[2023-10-17 03:47:55,824][62373] Updated weights for policy 0, policy_version 88300 (0.0009) -[2023-10-17 03:47:55,900][62408] Updated weights for policy 1, policy_version 87660 (0.0009) -[2023-10-17 03:47:56,197][62373] Updated weights for policy 0, policy_version 88310 (0.0007) -[2023-10-17 03:47:56,269][62408] Updated weights for policy 1, policy_version 87670 (0.0007) -[2023-10-17 03:47:56,570][62373] Updated weights for policy 0, policy_version 88320 (0.0007) -[2023-10-17 03:47:56,637][62408] Updated weights for policy 1, policy_version 87680 (0.0007) -[2023-10-17 03:47:57,214][61453] Fps is (10 sec: 19661.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 180224000. Throughput: 0: 1778.9, 1: 1756.7. Samples: 45058930. Policy #0 lag: (min: 31.0, avg: 39.9, max: 63.0) -[2023-10-17 03:47:57,214][61453] Avg episode reward: [(0, '10.330'), (1, '12.210')] -[2023-10-17 03:48:00,296][62373] Updated weights for policy 0, policy_version 88330 (0.0007) -[2023-10-17 03:48:00,563][62408] Updated weights for policy 1, policy_version 87690 (0.0008) -[2023-10-17 03:48:00,658][62373] Updated weights for policy 0, policy_version 88340 (0.0009) -[2023-10-17 03:48:00,931][62408] Updated weights for policy 1, policy_version 87700 (0.0008) -[2023-10-17 03:48:01,015][62373] Updated weights for policy 0, policy_version 88350 (0.0008) -[2023-10-17 03:48:01,299][62408] Updated weights for policy 1, policy_version 87710 (0.0008) -[2023-10-17 03:48:02,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 180289536. Throughput: 0: 1768.3, 1: 1738.4. Samples: 45079550. Policy #0 lag: (min: 31.0, avg: 39.9, max: 63.0) -[2023-10-17 03:48:02,215][61453] Avg episode reward: [(0, '10.180'), (1, '10.780')] -[2023-10-17 03:48:04,745][62373] Updated weights for policy 0, policy_version 88360 (0.0009) -[2023-10-17 03:48:05,117][62373] Updated weights for policy 0, policy_version 88370 (0.0008) -[2023-10-17 03:48:05,127][62408] Updated weights for policy 1, policy_version 87720 (0.0008) -[2023-10-17 03:48:05,486][62408] Updated weights for policy 1, policy_version 87730 (0.0009) -[2023-10-17 03:48:05,489][62373] Updated weights for policy 0, policy_version 88380 (0.0009) -[2023-10-17 03:48:05,858][62408] Updated weights for policy 1, policy_version 87740 (0.0007) -[2023-10-17 03:48:07,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 180355072. Throughput: 0: 1793.1, 1: 1768.7. Samples: 45091466. Policy #0 lag: (min: 31.0, avg: 39.9, max: 63.0) -[2023-10-17 03:48:07,215][61453] Avg episode reward: [(0, '10.510'), (1, '10.820')] -[2023-10-17 03:48:09,260][62373] Updated weights for policy 0, policy_version 88390 (0.0009) -[2023-10-17 03:48:09,628][62373] Updated weights for policy 0, policy_version 88400 (0.0010) -[2023-10-17 03:48:09,676][62408] Updated weights for policy 1, policy_version 87750 (0.0009) -[2023-10-17 03:48:10,003][62373] Updated weights for policy 0, policy_version 88410 (0.0009) -[2023-10-17 03:48:10,046][62408] Updated weights for policy 1, policy_version 87760 (0.0010) -[2023-10-17 03:48:10,422][62408] Updated weights for policy 1, policy_version 87770 (0.0007) -[2023-10-17 03:48:12,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 180420608. Throughput: 0: 1769.4, 1: 1744.4. Samples: 45111320. Policy #0 lag: (min: 31.0, avg: 39.9, max: 63.0) -[2023-10-17 03:48:12,215][61453] Avg episode reward: [(0, '10.460'), (1, '11.160')] -[2023-10-17 03:48:13,950][62373] Updated weights for policy 0, policy_version 88420 (0.0009) -[2023-10-17 03:48:14,303][62408] Updated weights for policy 1, policy_version 87780 (0.0008) -[2023-10-17 03:48:14,338][62373] Updated weights for policy 0, policy_version 88430 (0.0008) -[2023-10-17 03:48:14,669][62408] Updated weights for policy 1, policy_version 87790 (0.0009) -[2023-10-17 03:48:14,700][62373] Updated weights for policy 0, policy_version 88440 (0.0009) -[2023-10-17 03:48:15,039][62408] Updated weights for policy 1, policy_version 87800 (0.0009) -[2023-10-17 03:48:17,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 180486144. Throughput: 0: 1767.7, 1: 1743.3. Samples: 45133200. Policy #0 lag: (min: 31.0, avg: 39.9, max: 63.0) -[2023-10-17 03:48:17,214][61453] Avg episode reward: [(0, '10.730'), (1, '10.400')] -[2023-10-17 03:48:18,464][62373] Updated weights for policy 0, policy_version 88450 (0.0008) -[2023-10-17 03:48:18,839][62373] Updated weights for policy 0, policy_version 88460 (0.0008) -[2023-10-17 03:48:18,934][62408] Updated weights for policy 1, policy_version 87810 (0.0009) -[2023-10-17 03:48:19,214][62373] Updated weights for policy 0, policy_version 88470 (0.0009) -[2023-10-17 03:48:19,305][62408] Updated weights for policy 1, policy_version 87820 (0.0007) -[2023-10-17 03:48:19,575][62373] Updated weights for policy 0, policy_version 88480 (0.0009) -[2023-10-17 03:48:19,669][62408] Updated weights for policy 1, policy_version 87830 (0.0007) -[2023-10-17 03:48:20,029][62408] Updated weights for policy 1, policy_version 87840 (0.0009) -[2023-10-17 03:48:22,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 180551680. Throughput: 0: 1767.9, 1: 1748.4. Samples: 45143102. Policy #0 lag: (min: 31.0, avg: 39.9, max: 63.0) -[2023-10-17 03:48:22,215][61453] Avg episode reward: [(0, '11.650'), (1, '10.550')] -[2023-10-17 03:48:23,302][62373] Updated weights for policy 0, policy_version 88490 (0.0008) -[2023-10-17 03:48:23,671][62373] Updated weights for policy 0, policy_version 88500 (0.0009) -[2023-10-17 03:48:23,805][62408] Updated weights for policy 1, policy_version 87850 (0.0008) -[2023-10-17 03:48:24,037][62373] Updated weights for policy 0, policy_version 88510 (0.0008) -[2023-10-17 03:48:24,164][62408] Updated weights for policy 1, policy_version 87860 (0.0008) -[2023-10-17 03:48:24,539][62408] Updated weights for policy 1, policy_version 87870 (0.0011) -[2023-10-17 03:48:27,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 180617216. Throughput: 0: 1767.2, 1: 1747.5. Samples: 45164796. Policy #0 lag: (min: 31.0, avg: 39.9, max: 63.0) -[2023-10-17 03:48:27,215][61453] Avg episode reward: [(0, '12.480'), (1, '10.830')] -[2023-10-17 03:48:27,868][62373] Updated weights for policy 0, policy_version 88520 (0.0007) -[2023-10-17 03:48:28,249][62373] Updated weights for policy 0, policy_version 88530 (0.0007) -[2023-10-17 03:48:28,344][62408] Updated weights for policy 1, policy_version 87880 (0.0008) -[2023-10-17 03:48:28,612][62373] Updated weights for policy 0, policy_version 88540 (0.0008) -[2023-10-17 03:48:28,712][62408] Updated weights for policy 1, policy_version 87890 (0.0008) -[2023-10-17 03:48:29,079][62408] Updated weights for policy 1, policy_version 87900 (0.0007) -[2023-10-17 03:48:32,214][61453] Fps is (10 sec: 13107.6, 60 sec: 14199.6, 300 sec: 14106.9). Total num frames: 180682752. Throughput: 0: 1791.6, 1: 1767.1. Samples: 45186934. Policy #0 lag: (min: 31.0, avg: 39.9, max: 63.0) -[2023-10-17 03:48:32,214][61453] Avg episode reward: [(0, '11.990'), (1, '10.450')] -[2023-10-17 03:48:32,268][62373] Updated weights for policy 0, policy_version 88550 (0.0009) -[2023-10-17 03:48:32,628][62373] Updated weights for policy 0, policy_version 88560 (0.0008) -[2023-10-17 03:48:32,948][62408] Updated weights for policy 1, policy_version 87910 (0.0007) -[2023-10-17 03:48:33,002][62373] Updated weights for policy 0, policy_version 88570 (0.0008) -[2023-10-17 03:48:33,342][62408] Updated weights for policy 1, policy_version 87920 (0.0008) -[2023-10-17 03:48:33,727][62408] Updated weights for policy 1, policy_version 87930 (0.0009) -[2023-10-17 03:48:36,867][62373] Updated weights for policy 0, policy_version 88580 (0.0008) -[2023-10-17 03:48:37,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 180748288. Throughput: 0: 1770.3, 1: 1748.5. Samples: 45196350. Policy #0 lag: (min: 31.0, avg: 39.9, max: 63.0) -[2023-10-17 03:48:37,215][61453] Avg episode reward: [(0, '12.370'), (1, '11.300')] -[2023-10-17 03:48:37,243][62373] Updated weights for policy 0, policy_version 88590 (0.0009) -[2023-10-17 03:48:37,511][62408] Updated weights for policy 1, policy_version 87940 (0.0008) -[2023-10-17 03:48:37,617][62373] Updated weights for policy 0, policy_version 88600 (0.0008) -[2023-10-17 03:48:37,881][62408] Updated weights for policy 1, policy_version 87950 (0.0009) -[2023-10-17 03:48:38,244][62408] Updated weights for policy 1, policy_version 87960 (0.0009) -[2023-10-17 03:48:41,285][62373] Updated weights for policy 0, policy_version 88610 (0.0008) -[2023-10-17 03:48:41,656][62373] Updated weights for policy 0, policy_version 88620 (0.0008) -[2023-10-17 03:48:42,023][62373] Updated weights for policy 0, policy_version 88630 (0.0009) -[2023-10-17 03:48:42,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 180813824. Throughput: 0: 1787.8, 1: 1760.2. Samples: 45218592. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-17 03:48:42,215][61453] Avg episode reward: [(0, '12.420'), (1, '10.060')] -[2023-10-17 03:48:42,243][62408] Updated weights for policy 1, policy_version 87970 (0.0012) -[2023-10-17 03:48:42,402][62373] Updated weights for policy 0, policy_version 88640 (0.0007) -[2023-10-17 03:48:42,612][62408] Updated weights for policy 1, policy_version 87980 (0.0008) -[2023-10-17 03:48:42,984][62408] Updated weights for policy 1, policy_version 87990 (0.0008) -[2023-10-17 03:48:43,353][62408] Updated weights for policy 1, policy_version 88000 (0.0008) -[2023-10-17 03:48:46,125][62373] Updated weights for policy 0, policy_version 88650 (0.0008) -[2023-10-17 03:48:46,488][62373] Updated weights for policy 0, policy_version 88660 (0.0007) -[2023-10-17 03:48:46,868][62373] Updated weights for policy 0, policy_version 88670 (0.0009) -[2023-10-17 03:48:47,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14745.6, 300 sec: 14106.9). Total num frames: 180912128. Throughput: 0: 1768.3, 1: 1779.3. Samples: 45239192. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-17 03:48:47,215][61453] Avg episode reward: [(0, '11.910'), (1, '10.490')] -[2023-10-17 03:48:47,238][62408] Updated weights for policy 1, policy_version 88010 (0.0007) -[2023-10-17 03:48:47,610][62408] Updated weights for policy 1, policy_version 88020 (0.0008) -[2023-10-17 03:48:47,979][62408] Updated weights for policy 1, policy_version 88030 (0.0007) -[2023-10-17 03:48:50,574][62373] Updated weights for policy 0, policy_version 88680 (0.0008) -[2023-10-17 03:48:50,939][62373] Updated weights for policy 0, policy_version 88690 (0.0007) -[2023-10-17 03:48:51,305][62373] Updated weights for policy 0, policy_version 88700 (0.0007) -[2023-10-17 03:48:51,850][62408] Updated weights for policy 1, policy_version 88040 (0.0009) -[2023-10-17 03:48:52,214][61453] Fps is (10 sec: 16384.4, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 180977664. Throughput: 0: 1780.6, 1: 1748.0. Samples: 45250254. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-17 03:48:52,214][61453] Avg episode reward: [(0, '11.920'), (1, '10.420')] -[2023-10-17 03:48:52,215][62408] Updated weights for policy 1, policy_version 88050 (0.0008) -[2023-10-17 03:48:52,580][62408] Updated weights for policy 1, policy_version 88060 (0.0008) -[2023-10-17 03:48:55,034][62373] Updated weights for policy 0, policy_version 88710 (0.0010) -[2023-10-17 03:48:55,407][62373] Updated weights for policy 0, policy_version 88720 (0.0010) -[2023-10-17 03:48:55,780][62373] Updated weights for policy 0, policy_version 88730 (0.0008) -[2023-10-17 03:48:56,358][62408] Updated weights for policy 1, policy_version 88070 (0.0009) -[2023-10-17 03:48:56,723][62408] Updated weights for policy 1, policy_version 88080 (0.0010) -[2023-10-17 03:48:57,088][62408] Updated weights for policy 1, policy_version 88090 (0.0010) -[2023-10-17 03:48:57,214][61453] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 181043200. Throughput: 0: 1778.0, 1: 1779.3. Samples: 45271398. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-17 03:48:57,215][61453] Avg episode reward: [(0, '12.170'), (1, '10.860')] -[2023-10-17 03:48:59,579][62373] Updated weights for policy 0, policy_version 88740 (0.0009) -[2023-10-17 03:48:59,964][62373] Updated weights for policy 0, policy_version 88750 (0.0007) -[2023-10-17 03:49:00,343][62373] Updated weights for policy 0, policy_version 88760 (0.0010) -[2023-10-17 03:49:00,816][62408] Updated weights for policy 1, policy_version 88100 (0.0009) -[2023-10-17 03:49:01,180][62408] Updated weights for policy 1, policy_version 88110 (0.0010) -[2023-10-17 03:49:01,557][62408] Updated weights for policy 1, policy_version 88120 (0.0009) -[2023-10-17 03:49:02,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 181141504. Throughput: 0: 1778.2, 1: 1757.0. Samples: 45292282. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-17 03:49:02,215][61453] Avg episode reward: [(0, '13.720'), (1, '10.900')] -[2023-10-17 03:49:02,224][62094] Saving new best policy, reward=13.720! -[2023-10-17 03:49:04,085][62373] Updated weights for policy 0, policy_version 88770 (0.0008) -[2023-10-17 03:49:04,458][62373] Updated weights for policy 0, policy_version 88780 (0.0011) -[2023-10-17 03:49:04,837][62373] Updated weights for policy 0, policy_version 88790 (0.0010) -[2023-10-17 03:49:05,197][62373] Updated weights for policy 0, policy_version 88800 (0.0007) -[2023-10-17 03:49:05,368][62408] Updated weights for policy 1, policy_version 88130 (0.0008) -[2023-10-17 03:49:05,744][62408] Updated weights for policy 1, policy_version 88140 (0.0009) -[2023-10-17 03:49:06,111][62408] Updated weights for policy 1, policy_version 88150 (0.0010) -[2023-10-17 03:49:06,480][62408] Updated weights for policy 1, policy_version 88160 (0.0007) -[2023-10-17 03:49:07,214][61453] Fps is (10 sec: 16384.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 181207040. Throughput: 0: 1783.4, 1: 1781.5. Samples: 45303522. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-17 03:49:07,214][61453] Avg episode reward: [(0, '12.080'), (1, '10.530')] -[2023-10-17 03:49:09,147][62373] Updated weights for policy 0, policy_version 88810 (0.0008) -[2023-10-17 03:49:09,512][62373] Updated weights for policy 0, policy_version 88820 (0.0008) -[2023-10-17 03:49:09,888][62373] Updated weights for policy 0, policy_version 88830 (0.0009) -[2023-10-17 03:49:10,341][62408] Updated weights for policy 1, policy_version 88170 (0.0007) -[2023-10-17 03:49:10,706][62408] Updated weights for policy 1, policy_version 88180 (0.0009) -[2023-10-17 03:49:11,083][62408] Updated weights for policy 1, policy_version 88190 (0.0008) -[2023-10-17 03:49:12,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 181272576. Throughput: 0: 1776.0, 1: 1763.7. Samples: 45324084. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-17 03:49:12,215][61453] Avg episode reward: [(0, '12.020'), (1, '10.800')] -[2023-10-17 03:49:13,588][62373] Updated weights for policy 0, policy_version 88840 (0.0008) -[2023-10-17 03:49:13,961][62373] Updated weights for policy 0, policy_version 88850 (0.0009) -[2023-10-17 03:49:14,325][62373] Updated weights for policy 0, policy_version 88860 (0.0010) -[2023-10-17 03:49:14,863][62408] Updated weights for policy 1, policy_version 88200 (0.0008) -[2023-10-17 03:49:15,228][62408] Updated weights for policy 1, policy_version 88210 (0.0011) -[2023-10-17 03:49:15,602][62408] Updated weights for policy 1, policy_version 88220 (0.0010) -[2023-10-17 03:49:17,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 181338112. Throughput: 0: 1776.0, 1: 1758.1. Samples: 45345972. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-17 03:49:17,215][61453] Avg episode reward: [(0, '11.970'), (1, '11.300')] -[2023-10-17 03:49:18,350][62373] Updated weights for policy 0, policy_version 88870 (0.0009) -[2023-10-17 03:49:18,720][62373] Updated weights for policy 0, policy_version 88880 (0.0011) -[2023-10-17 03:49:19,090][62373] Updated weights for policy 0, policy_version 88890 (0.0009) -[2023-10-17 03:49:19,338][62408] Updated weights for policy 1, policy_version 88230 (0.0008) -[2023-10-17 03:49:19,715][62408] Updated weights for policy 1, policy_version 88240 (0.0008) -[2023-10-17 03:49:20,080][62408] Updated weights for policy 1, policy_version 88250 (0.0009) -[2023-10-17 03:49:22,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 181403648. Throughput: 0: 1776.3, 1: 1778.6. Samples: 45356322. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-17 03:49:22,215][61453] Avg episode reward: [(0, '11.890'), (1, '11.420')] -[2023-10-17 03:49:22,835][62373] Updated weights for policy 0, policy_version 88900 (0.0008) -[2023-10-17 03:49:23,214][62373] Updated weights for policy 0, policy_version 88910 (0.0009) -[2023-10-17 03:49:23,578][62373] Updated weights for policy 0, policy_version 88920 (0.0008) -[2023-10-17 03:49:23,936][62408] Updated weights for policy 1, policy_version 88260 (0.0010) -[2023-10-17 03:49:24,299][62408] Updated weights for policy 1, policy_version 88270 (0.0010) -[2023-10-17 03:49:24,662][62408] Updated weights for policy 1, policy_version 88280 (0.0010) -[2023-10-17 03:49:27,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 181469184. Throughput: 0: 1774.5, 1: 1766.2. Samples: 45377924. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-17 03:49:27,215][61453] Avg episode reward: [(0, '11.780'), (1, '11.930')] -[2023-10-17 03:49:27,429][62373] Updated weights for policy 0, policy_version 88930 (0.0008) -[2023-10-17 03:49:27,799][62373] Updated weights for policy 0, policy_version 88940 (0.0008) -[2023-10-17 03:49:28,171][62373] Updated weights for policy 0, policy_version 88950 (0.0008) -[2023-10-17 03:49:28,215][62408] Updated weights for policy 1, policy_version 88290 (0.0009) -[2023-10-17 03:49:28,540][62373] Updated weights for policy 0, policy_version 88960 (0.0011) -[2023-10-17 03:49:28,575][62408] Updated weights for policy 1, policy_version 88300 (0.0007) -[2023-10-17 03:49:28,941][62408] Updated weights for policy 1, policy_version 88310 (0.0009) -[2023-10-17 03:49:29,311][62408] Updated weights for policy 1, policy_version 88320 (0.0009) -[2023-10-17 03:49:32,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 181534720. Throughput: 0: 1804.0, 1: 1773.6. Samples: 45400186. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-10-17 03:49:32,215][61453] Avg episode reward: [(0, '11.950'), (1, '11.270')] -[2023-10-17 03:49:32,222][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000088320_90439680.pth... -[2023-10-17 03:49:32,256][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000086688_88768512.pth -[2023-10-17 03:49:32,395][62373] Updated weights for policy 0, policy_version 88970 (0.0010) -[2023-10-17 03:49:32,764][62373] Updated weights for policy 0, policy_version 88980 (0.0007) -[2023-10-17 03:49:33,081][62408] Updated weights for policy 1, policy_version 88330 (0.0007) -[2023-10-17 03:49:33,134][62373] Updated weights for policy 0, policy_version 88990 (0.0008) -[2023-10-17 03:49:33,205][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000088992_91127808.pth... -[2023-10-17 03:49:33,248][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000087328_89423872.pth -[2023-10-17 03:49:33,459][62408] Updated weights for policy 1, policy_version 88340 (0.0008) -[2023-10-17 03:49:33,822][62408] Updated weights for policy 1, policy_version 88350 (0.0008) -[2023-10-17 03:49:36,958][62373] Updated weights for policy 0, policy_version 89000 (0.0008) -[2023-10-17 03:49:37,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 181600256. Throughput: 0: 1767.6, 1: 1775.3. Samples: 45409684. Policy #0 lag: (min: 6.0, avg: 6.7, max: 24.0) -[2023-10-17 03:49:37,215][61453] Avg episode reward: [(0, '10.740'), (1, '10.430')] -[2023-10-17 03:49:37,332][62373] Updated weights for policy 0, policy_version 89010 (0.0008) -[2023-10-17 03:49:37,699][62373] Updated weights for policy 0, policy_version 89020 (0.0009) -[2023-10-17 03:49:37,804][62408] Updated weights for policy 1, policy_version 88360 (0.0008) -[2023-10-17 03:49:38,174][62408] Updated weights for policy 1, policy_version 88370 (0.0009) -[2023-10-17 03:49:38,541][62408] Updated weights for policy 1, policy_version 88380 (0.0008) -[2023-10-17 03:49:41,507][62373] Updated weights for policy 0, policy_version 89030 (0.0008) -[2023-10-17 03:49:41,876][62373] Updated weights for policy 0, policy_version 89040 (0.0009) -[2023-10-17 03:49:42,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 181665792. Throughput: 0: 1788.4, 1: 1768.6. Samples: 45431466. Policy #0 lag: (min: 6.0, avg: 6.7, max: 24.0) -[2023-10-17 03:49:42,215][61453] Avg episode reward: [(0, '11.140'), (1, '11.160')] -[2023-10-17 03:49:42,246][62373] Updated weights for policy 0, policy_version 89050 (0.0009) -[2023-10-17 03:49:42,463][62408] Updated weights for policy 1, policy_version 88390 (0.0009) -[2023-10-17 03:49:42,829][62408] Updated weights for policy 1, policy_version 88400 (0.0010) -[2023-10-17 03:49:43,185][62408] Updated weights for policy 1, policy_version 88410 (0.0009) -[2023-10-17 03:49:45,964][62373] Updated weights for policy 0, policy_version 89060 (0.0008) -[2023-10-17 03:49:46,355][62373] Updated weights for policy 0, policy_version 89070 (0.0010) -[2023-10-17 03:49:46,713][62373] Updated weights for policy 0, policy_version 89080 (0.0010) -[2023-10-17 03:49:46,985][62408] Updated weights for policy 1, policy_version 88420 (0.0008) -[2023-10-17 03:49:47,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 181764096. Throughput: 0: 1763.5, 1: 1789.8. Samples: 45452178. Policy #0 lag: (min: 6.0, avg: 6.7, max: 24.0) -[2023-10-17 03:49:47,214][61453] Avg episode reward: [(0, '11.600'), (1, '11.220')] -[2023-10-17 03:49:47,353][62408] Updated weights for policy 1, policy_version 88430 (0.0010) -[2023-10-17 03:49:47,727][62408] Updated weights for policy 1, policy_version 88440 (0.0010) -[2023-10-17 03:49:50,386][62373] Updated weights for policy 0, policy_version 89090 (0.0008) -[2023-10-17 03:49:50,747][62373] Updated weights for policy 0, policy_version 89100 (0.0010) -[2023-10-17 03:49:51,121][62373] Updated weights for policy 0, policy_version 89110 (0.0009) -[2023-10-17 03:49:51,484][62373] Updated weights for policy 0, policy_version 89120 (0.0008) -[2023-10-17 03:49:51,534][62408] Updated weights for policy 1, policy_version 88450 (0.0011) -[2023-10-17 03:49:51,904][62408] Updated weights for policy 1, policy_version 88460 (0.0010) -[2023-10-17 03:49:52,214][61453] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 181829632. Throughput: 0: 1790.6, 1: 1761.5. Samples: 45463366. Policy #0 lag: (min: 6.0, avg: 6.7, max: 24.0) -[2023-10-17 03:49:52,214][61453] Avg episode reward: [(0, '10.870'), (1, '11.000')] -[2023-10-17 03:49:52,274][62408] Updated weights for policy 1, policy_version 88470 (0.0009) -[2023-10-17 03:49:52,639][62408] Updated weights for policy 1, policy_version 88480 (0.0008) -[2023-10-17 03:49:55,299][62373] Updated weights for policy 0, policy_version 89130 (0.0010) -[2023-10-17 03:49:55,664][62373] Updated weights for policy 0, policy_version 89140 (0.0009) -[2023-10-17 03:49:56,029][62373] Updated weights for policy 0, policy_version 89150 (0.0010) -[2023-10-17 03:49:56,452][62408] Updated weights for policy 1, policy_version 88490 (0.0009) -[2023-10-17 03:49:56,815][62408] Updated weights for policy 1, policy_version 88500 (0.0011) -[2023-10-17 03:49:57,186][62408] Updated weights for policy 1, policy_version 88510 (0.0010) -[2023-10-17 03:49:57,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 181895168. Throughput: 0: 1776.9, 1: 1788.6. Samples: 45484534. Policy #0 lag: (min: 6.0, avg: 6.7, max: 24.0) -[2023-10-17 03:49:57,215][61453] Avg episode reward: [(0, '10.490'), (1, '10.670')] -[2023-10-17 03:49:59,712][62373] Updated weights for policy 0, policy_version 89160 (0.0009) -[2023-10-17 03:50:00,080][62373] Updated weights for policy 0, policy_version 89170 (0.0008) -[2023-10-17 03:50:00,441][62373] Updated weights for policy 0, policy_version 89180 (0.0008) -[2023-10-17 03:50:01,066][62408] Updated weights for policy 1, policy_version 88520 (0.0010) -[2023-10-17 03:50:01,432][62408] Updated weights for policy 1, policy_version 88530 (0.0010) -[2023-10-17 03:50:01,803][62408] Updated weights for policy 1, policy_version 88540 (0.0011) -[2023-10-17 03:50:02,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 181993472. Throughput: 0: 1778.7, 1: 1768.3. Samples: 45505586. Policy #0 lag: (min: 6.0, avg: 6.7, max: 24.0) -[2023-10-17 03:50:02,215][61453] Avg episode reward: [(0, '10.650'), (1, '10.960')] -[2023-10-17 03:50:04,185][62373] Updated weights for policy 0, policy_version 89190 (0.0011) -[2023-10-17 03:50:04,554][62373] Updated weights for policy 0, policy_version 89200 (0.0009) -[2023-10-17 03:50:04,920][62373] Updated weights for policy 0, policy_version 89210 (0.0009) -[2023-10-17 03:50:05,684][62408] Updated weights for policy 1, policy_version 88550 (0.0009) -[2023-10-17 03:50:06,069][62408] Updated weights for policy 1, policy_version 88560 (0.0009) -[2023-10-17 03:50:06,435][62408] Updated weights for policy 1, policy_version 88570 (0.0009) -[2023-10-17 03:50:07,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 182059008. Throughput: 0: 1785.9, 1: 1779.4. Samples: 45516760. Policy #0 lag: (min: 6.0, avg: 6.7, max: 24.0) -[2023-10-17 03:50:07,215][61453] Avg episode reward: [(0, '10.570'), (1, '11.150')] -[2023-10-17 03:50:08,763][62373] Updated weights for policy 0, policy_version 89220 (0.0008) -[2023-10-17 03:50:09,144][62373] Updated weights for policy 0, policy_version 89230 (0.0008) -[2023-10-17 03:50:09,512][62373] Updated weights for policy 0, policy_version 89240 (0.0008) -[2023-10-17 03:50:10,206][62408] Updated weights for policy 1, policy_version 88580 (0.0007) -[2023-10-17 03:50:10,571][62408] Updated weights for policy 1, policy_version 88590 (0.0008) -[2023-10-17 03:50:10,941][62408] Updated weights for policy 1, policy_version 88600 (0.0009) -[2023-10-17 03:50:12,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 182124544. Throughput: 0: 1775.9, 1: 1771.6. Samples: 45537562. Policy #0 lag: (min: 6.0, avg: 6.7, max: 24.0) -[2023-10-17 03:50:12,215][61453] Avg episode reward: [(0, '10.520'), (1, '11.330')] -[2023-10-17 03:50:13,244][62373] Updated weights for policy 0, policy_version 89250 (0.0010) -[2023-10-17 03:50:13,615][62373] Updated weights for policy 0, policy_version 89260 (0.0009) -[2023-10-17 03:50:13,988][62373] Updated weights for policy 0, policy_version 89270 (0.0010) -[2023-10-17 03:50:14,356][62373] Updated weights for policy 0, policy_version 89280 (0.0009) -[2023-10-17 03:50:14,753][62408] Updated weights for policy 1, policy_version 88610 (0.0011) -[2023-10-17 03:50:15,109][62408] Updated weights for policy 1, policy_version 88620 (0.0010) -[2023-10-17 03:50:15,483][62408] Updated weights for policy 1, policy_version 88630 (0.0009) -[2023-10-17 03:50:15,843][62408] Updated weights for policy 1, policy_version 88640 (0.0009) -[2023-10-17 03:50:17,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 182190080. Throughput: 0: 1782.3, 1: 1752.1. Samples: 45559234. Policy #0 lag: (min: 6.0, avg: 6.7, max: 24.0) -[2023-10-17 03:50:17,214][61453] Avg episode reward: [(0, '10.530'), (1, '10.790')] -[2023-10-17 03:50:18,094][62373] Updated weights for policy 0, policy_version 89290 (0.0007) -[2023-10-17 03:50:18,468][62373] Updated weights for policy 0, policy_version 89300 (0.0007) -[2023-10-17 03:50:18,830][62373] Updated weights for policy 0, policy_version 89310 (0.0008) -[2023-10-17 03:50:19,612][62408] Updated weights for policy 1, policy_version 88650 (0.0009) -[2023-10-17 03:50:19,977][62408] Updated weights for policy 1, policy_version 88660 (0.0010) -[2023-10-17 03:50:20,347][62408] Updated weights for policy 1, policy_version 88670 (0.0010) -[2023-10-17 03:50:22,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 182255616. Throughput: 0: 1783.2, 1: 1772.4. Samples: 45569688. Policy #0 lag: (min: 6.0, avg: 6.7, max: 24.0) -[2023-10-17 03:50:22,214][61453] Avg episode reward: [(0, '10.440'), (1, '10.640')] -[2023-10-17 03:50:22,658][62373] Updated weights for policy 0, policy_version 89320 (0.0007) -[2023-10-17 03:50:23,031][62373] Updated weights for policy 0, policy_version 89330 (0.0009) -[2023-10-17 03:50:23,396][62373] Updated weights for policy 0, policy_version 89340 (0.0010) -[2023-10-17 03:50:24,023][62408] Updated weights for policy 1, policy_version 88680 (0.0010) -[2023-10-17 03:50:24,387][62408] Updated weights for policy 1, policy_version 88690 (0.0010) -[2023-10-17 03:50:24,764][62408] Updated weights for policy 1, policy_version 88700 (0.0010) -[2023-10-17 03:50:27,181][62373] Updated weights for policy 0, policy_version 89350 (0.0009) -[2023-10-17 03:50:27,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 182321152. Throughput: 0: 1787.4, 1: 1763.3. Samples: 45591248. Policy #0 lag: (min: 6.0, avg: 6.7, max: 24.0) -[2023-10-17 03:50:27,215][61453] Avg episode reward: [(0, '10.810'), (1, '12.250')] -[2023-10-17 03:50:27,558][62373] Updated weights for policy 0, policy_version 89360 (0.0010) -[2023-10-17 03:50:27,933][62373] Updated weights for policy 0, policy_version 89370 (0.0007) -[2023-10-17 03:50:28,650][62408] Updated weights for policy 1, policy_version 88710 (0.0008) -[2023-10-17 03:50:29,019][62408] Updated weights for policy 1, policy_version 88720 (0.0009) -[2023-10-17 03:50:29,388][62408] Updated weights for policy 1, policy_version 88730 (0.0008) -[2023-10-17 03:50:31,784][62373] Updated weights for policy 0, policy_version 89380 (0.0009) -[2023-10-17 03:50:32,166][62373] Updated weights for policy 0, policy_version 89390 (0.0008) -[2023-10-17 03:50:32,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 13995.8). Total num frames: 182386688. Throughput: 0: 1804.3, 1: 1767.4. Samples: 45612906. Policy #0 lag: (min: 29.0, avg: 33.8, max: 61.0) -[2023-10-17 03:50:32,215][61453] Avg episode reward: [(0, '10.600'), (1, '10.740')] -[2023-10-17 03:50:32,542][62373] Updated weights for policy 0, policy_version 89400 (0.0007) -[2023-10-17 03:50:33,130][62408] Updated weights for policy 1, policy_version 88740 (0.0010) -[2023-10-17 03:50:33,501][62408] Updated weights for policy 1, policy_version 88750 (0.0007) -[2023-10-17 03:50:33,879][62408] Updated weights for policy 1, policy_version 88760 (0.0008) -[2023-10-17 03:50:36,355][62373] Updated weights for policy 0, policy_version 89410 (0.0008) -[2023-10-17 03:50:36,717][62373] Updated weights for policy 0, policy_version 89420 (0.0008) -[2023-10-17 03:50:37,092][62373] Updated weights for policy 0, policy_version 89430 (0.0011) -[2023-10-17 03:50:37,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 182452224. Throughput: 0: 1780.2, 1: 1765.7. Samples: 45622930. Policy #0 lag: (min: 29.0, avg: 33.8, max: 61.0) -[2023-10-17 03:50:37,215][61453] Avg episode reward: [(0, '11.160'), (1, '10.620')] -[2023-10-17 03:50:37,456][62373] Updated weights for policy 0, policy_version 89440 (0.0009) -[2023-10-17 03:50:37,788][62408] Updated weights for policy 1, policy_version 88770 (0.0008) -[2023-10-17 03:50:38,161][62408] Updated weights for policy 1, policy_version 88780 (0.0010) -[2023-10-17 03:50:38,528][62408] Updated weights for policy 1, policy_version 88790 (0.0009) -[2023-10-17 03:50:38,888][62408] Updated weights for policy 1, policy_version 88800 (0.0007) -[2023-10-17 03:50:41,031][62373] Updated weights for policy 0, policy_version 89450 (0.0011) -[2023-10-17 03:50:41,396][62373] Updated weights for policy 0, policy_version 89460 (0.0009) -[2023-10-17 03:50:41,764][62373] Updated weights for policy 0, policy_version 89470 (0.0009) -[2023-10-17 03:50:42,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14745.6, 300 sec: 14106.9). Total num frames: 182550528. Throughput: 0: 1800.7, 1: 1764.8. Samples: 45644982. Policy #0 lag: (min: 29.0, avg: 33.8, max: 61.0) -[2023-10-17 03:50:42,215][61453] Avg episode reward: [(0, '11.650'), (1, '11.000')] -[2023-10-17 03:50:42,581][62408] Updated weights for policy 1, policy_version 88810 (0.0007) -[2023-10-17 03:50:42,948][62408] Updated weights for policy 1, policy_version 88820 (0.0007) -[2023-10-17 03:50:43,317][62408] Updated weights for policy 1, policy_version 88830 (0.0007) -[2023-10-17 03:50:45,644][62373] Updated weights for policy 0, policy_version 89480 (0.0008) -[2023-10-17 03:50:46,019][62373] Updated weights for policy 0, policy_version 89490 (0.0007) -[2023-10-17 03:50:46,394][62373] Updated weights for policy 0, policy_version 89500 (0.0007) -[2023-10-17 03:50:47,193][62408] Updated weights for policy 1, policy_version 88840 (0.0008) -[2023-10-17 03:50:47,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 182616064. Throughput: 0: 1771.3, 1: 1794.4. Samples: 45666044. Policy #0 lag: (min: 29.0, avg: 33.8, max: 61.0) -[2023-10-17 03:50:47,215][61453] Avg episode reward: [(0, '10.950'), (1, '11.050')] -[2023-10-17 03:50:47,560][62408] Updated weights for policy 1, policy_version 88850 (0.0007) -[2023-10-17 03:50:47,929][62408] Updated weights for policy 1, policy_version 88860 (0.0009) -[2023-10-17 03:50:50,115][62373] Updated weights for policy 0, policy_version 89510 (0.0007) -[2023-10-17 03:50:50,479][62373] Updated weights for policy 0, policy_version 89520 (0.0009) -[2023-10-17 03:50:50,852][62373] Updated weights for policy 0, policy_version 89530 (0.0011) -[2023-10-17 03:50:51,971][62408] Updated weights for policy 1, policy_version 88870 (0.0011) -[2023-10-17 03:50:52,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 182681600. Throughput: 0: 1798.3, 1: 1763.8. Samples: 45677056. Policy #0 lag: (min: 29.0, avg: 33.8, max: 61.0) -[2023-10-17 03:50:52,215][61453] Avg episode reward: [(0, '11.050'), (1, '10.850')] -[2023-10-17 03:50:52,345][62408] Updated weights for policy 1, policy_version 88880 (0.0010) -[2023-10-17 03:50:52,716][62408] Updated weights for policy 1, policy_version 88890 (0.0008) -[2023-10-17 03:50:54,646][62373] Updated weights for policy 0, policy_version 89540 (0.0010) -[2023-10-17 03:50:55,005][62373] Updated weights for policy 0, policy_version 89550 (0.0010) -[2023-10-17 03:50:55,365][62373] Updated weights for policy 0, policy_version 89560 (0.0010) -[2023-10-17 03:50:56,451][62408] Updated weights for policy 1, policy_version 88900 (0.0008) -[2023-10-17 03:50:56,827][62408] Updated weights for policy 1, policy_version 88910 (0.0010) -[2023-10-17 03:50:57,187][62408] Updated weights for policy 1, policy_version 88920 (0.0009) -[2023-10-17 03:50:57,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 182747136. Throughput: 0: 1774.5, 1: 1783.4. Samples: 45697668. Policy #0 lag: (min: 29.0, avg: 33.8, max: 61.0) -[2023-10-17 03:50:57,215][61453] Avg episode reward: [(0, '11.170'), (1, '11.980')] -[2023-10-17 03:50:59,299][62373] Updated weights for policy 0, policy_version 89570 (0.0010) -[2023-10-17 03:50:59,669][62373] Updated weights for policy 0, policy_version 89580 (0.0007) -[2023-10-17 03:51:00,032][62373] Updated weights for policy 0, policy_version 89590 (0.0010) -[2023-10-17 03:51:00,404][62373] Updated weights for policy 0, policy_version 89600 (0.0009) -[2023-10-17 03:51:00,871][62408] Updated weights for policy 1, policy_version 88930 (0.0007) -[2023-10-17 03:51:01,226][62408] Updated weights for policy 1, policy_version 88940 (0.0008) -[2023-10-17 03:51:01,596][62408] Updated weights for policy 1, policy_version 88950 (0.0009) -[2023-10-17 03:51:01,965][62408] Updated weights for policy 1, policy_version 88960 (0.0007) -[2023-10-17 03:51:02,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 182845440. Throughput: 0: 1769.4, 1: 1768.5. Samples: 45718440. Policy #0 lag: (min: 29.0, avg: 33.8, max: 61.0) -[2023-10-17 03:51:02,215][61453] Avg episode reward: [(0, '10.970'), (1, '11.610')] -[2023-10-17 03:51:04,133][62373] Updated weights for policy 0, policy_version 89610 (0.0009) -[2023-10-17 03:51:04,508][62373] Updated weights for policy 0, policy_version 89620 (0.0009) -[2023-10-17 03:51:04,874][62373] Updated weights for policy 0, policy_version 89630 (0.0007) -[2023-10-17 03:51:05,912][62408] Updated weights for policy 1, policy_version 88970 (0.0011) -[2023-10-17 03:51:06,277][62408] Updated weights for policy 1, policy_version 88980 (0.0007) -[2023-10-17 03:51:06,659][62408] Updated weights for policy 1, policy_version 88990 (0.0007) -[2023-10-17 03:51:07,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 182910976. Throughput: 0: 1775.5, 1: 1775.4. Samples: 45729482. Policy #0 lag: (min: 29.0, avg: 33.8, max: 61.0) -[2023-10-17 03:51:07,215][61453] Avg episode reward: [(0, '11.590'), (1, '11.340')] -[2023-10-17 03:51:08,728][62373] Updated weights for policy 0, policy_version 89640 (0.0009) -[2023-10-17 03:51:09,099][62373] Updated weights for policy 0, policy_version 89650 (0.0009) -[2023-10-17 03:51:09,467][62373] Updated weights for policy 0, policy_version 89660 (0.0008) -[2023-10-17 03:51:10,506][62408] Updated weights for policy 1, policy_version 89000 (0.0009) -[2023-10-17 03:51:10,869][62408] Updated weights for policy 1, policy_version 89010 (0.0007) -[2023-10-17 03:51:11,228][62408] Updated weights for policy 1, policy_version 89020 (0.0009) -[2023-10-17 03:51:12,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 182976512. Throughput: 0: 1768.3, 1: 1775.5. Samples: 45750716. Policy #0 lag: (min: 29.0, avg: 33.8, max: 61.0) -[2023-10-17 03:51:12,215][61453] Avg episode reward: [(0, '11.810'), (1, '11.480')] -[2023-10-17 03:51:13,345][62373] Updated weights for policy 0, policy_version 89670 (0.0009) -[2023-10-17 03:51:13,720][62373] Updated weights for policy 0, policy_version 89680 (0.0008) -[2023-10-17 03:51:14,090][62373] Updated weights for policy 0, policy_version 89690 (0.0009) -[2023-10-17 03:51:14,963][62408] Updated weights for policy 1, policy_version 89030 (0.0009) -[2023-10-17 03:51:15,324][62408] Updated weights for policy 1, policy_version 89040 (0.0009) -[2023-10-17 03:51:15,690][62408] Updated weights for policy 1, policy_version 89050 (0.0008) -[2023-10-17 03:51:17,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 183042048. Throughput: 0: 1784.4, 1: 1759.1. Samples: 45772366. Policy #0 lag: (min: 29.0, avg: 33.8, max: 61.0) -[2023-10-17 03:51:17,215][61453] Avg episode reward: [(0, '10.890'), (1, '11.120')] -[2023-10-17 03:51:17,754][62373] Updated weights for policy 0, policy_version 89700 (0.0010) -[2023-10-17 03:51:18,129][62373] Updated weights for policy 0, policy_version 89710 (0.0008) -[2023-10-17 03:51:18,506][62373] Updated weights for policy 0, policy_version 89720 (0.0007) -[2023-10-17 03:51:19,707][62408] Updated weights for policy 1, policy_version 89060 (0.0008) -[2023-10-17 03:51:20,075][62408] Updated weights for policy 1, policy_version 89070 (0.0008) -[2023-10-17 03:51:20,449][62408] Updated weights for policy 1, policy_version 89080 (0.0009) -[2023-10-17 03:51:22,196][62373] Updated weights for policy 0, policy_version 89730 (0.0007) -[2023-10-17 03:51:22,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 183107584. Throughput: 0: 1778.3, 1: 1780.2. Samples: 45783064. Policy #0 lag: (min: 29.0, avg: 33.8, max: 61.0) -[2023-10-17 03:51:22,214][61453] Avg episode reward: [(0, '10.950'), (1, '11.430')] -[2023-10-17 03:51:22,561][62373] Updated weights for policy 0, policy_version 89740 (0.0010) -[2023-10-17 03:51:22,934][62373] Updated weights for policy 0, policy_version 89750 (0.0009) -[2023-10-17 03:51:23,304][62373] Updated weights for policy 0, policy_version 89760 (0.0010) -[2023-10-17 03:51:24,380][62408] Updated weights for policy 1, policy_version 89090 (0.0010) -[2023-10-17 03:51:24,744][62408] Updated weights for policy 1, policy_version 89100 (0.0007) -[2023-10-17 03:51:25,120][62408] Updated weights for policy 1, policy_version 89110 (0.0007) -[2023-10-17 03:51:25,481][62408] Updated weights for policy 1, policy_version 89120 (0.0009) -[2023-10-17 03:51:27,073][62373] Updated weights for policy 0, policy_version 89770 (0.0010) -[2023-10-17 03:51:27,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 183173120. Throughput: 0: 1787.0, 1: 1751.7. Samples: 45804222. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-17 03:51:27,215][61453] Avg episode reward: [(0, '11.650'), (1, '12.150')] -[2023-10-17 03:51:27,428][62373] Updated weights for policy 0, policy_version 89780 (0.0010) -[2023-10-17 03:51:27,795][62373] Updated weights for policy 0, policy_version 89790 (0.0011) -[2023-10-17 03:51:29,138][62408] Updated weights for policy 1, policy_version 89130 (0.0008) -[2023-10-17 03:51:29,500][62408] Updated weights for policy 1, policy_version 89140 (0.0010) -[2023-10-17 03:51:29,875][62408] Updated weights for policy 1, policy_version 89150 (0.0007) -[2023-10-17 03:51:31,754][62373] Updated weights for policy 0, policy_version 89800 (0.0008) -[2023-10-17 03:51:32,131][62373] Updated weights for policy 0, policy_version 89810 (0.0008) -[2023-10-17 03:51:32,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 183238656. Throughput: 0: 1798.2, 1: 1760.3. Samples: 45826176. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-17 03:51:32,215][61453] Avg episode reward: [(0, '11.110'), (1, '11.520')] -[2023-10-17 03:51:32,228][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000089152_91291648.pth... -[2023-10-17 03:51:32,262][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000087520_89620480.pth -[2023-10-17 03:51:32,499][62373] Updated weights for policy 0, policy_version 89820 (0.0008) -[2023-10-17 03:51:32,647][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000089824_91979776.pth... -[2023-10-17 03:51:32,686][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000088160_90275840.pth -[2023-10-17 03:51:33,675][62408] Updated weights for policy 1, policy_version 89160 (0.0008) -[2023-10-17 03:51:34,047][62408] Updated weights for policy 1, policy_version 89170 (0.0007) -[2023-10-17 03:51:34,416][62408] Updated weights for policy 1, policy_version 89180 (0.0007) -[2023-10-17 03:51:36,320][62373] Updated weights for policy 0, policy_version 89830 (0.0008) -[2023-10-17 03:51:36,698][62373] Updated weights for policy 0, policy_version 89840 (0.0008) -[2023-10-17 03:51:37,070][62373] Updated weights for policy 0, policy_version 89850 (0.0008) -[2023-10-17 03:51:37,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 183304192. Throughput: 0: 1779.6, 1: 1760.8. Samples: 45836378. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-17 03:51:37,215][61453] Avg episode reward: [(0, '11.250'), (1, '10.780')] -[2023-10-17 03:51:38,096][62408] Updated weights for policy 1, policy_version 89190 (0.0008) -[2023-10-17 03:51:38,476][62408] Updated weights for policy 1, policy_version 89200 (0.0007) -[2023-10-17 03:51:38,842][62408] Updated weights for policy 1, policy_version 89210 (0.0008) -[2023-10-17 03:51:40,851][62373] Updated weights for policy 0, policy_version 89860 (0.0008) -[2023-10-17 03:51:41,215][62373] Updated weights for policy 0, policy_version 89870 (0.0010) -[2023-10-17 03:51:41,586][62373] Updated weights for policy 0, policy_version 89880 (0.0010) -[2023-10-17 03:51:42,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 183402496. Throughput: 0: 1802.7, 1: 1761.6. Samples: 45858060. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-17 03:51:42,215][61453] Avg episode reward: [(0, '10.810'), (1, '11.110')] -[2023-10-17 03:51:42,706][62408] Updated weights for policy 1, policy_version 89220 (0.0008) -[2023-10-17 03:51:43,078][62408] Updated weights for policy 1, policy_version 89230 (0.0008) -[2023-10-17 03:51:43,439][62408] Updated weights for policy 1, policy_version 89240 (0.0008) -[2023-10-17 03:51:45,345][62373] Updated weights for policy 0, policy_version 89890 (0.0010) -[2023-10-17 03:51:45,710][62373] Updated weights for policy 0, policy_version 89900 (0.0010) -[2023-10-17 03:51:46,075][62373] Updated weights for policy 0, policy_version 89910 (0.0010) -[2023-10-17 03:51:46,453][62373] Updated weights for policy 0, policy_version 89920 (0.0011) -[2023-10-17 03:51:47,214][61453] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 183468032. Throughput: 0: 1777.9, 1: 1791.0. Samples: 45879040. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-17 03:51:47,215][61453] Avg episode reward: [(0, '10.440'), (1, '11.510')] -[2023-10-17 03:51:47,303][62408] Updated weights for policy 1, policy_version 89250 (0.0008) -[2023-10-17 03:51:47,678][62408] Updated weights for policy 1, policy_version 89260 (0.0009) -[2023-10-17 03:51:48,048][62408] Updated weights for policy 1, policy_version 89270 (0.0009) -[2023-10-17 03:51:48,405][62408] Updated weights for policy 1, policy_version 89280 (0.0010) -[2023-10-17 03:51:50,215][62373] Updated weights for policy 0, policy_version 89930 (0.0007) -[2023-10-17 03:51:50,582][62373] Updated weights for policy 0, policy_version 89940 (0.0008) -[2023-10-17 03:51:50,952][62373] Updated weights for policy 0, policy_version 89950 (0.0010) -[2023-10-17 03:51:52,152][62408] Updated weights for policy 1, policy_version 89290 (0.0009) -[2023-10-17 03:51:52,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 183533568. Throughput: 0: 1803.5, 1: 1764.3. Samples: 45890032. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-17 03:51:52,214][61453] Avg episode reward: [(0, '10.710'), (1, '12.540')] -[2023-10-17 03:51:52,509][62408] Updated weights for policy 1, policy_version 89300 (0.0007) -[2023-10-17 03:51:52,880][62408] Updated weights for policy 1, policy_version 89310 (0.0007) -[2023-10-17 03:51:54,693][62373] Updated weights for policy 0, policy_version 89960 (0.0008) -[2023-10-17 03:51:55,061][62373] Updated weights for policy 0, policy_version 89970 (0.0007) -[2023-10-17 03:51:55,425][62373] Updated weights for policy 0, policy_version 89980 (0.0008) -[2023-10-17 03:51:56,760][62408] Updated weights for policy 1, policy_version 89320 (0.0007) -[2023-10-17 03:51:57,131][62408] Updated weights for policy 1, policy_version 89330 (0.0008) -[2023-10-17 03:51:57,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 183599104. Throughput: 0: 1783.4, 1: 1779.8. Samples: 45911060. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-17 03:51:57,214][61453] Avg episode reward: [(0, '10.460'), (1, '12.030')] -[2023-10-17 03:51:57,498][62408] Updated weights for policy 1, policy_version 89340 (0.0009) -[2023-10-17 03:51:59,096][62373] Updated weights for policy 0, policy_version 89990 (0.0011) -[2023-10-17 03:51:59,461][62373] Updated weights for policy 0, policy_version 90000 (0.0010) -[2023-10-17 03:51:59,836][62373] Updated weights for policy 0, policy_version 90010 (0.0008) -[2023-10-17 03:52:01,141][62408] Updated weights for policy 1, policy_version 89350 (0.0007) -[2023-10-17 03:52:01,504][62408] Updated weights for policy 1, policy_version 89360 (0.0009) -[2023-10-17 03:52:01,870][62408] Updated weights for policy 1, policy_version 89370 (0.0009) -[2023-10-17 03:52:02,214][61453] Fps is (10 sec: 16383.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 183697408. Throughput: 0: 1785.8, 1: 1771.0. Samples: 45932422. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-17 03:52:02,215][61453] Avg episode reward: [(0, '10.320'), (1, '12.410')] -[2023-10-17 03:52:03,623][62373] Updated weights for policy 0, policy_version 90020 (0.0008) -[2023-10-17 03:52:04,006][62373] Updated weights for policy 0, policy_version 90030 (0.0009) -[2023-10-17 03:52:04,367][62373] Updated weights for policy 0, policy_version 90040 (0.0009) -[2023-10-17 03:52:05,821][62408] Updated weights for policy 1, policy_version 89380 (0.0008) -[2023-10-17 03:52:06,192][62408] Updated weights for policy 1, policy_version 89390 (0.0008) -[2023-10-17 03:52:06,563][62408] Updated weights for policy 1, policy_version 89400 (0.0007) -[2023-10-17 03:52:07,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 183762944. Throughput: 0: 1782.4, 1: 1771.9. Samples: 45943008. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-17 03:52:07,214][61453] Avg episode reward: [(0, '9.700'), (1, '12.210')] -[2023-10-17 03:52:08,170][62373] Updated weights for policy 0, policy_version 90050 (0.0009) -[2023-10-17 03:52:08,544][62373] Updated weights for policy 0, policy_version 90060 (0.0008) -[2023-10-17 03:52:08,910][62373] Updated weights for policy 0, policy_version 90070 (0.0007) -[2023-10-17 03:52:09,272][62373] Updated weights for policy 0, policy_version 90080 (0.0007) -[2023-10-17 03:52:10,316][62408] Updated weights for policy 1, policy_version 89410 (0.0007) -[2023-10-17 03:52:10,673][62408] Updated weights for policy 1, policy_version 89420 (0.0008) -[2023-10-17 03:52:11,032][62408] Updated weights for policy 1, policy_version 89430 (0.0009) -[2023-10-17 03:52:11,401][62408] Updated weights for policy 1, policy_version 89440 (0.0008) -[2023-10-17 03:52:12,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 183828480. Throughput: 0: 1778.4, 1: 1784.8. Samples: 45964568. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-17 03:52:12,215][61453] Avg episode reward: [(0, '9.450'), (1, '12.260')] -[2023-10-17 03:52:12,894][62373] Updated weights for policy 0, policy_version 90090 (0.0007) -[2023-10-17 03:52:13,261][62373] Updated weights for policy 0, policy_version 90100 (0.0009) -[2023-10-17 03:52:13,631][62373] Updated weights for policy 0, policy_version 90110 (0.0007) -[2023-10-17 03:52:15,260][62408] Updated weights for policy 1, policy_version 89450 (0.0011) -[2023-10-17 03:52:15,615][62408] Updated weights for policy 1, policy_version 89460 (0.0010) -[2023-10-17 03:52:15,981][62408] Updated weights for policy 1, policy_version 89470 (0.0010) -[2023-10-17 03:52:17,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 183894016. Throughput: 0: 1794.8, 1: 1757.6. Samples: 45986032. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-17 03:52:17,215][61453] Avg episode reward: [(0, '9.470'), (1, '12.780')] -[2023-10-17 03:52:17,462][62373] Updated weights for policy 0, policy_version 90120 (0.0008) -[2023-10-17 03:52:17,835][62373] Updated weights for policy 0, policy_version 90130 (0.0008) -[2023-10-17 03:52:18,205][62373] Updated weights for policy 0, policy_version 90140 (0.0009) -[2023-10-17 03:52:19,735][62408] Updated weights for policy 1, policy_version 89480 (0.0008) -[2023-10-17 03:52:20,105][62408] Updated weights for policy 1, policy_version 89490 (0.0008) -[2023-10-17 03:52:20,472][62408] Updated weights for policy 1, policy_version 89500 (0.0007) -[2023-10-17 03:52:22,092][62373] Updated weights for policy 0, policy_version 90150 (0.0008) -[2023-10-17 03:52:22,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 183959552. Throughput: 0: 1778.4, 1: 1781.3. Samples: 45996566. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-10-17 03:52:22,214][61453] Avg episode reward: [(0, '10.150'), (1, '12.170')] -[2023-10-17 03:52:22,453][62373] Updated weights for policy 0, policy_version 90160 (0.0009) -[2023-10-17 03:52:22,826][62373] Updated weights for policy 0, policy_version 90170 (0.0009) -[2023-10-17 03:52:24,381][62408] Updated weights for policy 1, policy_version 89510 (0.0008) -[2023-10-17 03:52:24,770][62408] Updated weights for policy 1, policy_version 89520 (0.0011) -[2023-10-17 03:52:25,136][62408] Updated weights for policy 1, policy_version 89530 (0.0011) -[2023-10-17 03:52:26,621][62373] Updated weights for policy 0, policy_version 90180 (0.0008) -[2023-10-17 03:52:26,998][62373] Updated weights for policy 0, policy_version 90190 (0.0010) -[2023-10-17 03:52:27,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 184025088. Throughput: 0: 1782.8, 1: 1755.0. Samples: 46017258. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:52:27,215][61453] Avg episode reward: [(0, '10.730'), (1, '12.150')] -[2023-10-17 03:52:27,355][62373] Updated weights for policy 0, policy_version 90200 (0.0008) -[2023-10-17 03:52:28,984][62408] Updated weights for policy 1, policy_version 89540 (0.0010) -[2023-10-17 03:52:29,354][62408] Updated weights for policy 1, policy_version 89550 (0.0011) -[2023-10-17 03:52:29,725][62408] Updated weights for policy 1, policy_version 89560 (0.0010) -[2023-10-17 03:52:30,914][62373] Updated weights for policy 0, policy_version 90210 (0.0008) -[2023-10-17 03:52:31,280][62373] Updated weights for policy 0, policy_version 90220 (0.0010) -[2023-10-17 03:52:31,658][62373] Updated weights for policy 0, policy_version 90230 (0.0011) -[2023-10-17 03:52:32,034][62373] Updated weights for policy 0, policy_version 90240 (0.0009) -[2023-10-17 03:52:32,214][61453] Fps is (10 sec: 16383.5, 60 sec: 14745.6, 300 sec: 14329.0). Total num frames: 184123392. Throughput: 0: 1783.8, 1: 1750.0. Samples: 46038062. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:52:32,215][61453] Avg episode reward: [(0, '9.990'), (1, '12.510')] -[2023-10-17 03:52:33,595][62408] Updated weights for policy 1, policy_version 89570 (0.0011) -[2023-10-17 03:52:33,966][62408] Updated weights for policy 1, policy_version 89580 (0.0009) -[2023-10-17 03:52:34,333][62408] Updated weights for policy 1, policy_version 89590 (0.0009) -[2023-10-17 03:52:34,695][62408] Updated weights for policy 1, policy_version 89600 (0.0007) -[2023-10-17 03:52:35,792][62373] Updated weights for policy 0, policy_version 90250 (0.0010) -[2023-10-17 03:52:36,156][62373] Updated weights for policy 0, policy_version 90260 (0.0007) -[2023-10-17 03:52:36,526][62373] Updated weights for policy 0, policy_version 90270 (0.0008) -[2023-10-17 03:52:37,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 184188928. Throughput: 0: 1786.3, 1: 1747.7. Samples: 46049060. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:52:37,214][61453] Avg episode reward: [(0, '10.490'), (1, '12.280')] -[2023-10-17 03:52:38,549][62408] Updated weights for policy 1, policy_version 89610 (0.0008) -[2023-10-17 03:52:38,906][62408] Updated weights for policy 1, policy_version 89620 (0.0007) -[2023-10-17 03:52:39,271][62408] Updated weights for policy 1, policy_version 89630 (0.0007) -[2023-10-17 03:52:40,184][62373] Updated weights for policy 0, policy_version 90280 (0.0008) -[2023-10-17 03:52:40,549][62373] Updated weights for policy 0, policy_version 90290 (0.0008) -[2023-10-17 03:52:40,919][62373] Updated weights for policy 0, policy_version 90300 (0.0008) -[2023-10-17 03:52:42,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 184254464. Throughput: 0: 1789.0, 1: 1745.2. Samples: 46070100. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:52:42,215][61453] Avg episode reward: [(0, '10.750'), (1, '11.790')] -[2023-10-17 03:52:42,957][62408] Updated weights for policy 1, policy_version 89640 (0.0007) -[2023-10-17 03:52:43,334][62408] Updated weights for policy 1, policy_version 89650 (0.0008) -[2023-10-17 03:52:43,703][62408] Updated weights for policy 1, policy_version 89660 (0.0007) -[2023-10-17 03:52:44,831][62373] Updated weights for policy 0, policy_version 90310 (0.0008) -[2023-10-17 03:52:45,206][62373] Updated weights for policy 0, policy_version 90320 (0.0009) -[2023-10-17 03:52:45,577][62373] Updated weights for policy 0, policy_version 90330 (0.0009) -[2023-10-17 03:52:47,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 184320000. Throughput: 0: 1772.2, 1: 1773.3. Samples: 46091970. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:52:47,214][61453] Avg episode reward: [(0, '10.380'), (1, '12.030')] -[2023-10-17 03:52:47,572][62408] Updated weights for policy 1, policy_version 89670 (0.0008) -[2023-10-17 03:52:47,936][62408] Updated weights for policy 1, policy_version 89680 (0.0008) -[2023-10-17 03:52:48,304][62408] Updated weights for policy 1, policy_version 89690 (0.0009) -[2023-10-17 03:52:49,331][62373] Updated weights for policy 0, policy_version 90340 (0.0010) -[2023-10-17 03:52:49,708][62373] Updated weights for policy 0, policy_version 90350 (0.0010) -[2023-10-17 03:52:50,078][62373] Updated weights for policy 0, policy_version 90360 (0.0009) -[2023-10-17 03:52:52,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 184385536. Throughput: 0: 1786.9, 1: 1747.6. Samples: 46102058. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:52:52,214][61453] Avg episode reward: [(0, '10.350'), (1, '11.890')] -[2023-10-17 03:52:52,294][62408] Updated weights for policy 1, policy_version 89700 (0.0008) -[2023-10-17 03:52:52,670][62408] Updated weights for policy 1, policy_version 89710 (0.0008) -[2023-10-17 03:52:53,050][62408] Updated weights for policy 1, policy_version 89720 (0.0009) -[2023-10-17 03:52:53,873][62373] Updated weights for policy 0, policy_version 90370 (0.0009) -[2023-10-17 03:52:54,234][62373] Updated weights for policy 0, policy_version 90380 (0.0008) -[2023-10-17 03:52:54,608][62373] Updated weights for policy 0, policy_version 90390 (0.0009) -[2023-10-17 03:52:54,984][62373] Updated weights for policy 0, policy_version 90400 (0.0009) -[2023-10-17 03:52:56,852][62408] Updated weights for policy 1, policy_version 89730 (0.0009) -[2023-10-17 03:52:57,214][61453] Fps is (10 sec: 13106.7, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 184451072. Throughput: 0: 1773.7, 1: 1763.3. Samples: 46123736. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:52:57,216][61453] Avg episode reward: [(0, '9.430'), (1, '11.970')] -[2023-10-17 03:52:57,221][62408] Updated weights for policy 1, policy_version 89740 (0.0009) -[2023-10-17 03:52:57,581][62408] Updated weights for policy 1, policy_version 89750 (0.0010) -[2023-10-17 03:52:57,950][62408] Updated weights for policy 1, policy_version 89760 (0.0010) -[2023-10-17 03:52:58,805][62373] Updated weights for policy 0, policy_version 90410 (0.0009) -[2023-10-17 03:52:59,158][62373] Updated weights for policy 0, policy_version 90420 (0.0009) -[2023-10-17 03:52:59,537][62373] Updated weights for policy 0, policy_version 90430 (0.0010) -[2023-10-17 03:53:01,895][62408] Updated weights for policy 1, policy_version 89770 (0.0008) -[2023-10-17 03:53:02,214][61453] Fps is (10 sec: 13107.1, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 184516608. Throughput: 0: 1774.8, 1: 1770.1. Samples: 46145556. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:53:02,214][61453] Avg episode reward: [(0, '10.160'), (1, '11.620')] -[2023-10-17 03:53:02,259][62408] Updated weights for policy 1, policy_version 89780 (0.0008) -[2023-10-17 03:53:02,633][62408] Updated weights for policy 1, policy_version 89790 (0.0009) -[2023-10-17 03:53:03,180][62373] Updated weights for policy 0, policy_version 90440 (0.0007) -[2023-10-17 03:53:03,550][62373] Updated weights for policy 0, policy_version 90450 (0.0008) -[2023-10-17 03:53:03,926][62373] Updated weights for policy 0, policy_version 90460 (0.0011) -[2023-10-17 03:53:06,445][62408] Updated weights for policy 1, policy_version 89800 (0.0008) -[2023-10-17 03:53:06,804][62408] Updated weights for policy 1, policy_version 89810 (0.0007) -[2023-10-17 03:53:07,170][62408] Updated weights for policy 1, policy_version 89820 (0.0007) -[2023-10-17 03:53:07,214][61453] Fps is (10 sec: 13107.6, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 184582144. Throughput: 0: 1778.1, 1: 1760.6. Samples: 46155808. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:53:07,215][61453] Avg episode reward: [(0, '10.400'), (1, '11.760')] -[2023-10-17 03:53:07,800][62373] Updated weights for policy 0, policy_version 90470 (0.0007) -[2023-10-17 03:53:08,168][62373] Updated weights for policy 0, policy_version 90480 (0.0008) -[2023-10-17 03:53:08,541][62373] Updated weights for policy 0, policy_version 90490 (0.0008) -[2023-10-17 03:53:11,065][62408] Updated weights for policy 1, policy_version 89830 (0.0008) -[2023-10-17 03:53:11,454][62408] Updated weights for policy 1, policy_version 89840 (0.0008) -[2023-10-17 03:53:11,828][62408] Updated weights for policy 1, policy_version 89850 (0.0009) -[2023-10-17 03:53:12,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 184680448. Throughput: 0: 1780.7, 1: 1782.1. Samples: 46177586. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:53:12,215][61453] Avg episode reward: [(0, '9.900'), (1, '11.640')] -[2023-10-17 03:53:12,242][62373] Updated weights for policy 0, policy_version 90500 (0.0008) -[2023-10-17 03:53:12,605][62373] Updated weights for policy 0, policy_version 90510 (0.0007) -[2023-10-17 03:53:12,978][62373] Updated weights for policy 0, policy_version 90520 (0.0007) -[2023-10-17 03:53:15,546][62408] Updated weights for policy 1, policy_version 89860 (0.0008) -[2023-10-17 03:53:15,908][62408] Updated weights for policy 1, policy_version 89870 (0.0008) -[2023-10-17 03:53:16,284][62408] Updated weights for policy 1, policy_version 89880 (0.0008) -[2023-10-17 03:53:16,711][62373] Updated weights for policy 0, policy_version 90530 (0.0009) -[2023-10-17 03:53:17,073][62373] Updated weights for policy 0, policy_version 90540 (0.0008) -[2023-10-17 03:53:17,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 184745984. Throughput: 0: 1802.9, 1: 1756.9. Samples: 46198254. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:53:17,215][61453] Avg episode reward: [(0, '10.370'), (1, '11.390')] -[2023-10-17 03:53:17,439][62373] Updated weights for policy 0, policy_version 90550 (0.0007) -[2023-10-17 03:53:17,811][62373] Updated weights for policy 0, policy_version 90560 (0.0010) -[2023-10-17 03:53:20,056][62408] Updated weights for policy 1, policy_version 89890 (0.0008) -[2023-10-17 03:53:20,418][62408] Updated weights for policy 1, policy_version 89900 (0.0008) -[2023-10-17 03:53:20,792][62408] Updated weights for policy 1, policy_version 89910 (0.0009) -[2023-10-17 03:53:21,153][62408] Updated weights for policy 1, policy_version 89920 (0.0010) -[2023-10-17 03:53:21,631][62373] Updated weights for policy 0, policy_version 90570 (0.0009) -[2023-10-17 03:53:22,000][62373] Updated weights for policy 0, policy_version 90580 (0.0007) -[2023-10-17 03:53:22,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 184811520. Throughput: 0: 1780.3, 1: 1795.7. Samples: 46209980. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:53:22,214][61453] Avg episode reward: [(0, '10.630'), (1, '12.010')] -[2023-10-17 03:53:22,359][62373] Updated weights for policy 0, policy_version 90590 (0.0008) -[2023-10-17 03:53:24,900][62408] Updated weights for policy 1, policy_version 89930 (0.0011) -[2023-10-17 03:53:25,267][62408] Updated weights for policy 1, policy_version 89940 (0.0009) -[2023-10-17 03:53:25,635][62408] Updated weights for policy 1, policy_version 89950 (0.0009) -[2023-10-17 03:53:26,154][62373] Updated weights for policy 0, policy_version 90600 (0.0009) -[2023-10-17 03:53:26,528][62373] Updated weights for policy 0, policy_version 90610 (0.0008) -[2023-10-17 03:53:26,896][62373] Updated weights for policy 0, policy_version 90620 (0.0009) -[2023-10-17 03:53:27,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 184909824. Throughput: 0: 1799.2, 1: 1770.2. Samples: 46230726. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-17 03:53:27,215][61453] Avg episode reward: [(0, '10.440'), (1, '12.580')] -[2023-10-17 03:53:29,348][62408] Updated weights for policy 1, policy_version 89960 (0.0007) -[2023-10-17 03:53:29,707][62408] Updated weights for policy 1, policy_version 89970 (0.0009) -[2023-10-17 03:53:30,073][62408] Updated weights for policy 1, policy_version 89980 (0.0007) -[2023-10-17 03:53:30,760][62373] Updated weights for policy 0, policy_version 90630 (0.0009) -[2023-10-17 03:53:31,129][62373] Updated weights for policy 0, policy_version 90640 (0.0011) -[2023-10-17 03:53:31,488][62373] Updated weights for policy 0, policy_version 90650 (0.0010) -[2023-10-17 03:53:32,214][61453] Fps is (10 sec: 16383.4, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 184975360. Throughput: 0: 1782.8, 1: 1769.4. Samples: 46251820. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-17 03:53:32,215][61453] Avg episode reward: [(0, '11.050'), (1, '12.250')] -[2023-10-17 03:53:32,227][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000090656_92831744.pth... -[2023-10-17 03:53:32,227][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000089984_92143616.pth... -[2023-10-17 03:53:32,263][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000088320_90439680.pth -[2023-10-17 03:53:32,266][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000088992_91127808.pth -[2023-10-17 03:53:33,908][62408] Updated weights for policy 1, policy_version 89990 (0.0010) -[2023-10-17 03:53:34,269][62408] Updated weights for policy 1, policy_version 90000 (0.0011) -[2023-10-17 03:53:34,645][62408] Updated weights for policy 1, policy_version 90010 (0.0010) -[2023-10-17 03:53:35,364][62373] Updated weights for policy 0, policy_version 90660 (0.0007) -[2023-10-17 03:53:35,754][62373] Updated weights for policy 0, policy_version 90670 (0.0010) -[2023-10-17 03:53:36,115][62373] Updated weights for policy 0, policy_version 90680 (0.0009) -[2023-10-17 03:53:37,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 185040896. Throughput: 0: 1804.8, 1: 1772.7. Samples: 46263044. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-17 03:53:37,215][61453] Avg episode reward: [(0, '10.100'), (1, '12.690')] -[2023-10-17 03:53:38,562][62408] Updated weights for policy 1, policy_version 90020 (0.0011) -[2023-10-17 03:53:38,932][62408] Updated weights for policy 1, policy_version 90030 (0.0010) -[2023-10-17 03:53:39,300][62408] Updated weights for policy 1, policy_version 90040 (0.0010) -[2023-10-17 03:53:39,798][62373] Updated weights for policy 0, policy_version 90690 (0.0007) -[2023-10-17 03:53:40,173][62373] Updated weights for policy 0, policy_version 90700 (0.0009) -[2023-10-17 03:53:40,531][62373] Updated weights for policy 0, policy_version 90710 (0.0008) -[2023-10-17 03:53:40,900][62373] Updated weights for policy 0, policy_version 90720 (0.0010) -[2023-10-17 03:53:42,214][61453] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 185106432. Throughput: 0: 1784.6, 1: 1765.5. Samples: 46283490. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-17 03:53:42,214][61453] Avg episode reward: [(0, '10.230'), (1, '12.410')] -[2023-10-17 03:53:43,055][62408] Updated weights for policy 1, policy_version 90050 (0.0009) -[2023-10-17 03:53:43,425][62408] Updated weights for policy 1, policy_version 90060 (0.0008) -[2023-10-17 03:53:43,786][62408] Updated weights for policy 1, policy_version 90070 (0.0008) -[2023-10-17 03:53:44,154][62408] Updated weights for policy 1, policy_version 90080 (0.0009) -[2023-10-17 03:53:44,520][62373] Updated weights for policy 0, policy_version 90730 (0.0007) -[2023-10-17 03:53:44,893][62373] Updated weights for policy 0, policy_version 90740 (0.0008) -[2023-10-17 03:53:45,262][62373] Updated weights for policy 0, policy_version 90750 (0.0009) -[2023-10-17 03:53:47,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 185171968. Throughput: 0: 1781.9, 1: 1776.3. Samples: 46305678. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-17 03:53:47,215][61453] Avg episode reward: [(0, '9.930'), (1, '11.980')] -[2023-10-17 03:53:47,885][62408] Updated weights for policy 1, policy_version 90090 (0.0009) -[2023-10-17 03:53:48,258][62408] Updated weights for policy 1, policy_version 90100 (0.0008) -[2023-10-17 03:53:48,623][62408] Updated weights for policy 1, policy_version 90110 (0.0010) -[2023-10-17 03:53:49,221][62373] Updated weights for policy 0, policy_version 90760 (0.0010) -[2023-10-17 03:53:49,593][62373] Updated weights for policy 0, policy_version 90770 (0.0009) -[2023-10-17 03:53:49,954][62373] Updated weights for policy 0, policy_version 90780 (0.0007) -[2023-10-17 03:53:52,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 185237504. Throughput: 0: 1782.9, 1: 1761.3. Samples: 46315300. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-17 03:53:52,215][61453] Avg episode reward: [(0, '10.220'), (1, '12.150')] -[2023-10-17 03:53:52,487][62408] Updated weights for policy 1, policy_version 90120 (0.0007) -[2023-10-17 03:53:52,858][62408] Updated weights for policy 1, policy_version 90130 (0.0008) -[2023-10-17 03:53:53,220][62408] Updated weights for policy 1, policy_version 90140 (0.0008) -[2023-10-17 03:53:53,897][62373] Updated weights for policy 0, policy_version 90790 (0.0009) -[2023-10-17 03:53:54,271][62373] Updated weights for policy 0, policy_version 90800 (0.0009) -[2023-10-17 03:53:54,650][62373] Updated weights for policy 0, policy_version 90810 (0.0009) -[2023-10-17 03:53:57,119][62408] Updated weights for policy 1, policy_version 90150 (0.0009) -[2023-10-17 03:53:57,214][61453] Fps is (10 sec: 13107.6, 60 sec: 14199.6, 300 sec: 14106.9). Total num frames: 185303040. Throughput: 0: 1775.9, 1: 1769.0. Samples: 46337106. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-17 03:53:57,214][61453] Avg episode reward: [(0, '10.170'), (1, '10.730')] -[2023-10-17 03:53:57,499][62408] Updated weights for policy 1, policy_version 90160 (0.0008) -[2023-10-17 03:53:57,867][62408] Updated weights for policy 1, policy_version 90170 (0.0010) -[2023-10-17 03:53:58,462][62373] Updated weights for policy 0, policy_version 90820 (0.0008) -[2023-10-17 03:53:58,828][62373] Updated weights for policy 0, policy_version 90830 (0.0009) -[2023-10-17 03:53:59,197][62373] Updated weights for policy 0, policy_version 90840 (0.0007) -[2023-10-17 03:54:01,632][62408] Updated weights for policy 1, policy_version 90180 (0.0008) -[2023-10-17 03:54:02,002][62408] Updated weights for policy 1, policy_version 90190 (0.0009) -[2023-10-17 03:54:02,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 185368576. Throughput: 0: 1782.7, 1: 1785.9. Samples: 46358840. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-17 03:54:02,215][61453] Avg episode reward: [(0, '10.670'), (1, '10.830')] -[2023-10-17 03:54:02,368][62408] Updated weights for policy 1, policy_version 90200 (0.0009) -[2023-10-17 03:54:02,945][62373] Updated weights for policy 0, policy_version 90850 (0.0010) -[2023-10-17 03:54:03,302][62373] Updated weights for policy 0, policy_version 90860 (0.0009) -[2023-10-17 03:54:03,677][62373] Updated weights for policy 0, policy_version 90870 (0.0007) -[2023-10-17 03:54:04,044][62373] Updated weights for policy 0, policy_version 90880 (0.0008) -[2023-10-17 03:54:06,356][62408] Updated weights for policy 1, policy_version 90210 (0.0008) -[2023-10-17 03:54:06,719][62408] Updated weights for policy 1, policy_version 90220 (0.0008) -[2023-10-17 03:54:07,089][62408] Updated weights for policy 1, policy_version 90230 (0.0011) -[2023-10-17 03:54:07,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 185434112. Throughput: 0: 1773.7, 1: 1758.0. Samples: 46368908. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-17 03:54:07,215][61453] Avg episode reward: [(0, '10.140'), (1, '11.150')] -[2023-10-17 03:54:07,462][62408] Updated weights for policy 1, policy_version 90240 (0.0010) -[2023-10-17 03:54:07,820][62373] Updated weights for policy 0, policy_version 90890 (0.0009) -[2023-10-17 03:54:08,180][62373] Updated weights for policy 0, policy_version 90900 (0.0008) -[2023-10-17 03:54:08,553][62373] Updated weights for policy 0, policy_version 90910 (0.0008) -[2023-10-17 03:54:11,195][62408] Updated weights for policy 1, policy_version 90250 (0.0010) -[2023-10-17 03:54:11,554][62408] Updated weights for policy 1, policy_version 90260 (0.0008) -[2023-10-17 03:54:11,931][62408] Updated weights for policy 1, policy_version 90270 (0.0009) -[2023-10-17 03:54:12,214][61453] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 185532416. Throughput: 0: 1776.4, 1: 1779.9. Samples: 46390758. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-17 03:54:12,215][61453] Avg episode reward: [(0, '10.860'), (1, '11.170')] -[2023-10-17 03:54:12,379][62373] Updated weights for policy 0, policy_version 90920 (0.0008) -[2023-10-17 03:54:12,747][62373] Updated weights for policy 0, policy_version 90930 (0.0007) -[2023-10-17 03:54:13,123][62373] Updated weights for policy 0, policy_version 90940 (0.0008) -[2023-10-17 03:54:15,780][62408] Updated weights for policy 1, policy_version 90280 (0.0010) -[2023-10-17 03:54:16,153][62408] Updated weights for policy 1, policy_version 90290 (0.0008) -[2023-10-17 03:54:16,522][62408] Updated weights for policy 1, policy_version 90300 (0.0008) -[2023-10-17 03:54:16,893][62373] Updated weights for policy 0, policy_version 90950 (0.0009) -[2023-10-17 03:54:17,214][61453] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 185597952. Throughput: 0: 1796.3, 1: 1747.7. Samples: 46411298. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-17 03:54:17,214][61453] Avg episode reward: [(0, '11.450'), (1, '10.680')] -[2023-10-17 03:54:17,257][62373] Updated weights for policy 0, policy_version 90960 (0.0011) -[2023-10-17 03:54:17,630][62373] Updated weights for policy 0, policy_version 90970 (0.0008) -[2023-10-17 03:54:20,207][62408] Updated weights for policy 1, policy_version 90310 (0.0008) -[2023-10-17 03:54:20,572][62408] Updated weights for policy 1, policy_version 90320 (0.0008) -[2023-10-17 03:54:20,950][62408] Updated weights for policy 1, policy_version 90330 (0.0010) -[2023-10-17 03:54:21,508][62373] Updated weights for policy 0, policy_version 90980 (0.0009) -[2023-10-17 03:54:21,886][62373] Updated weights for policy 0, policy_version 90990 (0.0008) -[2023-10-17 03:54:22,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 185663488. Throughput: 0: 1768.7, 1: 1782.2. Samples: 46422836. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-10-17 03:54:22,215][61453] Avg episode reward: [(0, '10.800'), (1, '11.620')] -[2023-10-17 03:54:22,249][62373] Updated weights for policy 0, policy_version 91000 (0.0008) -[2023-10-17 03:54:24,808][62408] Updated weights for policy 1, policy_version 90340 (0.0011) -[2023-10-17 03:54:25,173][62408] Updated weights for policy 1, policy_version 90350 (0.0009) -[2023-10-17 03:54:25,539][62408] Updated weights for policy 1, policy_version 90360 (0.0007) -[2023-10-17 03:54:26,003][62373] Updated weights for policy 0, policy_version 91010 (0.0011) -[2023-10-17 03:54:26,367][62373] Updated weights for policy 0, policy_version 91020 (0.0007) -[2023-10-17 03:54:26,738][62373] Updated weights for policy 0, policy_version 91030 (0.0009) -[2023-10-17 03:54:27,099][62373] Updated weights for policy 0, policy_version 91040 (0.0010) -[2023-10-17 03:54:27,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 185761792. Throughput: 0: 1800.1, 1: 1754.6. Samples: 46443452. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:54:27,214][61453] Avg episode reward: [(0, '10.560'), (1, '10.540')] -[2023-10-17 03:54:29,343][62408] Updated weights for policy 1, policy_version 90370 (0.0009) -[2023-10-17 03:54:29,710][62408] Updated weights for policy 1, policy_version 90380 (0.0009) -[2023-10-17 03:54:30,083][62408] Updated weights for policy 1, policy_version 90390 (0.0009) -[2023-10-17 03:54:30,439][62408] Updated weights for policy 1, policy_version 90400 (0.0009) -[2023-10-17 03:54:30,905][62373] Updated weights for policy 0, policy_version 91050 (0.0009) -[2023-10-17 03:54:31,270][62373] Updated weights for policy 0, policy_version 91060 (0.0009) -[2023-10-17 03:54:31,640][62373] Updated weights for policy 0, policy_version 91070 (0.0007) -[2023-10-17 03:54:32,214][61453] Fps is (10 sec: 16383.6, 60 sec: 14199.5, 300 sec: 14329.0). Total num frames: 185827328. Throughput: 0: 1770.8, 1: 1758.1. Samples: 46464478. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:54:32,215][61453] Avg episode reward: [(0, '10.770'), (1, '11.360')] -[2023-10-17 03:54:34,188][62408] Updated weights for policy 1, policy_version 90410 (0.0007) -[2023-10-17 03:54:34,553][62408] Updated weights for policy 1, policy_version 90420 (0.0009) -[2023-10-17 03:54:34,928][62408] Updated weights for policy 1, policy_version 90430 (0.0010) -[2023-10-17 03:54:35,408][62373] Updated weights for policy 0, policy_version 91080 (0.0007) -[2023-10-17 03:54:35,777][62373] Updated weights for policy 0, policy_version 91090 (0.0007) -[2023-10-17 03:54:36,144][62373] Updated weights for policy 0, policy_version 91100 (0.0007) -[2023-10-17 03:54:37,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 185892864. Throughput: 0: 1802.6, 1: 1765.2. Samples: 46475850. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:54:37,215][61453] Avg episode reward: [(0, '10.400'), (1, '10.840')] -[2023-10-17 03:54:38,761][62408] Updated weights for policy 1, policy_version 90440 (0.0012) -[2023-10-17 03:54:39,128][62408] Updated weights for policy 1, policy_version 90450 (0.0009) -[2023-10-17 03:54:39,491][62408] Updated weights for policy 1, policy_version 90460 (0.0009) -[2023-10-17 03:54:39,911][62373] Updated weights for policy 0, policy_version 91110 (0.0009) -[2023-10-17 03:54:40,282][62373] Updated weights for policy 0, policy_version 91120 (0.0008) -[2023-10-17 03:54:40,650][62373] Updated weights for policy 0, policy_version 91130 (0.0008) -[2023-10-17 03:54:42,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 185958400. Throughput: 0: 1779.0, 1: 1754.8. Samples: 46496124. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:54:42,215][61453] Avg episode reward: [(0, '10.550'), (1, '10.750')] -[2023-10-17 03:54:43,476][62408] Updated weights for policy 1, policy_version 90470 (0.0010) -[2023-10-17 03:54:43,866][62408] Updated weights for policy 1, policy_version 90480 (0.0008) -[2023-10-17 03:54:44,229][62408] Updated weights for policy 1, policy_version 90490 (0.0007) -[2023-10-17 03:54:44,388][62373] Updated weights for policy 0, policy_version 91140 (0.0008) -[2023-10-17 03:54:44,762][62373] Updated weights for policy 0, policy_version 91150 (0.0010) -[2023-10-17 03:54:45,142][62373] Updated weights for policy 0, policy_version 91160 (0.0009) -[2023-10-17 03:54:47,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 186023936. Throughput: 0: 1773.4, 1: 1765.0. Samples: 46518068. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:54:47,214][61453] Avg episode reward: [(0, '10.370'), (1, '11.610')] -[2023-10-17 03:54:48,093][62408] Updated weights for policy 1, policy_version 90500 (0.0008) -[2023-10-17 03:54:48,459][62408] Updated weights for policy 1, policy_version 90510 (0.0007) -[2023-10-17 03:54:48,829][62408] Updated weights for policy 1, policy_version 90520 (0.0009) -[2023-10-17 03:54:48,883][62373] Updated weights for policy 0, policy_version 91170 (0.0008) -[2023-10-17 03:54:49,258][62373] Updated weights for policy 0, policy_version 91180 (0.0009) -[2023-10-17 03:54:49,615][62373] Updated weights for policy 0, policy_version 91190 (0.0007) -[2023-10-17 03:54:49,987][62373] Updated weights for policy 0, policy_version 91200 (0.0007) -[2023-10-17 03:54:52,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 186089472. Throughput: 0: 1778.0, 1: 1759.2. Samples: 46528084. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:54:52,215][61453] Avg episode reward: [(0, '9.600'), (1, '11.010')] -[2023-10-17 03:54:52,795][62408] Updated weights for policy 1, policy_version 90530 (0.0008) -[2023-10-17 03:54:53,159][62408] Updated weights for policy 1, policy_version 90540 (0.0007) -[2023-10-17 03:54:53,520][62408] Updated weights for policy 1, policy_version 90550 (0.0009) -[2023-10-17 03:54:53,778][62373] Updated weights for policy 0, policy_version 91210 (0.0007) -[2023-10-17 03:54:53,886][62408] Updated weights for policy 1, policy_version 90560 (0.0008) -[2023-10-17 03:54:54,147][62373] Updated weights for policy 0, policy_version 91220 (0.0007) -[2023-10-17 03:54:54,522][62373] Updated weights for policy 0, policy_version 91230 (0.0010) -[2023-10-17 03:54:57,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 186155008. Throughput: 0: 1776.0, 1: 1767.1. Samples: 46550198. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:54:57,215][61453] Avg episode reward: [(0, '9.500'), (1, '11.840')] -[2023-10-17 03:54:57,635][62408] Updated weights for policy 1, policy_version 90570 (0.0007) -[2023-10-17 03:54:58,003][62408] Updated weights for policy 1, policy_version 90580 (0.0010) -[2023-10-17 03:54:58,353][62373] Updated weights for policy 0, policy_version 91240 (0.0009) -[2023-10-17 03:54:58,372][62408] Updated weights for policy 1, policy_version 90590 (0.0007) -[2023-10-17 03:54:58,726][62373] Updated weights for policy 0, policy_version 91250 (0.0009) -[2023-10-17 03:54:59,092][62373] Updated weights for policy 0, policy_version 91260 (0.0008) -[2023-10-17 03:55:01,965][62408] Updated weights for policy 1, policy_version 90600 (0.0011) -[2023-10-17 03:55:02,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 186220544. Throughput: 0: 1783.8, 1: 1795.9. Samples: 46572382. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:55:02,215][61453] Avg episode reward: [(0, '9.350'), (1, '11.590')] -[2023-10-17 03:55:02,334][62408] Updated weights for policy 1, policy_version 90610 (0.0009) -[2023-10-17 03:55:02,705][62408] Updated weights for policy 1, policy_version 90620 (0.0007) -[2023-10-17 03:55:02,748][62373] Updated weights for policy 0, policy_version 91270 (0.0008) -[2023-10-17 03:55:03,119][62373] Updated weights for policy 0, policy_version 91280 (0.0007) -[2023-10-17 03:55:03,486][62373] Updated weights for policy 0, policy_version 91290 (0.0010) -[2023-10-17 03:55:06,699][62408] Updated weights for policy 1, policy_version 90630 (0.0008) -[2023-10-17 03:55:07,067][62408] Updated weights for policy 1, policy_version 90640 (0.0008) -[2023-10-17 03:55:07,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 186286080. Throughput: 0: 1775.0, 1: 1762.2. Samples: 46582008. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:55:07,215][61453] Avg episode reward: [(0, '9.360'), (1, '12.360')] -[2023-10-17 03:55:07,437][62408] Updated weights for policy 1, policy_version 90650 (0.0008) -[2023-10-17 03:55:07,441][62373] Updated weights for policy 0, policy_version 91300 (0.0010) -[2023-10-17 03:55:07,810][62373] Updated weights for policy 0, policy_version 91310 (0.0009) -[2023-10-17 03:55:08,174][62373] Updated weights for policy 0, policy_version 91320 (0.0011) -[2023-10-17 03:55:11,251][62408] Updated weights for policy 1, policy_version 90660 (0.0007) -[2023-10-17 03:55:11,617][62408] Updated weights for policy 1, policy_version 90670 (0.0009) -[2023-10-17 03:55:11,811][62373] Updated weights for policy 0, policy_version 91330 (0.0009) -[2023-10-17 03:55:11,992][62408] Updated weights for policy 1, policy_version 90680 (0.0007) -[2023-10-17 03:55:12,173][62373] Updated weights for policy 0, policy_version 91340 (0.0008) -[2023-10-17 03:55:12,214][61453] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 186351616. Throughput: 0: 1774.5, 1: 1792.8. Samples: 46603980. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:55:12,215][61453] Avg episode reward: [(0, '9.580'), (1, '12.290')] -[2023-10-17 03:55:12,543][62373] Updated weights for policy 0, policy_version 91350 (0.0010) -[2023-10-17 03:55:12,905][62373] Updated weights for policy 0, policy_version 91360 (0.0009) -[2023-10-17 03:55:15,805][62408] Updated weights for policy 1, policy_version 90690 (0.0009) -[2023-10-17 03:55:16,177][62408] Updated weights for policy 1, policy_version 90700 (0.0008) -[2023-10-17 03:55:16,544][62408] Updated weights for policy 1, policy_version 90710 (0.0008) -[2023-10-17 03:55:16,790][62373] Updated weights for policy 0, policy_version 91370 (0.0007) -[2023-10-17 03:55:16,904][62408] Updated weights for policy 1, policy_version 90720 (0.0008) -[2023-10-17 03:55:17,161][62373] Updated weights for policy 0, policy_version 91380 (0.0011) -[2023-10-17 03:55:17,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 186449920. Throughput: 0: 1790.6, 1: 1760.1. Samples: 46624260. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:55:17,215][61453] Avg episode reward: [(0, '9.670'), (1, '12.900')] -[2023-10-17 03:55:17,224][62252] Saving new best policy, reward=12.900! -[2023-10-17 03:55:17,530][62373] Updated weights for policy 0, policy_version 91390 (0.0008) -[2023-10-17 03:55:20,696][62408] Updated weights for policy 1, policy_version 90730 (0.0011) -[2023-10-17 03:55:21,060][62408] Updated weights for policy 1, policy_version 90740 (0.0009) -[2023-10-17 03:55:21,347][62373] Updated weights for policy 0, policy_version 91400 (0.0008) -[2023-10-17 03:55:21,426][62408] Updated weights for policy 1, policy_version 90750 (0.0007) -[2023-10-17 03:55:21,716][62373] Updated weights for policy 0, policy_version 91410 (0.0007) -[2023-10-17 03:55:22,082][62373] Updated weights for policy 0, policy_version 91420 (0.0008) -[2023-10-17 03:55:22,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 186515456. Throughput: 0: 1768.6, 1: 1786.9. Samples: 46635846. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:55:22,214][61453] Avg episode reward: [(0, '9.800'), (1, '12.790')] -[2023-10-17 03:55:25,334][62408] Updated weights for policy 1, policy_version 90760 (0.0007) -[2023-10-17 03:55:25,706][62408] Updated weights for policy 1, policy_version 90770 (0.0009) -[2023-10-17 03:55:25,799][62373] Updated weights for policy 0, policy_version 91430 (0.0007) -[2023-10-17 03:55:26,067][62408] Updated weights for policy 1, policy_version 90780 (0.0009) -[2023-10-17 03:55:26,162][62373] Updated weights for policy 0, policy_version 91440 (0.0007) -[2023-10-17 03:55:26,527][62373] Updated weights for policy 0, policy_version 91450 (0.0011) -[2023-10-17 03:55:27,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 186613760. Throughput: 0: 1795.5, 1: 1773.4. Samples: 46656726. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:55:27,215][61453] Avg episode reward: [(0, '9.890'), (1, '12.420')] -[2023-10-17 03:55:30,167][62408] Updated weights for policy 1, policy_version 90790 (0.0008) -[2023-10-17 03:55:30,397][62373] Updated weights for policy 0, policy_version 91460 (0.0009) -[2023-10-17 03:55:30,552][62408] Updated weights for policy 1, policy_version 90800 (0.0008) -[2023-10-17 03:55:30,757][62373] Updated weights for policy 0, policy_version 91470 (0.0008) -[2023-10-17 03:55:30,914][62408] Updated weights for policy 1, policy_version 90810 (0.0008) -[2023-10-17 03:55:31,124][62373] Updated weights for policy 0, policy_version 91480 (0.0007) -[2023-10-17 03:55:32,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 186679296. Throughput: 0: 1771.1, 1: 1756.8. Samples: 46676824. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:55:32,215][61453] Avg episode reward: [(0, '11.150'), (1, '12.560')] -[2023-10-17 03:55:32,224][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000090816_92995584.pth... -[2023-10-17 03:55:32,224][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000091488_93683712.pth... -[2023-10-17 03:55:32,256][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000089152_91291648.pth -[2023-10-17 03:55:32,260][62252] Saving a milestone ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/milestones/checkpoint_000090816_92995584.pth -[2023-10-17 03:55:32,266][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000089824_91979776.pth -[2023-10-17 03:55:32,271][62094] Saving a milestone ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/milestones/checkpoint_000091488_93683712.pth -[2023-10-17 03:55:34,784][62408] Updated weights for policy 1, policy_version 90820 (0.0009) -[2023-10-17 03:55:35,067][62373] Updated weights for policy 0, policy_version 91490 (0.0010) -[2023-10-17 03:55:35,141][62408] Updated weights for policy 1, policy_version 90830 (0.0008) -[2023-10-17 03:55:35,437][62373] Updated weights for policy 0, policy_version 91500 (0.0007) -[2023-10-17 03:55:35,512][62408] Updated weights for policy 1, policy_version 90840 (0.0008) -[2023-10-17 03:55:35,806][62373] Updated weights for policy 0, policy_version 91510 (0.0009) -[2023-10-17 03:55:36,174][62373] Updated weights for policy 0, policy_version 91520 (0.0010) -[2023-10-17 03:55:37,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 186744832. Throughput: 0: 1792.0, 1: 1774.2. Samples: 46688562. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:55:37,214][61453] Avg episode reward: [(0, '11.040'), (1, '12.760')] -[2023-10-17 03:55:39,508][62408] Updated weights for policy 1, policy_version 90850 (0.0008) -[2023-10-17 03:55:39,882][62408] Updated weights for policy 1, policy_version 90860 (0.0009) -[2023-10-17 03:55:40,070][62373] Updated weights for policy 0, policy_version 91530 (0.0009) -[2023-10-17 03:55:40,260][62408] Updated weights for policy 1, policy_version 90870 (0.0009) -[2023-10-17 03:55:40,438][62373] Updated weights for policy 0, policy_version 91540 (0.0009) -[2023-10-17 03:55:40,624][62408] Updated weights for policy 1, policy_version 90880 (0.0010) -[2023-10-17 03:55:40,809][62373] Updated weights for policy 0, policy_version 91550 (0.0009) -[2023-10-17 03:55:42,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 186810368. Throughput: 0: 1762.6, 1: 1738.5. Samples: 46707746. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:55:42,215][61453] Avg episode reward: [(0, '11.080'), (1, '12.170')] -[2023-10-17 03:55:44,455][62408] Updated weights for policy 1, policy_version 90890 (0.0008) -[2023-10-17 03:55:44,501][62373] Updated weights for policy 0, policy_version 91560 (0.0008) -[2023-10-17 03:55:44,814][62408] Updated weights for policy 1, policy_version 90900 (0.0008) -[2023-10-17 03:55:44,874][62373] Updated weights for policy 0, policy_version 91570 (0.0008) -[2023-10-17 03:55:45,185][62408] Updated weights for policy 1, policy_version 90910 (0.0008) -[2023-10-17 03:55:45,254][62373] Updated weights for policy 0, policy_version 91580 (0.0009) -[2023-10-17 03:55:47,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 186875904. Throughput: 0: 1763.5, 1: 1737.8. Samples: 46729940. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:55:47,215][61453] Avg episode reward: [(0, '11.040'), (1, '12.240')] -[2023-10-17 03:55:48,814][62408] Updated weights for policy 1, policy_version 90920 (0.0009) -[2023-10-17 03:55:48,984][62373] Updated weights for policy 0, policy_version 91590 (0.0008) -[2023-10-17 03:55:49,182][62408] Updated weights for policy 1, policy_version 90930 (0.0008) -[2023-10-17 03:55:49,346][62373] Updated weights for policy 0, policy_version 91600 (0.0007) -[2023-10-17 03:55:49,546][62408] Updated weights for policy 1, policy_version 90940 (0.0008) -[2023-10-17 03:55:49,718][62373] Updated weights for policy 0, policy_version 91610 (0.0007) -[2023-10-17 03:55:52,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 186941440. Throughput: 0: 1764.4, 1: 1740.3. Samples: 46739722. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:55:52,215][61453] Avg episode reward: [(0, '11.580'), (1, '11.450')] -[2023-10-17 03:55:53,332][62408] Updated weights for policy 1, policy_version 90950 (0.0008) -[2023-10-17 03:55:53,544][62373] Updated weights for policy 0, policy_version 91620 (0.0008) -[2023-10-17 03:55:53,700][62408] Updated weights for policy 1, policy_version 90960 (0.0007) -[2023-10-17 03:55:53,918][62373] Updated weights for policy 0, policy_version 91630 (0.0007) -[2023-10-17 03:55:54,063][62408] Updated weights for policy 1, policy_version 90970 (0.0009) -[2023-10-17 03:55:54,283][62373] Updated weights for policy 0, policy_version 91640 (0.0009) -[2023-10-17 03:55:57,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 187006976. Throughput: 0: 1763.6, 1: 1742.8. Samples: 46761768. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:55:57,215][61453] Avg episode reward: [(0, '11.640'), (1, '12.020')] -[2023-10-17 03:55:57,954][62408] Updated weights for policy 1, policy_version 90980 (0.0009) -[2023-10-17 03:55:57,994][62373] Updated weights for policy 0, policy_version 91650 (0.0007) -[2023-10-17 03:55:58,314][62408] Updated weights for policy 1, policy_version 90990 (0.0007) -[2023-10-17 03:55:58,370][62373] Updated weights for policy 0, policy_version 91660 (0.0008) -[2023-10-17 03:55:58,680][62408] Updated weights for policy 1, policy_version 91000 (0.0007) -[2023-10-17 03:55:58,746][62373] Updated weights for policy 0, policy_version 91670 (0.0008) -[2023-10-17 03:55:59,115][62373] Updated weights for policy 0, policy_version 91680 (0.0007) -[2023-10-17 03:56:02,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 187072512. Throughput: 0: 1779.2, 1: 1771.2. Samples: 46784028. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:56:02,215][61453] Avg episode reward: [(0, '11.750'), (1, '12.150')] -[2023-10-17 03:56:02,539][62408] Updated weights for policy 1, policy_version 91010 (0.0008) -[2023-10-17 03:56:02,903][62408] Updated weights for policy 1, policy_version 91020 (0.0007) -[2023-10-17 03:56:02,975][62373] Updated weights for policy 0, policy_version 91690 (0.0009) -[2023-10-17 03:56:03,263][62408] Updated weights for policy 1, policy_version 91030 (0.0008) -[2023-10-17 03:56:03,347][62373] Updated weights for policy 0, policy_version 91700 (0.0008) -[2023-10-17 03:56:03,627][62408] Updated weights for policy 1, policy_version 91040 (0.0008) -[2023-10-17 03:56:03,719][62373] Updated weights for policy 0, policy_version 91710 (0.0009) -[2023-10-17 03:56:07,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 187138048. Throughput: 0: 1763.0, 1: 1740.1. Samples: 46793486. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:56:07,215][61453] Avg episode reward: [(0, '10.690'), (1, '11.760')] -[2023-10-17 03:56:07,474][62408] Updated weights for policy 1, policy_version 91050 (0.0009) -[2023-10-17 03:56:07,519][62373] Updated weights for policy 0, policy_version 91720 (0.0009) -[2023-10-17 03:56:07,838][62408] Updated weights for policy 1, policy_version 91060 (0.0007) -[2023-10-17 03:56:07,892][62373] Updated weights for policy 0, policy_version 91730 (0.0008) -[2023-10-17 03:56:08,213][62408] Updated weights for policy 1, policy_version 91070 (0.0008) -[2023-10-17 03:56:08,259][62373] Updated weights for policy 0, policy_version 91740 (0.0008) -[2023-10-17 03:56:11,886][62373] Updated weights for policy 0, policy_version 91750 (0.0009) -[2023-10-17 03:56:12,159][62408] Updated weights for policy 1, policy_version 91080 (0.0008) -[2023-10-17 03:56:12,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 187203584. Throughput: 0: 1774.6, 1: 1755.1. Samples: 46815564. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:56:12,215][61453] Avg episode reward: [(0, '11.020'), (1, '11.190')] -[2023-10-17 03:56:12,253][62373] Updated weights for policy 0, policy_version 91760 (0.0008) -[2023-10-17 03:56:12,528][62408] Updated weights for policy 1, policy_version 91090 (0.0008) -[2023-10-17 03:56:12,620][62373] Updated weights for policy 0, policy_version 91770 (0.0007) -[2023-10-17 03:56:12,886][62408] Updated weights for policy 1, policy_version 91100 (0.0007) -[2023-10-17 03:56:16,588][62373] Updated weights for policy 0, policy_version 91780 (0.0009) -[2023-10-17 03:56:16,764][62408] Updated weights for policy 1, policy_version 91110 (0.0010) -[2023-10-17 03:56:16,963][62373] Updated weights for policy 0, policy_version 91790 (0.0009) -[2023-10-17 03:56:17,145][62408] Updated weights for policy 1, policy_version 91120 (0.0007) -[2023-10-17 03:56:17,214][61453] Fps is (10 sec: 13107.4, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 187269120. Throughput: 0: 1782.3, 1: 1769.1. Samples: 46836636. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:56:17,214][61453] Avg episode reward: [(0, '11.650'), (1, '11.350')] -[2023-10-17 03:56:17,327][62373] Updated weights for policy 0, policy_version 91800 (0.0010) -[2023-10-17 03:56:17,515][62408] Updated weights for policy 1, policy_version 91130 (0.0009) -[2023-10-17 03:56:21,021][62373] Updated weights for policy 0, policy_version 91810 (0.0008) -[2023-10-17 03:56:21,391][62408] Updated weights for policy 1, policy_version 91140 (0.0008) -[2023-10-17 03:56:21,395][62373] Updated weights for policy 0, policy_version 91820 (0.0009) -[2023-10-17 03:56:21,752][62373] Updated weights for policy 0, policy_version 91830 (0.0007) -[2023-10-17 03:56:21,757][62408] Updated weights for policy 1, policy_version 91150 (0.0008) -[2023-10-17 03:56:22,126][62373] Updated weights for policy 0, policy_version 91840 (0.0010) -[2023-10-17 03:56:22,126][62408] Updated weights for policy 1, policy_version 91160 (0.0009) -[2023-10-17 03:56:22,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 187367424. Throughput: 0: 1770.4, 1: 1757.0. Samples: 46847296. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:56:22,215][61453] Avg episode reward: [(0, '10.900'), (1, '11.040')] -[2023-10-17 03:56:25,789][62373] Updated weights for policy 0, policy_version 91850 (0.0008) -[2023-10-17 03:56:25,872][62408] Updated weights for policy 1, policy_version 91170 (0.0009) -[2023-10-17 03:56:26,153][62373] Updated weights for policy 0, policy_version 91860 (0.0008) -[2023-10-17 03:56:26,233][62408] Updated weights for policy 1, policy_version 91180 (0.0008) -[2023-10-17 03:56:26,522][62373] Updated weights for policy 0, policy_version 91870 (0.0008) -[2023-10-17 03:56:26,596][62408] Updated weights for policy 1, policy_version 91190 (0.0008) -[2023-10-17 03:56:26,967][62408] Updated weights for policy 1, policy_version 91200 (0.0008) -[2023-10-17 03:56:27,214][61453] Fps is (10 sec: 19661.0, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 187465728. Throughput: 0: 1797.0, 1: 1789.9. Samples: 46869158. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:56:27,214][61453] Avg episode reward: [(0, '11.240'), (1, '10.970')] -[2023-10-17 03:56:30,204][62373] Updated weights for policy 0, policy_version 91880 (0.0008) -[2023-10-17 03:56:30,575][62373] Updated weights for policy 0, policy_version 91890 (0.0008) -[2023-10-17 03:56:30,695][62408] Updated weights for policy 1, policy_version 91210 (0.0009) -[2023-10-17 03:56:30,946][62373] Updated weights for policy 0, policy_version 91900 (0.0008) -[2023-10-17 03:56:31,050][62408] Updated weights for policy 1, policy_version 91220 (0.0007) -[2023-10-17 03:56:31,418][62408] Updated weights for policy 1, policy_version 91230 (0.0008) -[2023-10-17 03:56:32,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 187531264. Throughput: 0: 1777.9, 1: 1762.1. Samples: 46889238. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:56:32,215][61453] Avg episode reward: [(0, '10.920'), (1, '10.650')] -[2023-10-17 03:56:34,816][62373] Updated weights for policy 0, policy_version 91910 (0.0008) -[2023-10-17 03:56:35,175][62373] Updated weights for policy 0, policy_version 91920 (0.0008) -[2023-10-17 03:56:35,182][62408] Updated weights for policy 1, policy_version 91240 (0.0007) -[2023-10-17 03:56:35,544][62408] Updated weights for policy 1, policy_version 91250 (0.0008) -[2023-10-17 03:56:35,545][62373] Updated weights for policy 0, policy_version 91930 (0.0008) -[2023-10-17 03:56:35,918][62408] Updated weights for policy 1, policy_version 91260 (0.0008) -[2023-10-17 03:56:37,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 187596800. Throughput: 0: 1802.1, 1: 1790.5. Samples: 46901388. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:56:37,215][61453] Avg episode reward: [(0, '10.830'), (1, '10.730')] -[2023-10-17 03:56:39,216][62373] Updated weights for policy 0, policy_version 91940 (0.0009) -[2023-10-17 03:56:39,588][62373] Updated weights for policy 0, policy_version 91950 (0.0007) -[2023-10-17 03:56:39,780][62408] Updated weights for policy 1, policy_version 91270 (0.0008) -[2023-10-17 03:56:39,963][62373] Updated weights for policy 0, policy_version 91960 (0.0008) -[2023-10-17 03:56:40,147][62408] Updated weights for policy 1, policy_version 91280 (0.0008) -[2023-10-17 03:56:40,520][62408] Updated weights for policy 1, policy_version 91290 (0.0009) -[2023-10-17 03:56:42,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 187662336. Throughput: 0: 1779.0, 1: 1751.0. Samples: 46920616. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:56:42,215][61453] Avg episode reward: [(0, '10.830'), (1, '10.180')] -[2023-10-17 03:56:43,807][62373] Updated weights for policy 0, policy_version 91970 (0.0008) -[2023-10-17 03:56:44,196][62373] Updated weights for policy 0, policy_version 91980 (0.0009) -[2023-10-17 03:56:44,263][62408] Updated weights for policy 1, policy_version 91300 (0.0009) -[2023-10-17 03:56:44,559][62373] Updated weights for policy 0, policy_version 91990 (0.0007) -[2023-10-17 03:56:44,626][62408] Updated weights for policy 1, policy_version 91310 (0.0008) -[2023-10-17 03:56:44,928][62373] Updated weights for policy 0, policy_version 92000 (0.0007) -[2023-10-17 03:56:44,997][62408] Updated weights for policy 1, policy_version 91320 (0.0010) -[2023-10-17 03:56:47,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 187727872. Throughput: 0: 1778.7, 1: 1752.9. Samples: 46942950. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:56:47,214][61453] Avg episode reward: [(0, '10.620'), (1, '11.400')] -[2023-10-17 03:56:48,735][62373] Updated weights for policy 0, policy_version 92010 (0.0008) -[2023-10-17 03:56:48,929][62408] Updated weights for policy 1, policy_version 91330 (0.0007) -[2023-10-17 03:56:49,099][62373] Updated weights for policy 0, policy_version 92020 (0.0008) -[2023-10-17 03:56:49,291][62408] Updated weights for policy 1, policy_version 91340 (0.0008) -[2023-10-17 03:56:49,475][62373] Updated weights for policy 0, policy_version 92030 (0.0007) -[2023-10-17 03:56:49,657][62408] Updated weights for policy 1, policy_version 91350 (0.0009) -[2023-10-17 03:56:50,028][62408] Updated weights for policy 1, policy_version 91360 (0.0009) -[2023-10-17 03:56:52,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 187793408. Throughput: 0: 1783.2, 1: 1754.1. Samples: 46952664. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:56:52,215][61453] Avg episode reward: [(0, '10.140'), (1, '10.610')] -[2023-10-17 03:56:53,103][62373] Updated weights for policy 0, policy_version 92040 (0.0007) -[2023-10-17 03:56:53,473][62373] Updated weights for policy 0, policy_version 92050 (0.0009) -[2023-10-17 03:56:53,840][62373] Updated weights for policy 0, policy_version 92060 (0.0007) -[2023-10-17 03:56:53,924][62408] Updated weights for policy 1, policy_version 91370 (0.0007) -[2023-10-17 03:56:54,284][62408] Updated weights for policy 1, policy_version 91380 (0.0009) -[2023-10-17 03:56:54,657][62408] Updated weights for policy 1, policy_version 91390 (0.0008) -[2023-10-17 03:56:57,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 187858944. Throughput: 0: 1787.3, 1: 1754.9. Samples: 46974962. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:56:57,215][61453] Avg episode reward: [(0, '10.640'), (1, '10.610')] -[2023-10-17 03:56:57,638][62373] Updated weights for policy 0, policy_version 92070 (0.0008) -[2023-10-17 03:56:58,000][62373] Updated weights for policy 0, policy_version 92080 (0.0009) -[2023-10-17 03:56:58,371][62373] Updated weights for policy 0, policy_version 92090 (0.0007) -[2023-10-17 03:56:58,591][62408] Updated weights for policy 1, policy_version 91400 (0.0009) -[2023-10-17 03:56:58,955][62408] Updated weights for policy 1, policy_version 91410 (0.0010) -[2023-10-17 03:56:59,316][62408] Updated weights for policy 1, policy_version 91420 (0.0009) -[2023-10-17 03:57:02,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 187924480. Throughput: 0: 1801.2, 1: 1763.8. Samples: 46997060. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:57:02,215][61453] Avg episode reward: [(0, '9.970'), (1, '10.810')] -[2023-10-17 03:57:02,289][62373] Updated weights for policy 0, policy_version 92100 (0.0008) -[2023-10-17 03:57:02,656][62373] Updated weights for policy 0, policy_version 92110 (0.0008) -[2023-10-17 03:57:03,022][62373] Updated weights for policy 0, policy_version 92120 (0.0009) -[2023-10-17 03:57:03,251][62408] Updated weights for policy 1, policy_version 91430 (0.0007) -[2023-10-17 03:57:03,642][62408] Updated weights for policy 1, policy_version 91440 (0.0010) -[2023-10-17 03:57:04,007][62408] Updated weights for policy 1, policy_version 91450 (0.0010) -[2023-10-17 03:57:06,942][62373] Updated weights for policy 0, policy_version 92130 (0.0009) -[2023-10-17 03:57:07,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 187990016. Throughput: 0: 1784.1, 1: 1755.9. Samples: 47006596. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:57:07,214][61453] Avg episode reward: [(0, '9.790'), (1, '11.170')] -[2023-10-17 03:57:07,311][62373] Updated weights for policy 0, policy_version 92140 (0.0008) -[2023-10-17 03:57:07,671][62373] Updated weights for policy 0, policy_version 92150 (0.0008) -[2023-10-17 03:57:07,674][62408] Updated weights for policy 1, policy_version 91460 (0.0008) -[2023-10-17 03:57:08,032][62373] Updated weights for policy 0, policy_version 92160 (0.0007) -[2023-10-17 03:57:08,040][62408] Updated weights for policy 1, policy_version 91470 (0.0009) -[2023-10-17 03:57:08,407][62408] Updated weights for policy 1, policy_version 91480 (0.0010) -[2023-10-17 03:57:11,815][62373] Updated weights for policy 0, policy_version 92170 (0.0010) -[2023-10-17 03:57:12,166][62408] Updated weights for policy 1, policy_version 91490 (0.0009) -[2023-10-17 03:57:12,185][62373] Updated weights for policy 0, policy_version 92180 (0.0008) -[2023-10-17 03:57:12,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 188055552. Throughput: 0: 1785.4, 1: 1754.7. Samples: 47028464. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:57:12,215][61453] Avg episode reward: [(0, '10.570'), (1, '12.180')] -[2023-10-17 03:57:12,532][62408] Updated weights for policy 1, policy_version 91500 (0.0007) -[2023-10-17 03:57:12,566][62373] Updated weights for policy 0, policy_version 92190 (0.0009) -[2023-10-17 03:57:12,904][62408] Updated weights for policy 1, policy_version 91510 (0.0007) -[2023-10-17 03:57:13,263][62408] Updated weights for policy 1, policy_version 91520 (0.0009) -[2023-10-17 03:57:16,355][62373] Updated weights for policy 0, policy_version 92200 (0.0008) -[2023-10-17 03:57:16,722][62373] Updated weights for policy 0, policy_version 92210 (0.0007) -[2023-10-17 03:57:16,984][62408] Updated weights for policy 1, policy_version 91530 (0.0010) -[2023-10-17 03:57:17,092][62373] Updated weights for policy 0, policy_version 92220 (0.0008) -[2023-10-17 03:57:17,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 188121088. Throughput: 0: 1778.6, 1: 1782.3. Samples: 47049476. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 03:57:17,215][61453] Avg episode reward: [(0, '10.320'), (1, '12.150')] -[2023-10-17 03:57:17,347][62408] Updated weights for policy 1, policy_version 91540 (0.0008) -[2023-10-17 03:57:17,721][62408] Updated weights for policy 1, policy_version 91550 (0.0009) -[2023-10-17 03:57:20,935][62373] Updated weights for policy 0, policy_version 92230 (0.0009) -[2023-10-17 03:57:21,308][62373] Updated weights for policy 0, policy_version 92240 (0.0008) -[2023-10-17 03:57:21,625][62408] Updated weights for policy 1, policy_version 91560 (0.0008) -[2023-10-17 03:57:21,678][62373] Updated weights for policy 0, policy_version 92250 (0.0008) -[2023-10-17 03:57:21,992][62408] Updated weights for policy 1, policy_version 91570 (0.0008) -[2023-10-17 03:57:22,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 188219392. Throughput: 0: 1776.1, 1: 1759.8. Samples: 47060506. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-17 03:57:22,215][61453] Avg episode reward: [(0, '10.920'), (1, '11.650')] -[2023-10-17 03:57:22,365][62408] Updated weights for policy 1, policy_version 91580 (0.0008) -[2023-10-17 03:57:25,495][62373] Updated weights for policy 0, policy_version 92260 (0.0008) -[2023-10-17 03:57:25,852][62373] Updated weights for policy 0, policy_version 92270 (0.0010) -[2023-10-17 03:57:26,083][62408] Updated weights for policy 1, policy_version 91590 (0.0007) -[2023-10-17 03:57:26,226][62373] Updated weights for policy 0, policy_version 92280 (0.0007) -[2023-10-17 03:57:26,462][62408] Updated weights for policy 1, policy_version 91600 (0.0008) -[2023-10-17 03:57:26,826][62408] Updated weights for policy 1, policy_version 91610 (0.0008) -[2023-10-17 03:57:27,214][61453] Fps is (10 sec: 19660.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 188317696. Throughput: 0: 1783.5, 1: 1796.3. Samples: 47081706. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-17 03:57:27,215][61453] Avg episode reward: [(0, '11.030'), (1, '12.080')] -[2023-10-17 03:57:30,152][62373] Updated weights for policy 0, policy_version 92290 (0.0007) -[2023-10-17 03:57:30,536][62373] Updated weights for policy 0, policy_version 92300 (0.0009) -[2023-10-17 03:57:30,821][62408] Updated weights for policy 1, policy_version 91620 (0.0008) -[2023-10-17 03:57:30,913][62373] Updated weights for policy 0, policy_version 92310 (0.0008) -[2023-10-17 03:57:31,186][62408] Updated weights for policy 1, policy_version 91630 (0.0008) -[2023-10-17 03:57:31,274][62373] Updated weights for policy 0, policy_version 92320 (0.0007) -[2023-10-17 03:57:31,559][62408] Updated weights for policy 1, policy_version 91640 (0.0009) -[2023-10-17 03:57:32,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 188383232. Throughput: 0: 1762.1, 1: 1757.9. Samples: 47101352. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-17 03:57:32,215][61453] Avg episode reward: [(0, '10.090'), (1, '12.260')] -[2023-10-17 03:57:32,225][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000092320_94535680.pth... -[2023-10-17 03:57:32,225][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000091648_93847552.pth... -[2023-10-17 03:57:32,256][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000089984_92143616.pth -[2023-10-17 03:57:32,257][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000090656_92831744.pth -[2023-10-17 03:57:34,942][62373] Updated weights for policy 0, policy_version 92330 (0.0007) -[2023-10-17 03:57:35,295][62408] Updated weights for policy 1, policy_version 91650 (0.0007) -[2023-10-17 03:57:35,316][62373] Updated weights for policy 0, policy_version 92340 (0.0009) -[2023-10-17 03:57:35,671][62408] Updated weights for policy 1, policy_version 91660 (0.0008) -[2023-10-17 03:57:35,675][62373] Updated weights for policy 0, policy_version 92350 (0.0008) -[2023-10-17 03:57:36,040][62408] Updated weights for policy 1, policy_version 91670 (0.0008) -[2023-10-17 03:57:36,405][62408] Updated weights for policy 1, policy_version 91680 (0.0008) -[2023-10-17 03:57:37,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 188448768. Throughput: 0: 1786.0, 1: 1786.6. Samples: 47113432. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-17 03:57:37,214][61453] Avg episode reward: [(0, '10.900'), (1, '12.660')] -[2023-10-17 03:57:39,546][62373] Updated weights for policy 0, policy_version 92360 (0.0009) -[2023-10-17 03:57:39,900][62373] Updated weights for policy 0, policy_version 92370 (0.0007) -[2023-10-17 03:57:40,159][62408] Updated weights for policy 1, policy_version 91690 (0.0007) -[2023-10-17 03:57:40,269][62373] Updated weights for policy 0, policy_version 92380 (0.0007) -[2023-10-17 03:57:40,522][62408] Updated weights for policy 1, policy_version 91700 (0.0010) -[2023-10-17 03:57:40,882][62408] Updated weights for policy 1, policy_version 91710 (0.0007) -[2023-10-17 03:57:42,214][61453] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 188514304. Throughput: 0: 1752.6, 1: 1769.3. Samples: 47133448. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-17 03:57:42,215][61453] Avg episode reward: [(0, '11.250'), (1, '12.400')] -[2023-10-17 03:57:43,945][62373] Updated weights for policy 0, policy_version 92390 (0.0009) -[2023-10-17 03:57:44,310][62373] Updated weights for policy 0, policy_version 92400 (0.0007) -[2023-10-17 03:57:44,684][62373] Updated weights for policy 0, policy_version 92410 (0.0007) -[2023-10-17 03:57:44,719][62408] Updated weights for policy 1, policy_version 91720 (0.0008) -[2023-10-17 03:57:45,084][62408] Updated weights for policy 1, policy_version 91730 (0.0009) -[2023-10-17 03:57:45,454][62408] Updated weights for policy 1, policy_version 91740 (0.0009) -[2023-10-17 03:57:47,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 188579840. Throughput: 0: 1768.5, 1: 1758.2. Samples: 47155764. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-17 03:57:47,215][61453] Avg episode reward: [(0, '11.930'), (1, '12.200')] -[2023-10-17 03:57:48,361][62373] Updated weights for policy 0, policy_version 92420 (0.0007) -[2023-10-17 03:57:48,733][62373] Updated weights for policy 0, policy_version 92430 (0.0007) -[2023-10-17 03:57:49,103][62373] Updated weights for policy 0, policy_version 92440 (0.0008) -[2023-10-17 03:57:49,497][62408] Updated weights for policy 1, policy_version 91750 (0.0010) -[2023-10-17 03:57:49,878][62408] Updated weights for policy 1, policy_version 91760 (0.0009) -[2023-10-17 03:57:50,255][62408] Updated weights for policy 1, policy_version 91770 (0.0009) -[2023-10-17 03:57:52,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 188645376. Throughput: 0: 1767.9, 1: 1773.6. Samples: 47165964. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-17 03:57:52,215][61453] Avg episode reward: [(0, '11.180'), (1, '12.110')] -[2023-10-17 03:57:52,876][62373] Updated weights for policy 0, policy_version 92450 (0.0009) -[2023-10-17 03:57:53,247][62373] Updated weights for policy 0, policy_version 92460 (0.0009) -[2023-10-17 03:57:53,616][62373] Updated weights for policy 0, policy_version 92470 (0.0009) -[2023-10-17 03:57:53,987][62373] Updated weights for policy 0, policy_version 92480 (0.0008) -[2023-10-17 03:57:54,032][62408] Updated weights for policy 1, policy_version 91780 (0.0009) -[2023-10-17 03:57:54,399][62408] Updated weights for policy 1, policy_version 91790 (0.0009) -[2023-10-17 03:57:54,771][62408] Updated weights for policy 1, policy_version 91800 (0.0008) -[2023-10-17 03:57:57,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 188710912. Throughput: 0: 1776.5, 1: 1760.0. Samples: 47187610. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-17 03:57:57,215][61453] Avg episode reward: [(0, '10.790'), (1, '11.220')] -[2023-10-17 03:57:57,719][62373] Updated weights for policy 0, policy_version 92490 (0.0009) -[2023-10-17 03:57:58,087][62373] Updated weights for policy 0, policy_version 92500 (0.0008) -[2023-10-17 03:57:58,452][62373] Updated weights for policy 0, policy_version 92510 (0.0010) -[2023-10-17 03:57:58,615][62408] Updated weights for policy 1, policy_version 91810 (0.0009) -[2023-10-17 03:57:58,979][62408] Updated weights for policy 1, policy_version 91820 (0.0008) -[2023-10-17 03:57:59,339][62408] Updated weights for policy 1, policy_version 91830 (0.0010) -[2023-10-17 03:57:59,706][62408] Updated weights for policy 1, policy_version 91840 (0.0009) -[2023-10-17 03:58:02,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 188776448. Throughput: 0: 1802.4, 1: 1764.8. Samples: 47210000. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-17 03:58:02,215][61453] Avg episode reward: [(0, '10.930'), (1, '11.650')] -[2023-10-17 03:58:02,292][62373] Updated weights for policy 0, policy_version 92520 (0.0008) -[2023-10-17 03:58:02,664][62373] Updated weights for policy 0, policy_version 92530 (0.0009) -[2023-10-17 03:58:03,037][62373] Updated weights for policy 0, policy_version 92540 (0.0009) -[2023-10-17 03:58:03,392][62408] Updated weights for policy 1, policy_version 91850 (0.0009) -[2023-10-17 03:58:03,755][62408] Updated weights for policy 1, policy_version 91860 (0.0008) -[2023-10-17 03:58:04,125][62408] Updated weights for policy 1, policy_version 91870 (0.0009) -[2023-10-17 03:58:07,022][62373] Updated weights for policy 0, policy_version 92550 (0.0010) -[2023-10-17 03:58:07,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 188841984. Throughput: 0: 1779.3, 1: 1758.5. Samples: 47219702. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-17 03:58:07,214][61453] Avg episode reward: [(0, '10.230'), (1, '11.350')] -[2023-10-17 03:58:07,391][62373] Updated weights for policy 0, policy_version 92560 (0.0009) -[2023-10-17 03:58:07,766][62373] Updated weights for policy 0, policy_version 92570 (0.0008) -[2023-10-17 03:58:08,123][62408] Updated weights for policy 1, policy_version 91880 (0.0009) -[2023-10-17 03:58:08,486][62408] Updated weights for policy 1, policy_version 91890 (0.0009) -[2023-10-17 03:58:08,849][62408] Updated weights for policy 1, policy_version 91900 (0.0010) -[2023-10-17 03:58:11,718][62373] Updated weights for policy 0, policy_version 92580 (0.0007) -[2023-10-17 03:58:12,082][62373] Updated weights for policy 0, policy_version 92590 (0.0008) -[2023-10-17 03:58:12,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 188907520. Throughput: 0: 1792.0, 1: 1756.3. Samples: 47241382. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-17 03:58:12,215][61453] Avg episode reward: [(0, '10.200'), (1, '11.000')] -[2023-10-17 03:58:12,443][62373] Updated weights for policy 0, policy_version 92600 (0.0008) -[2023-10-17 03:58:12,643][62408] Updated weights for policy 1, policy_version 91910 (0.0008) -[2023-10-17 03:58:13,013][62408] Updated weights for policy 1, policy_version 91920 (0.0008) -[2023-10-17 03:58:13,383][62408] Updated weights for policy 1, policy_version 91930 (0.0010) -[2023-10-17 03:58:16,213][62373] Updated weights for policy 0, policy_version 92610 (0.0007) -[2023-10-17 03:58:16,600][62373] Updated weights for policy 0, policy_version 92620 (0.0007) -[2023-10-17 03:58:16,968][62373] Updated weights for policy 0, policy_version 92630 (0.0010) -[2023-10-17 03:58:17,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 188973056. Throughput: 0: 1791.1, 1: 1794.1. Samples: 47262682. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-10-17 03:58:17,214][61453] Avg episode reward: [(0, '10.270'), (1, '10.870')] -[2023-10-17 03:58:17,246][62408] Updated weights for policy 1, policy_version 91940 (0.0008) -[2023-10-17 03:58:17,341][62373] Updated weights for policy 0, policy_version 92640 (0.0009) -[2023-10-17 03:58:17,618][62408] Updated weights for policy 1, policy_version 91950 (0.0008) -[2023-10-17 03:58:17,983][62408] Updated weights for policy 1, policy_version 91960 (0.0008) -[2023-10-17 03:58:21,036][62373] Updated weights for policy 0, policy_version 92650 (0.0008) -[2023-10-17 03:58:21,408][62373] Updated weights for policy 0, policy_version 92660 (0.0008) -[2023-10-17 03:58:21,737][62408] Updated weights for policy 1, policy_version 91970 (0.0007) -[2023-10-17 03:58:21,770][62373] Updated weights for policy 0, policy_version 92670 (0.0007) -[2023-10-17 03:58:22,107][62408] Updated weights for policy 1, policy_version 91980 (0.0007) -[2023-10-17 03:58:22,214][61453] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 189071360. Throughput: 0: 1788.4, 1: 1764.0. Samples: 47273290. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-17 03:58:22,214][61453] Avg episode reward: [(0, '9.910'), (1, '11.000')] -[2023-10-17 03:58:22,477][62408] Updated weights for policy 1, policy_version 91990 (0.0008) -[2023-10-17 03:58:22,846][62408] Updated weights for policy 1, policy_version 92000 (0.0008) -[2023-10-17 03:58:25,609][62373] Updated weights for policy 0, policy_version 92680 (0.0007) -[2023-10-17 03:58:25,977][62373] Updated weights for policy 0, policy_version 92690 (0.0008) -[2023-10-17 03:58:26,342][62373] Updated weights for policy 0, policy_version 92700 (0.0009) -[2023-10-17 03:58:26,643][62408] Updated weights for policy 1, policy_version 92010 (0.0009) -[2023-10-17 03:58:27,007][62408] Updated weights for policy 1, policy_version 92020 (0.0009) -[2023-10-17 03:58:27,214][61453] Fps is (10 sec: 16384.1, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 189136896. Throughput: 0: 1794.9, 1: 1788.6. Samples: 47294704. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-17 03:58:27,214][61453] Avg episode reward: [(0, '10.040'), (1, '11.600')] -[2023-10-17 03:58:27,380][62408] Updated weights for policy 1, policy_version 92030 (0.0008) -[2023-10-17 03:58:30,050][62373] Updated weights for policy 0, policy_version 92710 (0.0007) -[2023-10-17 03:58:30,417][62373] Updated weights for policy 0, policy_version 92720 (0.0010) -[2023-10-17 03:58:30,785][62373] Updated weights for policy 0, policy_version 92730 (0.0008) -[2023-10-17 03:58:31,166][62408] Updated weights for policy 1, policy_version 92040 (0.0008) -[2023-10-17 03:58:31,538][62408] Updated weights for policy 1, policy_version 92050 (0.0008) -[2023-10-17 03:58:31,912][62408] Updated weights for policy 1, policy_version 92060 (0.0009) -[2023-10-17 03:58:32,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 189235200. Throughput: 0: 1769.6, 1: 1767.9. Samples: 47314950. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-17 03:58:32,215][61453] Avg episode reward: [(0, '10.420'), (1, '11.580')] -[2023-10-17 03:58:34,498][62373] Updated weights for policy 0, policy_version 92740 (0.0008) -[2023-10-17 03:58:34,871][62373] Updated weights for policy 0, policy_version 92750 (0.0008) -[2023-10-17 03:58:35,253][62373] Updated weights for policy 0, policy_version 92760 (0.0009) -[2023-10-17 03:58:35,780][62408] Updated weights for policy 1, policy_version 92070 (0.0010) -[2023-10-17 03:58:36,147][62408] Updated weights for policy 1, policy_version 92080 (0.0011) -[2023-10-17 03:58:36,524][62408] Updated weights for policy 1, policy_version 92090 (0.0010) -[2023-10-17 03:58:37,214][61453] Fps is (10 sec: 16383.4, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 189300736. Throughput: 0: 1792.4, 1: 1779.2. Samples: 47326686. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-17 03:58:37,215][61453] Avg episode reward: [(0, '10.400'), (1, '11.590')] -[2023-10-17 03:58:38,988][62373] Updated weights for policy 0, policy_version 92770 (0.0009) -[2023-10-17 03:58:39,353][62373] Updated weights for policy 0, policy_version 92780 (0.0009) -[2023-10-17 03:58:39,721][62373] Updated weights for policy 0, policy_version 92790 (0.0010) -[2023-10-17 03:58:40,090][62373] Updated weights for policy 0, policy_version 92800 (0.0010) -[2023-10-17 03:58:40,315][62408] Updated weights for policy 1, policy_version 92100 (0.0009) -[2023-10-17 03:58:40,679][62408] Updated weights for policy 1, policy_version 92110 (0.0009) -[2023-10-17 03:58:41,054][62408] Updated weights for policy 1, policy_version 92120 (0.0011) -[2023-10-17 03:58:42,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 189366272. Throughput: 0: 1769.6, 1: 1771.9. Samples: 47346978. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-17 03:58:42,215][61453] Avg episode reward: [(0, '10.910'), (1, '11.810')] -[2023-10-17 03:58:44,033][62373] Updated weights for policy 0, policy_version 92810 (0.0008) -[2023-10-17 03:58:44,410][62373] Updated weights for policy 0, policy_version 92820 (0.0008) -[2023-10-17 03:58:44,780][62373] Updated weights for policy 0, policy_version 92830 (0.0008) -[2023-10-17 03:58:45,016][62408] Updated weights for policy 1, policy_version 92130 (0.0009) -[2023-10-17 03:58:45,385][62408] Updated weights for policy 1, policy_version 92140 (0.0008) -[2023-10-17 03:58:45,751][62408] Updated weights for policy 1, policy_version 92150 (0.0008) -[2023-10-17 03:58:46,115][62408] Updated weights for policy 1, policy_version 92160 (0.0008) -[2023-10-17 03:58:47,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 189431808. Throughput: 0: 1768.1, 1: 1753.8. Samples: 47368484. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-17 03:58:47,215][61453] Avg episode reward: [(0, '10.460'), (1, '11.920')] -[2023-10-17 03:58:48,642][62373] Updated weights for policy 0, policy_version 92840 (0.0009) -[2023-10-17 03:58:49,007][62373] Updated weights for policy 0, policy_version 92850 (0.0011) -[2023-10-17 03:58:49,388][62373] Updated weights for policy 0, policy_version 92860 (0.0007) -[2023-10-17 03:58:49,939][62408] Updated weights for policy 1, policy_version 92170 (0.0008) -[2023-10-17 03:58:50,315][62408] Updated weights for policy 1, policy_version 92180 (0.0008) -[2023-10-17 03:58:50,686][62408] Updated weights for policy 1, policy_version 92190 (0.0010) -[2023-10-17 03:58:52,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 189497344. Throughput: 0: 1762.7, 1: 1774.7. Samples: 47378882. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-17 03:58:52,215][61453] Avg episode reward: [(0, '10.480'), (1, '12.900')] -[2023-10-17 03:58:53,222][62373] Updated weights for policy 0, policy_version 92870 (0.0008) -[2023-10-17 03:58:53,601][62373] Updated weights for policy 0, policy_version 92880 (0.0011) -[2023-10-17 03:58:53,973][62373] Updated weights for policy 0, policy_version 92890 (0.0009) -[2023-10-17 03:58:54,389][62408] Updated weights for policy 1, policy_version 92200 (0.0008) -[2023-10-17 03:58:54,757][62408] Updated weights for policy 1, policy_version 92210 (0.0009) -[2023-10-17 03:58:55,130][62408] Updated weights for policy 1, policy_version 92220 (0.0009) -[2023-10-17 03:58:57,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 189562880. Throughput: 0: 1770.1, 1: 1757.5. Samples: 47400124. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-17 03:58:57,215][61453] Avg episode reward: [(0, '11.120'), (1, '12.940')] -[2023-10-17 03:58:57,217][62252] Saving new best policy, reward=12.940! -[2023-10-17 03:58:57,668][62373] Updated weights for policy 0, policy_version 92900 (0.0008) -[2023-10-17 03:58:58,037][62373] Updated weights for policy 0, policy_version 92910 (0.0010) -[2023-10-17 03:58:58,399][62373] Updated weights for policy 0, policy_version 92920 (0.0008) -[2023-10-17 03:58:59,085][62408] Updated weights for policy 1, policy_version 92230 (0.0009) -[2023-10-17 03:58:59,446][62408] Updated weights for policy 1, policy_version 92240 (0.0008) -[2023-10-17 03:58:59,824][62408] Updated weights for policy 1, policy_version 92250 (0.0010) -[2023-10-17 03:59:02,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 189628416. Throughput: 0: 1797.1, 1: 1750.6. Samples: 47422328. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-17 03:59:02,215][61453] Avg episode reward: [(0, '11.400'), (1, '12.320')] -[2023-10-17 03:59:02,246][62373] Updated weights for policy 0, policy_version 92930 (0.0009) -[2023-10-17 03:59:02,622][62373] Updated weights for policy 0, policy_version 92940 (0.0011) -[2023-10-17 03:59:02,984][62373] Updated weights for policy 0, policy_version 92950 (0.0008) -[2023-10-17 03:59:03,352][62373] Updated weights for policy 0, policy_version 92960 (0.0007) -[2023-10-17 03:59:03,387][62408] Updated weights for policy 1, policy_version 92260 (0.0008) -[2023-10-17 03:59:03,762][62408] Updated weights for policy 1, policy_version 92270 (0.0009) -[2023-10-17 03:59:04,139][62408] Updated weights for policy 1, policy_version 92280 (0.0010) -[2023-10-17 03:59:07,112][62373] Updated weights for policy 0, policy_version 92970 (0.0008) -[2023-10-17 03:59:07,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 189693952. Throughput: 0: 1775.0, 1: 1753.4. Samples: 47432068. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-17 03:59:07,215][61453] Avg episode reward: [(0, '11.330'), (1, '12.620')] -[2023-10-17 03:59:07,485][62373] Updated weights for policy 0, policy_version 92980 (0.0007) -[2023-10-17 03:59:07,850][62373] Updated weights for policy 0, policy_version 92990 (0.0007) -[2023-10-17 03:59:08,121][62408] Updated weights for policy 1, policy_version 92290 (0.0010) -[2023-10-17 03:59:08,494][62408] Updated weights for policy 1, policy_version 92300 (0.0008) -[2023-10-17 03:59:08,860][62408] Updated weights for policy 1, policy_version 92310 (0.0008) -[2023-10-17 03:59:09,228][62408] Updated weights for policy 1, policy_version 92320 (0.0010) -[2023-10-17 03:59:11,758][62373] Updated weights for policy 0, policy_version 93000 (0.0008) -[2023-10-17 03:59:12,128][62373] Updated weights for policy 0, policy_version 93010 (0.0007) -[2023-10-17 03:59:12,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 189759488. Throughput: 0: 1788.3, 1: 1752.2. Samples: 47454024. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-17 03:59:12,215][61453] Avg episode reward: [(0, '11.520'), (1, '13.220')] -[2023-10-17 03:59:12,216][62252] Saving new best policy, reward=13.220! -[2023-10-17 03:59:12,489][62373] Updated weights for policy 0, policy_version 93020 (0.0008) -[2023-10-17 03:59:12,927][62408] Updated weights for policy 1, policy_version 92330 (0.0010) -[2023-10-17 03:59:13,299][62408] Updated weights for policy 1, policy_version 92340 (0.0008) -[2023-10-17 03:59:13,666][62408] Updated weights for policy 1, policy_version 92350 (0.0009) -[2023-10-17 03:59:16,359][62373] Updated weights for policy 0, policy_version 93030 (0.0009) -[2023-10-17 03:59:16,722][62373] Updated weights for policy 0, policy_version 93040 (0.0007) -[2023-10-17 03:59:17,087][62373] Updated weights for policy 0, policy_version 93050 (0.0008) -[2023-10-17 03:59:17,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 189825024. Throughput: 0: 1774.2, 1: 1776.9. Samples: 47474748. Policy #0 lag: (min: 14.0, avg: 14.0, max: 14.0) -[2023-10-17 03:59:17,215][61453] Avg episode reward: [(0, '11.600'), (1, '12.630')] -[2023-10-17 03:59:17,600][62408] Updated weights for policy 1, policy_version 92360 (0.0010) -[2023-10-17 03:59:17,974][62408] Updated weights for policy 1, policy_version 92370 (0.0007) -[2023-10-17 03:59:18,344][62408] Updated weights for policy 1, policy_version 92380 (0.0008) -[2023-10-17 03:59:20,849][62373] Updated weights for policy 0, policy_version 93060 (0.0009) -[2023-10-17 03:59:21,216][62373] Updated weights for policy 0, policy_version 93070 (0.0009) -[2023-10-17 03:59:21,576][62373] Updated weights for policy 0, policy_version 93080 (0.0010) -[2023-10-17 03:59:22,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 189923328. Throughput: 0: 1777.5, 1: 1749.9. Samples: 47485420. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-17 03:59:22,215][61453] Avg episode reward: [(0, '11.300'), (1, '12.340')] -[2023-10-17 03:59:22,286][62408] Updated weights for policy 1, policy_version 92390 (0.0009) -[2023-10-17 03:59:22,655][62408] Updated weights for policy 1, policy_version 92400 (0.0008) -[2023-10-17 03:59:23,022][62408] Updated weights for policy 1, policy_version 92410 (0.0007) -[2023-10-17 03:59:25,435][62373] Updated weights for policy 0, policy_version 93090 (0.0009) -[2023-10-17 03:59:25,822][62373] Updated weights for policy 0, policy_version 93100 (0.0010) -[2023-10-17 03:59:26,192][62373] Updated weights for policy 0, policy_version 93110 (0.0009) -[2023-10-17 03:59:26,557][62373] Updated weights for policy 0, policy_version 93120 (0.0007) -[2023-10-17 03:59:26,986][62408] Updated weights for policy 1, policy_version 92420 (0.0008) -[2023-10-17 03:59:27,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 189988864. Throughput: 0: 1781.3, 1: 1767.4. Samples: 47506670. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-17 03:59:27,215][61453] Avg episode reward: [(0, '11.410'), (1, '12.160')] -[2023-10-17 03:59:27,354][62408] Updated weights for policy 1, policy_version 92430 (0.0011) -[2023-10-17 03:59:27,722][62408] Updated weights for policy 1, policy_version 92440 (0.0011) -[2023-10-17 03:59:30,233][62373] Updated weights for policy 0, policy_version 93130 (0.0007) -[2023-10-17 03:59:30,612][62373] Updated weights for policy 0, policy_version 93140 (0.0008) -[2023-10-17 03:59:30,977][62373] Updated weights for policy 0, policy_version 93150 (0.0009) -[2023-10-17 03:59:31,387][62408] Updated weights for policy 1, policy_version 92450 (0.0008) -[2023-10-17 03:59:31,755][62408] Updated weights for policy 1, policy_version 92460 (0.0007) -[2023-10-17 03:59:32,131][62408] Updated weights for policy 1, policy_version 92470 (0.0007) -[2023-10-17 03:59:32,214][61453] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 190054400. Throughput: 0: 1766.2, 1: 1771.1. Samples: 47527660. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-17 03:59:32,215][61453] Avg episode reward: [(0, '11.930'), (1, '11.480')] -[2023-10-17 03:59:32,222][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000093152_95387648.pth... -[2023-10-17 03:59:32,252][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000091488_93683712.pth -[2023-10-17 03:59:32,495][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000092480_94699520.pth... -[2023-10-17 03:59:32,497][62408] Updated weights for policy 1, policy_version 92480 (0.0008) -[2023-10-17 03:59:32,533][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000090816_92995584.pth -[2023-10-17 03:59:34,697][62373] Updated weights for policy 0, policy_version 93160 (0.0007) -[2023-10-17 03:59:35,063][62373] Updated weights for policy 0, policy_version 93170 (0.0008) -[2023-10-17 03:59:35,431][62373] Updated weights for policy 0, policy_version 93180 (0.0007) -[2023-10-17 03:59:36,241][62408] Updated weights for policy 1, policy_version 92490 (0.0008) -[2023-10-17 03:59:36,605][62408] Updated weights for policy 1, policy_version 92500 (0.0008) -[2023-10-17 03:59:36,979][62408] Updated weights for policy 1, policy_version 92510 (0.0009) -[2023-10-17 03:59:37,214][61453] Fps is (10 sec: 16384.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 190152704. Throughput: 0: 1794.8, 1: 1760.9. Samples: 47538888. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-17 03:59:37,214][61453] Avg episode reward: [(0, '12.030'), (1, '11.100')] -[2023-10-17 03:59:39,220][62373] Updated weights for policy 0, policy_version 93190 (0.0010) -[2023-10-17 03:59:39,595][62373] Updated weights for policy 0, policy_version 93200 (0.0010) -[2023-10-17 03:59:39,960][62373] Updated weights for policy 0, policy_version 93210 (0.0010) -[2023-10-17 03:59:40,764][62408] Updated weights for policy 1, policy_version 92520 (0.0009) -[2023-10-17 03:59:41,133][62408] Updated weights for policy 1, policy_version 92530 (0.0007) -[2023-10-17 03:59:41,502][62408] Updated weights for policy 1, policy_version 92540 (0.0010) -[2023-10-17 03:59:42,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 190218240. Throughput: 0: 1774.7, 1: 1774.8. Samples: 47559852. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-17 03:59:42,215][61453] Avg episode reward: [(0, '11.010'), (1, '11.070')] -[2023-10-17 03:59:43,678][62373] Updated weights for policy 0, policy_version 93220 (0.0007) -[2023-10-17 03:59:44,054][62373] Updated weights for policy 0, policy_version 93230 (0.0008) -[2023-10-17 03:59:44,430][62373] Updated weights for policy 0, policy_version 93240 (0.0007) -[2023-10-17 03:59:45,302][62408] Updated weights for policy 1, policy_version 92550 (0.0009) -[2023-10-17 03:59:45,671][62408] Updated weights for policy 1, policy_version 92560 (0.0011) -[2023-10-17 03:59:46,038][62408] Updated weights for policy 1, policy_version 92570 (0.0009) -[2023-10-17 03:59:47,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 190283776. Throughput: 0: 1764.2, 1: 1757.5. Samples: 47580802. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-17 03:59:47,214][61453] Avg episode reward: [(0, '11.720'), (1, '10.600')] -[2023-10-17 03:59:48,414][62373] Updated weights for policy 0, policy_version 93250 (0.0008) -[2023-10-17 03:59:48,818][62373] Updated weights for policy 0, policy_version 93260 (0.0009) -[2023-10-17 03:59:49,185][62373] Updated weights for policy 0, policy_version 93270 (0.0008) -[2023-10-17 03:59:49,562][62373] Updated weights for policy 0, policy_version 93280 (0.0008) -[2023-10-17 03:59:49,876][62408] Updated weights for policy 1, policy_version 92580 (0.0008) -[2023-10-17 03:59:50,251][62408] Updated weights for policy 1, policy_version 92590 (0.0008) -[2023-10-17 03:59:50,622][62408] Updated weights for policy 1, policy_version 92600 (0.0009) -[2023-10-17 03:59:52,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 190349312. Throughput: 0: 1757.2, 1: 1787.4. Samples: 47591574. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-17 03:59:52,215][61453] Avg episode reward: [(0, '11.890'), (1, '10.220')] -[2023-10-17 03:59:53,391][62373] Updated weights for policy 0, policy_version 93290 (0.0009) -[2023-10-17 03:59:53,760][62373] Updated weights for policy 0, policy_version 93300 (0.0011) -[2023-10-17 03:59:54,128][62373] Updated weights for policy 0, policy_version 93310 (0.0010) -[2023-10-17 03:59:54,367][62408] Updated weights for policy 1, policy_version 92610 (0.0007) -[2023-10-17 03:59:54,735][62408] Updated weights for policy 1, policy_version 92620 (0.0009) -[2023-10-17 03:59:55,102][62408] Updated weights for policy 1, policy_version 92630 (0.0009) -[2023-10-17 03:59:55,465][62408] Updated weights for policy 1, policy_version 92640 (0.0009) -[2023-10-17 03:59:57,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 190414848. Throughput: 0: 1763.7, 1: 1758.9. Samples: 47612542. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-17 03:59:57,215][61453] Avg episode reward: [(0, '11.820'), (1, '10.890')] -[2023-10-17 03:59:57,885][62373] Updated weights for policy 0, policy_version 93320 (0.0010) -[2023-10-17 03:59:58,249][62373] Updated weights for policy 0, policy_version 93330 (0.0009) -[2023-10-17 03:59:58,616][62373] Updated weights for policy 0, policy_version 93340 (0.0009) -[2023-10-17 03:59:59,183][62408] Updated weights for policy 1, policy_version 92650 (0.0010) -[2023-10-17 03:59:59,545][62408] Updated weights for policy 1, policy_version 92660 (0.0007) -[2023-10-17 03:59:59,921][62408] Updated weights for policy 1, policy_version 92670 (0.0011) -[2023-10-17 04:00:02,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 190480384. Throughput: 0: 1789.7, 1: 1769.3. Samples: 47634902. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-17 04:00:02,215][61453] Avg episode reward: [(0, '11.990'), (1, '10.010')] -[2023-10-17 04:00:02,400][62373] Updated weights for policy 0, policy_version 93350 (0.0010) -[2023-10-17 04:00:02,769][62373] Updated weights for policy 0, policy_version 93360 (0.0009) -[2023-10-17 04:00:03,143][62373] Updated weights for policy 0, policy_version 93370 (0.0009) -[2023-10-17 04:00:03,680][62408] Updated weights for policy 1, policy_version 92680 (0.0008) -[2023-10-17 04:00:04,052][62408] Updated weights for policy 1, policy_version 92690 (0.0007) -[2023-10-17 04:00:04,416][62408] Updated weights for policy 1, policy_version 92700 (0.0007) -[2023-10-17 04:00:07,141][62373] Updated weights for policy 0, policy_version 93380 (0.0007) -[2023-10-17 04:00:07,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 190545920. Throughput: 0: 1764.8, 1: 1770.2. Samples: 47644494. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-17 04:00:07,215][61453] Avg episode reward: [(0, '10.770'), (1, '10.490')] -[2023-10-17 04:00:07,510][62373] Updated weights for policy 0, policy_version 93390 (0.0007) -[2023-10-17 04:00:07,874][62373] Updated weights for policy 0, policy_version 93400 (0.0008) -[2023-10-17 04:00:08,250][62408] Updated weights for policy 1, policy_version 92710 (0.0008) -[2023-10-17 04:00:08,610][62408] Updated weights for policy 1, policy_version 92720 (0.0010) -[2023-10-17 04:00:08,980][62408] Updated weights for policy 1, policy_version 92730 (0.0008) -[2023-10-17 04:00:11,678][62373] Updated weights for policy 0, policy_version 93410 (0.0008) -[2023-10-17 04:00:12,048][62373] Updated weights for policy 0, policy_version 93420 (0.0009) -[2023-10-17 04:00:12,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 190611456. Throughput: 0: 1779.3, 1: 1770.5. Samples: 47666410. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-17 04:00:12,215][61453] Avg episode reward: [(0, '10.430'), (1, '10.660')] -[2023-10-17 04:00:12,422][62373] Updated weights for policy 0, policy_version 93430 (0.0008) -[2023-10-17 04:00:12,736][62408] Updated weights for policy 1, policy_version 92740 (0.0009) -[2023-10-17 04:00:12,788][62373] Updated weights for policy 0, policy_version 93440 (0.0008) -[2023-10-17 04:00:13,105][62408] Updated weights for policy 1, policy_version 92750 (0.0011) -[2023-10-17 04:00:13,474][62408] Updated weights for policy 1, policy_version 92760 (0.0009) -[2023-10-17 04:00:16,764][62373] Updated weights for policy 0, policy_version 93450 (0.0009) -[2023-10-17 04:00:17,136][62373] Updated weights for policy 0, policy_version 93460 (0.0009) -[2023-10-17 04:00:17,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 190676992. Throughput: 0: 1770.2, 1: 1770.5. Samples: 47686988. Policy #0 lag: (min: 12.0, avg: 12.0, max: 12.0) -[2023-10-17 04:00:17,214][61453] Avg episode reward: [(0, '10.700'), (1, '10.680')] -[2023-10-17 04:00:17,495][62373] Updated weights for policy 0, policy_version 93470 (0.0007) -[2023-10-17 04:00:17,498][62408] Updated weights for policy 1, policy_version 92770 (0.0011) -[2023-10-17 04:00:17,873][62408] Updated weights for policy 1, policy_version 92780 (0.0009) -[2023-10-17 04:00:18,242][62408] Updated weights for policy 1, policy_version 92790 (0.0009) -[2023-10-17 04:00:18,608][62408] Updated weights for policy 1, policy_version 92800 (0.0009) -[2023-10-17 04:00:21,189][62373] Updated weights for policy 0, policy_version 93480 (0.0009) -[2023-10-17 04:00:21,553][62373] Updated weights for policy 0, policy_version 93490 (0.0009) -[2023-10-17 04:00:21,925][62373] Updated weights for policy 0, policy_version 93500 (0.0008) -[2023-10-17 04:00:22,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 190775296. Throughput: 0: 1764.1, 1: 1759.2. Samples: 47697436. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 04:00:22,215][61453] Avg episode reward: [(0, '11.550'), (1, '10.850')] -[2023-10-17 04:00:22,529][62408] Updated weights for policy 1, policy_version 92810 (0.0008) -[2023-10-17 04:00:22,911][62408] Updated weights for policy 1, policy_version 92820 (0.0009) -[2023-10-17 04:00:23,277][62408] Updated weights for policy 1, policy_version 92830 (0.0009) -[2023-10-17 04:00:25,626][62373] Updated weights for policy 0, policy_version 93510 (0.0008) -[2023-10-17 04:00:26,002][62373] Updated weights for policy 0, policy_version 93520 (0.0009) -[2023-10-17 04:00:26,365][62373] Updated weights for policy 0, policy_version 93530 (0.0009) -[2023-10-17 04:00:27,178][62408] Updated weights for policy 1, policy_version 92840 (0.0010) -[2023-10-17 04:00:27,214][61453] Fps is (10 sec: 16383.6, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 190840832. Throughput: 0: 1771.8, 1: 1764.9. Samples: 47719006. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 04:00:27,215][61453] Avg episode reward: [(0, '11.340'), (1, '11.430')] -[2023-10-17 04:00:27,546][62408] Updated weights for policy 1, policy_version 92850 (0.0010) -[2023-10-17 04:00:27,925][62408] Updated weights for policy 1, policy_version 92860 (0.0008) -[2023-10-17 04:00:30,069][62373] Updated weights for policy 0, policy_version 93540 (0.0009) -[2023-10-17 04:00:30,434][62373] Updated weights for policy 0, policy_version 93550 (0.0010) -[2023-10-17 04:00:30,798][62373] Updated weights for policy 0, policy_version 93560 (0.0010) -[2023-10-17 04:00:31,901][62408] Updated weights for policy 1, policy_version 92870 (0.0009) -[2023-10-17 04:00:32,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 190906368. Throughput: 0: 1761.8, 1: 1781.6. Samples: 47740254. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 04:00:32,215][61453] Avg episode reward: [(0, '10.720'), (1, '11.560')] -[2023-10-17 04:00:32,263][62408] Updated weights for policy 1, policy_version 92880 (0.0009) -[2023-10-17 04:00:32,634][62408] Updated weights for policy 1, policy_version 92890 (0.0007) -[2023-10-17 04:00:34,623][62373] Updated weights for policy 0, policy_version 93570 (0.0010) -[2023-10-17 04:00:35,024][62373] Updated weights for policy 0, policy_version 93580 (0.0008) -[2023-10-17 04:00:35,397][62373] Updated weights for policy 0, policy_version 93590 (0.0008) -[2023-10-17 04:00:35,759][62373] Updated weights for policy 0, policy_version 93600 (0.0010) -[2023-10-17 04:00:36,435][62408] Updated weights for policy 1, policy_version 92900 (0.0008) -[2023-10-17 04:00:36,801][62408] Updated weights for policy 1, policy_version 92910 (0.0009) -[2023-10-17 04:00:37,173][62408] Updated weights for policy 1, policy_version 92920 (0.0012) -[2023-10-17 04:00:37,214][61453] Fps is (10 sec: 13107.5, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 190971904. Throughput: 0: 1790.8, 1: 1752.4. Samples: 47751014. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 04:00:37,214][61453] Avg episode reward: [(0, '10.830'), (1, '11.700')] -[2023-10-17 04:00:39,666][62373] Updated weights for policy 0, policy_version 93610 (0.0008) -[2023-10-17 04:00:40,037][62373] Updated weights for policy 0, policy_version 93620 (0.0008) -[2023-10-17 04:00:40,409][62373] Updated weights for policy 0, policy_version 93630 (0.0007) -[2023-10-17 04:00:41,054][62408] Updated weights for policy 1, policy_version 92930 (0.0010) -[2023-10-17 04:00:41,414][62408] Updated weights for policy 1, policy_version 92940 (0.0010) -[2023-10-17 04:00:41,791][62408] Updated weights for policy 1, policy_version 92950 (0.0008) -[2023-10-17 04:00:42,163][62408] Updated weights for policy 1, policy_version 92960 (0.0007) -[2023-10-17 04:00:42,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 191070208. Throughput: 0: 1759.6, 1: 1780.4. Samples: 47771846. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 04:00:42,215][61453] Avg episode reward: [(0, '11.000'), (1, '12.150')] -[2023-10-17 04:00:44,235][62373] Updated weights for policy 0, policy_version 93640 (0.0010) -[2023-10-17 04:00:44,623][62373] Updated weights for policy 0, policy_version 93650 (0.0010) -[2023-10-17 04:00:44,989][62373] Updated weights for policy 0, policy_version 93660 (0.0009) -[2023-10-17 04:00:45,774][62408] Updated weights for policy 1, policy_version 92970 (0.0011) -[2023-10-17 04:00:46,153][62408] Updated weights for policy 1, policy_version 92980 (0.0011) -[2023-10-17 04:00:46,519][62408] Updated weights for policy 1, policy_version 92990 (0.0009) -[2023-10-17 04:00:47,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 191135744. Throughput: 0: 1760.3, 1: 1743.7. Samples: 47792582. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 04:00:47,215][61453] Avg episode reward: [(0, '11.490'), (1, '12.530')] -[2023-10-17 04:00:48,901][62373] Updated weights for policy 0, policy_version 93670 (0.0009) -[2023-10-17 04:00:49,275][62373] Updated weights for policy 0, policy_version 93680 (0.0008) -[2023-10-17 04:00:49,637][62373] Updated weights for policy 0, policy_version 93690 (0.0007) -[2023-10-17 04:00:50,258][62408] Updated weights for policy 1, policy_version 93000 (0.0007) -[2023-10-17 04:00:50,626][62408] Updated weights for policy 1, policy_version 93010 (0.0010) -[2023-10-17 04:00:50,996][62408] Updated weights for policy 1, policy_version 93020 (0.0009) -[2023-10-17 04:00:52,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 191201280. Throughput: 0: 1761.0, 1: 1776.7. Samples: 47803692. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 04:00:52,215][61453] Avg episode reward: [(0, '12.050'), (1, '12.020')] -[2023-10-17 04:00:53,364][62373] Updated weights for policy 0, policy_version 93700 (0.0007) -[2023-10-17 04:00:53,726][62373] Updated weights for policy 0, policy_version 93710 (0.0008) -[2023-10-17 04:00:54,097][62373] Updated weights for policy 0, policy_version 93720 (0.0008) -[2023-10-17 04:00:54,837][62408] Updated weights for policy 1, policy_version 93030 (0.0009) -[2023-10-17 04:00:55,224][62408] Updated weights for policy 1, policy_version 93040 (0.0008) -[2023-10-17 04:00:55,587][62408] Updated weights for policy 1, policy_version 93050 (0.0009) -[2023-10-17 04:00:57,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 191266816. Throughput: 0: 1771.7, 1: 1749.8. Samples: 47824878. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 04:00:57,214][61453] Avg episode reward: [(0, '10.460'), (1, '12.260')] -[2023-10-17 04:00:57,727][62373] Updated weights for policy 0, policy_version 93730 (0.0008) -[2023-10-17 04:00:58,095][62373] Updated weights for policy 0, policy_version 93740 (0.0009) -[2023-10-17 04:00:58,458][62373] Updated weights for policy 0, policy_version 93750 (0.0008) -[2023-10-17 04:00:58,826][62373] Updated weights for policy 0, policy_version 93760 (0.0008) -[2023-10-17 04:00:59,337][62408] Updated weights for policy 1, policy_version 93060 (0.0008) -[2023-10-17 04:00:59,710][62408] Updated weights for policy 1, policy_version 93070 (0.0007) -[2023-10-17 04:01:00,072][62408] Updated weights for policy 1, policy_version 93080 (0.0010) -[2023-10-17 04:01:02,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 191332352. Throughput: 0: 1798.0, 1: 1760.2. Samples: 47847106. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 04:01:02,214][61453] Avg episode reward: [(0, '11.330'), (1, '12.110')] -[2023-10-17 04:01:02,607][62373] Updated weights for policy 0, policy_version 93770 (0.0008) -[2023-10-17 04:01:02,977][62373] Updated weights for policy 0, policy_version 93780 (0.0011) -[2023-10-17 04:01:03,340][62373] Updated weights for policy 0, policy_version 93790 (0.0009) -[2023-10-17 04:01:03,916][62408] Updated weights for policy 1, policy_version 93090 (0.0007) -[2023-10-17 04:01:04,283][62408] Updated weights for policy 1, policy_version 93100 (0.0010) -[2023-10-17 04:01:04,647][62408] Updated weights for policy 1, policy_version 93110 (0.0011) -[2023-10-17 04:01:05,009][62408] Updated weights for policy 1, policy_version 93120 (0.0011) -[2023-10-17 04:01:06,992][62373] Updated weights for policy 0, policy_version 93800 (0.0012) -[2023-10-17 04:01:07,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 191397888. Throughput: 0: 1781.6, 1: 1763.5. Samples: 47856964. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 04:01:07,215][61453] Avg episode reward: [(0, '11.360'), (1, '12.280')] -[2023-10-17 04:01:07,364][62373] Updated weights for policy 0, policy_version 93810 (0.0010) -[2023-10-17 04:01:07,740][62373] Updated weights for policy 0, policy_version 93820 (0.0010) -[2023-10-17 04:01:09,134][62408] Updated weights for policy 1, policy_version 93130 (0.0008) -[2023-10-17 04:01:09,512][62408] Updated weights for policy 1, policy_version 93140 (0.0008) -[2023-10-17 04:01:09,882][62408] Updated weights for policy 1, policy_version 93150 (0.0008) -[2023-10-17 04:01:11,720][62373] Updated weights for policy 0, policy_version 93830 (0.0009) -[2023-10-17 04:01:12,083][62373] Updated weights for policy 0, policy_version 93840 (0.0008) -[2023-10-17 04:01:12,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 191463424. Throughput: 0: 1789.3, 1: 1755.2. Samples: 47878504. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 04:01:12,215][61453] Avg episode reward: [(0, '11.180'), (1, '11.490')] -[2023-10-17 04:01:12,462][62373] Updated weights for policy 0, policy_version 93850 (0.0008) -[2023-10-17 04:01:13,567][62408] Updated weights for policy 1, policy_version 93160 (0.0008) -[2023-10-17 04:01:13,937][62408] Updated weights for policy 1, policy_version 93170 (0.0008) -[2023-10-17 04:01:14,292][62408] Updated weights for policy 1, policy_version 93180 (0.0009) -[2023-10-17 04:01:16,150][62373] Updated weights for policy 0, policy_version 93860 (0.0008) -[2023-10-17 04:01:16,523][62373] Updated weights for policy 0, policy_version 93870 (0.0008) -[2023-10-17 04:01:16,896][62373] Updated weights for policy 0, policy_version 93880 (0.0008) -[2023-10-17 04:01:17,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14745.5, 300 sec: 14218.0). Total num frames: 191561728. Throughput: 0: 1781.0, 1: 1764.8. Samples: 47899812. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 04:01:17,215][61453] Avg episode reward: [(0, '11.420'), (1, '10.930')] -[2023-10-17 04:01:18,178][62408] Updated weights for policy 1, policy_version 93190 (0.0009) -[2023-10-17 04:01:18,558][62408] Updated weights for policy 1, policy_version 93200 (0.0010) -[2023-10-17 04:01:18,928][62408] Updated weights for policy 1, policy_version 93210 (0.0010) -[2023-10-17 04:01:20,573][62373] Updated weights for policy 0, policy_version 93890 (0.0010) -[2023-10-17 04:01:20,975][62373] Updated weights for policy 0, policy_version 93900 (0.0007) -[2023-10-17 04:01:21,343][62373] Updated weights for policy 0, policy_version 93910 (0.0007) -[2023-10-17 04:01:21,717][62373] Updated weights for policy 0, policy_version 93920 (0.0007) -[2023-10-17 04:01:22,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 191627264. Throughput: 0: 1784.3, 1: 1759.0. Samples: 47910462. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 04:01:22,215][61453] Avg episode reward: [(0, '10.980'), (1, '10.590')] -[2023-10-17 04:01:22,735][62408] Updated weights for policy 1, policy_version 93220 (0.0011) -[2023-10-17 04:01:23,100][62408] Updated weights for policy 1, policy_version 93230 (0.0010) -[2023-10-17 04:01:23,481][62408] Updated weights for policy 1, policy_version 93240 (0.0010) -[2023-10-17 04:01:25,369][62373] Updated weights for policy 0, policy_version 93930 (0.0010) -[2023-10-17 04:01:25,734][62373] Updated weights for policy 0, policy_version 93940 (0.0008) -[2023-10-17 04:01:26,101][62373] Updated weights for policy 0, policy_version 93950 (0.0008) -[2023-10-17 04:01:27,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 191692800. Throughput: 0: 1790.7, 1: 1758.9. Samples: 47931574. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 04:01:27,216][61453] Avg episode reward: [(0, '11.120'), (1, '10.570')] -[2023-10-17 04:01:27,350][62408] Updated weights for policy 1, policy_version 93250 (0.0010) -[2023-10-17 04:01:27,724][62408] Updated weights for policy 1, policy_version 93260 (0.0010) -[2023-10-17 04:01:28,096][62408] Updated weights for policy 1, policy_version 93270 (0.0009) -[2023-10-17 04:01:28,462][62408] Updated weights for policy 1, policy_version 93280 (0.0007) -[2023-10-17 04:01:29,849][62373] Updated weights for policy 0, policy_version 93960 (0.0007) -[2023-10-17 04:01:30,220][62373] Updated weights for policy 0, policy_version 93970 (0.0010) -[2023-10-17 04:01:30,578][62373] Updated weights for policy 0, policy_version 93980 (0.0008) -[2023-10-17 04:01:32,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 191758336. Throughput: 0: 1781.4, 1: 1788.6. Samples: 47953230. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 04:01:32,215][61453] Avg episode reward: [(0, '11.360'), (1, '10.630')] -[2023-10-17 04:01:32,227][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000093984_96239616.pth... -[2023-10-17 04:01:32,229][62408] Updated weights for policy 1, policy_version 93290 (0.0008) -[2023-10-17 04:01:32,269][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000092320_94535680.pth -[2023-10-17 04:01:32,601][62408] Updated weights for policy 1, policy_version 93300 (0.0009) -[2023-10-17 04:01:32,968][62408] Updated weights for policy 1, policy_version 93310 (0.0008) -[2023-10-17 04:01:33,041][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000093312_95551488.pth... -[2023-10-17 04:01:33,079][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000091648_93847552.pth -[2023-10-17 04:01:34,553][62373] Updated weights for policy 0, policy_version 93990 (0.0009) -[2023-10-17 04:01:34,930][62373] Updated weights for policy 0, policy_version 94000 (0.0010) -[2023-10-17 04:01:35,295][62373] Updated weights for policy 0, policy_version 94010 (0.0008) -[2023-10-17 04:01:36,716][62408] Updated weights for policy 1, policy_version 93320 (0.0008) -[2023-10-17 04:01:37,077][62408] Updated weights for policy 1, policy_version 93330 (0.0009) -[2023-10-17 04:01:37,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 191823872. Throughput: 0: 1798.1, 1: 1755.4. Samples: 47963600. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 04:01:37,215][61453] Avg episode reward: [(0, '11.010'), (1, '11.050')] -[2023-10-17 04:01:37,445][62408] Updated weights for policy 1, policy_version 93340 (0.0011) -[2023-10-17 04:01:39,054][62373] Updated weights for policy 0, policy_version 94020 (0.0008) -[2023-10-17 04:01:39,430][62373] Updated weights for policy 0, policy_version 94030 (0.0012) -[2023-10-17 04:01:39,796][62373] Updated weights for policy 0, policy_version 94040 (0.0010) -[2023-10-17 04:01:41,414][62408] Updated weights for policy 1, policy_version 93350 (0.0012) -[2023-10-17 04:01:41,794][62408] Updated weights for policy 1, policy_version 93360 (0.0010) -[2023-10-17 04:01:42,158][62408] Updated weights for policy 1, policy_version 93370 (0.0010) -[2023-10-17 04:01:42,214][61453] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 191889408. Throughput: 0: 1774.9, 1: 1787.0. Samples: 47985164. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 04:01:42,215][61453] Avg episode reward: [(0, '11.470'), (1, '11.030')] -[2023-10-17 04:01:43,614][62373] Updated weights for policy 0, policy_version 94050 (0.0009) -[2023-10-17 04:01:43,989][62373] Updated weights for policy 0, policy_version 94060 (0.0008) -[2023-10-17 04:01:44,358][62373] Updated weights for policy 0, policy_version 94070 (0.0007) -[2023-10-17 04:01:44,722][62373] Updated weights for policy 0, policy_version 94080 (0.0008) -[2023-10-17 04:01:45,947][62408] Updated weights for policy 1, policy_version 93380 (0.0009) -[2023-10-17 04:01:46,310][62408] Updated weights for policy 1, policy_version 93390 (0.0008) -[2023-10-17 04:01:46,676][62408] Updated weights for policy 1, policy_version 93400 (0.0007) -[2023-10-17 04:01:47,214][61453] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 191987712. Throughput: 0: 1775.5, 1: 1759.9. Samples: 48006198. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 04:01:47,214][61453] Avg episode reward: [(0, '11.140'), (1, '10.960')] -[2023-10-17 04:01:48,531][62373] Updated weights for policy 0, policy_version 94090 (0.0011) -[2023-10-17 04:01:48,894][62373] Updated weights for policy 0, policy_version 94100 (0.0010) -[2023-10-17 04:01:49,275][62373] Updated weights for policy 0, policy_version 94110 (0.0009) -[2023-10-17 04:01:50,411][62408] Updated weights for policy 1, policy_version 93410 (0.0009) -[2023-10-17 04:01:50,785][62408] Updated weights for policy 1, policy_version 93420 (0.0009) -[2023-10-17 04:01:51,146][62408] Updated weights for policy 1, policy_version 93430 (0.0007) -[2023-10-17 04:01:51,513][62408] Updated weights for policy 1, policy_version 93440 (0.0010) -[2023-10-17 04:01:52,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 192053248. Throughput: 0: 1773.2, 1: 1782.0. Samples: 48016946. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 04:01:52,215][61453] Avg episode reward: [(0, '11.360'), (1, '11.620')] -[2023-10-17 04:01:52,983][62373] Updated weights for policy 0, policy_version 94120 (0.0009) -[2023-10-17 04:01:53,364][62373] Updated weights for policy 0, policy_version 94130 (0.0008) -[2023-10-17 04:01:53,721][62373] Updated weights for policy 0, policy_version 94140 (0.0009) -[2023-10-17 04:01:55,335][62408] Updated weights for policy 1, policy_version 93450 (0.0009) -[2023-10-17 04:01:55,702][62408] Updated weights for policy 1, policy_version 93460 (0.0008) -[2023-10-17 04:01:56,063][62408] Updated weights for policy 1, policy_version 93470 (0.0010) -[2023-10-17 04:01:57,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 192118784. Throughput: 0: 1775.8, 1: 1774.5. Samples: 48038268. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 04:01:57,215][61453] Avg episode reward: [(0, '11.780'), (1, '10.970')] -[2023-10-17 04:01:57,647][62373] Updated weights for policy 0, policy_version 94150 (0.0008) -[2023-10-17 04:01:58,026][62373] Updated weights for policy 0, policy_version 94160 (0.0007) -[2023-10-17 04:01:58,391][62373] Updated weights for policy 0, policy_version 94170 (0.0007) -[2023-10-17 04:01:59,982][62408] Updated weights for policy 1, policy_version 93480 (0.0011) -[2023-10-17 04:02:00,359][62408] Updated weights for policy 1, policy_version 93490 (0.0011) -[2023-10-17 04:02:00,723][62408] Updated weights for policy 1, policy_version 93500 (0.0011) -[2023-10-17 04:02:02,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 192184320. Throughput: 0: 1794.4, 1: 1755.3. Samples: 48059548. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 04:02:02,215][61453] Avg episode reward: [(0, '12.010'), (1, '11.260')] -[2023-10-17 04:02:02,319][62373] Updated weights for policy 0, policy_version 94180 (0.0009) -[2023-10-17 04:02:02,685][62373] Updated weights for policy 0, policy_version 94190 (0.0007) -[2023-10-17 04:02:03,060][62373] Updated weights for policy 0, policy_version 94200 (0.0008) -[2023-10-17 04:02:04,601][62408] Updated weights for policy 1, policy_version 93510 (0.0011) -[2023-10-17 04:02:04,973][62408] Updated weights for policy 1, policy_version 93520 (0.0008) -[2023-10-17 04:02:05,340][62408] Updated weights for policy 1, policy_version 93530 (0.0007) -[2023-10-17 04:02:06,874][62373] Updated weights for policy 0, policy_version 94210 (0.0008) -[2023-10-17 04:02:07,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 192249856. Throughput: 0: 1768.1, 1: 1776.7. Samples: 48069976. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 04:02:07,215][61453] Avg episode reward: [(0, '11.990'), (1, '12.010')] -[2023-10-17 04:02:07,279][62373] Updated weights for policy 0, policy_version 94220 (0.0009) -[2023-10-17 04:02:07,650][62373] Updated weights for policy 0, policy_version 94230 (0.0009) -[2023-10-17 04:02:08,014][62373] Updated weights for policy 0, policy_version 94240 (0.0008) -[2023-10-17 04:02:09,108][62408] Updated weights for policy 1, policy_version 93540 (0.0008) -[2023-10-17 04:02:09,469][62408] Updated weights for policy 1, policy_version 93550 (0.0007) -[2023-10-17 04:02:09,839][62408] Updated weights for policy 1, policy_version 93560 (0.0008) -[2023-10-17 04:02:11,680][62373] Updated weights for policy 0, policy_version 94250 (0.0010) -[2023-10-17 04:02:12,038][62373] Updated weights for policy 0, policy_version 94260 (0.0011) -[2023-10-17 04:02:12,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 192315392. Throughput: 0: 1790.3, 1: 1756.7. Samples: 48091190. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 04:02:12,214][61453] Avg episode reward: [(0, '11.840'), (1, '11.630')] -[2023-10-17 04:02:12,406][62373] Updated weights for policy 0, policy_version 94270 (0.0011) -[2023-10-17 04:02:13,468][62408] Updated weights for policy 1, policy_version 93570 (0.0009) -[2023-10-17 04:02:13,837][62408] Updated weights for policy 1, policy_version 93580 (0.0007) -[2023-10-17 04:02:14,202][62408] Updated weights for policy 1, policy_version 93590 (0.0007) -[2023-10-17 04:02:14,575][62408] Updated weights for policy 1, policy_version 93600 (0.0007) -[2023-10-17 04:02:16,105][62373] Updated weights for policy 0, policy_version 94280 (0.0009) -[2023-10-17 04:02:16,473][62373] Updated weights for policy 0, policy_version 94290 (0.0010) -[2023-10-17 04:02:16,839][62373] Updated weights for policy 0, policy_version 94300 (0.0009) -[2023-10-17 04:02:17,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 192413696. Throughput: 0: 1772.4, 1: 1761.9. Samples: 48112274. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 04:02:17,215][61453] Avg episode reward: [(0, '11.120'), (1, '11.780')] -[2023-10-17 04:02:18,480][62408] Updated weights for policy 1, policy_version 93610 (0.0009) -[2023-10-17 04:02:18,849][62408] Updated weights for policy 1, policy_version 93620 (0.0010) -[2023-10-17 04:02:19,225][62408] Updated weights for policy 1, policy_version 93630 (0.0010) -[2023-10-17 04:02:20,672][62373] Updated weights for policy 0, policy_version 94310 (0.0010) -[2023-10-17 04:02:21,041][62373] Updated weights for policy 0, policy_version 94320 (0.0010) -[2023-10-17 04:02:21,414][62373] Updated weights for policy 0, policy_version 94330 (0.0010) -[2023-10-17 04:02:22,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 192479232. Throughput: 0: 1783.0, 1: 1762.8. Samples: 48123162. Policy #0 lag: (min: 17.0, avg: 23.4, max: 49.0) -[2023-10-17 04:02:22,215][61453] Avg episode reward: [(0, '11.250'), (1, '11.250')] -[2023-10-17 04:02:23,066][62408] Updated weights for policy 1, policy_version 93640 (0.0010) -[2023-10-17 04:02:23,433][62408] Updated weights for policy 1, policy_version 93650 (0.0011) -[2023-10-17 04:02:23,806][62408] Updated weights for policy 1, policy_version 93660 (0.0010) -[2023-10-17 04:02:25,238][62373] Updated weights for policy 0, policy_version 94340 (0.0007) -[2023-10-17 04:02:25,611][62373] Updated weights for policy 0, policy_version 94350 (0.0009) -[2023-10-17 04:02:25,982][62373] Updated weights for policy 0, policy_version 94360 (0.0011) -[2023-10-17 04:02:27,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 192544768. Throughput: 0: 1774.7, 1: 1760.1. Samples: 48144232. Policy #0 lag: (min: 17.0, avg: 23.4, max: 49.0) -[2023-10-17 04:02:27,215][61453] Avg episode reward: [(0, '10.630'), (1, '11.030')] -[2023-10-17 04:02:27,616][62408] Updated weights for policy 1, policy_version 93670 (0.0010) -[2023-10-17 04:02:28,003][62408] Updated weights for policy 1, policy_version 93680 (0.0009) -[2023-10-17 04:02:28,363][62408] Updated weights for policy 1, policy_version 93690 (0.0007) -[2023-10-17 04:02:29,682][62373] Updated weights for policy 0, policy_version 94370 (0.0010) -[2023-10-17 04:02:30,053][62373] Updated weights for policy 0, policy_version 94380 (0.0009) -[2023-10-17 04:02:30,423][62373] Updated weights for policy 0, policy_version 94390 (0.0010) -[2023-10-17 04:02:30,784][62373] Updated weights for policy 0, policy_version 94400 (0.0008) -[2023-10-17 04:02:32,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 192610304. Throughput: 0: 1759.7, 1: 1784.7. Samples: 48165694. Policy #0 lag: (min: 17.0, avg: 23.4, max: 49.0) -[2023-10-17 04:02:32,215][61453] Avg episode reward: [(0, '10.340'), (1, '11.140')] -[2023-10-17 04:02:32,309][62408] Updated weights for policy 1, policy_version 93700 (0.0009) -[2023-10-17 04:02:32,667][62408] Updated weights for policy 1, policy_version 93710 (0.0007) -[2023-10-17 04:02:33,035][62408] Updated weights for policy 1, policy_version 93720 (0.0010) -[2023-10-17 04:02:34,581][62373] Updated weights for policy 0, policy_version 94410 (0.0010) -[2023-10-17 04:02:34,942][62373] Updated weights for policy 0, policy_version 94420 (0.0007) -[2023-10-17 04:02:35,313][62373] Updated weights for policy 0, policy_version 94430 (0.0008) -[2023-10-17 04:02:36,929][62408] Updated weights for policy 1, policy_version 93730 (0.0007) -[2023-10-17 04:02:37,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 192675840. Throughput: 0: 1777.6, 1: 1758.4. Samples: 48176064. Policy #0 lag: (min: 17.0, avg: 23.4, max: 49.0) -[2023-10-17 04:02:37,215][61453] Avg episode reward: [(0, '10.200'), (1, '10.950')] -[2023-10-17 04:02:37,302][62408] Updated weights for policy 1, policy_version 93740 (0.0008) -[2023-10-17 04:02:37,676][62408] Updated weights for policy 1, policy_version 93750 (0.0008) -[2023-10-17 04:02:38,042][62408] Updated weights for policy 1, policy_version 93760 (0.0008) -[2023-10-17 04:02:39,042][62373] Updated weights for policy 0, policy_version 94440 (0.0009) -[2023-10-17 04:02:39,414][62373] Updated weights for policy 0, policy_version 94450 (0.0009) -[2023-10-17 04:02:39,784][62373] Updated weights for policy 0, policy_version 94460 (0.0007) -[2023-10-17 04:02:41,802][62408] Updated weights for policy 1, policy_version 93770 (0.0007) -[2023-10-17 04:02:42,175][62408] Updated weights for policy 1, policy_version 93780 (0.0009) -[2023-10-17 04:02:42,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 192741376. Throughput: 0: 1762.9, 1: 1771.3. Samples: 48197306. Policy #0 lag: (min: 17.0, avg: 23.4, max: 49.0) -[2023-10-17 04:02:42,214][61453] Avg episode reward: [(0, '10.010'), (1, '10.310')] -[2023-10-17 04:02:42,543][62408] Updated weights for policy 1, policy_version 93790 (0.0008) -[2023-10-17 04:02:43,607][62373] Updated weights for policy 0, policy_version 94470 (0.0009) -[2023-10-17 04:02:43,970][62373] Updated weights for policy 0, policy_version 94480 (0.0011) -[2023-10-17 04:02:44,347][62373] Updated weights for policy 0, policy_version 94490 (0.0009) -[2023-10-17 04:02:46,488][62408] Updated weights for policy 1, policy_version 93800 (0.0009) -[2023-10-17 04:02:46,866][62408] Updated weights for policy 1, policy_version 93810 (0.0008) -[2023-10-17 04:02:47,214][61453] Fps is (10 sec: 13107.3, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 192806912. Throughput: 0: 1770.1, 1: 1765.0. Samples: 48218630. Policy #0 lag: (min: 17.0, avg: 23.4, max: 49.0) -[2023-10-17 04:02:47,214][61453] Avg episode reward: [(0, '9.660'), (1, '10.410')] -[2023-10-17 04:02:47,223][62408] Updated weights for policy 1, policy_version 93820 (0.0008) -[2023-10-17 04:02:48,295][62373] Updated weights for policy 0, policy_version 94500 (0.0010) -[2023-10-17 04:02:48,659][62373] Updated weights for policy 0, policy_version 94510 (0.0009) -[2023-10-17 04:02:49,030][62373] Updated weights for policy 0, policy_version 94520 (0.0009) -[2023-10-17 04:02:51,050][62408] Updated weights for policy 1, policy_version 93830 (0.0008) -[2023-10-17 04:02:51,419][62408] Updated weights for policy 1, policy_version 93840 (0.0008) -[2023-10-17 04:02:51,775][62408] Updated weights for policy 1, policy_version 93850 (0.0007) -[2023-10-17 04:02:52,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 192905216. Throughput: 0: 1768.1, 1: 1766.1. Samples: 48229016. Policy #0 lag: (min: 17.0, avg: 23.4, max: 49.0) -[2023-10-17 04:02:52,215][61453] Avg episode reward: [(0, '10.010'), (1, '10.810')] -[2023-10-17 04:02:52,716][62373] Updated weights for policy 0, policy_version 94530 (0.0008) -[2023-10-17 04:02:53,084][62373] Updated weights for policy 0, policy_version 94540 (0.0011) -[2023-10-17 04:02:53,458][62373] Updated weights for policy 0, policy_version 94550 (0.0010) -[2023-10-17 04:02:53,823][62373] Updated weights for policy 0, policy_version 94560 (0.0010) -[2023-10-17 04:02:55,576][62408] Updated weights for policy 1, policy_version 93860 (0.0009) -[2023-10-17 04:02:55,946][62408] Updated weights for policy 1, policy_version 93870 (0.0011) -[2023-10-17 04:02:56,307][62408] Updated weights for policy 1, policy_version 93880 (0.0008) -[2023-10-17 04:02:57,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 192970752. Throughput: 0: 1771.8, 1: 1778.0. Samples: 48250932. Policy #0 lag: (min: 17.0, avg: 23.4, max: 49.0) -[2023-10-17 04:02:57,214][61453] Avg episode reward: [(0, '10.570'), (1, '11.220')] -[2023-10-17 04:02:57,622][62373] Updated weights for policy 0, policy_version 94570 (0.0009) -[2023-10-17 04:02:57,998][62373] Updated weights for policy 0, policy_version 94580 (0.0010) -[2023-10-17 04:02:58,359][62373] Updated weights for policy 0, policy_version 94590 (0.0008) -[2023-10-17 04:03:00,079][62408] Updated weights for policy 1, policy_version 93890 (0.0009) -[2023-10-17 04:03:00,454][62408] Updated weights for policy 1, policy_version 93900 (0.0009) -[2023-10-17 04:03:00,824][62408] Updated weights for policy 1, policy_version 93910 (0.0008) -[2023-10-17 04:03:01,186][62408] Updated weights for policy 1, policy_version 93920 (0.0010) -[2023-10-17 04:03:02,038][62373] Updated weights for policy 0, policy_version 94600 (0.0008) -[2023-10-17 04:03:02,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 193036288. Throughput: 0: 1796.0, 1: 1753.9. Samples: 48272018. Policy #0 lag: (min: 17.0, avg: 23.4, max: 49.0) -[2023-10-17 04:03:02,215][61453] Avg episode reward: [(0, '10.650'), (1, '11.450')] -[2023-10-17 04:03:02,417][62373] Updated weights for policy 0, policy_version 94610 (0.0008) -[2023-10-17 04:03:02,792][62373] Updated weights for policy 0, policy_version 94620 (0.0008) -[2023-10-17 04:03:04,951][62408] Updated weights for policy 1, policy_version 93930 (0.0009) -[2023-10-17 04:03:05,331][62408] Updated weights for policy 1, policy_version 93940 (0.0009) -[2023-10-17 04:03:05,700][62408] Updated weights for policy 1, policy_version 93950 (0.0010) -[2023-10-17 04:03:06,483][62373] Updated weights for policy 0, policy_version 94630 (0.0008) -[2023-10-17 04:03:06,853][62373] Updated weights for policy 0, policy_version 94640 (0.0008) -[2023-10-17 04:03:07,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 193101824. Throughput: 0: 1776.8, 1: 1778.0. Samples: 48283126. Policy #0 lag: (min: 17.0, avg: 23.4, max: 49.0) -[2023-10-17 04:03:07,215][61453] Avg episode reward: [(0, '10.330'), (1, '11.810')] -[2023-10-17 04:03:07,227][62373] Updated weights for policy 0, policy_version 94650 (0.0008) -[2023-10-17 04:03:09,555][62408] Updated weights for policy 1, policy_version 93960 (0.0009) -[2023-10-17 04:03:09,925][62408] Updated weights for policy 1, policy_version 93970 (0.0007) -[2023-10-17 04:03:10,281][62408] Updated weights for policy 1, policy_version 93980 (0.0011) -[2023-10-17 04:03:10,948][62373] Updated weights for policy 0, policy_version 94660 (0.0010) -[2023-10-17 04:03:11,313][62373] Updated weights for policy 0, policy_version 94670 (0.0009) -[2023-10-17 04:03:11,687][62373] Updated weights for policy 0, policy_version 94680 (0.0007) -[2023-10-17 04:03:12,214][61453] Fps is (10 sec: 16384.3, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 193200128. Throughput: 0: 1797.9, 1: 1750.3. Samples: 48303900. Policy #0 lag: (min: 17.0, avg: 23.4, max: 49.0) -[2023-10-17 04:03:12,215][61453] Avg episode reward: [(0, '11.010'), (1, '11.300')] -[2023-10-17 04:03:14,065][62408] Updated weights for policy 1, policy_version 93990 (0.0009) -[2023-10-17 04:03:14,458][62408] Updated weights for policy 1, policy_version 94000 (0.0011) -[2023-10-17 04:03:14,827][62408] Updated weights for policy 1, policy_version 94010 (0.0007) -[2023-10-17 04:03:15,481][62373] Updated weights for policy 0, policy_version 94690 (0.0008) -[2023-10-17 04:03:15,851][62373] Updated weights for policy 0, policy_version 94700 (0.0007) -[2023-10-17 04:03:16,221][62373] Updated weights for policy 0, policy_version 94710 (0.0008) -[2023-10-17 04:03:16,595][62373] Updated weights for policy 0, policy_version 94720 (0.0011) -[2023-10-17 04:03:17,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 193265664. Throughput: 0: 1779.9, 1: 1755.1. Samples: 48324768. Policy #0 lag: (min: 17.0, avg: 23.4, max: 49.0) -[2023-10-17 04:03:17,215][61453] Avg episode reward: [(0, '10.200'), (1, '11.940')] -[2023-10-17 04:03:18,717][62408] Updated weights for policy 1, policy_version 94020 (0.0008) -[2023-10-17 04:03:19,081][62408] Updated weights for policy 1, policy_version 94030 (0.0007) -[2023-10-17 04:03:19,449][62408] Updated weights for policy 1, policy_version 94040 (0.0008) -[2023-10-17 04:03:20,418][62373] Updated weights for policy 0, policy_version 94730 (0.0009) -[2023-10-17 04:03:20,780][62373] Updated weights for policy 0, policy_version 94740 (0.0008) -[2023-10-17 04:03:21,151][62373] Updated weights for policy 0, policy_version 94750 (0.0007) -[2023-10-17 04:03:22,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 193331200. Throughput: 0: 1804.3, 1: 1749.5. Samples: 48335986. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 04:03:22,215][61453] Avg episode reward: [(0, '10.990'), (1, '13.210')] -[2023-10-17 04:03:23,335][62408] Updated weights for policy 1, policy_version 94050 (0.0008) -[2023-10-17 04:03:23,704][62408] Updated weights for policy 1, policy_version 94060 (0.0011) -[2023-10-17 04:03:24,065][62408] Updated weights for policy 1, policy_version 94070 (0.0011) -[2023-10-17 04:03:24,432][62408] Updated weights for policy 1, policy_version 94080 (0.0009) -[2023-10-17 04:03:24,649][62373] Updated weights for policy 0, policy_version 94760 (0.0007) -[2023-10-17 04:03:25,025][62373] Updated weights for policy 0, policy_version 94770 (0.0009) -[2023-10-17 04:03:25,397][62373] Updated weights for policy 0, policy_version 94780 (0.0009) -[2023-10-17 04:03:27,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 193396736. Throughput: 0: 1790.6, 1: 1754.0. Samples: 48356814. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 04:03:27,215][61453] Avg episode reward: [(0, '11.530'), (1, '12.690')] -[2023-10-17 04:03:28,193][62408] Updated weights for policy 1, policy_version 94090 (0.0009) -[2023-10-17 04:03:28,567][62408] Updated weights for policy 1, policy_version 94100 (0.0009) -[2023-10-17 04:03:28,935][62408] Updated weights for policy 1, policy_version 94110 (0.0008) -[2023-10-17 04:03:29,244][62373] Updated weights for policy 0, policy_version 94790 (0.0008) -[2023-10-17 04:03:29,613][62373] Updated weights for policy 0, policy_version 94800 (0.0009) -[2023-10-17 04:03:29,987][62373] Updated weights for policy 0, policy_version 94810 (0.0010) -[2023-10-17 04:03:32,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 193462272. Throughput: 0: 1788.6, 1: 1777.3. Samples: 48379096. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 04:03:32,215][61453] Avg episode reward: [(0, '10.700'), (1, '12.510')] -[2023-10-17 04:03:32,223][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000094816_97091584.pth... -[2023-10-17 04:03:32,223][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000094112_96370688.pth... -[2023-10-17 04:03:32,262][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000092480_94699520.pth -[2023-10-17 04:03:32,263][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000093152_95387648.pth -[2023-10-17 04:03:32,839][62408] Updated weights for policy 1, policy_version 94120 (0.0008) -[2023-10-17 04:03:33,202][62408] Updated weights for policy 1, policy_version 94130 (0.0008) -[2023-10-17 04:03:33,578][62408] Updated weights for policy 1, policy_version 94140 (0.0007) -[2023-10-17 04:03:33,773][62373] Updated weights for policy 0, policy_version 94820 (0.0007) -[2023-10-17 04:03:34,139][62373] Updated weights for policy 0, policy_version 94830 (0.0009) -[2023-10-17 04:03:34,517][62373] Updated weights for policy 0, policy_version 94840 (0.0008) -[2023-10-17 04:03:37,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 193527808. Throughput: 0: 1793.4, 1: 1756.0. Samples: 48388738. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 04:03:37,214][61453] Avg episode reward: [(0, '11.080'), (1, '12.510')] -[2023-10-17 04:03:37,570][62408] Updated weights for policy 1, policy_version 94150 (0.0007) -[2023-10-17 04:03:37,928][62408] Updated weights for policy 1, policy_version 94160 (0.0009) -[2023-10-17 04:03:38,294][62373] Updated weights for policy 0, policy_version 94850 (0.0009) -[2023-10-17 04:03:38,297][62408] Updated weights for policy 1, policy_version 94170 (0.0008) -[2023-10-17 04:03:38,659][62373] Updated weights for policy 0, policy_version 94860 (0.0009) -[2023-10-17 04:03:39,032][62373] Updated weights for policy 0, policy_version 94870 (0.0007) -[2023-10-17 04:03:39,402][62373] Updated weights for policy 0, policy_version 94880 (0.0009) -[2023-10-17 04:03:42,125][62408] Updated weights for policy 1, policy_version 94180 (0.0009) -[2023-10-17 04:03:42,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 193593344. Throughput: 0: 1789.8, 1: 1762.5. Samples: 48410786. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 04:03:42,214][61453] Avg episode reward: [(0, '10.610'), (1, '11.960')] -[2023-10-17 04:03:42,490][62408] Updated weights for policy 1, policy_version 94190 (0.0011) -[2023-10-17 04:03:42,868][62408] Updated weights for policy 1, policy_version 94200 (0.0009) -[2023-10-17 04:03:43,095][62373] Updated weights for policy 0, policy_version 94890 (0.0007) -[2023-10-17 04:03:43,460][62373] Updated weights for policy 0, policy_version 94900 (0.0008) -[2023-10-17 04:03:43,825][62373] Updated weights for policy 0, policy_version 94910 (0.0007) -[2023-10-17 04:03:46,636][62408] Updated weights for policy 1, policy_version 94210 (0.0008) -[2023-10-17 04:03:47,004][62408] Updated weights for policy 1, policy_version 94220 (0.0007) -[2023-10-17 04:03:47,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 193658880. Throughput: 0: 1792.8, 1: 1774.6. Samples: 48432550. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 04:03:47,215][61453] Avg episode reward: [(0, '10.660'), (1, '12.860')] -[2023-10-17 04:03:47,358][62408] Updated weights for policy 1, policy_version 94230 (0.0007) -[2023-10-17 04:03:47,717][62373] Updated weights for policy 0, policy_version 94920 (0.0009) -[2023-10-17 04:03:47,726][62408] Updated weights for policy 1, policy_version 94240 (0.0007) -[2023-10-17 04:03:48,097][62373] Updated weights for policy 0, policy_version 94930 (0.0011) -[2023-10-17 04:03:48,471][62373] Updated weights for policy 0, policy_version 94940 (0.0011) -[2023-10-17 04:03:51,444][62408] Updated weights for policy 1, policy_version 94250 (0.0007) -[2023-10-17 04:03:51,811][62408] Updated weights for policy 1, policy_version 94260 (0.0008) -[2023-10-17 04:03:52,169][62408] Updated weights for policy 1, policy_version 94270 (0.0007) -[2023-10-17 04:03:52,214][61453] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 193724416. Throughput: 0: 1783.7, 1: 1756.9. Samples: 48442454. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 04:03:52,214][61453] Avg episode reward: [(0, '11.670'), (1, '12.870')] -[2023-10-17 04:03:52,324][62373] Updated weights for policy 0, policy_version 94950 (0.0009) -[2023-10-17 04:03:52,688][62373] Updated weights for policy 0, policy_version 94960 (0.0007) -[2023-10-17 04:03:53,066][62373] Updated weights for policy 0, policy_version 94970 (0.0008) -[2023-10-17 04:03:56,015][62408] Updated weights for policy 1, policy_version 94280 (0.0008) -[2023-10-17 04:03:56,375][62408] Updated weights for policy 1, policy_version 94290 (0.0007) -[2023-10-17 04:03:56,746][62408] Updated weights for policy 1, policy_version 94300 (0.0007) -[2023-10-17 04:03:56,772][62373] Updated weights for policy 0, policy_version 94980 (0.0008) -[2023-10-17 04:03:57,140][62373] Updated weights for policy 0, policy_version 94990 (0.0009) -[2023-10-17 04:03:57,214][61453] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 193822720. Throughput: 0: 1790.0, 1: 1781.1. Samples: 48464600. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 04:03:57,214][61453] Avg episode reward: [(0, '11.210'), (1, '11.580')] -[2023-10-17 04:03:57,501][62373] Updated weights for policy 0, policy_version 95000 (0.0008) -[2023-10-17 04:04:00,670][62408] Updated weights for policy 1, policy_version 94310 (0.0008) -[2023-10-17 04:04:01,045][62408] Updated weights for policy 1, policy_version 94320 (0.0008) -[2023-10-17 04:04:01,405][62408] Updated weights for policy 1, policy_version 94330 (0.0009) -[2023-10-17 04:04:01,580][62373] Updated weights for policy 0, policy_version 95010 (0.0009) -[2023-10-17 04:04:01,947][62373] Updated weights for policy 0, policy_version 95020 (0.0009) -[2023-10-17 04:04:02,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 193888256. Throughput: 0: 1800.4, 1: 1747.6. Samples: 48484430. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 04:04:02,215][61453] Avg episode reward: [(0, '11.960'), (1, '11.450')] -[2023-10-17 04:04:02,315][62373] Updated weights for policy 0, policy_version 95030 (0.0007) -[2023-10-17 04:04:02,675][62373] Updated weights for policy 0, policy_version 95040 (0.0010) -[2023-10-17 04:04:05,266][62408] Updated weights for policy 1, policy_version 94340 (0.0007) -[2023-10-17 04:04:05,637][62408] Updated weights for policy 1, policy_version 94350 (0.0010) -[2023-10-17 04:04:06,005][62408] Updated weights for policy 1, policy_version 94360 (0.0010) -[2023-10-17 04:04:06,532][62373] Updated weights for policy 0, policy_version 95050 (0.0007) -[2023-10-17 04:04:06,905][62373] Updated weights for policy 0, policy_version 95060 (0.0008) -[2023-10-17 04:04:07,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 193953792. Throughput: 0: 1773.2, 1: 1780.8. Samples: 48495912. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 04:04:07,214][61453] Avg episode reward: [(0, '11.100'), (1, '11.940')] -[2023-10-17 04:04:07,281][62373] Updated weights for policy 0, policy_version 95070 (0.0009) -[2023-10-17 04:04:09,844][62408] Updated weights for policy 1, policy_version 94370 (0.0009) -[2023-10-17 04:04:10,209][62408] Updated weights for policy 1, policy_version 94380 (0.0008) -[2023-10-17 04:04:10,570][62408] Updated weights for policy 1, policy_version 94390 (0.0009) -[2023-10-17 04:04:10,936][62408] Updated weights for policy 1, policy_version 94400 (0.0007) -[2023-10-17 04:04:11,183][62373] Updated weights for policy 0, policy_version 95080 (0.0010) -[2023-10-17 04:04:11,550][62373] Updated weights for policy 0, policy_version 95090 (0.0011) -[2023-10-17 04:04:11,924][62373] Updated weights for policy 0, policy_version 95100 (0.0010) -[2023-10-17 04:04:12,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14329.1). Total num frames: 194052096. Throughput: 0: 1800.1, 1: 1753.8. Samples: 48516742. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 04:04:12,215][61453] Avg episode reward: [(0, '11.230'), (1, '11.480')] -[2023-10-17 04:04:14,475][62408] Updated weights for policy 1, policy_version 94410 (0.0011) -[2023-10-17 04:04:14,836][62408] Updated weights for policy 1, policy_version 94420 (0.0007) -[2023-10-17 04:04:15,207][62408] Updated weights for policy 1, policy_version 94430 (0.0009) -[2023-10-17 04:04:15,635][62373] Updated weights for policy 0, policy_version 95110 (0.0009) -[2023-10-17 04:04:15,993][62373] Updated weights for policy 0, policy_version 95120 (0.0009) -[2023-10-17 04:04:16,362][62373] Updated weights for policy 0, policy_version 95130 (0.0009) -[2023-10-17 04:04:17,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 194117632. Throughput: 0: 1765.0, 1: 1751.8. Samples: 48537352. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 04:04:17,215][61453] Avg episode reward: [(0, '10.880'), (1, '11.940')] -[2023-10-17 04:04:19,144][62408] Updated weights for policy 1, policy_version 94440 (0.0009) -[2023-10-17 04:04:19,509][62408] Updated weights for policy 1, policy_version 94450 (0.0010) -[2023-10-17 04:04:19,875][62408] Updated weights for policy 1, policy_version 94460 (0.0008) -[2023-10-17 04:04:20,183][62373] Updated weights for policy 0, policy_version 95140 (0.0011) -[2023-10-17 04:04:20,539][62373] Updated weights for policy 0, policy_version 95150 (0.0009) -[2023-10-17 04:04:20,905][62373] Updated weights for policy 0, policy_version 95160 (0.0009) -[2023-10-17 04:04:22,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 194183168. Throughput: 0: 1795.0, 1: 1759.2. Samples: 48548674. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 04:04:22,214][61453] Avg episode reward: [(0, '11.630'), (1, '11.080')] -[2023-10-17 04:04:23,591][62408] Updated weights for policy 1, policy_version 94470 (0.0008) -[2023-10-17 04:04:23,962][62408] Updated weights for policy 1, policy_version 94480 (0.0008) -[2023-10-17 04:04:24,322][62408] Updated weights for policy 1, policy_version 94490 (0.0007) -[2023-10-17 04:04:24,772][62373] Updated weights for policy 0, policy_version 95170 (0.0008) -[2023-10-17 04:04:25,157][62373] Updated weights for policy 0, policy_version 95180 (0.0007) -[2023-10-17 04:04:25,528][62373] Updated weights for policy 0, policy_version 95190 (0.0008) -[2023-10-17 04:04:25,889][62373] Updated weights for policy 0, policy_version 95200 (0.0008) -[2023-10-17 04:04:27,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 194248704. Throughput: 0: 1764.6, 1: 1761.4. Samples: 48569456. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 04:04:27,215][61453] Avg episode reward: [(0, '11.040'), (1, '10.970')] -[2023-10-17 04:04:28,211][62408] Updated weights for policy 1, policy_version 94500 (0.0007) -[2023-10-17 04:04:28,580][62408] Updated weights for policy 1, policy_version 94510 (0.0008) -[2023-10-17 04:04:28,947][62408] Updated weights for policy 1, policy_version 94520 (0.0007) -[2023-10-17 04:04:29,733][62373] Updated weights for policy 0, policy_version 95210 (0.0010) -[2023-10-17 04:04:30,099][62373] Updated weights for policy 0, policy_version 95220 (0.0011) -[2023-10-17 04:04:30,469][62373] Updated weights for policy 0, policy_version 95230 (0.0011) -[2023-10-17 04:04:32,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 194314240. Throughput: 0: 1761.4, 1: 1767.2. Samples: 48591340. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 04:04:32,215][61453] Avg episode reward: [(0, '11.030'), (1, '11.690')] -[2023-10-17 04:04:32,854][62408] Updated weights for policy 1, policy_version 94530 (0.0008) -[2023-10-17 04:04:33,221][62408] Updated weights for policy 1, policy_version 94540 (0.0011) -[2023-10-17 04:04:33,591][62408] Updated weights for policy 1, policy_version 94550 (0.0010) -[2023-10-17 04:04:33,963][62408] Updated weights for policy 1, policy_version 94560 (0.0007) -[2023-10-17 04:04:34,244][62373] Updated weights for policy 0, policy_version 95240 (0.0011) -[2023-10-17 04:04:34,618][62373] Updated weights for policy 0, policy_version 95250 (0.0008) -[2023-10-17 04:04:34,995][62373] Updated weights for policy 0, policy_version 95260 (0.0010) -[2023-10-17 04:04:37,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 194379776. Throughput: 0: 1768.5, 1: 1758.4. Samples: 48601166. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 04:04:37,215][61453] Avg episode reward: [(0, '11.600'), (1, '11.620')] -[2023-10-17 04:04:37,799][62408] Updated weights for policy 1, policy_version 94570 (0.0007) -[2023-10-17 04:04:38,163][62408] Updated weights for policy 1, policy_version 94580 (0.0007) -[2023-10-17 04:04:38,528][62408] Updated weights for policy 1, policy_version 94590 (0.0008) -[2023-10-17 04:04:38,655][62373] Updated weights for policy 0, policy_version 95270 (0.0009) -[2023-10-17 04:04:39,021][62373] Updated weights for policy 0, policy_version 95280 (0.0009) -[2023-10-17 04:04:39,382][62373] Updated weights for policy 0, policy_version 95290 (0.0009) -[2023-10-17 04:04:42,214][61453] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 194445312. Throughput: 0: 1758.8, 1: 1760.2. Samples: 48622956. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 04:04:42,214][61453] Avg episode reward: [(0, '11.690'), (1, '12.480')] -[2023-10-17 04:04:42,334][62408] Updated weights for policy 1, policy_version 94600 (0.0007) -[2023-10-17 04:04:42,701][62408] Updated weights for policy 1, policy_version 94610 (0.0012) -[2023-10-17 04:04:43,070][62408] Updated weights for policy 1, policy_version 94620 (0.0010) -[2023-10-17 04:04:43,136][62373] Updated weights for policy 0, policy_version 95300 (0.0008) -[2023-10-17 04:04:43,506][62373] Updated weights for policy 0, policy_version 95310 (0.0007) -[2023-10-17 04:04:43,884][62373] Updated weights for policy 0, policy_version 95320 (0.0008) -[2023-10-17 04:04:47,072][62408] Updated weights for policy 1, policy_version 94630 (0.0008) -[2023-10-17 04:04:47,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 194510848. Throughput: 0: 1779.5, 1: 1787.3. Samples: 48644934. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 04:04:47,214][61453] Avg episode reward: [(0, '11.940'), (1, '12.150')] -[2023-10-17 04:04:47,457][62408] Updated weights for policy 1, policy_version 94640 (0.0007) -[2023-10-17 04:04:47,795][62373] Updated weights for policy 0, policy_version 95330 (0.0008) -[2023-10-17 04:04:47,815][62408] Updated weights for policy 1, policy_version 94650 (0.0007) -[2023-10-17 04:04:48,169][62373] Updated weights for policy 0, policy_version 95340 (0.0008) -[2023-10-17 04:04:48,544][62373] Updated weights for policy 0, policy_version 95350 (0.0008) -[2023-10-17 04:04:48,905][62373] Updated weights for policy 0, policy_version 95360 (0.0009) -[2023-10-17 04:04:51,642][62408] Updated weights for policy 1, policy_version 94660 (0.0008) -[2023-10-17 04:04:52,005][62408] Updated weights for policy 1, policy_version 94670 (0.0008) -[2023-10-17 04:04:52,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 194576384. Throughput: 0: 1765.1, 1: 1755.5. Samples: 48654340. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 04:04:52,215][61453] Avg episode reward: [(0, '11.560'), (1, '11.780')] -[2023-10-17 04:04:52,370][62408] Updated weights for policy 1, policy_version 94680 (0.0009) -[2023-10-17 04:04:52,707][62373] Updated weights for policy 0, policy_version 95370 (0.0009) -[2023-10-17 04:04:53,063][62373] Updated weights for policy 0, policy_version 95380 (0.0009) -[2023-10-17 04:04:53,435][62373] Updated weights for policy 0, policy_version 95390 (0.0007) -[2023-10-17 04:04:56,275][62408] Updated weights for policy 1, policy_version 94690 (0.0007) -[2023-10-17 04:04:56,641][62408] Updated weights for policy 1, policy_version 94700 (0.0009) -[2023-10-17 04:04:57,012][62408] Updated weights for policy 1, policy_version 94710 (0.0008) -[2023-10-17 04:04:57,161][62373] Updated weights for policy 0, policy_version 95400 (0.0008) -[2023-10-17 04:04:57,214][61453] Fps is (10 sec: 13107.2, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 194641920. Throughput: 0: 1765.7, 1: 1776.9. Samples: 48676156. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 04:04:57,214][61453] Avg episode reward: [(0, '12.290'), (1, '11.700')] -[2023-10-17 04:04:57,370][62408] Updated weights for policy 1, policy_version 94720 (0.0008) -[2023-10-17 04:04:57,531][62373] Updated weights for policy 0, policy_version 95410 (0.0008) -[2023-10-17 04:04:57,909][62373] Updated weights for policy 0, policy_version 95420 (0.0008) -[2023-10-17 04:05:01,179][62408] Updated weights for policy 1, policy_version 94730 (0.0010) -[2023-10-17 04:05:01,546][62408] Updated weights for policy 1, policy_version 94740 (0.0009) -[2023-10-17 04:05:01,617][62373] Updated weights for policy 0, policy_version 95430 (0.0007) -[2023-10-17 04:05:01,913][62408] Updated weights for policy 1, policy_version 94750 (0.0007) -[2023-10-17 04:05:01,984][62373] Updated weights for policy 0, policy_version 95440 (0.0008) -[2023-10-17 04:05:02,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 194740224. Throughput: 0: 1787.6, 1: 1751.1. Samples: 48696596. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 04:05:02,215][61453] Avg episode reward: [(0, '12.160'), (1, '12.230')] -[2023-10-17 04:05:02,342][62373] Updated weights for policy 0, policy_version 95450 (0.0008) -[2023-10-17 04:05:05,855][62408] Updated weights for policy 1, policy_version 94760 (0.0008) -[2023-10-17 04:05:05,963][62373] Updated weights for policy 0, policy_version 95460 (0.0008) -[2023-10-17 04:05:06,222][62408] Updated weights for policy 1, policy_version 94770 (0.0008) -[2023-10-17 04:05:06,331][62373] Updated weights for policy 0, policy_version 95470 (0.0009) -[2023-10-17 04:05:06,594][62408] Updated weights for policy 1, policy_version 94780 (0.0008) -[2023-10-17 04:05:06,693][62373] Updated weights for policy 0, policy_version 95480 (0.0011) -[2023-10-17 04:05:07,214][61453] Fps is (10 sec: 19660.7, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 194838528. Throughput: 0: 1775.1, 1: 1772.7. Samples: 48708326. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 04:05:07,215][61453] Avg episode reward: [(0, '12.550'), (1, '11.880')] -[2023-10-17 04:05:10,351][62408] Updated weights for policy 1, policy_version 94790 (0.0008) -[2023-10-17 04:05:10,599][62373] Updated weights for policy 0, policy_version 95490 (0.0010) -[2023-10-17 04:05:10,715][62408] Updated weights for policy 1, policy_version 94800 (0.0008) -[2023-10-17 04:05:10,975][62373] Updated weights for policy 0, policy_version 95500 (0.0008) -[2023-10-17 04:05:11,083][62408] Updated weights for policy 1, policy_version 94810 (0.0009) -[2023-10-17 04:05:11,344][62373] Updated weights for policy 0, policy_version 95510 (0.0009) -[2023-10-17 04:05:11,718][62373] Updated weights for policy 0, policy_version 95520 (0.0009) -[2023-10-17 04:05:12,214][61453] Fps is (10 sec: 16384.5, 60 sec: 14199.5, 300 sec: 14329.1). Total num frames: 194904064. Throughput: 0: 1791.9, 1: 1751.4. Samples: 48728906. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 04:05:12,214][61453] Avg episode reward: [(0, '12.310'), (1, '12.010')] -[2023-10-17 04:05:14,920][62408] Updated weights for policy 1, policy_version 94820 (0.0007) -[2023-10-17 04:05:15,290][62408] Updated weights for policy 1, policy_version 94830 (0.0007) -[2023-10-17 04:05:15,528][62373] Updated weights for policy 0, policy_version 95530 (0.0009) -[2023-10-17 04:05:15,666][62408] Updated weights for policy 1, policy_version 94840 (0.0008) -[2023-10-17 04:05:15,908][62373] Updated weights for policy 0, policy_version 95540 (0.0008) -[2023-10-17 04:05:16,280][62373] Updated weights for policy 0, policy_version 95550 (0.0007) -[2023-10-17 04:05:17,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 194969600. Throughput: 0: 1773.2, 1: 1741.3. Samples: 48749492. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 04:05:17,215][61453] Avg episode reward: [(0, '12.100'), (1, '11.220')] -[2023-10-17 04:05:19,588][62408] Updated weights for policy 1, policy_version 94850 (0.0009) -[2023-10-17 04:05:19,951][62408] Updated weights for policy 1, policy_version 94860 (0.0007) -[2023-10-17 04:05:19,971][62373] Updated weights for policy 0, policy_version 95560 (0.0008) -[2023-10-17 04:05:20,327][62408] Updated weights for policy 1, policy_version 94870 (0.0007) -[2023-10-17 04:05:20,339][62373] Updated weights for policy 0, policy_version 95570 (0.0009) -[2023-10-17 04:05:20,691][62408] Updated weights for policy 1, policy_version 94880 (0.0009) -[2023-10-17 04:05:20,703][62373] Updated weights for policy 0, policy_version 95580 (0.0007) -[2023-10-17 04:05:22,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 195035136. Throughput: 0: 1795.6, 1: 1761.7. Samples: 48761244. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-17 04:05:22,214][61453] Avg episode reward: [(0, '11.930'), (1, '11.680')] -[2023-10-17 04:05:24,528][62373] Updated weights for policy 0, policy_version 95590 (0.0009) -[2023-10-17 04:05:24,532][62408] Updated weights for policy 1, policy_version 94890 (0.0007) -[2023-10-17 04:05:24,886][62408] Updated weights for policy 1, policy_version 94900 (0.0007) -[2023-10-17 04:05:24,899][62373] Updated weights for policy 0, policy_version 95600 (0.0009) -[2023-10-17 04:05:25,249][62408] Updated weights for policy 1, policy_version 94910 (0.0007) -[2023-10-17 04:05:25,278][62373] Updated weights for policy 0, policy_version 95610 (0.0008) -[2023-10-17 04:05:27,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 195100672. Throughput: 0: 1775.0, 1: 1739.4. Samples: 48781106. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-17 04:05:27,215][61453] Avg episode reward: [(0, '11.400'), (1, '11.810')] -[2023-10-17 04:05:29,024][62373] Updated weights for policy 0, policy_version 95620 (0.0007) -[2023-10-17 04:05:29,138][62408] Updated weights for policy 1, policy_version 94920 (0.0010) -[2023-10-17 04:05:29,382][62373] Updated weights for policy 0, policy_version 95630 (0.0007) -[2023-10-17 04:05:29,495][62408] Updated weights for policy 1, policy_version 94930 (0.0009) -[2023-10-17 04:05:29,752][62373] Updated weights for policy 0, policy_version 95640 (0.0008) -[2023-10-17 04:05:29,861][62408] Updated weights for policy 1, policy_version 94940 (0.0007) -[2023-10-17 04:05:32,214][61453] Fps is (10 sec: 13106.7, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 195166208. Throughput: 0: 1776.7, 1: 1747.2. Samples: 48803510. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-17 04:05:32,215][61453] Avg episode reward: [(0, '11.400'), (1, '11.780')] -[2023-10-17 04:05:32,225][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000095648_97943552.pth... -[2023-10-17 04:05:32,225][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000094944_97222656.pth... -[2023-10-17 04:05:32,255][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000093984_96239616.pth -[2023-10-17 04:05:32,264][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000093312_95551488.pth -[2023-10-17 04:05:33,476][62373] Updated weights for policy 0, policy_version 95650 (0.0008) -[2023-10-17 04:05:33,731][62408] Updated weights for policy 1, policy_version 94950 (0.0007) -[2023-10-17 04:05:33,834][62373] Updated weights for policy 0, policy_version 95660 (0.0008) -[2023-10-17 04:05:34,124][62408] Updated weights for policy 1, policy_version 94960 (0.0007) -[2023-10-17 04:05:34,199][62373] Updated weights for policy 0, policy_version 95670 (0.0008) -[2023-10-17 04:05:34,484][62408] Updated weights for policy 1, policy_version 94970 (0.0008) -[2023-10-17 04:05:34,570][62373] Updated weights for policy 0, policy_version 95680 (0.0009) -[2023-10-17 04:05:37,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 195231744. Throughput: 0: 1779.6, 1: 1745.9. Samples: 48812984. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-17 04:05:37,215][61453] Avg episode reward: [(0, '11.810'), (1, '11.320')] -[2023-10-17 04:05:38,421][62408] Updated weights for policy 1, policy_version 94980 (0.0008) -[2023-10-17 04:05:38,468][62373] Updated weights for policy 0, policy_version 95690 (0.0007) -[2023-10-17 04:05:38,788][62408] Updated weights for policy 1, policy_version 94990 (0.0008) -[2023-10-17 04:05:38,842][62373] Updated weights for policy 0, policy_version 95700 (0.0007) -[2023-10-17 04:05:39,153][62408] Updated weights for policy 1, policy_version 95000 (0.0009) -[2023-10-17 04:05:39,205][62373] Updated weights for policy 0, policy_version 95710 (0.0010) -[2023-10-17 04:05:42,214][61453] Fps is (10 sec: 13107.7, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 195297280. Throughput: 0: 1776.7, 1: 1746.8. Samples: 48834716. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-17 04:05:42,215][61453] Avg episode reward: [(0, '11.350'), (1, '11.770')] -[2023-10-17 04:05:42,964][62408] Updated weights for policy 1, policy_version 95010 (0.0008) -[2023-10-17 04:05:43,052][62373] Updated weights for policy 0, policy_version 95720 (0.0009) -[2023-10-17 04:05:43,331][62408] Updated weights for policy 1, policy_version 95020 (0.0007) -[2023-10-17 04:05:43,412][62373] Updated weights for policy 0, policy_version 95730 (0.0008) -[2023-10-17 04:05:43,700][62408] Updated weights for policy 1, policy_version 95030 (0.0008) -[2023-10-17 04:05:43,777][62373] Updated weights for policy 0, policy_version 95740 (0.0009) -[2023-10-17 04:05:44,058][62408] Updated weights for policy 1, policy_version 95040 (0.0007) -[2023-10-17 04:05:47,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 195362816. Throughput: 0: 1788.8, 1: 1776.0. Samples: 48857014. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-17 04:05:47,215][61453] Avg episode reward: [(0, '11.550'), (1, '12.060')] -[2023-10-17 04:05:47,590][62373] Updated weights for policy 0, policy_version 95750 (0.0008) -[2023-10-17 04:05:47,892][62408] Updated weights for policy 1, policy_version 95050 (0.0008) -[2023-10-17 04:05:47,946][62373] Updated weights for policy 0, policy_version 95760 (0.0007) -[2023-10-17 04:05:48,257][62408] Updated weights for policy 1, policy_version 95060 (0.0007) -[2023-10-17 04:05:48,318][62373] Updated weights for policy 0, policy_version 95770 (0.0008) -[2023-10-17 04:05:48,625][62408] Updated weights for policy 1, policy_version 95070 (0.0008) -[2023-10-17 04:05:52,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 195428352. Throughput: 0: 1767.7, 1: 1746.0. Samples: 48866442. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-17 04:05:52,215][61453] Avg episode reward: [(0, '11.340'), (1, '11.920')] -[2023-10-17 04:05:52,258][62373] Updated weights for policy 0, policy_version 95780 (0.0008) -[2023-10-17 04:05:52,583][62408] Updated weights for policy 1, policy_version 95080 (0.0009) -[2023-10-17 04:05:52,618][62373] Updated weights for policy 0, policy_version 95790 (0.0007) -[2023-10-17 04:05:52,944][62408] Updated weights for policy 1, policy_version 95090 (0.0008) -[2023-10-17 04:05:52,990][62373] Updated weights for policy 0, policy_version 95800 (0.0009) -[2023-10-17 04:05:53,308][62408] Updated weights for policy 1, policy_version 95100 (0.0008) -[2023-10-17 04:05:56,814][62373] Updated weights for policy 0, policy_version 95810 (0.0009) -[2023-10-17 04:05:57,167][62408] Updated weights for policy 1, policy_version 95110 (0.0009) -[2023-10-17 04:05:57,172][62373] Updated weights for policy 0, policy_version 95820 (0.0008) -[2023-10-17 04:05:57,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 195493888. Throughput: 0: 1778.9, 1: 1763.2. Samples: 48888304. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-17 04:05:57,215][61453] Avg episode reward: [(0, '11.600'), (1, '12.330')] -[2023-10-17 04:05:57,527][62408] Updated weights for policy 1, policy_version 95120 (0.0007) -[2023-10-17 04:05:57,539][62373] Updated weights for policy 0, policy_version 95830 (0.0008) -[2023-10-17 04:05:57,896][62408] Updated weights for policy 1, policy_version 95130 (0.0007) -[2023-10-17 04:05:57,903][62373] Updated weights for policy 0, policy_version 95840 (0.0008) -[2023-10-17 04:06:01,763][62408] Updated weights for policy 1, policy_version 95140 (0.0009) -[2023-10-17 04:06:01,784][62373] Updated weights for policy 0, policy_version 95850 (0.0007) -[2023-10-17 04:06:02,128][62408] Updated weights for policy 1, policy_version 95150 (0.0008) -[2023-10-17 04:06:02,157][62373] Updated weights for policy 0, policy_version 95860 (0.0007) -[2023-10-17 04:06:02,214][61453] Fps is (10 sec: 13107.0, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 195559424. Throughput: 0: 1786.0, 1: 1767.6. Samples: 48909402. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-17 04:06:02,215][61453] Avg episode reward: [(0, '11.430'), (1, '12.140')] -[2023-10-17 04:06:02,494][62408] Updated weights for policy 1, policy_version 95160 (0.0009) -[2023-10-17 04:06:02,525][62373] Updated weights for policy 0, policy_version 95870 (0.0009) -[2023-10-17 04:06:06,267][62373] Updated weights for policy 0, policy_version 95880 (0.0009) -[2023-10-17 04:06:06,322][62408] Updated weights for policy 1, policy_version 95170 (0.0009) -[2023-10-17 04:06:06,637][62373] Updated weights for policy 0, policy_version 95890 (0.0008) -[2023-10-17 04:06:06,694][62408] Updated weights for policy 1, policy_version 95180 (0.0007) -[2023-10-17 04:06:06,997][62373] Updated weights for policy 0, policy_version 95900 (0.0009) -[2023-10-17 04:06:07,062][62408] Updated weights for policy 1, policy_version 95190 (0.0009) -[2023-10-17 04:06:07,214][61453] Fps is (10 sec: 16383.8, 60 sec: 13653.3, 300 sec: 14218.0). Total num frames: 195657728. Throughput: 0: 1771.9, 1: 1754.4. Samples: 48919926. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-17 04:06:07,215][61453] Avg episode reward: [(0, '11.630'), (1, '12.380')] -[2023-10-17 04:06:07,413][62408] Updated weights for policy 1, policy_version 95200 (0.0007) -[2023-10-17 04:06:10,722][62373] Updated weights for policy 0, policy_version 95910 (0.0009) -[2023-10-17 04:06:11,079][62373] Updated weights for policy 0, policy_version 95920 (0.0008) -[2023-10-17 04:06:11,412][62408] Updated weights for policy 1, policy_version 95210 (0.0009) -[2023-10-17 04:06:11,452][62373] Updated weights for policy 0, policy_version 95930 (0.0009) -[2023-10-17 04:06:11,786][62408] Updated weights for policy 1, policy_version 95220 (0.0009) -[2023-10-17 04:06:12,146][62408] Updated weights for policy 1, policy_version 95230 (0.0008) -[2023-10-17 04:06:12,214][61453] Fps is (10 sec: 16384.3, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 195723264. Throughput: 0: 1785.3, 1: 1773.2. Samples: 48941236. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-17 04:06:12,215][61453] Avg episode reward: [(0, '11.150'), (1, '12.100')] -[2023-10-17 04:06:15,253][62373] Updated weights for policy 0, policy_version 95940 (0.0007) -[2023-10-17 04:06:15,612][62373] Updated weights for policy 0, policy_version 95950 (0.0009) -[2023-10-17 04:06:15,867][62408] Updated weights for policy 1, policy_version 95240 (0.0008) -[2023-10-17 04:06:15,984][62373] Updated weights for policy 0, policy_version 95960 (0.0010) -[2023-10-17 04:06:16,244][62408] Updated weights for policy 1, policy_version 95250 (0.0008) -[2023-10-17 04:06:16,609][62408] Updated weights for policy 1, policy_version 95260 (0.0009) -[2023-10-17 04:06:17,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 195821568. Throughput: 0: 1763.2, 1: 1740.0. Samples: 48961154. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-10-17 04:06:17,215][61453] Avg episode reward: [(0, '10.230'), (1, '11.930')] -[2023-10-17 04:06:19,775][62373] Updated weights for policy 0, policy_version 95970 (0.0009) -[2023-10-17 04:06:20,138][62373] Updated weights for policy 0, policy_version 95980 (0.0009) -[2023-10-17 04:06:20,429][62408] Updated weights for policy 1, policy_version 95270 (0.0008) -[2023-10-17 04:06:20,516][62373] Updated weights for policy 0, policy_version 95990 (0.0007) -[2023-10-17 04:06:20,815][62408] Updated weights for policy 1, policy_version 95280 (0.0009) -[2023-10-17 04:06:20,870][62373] Updated weights for policy 0, policy_version 96000 (0.0007) -[2023-10-17 04:06:21,197][62408] Updated weights for policy 1, policy_version 95290 (0.0009) -[2023-10-17 04:06:22,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 195887104. Throughput: 0: 1785.3, 1: 1777.8. Samples: 48973326. Policy #0 lag: (min: 25.0, avg: 38.2, max: 57.0) -[2023-10-17 04:06:22,215][61453] Avg episode reward: [(0, '10.320'), (1, '11.110')] -[2023-10-17 04:06:24,669][62373] Updated weights for policy 0, policy_version 96010 (0.0008) -[2023-10-17 04:06:24,956][62408] Updated weights for policy 1, policy_version 95300 (0.0007) -[2023-10-17 04:06:25,030][62373] Updated weights for policy 0, policy_version 96020 (0.0007) -[2023-10-17 04:06:25,318][62408] Updated weights for policy 1, policy_version 95310 (0.0008) -[2023-10-17 04:06:25,405][62373] Updated weights for policy 0, policy_version 96030 (0.0008) -[2023-10-17 04:06:25,681][62408] Updated weights for policy 1, policy_version 95320 (0.0007) -[2023-10-17 04:06:27,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 195952640. Throughput: 0: 1764.0, 1: 1751.8. Samples: 48992928. Policy #0 lag: (min: 25.0, avg: 38.2, max: 57.0) -[2023-10-17 04:06:27,214][61453] Avg episode reward: [(0, '10.440'), (1, '10.540')] -[2023-10-17 04:06:29,263][62373] Updated weights for policy 0, policy_version 96040 (0.0008) -[2023-10-17 04:06:29,463][62408] Updated weights for policy 1, policy_version 95330 (0.0009) -[2023-10-17 04:06:29,629][62373] Updated weights for policy 0, policy_version 96050 (0.0007) -[2023-10-17 04:06:29,825][62408] Updated weights for policy 1, policy_version 95340 (0.0010) -[2023-10-17 04:06:30,006][62373] Updated weights for policy 0, policy_version 96060 (0.0008) -[2023-10-17 04:06:30,199][62408] Updated weights for policy 1, policy_version 95350 (0.0011) -[2023-10-17 04:06:30,563][62408] Updated weights for policy 1, policy_version 95360 (0.0011) -[2023-10-17 04:06:32,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 196018176. Throughput: 0: 1761.8, 1: 1746.4. Samples: 49014882. Policy #0 lag: (min: 25.0, avg: 38.2, max: 57.0) -[2023-10-17 04:06:32,215][61453] Avg episode reward: [(0, '10.430'), (1, '10.520')] -[2023-10-17 04:06:33,784][62373] Updated weights for policy 0, policy_version 96070 (0.0007) -[2023-10-17 04:06:34,150][62373] Updated weights for policy 0, policy_version 96080 (0.0009) -[2023-10-17 04:06:34,298][62408] Updated weights for policy 1, policy_version 95370 (0.0007) -[2023-10-17 04:06:34,512][62373] Updated weights for policy 0, policy_version 96090 (0.0008) -[2023-10-17 04:06:34,655][62408] Updated weights for policy 1, policy_version 95380 (0.0009) -[2023-10-17 04:06:35,020][62408] Updated weights for policy 1, policy_version 95390 (0.0010) -[2023-10-17 04:06:37,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 196083712. Throughput: 0: 1763.8, 1: 1758.9. Samples: 49024962. Policy #0 lag: (min: 25.0, avg: 38.2, max: 57.0) -[2023-10-17 04:06:37,215][61453] Avg episode reward: [(0, '10.840'), (1, '10.640')] -[2023-10-17 04:06:38,315][62373] Updated weights for policy 0, policy_version 96100 (0.0009) -[2023-10-17 04:06:38,684][62373] Updated weights for policy 0, policy_version 96110 (0.0008) -[2023-10-17 04:06:38,919][62408] Updated weights for policy 1, policy_version 95400 (0.0009) -[2023-10-17 04:06:39,060][62373] Updated weights for policy 0, policy_version 96120 (0.0009) -[2023-10-17 04:06:39,283][62408] Updated weights for policy 1, policy_version 95410 (0.0007) -[2023-10-17 04:06:39,658][62408] Updated weights for policy 1, policy_version 95420 (0.0011) -[2023-10-17 04:06:42,214][61453] Fps is (10 sec: 13107.6, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 196149248. Throughput: 0: 1769.3, 1: 1750.3. Samples: 49046688. Policy #0 lag: (min: 25.0, avg: 38.2, max: 57.0) -[2023-10-17 04:06:42,214][61453] Avg episode reward: [(0, '11.230'), (1, '11.290')] -[2023-10-17 04:06:42,779][62373] Updated weights for policy 0, policy_version 96130 (0.0009) -[2023-10-17 04:06:43,147][62373] Updated weights for policy 0, policy_version 96140 (0.0007) -[2023-10-17 04:06:43,511][62373] Updated weights for policy 0, policy_version 96150 (0.0009) -[2023-10-17 04:06:43,515][62408] Updated weights for policy 1, policy_version 95430 (0.0008) -[2023-10-17 04:06:43,884][62408] Updated weights for policy 1, policy_version 95440 (0.0008) -[2023-10-17 04:06:43,888][62373] Updated weights for policy 0, policy_version 96160 (0.0008) -[2023-10-17 04:06:44,251][62408] Updated weights for policy 1, policy_version 95450 (0.0008) -[2023-10-17 04:06:47,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 196214784. Throughput: 0: 1781.2, 1: 1759.6. Samples: 49068736. Policy #0 lag: (min: 25.0, avg: 38.2, max: 57.0) -[2023-10-17 04:06:47,215][61453] Avg episode reward: [(0, '10.770'), (1, '10.740')] -[2023-10-17 04:06:47,795][62373] Updated weights for policy 0, policy_version 96170 (0.0008) -[2023-10-17 04:06:47,992][62408] Updated weights for policy 1, policy_version 95460 (0.0009) -[2023-10-17 04:06:48,169][62373] Updated weights for policy 0, policy_version 96180 (0.0008) -[2023-10-17 04:06:48,348][62408] Updated weights for policy 1, policy_version 95470 (0.0009) -[2023-10-17 04:06:48,536][62373] Updated weights for policy 0, policy_version 96190 (0.0008) -[2023-10-17 04:06:48,713][62408] Updated weights for policy 1, policy_version 95480 (0.0009) -[2023-10-17 04:06:52,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 196280320. Throughput: 0: 1762.6, 1: 1750.4. Samples: 49078010. Policy #0 lag: (min: 25.0, avg: 38.2, max: 57.0) -[2023-10-17 04:06:52,215][61453] Avg episode reward: [(0, '11.350'), (1, '11.000')] -[2023-10-17 04:06:52,446][62373] Updated weights for policy 0, policy_version 96200 (0.0009) -[2023-10-17 04:06:52,813][62408] Updated weights for policy 1, policy_version 95490 (0.0010) -[2023-10-17 04:06:52,814][62373] Updated weights for policy 0, policy_version 96210 (0.0007) -[2023-10-17 04:06:53,177][62373] Updated weights for policy 0, policy_version 96220 (0.0010) -[2023-10-17 04:06:53,187][62408] Updated weights for policy 1, policy_version 95500 (0.0008) -[2023-10-17 04:06:53,546][62408] Updated weights for policy 1, policy_version 95510 (0.0007) -[2023-10-17 04:06:53,913][62408] Updated weights for policy 1, policy_version 95520 (0.0007) -[2023-10-17 04:06:56,961][62373] Updated weights for policy 0, policy_version 96230 (0.0008) -[2023-10-17 04:06:57,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 196345856. Throughput: 0: 1776.1, 1: 1756.4. Samples: 49100198. Policy #0 lag: (min: 25.0, avg: 38.2, max: 57.0) -[2023-10-17 04:06:57,215][61453] Avg episode reward: [(0, '11.520'), (1, '11.870')] -[2023-10-17 04:06:57,340][62373] Updated weights for policy 0, policy_version 96240 (0.0009) -[2023-10-17 04:06:57,584][62408] Updated weights for policy 1, policy_version 95530 (0.0008) -[2023-10-17 04:06:57,708][62373] Updated weights for policy 0, policy_version 96250 (0.0008) -[2023-10-17 04:06:57,951][62408] Updated weights for policy 1, policy_version 95540 (0.0007) -[2023-10-17 04:06:58,318][62408] Updated weights for policy 1, policy_version 95550 (0.0007) -[2023-10-17 04:07:01,439][62373] Updated weights for policy 0, policy_version 96260 (0.0008) -[2023-10-17 04:07:01,802][62373] Updated weights for policy 0, policy_version 96270 (0.0008) -[2023-10-17 04:07:01,982][62408] Updated weights for policy 1, policy_version 95560 (0.0008) -[2023-10-17 04:07:02,171][62373] Updated weights for policy 0, policy_version 96280 (0.0008) -[2023-10-17 04:07:02,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 196411392. Throughput: 0: 1780.6, 1: 1787.2. Samples: 49121704. Policy #0 lag: (min: 25.0, avg: 38.2, max: 57.0) -[2023-10-17 04:07:02,215][61453] Avg episode reward: [(0, '11.250'), (1, '12.750')] -[2023-10-17 04:07:02,351][62408] Updated weights for policy 1, policy_version 95570 (0.0007) -[2023-10-17 04:07:02,719][62408] Updated weights for policy 1, policy_version 95580 (0.0009) -[2023-10-17 04:07:05,930][62373] Updated weights for policy 0, policy_version 96290 (0.0008) -[2023-10-17 04:07:06,308][62373] Updated weights for policy 0, policy_version 96300 (0.0007) -[2023-10-17 04:07:06,678][62373] Updated weights for policy 0, policy_version 96310 (0.0008) -[2023-10-17 04:07:06,825][62408] Updated weights for policy 1, policy_version 95590 (0.0008) -[2023-10-17 04:07:07,039][62373] Updated weights for policy 0, policy_version 96320 (0.0008) -[2023-10-17 04:07:07,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 196509696. Throughput: 0: 1774.0, 1: 1756.7. Samples: 49132208. Policy #0 lag: (min: 25.0, avg: 38.2, max: 57.0) -[2023-10-17 04:07:07,215][61453] Avg episode reward: [(0, '11.170'), (1, '12.750')] -[2023-10-17 04:07:07,223][62408] Updated weights for policy 1, policy_version 95600 (0.0009) -[2023-10-17 04:07:07,584][62408] Updated weights for policy 1, policy_version 95610 (0.0007) -[2023-10-17 04:07:10,903][62373] Updated weights for policy 0, policy_version 96330 (0.0010) -[2023-10-17 04:07:11,278][62373] Updated weights for policy 0, policy_version 96340 (0.0007) -[2023-10-17 04:07:11,297][62408] Updated weights for policy 1, policy_version 95620 (0.0007) -[2023-10-17 04:07:11,640][62373] Updated weights for policy 0, policy_version 96350 (0.0007) -[2023-10-17 04:07:11,657][62408] Updated weights for policy 1, policy_version 95630 (0.0007) -[2023-10-17 04:07:12,033][62408] Updated weights for policy 1, policy_version 95640 (0.0009) -[2023-10-17 04:07:12,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 196575232. Throughput: 0: 1787.1, 1: 1782.7. Samples: 49153572. Policy #0 lag: (min: 25.0, avg: 38.2, max: 57.0) -[2023-10-17 04:07:12,215][61453] Avg episode reward: [(0, '10.960'), (1, '12.740')] -[2023-10-17 04:07:15,520][62373] Updated weights for policy 0, policy_version 96360 (0.0010) -[2023-10-17 04:07:15,824][62408] Updated weights for policy 1, policy_version 95650 (0.0010) -[2023-10-17 04:07:15,895][62373] Updated weights for policy 0, policy_version 96370 (0.0010) -[2023-10-17 04:07:16,178][62408] Updated weights for policy 1, policy_version 95660 (0.0008) -[2023-10-17 04:07:16,268][62373] Updated weights for policy 0, policy_version 96380 (0.0008) -[2023-10-17 04:07:16,557][62408] Updated weights for policy 1, policy_version 95670 (0.0008) -[2023-10-17 04:07:16,921][62408] Updated weights for policy 1, policy_version 95680 (0.0007) -[2023-10-17 04:07:17,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 196673536. Throughput: 0: 1768.1, 1: 1757.8. Samples: 49173550. Policy #0 lag: (min: 25.0, avg: 38.2, max: 57.0) -[2023-10-17 04:07:17,215][61453] Avg episode reward: [(0, '10.760'), (1, '12.210')] -[2023-10-17 04:07:20,162][62373] Updated weights for policy 0, policy_version 96390 (0.0010) -[2023-10-17 04:07:20,540][62373] Updated weights for policy 0, policy_version 96400 (0.0007) -[2023-10-17 04:07:20,760][62408] Updated weights for policy 1, policy_version 95690 (0.0008) -[2023-10-17 04:07:20,898][62373] Updated weights for policy 0, policy_version 96410 (0.0010) -[2023-10-17 04:07:21,131][62408] Updated weights for policy 1, policy_version 95700 (0.0008) -[2023-10-17 04:07:21,501][62408] Updated weights for policy 1, policy_version 95710 (0.0007) -[2023-10-17 04:07:22,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 196739072. Throughput: 0: 1799.8, 1: 1778.3. Samples: 49185974. Policy #0 lag: (min: 30.0, avg: 47.1, max: 62.0) -[2023-10-17 04:07:22,215][61453] Avg episode reward: [(0, '10.910'), (1, '12.440')] -[2023-10-17 04:07:24,716][62373] Updated weights for policy 0, policy_version 96420 (0.0007) -[2023-10-17 04:07:25,085][62373] Updated weights for policy 0, policy_version 96430 (0.0007) -[2023-10-17 04:07:25,271][62408] Updated weights for policy 1, policy_version 95720 (0.0008) -[2023-10-17 04:07:25,452][62373] Updated weights for policy 0, policy_version 96440 (0.0007) -[2023-10-17 04:07:25,641][62408] Updated weights for policy 1, policy_version 95730 (0.0008) -[2023-10-17 04:07:26,010][62408] Updated weights for policy 1, policy_version 95740 (0.0008) -[2023-10-17 04:07:27,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 196804608. Throughput: 0: 1761.7, 1: 1768.6. Samples: 49205550. Policy #0 lag: (min: 30.0, avg: 47.1, max: 62.0) -[2023-10-17 04:07:27,215][61453] Avg episode reward: [(0, '11.620'), (1, '12.520')] -[2023-10-17 04:07:29,335][62373] Updated weights for policy 0, policy_version 96450 (0.0008) -[2023-10-17 04:07:29,698][62373] Updated weights for policy 0, policy_version 96460 (0.0007) -[2023-10-17 04:07:29,903][62408] Updated weights for policy 1, policy_version 95750 (0.0009) -[2023-10-17 04:07:30,059][62373] Updated weights for policy 0, policy_version 96470 (0.0008) -[2023-10-17 04:07:30,266][62408] Updated weights for policy 1, policy_version 95760 (0.0009) -[2023-10-17 04:07:30,426][62373] Updated weights for policy 0, policy_version 96480 (0.0007) -[2023-10-17 04:07:30,633][62408] Updated weights for policy 1, policy_version 95770 (0.0010) -[2023-10-17 04:07:32,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 196870144. Throughput: 0: 1766.0, 1: 1755.1. Samples: 49227182. Policy #0 lag: (min: 30.0, avg: 47.1, max: 62.0) -[2023-10-17 04:07:32,215][61453] Avg episode reward: [(0, '11.830'), (1, '12.210')] -[2023-10-17 04:07:32,226][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000096480_98795520.pth... -[2023-10-17 04:07:32,226][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000095776_98074624.pth... -[2023-10-17 04:07:32,258][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000094816_97091584.pth -[2023-10-17 04:07:32,263][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000094112_96370688.pth -[2023-10-17 04:07:34,209][62373] Updated weights for policy 0, policy_version 96490 (0.0007) -[2023-10-17 04:07:34,470][62408] Updated weights for policy 1, policy_version 95780 (0.0009) -[2023-10-17 04:07:34,580][62373] Updated weights for policy 0, policy_version 96500 (0.0009) -[2023-10-17 04:07:34,832][62408] Updated weights for policy 1, policy_version 95790 (0.0009) -[2023-10-17 04:07:34,957][62373] Updated weights for policy 0, policy_version 96510 (0.0010) -[2023-10-17 04:07:35,203][62408] Updated weights for policy 1, policy_version 95800 (0.0008) -[2023-10-17 04:07:37,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 196935680. Throughput: 0: 1773.5, 1: 1776.9. Samples: 49237778. Policy #0 lag: (min: 30.0, avg: 47.1, max: 62.0) -[2023-10-17 04:07:37,215][61453] Avg episode reward: [(0, '11.200'), (1, '12.160')] -[2023-10-17 04:07:38,858][62373] Updated weights for policy 0, policy_version 96520 (0.0009) -[2023-10-17 04:07:39,107][62408] Updated weights for policy 1, policy_version 95810 (0.0009) -[2023-10-17 04:07:39,235][62373] Updated weights for policy 0, policy_version 96530 (0.0009) -[2023-10-17 04:07:39,471][62408] Updated weights for policy 1, policy_version 95820 (0.0009) -[2023-10-17 04:07:39,608][62373] Updated weights for policy 0, policy_version 96540 (0.0008) -[2023-10-17 04:07:39,836][62408] Updated weights for policy 1, policy_version 95830 (0.0010) -[2023-10-17 04:07:40,201][62408] Updated weights for policy 1, policy_version 95840 (0.0008) -[2023-10-17 04:07:42,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 197001216. Throughput: 0: 1766.7, 1: 1761.3. Samples: 49258962. Policy #0 lag: (min: 30.0, avg: 47.1, max: 62.0) -[2023-10-17 04:07:42,215][61453] Avg episode reward: [(0, '11.300'), (1, '11.800')] -[2023-10-17 04:07:43,422][62373] Updated weights for policy 0, policy_version 96550 (0.0009) -[2023-10-17 04:07:43,797][62373] Updated weights for policy 0, policy_version 96560 (0.0008) -[2023-10-17 04:07:43,995][62408] Updated weights for policy 1, policy_version 95850 (0.0008) -[2023-10-17 04:07:44,161][62373] Updated weights for policy 0, policy_version 96570 (0.0009) -[2023-10-17 04:07:44,353][62408] Updated weights for policy 1, policy_version 95860 (0.0008) -[2023-10-17 04:07:44,726][62408] Updated weights for policy 1, policy_version 95870 (0.0008) -[2023-10-17 04:07:47,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 197066752. Throughput: 0: 1777.0, 1: 1758.2. Samples: 49280788. Policy #0 lag: (min: 30.0, avg: 47.1, max: 62.0) -[2023-10-17 04:07:47,215][61453] Avg episode reward: [(0, '11.980'), (1, '12.120')] -[2023-10-17 04:07:47,846][62373] Updated weights for policy 0, policy_version 96580 (0.0008) -[2023-10-17 04:07:48,211][62373] Updated weights for policy 0, policy_version 96590 (0.0008) -[2023-10-17 04:07:48,580][62373] Updated weights for policy 0, policy_version 96600 (0.0008) -[2023-10-17 04:07:48,633][62408] Updated weights for policy 1, policy_version 95880 (0.0007) -[2023-10-17 04:07:49,008][62408] Updated weights for policy 1, policy_version 95890 (0.0009) -[2023-10-17 04:07:49,377][62408] Updated weights for policy 1, policy_version 95900 (0.0010) -[2023-10-17 04:07:52,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 197132288. Throughput: 0: 1761.1, 1: 1753.5. Samples: 49290366. Policy #0 lag: (min: 30.0, avg: 47.1, max: 62.0) -[2023-10-17 04:07:52,214][61453] Avg episode reward: [(0, '11.660'), (1, '11.620')] -[2023-10-17 04:07:52,353][62373] Updated weights for policy 0, policy_version 96610 (0.0007) -[2023-10-17 04:07:52,717][62373] Updated weights for policy 0, policy_version 96620 (0.0007) -[2023-10-17 04:07:53,097][62373] Updated weights for policy 0, policy_version 96630 (0.0009) -[2023-10-17 04:07:53,351][62408] Updated weights for policy 1, policy_version 95910 (0.0007) -[2023-10-17 04:07:53,458][62373] Updated weights for policy 0, policy_version 96640 (0.0009) -[2023-10-17 04:07:53,744][62408] Updated weights for policy 1, policy_version 95920 (0.0008) -[2023-10-17 04:07:54,115][62408] Updated weights for policy 1, policy_version 95930 (0.0010) -[2023-10-17 04:07:57,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 197197824. Throughput: 0: 1772.0, 1: 1750.7. Samples: 49312094. Policy #0 lag: (min: 30.0, avg: 47.1, max: 62.0) -[2023-10-17 04:07:57,215][61453] Avg episode reward: [(0, '11.780'), (1, '11.040')] -[2023-10-17 04:07:57,218][62373] Updated weights for policy 0, policy_version 96650 (0.0007) -[2023-10-17 04:07:57,589][62373] Updated weights for policy 0, policy_version 96660 (0.0007) -[2023-10-17 04:07:57,894][62408] Updated weights for policy 1, policy_version 95940 (0.0007) -[2023-10-17 04:07:57,961][62373] Updated weights for policy 0, policy_version 96670 (0.0007) -[2023-10-17 04:07:58,257][62408] Updated weights for policy 1, policy_version 95950 (0.0010) -[2023-10-17 04:07:58,633][62408] Updated weights for policy 1, policy_version 95960 (0.0008) -[2023-10-17 04:08:01,573][62373] Updated weights for policy 0, policy_version 96680 (0.0007) -[2023-10-17 04:08:01,948][62373] Updated weights for policy 0, policy_version 96690 (0.0008) -[2023-10-17 04:08:02,214][61453] Fps is (10 sec: 13106.8, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 197263360. Throughput: 0: 1776.5, 1: 1774.8. Samples: 49333360. Policy #0 lag: (min: 30.0, avg: 47.1, max: 62.0) -[2023-10-17 04:08:02,215][61453] Avg episode reward: [(0, '11.910'), (1, '10.680')] -[2023-10-17 04:08:02,312][62373] Updated weights for policy 0, policy_version 96700 (0.0008) -[2023-10-17 04:08:02,359][62408] Updated weights for policy 1, policy_version 95970 (0.0009) -[2023-10-17 04:08:02,724][62408] Updated weights for policy 1, policy_version 95980 (0.0009) -[2023-10-17 04:08:03,086][62408] Updated weights for policy 1, policy_version 95990 (0.0008) -[2023-10-17 04:08:03,450][62408] Updated weights for policy 1, policy_version 96000 (0.0008) -[2023-10-17 04:08:06,058][62373] Updated weights for policy 0, policy_version 96710 (0.0009) -[2023-10-17 04:08:06,424][62373] Updated weights for policy 0, policy_version 96720 (0.0011) -[2023-10-17 04:08:06,793][62373] Updated weights for policy 0, policy_version 96730 (0.0012) -[2023-10-17 04:08:07,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 197361664. Throughput: 0: 1763.1, 1: 1744.2. Samples: 49343802. Policy #0 lag: (min: 30.0, avg: 47.1, max: 62.0) -[2023-10-17 04:08:07,215][61453] Avg episode reward: [(0, '12.300'), (1, '10.460')] -[2023-10-17 04:08:07,365][62408] Updated weights for policy 1, policy_version 96010 (0.0007) -[2023-10-17 04:08:07,740][62408] Updated weights for policy 1, policy_version 96020 (0.0009) -[2023-10-17 04:08:08,105][62408] Updated weights for policy 1, policy_version 96030 (0.0008) -[2023-10-17 04:08:10,800][62373] Updated weights for policy 0, policy_version 96740 (0.0011) -[2023-10-17 04:08:11,168][62373] Updated weights for policy 0, policy_version 96750 (0.0008) -[2023-10-17 04:08:11,544][62373] Updated weights for policy 0, policy_version 96760 (0.0008) -[2023-10-17 04:08:11,917][62408] Updated weights for policy 1, policy_version 96040 (0.0010) -[2023-10-17 04:08:12,214][61453] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 197427200. Throughput: 0: 1788.4, 1: 1763.3. Samples: 49365378. Policy #0 lag: (min: 30.0, avg: 47.1, max: 62.0) -[2023-10-17 04:08:12,215][61453] Avg episode reward: [(0, '12.370'), (1, '10.830')] -[2023-10-17 04:08:12,295][62408] Updated weights for policy 1, policy_version 96050 (0.0011) -[2023-10-17 04:08:12,666][62408] Updated weights for policy 1, policy_version 96060 (0.0007) -[2023-10-17 04:08:15,393][62373] Updated weights for policy 0, policy_version 96770 (0.0007) -[2023-10-17 04:08:15,750][62373] Updated weights for policy 0, policy_version 96780 (0.0008) -[2023-10-17 04:08:16,130][62373] Updated weights for policy 0, policy_version 96790 (0.0008) -[2023-10-17 04:08:16,497][62373] Updated weights for policy 0, policy_version 96800 (0.0009) -[2023-10-17 04:08:16,506][62408] Updated weights for policy 1, policy_version 96070 (0.0009) -[2023-10-17 04:08:16,875][62408] Updated weights for policy 1, policy_version 96080 (0.0010) -[2023-10-17 04:08:17,214][61453] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 197492736. Throughput: 0: 1760.6, 1: 1761.8. Samples: 49385690. Policy #0 lag: (min: 30.0, avg: 47.1, max: 62.0) -[2023-10-17 04:08:17,215][61453] Avg episode reward: [(0, '12.340'), (1, '10.900')] -[2023-10-17 04:08:17,240][62408] Updated weights for policy 1, policy_version 96090 (0.0009) -[2023-10-17 04:08:20,411][62373] Updated weights for policy 0, policy_version 96810 (0.0008) -[2023-10-17 04:08:20,776][62373] Updated weights for policy 0, policy_version 96820 (0.0007) -[2023-10-17 04:08:21,047][62408] Updated weights for policy 1, policy_version 96100 (0.0008) -[2023-10-17 04:08:21,148][62373] Updated weights for policy 0, policy_version 96830 (0.0008) -[2023-10-17 04:08:21,419][62408] Updated weights for policy 1, policy_version 96110 (0.0008) -[2023-10-17 04:08:21,778][62408] Updated weights for policy 1, policy_version 96120 (0.0007) -[2023-10-17 04:08:22,214][61453] Fps is (10 sec: 16383.5, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 197591040. Throughput: 0: 1788.3, 1: 1756.5. Samples: 49397296. Policy #0 lag: (min: 22.0, avg: 24.9, max: 54.0) -[2023-10-17 04:08:22,216][61453] Avg episode reward: [(0, '12.360'), (1, '10.520')] -[2023-10-17 04:08:24,913][62373] Updated weights for policy 0, policy_version 96840 (0.0008) -[2023-10-17 04:08:25,284][62373] Updated weights for policy 0, policy_version 96850 (0.0008) -[2023-10-17 04:08:25,641][62373] Updated weights for policy 0, policy_version 96860 (0.0009) -[2023-10-17 04:08:25,677][62408] Updated weights for policy 1, policy_version 96130 (0.0007) -[2023-10-17 04:08:26,052][62408] Updated weights for policy 1, policy_version 96140 (0.0007) -[2023-10-17 04:08:26,428][62408] Updated weights for policy 1, policy_version 96150 (0.0009) -[2023-10-17 04:08:26,793][62408] Updated weights for policy 1, policy_version 96160 (0.0008) -[2023-10-17 04:08:27,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 197656576. Throughput: 0: 1759.4, 1: 1764.6. Samples: 49417542. Policy #0 lag: (min: 22.0, avg: 24.9, max: 54.0) -[2023-10-17 04:08:27,215][61453] Avg episode reward: [(0, '12.270'), (1, '10.240')] -[2023-10-17 04:08:29,444][62373] Updated weights for policy 0, policy_version 96870 (0.0008) -[2023-10-17 04:08:29,825][62373] Updated weights for policy 0, policy_version 96880 (0.0011) -[2023-10-17 04:08:30,185][62373] Updated weights for policy 0, policy_version 96890 (0.0009) -[2023-10-17 04:08:30,625][62408] Updated weights for policy 1, policy_version 96170 (0.0009) -[2023-10-17 04:08:30,991][62408] Updated weights for policy 1, policy_version 96180 (0.0009) -[2023-10-17 04:08:31,352][62408] Updated weights for policy 1, policy_version 96190 (0.0007) -[2023-10-17 04:08:32,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 197722112. Throughput: 0: 1763.3, 1: 1744.1. Samples: 49438624. Policy #0 lag: (min: 22.0, avg: 24.9, max: 54.0) -[2023-10-17 04:08:32,215][61453] Avg episode reward: [(0, '12.460'), (1, '10.760')] -[2023-10-17 04:08:34,003][62373] Updated weights for policy 0, policy_version 96900 (0.0009) -[2023-10-17 04:08:34,364][62373] Updated weights for policy 0, policy_version 96910 (0.0007) -[2023-10-17 04:08:34,739][62373] Updated weights for policy 0, policy_version 96920 (0.0008) -[2023-10-17 04:08:34,989][62408] Updated weights for policy 1, policy_version 96200 (0.0010) -[2023-10-17 04:08:35,357][62408] Updated weights for policy 1, policy_version 96210 (0.0010) -[2023-10-17 04:08:35,716][62408] Updated weights for policy 1, policy_version 96220 (0.0011) -[2023-10-17 04:08:37,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 197787648. Throughput: 0: 1765.4, 1: 1775.8. Samples: 49449720. Policy #0 lag: (min: 22.0, avg: 24.9, max: 54.0) -[2023-10-17 04:08:37,215][61453] Avg episode reward: [(0, '13.010'), (1, '11.450')] -[2023-10-17 04:08:38,478][62373] Updated weights for policy 0, policy_version 96930 (0.0007) -[2023-10-17 04:08:38,850][62373] Updated weights for policy 0, policy_version 96940 (0.0007) -[2023-10-17 04:08:39,229][62373] Updated weights for policy 0, policy_version 96950 (0.0007) -[2023-10-17 04:08:39,597][62373] Updated weights for policy 0, policy_version 96960 (0.0008) -[2023-10-17 04:08:39,792][62408] Updated weights for policy 1, policy_version 96230 (0.0008) -[2023-10-17 04:08:40,157][62408] Updated weights for policy 1, policy_version 96240 (0.0011) -[2023-10-17 04:08:40,526][62408] Updated weights for policy 1, policy_version 96250 (0.0011) -[2023-10-17 04:08:42,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 197853184. Throughput: 0: 1771.1, 1: 1752.8. Samples: 49470668. Policy #0 lag: (min: 22.0, avg: 24.9, max: 54.0) -[2023-10-17 04:08:42,215][61453] Avg episode reward: [(0, '12.870'), (1, '11.740')] -[2023-10-17 04:08:43,342][62373] Updated weights for policy 0, policy_version 96970 (0.0007) -[2023-10-17 04:08:43,707][62373] Updated weights for policy 0, policy_version 96980 (0.0010) -[2023-10-17 04:08:44,084][62373] Updated weights for policy 0, policy_version 96990 (0.0008) -[2023-10-17 04:08:44,518][62408] Updated weights for policy 1, policy_version 96260 (0.0011) -[2023-10-17 04:08:44,918][62408] Updated weights for policy 1, policy_version 96270 (0.0008) -[2023-10-17 04:08:45,277][62408] Updated weights for policy 1, policy_version 96280 (0.0010) -[2023-10-17 04:08:47,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 197918720. Throughput: 0: 1788.0, 1: 1752.1. Samples: 49492664. Policy #0 lag: (min: 22.0, avg: 24.9, max: 54.0) -[2023-10-17 04:08:47,215][61453] Avg episode reward: [(0, '12.000'), (1, '12.550')] -[2023-10-17 04:08:47,915][62373] Updated weights for policy 0, policy_version 97000 (0.0009) -[2023-10-17 04:08:48,291][62373] Updated weights for policy 0, policy_version 97010 (0.0008) -[2023-10-17 04:08:48,650][62373] Updated weights for policy 0, policy_version 97020 (0.0007) -[2023-10-17 04:08:49,009][62408] Updated weights for policy 1, policy_version 96290 (0.0009) -[2023-10-17 04:08:49,380][62408] Updated weights for policy 1, policy_version 96300 (0.0008) -[2023-10-17 04:08:49,741][62408] Updated weights for policy 1, policy_version 96310 (0.0007) -[2023-10-17 04:08:50,117][62408] Updated weights for policy 1, policy_version 96320 (0.0008) -[2023-10-17 04:08:52,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.4, 300 sec: 14106.9). Total num frames: 197984256. Throughput: 0: 1768.2, 1: 1759.3. Samples: 49502538. Policy #0 lag: (min: 22.0, avg: 24.9, max: 54.0) -[2023-10-17 04:08:52,215][61453] Avg episode reward: [(0, '11.460'), (1, '11.760')] -[2023-10-17 04:08:52,528][62373] Updated weights for policy 0, policy_version 97030 (0.0009) -[2023-10-17 04:08:52,896][62373] Updated weights for policy 0, policy_version 97040 (0.0009) -[2023-10-17 04:08:53,256][62373] Updated weights for policy 0, policy_version 97050 (0.0008) -[2023-10-17 04:08:54,131][62408] Updated weights for policy 1, policy_version 96330 (0.0008) -[2023-10-17 04:08:54,504][62408] Updated weights for policy 1, policy_version 96340 (0.0010) -[2023-10-17 04:08:54,871][62408] Updated weights for policy 1, policy_version 96350 (0.0009) -[2023-10-17 04:08:56,917][62373] Updated weights for policy 0, policy_version 97060 (0.0009) -[2023-10-17 04:08:57,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 198049792. Throughput: 0: 1779.7, 1: 1749.8. Samples: 49524206. Policy #0 lag: (min: 22.0, avg: 24.9, max: 54.0) -[2023-10-17 04:08:57,214][61453] Avg episode reward: [(0, '11.320'), (1, '11.660')] -[2023-10-17 04:08:57,294][62373] Updated weights for policy 0, policy_version 97070 (0.0009) -[2023-10-17 04:08:57,661][62373] Updated weights for policy 0, policy_version 97080 (0.0008) -[2023-10-17 04:08:58,779][62408] Updated weights for policy 1, policy_version 96360 (0.0008) -[2023-10-17 04:08:59,146][62408] Updated weights for policy 1, policy_version 96370 (0.0011) -[2023-10-17 04:08:59,510][62408] Updated weights for policy 1, policy_version 96380 (0.0011) -[2023-10-17 04:09:01,350][62373] Updated weights for policy 0, policy_version 97090 (0.0008) -[2023-10-17 04:09:01,717][62373] Updated weights for policy 0, policy_version 97100 (0.0010) -[2023-10-17 04:09:02,101][62373] Updated weights for policy 0, policy_version 97110 (0.0007) -[2023-10-17 04:09:02,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 198115328. Throughput: 0: 1794.6, 1: 1763.3. Samples: 49545792. Policy #0 lag: (min: 22.0, avg: 24.9, max: 54.0) -[2023-10-17 04:09:02,214][61453] Avg episode reward: [(0, '11.620'), (1, '12.520')] -[2023-10-17 04:09:02,467][62373] Updated weights for policy 0, policy_version 97120 (0.0008) -[2023-10-17 04:09:03,321][62408] Updated weights for policy 1, policy_version 96390 (0.0010) -[2023-10-17 04:09:03,688][62408] Updated weights for policy 1, policy_version 96400 (0.0009) -[2023-10-17 04:09:04,058][62408] Updated weights for policy 1, policy_version 96410 (0.0009) -[2023-10-17 04:09:06,280][62373] Updated weights for policy 0, policy_version 97130 (0.0010) -[2023-10-17 04:09:06,658][62373] Updated weights for policy 0, policy_version 97140 (0.0008) -[2023-10-17 04:09:07,030][62373] Updated weights for policy 0, policy_version 97150 (0.0008) -[2023-10-17 04:09:07,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 198213632. Throughput: 0: 1783.1, 1: 1749.0. Samples: 49556238. Policy #0 lag: (min: 22.0, avg: 24.9, max: 54.0) -[2023-10-17 04:09:07,214][61453] Avg episode reward: [(0, '11.680'), (1, '11.740')] -[2023-10-17 04:09:07,874][62408] Updated weights for policy 1, policy_version 96420 (0.0009) -[2023-10-17 04:09:08,248][62408] Updated weights for policy 1, policy_version 96430 (0.0008) -[2023-10-17 04:09:08,614][62408] Updated weights for policy 1, policy_version 96440 (0.0008) -[2023-10-17 04:09:10,768][62373] Updated weights for policy 0, policy_version 97160 (0.0009) -[2023-10-17 04:09:11,141][62373] Updated weights for policy 0, policy_version 97170 (0.0009) -[2023-10-17 04:09:11,509][62373] Updated weights for policy 0, policy_version 97180 (0.0008) -[2023-10-17 04:09:12,214][61453] Fps is (10 sec: 16383.9, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 198279168. Throughput: 0: 1804.2, 1: 1754.1. Samples: 49577662. Policy #0 lag: (min: 22.0, avg: 24.9, max: 54.0) -[2023-10-17 04:09:12,215][61453] Avg episode reward: [(0, '11.020'), (1, '12.010')] -[2023-10-17 04:09:12,375][62408] Updated weights for policy 1, policy_version 96450 (0.0008) -[2023-10-17 04:09:12,735][62408] Updated weights for policy 1, policy_version 96460 (0.0009) -[2023-10-17 04:09:13,108][62408] Updated weights for policy 1, policy_version 96470 (0.0008) -[2023-10-17 04:09:13,477][62408] Updated weights for policy 1, policy_version 96480 (0.0008) -[2023-10-17 04:09:15,335][62373] Updated weights for policy 0, policy_version 97190 (0.0008) -[2023-10-17 04:09:15,698][62373] Updated weights for policy 0, policy_version 97200 (0.0009) -[2023-10-17 04:09:16,069][62373] Updated weights for policy 0, policy_version 97210 (0.0009) -[2023-10-17 04:09:17,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 198344704. Throughput: 0: 1783.3, 1: 1774.9. Samples: 49598744. Policy #0 lag: (min: 22.0, avg: 24.9, max: 54.0) -[2023-10-17 04:09:17,215][61453] Avg episode reward: [(0, '11.380'), (1, '12.370')] -[2023-10-17 04:09:17,430][62408] Updated weights for policy 1, policy_version 96490 (0.0008) -[2023-10-17 04:09:17,785][62408] Updated weights for policy 1, policy_version 96500 (0.0008) -[2023-10-17 04:09:18,143][62408] Updated weights for policy 1, policy_version 96510 (0.0008) -[2023-10-17 04:09:19,723][62373] Updated weights for policy 0, policy_version 97220 (0.0008) -[2023-10-17 04:09:20,096][62373] Updated weights for policy 0, policy_version 97230 (0.0009) -[2023-10-17 04:09:20,464][62373] Updated weights for policy 0, policy_version 97240 (0.0008) -[2023-10-17 04:09:21,944][62408] Updated weights for policy 1, policy_version 96520 (0.0008) -[2023-10-17 04:09:22,214][61453] Fps is (10 sec: 13107.0, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 198410240. Throughput: 0: 1810.0, 1: 1746.0. Samples: 49609740. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-17 04:09:22,215][61453] Avg episode reward: [(0, '11.310'), (1, '12.360')] -[2023-10-17 04:09:22,311][62408] Updated weights for policy 1, policy_version 96530 (0.0007) -[2023-10-17 04:09:22,682][62408] Updated weights for policy 1, policy_version 96540 (0.0007) -[2023-10-17 04:09:24,194][62373] Updated weights for policy 0, policy_version 97250 (0.0009) -[2023-10-17 04:09:24,563][62373] Updated weights for policy 0, policy_version 97260 (0.0008) -[2023-10-17 04:09:24,941][62373] Updated weights for policy 0, policy_version 97270 (0.0009) -[2023-10-17 04:09:25,308][62373] Updated weights for policy 0, policy_version 97280 (0.0010) -[2023-10-17 04:09:26,405][62408] Updated weights for policy 1, policy_version 96550 (0.0009) -[2023-10-17 04:09:26,777][62408] Updated weights for policy 1, policy_version 96560 (0.0010) -[2023-10-17 04:09:27,143][62408] Updated weights for policy 1, policy_version 96570 (0.0010) -[2023-10-17 04:09:27,214][61453] Fps is (10 sec: 13107.5, 60 sec: 13653.4, 300 sec: 14106.9). Total num frames: 198475776. Throughput: 0: 1782.6, 1: 1776.6. Samples: 49630834. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-17 04:09:27,214][61453] Avg episode reward: [(0, '11.550'), (1, '12.290')] -[2023-10-17 04:09:29,068][62373] Updated weights for policy 0, policy_version 97290 (0.0008) -[2023-10-17 04:09:29,439][62373] Updated weights for policy 0, policy_version 97300 (0.0009) -[2023-10-17 04:09:29,810][62373] Updated weights for policy 0, policy_version 97310 (0.0008) -[2023-10-17 04:09:31,032][62408] Updated weights for policy 1, policy_version 96580 (0.0007) -[2023-10-17 04:09:31,441][62408] Updated weights for policy 1, policy_version 96590 (0.0007) -[2023-10-17 04:09:31,817][62408] Updated weights for policy 1, policy_version 96600 (0.0010) -[2023-10-17 04:09:32,214][61453] Fps is (10 sec: 16384.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 198574080. Throughput: 0: 1785.2, 1: 1751.2. Samples: 49651798. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-17 04:09:32,214][61453] Avg episode reward: [(0, '11.330'), (1, '12.390')] -[2023-10-17 04:09:32,223][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000096608_98926592.pth... -[2023-10-17 04:09:32,223][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000097312_99647488.pth... -[2023-10-17 04:09:32,258][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000095648_97943552.pth -[2023-10-17 04:09:32,259][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000094944_97222656.pth -[2023-10-17 04:09:33,665][62373] Updated weights for policy 0, policy_version 97320 (0.0007) -[2023-10-17 04:09:34,031][62373] Updated weights for policy 0, policy_version 97330 (0.0010) -[2023-10-17 04:09:34,406][62373] Updated weights for policy 0, policy_version 97340 (0.0011) -[2023-10-17 04:09:35,745][62408] Updated weights for policy 1, policy_version 96610 (0.0007) -[2023-10-17 04:09:36,121][62408] Updated weights for policy 1, policy_version 96620 (0.0008) -[2023-10-17 04:09:36,483][62408] Updated weights for policy 1, policy_version 96630 (0.0009) -[2023-10-17 04:09:36,851][62408] Updated weights for policy 1, policy_version 96640 (0.0008) -[2023-10-17 04:09:37,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 198639616. Throughput: 0: 1786.6, 1: 1764.9. Samples: 49662356. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-17 04:09:37,215][61453] Avg episode reward: [(0, '11.300'), (1, '13.150')] -[2023-10-17 04:09:38,166][62373] Updated weights for policy 0, policy_version 97350 (0.0009) -[2023-10-17 04:09:38,525][62373] Updated weights for policy 0, policy_version 97360 (0.0008) -[2023-10-17 04:09:38,898][62373] Updated weights for policy 0, policy_version 97370 (0.0010) -[2023-10-17 04:09:40,684][62408] Updated weights for policy 1, policy_version 96650 (0.0008) -[2023-10-17 04:09:41,057][62408] Updated weights for policy 1, policy_version 96660 (0.0008) -[2023-10-17 04:09:41,417][62408] Updated weights for policy 1, policy_version 96670 (0.0008) -[2023-10-17 04:09:42,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 198705152. Throughput: 0: 1786.0, 1: 1764.3. Samples: 49683970. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-17 04:09:42,215][61453] Avg episode reward: [(0, '10.930'), (1, '12.880')] -[2023-10-17 04:09:42,703][62373] Updated weights for policy 0, policy_version 97380 (0.0011) -[2023-10-17 04:09:43,073][62373] Updated weights for policy 0, policy_version 97390 (0.0010) -[2023-10-17 04:09:43,442][62373] Updated weights for policy 0, policy_version 97400 (0.0009) -[2023-10-17 04:09:45,232][62408] Updated weights for policy 1, policy_version 96680 (0.0008) -[2023-10-17 04:09:45,601][62408] Updated weights for policy 1, policy_version 96690 (0.0009) -[2023-10-17 04:09:45,968][62408] Updated weights for policy 1, policy_version 96700 (0.0009) -[2023-10-17 04:09:47,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 198770688. Throughput: 0: 1793.8, 1: 1747.7. Samples: 49705160. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-17 04:09:47,215][61453] Avg episode reward: [(0, '11.280'), (1, '12.400')] -[2023-10-17 04:09:47,303][62373] Updated weights for policy 0, policy_version 97410 (0.0009) -[2023-10-17 04:09:47,679][62373] Updated weights for policy 0, policy_version 97420 (0.0008) -[2023-10-17 04:09:48,045][62373] Updated weights for policy 0, policy_version 97430 (0.0009) -[2023-10-17 04:09:48,418][62373] Updated weights for policy 0, policy_version 97440 (0.0008) -[2023-10-17 04:09:49,762][62408] Updated weights for policy 1, policy_version 96710 (0.0007) -[2023-10-17 04:09:50,130][62408] Updated weights for policy 1, policy_version 96720 (0.0008) -[2023-10-17 04:09:50,505][62408] Updated weights for policy 1, policy_version 96730 (0.0009) -[2023-10-17 04:09:52,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 198836224. Throughput: 0: 1774.2, 1: 1770.5. Samples: 49715752. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-17 04:09:52,214][61453] Avg episode reward: [(0, '11.400'), (1, '12.950')] -[2023-10-17 04:09:52,458][62373] Updated weights for policy 0, policy_version 97450 (0.0007) -[2023-10-17 04:09:52,824][62373] Updated weights for policy 0, policy_version 97460 (0.0008) -[2023-10-17 04:09:53,197][62373] Updated weights for policy 0, policy_version 97470 (0.0007) -[2023-10-17 04:09:54,451][62408] Updated weights for policy 1, policy_version 96740 (0.0010) -[2023-10-17 04:09:54,820][62408] Updated weights for policy 1, policy_version 96750 (0.0011) -[2023-10-17 04:09:55,194][62408] Updated weights for policy 1, policy_version 96760 (0.0011) -[2023-10-17 04:09:56,901][62373] Updated weights for policy 0, policy_version 97480 (0.0009) -[2023-10-17 04:09:57,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 198901760. Throughput: 0: 1784.7, 1: 1750.3. Samples: 49736734. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-17 04:09:57,215][61453] Avg episode reward: [(0, '12.290'), (1, '12.530')] -[2023-10-17 04:09:57,263][62373] Updated weights for policy 0, policy_version 97490 (0.0007) -[2023-10-17 04:09:57,636][62373] Updated weights for policy 0, policy_version 97500 (0.0008) -[2023-10-17 04:09:59,035][62408] Updated weights for policy 1, policy_version 96770 (0.0010) -[2023-10-17 04:09:59,413][62408] Updated weights for policy 1, policy_version 96780 (0.0009) -[2023-10-17 04:09:59,774][62408] Updated weights for policy 1, policy_version 96790 (0.0007) -[2023-10-17 04:10:00,136][62408] Updated weights for policy 1, policy_version 96800 (0.0008) -[2023-10-17 04:10:01,489][62373] Updated weights for policy 0, policy_version 97510 (0.0009) -[2023-10-17 04:10:01,860][62373] Updated weights for policy 0, policy_version 97520 (0.0008) -[2023-10-17 04:10:02,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 13995.8). Total num frames: 198967296. Throughput: 0: 1789.3, 1: 1755.3. Samples: 49758252. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-17 04:10:02,214][61453] Avg episode reward: [(0, '12.040'), (1, '12.580')] -[2023-10-17 04:10:02,234][62373] Updated weights for policy 0, policy_version 97530 (0.0008) -[2023-10-17 04:10:03,696][62408] Updated weights for policy 1, policy_version 96810 (0.0010) -[2023-10-17 04:10:04,067][62408] Updated weights for policy 1, policy_version 96820 (0.0010) -[2023-10-17 04:10:04,431][62408] Updated weights for policy 1, policy_version 96830 (0.0010) -[2023-10-17 04:10:05,985][62373] Updated weights for policy 0, policy_version 97540 (0.0009) -[2023-10-17 04:10:06,348][62373] Updated weights for policy 0, policy_version 97550 (0.0010) -[2023-10-17 04:10:06,730][62373] Updated weights for policy 0, policy_version 97560 (0.0010) -[2023-10-17 04:10:07,214][61453] Fps is (10 sec: 16384.2, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 199065600. Throughput: 0: 1779.8, 1: 1756.9. Samples: 49768892. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-17 04:10:07,214][61453] Avg episode reward: [(0, '12.650'), (1, '12.060')] -[2023-10-17 04:10:08,378][62408] Updated weights for policy 1, policy_version 96840 (0.0008) -[2023-10-17 04:10:08,746][62408] Updated weights for policy 1, policy_version 96850 (0.0008) -[2023-10-17 04:10:09,113][62408] Updated weights for policy 1, policy_version 96860 (0.0009) -[2023-10-17 04:10:10,427][62373] Updated weights for policy 0, policy_version 97570 (0.0007) -[2023-10-17 04:10:10,789][62373] Updated weights for policy 0, policy_version 97580 (0.0010) -[2023-10-17 04:10:11,156][62373] Updated weights for policy 0, policy_version 97590 (0.0009) -[2023-10-17 04:10:11,529][62373] Updated weights for policy 0, policy_version 97600 (0.0011) -[2023-10-17 04:10:12,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 199131136. Throughput: 0: 1785.9, 1: 1754.8. Samples: 49790168. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-17 04:10:12,215][61453] Avg episode reward: [(0, '12.610'), (1, '11.280')] -[2023-10-17 04:10:12,874][62408] Updated weights for policy 1, policy_version 96870 (0.0008) -[2023-10-17 04:10:13,232][62408] Updated weights for policy 1, policy_version 96880 (0.0008) -[2023-10-17 04:10:13,599][62408] Updated weights for policy 1, policy_version 96890 (0.0010) -[2023-10-17 04:10:15,215][62373] Updated weights for policy 0, policy_version 97610 (0.0007) -[2023-10-17 04:10:15,584][62373] Updated weights for policy 0, policy_version 97620 (0.0009) -[2023-10-17 04:10:15,959][62373] Updated weights for policy 0, policy_version 97630 (0.0009) -[2023-10-17 04:10:17,214][61453] Fps is (10 sec: 13106.9, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 199196672. Throughput: 0: 1766.4, 1: 1788.0. Samples: 49811746. Policy #0 lag: (min: 31.0, avg: 34.1, max: 63.0) -[2023-10-17 04:10:17,215][61453] Avg episode reward: [(0, '12.550'), (1, '11.520')] -[2023-10-17 04:10:17,468][62408] Updated weights for policy 1, policy_version 96900 (0.0008) -[2023-10-17 04:10:17,867][62408] Updated weights for policy 1, policy_version 96910 (0.0008) -[2023-10-17 04:10:18,247][62408] Updated weights for policy 1, policy_version 96920 (0.0007) -[2023-10-17 04:10:19,766][62373] Updated weights for policy 0, policy_version 97640 (0.0008) -[2023-10-17 04:10:20,122][62373] Updated weights for policy 0, policy_version 97650 (0.0010) -[2023-10-17 04:10:20,489][62373] Updated weights for policy 0, policy_version 97660 (0.0010) -[2023-10-17 04:10:22,032][62408] Updated weights for policy 1, policy_version 96930 (0.0008) -[2023-10-17 04:10:22,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 199262208. Throughput: 0: 1789.5, 1: 1761.1. Samples: 49822134. Policy #0 lag: (min: 31.0, avg: 39.5, max: 63.0) -[2023-10-17 04:10:22,215][61453] Avg episode reward: [(0, '13.340'), (1, '11.570')] -[2023-10-17 04:10:22,395][62408] Updated weights for policy 1, policy_version 96940 (0.0010) -[2023-10-17 04:10:22,763][62408] Updated weights for policy 1, policy_version 96950 (0.0008) -[2023-10-17 04:10:23,131][62408] Updated weights for policy 1, policy_version 96960 (0.0008) -[2023-10-17 04:10:24,340][62373] Updated weights for policy 0, policy_version 97670 (0.0008) -[2023-10-17 04:10:24,718][62373] Updated weights for policy 0, policy_version 97680 (0.0009) -[2023-10-17 04:10:25,086][62373] Updated weights for policy 0, policy_version 97690 (0.0008) -[2023-10-17 04:10:27,018][62408] Updated weights for policy 1, policy_version 96970 (0.0011) -[2023-10-17 04:10:27,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 199327744. Throughput: 0: 1770.0, 1: 1775.3. Samples: 49843506. Policy #0 lag: (min: 31.0, avg: 39.5, max: 63.0) -[2023-10-17 04:10:27,215][61453] Avg episode reward: [(0, '12.160'), (1, '11.240')] -[2023-10-17 04:10:27,387][62408] Updated weights for policy 1, policy_version 96980 (0.0008) -[2023-10-17 04:10:27,755][62408] Updated weights for policy 1, policy_version 96990 (0.0007) -[2023-10-17 04:10:28,753][62373] Updated weights for policy 0, policy_version 97700 (0.0009) -[2023-10-17 04:10:29,111][62373] Updated weights for policy 0, policy_version 97710 (0.0008) -[2023-10-17 04:10:29,486][62373] Updated weights for policy 0, policy_version 97720 (0.0009) -[2023-10-17 04:10:31,579][62408] Updated weights for policy 1, policy_version 97000 (0.0008) -[2023-10-17 04:10:31,939][62408] Updated weights for policy 1, policy_version 97010 (0.0007) -[2023-10-17 04:10:32,214][61453] Fps is (10 sec: 13107.1, 60 sec: 13653.3, 300 sec: 14106.9). Total num frames: 199393280. Throughput: 0: 1778.8, 1: 1773.9. Samples: 49865030. Policy #0 lag: (min: 31.0, avg: 39.5, max: 63.0) -[2023-10-17 04:10:32,215][61453] Avg episode reward: [(0, '12.650'), (1, '11.710')] -[2023-10-17 04:10:32,308][62408] Updated weights for policy 1, policy_version 97020 (0.0007) -[2023-10-17 04:10:33,177][62373] Updated weights for policy 0, policy_version 97730 (0.0009) -[2023-10-17 04:10:33,551][62373] Updated weights for policy 0, policy_version 97740 (0.0010) -[2023-10-17 04:10:33,917][62373] Updated weights for policy 0, policy_version 97750 (0.0008) -[2023-10-17 04:10:34,290][62373] Updated weights for policy 0, policy_version 97760 (0.0010) -[2023-10-17 04:10:36,159][62408] Updated weights for policy 1, policy_version 97030 (0.0009) -[2023-10-17 04:10:36,529][62408] Updated weights for policy 1, policy_version 97040 (0.0010) -[2023-10-17 04:10:36,886][62408] Updated weights for policy 1, policy_version 97050 (0.0008) -[2023-10-17 04:10:37,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 199491584. Throughput: 0: 1776.3, 1: 1768.3. Samples: 49875264. Policy #0 lag: (min: 31.0, avg: 39.5, max: 63.0) -[2023-10-17 04:10:37,215][61453] Avg episode reward: [(0, '11.700'), (1, '11.270')] -[2023-10-17 04:10:38,294][62373] Updated weights for policy 0, policy_version 97770 (0.0007) -[2023-10-17 04:10:38,660][62373] Updated weights for policy 0, policy_version 97780 (0.0007) -[2023-10-17 04:10:39,022][62373] Updated weights for policy 0, policy_version 97790 (0.0008) -[2023-10-17 04:10:40,745][62408] Updated weights for policy 1, policy_version 97060 (0.0008) -[2023-10-17 04:10:41,116][62408] Updated weights for policy 1, policy_version 97070 (0.0010) -[2023-10-17 04:10:41,484][62408] Updated weights for policy 1, policy_version 97080 (0.0007) -[2023-10-17 04:10:42,214][61453] Fps is (10 sec: 16384.0, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 199557120. Throughput: 0: 1778.6, 1: 1781.1. Samples: 49896920. Policy #0 lag: (min: 31.0, avg: 39.5, max: 63.0) -[2023-10-17 04:10:42,215][61453] Avg episode reward: [(0, '11.740'), (1, '11.320')] -[2023-10-17 04:10:42,629][62373] Updated weights for policy 0, policy_version 97800 (0.0008) -[2023-10-17 04:10:42,995][62373] Updated weights for policy 0, policy_version 97810 (0.0007) -[2023-10-17 04:10:43,359][62373] Updated weights for policy 0, policy_version 97820 (0.0009) -[2023-10-17 04:10:45,225][62408] Updated weights for policy 1, policy_version 97090 (0.0008) -[2023-10-17 04:10:45,593][62408] Updated weights for policy 1, policy_version 97100 (0.0008) -[2023-10-17 04:10:45,959][62408] Updated weights for policy 1, policy_version 97110 (0.0009) -[2023-10-17 04:10:46,321][62408] Updated weights for policy 1, policy_version 97120 (0.0008) -[2023-10-17 04:10:47,015][62373] Updated weights for policy 0, policy_version 97830 (0.0009) -[2023-10-17 04:10:47,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 199622656. Throughput: 0: 1797.4, 1: 1752.9. Samples: 49918014. Policy #0 lag: (min: 31.0, avg: 39.5, max: 63.0) -[2023-10-17 04:10:47,215][61453] Avg episode reward: [(0, '11.500'), (1, '11.720')] -[2023-10-17 04:10:47,394][62373] Updated weights for policy 0, policy_version 97840 (0.0008) -[2023-10-17 04:10:47,755][62373] Updated weights for policy 0, policy_version 97850 (0.0007) -[2023-10-17 04:10:50,219][62408] Updated weights for policy 1, policy_version 97130 (0.0008) -[2023-10-17 04:10:50,594][62408] Updated weights for policy 1, policy_version 97140 (0.0009) -[2023-10-17 04:10:50,964][62408] Updated weights for policy 1, policy_version 97150 (0.0009) -[2023-10-17 04:10:51,663][62373] Updated weights for policy 0, policy_version 97860 (0.0010) -[2023-10-17 04:10:52,023][62373] Updated weights for policy 0, policy_version 97870 (0.0009) -[2023-10-17 04:10:52,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 199688192. Throughput: 0: 1779.2, 1: 1782.4. Samples: 49929166. Policy #0 lag: (min: 31.0, avg: 39.5, max: 63.0) -[2023-10-17 04:10:52,215][61453] Avg episode reward: [(0, '11.310'), (1, '13.000')] -[2023-10-17 04:10:52,399][62373] Updated weights for policy 0, policy_version 97880 (0.0009) -[2023-10-17 04:10:54,760][62408] Updated weights for policy 1, policy_version 97160 (0.0008) -[2023-10-17 04:10:55,119][62408] Updated weights for policy 1, policy_version 97170 (0.0009) -[2023-10-17 04:10:55,491][62408] Updated weights for policy 1, policy_version 97180 (0.0010) -[2023-10-17 04:10:56,161][62373] Updated weights for policy 0, policy_version 97890 (0.0007) -[2023-10-17 04:10:56,517][62373] Updated weights for policy 0, policy_version 97900 (0.0007) -[2023-10-17 04:10:56,886][62373] Updated weights for policy 0, policy_version 97910 (0.0009) -[2023-10-17 04:10:57,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 199753728. Throughput: 0: 1796.8, 1: 1755.8. Samples: 49950034. Policy #0 lag: (min: 31.0, avg: 39.5, max: 63.0) -[2023-10-17 04:10:57,215][61453] Avg episode reward: [(0, '12.630'), (1, '12.130')] -[2023-10-17 04:10:57,260][62373] Updated weights for policy 0, policy_version 97920 (0.0010) -[2023-10-17 04:10:59,308][62408] Updated weights for policy 1, policy_version 97190 (0.0009) -[2023-10-17 04:10:59,669][62408] Updated weights for policy 1, policy_version 97200 (0.0010) -[2023-10-17 04:11:00,044][62408] Updated weights for policy 1, policy_version 97210 (0.0009) -[2023-10-17 04:11:01,088][62373] Updated weights for policy 0, policy_version 97930 (0.0007) -[2023-10-17 04:11:01,457][62373] Updated weights for policy 0, policy_version 97940 (0.0008) -[2023-10-17 04:11:01,825][62373] Updated weights for policy 0, policy_version 97950 (0.0010) -[2023-10-17 04:11:02,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14745.5, 300 sec: 14218.0). Total num frames: 199852032. Throughput: 0: 1778.5, 1: 1758.0. Samples: 49970886. Policy #0 lag: (min: 31.0, avg: 39.5, max: 63.0) -[2023-10-17 04:11:02,215][61453] Avg episode reward: [(0, '11.740'), (1, '12.280')] -[2023-10-17 04:11:03,835][62408] Updated weights for policy 1, policy_version 97220 (0.0008) -[2023-10-17 04:11:04,231][62408] Updated weights for policy 1, policy_version 97230 (0.0007) -[2023-10-17 04:11:04,592][62408] Updated weights for policy 1, policy_version 97240 (0.0007) -[2023-10-17 04:11:05,598][62373] Updated weights for policy 0, policy_version 97960 (0.0008) -[2023-10-17 04:11:05,965][62373] Updated weights for policy 0, policy_version 97970 (0.0009) -[2023-10-17 04:11:06,335][62373] Updated weights for policy 0, policy_version 97980 (0.0007) -[2023-10-17 04:11:07,214][61453] Fps is (10 sec: 16383.7, 60 sec: 14199.4, 300 sec: 14218.0). Total num frames: 199917568. Throughput: 0: 1790.8, 1: 1761.7. Samples: 49981996. Policy #0 lag: (min: 31.0, avg: 39.5, max: 63.0) -[2023-10-17 04:11:07,215][61453] Avg episode reward: [(0, '11.960'), (1, '11.440')] -[2023-10-17 04:11:08,325][62408] Updated weights for policy 1, policy_version 97250 (0.0008) -[2023-10-17 04:11:08,699][62408] Updated weights for policy 1, policy_version 97260 (0.0011) -[2023-10-17 04:11:09,068][62408] Updated weights for policy 1, policy_version 97270 (0.0009) -[2023-10-17 04:11:09,430][62408] Updated weights for policy 1, policy_version 97280 (0.0007) -[2023-10-17 04:11:10,000][62373] Updated weights for policy 0, policy_version 97990 (0.0009) -[2023-10-17 04:11:10,378][62373] Updated weights for policy 0, policy_version 98000 (0.0011) -[2023-10-17 04:11:10,744][62373] Updated weights for policy 0, policy_version 98010 (0.0010) -[2023-10-17 04:11:12,214][61453] Fps is (10 sec: 13107.5, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 199983104. Throughput: 0: 1781.8, 1: 1760.9. Samples: 50002928. Policy #0 lag: (min: 31.0, avg: 39.5, max: 63.0) -[2023-10-17 04:11:12,215][61453] Avg episode reward: [(0, '11.960'), (1, '11.570')] -[2023-10-17 04:11:13,151][62408] Updated weights for policy 1, policy_version 97290 (0.0008) -[2023-10-17 04:11:13,522][62408] Updated weights for policy 1, policy_version 97300 (0.0011) -[2023-10-17 04:11:13,888][62408] Updated weights for policy 1, policy_version 97310 (0.0010) -[2023-10-17 04:11:14,462][62373] Updated weights for policy 0, policy_version 98020 (0.0009) -[2023-10-17 04:11:14,837][62373] Updated weights for policy 0, policy_version 98030 (0.0009) -[2023-10-17 04:11:15,205][62373] Updated weights for policy 0, policy_version 98040 (0.0007) -[2023-10-17 04:11:17,214][61453] Fps is (10 sec: 13107.4, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 200048640. Throughput: 0: 1776.2, 1: 1783.2. Samples: 50025202. Policy #0 lag: (min: 31.0, avg: 39.5, max: 63.0) -[2023-10-17 04:11:17,215][61453] Avg episode reward: [(0, '12.320'), (1, '11.470')] -[2023-10-17 04:11:17,700][62408] Updated weights for policy 1, policy_version 97320 (0.0008) -[2023-10-17 04:11:18,067][62408] Updated weights for policy 1, policy_version 97330 (0.0010) -[2023-10-17 04:11:18,441][62408] Updated weights for policy 1, policy_version 97340 (0.0008) -[2023-10-17 04:11:18,836][62373] Updated weights for policy 0, policy_version 98050 (0.0008) -[2023-10-17 04:11:19,207][62373] Updated weights for policy 0, policy_version 98060 (0.0008) -[2023-10-17 04:11:19,577][62373] Updated weights for policy 0, policy_version 98070 (0.0009) -[2023-10-17 04:11:19,952][62373] Updated weights for policy 0, policy_version 98080 (0.0009) -[2023-10-17 04:11:22,120][62408] Updated weights for policy 1, policy_version 97350 (0.0009) -[2023-10-17 04:11:22,214][61453] Fps is (10 sec: 13107.0, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 200114176. Throughput: 0: 1785.3, 1: 1766.0. Samples: 50035074. Policy #0 lag: (min: 31.0, avg: 39.5, max: 63.0) -[2023-10-17 04:11:22,215][61453] Avg episode reward: [(0, '12.460'), (1, '11.810')] -[2023-10-17 04:11:22,487][62408] Updated weights for policy 1, policy_version 97360 (0.0008) -[2023-10-17 04:11:22,856][62408] Updated weights for policy 1, policy_version 97370 (0.0007) -[2023-10-17 04:11:23,784][62373] Updated weights for policy 0, policy_version 98090 (0.0009) -[2023-10-17 04:11:24,147][62373] Updated weights for policy 0, policy_version 98100 (0.0009) -[2023-10-17 04:11:24,520][62373] Updated weights for policy 0, policy_version 98110 (0.0008) -[2023-10-17 04:11:26,558][62408] Updated weights for policy 1, policy_version 97380 (0.0007) -[2023-10-17 04:11:26,929][62408] Updated weights for policy 1, policy_version 97390 (0.0009) -[2023-10-17 04:11:27,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14106.9). Total num frames: 200179712. Throughput: 0: 1782.1, 1: 1789.3. Samples: 50057630. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 04:11:27,215][61453] Avg episode reward: [(0, '13.040'), (1, '11.290')] -[2023-10-17 04:11:27,296][62408] Updated weights for policy 1, policy_version 97400 (0.0007) -[2023-10-17 04:11:28,365][62373] Updated weights for policy 0, policy_version 98120 (0.0008) -[2023-10-17 04:11:28,737][62373] Updated weights for policy 0, policy_version 98130 (0.0010) -[2023-10-17 04:11:29,100][62373] Updated weights for policy 0, policy_version 98140 (0.0011) -[2023-10-17 04:11:31,041][62408] Updated weights for policy 1, policy_version 97410 (0.0007) -[2023-10-17 04:11:31,406][62408] Updated weights for policy 1, policy_version 97420 (0.0007) -[2023-10-17 04:11:31,773][62408] Updated weights for policy 1, policy_version 97430 (0.0007) -[2023-10-17 04:11:32,133][62408] Updated weights for policy 1, policy_version 97440 (0.0009) -[2023-10-17 04:11:32,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14745.6, 300 sec: 14218.0). Total num frames: 200278016. Throughput: 0: 1781.4, 1: 1792.9. Samples: 50078858. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 04:11:32,215][61453] Avg episode reward: [(0, '12.680'), (1, '12.310')] -[2023-10-17 04:11:32,223][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000098144_100499456.pth... -[2023-10-17 04:11:32,223][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000097440_99778560.pth... -[2023-10-17 04:11:32,264][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000096480_98795520.pth -[2023-10-17 04:11:32,264][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000095776_98074624.pth -[2023-10-17 04:11:32,894][62373] Updated weights for policy 0, policy_version 98150 (0.0010) -[2023-10-17 04:11:33,262][62373] Updated weights for policy 0, policy_version 98160 (0.0009) -[2023-10-17 04:11:33,635][62373] Updated weights for policy 0, policy_version 98170 (0.0011) -[2023-10-17 04:11:35,942][62408] Updated weights for policy 1, policy_version 97450 (0.0007) -[2023-10-17 04:11:36,311][62408] Updated weights for policy 1, policy_version 97460 (0.0007) -[2023-10-17 04:11:36,674][62408] Updated weights for policy 1, policy_version 97470 (0.0007) -[2023-10-17 04:11:37,214][61453] Fps is (10 sec: 16384.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 200343552. Throughput: 0: 1778.5, 1: 1784.0. Samples: 50089478. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 04:11:37,214][61453] Avg episode reward: [(0, '12.440'), (1, '12.440')] -[2023-10-17 04:11:37,433][62373] Updated weights for policy 0, policy_version 98180 (0.0009) -[2023-10-17 04:11:37,799][62373] Updated weights for policy 0, policy_version 98190 (0.0008) -[2023-10-17 04:11:38,172][62373] Updated weights for policy 0, policy_version 98200 (0.0007) -[2023-10-17 04:11:40,624][62408] Updated weights for policy 1, policy_version 97480 (0.0007) -[2023-10-17 04:11:40,976][62408] Updated weights for policy 1, policy_version 97490 (0.0008) -[2023-10-17 04:11:41,341][62408] Updated weights for policy 1, policy_version 97500 (0.0007) -[2023-10-17 04:11:41,813][62373] Updated weights for policy 0, policy_version 98210 (0.0008) -[2023-10-17 04:11:42,195][62373] Updated weights for policy 0, policy_version 98220 (0.0009) -[2023-10-17 04:11:42,214][61453] Fps is (10 sec: 13107.3, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 200409088. Throughput: 0: 1785.6, 1: 1794.3. Samples: 50111130. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 04:11:42,215][61453] Avg episode reward: [(0, '12.650'), (1, '12.030')] -[2023-10-17 04:11:42,560][62373] Updated weights for policy 0, policy_version 98230 (0.0011) -[2023-10-17 04:11:42,926][62373] Updated weights for policy 0, policy_version 98240 (0.0008) -[2023-10-17 04:11:45,059][62408] Updated weights for policy 1, policy_version 97510 (0.0009) -[2023-10-17 04:11:45,420][62408] Updated weights for policy 1, policy_version 97520 (0.0010) -[2023-10-17 04:11:45,793][62408] Updated weights for policy 1, policy_version 97530 (0.0011) -[2023-10-17 04:11:46,760][62373] Updated weights for policy 0, policy_version 98250 (0.0009) -[2023-10-17 04:11:47,126][62373] Updated weights for policy 0, policy_version 98260 (0.0011) -[2023-10-17 04:11:47,214][61453] Fps is (10 sec: 13107.2, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 200474624. Throughput: 0: 1805.3, 1: 1773.7. Samples: 50131942. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 04:11:47,214][61453] Avg episode reward: [(0, '13.400'), (1, '12.080')] -[2023-10-17 04:11:47,496][62373] Updated weights for policy 0, policy_version 98270 (0.0009) -[2023-10-17 04:11:49,545][62408] Updated weights for policy 1, policy_version 97540 (0.0009) -[2023-10-17 04:11:49,944][62408] Updated weights for policy 1, policy_version 97550 (0.0007) -[2023-10-17 04:11:50,313][62408] Updated weights for policy 1, policy_version 97560 (0.0007) -[2023-10-17 04:11:51,311][62373] Updated weights for policy 0, policy_version 98280 (0.0010) -[2023-10-17 04:11:51,691][62373] Updated weights for policy 0, policy_version 98290 (0.0008) -[2023-10-17 04:11:52,065][62373] Updated weights for policy 0, policy_version 98300 (0.0008) -[2023-10-17 04:11:52,214][61453] Fps is (10 sec: 13107.1, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 200540160. Throughput: 0: 1783.0, 1: 1795.4. Samples: 50143024. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 04:11:52,214][61453] Avg episode reward: [(0, '13.780'), (1, '12.960')] -[2023-10-17 04:11:52,215][62094] Saving new best policy, reward=13.780! -[2023-10-17 04:11:54,348][62408] Updated weights for policy 1, policy_version 97570 (0.0009) -[2023-10-17 04:11:54,707][62408] Updated weights for policy 1, policy_version 97580 (0.0010) -[2023-10-17 04:11:55,068][62408] Updated weights for policy 1, policy_version 97590 (0.0010) -[2023-10-17 04:11:55,441][62408] Updated weights for policy 1, policy_version 97600 (0.0010) -[2023-10-17 04:11:55,686][62373] Updated weights for policy 0, policy_version 98310 (0.0008) -[2023-10-17 04:11:56,050][62373] Updated weights for policy 0, policy_version 98320 (0.0010) -[2023-10-17 04:11:56,424][62373] Updated weights for policy 0, policy_version 98330 (0.0009) -[2023-10-17 04:11:57,214][61453] Fps is (10 sec: 16383.6, 60 sec: 14745.6, 300 sec: 14329.1). Total num frames: 200638464. Throughput: 0: 1803.8, 1: 1770.1. Samples: 50163754. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 04:11:57,215][61453] Avg episode reward: [(0, '13.370'), (1, '12.880')] -[2023-10-17 04:11:59,420][62408] Updated weights for policy 1, policy_version 97610 (0.0009) -[2023-10-17 04:11:59,788][62408] Updated weights for policy 1, policy_version 97620 (0.0007) -[2023-10-17 04:12:00,155][62408] Updated weights for policy 1, policy_version 97630 (0.0007) -[2023-10-17 04:12:00,274][62373] Updated weights for policy 0, policy_version 98340 (0.0007) -[2023-10-17 04:12:00,643][62373] Updated weights for policy 0, policy_version 98350 (0.0008) -[2023-10-17 04:12:01,015][62373] Updated weights for policy 0, policy_version 98360 (0.0009) -[2023-10-17 04:12:02,214][61453] Fps is (10 sec: 16383.8, 60 sec: 14199.5, 300 sec: 14218.0). Total num frames: 200704000. Throughput: 0: 1785.1, 1: 1767.7. Samples: 50185076. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-10-17 04:12:02,215][61453] Avg episode reward: [(0, '13.250'), (1, '12.160')] -[2023-10-17 04:12:04,015][62408] Updated weights for policy 1, policy_version 97640 (0.0008) -[2023-10-17 04:12:04,382][62408] Updated weights for policy 1, policy_version 97650 (0.0008) -[2023-10-17 04:12:04,759][62408] Updated weights for policy 1, policy_version 97660 (0.0008) -[2023-10-17 04:12:04,853][62373] Updated weights for policy 0, policy_version 98370 (0.0010) -[2023-10-17 04:12:05,216][62373] Updated weights for policy 0, policy_version 98380 (0.0009) -[2023-10-17 04:12:05,595][62373] Updated weights for policy 0, policy_version 98390 (0.0010) -[2023-10-17 04:12:05,955][62432] Stopping RolloutWorker_w11... -[2023-10-17 04:12:05,955][62417] Stopping RolloutWorker_w5... -[2023-10-17 04:12:05,955][62416] Stopping RolloutWorker_w4... -[2023-10-17 04:12:05,955][62433] Stopping RolloutWorker_w12... -[2023-10-17 04:12:05,955][62421] Stopping RolloutWorker_w7... -[2023-10-17 04:12:05,955][62434] Stopping RolloutWorker_w13... -[2023-10-17 04:12:05,955][62432] Loop rollout_proc11_evt_loop terminating... -[2023-10-17 04:12:05,955][62094] Stopping Batcher_0... -[2023-10-17 04:12:05,955][62406] Stopping RolloutWorker_w1... -[2023-10-17 04:12:05,955][62373] Updated weights for policy 0, policy_version 98400 (0.0011) -[2023-10-17 04:12:05,955][62429] Stopping RolloutWorker_w8... -[2023-10-17 04:12:05,955][62418] Stopping RolloutWorker_w6... -[2023-10-17 04:12:05,956][62417] Loop rollout_proc5_evt_loop terminating... -[2023-10-17 04:12:05,956][62434] Loop rollout_proc13_evt_loop terminating... -[2023-10-17 04:12:05,956][62416] Loop rollout_proc4_evt_loop terminating... -[2023-10-17 04:12:05,956][62421] Loop rollout_proc7_evt_loop terminating... -[2023-10-17 04:12:05,956][61453] Component RolloutWorker_w5 stopped! -[2023-10-17 04:12:05,956][63019] Stopping RolloutWorker_w14... -[2023-10-17 04:12:05,956][62418] Loop rollout_proc6_evt_loop terminating... -[2023-10-17 04:12:05,956][62433] Loop rollout_proc12_evt_loop terminating... -[2023-10-17 04:12:05,956][62429] Loop rollout_proc8_evt_loop terminating... -[2023-10-17 04:12:05,956][62252] Stopping Batcher_1... -[2023-10-17 04:12:05,956][62406] Loop rollout_proc1_evt_loop terminating... -[2023-10-17 04:12:05,956][62094] Loop batcher_evt_loop terminating... -[2023-10-17 04:12:05,956][62372] Stopping RolloutWorker_w2... -[2023-10-17 04:12:05,956][63019] Loop rollout_proc14_evt_loop terminating... -[2023-10-17 04:12:05,956][61453] Component RolloutWorker_w11 stopped! -[2023-10-17 04:12:05,956][62252] Loop batcher_evt_loop terminating... -[2023-10-17 04:12:05,956][62372] Loop rollout_proc2_evt_loop terminating... -[2023-10-17 04:12:05,956][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000098400_100761600.pth... -[2023-10-17 04:12:05,957][63085] Stopping RolloutWorker_w15... -[2023-10-17 04:12:05,957][61453] Component RolloutWorker_w4 stopped! -[2023-10-17 04:12:05,957][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000097664_100007936.pth... -[2023-10-17 04:12:05,957][63085] Loop rollout_proc15_evt_loop terminating... -[2023-10-17 04:12:05,957][61453] Component RolloutWorker_w12 stopped! -[2023-10-17 04:12:05,957][62430] Stopping RolloutWorker_w9... -[2023-10-17 04:12:05,957][61453] Component Batcher_0 stopped! -[2023-10-17 04:12:05,958][62430] Loop rollout_proc9_evt_loop terminating... -[2023-10-17 04:12:05,958][61453] Component RolloutWorker_w1 stopped! -[2023-10-17 04:12:05,958][61453] Component RolloutWorker_w7 stopped! -[2023-10-17 04:12:05,959][61453] Component RolloutWorker_w13 stopped! -[2023-10-17 04:12:05,959][61453] Component RolloutWorker_w8 stopped! -[2023-10-17 04:12:05,959][61453] Component RolloutWorker_w6 stopped! -[2023-10-17 04:12:05,960][61453] Component RolloutWorker_w2 stopped! -[2023-10-17 04:12:05,960][61453] Component Batcher_1 stopped! -[2023-10-17 04:12:05,960][61453] Component RolloutWorker_w14 stopped! -[2023-10-17 04:12:05,960][62409] Stopping RolloutWorker_w3... -[2023-10-17 04:12:05,960][61453] Component RolloutWorker_w15 stopped! -[2023-10-17 04:12:05,961][61453] Component RolloutWorker_w9 stopped! -[2023-10-17 04:12:05,961][62409] Loop rollout_proc3_evt_loop terminating... -[2023-10-17 04:12:05,961][62405] Stopping RolloutWorker_w0... -[2023-10-17 04:12:05,961][61453] Component RolloutWorker_w3 stopped! -[2023-10-17 04:12:05,961][62431] Stopping RolloutWorker_w10... -[2023-10-17 04:12:05,961][62405] Loop rollout_proc0_evt_loop terminating... -[2023-10-17 04:12:05,961][61453] Component RolloutWorker_w0 stopped! -[2023-10-17 04:12:05,962][62431] Loop rollout_proc10_evt_loop terminating... -[2023-10-17 04:12:05,962][61453] Component RolloutWorker_w10 stopped! -[2023-10-17 04:12:05,984][62408] Weights refcount: 2 0 -[2023-10-17 04:12:05,986][62373] Weights refcount: 2 0 -[2023-10-17 04:12:05,987][62408] Stopping InferenceWorker_p1-w0... -[2023-10-17 04:12:05,988][61453] Component InferenceWorker_p1-w0 stopped! -[2023-10-17 04:12:05,988][62408] Loop inference_proc1-0_evt_loop terminating... -[2023-10-17 04:12:05,988][62373] Stopping InferenceWorker_p0-w0... -[2023-10-17 04:12:05,988][61453] Component InferenceWorker_p0-w0 stopped! -[2023-10-17 04:12:05,989][62373] Loop inference_proc0-0_evt_loop terminating... -[2023-10-17 04:12:05,994][62094] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000097312_99647488.pth -[2023-10-17 04:12:05,999][62094] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p0/checkpoint_000098400_100761600.pth... -[2023-10-17 04:12:06,003][62252] Removing ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000096608_98926592.pth -[2023-10-17 04:12:06,010][62252] Saving ./train_atari/atari_wizardofwor_APPO/checkpoint_p1/checkpoint_000097664_100007936.pth... -[2023-10-17 04:12:06,039][62094] Stopping LearnerWorker_p0... -[2023-10-17 04:12:06,040][62094] Loop learner_proc0_evt_loop terminating... -[2023-10-17 04:12:06,040][61453] Component LearnerWorker_p0 stopped! -[2023-10-17 04:12:06,069][62252] Stopping LearnerWorker_p1... -[2023-10-17 04:12:06,070][62252] Loop learner_proc1_evt_loop terminating... -[2023-10-17 04:12:06,070][61453] Component LearnerWorker_p1 stopped! -[2023-10-17 04:12:06,071][61453] Waiting for process learner_proc0 to stop... -[2023-10-17 04:12:06,916][61453] Waiting for process learner_proc1 to stop... -[2023-10-17 04:12:06,992][61453] Waiting for process inference_proc0-0 to join... -[2023-10-17 04:12:07,025][61453] Waiting for process inference_proc1-0 to join... -[2023-10-17 04:12:07,025][61453] Waiting for process rollout_proc0 to join... -[2023-10-17 04:12:07,026][61453] Waiting for process rollout_proc1 to join... -[2023-10-17 04:12:07,026][61453] Waiting for process rollout_proc2 to join... -[2023-10-17 04:12:07,026][61453] Waiting for process rollout_proc3 to join... -[2023-10-17 04:12:07,027][61453] Waiting for process rollout_proc4 to join... -[2023-10-17 04:12:07,027][61453] Waiting for process rollout_proc5 to join... -[2023-10-17 04:12:07,027][61453] Waiting for process rollout_proc6 to join... -[2023-10-17 04:12:07,027][61453] Waiting for process rollout_proc7 to join... -[2023-10-17 04:12:07,028][61453] Waiting for process rollout_proc8 to join... -[2023-10-17 04:12:07,028][61453] Waiting for process rollout_proc9 to join... -[2023-10-17 04:12:07,028][61453] Waiting for process rollout_proc10 to join... -[2023-10-17 04:12:07,028][61453] Waiting for process rollout_proc11 to join... -[2023-10-17 04:12:07,029][61453] Waiting for process rollout_proc12 to join... -[2023-10-17 04:12:07,029][61453] Waiting for process rollout_proc13 to join... -[2023-10-17 04:12:07,029][61453] Waiting for process rollout_proc14 to join... -[2023-10-17 04:12:07,029][61453] Waiting for process rollout_proc15 to join... -[2023-10-17 04:12:07,030][61453] Batcher 0 profile tree view: -batching: 172.9632, releasing_batches: 0.0922 -[2023-10-17 04:12:07,030][61453] Batcher 1 profile tree view: -batching: 171.5055, releasing_batches: 0.0888 -[2023-10-17 04:12:07,030][61453] InferenceWorker_p0-w0 profile tree view: -wait_policy: 0.0001 - wait_policy_total: 2027.2607 -update_model: 204.4638 - weight_update: 0.0011 -one_step: 0.0028 - handle_policy_step: 11267.0496 - deserialize: 65.0348, stack: 195.5769, obs_to_device_normalize: 2501.7893, forward: 5086.3676, prepare_outputs: 2462.0215, send_messages: 468.6391 -[2023-10-17 04:12:07,030][61453] InferenceWorker_p1-w0 profile tree view: -wait_policy: 0.0001 - wait_policy_total: 2087.5460 -update_model: 202.6519 - weight_update: 0.0008 -one_step: 0.0028 - handle_policy_step: 11213.9652 - deserialize: 63.1497, stack: 195.0261, obs_to_device_normalize: 2507.5676, forward: 5069.0652, prepare_outputs: 2419.8652, send_messages: 469.0143 -[2023-10-17 04:12:07,031][61453] Learner 0 profile tree view: -misc: 0.0187, prepare_batch: 266.4063 -train: 3653.7424 - epoch_init: 0.1881, minibatch_init: 13.0744, losses_postprocess: 896.6461, kl_divergence: 32.0988, update: 393.1972, after_optimizer: 2133.8054 - calculate_losses: 168.1104 - losses_init: 0.3992, forward_head: 56.3241, bptt_initial: 1.4547, bptt: 1.8293, tail: 38.7264, advantages_returns: 11.2699, losses: 44.4588 -[2023-10-17 04:12:07,031][61453] Learner 1 profile tree view: -misc: 0.0183, prepare_batch: 264.4352 -train: 3611.2997 - epoch_init: 0.1903, minibatch_init: 13.1462, losses_postprocess: 892.7990, kl_divergence: 31.2285, update: 385.7980, after_optimizer: 2101.2914 - calculate_losses: 169.9553 - losses_init: 0.3927, forward_head: 59.5625, bptt_initial: 1.4191, bptt: 2.0165, tail: 38.0781, advantages_returns: 11.1537, losses: 43.5829 -[2023-10-17 04:12:07,031][61453] RolloutWorker_w0 profile tree view: -wait_for_trajectories: 1.2241, enqueue_policy_requests: 409.1964, process_policy_outputs: 192.8043, env_step: 6855.6712, finalize_trajectories: 3.4707, complete_rollouts: 2.9058 -post_env_step: 374.0828 - process_env_step: 84.5801 -[2023-10-17 04:12:07,031][61453] RolloutWorker_w15 profile tree view: -wait_for_trajectories: 1.2223, enqueue_policy_requests: 402.9210, process_policy_outputs: 190.7445, env_step: 6802.4917, finalize_trajectories: 3.4937, complete_rollouts: 2.9273 -post_env_step: 378.9348 - process_env_step: 83.9919 -[2023-10-17 04:12:07,032][61453] Loop Runner_EvtLoop terminating... -[2023-10-17 04:12:07,032][61453] Runner profile tree view: -main_loop: 14190.1754 -[2023-10-17 04:12:07,032][61453] Collected {0: 100761600, 1: 100007936}, FPS: 14148.5 +version https://git-lfs.github.com/spec/v1 +oid sha256:40d2720e7d9a54c528a732876fa71c8f69bf16024c64be87dc5d85013674fc03 +size 48494077